Lab 01 Datascience

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Project 2: Inference and Capital Punishment\n",
"\n",
"Welcome to Project 2! You will investigate the relationship between murder
and capital punishment (the death penalty) in the United States. By the end of the
project, you should know how to:\n",
"\n",
"1. Test whether observed data appears to be a random sample from a
distribution\n",
"2. Analyze a natural experiment\n",
"3. Implement and interpret a sign test\n",
"4. Create a function to run a general hypothesis test\n",
"5. Analyze visualizations and draw conclusions from them\n",
"\n",
"### Logistics\n",
"\n",
"\n",
"**Deadline.** This project is due at 11:59pm on Thursday 10/26. You can earn
an early submission bonus point by submitting your completed project by Wednesday
10/25. It's **much** better to be early than late, so start working now.\n",
"\n",
"**Checkpoint.** For full credit, you must also **complete Parts 1 and 2 of the
project (out of 5) and submit them by 11:59pm on Friday 10/20**. You will have some
lab time to work on these questions, but we recommend that you start the project
before lab and leave time to finish the checkpoint afterward.\n",
"\n",
"**Partners.** You may work with one other partner. It's best to work with
someone in your lab. Only one of you is required to submit the project. On
[okpy.org](http://okpy.org), the person who submits should also designate their
partner so that both of you receive credit.\n",
"\n",
"**Rules.** Don't share your code with anybody but your partner. You are
welcome to discuss questions with other students, but don't share the answers. The
experience of solving the problems in this project will prepare you for exams (and
life). If someone asks you for the answer, resist! Instead, you can demonstrate how
you would solve a similar problem.\n",
"\n",
"**Support.** You are not alone! Come to office hours, post on Piazza, and talk
to your classmates. If you want to ask about the details of your solution to a
problem, make a private Piazza post and the staff will respond. If you're ever
feeling overwhelmed or don't know how to make progress, email your TA or tutor for
help. You can find contact information for the staff on the [course website]
(http://data8.org/sp17/staff.html).\n",
"\n",
"**Tests.** Passing the tests for a question **does not** mean that you
answered the question correctly. Tests usually only check that your table has the
correct column labels. However, more tests will be applied to verify the
correctness of your submission in order to assign your final score, so be careful
and check your work!\n",
"\n",
"**Advice.** Develop your answers incrementally. To perform a complicated table
manipulation, break it up into steps, perform each step on a different line, give a
new name to each result, and check that each intermediate result is what you
expect. You can add any additional names or functions you want to the provided
cells. \n",
"\n",
"All of the concepts necessary for this project are found in the textbook. If
you are stuck on a particular problem, reading through the relevant textbook
section often will help clarify the concept.\n",
"\n",
"To get started, load `datascience`, `numpy`, `plots`, and òk`."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"=====================================================================\n",
"Assignment: Project 2: Inference and Capital Punishment\n",
"OK, version v1.12.5\n",
"=====================================================================\n",
"\n",
"\n",
"Open the following URL:\n",
"\n",
"https://okpy.org/client/login/\n",
"\n",
"After logging in, copy the code from the web page and paste it into the
box.\n",
"Then press the \"Enter\" key on your keyboard.\n",
"\n",
"Paste your code here: KgfMp2xSr5Zt8HWRIYK6UTOtl7a8Ow\n",
"Successfully logged in as isabellin105@berkeley.edu\n"
]
}
],
"source": [
"from datascience import *\n",
"import numpy as np\n",
"\n",
"%matplotlib inline\n",
"import matplotlib.pyplot as plots\n",
"plots.style.use('fivethirtyeight')\n",
"\n",
"from client.api.notebook import Notebook\n",
"ok = Notebook('project2.ok')\n",
"_ = ok.auth(inline=True)"
]
},
{
"metadata": {},
"source": [
"## Overview\n",
"\n",
"Punishment for crime has many [philosophical justifications]
(http://plato.stanford.edu/entries/punishment/#ThePun). An important one is that
fear of punishment may *deter* people from committing crimes.\n",
"\n",
"In the United States, some jurisdictions execute some people who are convicted
of particularly serious crimes, such as murder. This punishment is called the
*death penalty* or *capital punishment*. The death penalty is controversial, and
deterrence has been one focal point of the debate. There are other reasons to
support or oppose the death penalty, but in this project we'll focus on
deterrence.\n",
"\n",
"The key question about deterrence is:\n",
"\n",
"> Through our exploration, does instituting a death penalty for murder
actually reduce the number of murders?\n",
"\n",
"You might have a strong intuition in one direction, but the evidence turns out
to be surprisingly complex. Different sides have variously argued that the death
penalty has no deterrent effect and that each execution prevents 8 murders, all
using statistical arguments! We'll try to come to our own conclusion.\n",
"\n",
"Here is a road map for this project:\n",
"\n",
"1. In section 1, we'll investigate the main dataset we'll be using.\n",
"2. In section 2, we'll see how to test null hypotheses such as this: \"For
this set of U.S. states, the murder rate was equally likely to go up or down each
year.\"\n",
"3. In section 3, we'll apply a similar test to see whether U.S. states that
suddenly ended or reinstituted the death penalty were more likely to see murder
rates increase than decrease.\n",
"4. In section 4, we'll run some more tests to further claims we had been
developing in previous sections. \n",
"5. In section 5, we'll try to answer our question about deterrence using a
visualization rather than a formal hypothesis test.\n",
"\n",
"#### The data\n",
"\n",
"The main data source for this project comes from a [paper]
(http://cjlf.org/deathpenalty/DezRubShepDeterFinal.pdf) by three researchers,
Dezhbakhsh, Rubin, and Shepherd. The dataset contains rates of various violent
crimes for every year 1960-2003 (44 years) in every US state. The researchers
compiled the data from the FBI's Uniform Crime Reports.\n",
"\n",
"Since crimes are committed by people, not states, we need to account for the
number of people in each state when we're looking at state-level data. Murder
rates are calculated as follows:\n",
"\n",
"$$\\text{murder rate for state X in year Y} = \\frac{\\text{number of murders
in state X in year Y}}{\\text{population in state X in year Y}}*100000$$\n",
"\n",
"(Murder is rare, so we multiply by 100,000 just to avoid dealing with tiny
numbers.)"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>State</th> <th>Year</th> <th>Population</th> <th>Murder
Rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>Alaska</td> <td>1960</td> <td>226,167 </td> <td>10.2
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>... (2190 rows omitted)</p"
],
"text/plain": [
"State | Year | Population | Murder Rate\n",
"Alaska | 1960 | 226,167 | 10.2\n",
"Alaska | 1961 | 234,000 | 11.5\n",
"Alaska | 1962 | 246,000 | 4.5\n",
"Alaska | 1963 | 248,000 | 6.5\n",
"Alaska | 1964 | 250,000 | 10.4\n",
"Alaska | 1965 | 253,000 | 6.3\n",
"Alaska | 1966 | 272,000 | 12.9\n",
"Alaska | 1967 | 272,000 | 9.6\n",
"Alaska | 1968 | 277,000 | 10.5\n",
"Alaska | 1969 | 282,000 | 10.6\n",
"... (2190 rows omitted)"
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"murder_rates = Table.read_table('crime_rates.csv').select('State', 'Year',
'Population', 'Murder Rate')\n",
"murder_rates.set_format(\"Population\", NumberFormatter)"
]
},
{
"metadata": {},
"source": [
"## 1. Murder rates"
]
},
{
"metadata": {},
"source": [
"So far, this looks like a dataset that lends itself to an observational study.
In fact, the murder rates dataset isn't even enough to demonstrate an *association*
between the existence of the death penalty in a state in a year and the murder rate
in that state and year!\n",
"\n",
"**Question 1.1.** What additional information will we need before we can check
for that association? Assign èxtra_info` to a Python list (i.e. [#] or [#,
#, ...]) containing the number(s) for all of the additional facts below that we
*require* in order to check for association.\n",
"\n",
"1) What year(s) the death penalty was introduced in each state (if any).\n",
"\n",
"2) Day to day data about when murders occurred.\n",
"\n",
"3) What year(s) the death penalty was abolished in each state (if any).\n",
"\n",
"4) Rates of other crimes in each state."
]
},
{
"metadata": {},
"outputs": [],
"source": [
"extra_info = [1,3]"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"[ooooooooook] 100.0% passed\n",
"\n"
]
},
{
"data": {
"application/javascript": [
"IPython.notebook.save_checkpoint();"
],
"text/plain": [
"<IPython.core.display.Javascript object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"IPython.notebook.save_notebook();"
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"Saving notebook... Saved 'project2.ipynb'.\n",
"Backup... 100% complete\n",
"Backup successful for user: isabellin105@berkeley.edu\n",
"URL: https://okpy.org/cal/data8/fa17/project2/backups/J6031P\n",
"NOTE: this is only a backup. To submit your assignment, use:\n",
"\tpython3 ok --submit\n",
"\n"
]
}
],
"source": [
"_ = ok.grade(\"q1_1\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"Murder rates vary over time, and different states exhibit different trends.
The rates in some states change dramatically from year to year, while others are
quite stable. Let's plot a couple, just to see the variety.\n",
"\n",
"**Question 1.2.** Draw a line plot with years on the horizontal axis and
murder rates on the \n",
"vertical axis. Include two lines: one for Alaska murder rates and one for
Minnesota murder rates. Create this plot using a single call,
àk_mn.plot('Year')`.\n",
"\n",
"*Hint*: To create two lines, you will need create the table àk_mn` with two
columns of murder rates, in addition to a column of years. This table will have the
following structure:\n",
"\n",
"| Year | Murder rate in Alaska | Murder rate in Minnesota |\n",
"|------|-----------------------|--------------------------|\n",
"| 1960 | 10.2 | 1.2 |\n",
"| 1961 | 11.5 | 1 |\n",
"| 1962 | 4.5 | 0.9 |\n",
"\n",
"<center>... (41 rows omitted)</center>"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAAqYAAAEfCAYAAACTVgS/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAL
EgAACxIB0t1+/AAAIABJREFUeJzs3XlYU3f2P/B32HfCGnZQQJRF3MEN1zIuVey07rV1+9bq\ntHVsXVp/j
o7VUTtOq7a2ttNtrEvrUpe22qqtKBa1KCLghiCL7GDYwxZIfn/QhNx7kxBIIEHO63l8\nHu/NvTc3F8TD5/
M55/AqKiqkIIQQQgghRM+M9H0DhBBCCCGEABSYEkIIIYQQA0GBKSGEEEIIMQgU\nmBJCCCGEEINAgSkhhBB
CCDEIFJgSQgghhBCDQIEpIYQQQggxCBSYEkIIIYQQg9CjAtP09HR930K3\nRc9OO/T8Oo6enXbo+RFCupMe
FZgSQgghhBDDRYEpIYQQQggxCBSYEkIIIYQQg0CBKSGEEEIIMQgm\n+r4BQgghpKuIRCI0NTXp+zYI6bFMT
ExgbW2t+vUuvBdCSDtJJBKkpmXD3tYKfl5u+r4dQrq1hoYG\nAIC9vb2e74SQnkskEqGhoQHm5uZKX6fAlB
ADtvO/x3HrTgYAYNm8KRg/YoCe74iQ7qu+vh52dnb6\nvg1CejQrKytUVVWpDExpjSkhBqqgWCgPSgHgbGy
CHu+GkKcDj8fT9y0Q0qO19W+QAlNCDFROfglj\nu7C0DBKJRE93QwghhHQ+CkwJMVC5hczAtKlJAmF5lZ7u
hhBCCOl8FJgSYqDyCp9w9hWWluvhTggh\nPdXw4cOxfft2fd9Gp+Hz+Th9+nS3e6+cnBzw+XwkJSXp5HqGh
AJTQgxUbmEpZ18xBaaE9CjLly8H\nn8/Ha6+9xnlt06ZN4PP5mD17th7uTH+mTp2KNWvW6ORaaWlpmDRpkk
6udfv2bTg6OuIvf/mLTq7X\nU1FgSogBahSLUaQkCC16QoEpIT2Nl5cXTp06BZFIJN/X1NSE7777Dl5eXlp
fv7GxUetrqCKRSNDc\n3KzRsWKxuNPuQxWBQKAyO7y9Dhw4gCVLluD+/ftIS0vTyTV7IgpMCTFABcVlkEik
nP1FpWV6uBtC\niD6FhISgd+/eOHnypHzfuXPnYG5ujlGjRjGOXb58OWcEdfv27Rg+fDjnmN27dyM4OBjBw
cEAgNLS\nUsydOxdubm4IDQ3FgQMHOPdSWVmJlStXIiAgAF5eXpgyZQpjOvnQoUPw9PTE+fPnMXz4cLi4uC
gN\n0mRT0cePH8e0adPg5uaGr7/+GmVlZViyZAmCg4Ph5uaGyMhIHDx4kHHv8fHx+Pzzz8Hn88Hn85GT\nk
wMAePDgAWbNmgUvLy8EBARgyZIlKC4uVvtsFafXZfd0+vRpzJgxA+7u7oiIiEBsbKzaawBAXV0d\njh07ho
ULF2L69OlKnx3bP//5TwwZMgRubm4ICwvDxo0bUV9fL389Ly8Pc+fOhZ+fH9zd3TF06FB8\n//33Sq8lkUi
wevVq9O/fH48ePQIA7N27FyNGjICHhwf69euH119/HRUVFW3el75RHVNCDFBeEXd9\nKQCUPDH8HyqEdCez
X9vWpe93ZO/6Dp23YMECHDp0CC++
+CIA4ODBg5g/fz6ys7M7dL34+HjY2dnh\n+PHjkEpbfglesWIFcnNzcerUKVhaWmL9+vV4/Pix/BypVIrZs
2fDzs4OR44cgYODAw4fPozp06fj\nxo0bcHNraQJSX1+PnTt3YteuXXB2doZAIFB5H5s3b8bWrVvx0Ucfwd
TUFPX19QgPD8fKlSthZ2eH\nS5cuYdWqVfD29saYMWOwY8cOPHr0CIGBgdi4cSMAwNnZGUVFRZgyZQoWLFi
ALVu2QCwWY8uWLZg3\nbx4uXLgAIyPNx+G2bt2Kd999F+
+//z527tyJxYsXIzU1FTY2NirPOX36NLy9vRESEoLZs2dj0aJF\n2LRpE0xNTVWeY2Vlhb1798Ld3R1paWl
48803YWZmhg0bNgAA3nrrLTQ0NODHH3+Era0tMjIylF5H\nLBbj1Vdfxb1793Du3Dm4u7sDAIyMjLB9+3b4
+fkhNzcXa9euxdq1a/Hf//5X42ehDxp9peLj4zFn\nzhz069cPfD4fhw4dYrwu+62F/Wf16tUqryn7zYT95
9dff9XuExHyFMhTsr4UAIpKy+X/iRBCeo6Z\nM2ciKSkJjx49QnFxMX777TfMmzevw9czNzfH3r17ERwcjJ
CQEGRkZODChQvYvXs3IiMjER4ejn37\n9qGurk5+TlxcHFJTU7F//34MHjwYvXv3xoYNG+Dr64sjR47Ij2t
ubsbOnTsRGRmJgIAA2NraqryP\nV155BTExMfDz84Onpyc8PDzwxhtvoH///vDz88PChQsxbdo0HD9+HEBL
1y5TU1NYWVlBIBBAIBDA\n2NgYX375JUJDQ7F582YEBQUhNDQUn332GRITE9udILRixQpMnjwZ/v7+2LhxI
8rLy5Gamqr2nAMH\nDmDOnDkAgFGjRsHS0hJnz55Ve87atWsRGRkJX19fREdH480332SMiObm5iIyMhJhYW
Hw8/PDxIkT\nMXHiRMY1RCIR5syZg5ycHJw9e1YelMo+x5gxY+Dr64tRo0bh3XffxalTpwy+7KBGI6YikQj
BwcGY\nO3cuXn31Vc7r7GH6pKQkzJkzBzNmzGjz2t9//z1CQ0Pl2w4ODprcEiFPNWWJTwDQKG5CeWUNHPmq
\nf9ATQp4+fD4fzz77LA4ePAh7e3uMGjUK3t7eHb5ev379GGsr09LSYGRkhMGDB8v3+fj4MAKd5ORk\n1Nb
WIiAggHGt+vp6ZGVlybdNTEwQFham0X0MHDiQsd3c3Ixdu3bhxIkTKCwsRGNjIxobGzlLFtiS\nk5Nx9epV
eHp6cl7LyspifK62hISEyP8u+/ylpcp/JgNAZmYmrl+/ji++
+AJASwH5WbNm4cCBA4iJ\niVF53unTp7Fv3z5kZmZCJBKhubmZsR731VdfxZtvvonffvsNY8aMwbPPPosBA
5jd/5YtWwaBQIAf\nf/yR03/+8uXL2LVrFx4+fIiqqio0NzejsbERxcXFjK+rodEoMI2OjkZ0dDSAlgicjT
1Mf/bsWQQE\nBLT5jQQAjo6Oaof5CemJlJWKkikqLaPAlJAe6MUXX8Ty5cthbW2N9euVLwkwMjLizKo0NTV
xjmMH\nMTLquvJIJBK4urri559/5rymOCpqbm4OY2NjlddRdx8fffQR9u7dix07diA4OBg2NjZ499131QaG
\nsnuLjo7G1q1bOa+5uLhodC8yitPvsuehbqbqm2+
+QXNzM2OQTXZ8Xl6e0gS1GzduYPHixVi3bh22\nbdsGe3t7nD17Fv/4xz/kx7z00kuYMGECLly4gEuXLiE6
OhqrVq3CO+
+8Iz8mOjoa3333Hf744w+M\nHz9evv/x48eYPXs2XnrpJaxfvx6Ojo5ITk7GkiVLOjXZTRd0vsa0pqYGJ06
cwLp16zQ6fsGCBaiv\nr4e/vz9WrFih9rcLQnqChkYxitVk3xc/KUdwoG8X3hEhT6+OrvnUhzFjxsDU1BRC
oRBTp05Veoyz\nszNn2rmtaWgA6NOnDyQSCRITExEREQGgZSq5sLBQfkx4eDhKSkpgZGQEPz+/jn8QNa5du
4ZJkybJ\np8WlUikyMjJgb28vP8bMzIyT6R8eHo6TJ0/C29tb7bpOXWtqasK3336LTZs2ccpELVu2DIcOHV
Ia\nD12/fh3u7u5Yu3atfF9ubi7nOE9PTyxcuBALFy7E7t278emnnzIC05deegnh4eGYP38+Dh8+jHHj\nx
gFomblubGzE9u3b5b8k/PLLLzr5zJ1N51n5x48fR2NjI+bOnav2OBsbG2zZsgVff/01jh07hqio\nKCxatI
ixToWQnqigWAh1y0gLS6hkFCE9EY/HQ3x8PJKTk1WWOIqKikJKSgoOHDiAzMxM7NmzB9ev\nX2/z2oGBgZg
4cSJWrVqFhIQEpKSkYMWKFbC0tJQfM3bsWERGRsoTirKzs5GQkIBt27bh6tWrOvmM\nAQEBiIuLw7Vr1/Dw
4UOsWbOGkYAFtCwxSExMRE5ODoRCISQSCZYuXYqqqiosWrQIN2/eRHZ2Ni5d\nuoSVK1eiurpaJ/emzLlz5
yAUCvHyyy/LKxzI/jz//PM4dOiQ0tHWgIAAFBYW4ujRo8jOzsaXX37J\nybhft24dfv31V2RnZyMlJQW//v
orgoKCONdauHAhtm3bhvnz58srCPj7+0MikeCTTz5BdnY2jh8/\njk8//bRzHoKO6XzEdP/
+/ZgyZQqcnZ3VHufk5ITXX39dvj1w4ECUlZVhz549aosFp6ena3V/2p7f\nk9Gz046mz+9GagajXiGPB0ag
evdBOtKDta9d2J3Q9552DPn5BQYG6vsWuhV1iUQAMGHCBKxbtw5b\nt25FXV0dZs6ciaVLlyqdfmf75JNP8
MYbb2D69OlwcnLCunXr8ORJ67IiHo+Ho0ePYuvWrVi5ciVK\nS0vh6uqKiIiINgejNLVmzRrk5ORg5syZsL
CwwLx58zBz5kw8ePBAfszrr7+O5cuXIzIyEnV1dUhO\nToavry/OnTuHzZs34/nnn0dDQwO8vLwwbtw4ndU
pVebAgQMYPXo0HB0dOa/NmDED//znPxEbG8uY\nZgeAyZMn44033sA777yD+vp6jBs3DuvXr8dbb70lP0Yi
kWDt2rXIz8+HjY0NxowZo3SpAgAsWrQI\nUqkU8+fPx6FDhzBu3Djs2LEDe/bswb/
+9S8MGzYMW7ZswaJFi3T7ADoBr6Kiol0pvp6envj3v/
+N\n+fPnc15LSUlBVFQUTp48KR9Obo/Dhw/jzTffRFFRUbvP1UR6ejr9EOwgenbaac/zO3T6In640DrC\n0
S/AG/czWqd4/LwEeO/tJTq/R0NF33vaoefXqrKykjElTAjRD3X/FnU6lb9//374+vpi7NixHTo/\nNTWVEq
FIj8dOfBrSvw9ju6i0jEpGEUIIeSppNJVfU1ODzMxMAC1Dy3l5eUhJSYGDg4O8XEVtbS2O\nHTuGN954Q2l
W3+bNm5GYmIgffvgBQMvoqKmpKfr37w8jIyP88ssv+OKLL/DPf/5TRx+NkO6JXSoq\ntI8vLMxNUd/Q0q6v
vkGMyupa8O2UZ9USQggh3ZVGgWlSUhKmTZsm396+fTu2b9+OuXPnYt+
+fQCA\nEydOQCQSKZ3iB4CioiJGnTMA+M9//oPc3FwYGxvD398fe/fuVbu+lJCnXX1DI0qFlfJtHg/wEDjB
\nzcUR2XmtrfWKn5RTYEoIIeSpo1FgOnr06Db7q7744ovyVmnKyAJYmXnz5mnVtYKQpxF7Gt/d1RFm\npqZ
wc3FgBKZFJWUI6t2zEqAIIYQ8/XReLooQ0nF5RcxpfC+3luoWAmdmR7QiNXVOCSGEkO6KAlNC\nDMjjAlZg
6t7SscTNhRmYFpdSYEoIIeTpQ4EpIQaEPZVPI6aEEEJ6EgpMCTEg7Kl8bw8aMSWEENJz\nUGBKiIEQ1dZDW
N7aOs/Y2Agerk4AAEe+LcxMW3MVa2rrUS2q6/J7JIQQQjoTBaaEGIi8IlZGvosD\nTEyMAbS0AhQ48xmv06
gpIaSzDR8+HNu3b9f3bXQaPp+P06dPd+l7bt+
+HcOHD+/S9+xOKDAlxEDk\nFSqfxpcRuNA6U0J6muXLl4PP5+O1117jvLZp0ybw+fweV/976tSpWLNmjU6u
lZaWhkmTJml1jfZ+\njV5//XWcOXNGq/fUh0OHDsHT07PT34cCU0IMBDfxiRmYurk4MrZpxJSQnsHLywunT
p2CSCSS72tq\nasJ3330HLy/t6xk3NjZqfQ1VJBIJmpubNTpWLBZ32n2oIhAIYG5urvV12vM1srGxgaOjI/
sS5E8U\nmBJiIHLZNUzdnRnbbqzM/MLSsk6/J0KI/oWEhKB37944efKkfN+5c+dgbm6OUaNGMY5dvnw5ZwS
V\nPXUsO2b37t0IDg5GcHAwAKC0tBRz586Fm5sbQkNDceDAAc69VFZWYuXKlQgICICXlxemTJmCpKQk\n+e
uyUbXz589j+PDhcHFxQVpaGuc6OTk54PP5OH78OKZNmwY3Nzd8/fXXKCsrw5IlSxAcHAw3NzdE\nRkbi4MG
DjHuPj4/H559/Dj6fDz6fj5ycHADAgwcPMGvWLHh5eSEgIABLlixBcXEx570VKU7ly+7p\n9OnTmDFjBtzd
3REREYHY2Fi11wDa9zVS9fXYt28f+vXrB19fX6xYsQK1tbXyY6ZOnYq33noL7777\nLnr37o2AgABs2LABE
olEfkxjYyM2bdqE4OBguLu7Y9y4cfjtt9/kr4vFYqxduxZ9+/aFq6srQkJC\nGG3gKyoq8Oqrr8LX1xdubm
6IiYnB/fv3AQBXrlzB3/72N4hEIvlzly3xOHLkCMaNGyd/7i+//DIK\nCgrafGaqaNT5iRDS+XJV1DCVYU/
l04gpIdqzyl3bpe9X6/3vDp23YMECHDp0SN5h8eDBg5g/fz6y\ns7M7dL34+HjY2dnh+PHjkEqlAIAVK1Yg
NzcXp06dgqWlJdavX4/Hjx/Lz5FKpZg9ezbs7Oxw5MgR\nODg44PDhw5g+fTpu3LgBNzc3AEB9fT127tyJX
bt2wdnZGQKBQOV9bN68GVu3bsVHH30EU1NT1NfX\nIzw8HCtXroSdnR0uXbqEVatWwdvbG2PGjMGOHTvw6N
EjBAYGYuPGjQAAZ2dnFBUVYcqUKViwYAG2\nbNkCsViMLVu2YN68ebhw4QKMjDQfh9u6dSveffddvP/+
+9i5cycWL16M1NRU2NjYqD1Pm6/RtWvX\nIBAIcOrUKeTn52PhwoUICAjAm2+
+KT/m2LFjWLZsGc6fP4/U1FQsXboUAwYMwAsvvAAA+Nvf/oas\nrCx8/vnn8l8O5syZg4sXLyIsLAyffvop
zpw5gy+//BI+Pj4oKChAenq6/PrLly9HRkYGDh8+DD6f\njy1btuCFF17AzZs3ERERge3bt2PLli3yX0Ssr
VvaYjc2NuKdd95Bnz59IBQKsWnTJixZsgQ///yz\nxs9cEY2YEmIAqkV1qKhqnQIyMTHijJC6swNTWmNKSI
8xc+ZMJCUl4dGjRyguLsZvv/2mVVtvc3Nz\n7N27F8HBwQgJCUFGRgYuXLiA3bt3IzIyEuHh4di3bx/q6lq
rf8TFxSE1NRX79+/H4MGD0bt3b2zY\nsAG+vr44cuSI/Ljm5mbs3LkTkZGRCAgIgK2trcr7eOWVVxATEwM/
Pz94enrCw8MDb7zxBvr37w8/\nPz8sXLgQ06ZNw/HjxwEA9vb2MDU1hZWVFQQCAQQCAYyNjfHll18iNDQUm
zdvRlBQEEJDQ/HZZ58h\nMTGRMaKriRUrVmDy5Mnw9/fHxo0bUV5ejtTU1DbP0+ZrZGtri127diEoKAjjx4
/HjBkzcPnyZcYx\nQUFB+H//7/8hICAAzz33HEaPHi0/JisrC8ePH8fXX3+NkSNHws/PD6+88gqeeeYZ/O9
//wMA5Obm\nwt/fHyNGjIC3tzciIiLkQfSjR4/w888/Y/fu3Rg5ciRCQkLw2Wefobq6GseOHYOZmRns7Oxa
EnH/\nfO6yQH3BggWIjo6Gn58fBg8ejA8+
+ADXrl1Dfn6+po+cgUZMCTEA7MQnD4GTPCNfxsnBDiYmRmhq\napm6qayuhai2HtZWFl12n4QQ/eDz+Xj22
Wdx8OBB2NvbY9SoUfD29u7w9fr168dYW5mWlgYjIyMM\nHjxYvs/Hxwfu7u7y7eTkZNTW1iIgIIBxrfr6em
RlZcm3TUxMEBYWptF9DBw4kLHd3NyMXbt24cSJ\nEygsLERjYyMaGxs50+FsycnJuHr1qtLknKysLMbnakt
ISIj877LPX1paqupwOW2+RkFBQTA2bv2Z\n7+bmhps3b6q8L9kxsvtKTk6GVCpFZGQk45iGhgZERUUBAObN
m4fnnnsOgwcPxvjx4/HMM8/gmWee\ngZGRkfzrP2zYMPm59vb2CA4OxoMHD9Te+
+3bt/Hee+8hNTUVFRUV8hH4vLy8DiVLUWBKiAHIZWfk\nsxKfAMDIyAiuTnwUFLeuLS0RVqCXlVun3x8hRP
9efPFFLF+
+HNbW1li/fr3SY4yMjOSBgUxTUxPn\nONk0LBuPx1P5/hKJBK6urkqnaBVHRc3NzRlBljrs+/joo4+wd+9e
7NixA8HBwbCxscG7777bZmAo\nkUgQHR2NrVu3cl5zceH+PFXH1NRU/nfZ82A/U1U0+Rq19Z6y92W/p7pjJ
BIJeDweLl68yDnOwqJl\n8GLAgAFISUnBxYsXcfnyZSxfvhyhoaE4deqU2ntT9z0hEonw/PPPY+zYsfjss8
/g4uICoVCIyZMn\ndzipjgJTQgwAOyOfXSpKRuDswAhMi0rL0cubAlNCOqqjaz71YcyYMTA1NYVQKMTUqVO
VHuPs7MyZ\ndtZkGrpPnz6QSCRITExEREQEgJap38LCQvkx4eHhKCkpgZGREfz8/Dr+QdS4du0aJk2ahDlz
5gBo\nCQgzMjJgb28vP8bMzIyT6R8eHo6TJ0/C29ubE5h1JU2+Rp2hf//
+kEqlKC4ulo+QKmNra4uYmBjE\nxMRg3rx5mDhxIjIzMxEUFASJRIKEhASMHDkSAFBVVYV79+7JlyMoe+7p
6ekQCoX4xz/
+If+e+OGH\nH7T6LLTGlBADwJ7K93JzVnocuzVpEWXmE9Jj8Hg8xMfHIzk5WWWJo6ioKKSkpODAgQPIzMzE
nj17\ncP369TavHRgYiIkTJ2LVqlVISEhASkoKVqxYAUtLS/kxY8eORWRkpDyhKDs7GwkJCdi2bRuuXr2q\
nk88YEBCAuLg4XLt2DQ8fPsSaNWsYCVhAyxKDxMRE5OTkQCgUQiKRYOnSpaiqqsKiRYtw8+ZNZGdn\n49Kl
S1i5ciWqq6tVvJvuafI16gwBAQGYNWsWVqxYgdOnTyM7OxtJSUn46KOP5IHi3r17cfz4caSl\npSEzMxPHj
h2DnZ0dPDw84O/vjylTpmDVqlW4evUq7t69i1deeQW2traYOXMmgJbnXl9fj9jYWAiF\nQtTW1sLLywvm5u
b4/PPPkZ2djXPnzmHbtm1afRYKTAkxAOyuT+yMfBmBMzsBqqLT7okQYnhsbW1h\nZ2en8vUJEyZg3bp12Lp
1K8aOHYvHjx9j6dKlGl37k08+gY+PD6ZPn465c+di5syZ8PHxkb/O4/Fw\n9OhRjB49GitXrsTQoUOxaNEi
ZGRkMNaiamPNmjUYNGgQZs6ciSlTpsDKykoeGMm8/vrrMDMzQ2Rk\nJPz9/ZGbmwt3d3ecO3cORkZGeP755
xEZGYnVq1fDzMysSwNEoO2vUWf5+OOPMX/
+fGzcuBFDhw7F\n7NmzER8fL/8a2tra4sMPP8SECRMwZswYpKam4tixY7CysgLQ8vUfNGgQ5s6diwkTJqCu
rg7Hjx+X\n/3ISERGBxYsXY8mSJfD398eePXvg7OyMffv24cyZM4iIiMB7772Hf/3rX1p9Dl5FRYVmCyeeA
unp\n6QgMDNT3bXRL9Oy0o+75VVaL8Mo7e+TbZqYm2P/
+aqXlTW7fe4Ttn7RmvwYH+mDTyhd1f8MGhL73\ntEPPr1VlZSVjSpgQoh/q/i3SiCkhesZOfPIQOKmsucce
MS0soal8QgghTw8KTAnRM00TnwDAxdEe\nRkatGZLllTWob+i8doKEEEJIV9IoMI2Pj8ecOXPQr18/8Pl8H
Dp0iPH68uXL5S2qZH8mTpzY5nV/\n//13jBkzBgKBAOHh4fjqq6869ikI6cbYiU/eKhKfAMDExBgujszpD1
pnSggh5GmhUWAqEokQHByM\nHTt2MDL0FI0dOxZpaWnyP8eOHVN7zezsbMyaNQvDhg1DXFwc3nzzTaxdu1b
es5aQnoJTw1TNi
Cmg\npDUpdYAihBDylNCojml0dDSio6MBtLTqUsbc3FxtP1y2r7/+Gm5ubti5cyeAlq4HN2/exN69exET\n
E6PxdQjpzqRSKWcqX1VGvoybswNS0NplpaiUAlNCCCFPB52tMb127RoCAgIwePBgvPHGG212aUhI\nSMD48
eMZ+yZMmICkpCSIxWJd3RYhBq2iqgY1tfXybXMzE85UPZubqyNjm0ZMCdGcph18CCGdo61/\ngzoJTCdOnI
hPP/0Up0+fxtatW5GYmIjp06ejoaFB5TklJSWcNmEuLi5oamqCUCjUxW0RYvBylYyW\nqmv/BgACJz5ju4g
y8wnRiIWFBWpra/V9G4T0aLW1tfI2qcropCXp888/L/97SEgIBgwYgLCwMJw7\ndw7Tp0/XxVvIpaen6/X8
noyenXaUPb+ExLsQiUTybXMTaZvPuU5UyTjnYWbOU/
+1edo/X2cz5OfX\nlTVWzc3N0dTUhMrKyi57T0IIk4mJidqmBzoJTNnc3d3h4eGBzMxMlce4urpypvtLS0t
hYmICJycn\nledp80OMCk13HD077ah6fhdvPIS1tbV8e1D/4Dafs6+fGDaHL0A2GyJuBnz9/GCmx/7QnYm+
97RD\nz49J8d8bIcTwdEodU6FQiMLCQrXJUMOGDUNsbCxjX2xsLAYOHAjTp/Q/WELYODVM20h8AgAzU1M4\
n8m3l21IpUCKkESBCCCHdn0aBaU1NDVJSUpCSkgKJRIK8vDykpKQgNzcXNTU12LBhAxISEpCTk4Mr\nV65g
zpw5cHFxwbPPPiu/xrJly7Bs2TL59qJFi1BYWIi3334baWlp+Oabb3D48GG89tpruv+UhBgg\nqVSKvCJWq
SgNAlMAcHdhJUBRZj4hhJCngEaBaVJSEqKiohAVFYW6ujps374dUVFR2LZtG4yNjXHv\n3j3MmzcPQ4YMwf
LlyxEQEIDz58/D1rZ1VCcvLw95eXnybT8/Pxw9ehRXr17F6NGj8Z///Afvvfce\nlYoiPUZFVQ1q61q7Nll
amDFGQtVh1zItosx8QgghTwGN1piOHj0aFRWqu8ucOHGizWucOXOGs2/U\nqFGIi4vT5BYIeeo8KatibAuc
HdrMyFc8VhGNmBJCCHkadMoaU0JI256UMwNTZ0c7jc91Y4+YUmBK\nCCHkKUCBKSF68qScmbDkxG9PYEpF9
gkhhDx9KDAlRE+ErBFTJwfNA1OBM7PIfomwAk1NzTq5L0II\nIURfKDAlRE/Ya0yd2xGYWpibwcHeRr4tkU
g5I7CEEEJId0OBKSF6IqxgrzG1b9f5tM6UEELI04YC\nU0L0hD3Pn/mSAAAgAElEQVSV354RUwBwdWJO51N
gSgghpLujwJQQPWgUi1FZXSvf5vEAvl37WiW6\nu1KRfUIIIU8XCkwJ0QNheTVj25FvC2Nj43Zdg13LtLC0
TOv7IoQQQvSJAlNi8Morq5GWmYdGsVjf\nt6Iz7EQlZ4f2rS8FAA8Bc8T0YVYeZeYTQgjp1jTq/ESIvtx9m
INtn3yLpiYJ+gV4Y/3f5sDM1FTf\nt6W1MtaIaXvXlwKAj4crbK0tUS2qAwCIahuQlpmHkD6+OrlHQgghpK
vRiCkxaD/8eg1NTRIAwP2M\nXFy6nqLnO9INdtcnp3Z0fZIxMjLCgBB/xr7EO+la3RchhBCiTxSYEq00NTX
jyyO/4M0tn+HomcuQ\nSqU6u7ZUKkVWbhFj34+/Xkdzc/efri4tY0/ltz8wBYDBoYGM7VsUmBJCCOnGKDAl
Wjl6Jg7nr9xC\nfrEQ3/8cj5QHWTq7dkVVDSNzHQBKhJW4lvRAZ+
+hrdzCUnxz4lfsP34BZRXVbZ/wJ3YN0/a0I1UU\n3q83jI1b/xkXlpSjoFjYoWsRQggh+kaBKemwJ2WVOHs
pgbEvNU13gWlOfonS/acvXNXpyGxH1Dc0\n4sDJ37Bux5c4czEBZy/dwCcHftT4fCG761MHpvIBwMrSHMEB
Pox9NJ1PCCGku6LAlHTYdz9dhljM\nnFbPK3yis+vn5BUr3f84vxRJdzN09j7tIZVKce3Wfaza8hl+
+u0PNDdL5K+lpmVDVFuv0TXYWflO\nHcjKlxkUGsDYvnVHP8+GEEII0RYFpqRDsvOK8PuNO5z9eUU6DExVj
JgCwKnz13T2PpoqLCnDtk+
+\nw+6vTqqcti8sabuWaE1tPRoam+Tb5mYmsLGy6PB9DQ5jrjN98CgXNbV1Hb4eIYQQoi8UmJJ2k0ql\nOH
jqIpTNppcKK1FX36CT93lcoDowTcvMw4NHuTp5n7Y0isU48tNlrN72X6TcV79UoaCk7fWdQiU1\nTHk8Xof
vT+DsAC83J/m2RCJF8r3MDl+PEEII0RcKTLuB2Gu3sXbHF/jw61PympX6lHw/E6kPslW+\nrovp/EaxGPms
JJ6g3l6M7VPnr2r9Pm3JzivCW1v/ixO/xMvLVskYGxtxitxrMmLK6frkYKv1fQ5i\njZomptI6U0IIId0PB
aYGrkRYgc8On0VOXgniE+91STCmjkQiwaHTF9Uek1dUqvX75BcJIZG0Dsm6\nONljzrQxjGOS7j5SO92vLa
lUio+/
+RElwkrOayGBPvj3O0sxfWIkY3+hBiOmuuj6xMYuG3X7/iPq\nAkUIIaTbocDUwKVn5TOmzJPvPdLfzQCIS
0jF43xm4MlOvsnVwYhpTj4z8cnX0xX9AnwQ6OfB2H+6\nEwP1/GIhHhcwP6u9nTVeXxiDf7wxH15uznBzYY
+Ylrd5XXZxfRdH7QPTPr08YWttKd8W1TbgYVae\n1tclhBBCupJGgWl8fDzmzJmDfv36gc/n49ChQ/LXxGI
xNm3ahBEjRsDDwwNBQUFYunQpcnPVr/
+7\ncuUK+Hw+58/Dhw+1+0RPmfKqGsZ2XtET1Dc06uVeGhrFOPJTHGPfqKEhiBoWxtiXW6j9iGlOHnMk\n1
NfTFTweDzOiRzD2X711D8VP2g4GO+JGchpjO9DPA7s2LMOoISHyNaHurk6MYwpLhG2WsmKXinLS\nwVS+8i
5QlJ1PCCGke9EoMBWJRAgODsaOHTtgaWnJeK22thbJyclYvXo1Ll+
+jMOHDyM/Px8vvPAC\nmpqaVFyx1fXr15GWlib/4+/v3+Y5PUl5JTMwlUrVZ6t3prOxCYxsdBMTI8x5dgy8
3J0Zx+lijSl3\nxFQAoCUD3Vvh/aTSlm5QneFGCvOXpLGR/WHNyp63t7WCtZW5fLuhsanNQvucdqQd7PrER
l2gCCGE\ndHcaBabR0dHYuHEjYmJiYGTEPMXe3h6nTp3CX//6VwQGBmLw4MHYtWuXPNBsi4uLCwQCgfyPsb
Fx\nxz7JU6qikhvkZD4u7PL7qBHV4fQFZommSWOGwsWJD3cXR0b3obKKao3qeaoilUo5wbevpysAgMfj\nY
fozwxmvXfojBRWskWVtCcur8Cin9TnzeNyyTLL74Uznl6pPgOLUMO1g1ye2/n17Mb4OBcVl1AWK\nEEJIt9
Ipa0yrq1uCKT6f3+axY8eORVBQEKZPn464uLg2j+9pKqpEnH2ZrP7xXeF8fDLq6luXENhY\nWeC5v7RMq5u
YGMPDlRmcaVPPtKyiGjUKga2FuSkEzg7y7RGDguHi1LouUyxuxtnYGx1+P2VupjJH\nSwP9POFgr3zK3UPA
nM5XFww2NzdzRsE72vWJzdrKgtMF6paeGhEQQgghHWGi6ws2NjZiw4YNmDRp\nEjw9PVUe5+bmhg8+
+ACDBg1CY2Mjjhw5gpiYGJw5cwYjRoxQeV56unbTk9qe39WyHudBJGIGp0mp\nD5Ce3rfL7qFEWImrt9LQr
JAlPzEyGIX5rck1FqY8xn1ev3kbRs0dK211NyOXcS0XvgsyMpgB1qC+\n3jhxvkC+feLsJYT2doWlhVmH3p
PtXOx1xj14udiq/N7hNTcwjk2+8wC93LjBZnp6OiqqRKiubg1M\nbawtkJOdrZN7BgA3J2tcV7iXX+MSEOT
tqOaM7qG7/bs1NIb8/AIDuTMRhJCeS6eBaVNTE1555RVU\nVlbi22+/VXtsYGAg4wfSsGHD8PjxY3z44Ydq
A1Ntfoilp6d3ux+CUp4xrK2tGftq6sTw9vGFhblu\ngrC2/Hj5ezRLpPL7cHWyx8LZz8LUtPXbZ2BYMdIft
yY9SY3MOvys72SWMD7zgNAgzrV8fP1wPSUT\nldW18n2ZhZWc5KiOqKmtQ6GwmnEP0yeNhbur8gCvtEqMuM
TW//ibYcK5X9n3XlpmHuO6ft4CnX5P\n2vKdcOHqXfl2cVkN3D29YGNlqeYsw9Yd/90aEnp+hJDuRGdT+U1
NTViyZAnu3r2L06dPw9Gx/aM0\ngwcPRmYmdayRqW9oRG0dNwO/KxOg0rPy8cdt5lrhOdPGMoJSADpNgGIn
Pvn8ub5UkbmZKSaPHcrY\ndzY2QSetOG/dyWDUUPVyc1IZlAJoV5H9J2W6r2GqyM3FkbpAEUII6bZ0EpiKx
WIsWrQId+/exY8/\n/giBQNCh66Smpnb43KcRey2ioq5KgDobm8DY9vd1x4jBwZzjvN1dGNuPtSgZxU18Uv
49ET16MGPq\nvrK6Fv89fLbNck1tucnKxh8aHqT2eHbyU/GTcpXF7dkZ+bpaX6qI3QWKsvMJIYR0FxoFpjU
1NUhJ\nSUFKSgokEgny8vKQkpKC3NxcNDU14eWXX8bNmzfxxRdfgMfjobi4GMXFxairax29WrZsGZYtWybf
\n/uSTT/DTTz/h0aNHuH//PjZv3owzZ87g//7v/3T/KbupciUZ+TJdkQBVUVWDP1i1PGc/O0ZpX3eB\nMx8
mJq3fTpVVog61T21oFHNGHH08XJQea21lgSnjmKOmf9xOw6+/J7X7fWUaxWLcZjUxGNq/j9pz\nLMzN4Mhv
TYySSqGytmpZReeUilLE6QJ1LxPNzdQFihBCiOHTKDBNSkpCVFQUoqKiUFdXh+3btyMq\nKgrbtm1Dfn4+z
p49i8LCQnmGvezPiRMn5NfIy8tDXl5rsoxYLMbGjRsxcuRITJ48GdevX8fRo0cx\nffp03X/KbkrdiGlWF4
yYxl5LRnNza394D4Ej+vftpfRYY2NjTnZ6bkH7lxvkFpQyOl25uTjA0sJc\n5fHPRY9Ebx83xr79Jy50eKl
Dyv0sNDS21t915Nuit497m+exqxKoms7njJjqeCofaGkEoNgFqqa2\nHmmZ1AWKEEKI4dMo+Wn06NGoqKhQ
+bq612TOnDnD2F65ciVWrlypydv3WBXV3FJRMrIOUJ2VACWR\nSHDh91uMfc+MGqR0tFTGx92F0a40r+gJg
gN92/W+ylqRqmNqaoKVi2Zg3Y4vUd8gBtBSPurDr0/i\nX2sWtfv5sIvqD+3fR+1nlnF3dcSdhzny7QJVgW
kndH1iMzY2xoAQf1xJuCPfl3gno91fC0IIIaSr\ndUodU6Ib6joIdXYC1K07GRCWt76/qYkxxkT0V3uOF2u
daW5B+9eZarq+VJGbiyOWzpnM2JdXJMT+\n7y+0672bm5uRmMpcjzk0XP00voy7gNuaVBlhF4yYAtQFihBC
SPdEgakBY3czUuzqA3RuAtT5K8zR\n0kEhvTntONnYCVAdKbLf3hFTmdFDQzEmIoyx7+LVZFxNvKfxe6dl5
jHWxdpYWaCfv4+aM1ppMpVf\n39DIuL6xsRH4dtac43RBWRcoddUCCCGEEENAgakBq2CtMWV39cnqpASoot
IyJN9nlhgaOUh9ZjrA\nLRnVsl5U8wx5qVSKxwXKW5FqYvGsv3BKN33+3VmViUhs7Gz8gaEBMDHRrEUuu5y
Usql89mipI9+W\n0+JXV6ytLNDP35uxj7pAEUIIMXQUmAJIvp+J1zZ9jNc2fYzUtCx9345cGSsrf1BoAGO7
s0ZML7Cy\n2gP83OHNCjqVETg7wEyhvmm1qI5RAL8tT8oqGXVbrSzN4Oyo+VS3hbkZVi6awagOUFvXiA//d
0pl\n+SYZqVSKBCXrSzXl4mjPqUogUmirCgBC1tIM507IyFfELhv1R9KDTn0/QgghRFs9PjCtqqnFB198\n
j1JhJUqFlfjfsfP6viU59lQ+OzCVJUDpUqNYjMvXUxj7okcN1uhcHo8HTzfmWsu8Is3XmbLXl/p4\nuGqUe
KTIz8sNL86YwNiXkV2II2cut/HexSgVtha/NzM1QXi/3hq/r7GxMQRODox9RaXMUVNhObO4\nfmeUilLEDq
zTMvM490QIIYQYkh4fmP7423V5NjfQkjTT0ChWc0bXYHd9MjExgsDZAW4urcFPZyRA\nXbv1gLPOcvjgfhq
fr00CVEcSn5SZNGYIhvRnjhb+cOE6pz6pohvJzNHS/v16tTuj312gfjqfk5HP\n79zA1NWJj77+Xox9ipn6
hBBCiKHp0YFpZbUI5y7fVLpf39ijpXw7G/B4PPTyZgZrup7Ov3AlkbE9\ndng4zExNNT5fmwSojiY+sfF4P
Lw6/1lOKaYPvvgecQmpSs9JSGE2EmjPNL4Me50pOzO/K7o+sY0e\nGsrYvnLjjtadsQghhJDO0qMD0x9+vc
4opi7DDgr1gV0qysHOBgDQ28eDsV+XCVBZuUVIzy5g7Js4\ncmC7rsFei6qPEVMAsLW2xGsvTYfiSoCGxiZ
8/M2P+O+3Z9Eobh0VL35Szqi/yuMBA0OYyyY04eHK\nKhlVzJ7KZ5eK6vzANHJQP5iatiZwFT+pwMOs/E5/
X0IIIaQjemxgWl5ZjfNxiUpfq6gyhBFT5j04\n2MsCU2aXI10GpudZo6X9+/XijAK2hTtiqllmfl19A4pKW
7PneTzAW0UrUk0FB/pi7rSxnP2/xd/G\nhvf3y8snsYvq9wvwgb1t+8s4KS6zALhT+UJOO9LOqWGqyMbKEk
NYSVCqRo0JIYQQfeuxgekPF66j\nUcwdLQUMY8S0nHUPDvYt09K9vJiBaW5hqU7WxIpq6xF/8y5jX/SoQe2
+jrOjPSzMW6f+RbUNGj3P\nx6yRVXdXR5ibab6EQJWY6BF4df4URrUAAMjJK8E7//4K127d55SJGtKBaXwA
8BAwR4uLSsvkQblU\nKuWsMe2KEVMAiBrGrO967dY9xogxIYQQYih6ZGBaVlGNC/G3VL5uCIEpZyr/zxFTa
ysLTgJUdh5z\nbWZHxCWkMpY1ODnYcqoAaILH43HqmbKDTmUec6bxO7a+VJlxwwdg6+qFcHdljmjW1Tdi91
cncT8j\nl7F/WAcDU3tbK1hZtiZM1TeIUf5nLVpRbT3jFyELc1NYWZp36H3aq3/f3rC3tZJvi2obkJhKNU0
J\nIYQYnh4ZmJ46fxViseq6loYxlc8eMbWR/13XCVBSqRQXWJ2eJowYCGNjzYrLs3m5tT8Bipv41PH1\npc
r4erpi25rFGD6or9rj/LwEcHHid+g9eDwe3FnrTAv+TICqYNVzdXawa3cprI4yMTHGiMHBjH1X\nbtB0PiG
EEMPT4wLTJ2WV+O0qs4B8/369GNuGMGLK7vrEt2sNTHWdAHU3PQf5xa0Z5MbGRhg/IrzD\n11PWAaot3MQn
3Y2YylhZmmPlouewZPZfGMXwFXUkG18RJzP/zwQo9tKMrlhfqog9nX/7XqZBVJ8g\nhBBCFPW4wPTk+atoa
pLIt12c7DHjmRGMYwxhxLS8UvkaU0D3CVC//s4cLR0W3ofxfu3FSYAqVB+Y\nKm9FqtsRUxkej4fo0YPx7q
qX4OLEDQ6HhrfdelUdTmb+nyOm5ZXM76muKBWlqJe3G7wUmh80N0tw\nNfFel94DIYQQ0haTtg95epRV1uD
S9WTGvucnjeQECYYwYlpepXyNKaA6AUpdslBzczNKhJUoLBGi\noKQMhSVlKCgWorCkjBMEP6NhpydVlNUy
lUqlKqeui5+UM5oc2FhZwJHf8cBYE/6+HtixbjH2HfwJ\nN1PSAQCRA/vCR8tKAJwR0z8rDbB/2emqxCcZH
o+HqGFhOPzDJfm+uIRUTB47tEvvgxBCCFGnRwWm\nF+KTGaOlAmc+Rg8NQ1Mzc71pZbVIbSDV2ZR1fbK1tp
RvyxKgZOWVWjpAFaNPLy/OtSQSCb4+dh6x\n15PVrquV8XJzQnCgj1b378i3hZWlmfwz1NU3QlhepbLvvbJ
p/K549jZWllj9fy8g83EhamrrERLo\nq/X7erC7P/25RKKcFZh2dtcnZUYNDcW3P16CrHpX5uMi5BU9gZeb
s/oTCSGEkC7SY6byi0rLkJDC\nzER+ftIomJgYw8LcDJYWrdnUTU0S1NTW6+y907Py8f7nx/H1sXOoqa1r8
3hVXZ8UcROglE/nf//z\n7zh/5ZZGQSkATB47VOvgjMfjwduduUZUXQJUZyc+qcPj8eDv64Hwfr1hYtKxZC
9Fbi7MwLREWIGm\npmbOiKlTF0/lA4CTgx1C+/gx9sX9QUlQhBBCDEePCUxP/BIPiaS10Lu7qwNGDQ2Rb/P
tmAXVdZUY\nUt/QiPc+PYqE5If45XIivlWYSlVFVdcnRb283RnbyjLz76Xn4Ptffm/z/YyNjeAhcMSsqVGY
0M5O\nT6pwEqDUrDPljJh66T7xqatYmJsxliFIJFIUPynnjJh29VS+zGhWEtTvN+9AIpGoOJoQQgjpWj1i\
nKr+wpIzT7eb5yaMZ5ZD4djYoLGntPFRRVaOTKc707HxUi1pHSZPutl0/UlXXJ0X+vszAlJ0AVS2q\nw0f7
f4Bi0yVzMxP09nGHu6sjPARO8HB1grurI1yd+DoZLVTEfnbqMvN12YrUEHi4OjJ+ucgreoKq\nmlpYWbX+8
qOPqXwAiBgQhC+P/CyvWSssr8bd9ByEBfVq40xCCCGk82k0YhofH485c+agX79+4PP5\nOHToEON1qVSK7d
u3o2/fvnBzc8PUqVNx//79Nq97+vRpREREwNXVFREREfjxxx879ina8Gt8EiNA\n8xQ4YSSrriN7xJSdENR
R7IBMWF6N2roGteeo6vqkSF0HKKlUin0Hf+SMvK5+ZSb+
+fcFWDZvKqZN\niMTgsEB4CJx0HpQCgJeSBChlRLX1KBVWyreNjHjwdHNSemx34cZKgLqXnsP4/rO3s4apq
X5+J7Qw\nN8OwAcxarnEJd7S6ZrWoTqO2s4QQQkhbNApMRSIRgoODsWPHDlhaWnJe37NnDz7+
+GO89957uHjx\nIlxcXPDcc8+hurpaydVaJCQkYPHixZg5cyauXLmCmTNnYuHChbh582bHP40K86aPxd9em
gZnh5YA\n7/nJo2BkxPzofNZ0ua4y85UFZAUKNUOVKa9UnZEvo6wDlGyt5i+Xb3I6+8Q8Mxz9+3bdqBg7uz
2v\nsFRp8MIuE+UpcIKZqfatSPXJQ8AMrFMfZDO29TWNL8OuaZpw+wHqGxpVHK1ao1iMrXsPY+m6XVi7\n4
wtU1dS2fRIhhBCihkaBaXR0NDZu3IiYmBhOQCeVSrFv3z78/e9/R0xMDIKDg7Fv3z7U1NTg+PHj\nKq+5b9
8+jB49GqtXr0ZQUBBWr16NUaNGYd+
+fdp9IiWMjY0RNSwMb7/yHFYumoHhg/pxjuEGprpZ\nY5pXyA1M89vohMStYcoNTAHlCVDZeUU4eOo3xv5A
Pw/Mmhqlye3qjL2tNaOSQENjE0qEFZzj2O1U\nO6Owfldzd2G2Ps1n/SKi78A0tI8v43uqvkGMhOS0dl/n5
9gb8qD7cX4pp3sYIYQQ0l5aJz/l5OSg\nuLgY48ePl+
+ztLTEiBEj8Mcff6g878aNG4xzAGDChAlqz9GWsbERRgwO5gTXQOckP0mlUuQVcddW\nsgMVNnVdnxSxE6D
upedg91cnGSWxrCzN8MaiGZ0yXa8Oj8fjJECxg/Q/bj/A0TOXGft8uvn6UgCc\ntqRs+g5MjYyMMHpYKGMf
ew12W5qamvFLXCJjX2audq1xCSGEEK0XuhUXt4x4ubgwp25dXFxQWKj6\nP6ri4mKl55
SUlKg4o0V6enoH71T9+VUVZRCJWoPRzOzHWr9XRZUIJaVlnP0p99IwNJhbc1Qm+3E+\n414qy58gPZ2bOW0
KMeO4i/HcEasXooegsqwUlWVttwVtS3ufh7mxlHF/N5JSYGcBNDU348eLNxF3\ng7sO2cyoSevnrm/NzRLU
19WiWcJcuiB7Fg11Ir1/Rm9nG8bX5o9bd3Hj1m3wba3VnNXq1t1M5OYz\nE+7uP8zstM+l7+fV3Rny8wsMD
NT3LRBCDEi3y8rX5odYenq6yvNNLW1h/dM1+baxibnWPzBv33sE\na2vuf/T1Yqnaa0t4RozzBoaHwc7Gin
Och6c39p9WXQ5qwsgBmDk9up13rZy6Z6fKoMJK3E7Lk283\nwRR8Rxfs/vokMrILOc9m9LBQTBo/Sm+NDXS
pt58XCopbfykRiUTyzxsWEqT3/4wDA4EzV1IZSyny\nSkUYOmhAm+dKpVL87/TvnK9fvViK3r17M6pd6EJH
vvdIK3p+hJDuROupfIGgZeq1tJQ5IldaWgpX\nV9XrBQUCQbvP6Uz2rJEiXSQ/qcpELyotR6NYrPS1tro+K
WInQCnycnPCy88/08471i0vN+aIeOqD\nLLz93lfIyGaOpJuYGGHhC8/gbwumPRVBKcBNgFLk7KC8A1ZXi4
pgJkGduZgAkQaNJdKz8zlfQ6Bl\npLhEocICIYQQ0l5aB6a+vr4QCASIjY2V76uvr8e1a9cQERGh8ryhQ4c
yzgGA2NhYted0JjsbKyjG\nRFU1dWhq0qxbkirKEp+Algx6xZqpijTp+qSInQAFAGamJli5+DmYm+k3u529
xrSiSsTpqOXiZI/N\nf39JJx2nDAm7A5QiJwdu+S99iBoWxuh4Vi2qw6kLV9s872xsgsrXCkvUr58mhBBC1
NEoMK2pqUFK\nSgpSUlIgkUiQl5eHlJQU5ObmgsfjYfny5dizZw9+
+OEH3Lt3DytWrIC1tTVeeOEF+TWmT5+OzZs3\ny7dfffVVxMXFYdeuXXj48CE+
+OADXLlyBcuXL9f9p9SAsbExZ7pc2wSo3ELV62VVlYziZOSrSHyS\nYSdAAcDLz0+Ej4f+s9vtba1hb8tdg
iAzKDQA29cuRoCfRxfeVdfwcFUemJqYGKlMZutqttaWiHlm\nOGPfz5duoFRJ9QSZUmEFric9UPl6YanyX7
gIIYQQTWgUmCYlJSEqKgpRUVGoq6vD9u3bERUVhW3b\ntgEAVq5cieXLl2PNmjUYN24cioqKcOLECdjato4
MZWVloaioNVkiIiICX331FQ4fPoyRI0fiu++
+\nw1dffYUhQ4bo+CNqzt5Od9P5UqlU5YgpoLpklKalomQGBPsztiMH9tVZW1Fd8GYV2gdaiujPnzEe\na5
fNVLlMobtzVxGYOtrbGtTI8JRxwxgtVMXiZhw5E6fy+F/iEqGuln5bNXoJIYQQdTRKfho9ejQq\nKlSPovB
4PLzzzjt45513VB6TmsotRxMTE4OYmBhNbqFL8O1s8Di/dd2rNiOmT8oqUd+gfB0poCYw\nVTKVr46vpyuW
zZuCi1dvw89LgBefm2BQgU+QvxfuPMyRbzvY2+Dvi59DX39vPd5V51O1xtTZ0TDW\nl8qYm5li9rNR2Hfwj
HzflYQ7eHb8MPixuovVNzQi9tptxr4h/QNxM6U147uohFuFghBCCNGU1mtM\nnybsaXNtiuyzE5/MWC0o84
pVjZgyuz4pjmapMn7EAGxdvRBL50yGhblZm8d3panjIhAS6AMzUxMM\nH9QX77295KkPSoGWZQyK6zdlnPR
cw1SZqGFh8PFkjmwfPHmR06nr0vUUiGpb2+na2Vhi5pTRjGMK\nKDAlhBCiBQpMFeiyLenjAmbFgYEhzCn3
wpIySCTc2qTsqXx24f/uxtrKAhtXvoj//ect/H3xXznV\nD55WPB5P6aipvovrK2NkZIT5McxmF6lp2Ui+n
ynflkql+PnSDcYxE0cNgpebC4yMWkfoyyqqO9Te\ntLtqbm7WOkmSEEJIKwpMFXDXmOpuxLSvvzcjEUgsbl
baopPd9cnB3jAyuLWl69qW3QG7NSlgmIEp\nAIT3642wvn6MfYdOXZT/8nTrTgaKFBKbTEyMED16EExMjOH
qxGecV6SkqcTTKC0zD69t+gSL176P\nM2oqFRBCCNEcBaYK2F1vtBkxzStkjph6e7jA041ZPim/iJsowk1+
ejoC055IWWtSQ1tjKsPj8fDi\njPGMkmmPC0px+Y8UANwSUcMHBcu/N9kjw4qNBQyZqLYeu748gbU7vsDvN
+
+2+/z9319AWUU1Ghqb\ncODErz0mICeEkM5EgakC7lR+x0ZMlWXke7u7cP4DV1aAv6L66ZrK78mUZeZrsmZ
YX/y83DBqaChj\n35Gf4vAwK4+RwAYAz44fJv87e2S4sJusM/38u7O4nvQAOXkl2HfwR7VlstiqRXV4lNPa
ZEAqbVmD\n2x5VNbU4dPoivvn+AoTlVe06lxBCnlYUmCpgB4EdHTEtflKORnGTfNvW2hL2ttbwZAWm7Mz8h
kYx\nI4Q1LjMAACAASURBVLnExMRIaStS0j0oX2NqmCOmMnOeHQNT09ZlF+WVNfj3p8cYxwQH+jAy9jkj\n
pt2gyH7xk3JGPdamJglu38tUcwZTelYeZ9+l6ylobtZsvalUKsWuL0/ghwvXcSb2BnZ9eYKTbEYI\nIT0RB
aYKlCU/deQ/C/ZoqZe7M3g8HrxYNT3ZNR/ZGfn2ttYGVfqJtI+7qyNMTFr/idnbWcPK0lyP\nd9Q2Z0d7TB
47lLGvWlTH2J7Cet2NNTLcHUZMz12+yanHej/jscbn33+Uy9lXXlnDSBhTe37GY9xL\nb32/9OwCTsIkIYT
0RBSYKrCyNGeMFjU0NnUow5g9RS8rMs8eMc0resIIfNnrSx1pfWm3ZmFuhqnj\nWlvszmB1WTJUM54ZobLx
gcCZj8FhgYx9Hqy1tIUlQoMe/auta8DFa8mc/fcyHmt832mPuCOmAHDx\nKve6ypyNvcHZd+tOupIjCSGkZ
6HAVAGPx9PJOtPcAmYrUlnPeEe+LaO2ZV19IyMY5ZaKMozWlaTj\n5sWMw871S/HOsucwZdywtk8wANZWFv
jrpJFKX5s0ZgiMjJg/NhzsbWBhbirfrq1rRGV1bafeozZi\nryejrp77C2d5ZQ2Kn7TdUrVRLMajxwVKX7t
1N6PNJUBFpWW4mfqQsz8xlQJTQgihwJRFF5n5uawR\nUy+3lhFTZbUtFUdX2V2f2mpHSroHHw9XuDoZ9tpS
tujRgyFwZpaBsrI0w7jh4ZxjeTwe3FyY0/kF\nKhpI6JtEIsEvl7ijlTKaTOdnZBegqYlbgxgAmpsluPwHt
8udol+ULCMAgIycAq26zRFCyNOAAlMW\nbUdMJRIJZ+2obMQUgJKSUQqBaQe6PhHSGUxMjDF3+jjGvgkjB8
LSQvkaWQ/WOlPFmqeG5GZqOkqE\nlSpfv5/BXTvKlpbJnMY3N2N2dbt0PVnlkgBRbT1ilSwjAFoy+2/ffdT
m+8sIy6vw7Q+x+P7n31FT\nW9f2CYQQ0g1QYMqibWZ+UWk5xOLWzFx7WytGtyMvTs3H1iCWHQRTqSiiT5ED
+2Le9LHwFDghKiIM\ns6ZGqTzWXcAaMTXQzHx29yovN+a/x3sajJg+YCU+PfeXkYwkt4LiMk7wKhN7PRn1D
WKV107UcJ1p\nc3Mz3vvsKE6dv4ajZ+Kw//tfNTqPEEIMHQWmLOwR0/ZOreWyC+uzMvHZI6aMqfwK5ogpFd
cn+sTj\n8RATPQIf/GMZ/rZgGsxMTVUey24mYIiZ+Vm5RYxMeABY/uI0RlBZKqzEkzLVI6oSiQQPWaWihvT
v\ngyFhfRj7Ll69zTm3ubkZv1y+yTqXmUiWfD8TYoVSc6ok389ETl7rWvZrt+4pbXFMCCHdDQWmLNwR\n0/
YFpspKRSlSN5XPHp2l5CfSXbCn8gsNsPsTu21oWJAfAvw8EODrwdivbtT0cUEpautaE6dsrS3h\n5ebMWXt
7Pek+ausaGPtupqajVGEZgampMf5vzhTGWvL6BrFGo7bs5QCqWhwTQkh3Q4EpCzsYZK/7\nbAunFSlrxNTV
yZ4xQlNZXSuvE0nJT6S7Yic/FQvLNS423xXKK6tx7dY9xr4p41rqsfYL8GHsZ0/V\nK0rLZL7Wp7cneDwe+
vftBSeH1hmOhsYmXE1ktjllt3UdNSQUfDtrDAoNYOxvq2xURZUIiXcyOPuV\ntTgmhJDuhgJTFntOVr52U/
nsovrGxsacuo8FxUJO1ydjY+r6RLoPaysL2CvMNjQ1SVCqZkocaOl+\ndPzsFfzj/f34/uffNZrC7qhzcYm
MTHp3VwcMDGkJCNmBqbrMfHb90qDe3gAAIyMjjI3sz3gt9nrr\nqOajnAI8YJ0ra2QwOJQ5nZ94J0NtPdW4
hFQ0N3On7ZW1OCaEkO6GAlMW9lR+e9aYNjU1o7CUOYXJ\nnsoHAE83bmtS9sgs3466PpHuhTOd38Y60ys37
uDY2St4mJWPo2fisHHXN50yHd0oFuPX35MY+yaP\nHSr/99WnlyeMjFr/rRUUlylNepRKpZyOT/0CvOV/Hx
cZDsV/shnZhcjJb1kHyh4tDevrB19PVwBA\naJAfzExbM/tLhZUqu0BJpVLEXuOuXwW4LY4JIaQ7osCURVn
yk6ZJBUVPyhmjMg72NrCx4nbQUVbL\nlLo+ke7O3ZWdma8+MP39BnOqO/NxEd5+70vcTOEWn9fGlYQ7jLaq
1lbmGBPROrppaWGO3j5ujHOU\nlY16UlaJMoUERTNTE/Tyaj3PxYmP0CA/xjmXriWjrKIa15IeMPYrtnU1N
zPlnJd0lztVD7SUqipQ\nsX6XXaaOEEK6IwpMWUxNTWBjZSHflkiknF7hquQWsKfxuaOlQGvBfZn8oidKSk
XR+lLSvXAy89UE\nSg2NYtzLyOHsF9U2YOd/j+PAyd/Q1KT9GlWpVMoZrRw/YgAszM0Y+/r6tz2dzx4tDfD
zgKkps4bp\nuEhmEtSVG3fw08U/GFPvHgJH+TICmcGsdaaqukApy/aXyS9+YtCtYAkhRBM6CUzDwsLA5/M5
f2bN\nmqXyHGXHf/XVV7q4Ha11NDM/t5DZitSHtb5UhpOZXyxEWSW7VBQFpqR7ac9U/t2H2Yx6v2w//fYH\
nNu85CGF5lVb3lPIgC3kKSUFGRjxMihrCOS4ksO3AlF2bNKi3F+eYoeF9YGvdOktSLarjBMaKywhk\nBrHW
maZn53OWEdXWNeB60n3Oe7a+3tihTnWEEGJIdBKYxsbGIi0tTf7n8uXL4PF4mDFjhtrzPvzw\nQ8Z5c+fO1
cXtaI3b/UmzH/bsUlHeHsoDU3dXB8ZatFJhJYpZnXIoMCXdTXum8pNYHY58PFxgbMz8\ncfQwKx/rdnyJ+4
+UF6vXBDsojBgQBGdHbnvYoN7ejH+TjwtKOTMlD1jBal9/b7CZmZpi1NAQxj7F\nQUxrK3NEDQvjnOfIt4W
fl4BxDrsL1NXEu2hobE0Qc3KwRS9vAeMYSoAihHR3Jm0f0jZnZ+YI4IED\nB2Bra4vnnntO7Xn29vYQCARq
j9GHjmbmc2qYuikPTM1MTSFwdmC0bbz7MJtxDAWmpLsROLf8wiUL\nxMoqqlHf0MiZNpdKpbh9jxl0zZ0+F
rbWVtj11QkIy1tnD6pFdfj86K+4n10KTzcneAqc4O7qBHdX\nR9jZWDFGHiUSCZ6UV6GgWIiCYiHyi4W4fS
+T8T5Tx0UovXdrKwv4egqQnVcs3/cg4zGGhgfJ70Nx\n5JXHAwL9PJVea9zwAfj50k2lr00YOZDzPGQGhwU
w3j/xTjrGKGT6K2b5A8DYyP4oLatCVm7rOXmF\nTxAW1Evp9QkhpDvQSWCqSCqV4sCBA5g9ezYsLbmJP4re
fvttrFq1Cr6+vliwYAEWLlwIIyP9L3vl\nTOVrUMtULG7iZOSzp+wVeQicGIFpHqsGIXV9It2NiYkx5xeuo
tIy+HkxE4sKS8oY/epNTY0R0scP\n5mameO/tpfj4mx8YI6pSKXDrTgZusWp3WluZw8PVCfZ21iguLUfRk3
K1ywMC/TwQ2Et5MAkAwQE+\njMDwvkJg+pA1je/j6QprhbXoinw9XeHv645HOYWM/aqWEcgMDg3E9z/Hy7d
lXaBMTU2Qk1+CjGzm\n9cZGhuNaIrM2KyVAEUK6O50HprGxscjJycFLL72k9rj169dj9OjRsLa2xuXLl7Fh
wwYIhUKsWbNG\n7Xnp6Zr1ktbm/DpRNUSi1lHSh4+ykJ6ufPRTpqCkDNXVrVP+fDsr5OeprodowmtivAdbR
dkTpKcb\nVotBbZ99T9cTnp+5iZTxfZ2QmAJxHfMXu8sJdxnHBPXywOOcbPn2XycMhL2VCc5eviUffVX2b0
Uk\nEqGkVPMOU/0DPdR+DazNme9z9WYKhvf3AwBcunqD8ZqTrbnaawX5uiDlHjOQHhjsh7InxSh7Uqz0\nH
KlUChMjCSqrW5YQiETAuYu/I6i3J05e+IPx/n383FFZVgqJuI6xP/V+OtLT/TnXNuTvvcDAwLYP\nIoT0GD
oPTPfv349BgwYhLIy7jkrR2rVr5X/v378/JBIJ3n///TYDU21+iKWnp2t0fkFZPS4mtJZ3\nMbewbvO8ksq
7sLZuHWkNCeqt9pwhwjokpGarfH1geChnSYE+afrsiHI95fmF9s1GTmFrLVLj/9/e\nncdHVd39A//cZbas
k2SSyUYSCFnZV0FWAXkEqwJqRahFELUqtlV5RKyl+jx9VEQp1SqKKPwopGrZ\nCiIurcgajCAKEoWwypZMM
tknme3e+/tjkiF3tmyTZCb5vl8vXu3ce+bOmesk+c455/s9yhC39/3h\nZ9/IflYmjxvh1iYzMxMTbhyOtz
Z+jAs/X5W1b4tRQ7Jx9+03+6wNHBefiH9+9o3zcWWtBYlJvRAa\nokbljkOyPowbNcznf8/EpF74d34hrE0
2Dfj1XdN9jtgCwPhRQ/DloetT9qXVFvxXWm+cvvix7PXv\nvPUmZGRkIDQiGh/s/tp5vM4quvWrp3z2CCHd
g18D09LSUnzyySd49dVXW/3cYcOGobq6GgaDAXFx\ncf7sVqu5Z+U3n/zU3I5PrlxrmTZFuz6RYOVaMuqqQ
T61bLZY3TLeB+e6j/ABQG5GKl7/0yPYs/9r\nKEPCcc3gWDt61VCOayXlsqCvUUSYxrkGNTEuGon6GPRKjH
XbMtWTyPBQJMfHOJfVSBJw+vxl9MtM\nxblL8ml0T4lPTYWGqHHXtLHI2/EVAGDcyP7NBqWAYzq/aWB69Ic
zyOrTS5aIFRaixohBmQAAvU4L\nnmed9ZOrqk2orav3WD+ZEEKCgV8D07y8PKhUKtx5552tfu6JEyegVqsR
GemeMdvZ3LPym09+cg1M\nvZWKauQrMKVdn0iwStD7Lhl18vRF2SYUep3WLZu/KZZlkZKocxvxkyQJxopqx
xKa2jrExkQiIS5G\nVqqpLXIzUmXrvX88cwkqpULW57iYSERrm18DfvvNozEwpw/qzRaPpaU8GZDdG0oF7w
y6S41V+PDj\nvbI240b2h1KhAHB9i+OmO0VdKTa2+PUIISTQ+C0wlSQJGzZswKxZsxAWJg/s1qxZg3fffRf
ffOOY\nJtu9ezcMBgNGjBgBjUaD/fv346WXXsK8efOgUqn81aU2cxsxrWl+xNQtI99Lcf1GoSFqREWGue34
\nBFBGPgleCS4jk8Wl5ZAkyflFyzUbf0i/9DZ9CWMYBrroSI+ln9ojO70XPt//rfNxYdFFaNTyLPqs\nZkZ
Lm/axd6/45hs20bgLVNNEr2KXUnI3jR4se5wU7xqYllFgSggJWn4LTPfv34+zZ89izZo1bueM\nRqNs8b1C
ocDatWvxhz/8AaIoIi0tDUuXLsWDDz7or+60S0RYCFiWgSg6Mi9MdRZYbTbnKIUrq82G\nkjL5Hw9fGfmNk
uN1ngPTCMrIJ8EpWhsOlZJ31ts01VlQVVMHbUQoJEnCMZfA1Ns0flfJdSm0f+5S\nMXiekx3L7uCgb2i/vm
4VCBqlpyYgNUm+1MnTFseEEBKs/Fabafz48aisrMSwYcPczi1duhSVldcT\nIqZMmYL9+/fj8uXLuHr1Kg4
dOoRHHnkEPO/3XKw2YRjGLfGoysd0/tUSo6yIdlxMpNdahU0lxXue\nzqcRUxKsGIZx35q0YZ3plRIjSpuU
iVIqeORmpHZq/5oTFRmO+Ngo52NBEPHjGflWpNl9U1yf5ldD\nXbYnbWrS6EFux5L0LjvJUWBKCAliXV80N
EC1ZlvSptNoQPOJT428japSYEqCWUJclOxxcUNJp2Mn\n5aOAuRkpUCk9z0J0pRwfgWd4qAZJPtaH+0NMVI
RsF6hGSgWP0UNz3Y572uKYEEKCFQWmXrRmW1K3\nrUhbGpjqKTAl3Y/r1HJjoPS9yy5MgTaN38hXYJqVntw
piYnDBriPmo4amuOxqH+iPlq2nWpZeRUs\nVltHdo8QQjoMBaZetCYz371UVPPrSwFfI6a0xpQEL9fSTNcM
5Y4yUWflZaKG9AvMwDS3r/fkpqw+\nLUt8aq9h/d3rjnqaxgeub3HcSJKuL58ghJBgQ4GpF62pZXrZtVRUY
stGTCPDQxDmYQTENSgmJJgk\nuqwxLTaU44dTF2Qll+Jjo1pUW7QrxMZooYuO8Hgup4UZ+e3VJyUBvZp8wU
1L1vusneo6Sn3pGq0z\nJYQEJwpMvXBNfqqs8TxiWm+2yPb9ZhjfNUqbYhjG46gpTeWTYOZal7S4rAJHTsi
3xAzU0dJGnqbz\nlQq+1eWf2ophGPz+gVkYPTQbY0f0w5MLZ/lcQuCaSEkJUISQYBUYafAByDU49DZi+v2P
8nVzCXHR\nXstKeZKoj8Gpc5edj2nXJxLsQkPUiAwPQVVNHQDAbhdx6OhJWZtAXV/aqF9GCvYX/CA71jct0
a10\nVEdKjtfh9wtmtbhtU1cpAYoQEqRoxNQL1+l0b+WiDh/7UfZ4SD/vpV48cV2PSrs+ke7AddS0sa4p\n
0FgmqmNLLrVXdrp7/5rbhrQrUckoQkh3QYGpF+67P7kHpharDcdOyguGjxqS3arXcR3poGl80h24\n1jJtq
l9maqtmFbpCfGyU289iIO+m5Lp86FppBex2oYt6QwghbUeBqReuI6YVVTWQmlbRh2N7RbPl\nelmWaG04Mt
KSWvU6OX1TEBl+fep+xMCsNvSWkMDiOmLaVKBP4wOONZ43jx3qfJyojw7oUd7GLY4b\nCYLothudq71fn8D
jf3oTf/rLhmbbEkJIZ6E1pl6oVUqoVQpn4Gm3izDVmxEWonG2+frYT7LnjBqc\n3eppeJVSgf958tf4z6Hv
oI/RYvKYIe3vPCFdLNFnYNqnE3vSdnfcPBrR2jAYjFWYOGpgwI/yum5x\nfLm4zGtJulJjJdb8YxfsdhEGY
xVeefsjvLzkASgU9CeBENK1aMTUB1+1TK02G47+IM80vqGV0/iN\n4mOjMfeOSZgydiitLyXdQoKXyhSJ+u
iALRPliuc53DR6MO75xQRZndBA5ZqZ7ysBav83P8jKd10u\nNmLLpwda/FqFRRfxtw07UG+2tL6jhBDiAwW
mPriVjGqSmX/8x/OyafyoyLCAXoNGSGfSx2jh6TvW\n4JzAn8YPVq6jo5e9JEBJkoR9BSfcjv/ri3ycv1Tc
7OvUmOrxxv/bgf0FP+CZ5e/j7MWrbeswIYR4\nQIGpD64JUE0z8w9/J5/Gv2FwFo12EtJAoeARF6N1Oz44w
OuXBjO3rWC9BKZnLlzFNYP7mlJRlPDW\nxp0+k6YkScLqjTtRXlkDACgurcCfVv0dxorqdvScEEKuo8DUB7
dapg2Z+TabHUdPnJadu2Fw26bx\nCemuXBOgVEoeOT62+yTtkxwv3
3HuaonRLWETgMfR0kY/XynFv77I93r+071HcPTEGdmx6RNHIibK\n805ZhBDSWhSY+uC+xtQxlX/i1HnU1V
udxyMjQgO6xiEhXcF1a9J+mWkBn0AUzFy3OLZY7Sgrr5K1\nsdnsOHS0UHYsUS//ArH1swO4eMXgdv0Ll4u
xcft/ZMcy0hLxy1vHt7frhBDiRIGpD261TBum8g+7\nZOPfMCgLLEu3kpCmBrlk348d3q+LetIzeNri+IpL
AtS3J8+gts7sfBweqsGy386Vlayz20W8velj\nCML1KX2zxYpV72+TJUyFaJT47fwZnbobFiGk+6NoygdPy
U92u4AjrtP4bczGJ6Q7G5TTB3NnTEJW\nn2TMvm0CbhyW29Vd6vZc15m6JkC5brM6ZnguoiLD8cA9t8iOn/
u5GDv/87Xz8fsffea2LvWhe2/1\nuI6YEELag4rW+eBpKv+H0xdgqrteIiUyPAQ5NI1PiBuGYXD7lFG4fcq
oru5Kj+FaMupKcRmyejmm\n6qtr63CsUL4+dPzIAQAca+RHD81G/rfXZ4P+
+ck+DB+YiXM/X8Per+XrUiePGYzRQ3M64i0QQno4\nCkx9cA1Mq6pNyP/2R9mxEYOywHE0lUUI6XquWxxfK
b4+lZ//baFsKj5RH40+KQnOx/Pv/i+cPH0R\n1bX1ABxT+n9dtw2GskqX14jBvDtv7ojuE0KIf6byX3rpJW
i1Wtm/zMxMn885efIkpk+fjvj4eOTk\n5GD58uUeM0i7UkRYiOxxdW0djhynbHxCSGByDUybZua7ZuOPHzl
AVuIuMjwU9981Vdbm5yulsnrN\nSgWP3y2YCZWSktgIIR3DbyOmGRkZ+Pjjj52PfY0iVldXY+bMmbjxxhvx
5ZdfoqioCI899hhCQkLw\n+OOP+6tL7cbzHCLCNM4RBEmCW+JAvwDeP5sQ0rPooiOhUvKwWO0AHMXwTXVmX
Ckuw5kL12Rtx43o\n7/b8G4fl4tC3hThyvMjtHADMu3MKUhLj/N9xQghp4LfAlOd56PX6FrX95z//ifr6eq
xevRoajQa5\nubk4ffo03nrrLSxatCigCtVrI8KcgamrEYMyaRqfEBIwGIZBQlwMLlwucR4rNlbh1KVyWbv
+manQ\nRUd6fP7Ce27BT2cuyb6EA45NRCaPGdIxHSeEkAZ+y8q/cOECsrOzMXDgQCxYsAAXLlzw2ragoACj
\nR4+GRqNxHps8eTKuXbuGixcv+qtLfhHpUjKqKZrGJ4QEmmSXBKji0grs/0aejd+Y9ORJVGQ4fu2y\nhjQ
2JhIPzZkeUIMGhJDuyS8jpsOHD8dbb72FjIwMlJWVYcWKFZg6dSoOHz6M6Ohot/YGgwGJiYmy\nY7Gxsc5z
aWlpXl+rqMjzFFNLtfb5dks9TCaT2/EQtRIq1tbu/gSTnvReOwLdv7aje9dyLOyy31mH\nvzuNKyXXSz0pe
A7RYbzPe5oQpcKYIX3xZf4JRGvDcPfU4bh25XKH9DcjI6NDrksICU5+CUxvvln+\n7Xr48OEYPHgw8vLysG
jRIn+8hFN7fokVFRW1+vl903/Gj+dL3I5PHDUQOdk9Z8S0LfeOXEf3r+3o\n3rVOuUnAviPXkzSvlFQgNPT
6zM/Y4bkY0L/5mrKZmZn47QO/7JA+EkKINx1SYD8sLAzZ2dk4d+6c\nx/NxcXEoLS2VHWt8HBcXWAvrXUtG
NRpFRfUJIQHIdfcnV+N8TOMTQkhX65DA1Gw2o6ioyGsy1MiR\nI5Gfnw+z+fri+j179iAhIQGpqakd0aU28
xSYhoaoMCCrdxf0hhBCfIvXRYHjPP9qj4oMw4CstM7t\nECGEtIJfAtPnnnsOBw4cwIULF3DkyBHMmzcPdX
V1uPfeewEAL7zwAm6//XZn+7vuugsajQaPPvoo\nCgsLsWPHDqxatQqPPvpowC2u13pIfho2IJP2hyaEBCS
e5xCvi/J4bszwflRJhBAS0PyyxvTq1atY\nuHAhjEYjdDodhg8fji++
+AIpKY4an8XFxTh//ryzfWRkJLZt24bFixfjpptuglarxWOPPeb39aj+\n4GnEdBRl4xNCAlhSfAyulBjdj
vvKxieEkEDgl8D0/fff93l+9erVbsf69euH3bt3+
+PlO1R0ZDh4\nnnVu5adRKzEwm6bxCSGBKyleB3wv36UuNTkOqUmBtYafEEJcdcga0+4kRKPCLRNGOB/fN3
MyFAq/\n7UtACCF+l6iPcTtGo6WEkGBAEVYL3DdzMsaPHIBQjcrjbimEEBJIeiXEyh4zDDB2eL8u6g0hhLQ
c\njZi2UGpSHAWlhJCg0CshFglx1xOgxgzv57X0HSGEBBIaMSWEkG6G5zksfuhu7Prya9SbavDg7Gld\n3S
VCCGkRCkwJIaSNWPMZMGIdBFVfgAvp6u7IJMfr8PCcW1FUVAS1StnV3SGEkBahwJQQQlpLkqCs\n2ALeVOB
4zChgDx0BW9hYSArfOy8RQgjxjgJTQghpDUmConLH9aAUACQb+NpD4GvzIWj6wxY+AaIq\npev6SAghQYoC
U0IIaQVF9edQ1B70clYCV38CXP0JCKresIdPgKDOcaTFE0IIaRYFpoQQ0kJ89V4o\nqv/Torac5Tw4y3mIf
Bys0XdBVKV1bOcIIaQboHJRhBDSAnztYSirdsmOSawGZv1vYYmeDVGR4PF5\nrN0AdelaMNZrndFNQggJaj
RiSgjpeUQLGHsZWHsZIAkQlSk+k5a4uu+grNgmP8goYdE9AFGZDCiT\nIYQMAWspgqJ6LzhLkbytZIW6bD3
q9Y8DHNUTJYQQbygwJcFPrAMj1EHiY2gtH5ET68BaLoG1l4K1\nl4KxlYK1l4ERKt2b8nEQNP0gaHIgKlMA
xjGhxNUXQmX8AIB0vTHDw6y7X57gxDAQ1ZmwqDPBWK9A\nUbMXfN13108LFVAZ/w5L7IMAQ796CSHEE/rtS
IKW44//PvB1xwEIEDQDYImZ6wwoSM/F2AwNn41v\nAcneouewdgPYGgMUNXsgsaGOAFWRAGXVbgBik5YcLD
G/gqju6/VakjIJ1pg5AKsBX5t//ZmW81BW\nbIc16k76EkUIIR5QYEqCiyR5nS7l6k+Arz0Ee/jYLuoc6VK
SBNZyHoqafeDMhe26FCOawJuOeDoD\nS8w9EDS5LbqOVXsbGJsBnOWs8xhvKoCoiKfPKSGEeECBKQkOkh1c
3XEoavaCtXlPIlFW7YagzqYi\n5z2JJIKrPwFFzT6w1kstfBIDiY+GyMcCkg2c5QIAodlnWaNmQggZ3PK+M
TwsMfdBY3gDjN3oPKys\n3AlRoYeozmj5tVpDsoE3HQNnLkScaAJjj4PER3bMaxFCiB9RYEoCm1gPvrYAit
oDYISq5ttLNigr\nNsMS+zBNlXZ3ogW86Yjjs9Ek6HMlcVEQ1OkQ+VhIfCxERWzDeuQmv/7EenDmU+DqC8G
ZT4ER692u\nY428FfawUa3vJxcCs24e1CVvgpEsjb2CyrgR5rhFkBSxrb+mN0IdFKZ88DWHwIg1AIAIyQS1
YTXM\ncY9QcEoICXgUmJKAxNgrwdceAF/7dZM/5u4EVR+IiiQoavc7j3GWc+BNh2EPG90ZXSU+MHYjWOsl\
niMpUSHyUfy4q1EDRsMsSI9Z5bSYqk2ELnwBB0x9gON/XZDUQQgY7RkMlO1jLBXD1PzqCVMkKW8RN\n7fo8
SYp4WGPmQFW2Ho1JVIxYD1XZepj1iwBW0+ZrAwBjL3esqTUdASSr+3mhHKrSd2GOewTguoa5\ntwAAIABJR
EFUQtv1WoQQ0pEoMCUBhbFebUha+R7ep1YZ+baPkgTWbgBnPuVsoazc5ZjS91cwRFqF\ntVyAomYvuPpCOA
IxDrbwMbBF3AywqjZdk7GVNnw2jvpMaBLUOQ2fjd5tGzVneIjqvhDVfWHDbW3q\nq8d+aXJgjZwGZdUnzmO
svRQqYx4suvmtT9qTJLDWS+Br9oGvPwFZ1QAPWLsB6rL3YI59sN2BMCGE\ndBQKTEnXkySwljNQVH/lXv+x
KUYJe+hw2MLGyteQMgysUbOgKX7t+miRZIWyfDMssQtpSr+zSCK4\n+pMNaz0vupwUnF84rNpfQNAMbNl/F
0mCWroCVdnBhiDXGw720KGwhY+HpNC35110KHv4BLC2Yke1\ngAac+RTUxa9C0ORC0ORCVKZ6H+FtMprLmw
t9LmEAo4TI6wBc/5lirZehKlsPi+4BgFX66V0RQoj/\n+CUwXblyJXbu3IkzZ85AqVRi+PDh+NOf/oTcXO+
ZqxcvXsSgQYPcjm/evBlTpkzxR7dIoHMmNO0D\na7vqvRkbBnv4GNhCRwNciOc2fBSs2ltlRdA5SxF40zew
h430cmEJXN0xKGoPghFMsEZOhRA6tF1v\nqUcSreDrjkJRs893oASAEaqgMm6CoP4GVu0Mz0lqkgTWdtkxl
V5/EsniGXD1nqefJVYDe9ho2MNu\nhMRF+OPddCyGgTX6TrD2MrDWn52HWXsZ2Jp9UNTsg8SGQFBnOwJVdR
YAsdn1r01JXARsYWNhD7sB\nYHjUVb6GUJQ7z3OW8456qrp5VE+VEBJw/PJb6cCBA3jggQcwdOhQSJKEF19
8ETNmzMDXX3+NqCjf\nU6lbtmxB//79nY+ba0+6AdEMvvbrhoDQvdC5sxkfC3v4eNhDhwKMotnL2kNHgas7
LivNo6j8GII6\nExKvlbVlbCVQVmyXtVWVfwCrJMAeNqINb8oDSQRX/wP4uu+hFyvB2CICejSvRUSLo0C9v
RSszQDG\nXgbOXARGNHl/DqMAJJvsEGc+DU3xa7BFTIQtYlLDsTMNwdePYIRqn92QuCjYwsfBHjqizUsDug
yj\ngEX3a6hL3vCY0MeIdeDrvm0YVW0cOW2+YoCoSIAtfDyEkEGygPMaeztilHtko9ic+RRUxn/AEjOn\n+
fW3hBDSifwSmG7dulX2+J133kFKSgoOHz6MadOm+XxudHQ09Pog/2NNWuR6QlMBGMnstZ2oSnMk\nrahzWz
cNzzCwRt8FTfFfnFP6jGSGsmILLLoFjmuJFiiq/w1FzQF4+mOvrNgMiVU6/ri3lWgBbzoK\nRe1+5whiuGS
CpuR1WKJmQQgd1vZrdzLWchF83TEwtpKGHZNaUBmhgaDOcqz1VPaCovo/UNTsh/ye\nC1BU/we8qQCMaHYL
Xj1pVUJTAJO4CJjjHoGyYkfD2mhvgWdzASkHQZ0BW9gYiOpMjz8vEqOAOXY+\n1IY1spkJrv4ElBVbYI26u
/XLXRrWt4rKXrRUhhDiVx0yj1NbWwtRFKHVaptte99998FsNiM9PR2P\nPvoo7rjjjo7oEulAjL0SrOUcvP
0RZSSAtZxtXUJTG0l8DKyRt0BZucN5jDOfAld3FGBUUFbu9DlK\n6yjj8wEsjBKCJqd1Ly7UQFGbD772kOd
scckGVfmHsFvOwRo1o0WjwF1GqIay8hPZWsiW4WAPHdKw\n1jPeedSmnQ576DAoK7aBs5yTPYMRapq5JgNB
nQ1b+HiIqvRuEwhJfDQssfc3lKo63TBa/FPzU/UN\nu1IJ6hwI6syWjRizITDHPgC14W2w9lLnYd50BBKjg
k17a8um9Z3riPeCtf4Mi24BBE12888jhJAW\nYiorK32ncrbB/fffj7Nnz+Krr74Cx3ke1TAajcjLy8OoUa
PA8zw+
+eQTvPbaa1i9ejXuuecer9cu\nKvKRHEM6FSNZES0dhlY6BqaZjGBvJPCoZnJRyQyFjWn+i0zLLiohSfwnN
Lg+OiSB8drHeiRCjWuy\n8xJ4XGFnwMwkN/tyCqkCWulbREiFYFow5QoAFuhQzN4KG9PM0hVJAod6iOAhMZ
2QrCKJiJSOI0Y6\nBBbuZYe8EaFCFTMAlcxgCEyYj+tLCJdOQSftAwcfpZ6gQB2TChP6oI5Jg8B4Xlvc7Ug
i1LiKUOkc\nwqRzUMDxJcqKaJiYPjAxfWBGfJu33eWlGiSLH4GH/MuACBXqmFTUMn1QhzSIjFp2npFsiJAK
oZWO\nOfsEAPXohSvcnW3qS6OMjA7aZIAQEpT8Hpg++
+yz2Lp1Kz799FOkpaW16rlPPfUU8vPzcejQIX92\nyamoqIh+CbaR7N5JErj641BWftyqqd2mJDYM9rAbYQ
sb3SF1FRlbGTQlf/E5PSxxWli1t0HQ9AdX\ndwyq8g8hK7nDKGGOe9gxXen2ZAmstbEk0o/y58lwEDS5qC8
7grBQ+ciWxKhgjb7LfdmAZAdruQiu\nvtCZeS0xalij7ujQZQCs5WcoK7b6TEQDWIh8dJNC9TqIfBxEZXLr
srzFeiiqPoei9hAa753EaSFo\ncmBX50BUpztHlHvsz60kOYvktyexy/X+MbYyqA2rndd2x0JQ9XZUCFD1A
Vd/0vssAACz/reO//6E\nEOIHfp3KX7p0KbZu3YqdO3e2OigFgGHDhmHTpk3+7FLwkyTwNV9BUZsPkY+FNW
pm67bblOxQVO4G\nX/89RF4Pe/iNrV+72QRjK21IGmrbyLUjoWkc7KHDOnQqW1LoYI2YCmXVLg9nOdjCxzu
SbhqmQYXQ\nobBKFllWPyQrVKXvwRz3m+vT0i5TmV5fn9XAHjoK9vAxkLgIXCrviyz+gGwalZEsUBk3wW45
D2vE\nFHCWs+DqT3rMvGYkM1TlH8Iq1MIeMaHN98UjoQ7Kqt3gTV97PC0qEmCLmARRkQCJj/ZPJjergS3q\
nDtjDxoC1XoSkiIeoSOw20/R+wTAdUmlAUuhgjl0IdenbXpYNiI7PYpPEQG8EdTYkBO9aX0JI4PFb\nYLpk
yRJs27YNO3fuRGZmZpuuceLECUqEcsHX7IOyajcAgBMqoTa8BXPsA5CUSc0/WTRDVfb/nH9g\nOKEanKWo1
dnugGMqT1H1KRTVe+FpnajEaSGo+/q4gAKCOrNdQXFr2cPHga8/IQsgBVU6rFEzPGbH\n28NGA6JFVgCdEe
ugLn0XZt1CcNYLzZZE8pYtbmV0MOsfh7JiS8Na2+v42kPga1s2S6Cs2gVGrIEt\n8tb230fRAt70DRTV//Y
4GiYxKtgip8IedmOHJRpJCh2E1nzRIn4hKRNg1v8eiup/g6v/EYxY24pn\ne15HTAgh/uCXwHTx4sX48MMP
sXHjRmi1WpSUlAAAQkNDERbmWG/2wgsv4OjRo9ixw5GUkpeXB4VC\ngYEDB4JlWXz66adYu3Ytnn/
+eX90qVtg63+SBUkAwIi1UBvehkU3D6KvQFCogbr0PY/Tsqy9FMqK\nLVBUfea9PqgkghEqwNhKwdoNSBF3
Q1Htaf2k+
+hjwGBYmHX3NyQ81cIeNgKCZpDPgM4eMRGMZIai\n+svrlxFqHMsCfBAVSbBFTICgGeA9iGPVsEbPgajqA2
XFDrSkBJAnipp9YIRaWKPvatvopVDdZEtP\nz4k29pDBsGl/ERy1QUmbSHwUrNF3A5II1nqpIfmqEKytxHN
7l1kAQgjpCH4JTNeuXQsAbhn1S5Ys\nwdKlSwEAxcXFOH/+vOz8q6+
+ikuXLoHjOKSnp+Nvf/ubz8SnnoSxlUBlzIOntYuMZIG69D1YYu6F\nEDLQ/bzdCHXp2uaLnYu1UFR9BkX1
HthDh0Fi1A01Kg1g7UbZto82mADI14L6Gn0MGFwYrDH3tuop\ntoj/AiOaWzSK2epscYaBPWw0RGUyVGUbw
QgVHptJbEhDgfUcgFFAadwERrI4z/N134IRTbDE/KrF\nXwgYm6FhP/Wj8BYUO5aLzICo7oFrOnsqhoWoSo
WoSoUN08DYjc7NDTjLBUi8FrawG2EPHRl4Xz4J\nId1Oh2TlB6qgSaIQ6qAxvNFsYAkwsEbNcExBNx6xXoW
67D23EjyishdEPraZkk3emUwmhIY6AlOJ\nC29IGvI9+hjUJAnK8o8c+7K7af1UpsfPnlgHVfkWcPUnHA/5
uCbbUqbIMq8Z6xWoS993S1gRlSkw\n6xZ43RELktiwb/0+cGYfW3oyClgjJsMePj7gdgMKmp/bANWu+ydJ3
fdnnBASkALrLxABJAEq4ya3\noNSq/YUjWJIl80hQVmwDI9TCFjEFrOU8VGXr3YrXC+os58iaLfIW8LUHoK
g9fH1f+RZjYAsbA1vk\nzQCradv7CxYNxfoh2cDXHwfQAVOZbAgsuvvA2MoAhoPEey8dJSmTYI57xPGlo8l
ng7X+DLXhLVhi\n5oKRLA07MpWBtRsalmEY4euLSOOWnrawGwGaniWuKCglhHQyCkwDjKLyY7eMd3vocNjD
xjVk6YZC\nVb4ZgHj9OdVfgLVdAWc+LZt+BwB7yBDHOrKGUTCJ18Km/QVsEZPB1xY4difysv2jxIY6ywKV1
dnB\nxk+BpIj17xsOZAwHa8xc2C0jwUg2CKq+HTKV2dIqC5JCh/q4R93WDrN2Q7NrYN2uFcxbehJCCOm2\n
KDANII37xzclKtNgjZrlHLkQQofDwoZCZdwoq9HJ1btP09rCxsGm/YXnUQ9WA3vEBNjDxzj2l7f+\nDIlRN
dSmjIXIx8qmhyuNRYjtSUFpI4ZxbPUYKLhwmON+I6u20BqispdjP/Ug39KTEEJI90SBaYBg\nzeegrNguOy
ZxWph197mt+RM0OTDHPghV2TqvWdXWyGmwh09sfiqO4SGEDoUQOrQ93SediVXDErsA\nKuMHzvWpvkhsGER
Vb8d+6qreND1LCCEkYFFg2hlEC1jLBVlWtYwkNOzt3mQtIKOEWTcP4MI9X1KV\n5lhzWPqey+5LLCzRd0II
HeG37pMAxChgiZnrqC1bs9+RWc3rHDsxKWIh8nHO/9/t1wMTQgjpNigw\n7SCMvRKc+ceG2oBn0NpMeEv0P
c0W0ZcU8TDHPQpV2XqwtmuObStj7oGg6deOnpOgwbCwaafDFjmt\n4TGNhBJCCAluFJj6iySBtV1uqP9X2M
x+477ZIm6GEDKgZS/LR8Gs/x1Y2zWIXJT3skGk+6KAlBBC\nSDfRowLTCPE4FBWFjjqRqt7+qdcomBy76Jg
KXKbU23g5zQDYIqa07kkMC7ElW5QSQgghhASwnhWY\nSiehqK2FovYgJEYNQZMFQZ0LQZMFsK0baWRsZVDU
7gdvOiLLjvdG4mMgKhJ9thGUybCHj6MRMEII\nIYT0SD0mMGWEaqhRgsZtNRnJDL7u+4adkFgIqt4Q1JmQF
HENiSNRHkdUWctFxy469T/A03ahTV4R\nojIVdk0uBE0OJD6OAk5CCCGEEB96TGDK1Rc2KUnvSgRnOetSF5
KFyEc7C8xLnBZ83XGw1gveX4RR\nQlBnwa7JgaDOBrgwv/WfEEIIIaS76zGBqT1kCK6xlUgLrQZX/xMYsba
ZZ4hg7WWAvQyc+UefLSVO\nC1v4WNhDRwKs2n+dJoQQQgjpQXpMYApWBROTDmt0BiCJYK2XGko5FYK1lbTp
kqIi0bGLTshA/yRS\nEUIIIYT0YD0zmmJYiKpUiKpU2DANjK0MnPkUWFsxGHsZWHup1/3jAUBQZ8EWPh6iq
i+tGyWEEEII\n8ZOeGZi6kBQ62BU6+UHR4ghQbaWO/7WXQ+LCYA8ZBkmZ0DUdJYQQQgjpxigw9YZVQVQmA8
rkVu7Z\nRAghhBBC2oLt6g4QQgghhBACUGBKCCGEEEICBAWmhBBCCCEkIPg1MF27di0GDhwIvV6PCRMm4NC
h\nQz7bHzhwABMmTIBer8egQYPw/vvv+7M7hBBCCCEkiPgtMN26dSueeeYZPPXUU9i3bx9GjhyJu++
+\nG5cuXfLY/sKFC/jlL3+JkSNHYt+
+fXjyySfx9NNP41//+pe/ukQIIYQQQoKI3wLTN998E3PmzMG8\nefOQlZWFFStWQK/Xex0FXbduHeLj47Fi
xQpkZWVh3rx5uPfee/G3v/3NX10ihBBCCCFBxC+BqdVq\nxXfffYdJkybJjk+aNAlff/21x+cUFBS4tZ88e
TKO
HTsGm83mj265ycjI6JDr9gR079qH7l/b0b1r\nH7p/hJBg4pfA1Gg0QhAExMbGyo7HxsbCYDB4fI7BYPDY3
m63w2g0+qNbhBBCCCEkiFBWPiGEEEII\nCQh+CUxjYmLAcRxKS0tlx0tLSxEXF+fxOXFxcR7b8zyPmJgYf3
SLEEIIIYQEEb8EpkqlEoMHD8ae\nPXtkx/fs2YMbbrjB43NGjhzpsf2QIUOgUCj80S1CCCGEEBJE/DaV/9h
jjyEvLw8bNmzAqVOnsGTJ\nEhQXF2P+/PkAgIcffhgPP/yws/38+fNx7do1PPPMMzh16hQ2bNiAvLw8LFq0
yF9dIoQQQgghQcRv\ngemsWbPw0ksvYcWKFRg3bhwOHz6Mjz76CCkpKQCAy5cv4/Lly872aWlp+Oijj3Do0
CGMGzcOr776\nKpYvX4477rjD62scPHgQs2fPRk5ODrRaLTZt2iQ7bzAY8MgjjyA7OxsJCQm48847cfbsWb
frHD16\nFDNmzEBSUhKSk5MxdepUWcJVZWUlHnroIaSkpCAlJQUPPfQQKisr23uLulR7793Fixeh1Wo9/nv
9\n9ded7SwWC/77v/8bffr0QWJiImbPno0rV6502vvsKP747JWUlOChhx5CZmYmEhISMGbMGHz00Uey\nNv
TZ83zvzp8/j7lz5yI9PR29evXC/fff75ZY2R3v3cqVK3HTTTehV69eSE9Pxz333IPCwkJZG0mS\n8NJLLyE
7Oxvx8fG49dZb8eOPP8ratOTenDx5EtOnT0d8fDxycnKwfPlySJLU4e+REEKa8mvy08KF\nC3HixAkYDAbs
3bsXY8aMcZ7btWsXdu3aJWs/duxY7Nu3DwaDAcePH8eCBQt8Xt9kMiE3Nxcvv/wy\nNBqN7JwkSZg7dy7On
TuHTZs2Yd+
+fejVqxfuuOMOmEwmZ7sjR45g5syZGDt2LL744gt89dVXWLRo\nEXiel72P48ePY/Pmzdi8eTOOHz8uG+0N
Ru29d8nJyTh16pTs32uvvQaGYXD77bc7r7V06VLs3LkT\n7733Hj755BPU1NTgnnvugSAInfp+/c0fn73f/
OY3OH36NPLy8pCfn4/Zs2fj4YcfxsGDB51t6LPn\nfu9MJhNmzpwJSZKwY8cOfPrpp7BarZg9ezZEUXReqz
veuwMHDuCBBx7AZ599hh07doDnecyYMQMV\nFRXONn/961/x5ptvYvny5fjyyy8RGxuLmTNnoqamxtmmuXt
TXV2NmTNnIi4uDl9+
+SVefvllvPHG\nG1RXmhDS6ZjKysqg/EqclJSEV155BXPnzgUAnDlzBsOHD8f+/fsxYMAAAIAoisjMzMSyZ
cvw61//\nGgAwdepUjBs3Dn/84x89XvfUqVO44YYb8Omnn2LUqFEAgPz8fEybNg3ffPNNt6gJ2NZ752rGjB
lg\nGAbbtm0DAFRVVaFv375488038ctf/hKAY6R8wIAB2Lx5MyZPntwJ767jtfX+JSUlYfny5fjVr37l\nv
Fb//v3x8MMP4/HHH6fPnpd79+WXX+LOO+/E+fPnodVqATg+a2lpadi2bRsmTpzYI+4dANTW1iIl\nJQWbNm
3CtGnTIEkSsrOz8eCDD2Lx4sUAgPr6emRkZOB///d/MX/
+/Bbdm/feew/PP/88Tp8+7fzy\nsGLFCrz//vsoLCwEwzBd9p4JIT1LtykXZbFYAABqtdp5jGVZqFQq5Ofn
A3Bk/RcUFECv1+OWW25B\n3759MW3aNOzdu9f5nIKCAoSFhcmStkaNGoXQ0FCvmwUEu5bcO1cXLlzA3r17c
f/99zuPfffdd7DZ\nbLKNE5KTk5GVldVt7x3Q8vs3atQobN+
+HeXl5RBFEbt27YLRaMSECRMA0Gevkeu9s1gsYBgGKpXK\n2UatVoNlWWebnnLvamtrIYqiM0C/ePEiSkpK
ZD9zGo0GN954o/N9t+TeFBQUYPTo0bIR7cmTJ+Pa\ntWu4ePFiZ7w1QggB0I0C08zMTCQnJ+N//ud/UFFRA
avVilWrVuHKlSsoKSkB4AimAOCll17C3Llz\nsWXLFowePRqzZs3CiRMnADjWu8XExMhGCBiGgU6n87pZQL
Bryb1ztWHDBuh0OkyfPt15zGAwgOM4\nt3JfvjZa6A5aev/WrVsHhmHQp08fxMXF4aGHHsLatWsxcOBAAPT
Z83bvRowYgbCwMCxbtgwmkwkm\nkwnPPfccBEFwtukp9+6ZZ57BgAEDMHLkSABwvn9fm5u05N542/Ck8Rwh
hHSWbhOYKhQKbNy4EefP\nn0fv3r2RkJCA/fv34+abbwbLOt5m43q0+fPn47777sOgQYOwbNkyDB06FOvWr
evK7neplty7pux2\nOzZt2oR7772XSnuh5ffvz3/+M4xGI/71r39hz549ePzxx/HII484vxT1RC25dzqdDu
vXr8cXX3yB\n5ORkpKSkoKqqCoMGDfL4+eyunn32WRw+fBh///vfwXFcV3eHEEI6BN98k+AxePBgHDhwAFV
VVbDZ\nbNDpdJg8eTKGDBkCANDr9QCArKws2fOysrKcFQPi4uJgNBohSZJzhEGSJJSVlXndLKA7aO7eNbV7
\n926UlJS4rT2Ni4uDIAgwGo3Q6XTO46WlpRg9enSHv4eu1Nz9O3/+PNasWSNbSzlgwADk5+djzZo1\neOO
NN+iz5+OzN2nSJHz33XcwGo3gOA5arRaZmZlIS0sD0P1/bpcuXYqtW7di586dzvcMXP+dVlpa\nil69ejmP
N93cpCX3xtuGJ43nCCGks3TL4YbIyEjodDqcPXsWx44dc043p6amIiEhAUVFRbL2Z8+e\ndf5SHzlyJGpra
1FQUOA8X1BQAJPJ5HWzgO7E271rasOGDRgzZgz69u0rOz548GAoFArZxglXrlxx\nJl/0BN7uX11dHQC4jX
RxHOccyafPXvOfvZiYGGi1WuzduxelpaWYNm0agO5975YsWYItW7Zgx44d\nyMzMlJ1LTU2FXq+X/cyZzWb
k5+c733dL7s3IkSORn58Ps9nsbLNnzx4kJCQgNTW1I98eIYTIcM88\n88zzXd2JlqqtrcVPP/2EkpIS/P3v
f0dubi4iIiJgtVoRGRmJ7du3w2AwQJIkHDx4EAsXLsT48ePx\n1FNPAXCsq2JZFn/961/Ru3dvKJVKvP/+
+/jwww+xatUq6PV66HQ6HDlyBJs3b8aAAQNw5coVPPHE\nExg6dGhQl55p771rdOnSJTz99NN47rnn0K9fP
9k5tVqN4uJirF27Fv369UNVVRWeeOIJRERE4IUX\nXgjqadf23r+oqChs2bIFBw8eRE5ODiwWCzZu3Ih169
Zh6dKlyMjIoM+ej8/exo0bYTabYbVa8fnn\nn2PRokVYsGAB7r77bgDotvdu8eLF+OCDD7B+/XokJyc719g
Cjh33GIaBIAhYtWoV0tPTIQgC/vCH\nP6CkpASrVq2CSqVq0b1JT0/HunXrcOLECWRkZCA/Px/Lli3D73//
+6AP7AkhwSWoykXt378ft912\nm9vxe+
+9F6tXr8bbb7+NN954AwaDAXq9HrNnz8bTTz8NpVIpa79q1SqsXbsW5eXlyM7OxrJlyzBx\n4kTn+crKSjz
99NPYvXs3AGDatGl45ZVXnJmwwchf9+7FF1/EmjVr8NNPP8kyqRtZLBY899xz2Lx5\nM8xmM8aPH4/XXnsN
ycnJHfbeOoM/7t/Zs2fx/PPP4/DhwzCZTOjduzcee+wxzJkzx9mGPnue793z\nzz+PvLw8VFRUICUlBfPnz
8djjz0mS+jpjvfOW9+XLFmCpUuXAnBMy7/88stYv349KisrMWzYMLz6\n6qvIzc11tm/JvTl58iQWL16Mb7
/9FlqtFvPnz8eSJUuoVBQhpFMFVWBKCCGEEEK6r+CdWyWEEEII\nId0KBaaEEEIIISQgUGBKCCGEEEICAgW
mhBBCCCEkIFBgSgghhBBCAgIFpoQQQgghJCBQYEoIIYQQ\nQgICBaaE+NFtt92G3r17o6yszO1cbW0t+vfv
jzFjxsBut3dB7wghhJDARoEpIX60atUq1NfX49ln\nn3U79+KLL+Lq1at4/fXXwfN8F/SOEEIICWwUmBLiR
+np6Vi8eDE++ugj7Nmzx3n8++
+/xzvvvIOF\nCxdi2LBhndafurq6TnstQgghpL0oMCXEz373u98hNzcXTzzxBOrr6yGKIp588knEx8fjj3/
8o7Nd\n4/7l/fr1Q1xcHIYMGYK//OUvEEVRdr2VK1di6tSp6NOnD/R6PcaMGYO8vDy3183MzMScOXPw73//
\nGxMnToRer8c777zT4e+XEEII8RemsrJS6upOENLdFBQU4JZbbsHvfvc7JCUlYfHixcjLy8P06dMB\nONa
b3nzzzTAYDJg/fz6SkpJQUFCADz74AAsXLsSKFSuc10pPT8eMGTOQlZUFQRDw8ccf4+DBg3jz\nzTcxd+5c
Z7vMzEyEh4ejrKwMCxYsQGpqKtLS0jBx4sTOfvuEEEJIm1BgSkgHWbx4MdavXw+NRoOb\nbroJGzZscJ77v
//7P6xevRr79+9H7969ncf//Oc/Y+XKlTh27BhSU1MBOKbjQ0JCnG0kScKtt96K\niooK5OfnO49nZmbCYD
Bg69atmDRpUie8Q0IIIcS/aCqfkA6ybNkyxMTEQJIkvPLKK7Jz27dvx5gx\nYxAREQGj0ej8N3HiRIiiiIM
HDzrbNgalNpsNFRUVKC8vx7hx4/DTTz/BbDbLrtunTx8KSgkhhAQt\nSg0mpINERESgb9+
+MBgMiI+Pdx6XJAlnz55FUVER0tPTPT63abmp7du3Y+XKlTh58iQEQZC1q6mp\ngVqtdj5OS0vz75sghBBC
OhEFpoR0MklyrJ6ZMmUKFi1a5LFNnz59AAB79+7F/fffj3HjxmHVqlWI\nj4+HQqHArl278O6777olSjUNU
gkhhJBgQ4EpIZ2MZVmkpKTAZDI1m5i0fft2REREYOvkUHdxAAAB\nUElEQVTWrVAoFM7jX3zxRQf3khBCCO
l8tMaUkC4wa9Ys5OfnY+/evW7nqqqqYLPZAAAcxwGAbAq/\nrKwMH3zwQed0lBBCCOlENGJKSBd48skn8fn
nn+Ouu+7CnDlzMGjQIJhMJhQWFmLHjh349ttvodfr\nccstt2Dt2rWYNWsW7rrrLpSXl2PdunVITEyE0Wjs
6rdBCCGE+BUFpoR0gbCwMOzevRsrV67E9u3b\n8Y9//APh4eHo27cvnnnmGURFRQFwrEN9/fXX8frrr2Pp0
qVITk7Gb3/7WygUCjz55JNd/C4IIYQQ\n/6I6poQQQgghJCDQGlNCCCGEEBIQKDAlhBBCCCEBgQJTQgghhB
ASECgwJYQQQgghAYECU0IIIYQQ\nEhAoMCWEEEIIIQGBAlNCCCGEEBIQKDAlhBBCCCEBgQJTQgghhBASECg
wJYQQQgghAeH/A/wIsbWv\nXhKIAAAAAElFTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc4cd21e128>"
]
},
"metadata": {},
}
],
"source": [
"# The next lines are provided for you. They create a table\n",
"# containing only the Alaska information and one containing\n",
"# only the Minnesota information.\n",
"ak = murder_rates.where('State', 'Alaska').drop('State',
'Population').relabeled(1, 'Murder rate in Alaska')\n",
"mn = murder_rates.where('State', 'Minnesota').drop('State',
'Population').relabeled(1, 'Murder rate in Minnesota')\n",
"\n",
"# Fill in this line to make a table like the one pictured above.\n",
"ak_mn = ak.join('Year',mn)\n",
"ak_mn.plot('Year')"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/backups/KrJ3GY\n",
"\n"
]
}
],
"source": [
"_ = ok.grade(\"q1_2\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"Now what about the murder rates of other states? Say, for example, California
and New York? Fill in the cell below to plot the murder rates of different pairs of
states. **Note:** this should use similar code to question 1.2, with only the
variable names changed. The cell below will not be graded, but it creates a cool
interactive module!"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "017e88419a9c4f0ca7bb392581615828",
"version_major": 2,
"version_minor": 0
},
"text/html": [
"<p>Failed to display Jupyter Widget of type
<code>interactive</code>.</p>\n",
"<p>\n",
" If you're reading this message in Jupyter Notebook or JupyterLab, it may
mean\n",
" that the widgets JavaScript is still loading. If this message persists,
it\n",
" likely means that the widgets JavaScript library is either not installed
or\n",
" not enabled. See the <a
href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
" Widgets Documentation</a> for setup instructions.\n",
"</p>\n",
"<p>\n",
" If you're reading this message in another notebook frontend (for example,
a static\n",
" rendering on GitHub or <a
href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
" it may mean that your frontend doesn't currently support widgets.\n",
"</p>\n"
],
"text/plain": [
"interactive(children=(Dropdown(description='state1', index=4,
options=('Alabama', 'Alaska', 'Arizona', 'Arkansas', 'California', 'Colorado',
'Connecticut', 'Delaware', 'Florida', 'Georgia', 'Hawaii', 'Idaho', 'Illinois',
'Indiana', 'Iowa', 'Kansas', 'Kentucky', 'Louisiana', 'Maine', 'Maryland',
'Massachuse', 'Michigan', 'Minnesota', 'Mississippi', 'Missouri', 'Montana',
'Nebraska', 'Nevada', 'New Hampshire', 'New Jersey', 'New Mexico', 'New York',
'North Carolina', 'North Dakota', 'Ohio', 'Oklahoma', 'Oregon', 'Pennsylvania',
'Rhode Isla', 'South Carolina', 'South Dakota', 'Tennessee', 'Texas', 'Utah',
'Vermont', 'Virginia', 'Washington', 'West Virginia', 'Wisconsin', 'Wyoming'),
value='California'), Dropdown(description='state2', index=31, options=('Alabama',
'Alaska', 'Arizona', 'Arkansas', 'California', 'Colorado', 'Connecticut',
'Delaware', 'Florida', 'Georgia', 'Hawaii', 'Idaho', 'Illinois', 'Indiana', 'Iowa',
'Kansas', 'Kentucky', 'Louisiana', 'Maine', 'Maryland', 'Massachuse', 'Michigan',
'Minnesota', 'Mississippi', 'Missouri', 'Montana', 'Nebraska', 'Nevada', 'New
Hampshire', 'New Jersey', 'New Mexico', 'New York', 'North Carolina', 'North
Dakota', 'Ohio', 'Oklahoma', 'Oregon', 'Pennsylvania', 'Rhode Isla', 'South
Carolina', 'South Dakota', 'Tennessee', 'Texas', 'Utah', 'Vermont', 'Virginia',
'Washington', 'West Virginia', 'Wisconsin', 'Wyoming'), value='New York'),
Output()), _dom_classes=('widget-interact',))"
]
},
"metadata": {},
}
],
"source": [
"# Compare the murder rates of any two states by filling in the blanks
below\n",
"\n",
"from ipywidgets import interact, interactive, fixed, interact_manual\n",
"import ipywidgets as widgets\n",
"\n",
"def state(state1, state2):\n",
" state1_table = murder_rates.where('State', state1).drop('State',
'Population').relabeled(1, 'Murder rate in {}'.format(state1))\n",
" state2_table = murder_rates.where('State', state2).drop('State',
'Population').relabeled(1, 'Murder rate in {}'.format(state2))\n",
" s1_s2 = state1_table.join('Year',state2_table)\n",
" s1_s2.plot('Year')\n",
" plots.show()\n",
"\n",
"states_array = murder_rates.group('State').column('State')\n",
"\n",
"_ = interact(state,\n",
"
state1=widgets.Dropdown(options=list(states_array),value='California'),\n",
" state2=widgets.Dropdown(options=list(states_array),value='New
York')\n",
" )"
]
},
{
"metadata": {},
"source": [
"##### A reminder about tests\n",
"The automated tests check for basic errors (like the number of rows in your
àk_mn` table, or whether you defined a function named `most_murderous` for the
next question), but they **aren't comprehensive**.\n",
"\n",
"If you're not sure that your answer is correct, think about how you can check
it. For example, if a table has the right number of rows and columns, and a few
randomly-selected values from each column are correct, then you can be somewhat
confident you've computed it correctly. For the previous question, try checking
some of the values in àk_mn` manually, by searching through the `murder_rates`
table."
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" <thead>\n",
" <tr>\n",
Rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
],
"text/plain": [
"Alaska | 1960 | 226,167 | 10.2\n",
"Alaska | 1961 | 234,000 | 11.5\n",
"Alaska | 1962 | 246,000 | 4.5\n",
"Alaska | 1963 | 248,000 | 6.5\n",
"Alaska | 1964 | 250,000 | 10.4\n",
"Alaska | 1965 | 253,000 | 6.3\n",
"Alaska | 1966 | 272,000 | 12.9\n",
"Alaska | 1967 | 272,000 | 9.6\n",
"Alaska | 1968 | 277,000 | 10.5\n",
"Alaska | 1969 | 282,000 | 10.6\n",
]
},
"metadata": {},
}
],
"source": [
"murder_rates"
]
},
{
"metadata": {},
"source": [
"**Question 1.3.** Implement the function `most_murderous`, which takes a year
(an integer) as its argument. It does two things:\n",
"1. It draws a horizontal bar chart of the 5 states that had the highest murder
rate in that year.\n",
"2. It returns an array of the names of these states in order of *increasing*
murder rate.\n",
"\n",
"Assume that the argument is a year in `murder_rates`. You do not need to check
that it is."
]
},
{
"metadata": {
"manual_problem_id": "murder_rates_3"
},
"outputs": [
{
"data": {
"text/plain": [
"array(['California', 'Mississippi', 'Texas', 'New York', 'Louisiana'], \n",
" dtype='<U14')"
]
},
"metadata": {},
},
{
"data": {
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAAewAAAEcCAYAAAAFuId5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAL
EgAACxIB0t1+/AAAIABJREFUeJzt3XlcTfn/B/BXUbbi2rqlFSUhWxLJiMiefcvYiWSZsUQx\nZRvZlyG7h
uxRKAxDQiFrljEziZRlCJksWVpuvz/8nK+rut3MrdvJ6/l4eDy653zO57w/N/e+OrtG\nSkpKFoiIiKhI01
R3AURERJQ3BjYREZEIMLCJiIhEgIFNREQkAgxsIiIiEWBgExERiQADm4iISAQY\n2ERERCLAwKZCFxcXp+4
SVIrjKdo4nqKN41EeA5uIiEgEGNhEREQiUCwDOzIyEhKJBMnJyTm+BoDD\nhw+jcePGqFy5Mtzd3Qu0nsTE
REgkEsTExBToeoiIqPgqkoH99OlTTJs2DQ0bNoSenh6srKzQu3dv\n/P7771/Vn52dHWJjY1GpUiVh2vjx4
+Hi4oKbN29iwYIFqio9R0ZGRoiNjYW1tXWBroeIiIqvkuou\n4EuJiYno0KEDdHR04Ovri3r16kEmk+H06d
OYNGkS/vjjj3z3qa2tDalUKrxOSUnBixcv0KZNG1Sr\nVu2ra01LS4O2tnae7UqUKCG3fiIiovwqclvYU6Z
MAQBERESgR48esLCwgKWlJdzc3BAVFQUAWL16\nNezt7VGtWjVYWVlh/PjxSElJybXPz3eJR0ZGwszMDADg
4uICiUSCyMhIAEBoaCjs7e2hp6eHunXr\nYsmSJcjK+t/TR62treHn5wcPDw+YmJhg1KhRwu7ugwcPonv37
jAwMICdnR0iIiKE5b7cJZ6ZmYlx\n48ahfv360NfXR+PGjbFy5UrIZDKVvpdERFR8FKnA/vfff3HixAmMHD
kSOjo62eZLJBIAgKamJvz8\n/HD+/Hls3LgRV65cgaenp1LrsLOzQ3R0NAAgMDAQsbGxsLOzw7Vr1zB06FB
06dIF586dg6+vL5Yv\nX44NGzbILb9mzRrUqlULp06dgo+PjzB93rx5GD16NKKiotCoUSMMHz4cb968ybEG
mUwGAwMDbNmy\nBRcuXMBPP/2EpUuXYvv27UqNgYiIvj1Fapd4fHw8srKyUKtWLYXtxo4dK/xsamqKOXPmw
NXVFevW\nrYOmpuK/QbS1tVG1alUAQMWKFYVd1f7+/mjRogW8vb0BAObm5rh79y5WrlyJ0aNHC8vb29tj4s
SJ\nwuvExEShpo4dOwIAfHx8sHv3bty8eRPNmzfPVoOWlhZmzJghN4br168jODgYgwcPVlg/ERF9m4pU\nY
H++
+1mR06dPY/ny5bh9+zZevXqFzMxMpKWlISkpCQYGBl+17tjYWDg7O8tNa968ORYuXIhXr16h\nfPnyAIBGj
RrluHzdunWFnz/V8OzZs1zXFxAQgMDAQDx48ADv379Heno6jI2NFdbYZdgMhfOJSHyW\new/N9zK82UjRpu
x4LCws8tVvkQrsmjVrQkNDA7dv3861zf3799GvXz8MHjwY3t7eqFSpEq5fv44R\nI0YgLS2tQOrS0NAQfi5
XrlyObbS0tLK1z+0PkJCQEHh5eWHu3Llo2rQpypcvj40bN+LQoUMK68ht\n3WKTmppabMYCcDxFXVEfT36/
tOPi4vK9TFHG8SivSAV2xYoV4eTkhI0bN2L06NHZjmOnpKQgJiYG\naWlp8PPzQ4kSJQAAR48e/c/rtrS0x
IULF+SmnT9/HoaGhtDV1f3P/X/Zr42NDdzc3IRp9+7dU+k6\niIioeClSJ50BEM7Mbt26NQ4cOIC4uDjcvn
0bmzdvhoODA2rWrAmZTIY1a9YgISEB+/btw7p16/7z\nej08PHD27Fn4+fnhzp07CAoKgr+/PyZMmKCCUck
zNzfHjRs3cPz4cdy9exeLFi3CuXPnVL4eIiIq\nPopcYJuZmeH06dNwdHSEr68vWrRoARcXF/z2229YsWIF
6tWrhwULFmDNmjVo1qwZAgMDMXfu3P+8\n3oYNG2LLli0ICwtD8+bNMXv2bPzwww9yW8GqMmzYMHTv3h0jR
45E69atcf/
+fXh4eKh8PUREVHxo\npKSkKHemF6ldv3Hz1V2CShT1Y4r5xfEUbUV9PHtWe+erPY/5Fm0FOZ4it4VNRERE
2TGwiYiIRICB\nTUREJAIMbCIiIhFgYBMREYkAA5uIiEgEGNhEREQiwMAmIiISAQY2ERGRCDCwiYiIRICBT
UREJAIM\nbCIiIhFgYBMREYkAA5uIiEgEGNhEREQiwMAmIiISAQY2ERGRCDCwiYiIRICBTUREJAIMbCIiIh
Fg\nYBMREYkAA5uIiEgEGNhEREQiwMAmIiISAQY2ERGRCDCwiYiIRICBTUREJAIMbCIiIhFgYBMREYlA\nS
XUXQMrbs9pb3SWoRFxcHCwsLNRdhspwPEVbcRsPfbu4hU1ERCQCDGwiIiIRKNKB7efnh+bNm6uk\nr86dO2
Pq1Kkq6UsikeDgwYMq6euTyMhISCQSJCcnq7RfIiIqHgo9sN3d3SGRSDBu3Lhs83x9fSGR\nSNCvXz8AwPj
x43H48GGVrHf79u3w8fFRSV+xsbHo0KGDSvr6xM7ODrGxsahUqZJK+yUiouJBLVvY\nRkZGOHDgAFJTU4Vp
GRkZ2L17N4yMjIRpOjo6KguwihUrQldXVyV9SaVSlCpVSiV9faKtrQ2pVAoN\nDQ2V9ktERMWDWgK7bt26q
FGjBvbv3y9MO3bsGEqVKgUHBwdh2pe7xG/dugUXFxcYGxvD0NAQLVq0\nwJkzZwAA6enp8PT0RO3ataGnp4
e6deti1qxZwrJf7hIPDQ2Fvb099PX1YWZmhk6dOuHp06cAgIcP\nH2LAgAEwMzODgYEBbG1tERwcLCz7+S7
xxMRESCQS7N27Fx06dIBUKoWtrS1OnjwptP+0u/vo0aNw\ncHCAVCpFq1atcO3atWxtuEuciIhyorbLugYN
GoQdO3bg++
+/B/Bxl/XAgQORkJCQ6zKjRo1CvXr1\nEB4ejpIlS+LWrVsoXbo0AGDdunU4fPgwNm/eDBMTE/zzzz+Ii4v
LsZ+kpCSMGDECPj4+cHFxQWpq\nKi5fvizMnzx5Mj58+ICwsDDo6urizp07eY7H19cXP//8M+rWrYuNGzfC
1dUVV69eRbVq1YQ2P/30\nExYsWAADAwMsXLgQ/fr1Q0xMDMqWLavMW0ZERN8wtZ101qdPH8TExODu3btIS
kpCeHg4XF1dFS7z\n4MEDODo6olatWqhRowa6du2Kpk2bCvNq1qwJe3t7GBsbw87OTvhj4EuPHz9Geno6un
XrBlNTU9Sp\nUweDBw+Gnp6e0FezZs1gbW0NMzMztG3bFm3btlVY2/Dhw9GjRw/UqlULCxcuhKGhIQICAuT
aTJ06\nFU5OTqhTpw78/f3x7t077Nu3T9m3jIiIvmFq28KWSCTo0qULtm/fjgoVKsDBwQHGxsYKlxk7diwm
\nTJiAXbt2oVWrVnBxcUGtWrUAAK6urujRowdsbGzQpk0btGvXDu3atYOmZva/SaytreHo6Ah7e3u0\nbt0
ajo6O6NatG6pUqQIAGDNmDCZNmoTw8HC0atUKXbp0QcOGDRXWZmtrK/ysqakJGxsb/P3333Jt\nPv1xAXw8
Pl+3bt1sbRTpMmyG0m2JSNyWew/NdV5uew/F6lsdT35v6KPWO519//33cHd3R7ly5eDt\nnfddvLy8vNC3b
18cP34cJ0+exMKFC7Fs2TIMGjQIDRs2xI0bN3Dy5EmcPn0a7u7uqFevHg4cOJAt\ntEuUKIH9+/fj0qVLOH
nyJLZt24bZs2fj8OHDsLa2xuDBg+Hk5ITjx4/j1KlTcHZ2xo8//ggvL6+C\neiuUUq5cObWuX1VSU1OLzVg
AjqeoE+t4cvsyL253buN4lKfW67BbtWoFLS0tJCcno3PnzkotU7Nm\nTYwZMwZBQUEYNGgQtm3bJszT1dVF
t27dsGzZMgQFBeHMmTOIj4/PsR8NDQ00bdoU06dPR0REBAwM\nDOROgjM0NMTQoUOxZcsWeHt7Y+vWrQrr+
vwYeFZWFq5evQpLS0u5NpcuXRJ+Tk1NxZ9//pmtDRER\nUU7UuoWtoaGBs2fPIisrK8/LpN69e4effvoJ3b
p1g4mJCZ49e4bo6GjY2NgAAFavXg19fX1YW1tD\nS0sLe/fuRfny5eVO+vrk0qVLOHXqFJycnFC1alXcuHE
Djx49EsJz2rRpaNeuHczNzfHq1SucOHEi\nz2ANCAiAubk56tSpg02bNuHBgwcYPny4XJslS5agSpUq0NfX
x6JFi6CtrY3evXvn5y0jIqJvlNof\n/qHstdElSpRASkoKxo4di6SkJFSqVAnt27fH3LlzhX5+
+eUXxMfHQ0NDA9bW1ti7d2+OZ2CXL18e\nFy5cwIYNG/Dy5UsYGhpi6tSpwg1bZDIZPD098ejRI+jo6KBVq
1aYN2+ewvp8fX3h7+
+P69evw9jY\nGNu3b4ehoWG2NjNmzMCdO3dQu3Zt7NmzR5S76oiIqPBppKSkZKm7CDFLTExEgwYNEBERgUa
NGuXY\nJjIyEl27dsXdu3dRuXLlr15Xv3Hzv3rZokSsxxRzw/EUbWIdT25P5+Mx36Kt2B7DJiIiIuUwsImI
\niERA7cewxc7U1BQpKSkK27Rs2TLPNkRERIpwC5uIiEgEGNhEREQiwMAmIiISAQY2ERGRCDCwiYiI\nRIC
BTUREJAIMbCIiIhFgYBMREYkAA5uIiEgEGNhEREQiwMAmIiISAQY2ERGRCDCwiYiIRICBTURE\nJAIMbCIi
IhFgYBMREYkAA5uIiEgEGNhEREQiwMAmIiISAQY2ERGRCDCwiYiIRICBTUREJAIMbCIi\nIhFgYBMREYkAA
5uIiEgEGNhEREQiUFLdBZDy9qz2VncJKhEXFwcLCwt1l6EyHE/RVtzGQ98ubmET\nERGJAAObiIhIBBjYRE
REIsDAJiIiEoFv7qQziUSicP6AAQOwdu3aQqqGiIhIOd9cYMfGxgo/Hzt2\nDBMmTJCbVrp0aXWURUREpNA
3t0tcKpUK/ypUqJDrtPv372PIkCEwMTGBmZkZ+vfvj4SEBACATCZD\nx44d0adPH6Hfly9fon79+pgxYwYA
4MOHDxg7diysra2hr68PGxsb+Pv7IysrS1jm+vXr6Ny5M4yM\njGBkZISWLVvi/PnzhfROEBGRmOQ7sP/44
w9s2LABCxYsQFJSEgAgPj4er1+/Vnlx6vL69Wt06dIF\nEokEv/32G44dO4YKFSqgR48e+PDhAzQ1NbFhww
ZcvHgR69evBwBMnjwZ5cuXh6+vLwAgIyMDJiYm\nCAwMRHR0NLy8vODn54e9e/cK6xk2bBhMTU0RERGBM2f
OYMqUKShVqpRaxkxEREWb0rvEP3z4ADc3\nN4SFhSErKwsaGhro0KEDpFIpfHx8YG5ujlmzZhVgqYVnz549
KFeuHFauXClMW716NapXr47w8HB0\n6tQJxsbGWLZsGTw8PPD06VMcPnwYERER0NbWBgCUK1cO06dPF5Y3M
zPD5cuXERwcjL59+yIrKwuP\nHj1C27ZthZs61KhRQ2FdXYbNKIDREhHl33LvoSrrKy4uTmV9FQXKjie/N/
RROrDnzp2LU6dOYf36\n9WjdurXcitq1a4dNmzYVm8C+du0abt++DUNDQ7npb9+
+xb1794TXvXr1wpEjR7B06VIsXLgQtWvX\nlmu/fv167Ny5Ew8fPsT79+
+Rnp4Oc3NzAICGhgbGjh0LNzc3BAYG4rvvvkO3bt1Qs2bNXOsqV66c\nCkepPqmpqcVmLADHU9RxPAVDVXe
PK253oivI8Sgd2MHBwZg5cyb69OmDzMxMuXmmpqa4f/+
+yotT\nF5lMhiZNmuR4tnilSpWEn1NTU3Ht2jWUKFEC8fHxcu127tyJWbNm4eeff4aNjQ10dXWxZs0anD59
\nWmjj6+sLV1dX/P7774iIiICfnx/8/f3Rt2/fghscERGJktKB/eLFC9SqVSvHeTKZDGlpaSorSt0a\nNGi
AY8eOoWrVqtDV1c21nZeXF0qWLIng4GD07t0bzs7OcHJyAgBER0ejefPmGD58uND+7t272fqw\nsLCAhYUF
PDw8MHbsWGzbto2BTURE2Sh90pmpqSkuXbqU47wrV64Iu3qLgwEDBkBHRwcDBw7EuXPn\nkJCQgKioKEybN
k3Yk3Do0CHs3r0bGzZsgKOjI3788Ud4eHggOTkZAGBubo7Lly8jIiICd+7cwbx5\n83DlyhVhHS9fvoSnpy
eioqJw//59XLhwAZcuXcq2W52IiAjIR2D3798fK1asQFBQENLT0wF8PA57\n5swZrFmzBt9//32BFVnYypc
vj6NHj0JfXx+DBg2CnZ0dPDw88O7dO5QvXx5PnjzBxIkTMWPGDDRo\n0AAAMG3aNBgbG2P8+PEAADc3N3Tq
1AlDhgyBk5MTnj9/Djc3N2EdWlpaeP78OcaMGYMmTZpg6NCh\naNmyZbE5D4CIiFRLIyUlJSvvZkBmZiZGj
RqF/fv3o1SpUvjw4QPKlCmD9+/fo1evXti4cWNB1/rN\n6zduvrpLUImictKMqnA8RRvHUzBU9bhfnnSmPK
WPYZcoUQIBAQEYOXIkTp48iWfPnqFSpUpwcnKC\ng4NDgRRHREREHykd2A8ePIC+vj7s7e1hb28vNy8jIwO
PHz+GsbGxygskIiKifBzDbtCgAW7cuJHj\nvD/+
+EM4lktERESqp3Rgf34P7C+lp6dDU/Obuy05ERFRoVG4SzwlJQUpKSnC63/+
+QeVK1eWa/Pu\n3Tvs2rULUqm0YCokIiIixYG9bt06LFy4EBoaGtDQ0MCQIUNybJeVlQUvL68CKZCIiIjyC
OzOnTvD\nxMQEWVlZGDduHKZMmYLq1avLtSlVqhQsLS1Rr169Ai2UiIjoW6YwsK2trWFtbQ0AwtO5Pr+XNh
ER\nERUOpS/rcnV1Lcg6iIiISAGlAxsA/vrrLwQGBuLOnTt4//693DwNDQ2EhoaqtDgiIiL6SOnAvnz5\ns
nBM+
+7du6hbty5SUlLw8OFDGBoaZju2TURERKqj9MXTc+bMQdeuXREdHY2srCysWrUKN2/exIED\nB5CZmYkpU6
YUZJ1ERETfNKUD+9atW+jbty80NDQAfHwGNgC0atUKU6ZMwZw5cwqmQiIiIlI+sNPT\n01G2bFloamqiYsW
KePLkiTDP3Nwcf/31V4EUSERERPkI7OrVq+Px48cAgLp162L79u2QyWSQyWTY\nsWMH9PT0CqxIIiKib53S
gd2hQwdERUUBACZPnowTJ07A2NgYZmZm2LdvHzw8PAqsSCIiom+d0meJ\nf37rUUdHRxw/fhxhYWF4+/Yt2
rZtizZt2hRIgURERJTP67A/16BBAz5Sk4iIqJAovUu8UqVKuHLl\nSo7zrl27xluWEhERFSCVPA87MzNTuN
yLiIiIVC/PXeIymUwI609nhX/u3bt3OH78eLbnZBMREZHq\nKAzsBQsWYNGiRQA+3iu8ffv2ubYdMWKEais
jIiIigcLAdnBwAPBxd/iiRYswaNAgVKtWTa7Np+dh\nd+jQoeCqJCIi+sblGdifQltDQwNDhgyBgYFBoRRG
RERE/6P0ZV3Tp0+Xe/3y5UvEx8dDT08PhoaG\nKi+MiIiI/kfhWeLh4eGYNWtWtulLliyBhYUFnJycYG1tj
ZEjRyIjI6OgaiQiIvrmKdzCDggIyHa5\nVkREBH7+
+WfUqVMHgwcPxu3bt/Hrr7+iQYMGGD9+fIEWS0RE9K1SGNg3btzA1KlT5abt2LEDpUuX\nRkhICKRSqTB93
759DGwiIqICojCwnz9/jurVq8tNi4iIQLNmzeTC2tnZGXv27CmYCkmwZ7W3uktQ\nibi4OFhYWKi7DJXheI
o2joeKC4XHsHV0dPD27Vvh9d27d/HixQs0adJErp2uri4yMzMLpkIiIiJS\nHNgWFhY4cuSI8PrIkSPQ0ND
I9mSuxMREVK1atWAqJCIiIsW7xMeOHYtBgwbh33//hZ6eHnbu3Ik6\ndeqgWbNmcu2OHz+OevXqFWihRERE
3zKFW9hdunSBn58frl69it27d6NJkybYunWr3JnjSUlJOHXq\nFJydnQu82OKmTp06WLNmjbrLICIiEcjza
V1jxozBH3/8gYcPHyI0NBQ1a9aUmy+VShEfH4+hQ4eq\nrCh3d3dIJBLhPuafREZGQiKRIDk5WWXrUmTevH
mwsrJCSkqK3PS///4bUqkUISEhhVIHERGR0o/X\nLGylS5fGqlWr8Pz5c7XVMG3aNFStWlXu0raMjAy4u7u
ja9eu6Nmz51f1m5aWpqoSiYjoG1FkA7tl\ny5YwNjbOtpX9pb///ht9+/aFkZERzM3NMWLECCQlJQEAbt+
+DYlEIrx+
+/Yt9PT00KtXL2H5wMBA\nNGrUKMe+tbS0sH79eoSFheHgwYMAgGXLliEpKQlLliwR2t28eRNdu3aFvr4+q
levDg8PD7x69UqY\n7+bmBldXVyxduhRWVlawtrbOcX07d+6EiYkJfv/9dyXeISIi+pYU2cDW1NTErFmz8O
uvv+LevXs5\ntnny5Ak6deoEKysrhIeH48CBA3jz5g1cXV0hk8lQq1YtSKVSREVFAQAuXrwIXV1dXLhwQbi
ValRU\nlPCAk5xYWVlh5syZmDx5Mk6ePIklS5Zg9erVkEgkAIA3b96gV69ekEgkCA8PR2BgIM6dO4eJEyfK
\n9XPmzBncvn0bISEh2L9/f7b1rF69Gt7e3tizZw/PByAiomyUfviHOjg7O8POzg5z585FQEBAtvmb\nN29
GvXr1MHv2bGHa+vXrYWZmhpiYGNjY2KBFixaIjIxEr169EBUVhW7duuH48eO4evUqmjZtirNn\nz8LHx0dh
HR4eHvjtt9/Qu3dvDB8+XO6ytj179iAtLQ3r1q1DuXLlAADLly9H9+7d4evrCzMzMwBA\n2bJlsWrVKmhra
2frf/bs2di5cycOHTqk8Gz7LsNmKKyTiKioWO49VOm2cXFxBVeIGig7nvzeAKdI\nBzbwMczatWuHCRMmZJ
t3/fp1nDt3Lsenhd27dw82NjZwcHAQzsSOiorC6NGj8e7dO0RFRaFKlSp4\n9OiRwi1s4OOjRadOnYru3bt
nu1VrbGws6tWrJ4Q1ANjZ2QH4uEv+U2DXqVMnx7D29/dHamoqIiIi\nst1V7kufr0PMUlNTi81YAI6nqON4
1EPZMCpud24ryPEU2V3in9jY2MDFxSXHrWCZTAZnZ2dERkbK\n/bt69Srat28P4OMzve/cuYP4+HjExMQIz
/iOjIxEVFQUqlevrtTjQUuUKAEAKFlS+b9xPr/8rWzZ\nsjm2ad68OWQyGc84JyIihYr8FjYA+Pj4wM7ODu
Hh4XLTGzRogP3798PY2BhaWlo5LvvpOPaSJUtQ\nvXp1VK1aFQ4ODpg6dSokEkmeW9d5sbS0RFBQkNxfvRc
uXBDWnZfGjRtj9OjR6NWrFzQ0NDBp0qT/\nVA8RERVPRX4LGwBq1KiBoUOHYt26dXLTR44ciVevXmHYsGG4
fPkyEhIScOrUKUycOBGvX78W2rVo\n0QJBQUFo2bIlAMDU1BSVK1dGWFjYfw7sfv36QVtbG+7u7vjzzz8RG
RmJH3/8ET169ICpqalSfdja\n2iI4OBgrVqzA8uXL/1M9RERUPIkisAHA09Mz2+5oAwMDHDt2DJqamujVqx
eaNWuGKVOmQFtbG6VK\nlRLaOTg4ICMjQy6cc5r2NXR0dBAcHIx///0Xbdq0waBBg2Bvb4+VK1fmqx9bW1v
s27cPy5YtY2gT\nEVE2GikpKVnqLoKU02/cfHWXoBJiOWlGWRxP0cbxqIeyjwPmSWfKE80WNhER0beMgU1E
RCQCD
Gwi\nIiIRYGATERGJAAObiIhIBBjYREREIsDAJiIiEgEGNhERkQgwsImIiESAgU1ERCQCDGwiIiIRYGAT\n
ERGJAAObiIhIBBjYREREIsDAJiIiEgEGNhERkQgwsImIiESAgU1ERCQCDGwiIiIRYGATERGJAAOb\niIhIB
BjYREREIsDAJiIiEgEGNhERkQgwsImIiESAgU1ERCQCDGwiIiIRYGATERGJAAObiIhIBEqq\nuwBS3p7V3u
ouQSXi4uJgYWGh7jJUhuMp2jgeKi64hU1ERCQCDGwiIiIR+OYCe8eOHTA0NFS6vUQi\nwcGDBwuwIiIiorw
VuWPY7u7uePHiBfbs2VMg/ffs2RPOzs5Kt4+NjYVEIimQWoiIiJRV5AK7oJUp\nUwZlypRRur1UKi3AaoiI
iJQjql3iDx48wMCBA2FkZAQjIyN8//33ePTokTDfz88PzZs3l1vmy13g\nX75+
+PAhBgwYADMzMxgYGMDW1hbBwcHC/C93ic+aNQtNmjSBvr4+rK2t4ePjg/fv32erITg4GA0b\nNoSRkRFcX
V2RnJwstLl69Sp69OiBGjVqwNjYGB06dMDFixdV8yYREVGxJJrAlslkcHV1xbNnzxAW\nFoawsDA8efIEAw
cORFZW1lf3O3nyZLx79w5hYWE4f/48/Pz8UKFChVzbly1bFqtXr8aFCxewdOlS\nhISEYMmSJXJt7t+/j5C
QEGzfvh0hISG4ceMG5s6dK8x//fo1+vXrh99++w3h4eGwtrZGnz598OLF\ni68eBxERFW+i2SV+
+vRp3Lp1CzExMTA1NQUAbNq0CY0aNcLp06fh6Oj4Vf0+ePAALi4usLa2BgCY\nmZkpbO/p6Sn8bGpqikmTJ
mHVqlWYOXOmMD0jIwNr1qwRgn/o0KHYsWOHML9Vq1ZyfS5atAihoaE4\nfvw4+vXrl+u6uwybofS4iIio4C
z3HprrvLi4OKX6yO/19KIJ7NjYWBgYGAhhDUDYjf33339/dWCP\nGTMGkyZNQnh4OFq1aoUuXbqgYcOGubY
/ePAg1q5di/j4eKSmpiIzMxOZmZlybYyNjeW20vX19fH8\n+XPh9bNnz/Dzzz8jMjISz549Q2ZmJt69e4eH
Dx8qrLVcuXJfNcaiJjU1tdiMBeB4ijqOp2gT63hy\nC9uCvLGNaHaJK6KhoQEA0NTUzLZ7PCMjQ+GygwcPx
vXr1zFw4EDcuXMHzs7O8PPzy7HtpUuXMHz4\ncLRp0wa7d+/GmTNnMGPGDKSnp8u109LSylafTCYTXru7u+
Pq1auYP38+jh07hsjISFSrVg1paWlK\nj5mIiL4cUZLsAAAUmUlEQVQtoglsS0tLPH78GImJicK0hIQEPH7
8GLVr1wYAVKlSBU+fPpUL7Zs3\nb+bZt6GhIYYOHYotW7bA29sbW7duzbFddHQ0DAwM4OnpicaNG6NmzZp4
8OBBvscSHR0NNzc3tG/f\nHlZWVtDR0UFSUlK+
+yEiom9Hkdwl/urVK9y4cUNuWvXq1VG3bl24ublhwYIFAD4eT27QoAG++
+47\nAICDgwP+/fdfLF26FL169UJkZGSeNz2ZNm0a2rVrB3Nzc7x69QonTpyApaVljm3Nzc3x+PFjBAUF\n
oWnTpggPD5c7o1xZNWvWRFBQEJo0aYK3b9/Cx8cH2tra+e6HiIi+HUVyC/v8+fP47rvv5P75+Phg\n586dq
Fy5Mrp27YquXbtCT08PO3bsEHaJW1paYtmyZdiyZQtatGiBU6dOYdKkSQrXJZPJ4OnpCTs7\nO/To0QN6en
pYu3Ztjm07duyICRMmwMvLCy1atEBERAS8vfP/QI7Vq1cjNTUVjo6OGD58OL7//nuY\nmJjkux8iIvp2aKS
kpHz9NVFUqPqNm6/uElRCrCeZ5IbjKdo4nqJNrOPJ7emJPOmMiIjoG8fAJiIi\nEgEGNhERkQgwsImIiESA
gU1ERCQCDGwiIiIRYGATERGJAAObiIhIBBjYREREIsDAJiIiEgEGNhER\nkQgwsImIiESAgU1ERCQCDGwiI
iIRYGATERGJAAObiIhIBBjYREREIsDAJiIiEgEGNhERkQgwsImI\niESAgU1ERCQCDGwiIiIRYGATERGJAA
ObiIhIBBjYREREIsDAJiIiEgEGNhERkQgwsImIiESAgU1E\nRCQCGikpKVnqLoK+LXFxcbCwsFB3GSrD8RR
tHE/RxvEoj1vYREREIsDAJiIiEgEGNhERkQgwsImI\niESAgU1ERCQCDGwiIiIRYGATERGJAAObiIhIBHjj
FCIiIhHgFjYREZEIMLCJiIhEgIFNREQkAgxs\nIiIiEWBgExERiQADuwjYtGkT6tevD6lUilatWuHcuXMK2
0dFRaFVq1aQSqVo0KABAgICCqlSxZYt\nW4bWrVvD2NgYNWvWRL9+/fDnn38qXCYxMRESiSTbvxMnThRS1b
nz8/PLVletWrUULnPr1i106tQJ\n+vr6sLKywsKFC5GVVTQuxLC2ts7xve7bt2+uy+TUXl3/386ePYv+/fv
DysoKEokEO3bskJuflZUF\nPz8/1K5dG/r6+ujcuTP+
+uuvPPs9ePAg7OzsoKenBzs7O4SFhRXUEOQoGk96ejp8fX1hb2+PatWq\nwdLSEiNHjsSDBw8U9hkZGZnj7
+z27dsFPZw8fz/u7u7Z6mrbtm2e/arr+y6v8eT0PkskEkyZMiXX\nPv/r913J/zQi+s9CQkIwffp0LF26FM
2aNcOmTZvQp08fREdHw9jYOFv7hIQE9O3bFwMHDsSGDRsQ\nHR2NyZMno3LlyujWrZsaRvA/UVFRGDFiBBo
3boysrCzMnz8f3bt3x4ULF1CxYkWFywYHB6NevXrC\n67zaFxYLCwscOnRIeF2iRIlc27569Qo9evSAvb09
Tp48ibi4OHh4eKBs2bIYP358YZSrUEREBDIz\nM4XXT548gaOjI7p3765wuV9+
+QXt27cXXpcvX77AalQkNTUVderUwYABAzBmzJhs81euXAl/f3/4\n+/vDwsICixYtQo8ePXDp0iXo6urm2
OfFixcxfPhweHl5oWvXrggLC8PQoUNx7NgxNGnSRG3jefv2\nLa5fv44pU6bA2toar169wsyZM9G7d2+cPX
sWJUsq/uqOjo6W+wxVqVKlQMbwubx+PwDg6OiI9evX\nC6+1tbUV9qnO77u8xhMbGyv3OiYmBv3798/z8wR
8/fcdA1vN/P394erqiiFDhgAAFi9ejPDwcAQE\nBMDX1zdb+19//RX6+vpYvHgxAMDS0hKXL1/G6tWr1R7Y
ISEhcq/Xr18PExMTREdHo2PHjgqXrVSp\nEqRSaUGW91VKliypdF179+7Fu3fvsHbtWpQpUwZ16tTB7du3s
WbNGowbNw4aGhoFXK1iX35pb9u2\nDbq6uujRo4fC5SpUqFAkfjfOzs5wdnYGAIwdO1ZuXlZWFtauXYsffv
hB+BysXbsWFhYW2LdvH4YN\nG5Zjn2vXrkXLli2FrSJLS0tERkZi7dq12Lx5cwGORvF4KlSogAMHDshNW75
8OZo1a4bY2FjUrVtX\nYd9Vq1ZF5cqVVVtwHhSN55NSpUrl6/+SOr/v8hrPl+M4cuQIzM3N4eDgkGffX/t9
x13iapSWloZr\n166hTZs2ctPbtGmDCxcu5LjMxYsXs7V3cnJCTEwM0tPTC6zWr/HmzRvIZDJIJJI82w4aN
Ajm5uZo\n3749Dh48WAjVKSchIQG1a9dG/fr1MXz4cCQkJOTa9uLFi2jevDnKlCkjTHNycsLjx4+RmJhYCN
Uq\nLysrC9u2bUO/fv3k6s3J9OnTUaNGDbRu3RoBAQGQyWSFVKXyEhMTkZSUJPfZKFOmDOzt7XP9LAHA\np
UuXcvw8KVpGXV6/fg0ASn2eHB0dYWlpCRcXF5w5c6agS1Pa+fPnYW5uDhsbG0yYMAHPnj1T2F4s\n33dv3r
xBSEiIsOGVl6/9vmNgq1FycjIyMzNRtWpVuelVq1bF06dPc1zm6dOnObbPyMhAcnJygdX6\nNaZPnw5ra2s
0bdo01zY6OjqYO3cufv31V+zduxffffcdhg0bhj179hRipTlr0qQJ1qxZg3379uGX\nX35BUlISnJ2d8eLF
ixzb5/a7+TSvKImIiEBiYiIGDx6ssJ23tzcCAgJw4MAB9OzZEzNnzsTSpUsL\nqUrlJSUlAUC+PkuflsvvM
uqQlpaGmTNnokOHDjA0NMy1nb6+PpYtW4Zt27Zh27ZtsLCwQLdu3fI8\nL6YwtG3bFuvWrcPBgwcxb948XL
lyBS4uLvjw4UOuy4jl+27fvn1IS0vDgAEDFLb7r9933CVOBcLb\n2xvR0dE4evSowuO+lStXlju+26hRI7x
48QIrV65Ev379CqPUXLVr107udZMmTdCwYUPs3LkT48aN\nU1NVqrF161Y0btwY1tbWCtt5enoKP9evXx8y
mQxLly7F1KlTC7pE+n8ZGRlwc3PDy5cvsWvXLoVt\nLSwsYGFhIbxu2rQp7t+/j19+
+QX29vYFXapCvXr1En6uW7cuGjZsCGtraxw7dgwuLi5qrOy/27p1\nKzp16pTnuQL/9fuOW9hqVLlyZZQoU
SLbbqFnz55BT08vx2X09PRybF+yZMlCP2aVGy8vLwQHByM0\nNBRmZmb5Xt7Gxgbx8fGqL+w/0tHRQe3atX
OtLbffzad5RcWzZ89w5MgRpXfffc7GxgavXr0qclug\nn44H5uez9Gm5/C5TmDIyMjBixAjcunULBw8eRKV
KlfLdR1H9PBkYGKBatWoKaxPD992NGzcQExPz\nVZ8nIH+/Hwa2Gmlra6Nhw4aIiIiQmx4REQE7O7scl2na
tGmO7Rs1agQtLa0Cq1VZ06ZNE8I6r0ug\ncnPz5s0icZLTl96/f4+4uLhca2vatCnOnz+P9+/fC9MiIiJgY
GAAU1PTwiozTzt37kSpUqXktniU\ndfPmTZQuXRoVKlQogMq+nqmpKaRSqdxn4/379zh//nyunyUAsLW1zd
fnrzClp6dj2LBhuHXrFsLC\nwr76M1FUP0/Jycl4/PixwtqK+vcd8HHr2tTUFI6Ojl+1fH5+P9wlrmYeHh4
YPXo0bGxsYGdnh4CA\nADx58kQ4q3X06NEAIFwKMWzYMGzcuBHTp0/HsGHDcOHCBezcuRObNm1S2xg+mTJl
Cvbs2YPt27dD\nIpEIxxXLlSsHHR0dAMDs2bNx5coVhIaGAvgYHlpaWqhfvz40NTVx9OhRbNq0CbNmzVLXM
ASfjhka\nGRnh+fPnWLx4Md6+fSscp/pyLL1798bChQsxduxYTJkyBXfu3MGKFSvg6emp9jPEP8nKykJgYC
B6\n9uwp/E4+2bBhAzZu3IhLly4BAH777Tc8ffoUtra2KFOmDCIjI+Hn54chQ4agVKlShV77mzdvhC0R\nm
UyGhw8f4saNG6hYsSKMjY3h7u6OZcuWwcLCAubm5liyZAnKlSuH3r17C324uLjAxsZGuAJjzJgx\n6NSpE5
YvX47OnTvj0KFDiIyMxNGjR9U6HgMDAwwZMgQxMTHYtWsXNDQ0hM9T+fLlhRMFv/x+WLNm\nDUxMTGBlZYW
0tDQEBQXh8OHDCAwMVOt4KlasiAULFsDFxQVSqRT379/HnDlzULVqVXTp0kXooyh9\n3+X1/w34ePnd3r17
MWHChBw/46r+vmNgq1nPnj3x4sULLF68GElJSbCyskJQUBBMTEwAAA8fPpRr\nb2ZmhqCgIOFkIH19fSxcu
FDtl3QBED5EX9Yybdo0eHl5Afh47e+9e/fk5i9ZsgQPHjxAiRIlULNm\nTaxevVrtx68B4J9//sHIkSORnJ
yMKlWqoEmTJjh+/Ljwu/lyLBUqVMD+/fsxZcoUtG7dGhKJBB4e\nHkXqeHdkZCTu3r2LDRs2ZJuXnJyMuLg
44bWWlhY2bdqEGTNmQCaTwczMDF5eXhg1alRhliyIiYlB\n165dhdd+fn7w8/PDgAEDsHbtWkycOBHv3r3D
1KlTkZKSAhsbG4SEhMhdg33v3j25k7Y+/ZE8b948\nzJ8/H9WrV0dAQECBX4Od13imT5+OI0eOAEC2LTd/f
38MHDgQQPbvh/T0dPj4+OCff/5B6dKlhe+T\nT5cnFSRF41m2bBn+/PNP7N69Gy9fvoRUKkXLli3x66+/yv
1+itL3XV7/34CPl7KmpqYKv48vqfr7\njs/DJiIiEgEewyYiIhIBBjYREZEIMLCJiIhEgIFNREQkAgxsIiI
iEWBgExERiQADm6gY2bFjByQS\nCSQSCe7cuZNtflRUlDD/1KlThVKTtbU13N3dC3w9fn5+wtgkEgn09PRg
Z2eHX3755aufMLZjxw5s\n27ZNxZUSfR0GNlExpKuri927d2ebvmvXLrkbVRRHR48exfHjx7F9+3ZYWVnBx
8cH/v7+X9XXzp07\nsWPHDhVXSPR1GNhExVCXLl0QFBSErKz/3Rfp3bt3CA0Nlbt7kyooejyiqimzriZNms
DW1hbOzs4I\nCAiAhYVFodyak6igMbCJiqH+/fvjwYMHOH/
+vDDt0KFDkMlkOT7KsHPnzujcuXO26V/uzv60y/3s\n2bMYMmQITExM4OTkJMxfu3YtrK2tIZVK4ejomOtz
mBMSEjBq1CjUrFkTenp6cHBwQFhYmFybT7u4\n//zzT/Ts2ROGhoYYOnRovt4HTU1N1KtXL9stL+Pj4+Hm5
ob69etDX18fDRo0wKRJk5CSkiL3npw9\nexbR0dHCbvbP3yNlxkCkSryXOFExZGxsDHt7e+zZs0d4DvLu3b
vRuXNnlCtX7j/37+bmhl69eiEw\nMBAZGRkAgMDAQHh5ecHV1RU9e/ZEfHw8Ro4ciTdv3sgt+/DhQ7Rt2xZ
Vq1bF/PnzUaVKFYSEhGDw\n4MHYsWMHOnXqJNfe1dUVgwYNwsSJE6Gpmf9tjPv376N69epy0x4/fgwjIyPh
j4KEhAQsW7YMffr0\nwfHjxwEAS5cuhZubGzIzM7FixQoAEA4n5HcMRKrAwCYqpvr374+ZM2di4cKFSElJw
alTp7Bv3z6V\n9O3i4oI5c+YIr2UyGRYuXAgnJyesWbNGmF6lShUMHz5cbtkFCxYgKysLhw8fFp7v7OTkhE
ePHmH+\n/PnZwm706NH5OmktMzMTAJCSkoLAwEBcu3YNW7dulWvTokULtGjRQnhtZ2eHGjVqoGPHjrh+/To
a\nNGiA2rVrQ1dXF5mZmbC1tf1PYyBSBe4SJyqmunfvjrS0NBw9ehR79+6FVCpFq1atVNL3549EBIBH\njx
7h0aNH6N69u9x0FxcXlCwpv10QHh6Odu3aoXz58sjIyBD+OTk54Y8//sCrV68UrisvUqkUVapU\ngbm5Oeb
MmQNfX99sfaSlpWHp0qWwtbWFvr4+qlSpgo4dOwJAjmfXfym/YyBSBW5hExVTurq66Ny5\nM3bv3o379+
+jT58+X7VLOSf6+vpyrz89q1lPT09uesmSJYUt0E+ePXuG3bt353gWOwC8ePEC5cuX\nz3VdeTlx4gQ0NTX
xzz//YPHixZg1axYaNWqEli1bCm1mz56NDRs2wNPTE02bNoWuri4ePXqEQYMG\n4f3793muI79jIFIFBjZR
Mda/f3/07dsXMpkMmzdvzrVd6dKl8fr162zTPz8J63MaGhpyr6VSKQDg\n6dOnctMzMjLw4sULuWmVKlVC8
+bN8cMPP+TYt4GBgcJ15aVhw4YoWbIkGjdujObNm8PW1hbTpk1D\nVFSU8AdLSEgI+vfvj6lTpwrLfXmsXZ
H8joFIFRjYRMVY69at0aNHD1SoUAFWVla5tjM2NkZoaCjS\n0tKgra0NADh79myOIZ4TQ0NDGBkZ4cCBAxg
0aJAwPTQ0VDgp7RMnJydcunQJtWvXRpkyZb5iVMqr\nXLkyPD09MX36dISGhgq77N+
+fQstLS25tjldb12qVCkkJydnm16YYyD6hIFNVIyVKFFC4Zb1Jz17\n9sSWLVswbtw4uLq6IjExEf7+/krv
1tXU1ISnpycmTJiAsWPHolevXoiPj8eKFSuy9eHt7Q0nJyd0\n6tQJo0aNgomJCVJSUvDXX38hISHhq29yk
pthw4Zh1apVWLx4Mbp16wYNDQ20bdsWu3btQp06dVCj\nRg2EhYXh4sWL2Za1tLTE5s2bERISgurVq0NHRw
cWFhaFPgYigIFNRAC+++47LF+
+HKtWrUJoaCjq\n16+PDRs2yG0t52Xw4MFITU2Fv78/goODYWVlhU2bNsHNzU2unbGxMSIiIrBgwQLMnTsX
z58/R6VK\nlWBlZYUBAwaoemgoVaoUpk6dih9+
+AGHDh1C165dsWjRImRlZWHu3LkAAGdnZ2zevBlt2rSRW/aH\nH37AnTt3MGHCBLx58wYtWrTA4cOHC30MR
ACgkZKSkpV3MyIiIlInXtZFREQkAgxsIiIiEWBgExER\niQADm4iISAQY2ERERCLAwCYiIhIBBjYREZEIML
CJiIhEgIFNREQkAv8H51t7KSXK5SUAAAAASUVO\nRK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc4c2119048>"
]
},
"metadata": {},
}
],
"source": [
"def most_murderous(year):\n",
" # Assign most to a table of the most murderous states this year in
ascending order.\n",
" most = murder_rates.where('Year', year).sort('Murder Rate',descending =
True).take(np.arange(5)).sort('Murder Rate')\n",
" most.barh('State', 'Murder Rate')\n",
" return most.column('State')\n",
"\n",
"most_murderous(1990) # California, Mississippi, ..., "
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/backups/PNO3GW\n",
"\n"
]
},
{
"data": {
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAAgQAAAEcCAYAAAC4b6z9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAL
EgAACxIB0t1+/AAAIABJREFUeJzt3Xd4jff/x/FnYkQQYiUxEiFJI4i9Qs20KBUzgn5tYtbe\nfM1WrFJEz
IbS2JRodaBBaNQo1SoxUrNG8A010pDk90cv59cjm5wEeT2uK9fl3Pfn/tzvd+LkvHLf\n97mPWVRUVDwiIi
KSpZlndgEiIiKS+RQIRERERIFAREREFAhEREQEBQIRERFBgUBERERQIBAREREU\nCERERAQFAsnizp07l9k
lZIis0idknV6zSp+QdXrN7D4VCERERESBQERERLJYIPDz88PDwyOzy0iz\noKAgihcvnuRjERGRl5UpgaBf
v35YW1sza9Yso+WhoaFYW1tz586dl96HtbU127dvf+l5ngkNDcXH\nx4fSpUtjZ2dH9erVGTlyJJcuXUq3f
aRWmzZtOHHiRIbvV0RE3lyZdoQgV65cLFy4kNu3b6frvDEx\nMek6H8DKlStp2bIlBQoUYNWqVfz0008sXL
iQ+Ph45syZ88LzvmitlpaWFClS5IX3KyIi8rxMCwR1\n69bF3t4+wVGC5x08eBBPT09sbW1xcXFh7NixRi+
kzZs3Z9iwYUyYMAEnJyeaNGmCu7s7AF27dsXa\n2trw+JktW7ZQqVIlSpQoQadOnZI9InHt2jVGjx5Nr169
WLJkCfXq1aNkyZLUqlWLOXPmMG3aNADu\n3r1Lz549KVu2LHZ2dtSqVYsvvvjCaK7EagW4cuUKH3zwASVKl
KBEiRL85z//4dq1a0nW9Pwpg2en\nQpLr6+eff6Z169aULl0ae3t7mjZtyuHDh5P93ouISNaRaYHA3NycyZ
Mns3LlSv74449Ex/z55594\ne3tToUIF9u/fz8KFC9myZQtTpkwxGrdx40bi4+P55ptvWLJkCSEhIQAsWLC
A8PBww2OAy5cvs3Xr\nVr744gu2bt3KyZMnDS/qidm2bRsxMTEMHTo00fXW1tYAREdHU7FiRdavX8+hQ4fo
27cvQ4cOZd+
+\nfcnWGhcXR6dOnYiMjGTHjh3s2LGDGzdu8MEHHxAfH5/yNzKVff3111/4+PjwzTffsGfPHtzd3fH2\n9u
bu3bup3oeIiLy5smfmzhs3bkzNmjWZNm0agYGBCdZ/9tln2NnZ8cknn2Bubo6rqyuTJk1i6NCh\njB8/nty
5cwPg4ODAxx9/nGD7/PnzY2tra7Ts6dOnBAQEkD9/fgC6detGUFBQkjVGRESQL18+ihYt\nmmwvxYoVY9Cg
QYbH3bp1Y//
+/WzevJn69esblj9fa0hICKdOneL48eOULFkSgBUrVlC5cmX27dtH\ngwYNkt1vavv6dw0As2bNIjg4mF27
duHj45OqfYiIyJsrUwMBwJQpU3j33XeNXkyfCQ8Pp1q1apib\n//
+BDA8PD2JiYoiIiKB8+fIAVKpUKdX7s7e3N7xoAtjZ2SV7HUNq/0qPjY1l3rx5bN26levXrxMT\nE0NMTAx
vv/220bjnaw0PD6do0aKGMADg6OhI0aJFOXPmTKoDQUp9RUZG8vHHHxMaGkpkZCSxsbE8\nfvyYq1evJjnn
+93Hp2rfIiLPmzeuW7rOl9k37ckopuzTxcUl2fWZHgiqVq2Kl5cXEydOZOTIkane\nzszMzPDvPHnypHq7H
DlyJJgnLi4uyfFOTk7cv3+f69evJ3uUYOHChfj7+zNjxgzKli1L3rx5mTp1\nKpGRkUbj0lLrv3tMSUp99e
vXj1u3bjF9+nQcHBywsLDAy8sr2Qsb01Lr6+rhw4fq8w2TVXp91ftM\n6cUnLc6dO5eu872qMrvPV+I+BBM
nTiQsLIw9e/YYLXd1deXo0aNGL2xhYWHkzJmTUqVKJTtnjhw5\niI2NfenaWrZsSc6cOZk3b16i66Oiogx1
NW3alA4dOlChQgVKlSrF+fPnU5zf1dWV69evG7198eLF\ni1y/fp0yZcq8dP3PHDp0CF9fX5o0aYKbmxt58
+bl5s2b6Ta/iIi83l6JQFC6dGm6devGkiVLjJb3\n7NmTGzduMHz4cMLDw/nuu+
+YMmUKvXv3Nlw/kBQHBwf27dvHzZs3DS/aL6JEiRJMnz6d5cuX07dv\nX0JDQ7l8+TKHDx9m5MiRTJw4EQB
nZ2f2799PWFgYZ8+eZeTIkVy+fDnF+Rs0aEC5cuXw9fXl+PHj\nHD9+nN69e1OxYkXq1av3wnU/z8nJiY0b
N3LmzBl+/vlnevToQc6cOdNtfhEReb29EoEAYNSoUWTP\nbnwGo1ixYmzatImTJ09St25dBg4cSNu2bQ0vw
sn56KOPCA0NpVy5ctStW/elauvVqxfbtm3jzp07\ndOnSherVq9O/f38ARowYAcDIkSOpUqUK3t7eNGvWjN
y5c+Pt7Z3i3GZmZqxdu5ZChQrRokULWrRo\ngY2NDUFBQWk6ZZASf39/Hj58SIMGDejRowf/
+c9/cHBwSLf5RUTk9WYWFRWV+ve2SZbiM3B6Zpdg\ncq/6edj0klX6hKzT66ve5wb/cek2V2afW88omd3nK
3OEQERERDKPAoGIiIgoEIiIiIgCgYiIiKBA\nICIiIigQiIiICAoEIiIiggKBiIiIoEAgIiIiKBCIiIgICg
QiIiKCAoGIiIigQCAiIiIoEIiIiAgK\nBCIiIoICgYiIiKBAICIiIigQiIiICAoEIiIiggKBiIiIoEAgIiI
iKBCIiIgICgQiIiKCAoGIiIig\nQCAiIiIoEIiIiAgKBCIiIoICgYiIiKBAICIiIkD2zC5AXl0b/Mdldgkm
d+7cOVxcXDK7DJPLKn1C\n1uk1q/QpGUdHCERERESBQERERBQIMoW1tTXbt29Pl7kuXbqEtbU1x48fT5f5R
EQka1IgMJETJ05Q\nsGBBmjRpktmliIiIpEiBwETWrFlDz549OX36NOHh4ZldjoiISLIUCEzg8ePHbNq0iW
7duuHl5cWa\nNWuSHT958mSqVauGnZ0d7u7uTJw4kejoaMP6q1ev0rFjRxwdHSlatCjVq1dny5Ytic4VFxf
HiBEj\nqFChAhcuXADA39+f2rVrU6xYMdzc3Pjwww+JiopKv4ZFROS1p7cdmsD27duxt7enXLly+Pj40L17
\ndyZNmkSOHDkSHZ87d278/f0pWrQo4eHhDBs2jJw5czJhwgQAhg8fzt9//82OHTuwsrLi/Pnzic7z\n5Mk
T+vbty+
+//853331H0aJFATA3N8fPzw9HR0euXLnCqFGjGDVqFMuWLTPNN0BERF47CgQmsGbN\nGjp06ADA22+/jaW
lJTt37qRly5aJjh81apTh3yVLlmTYsGEsXLjQEAiuXLmCl5cX7u7uADg6OiaY\n4+HDh3To0IF79+6xc+dO
ChQoYFjXv39/o/mnTp1Kp06dWLJkCebmOkgkIiIKBOkuIiKCQ4cOsWLF\nCgDMzMxo3749a9asSTIQbN+
+ncWLFxMREcHDhw+JjY0lNjbWsL5v374MGzaMPXv2UL9+fd5//30q\nVapkNEefPn2wtbVlx44d5MmTx2jd
vn37mDdvHmfPnuX+/fvExsYSExPDzZs3DUcREvN+9/Ev+m0Q\nEUm1eeO6pTjm3Llzpi/kFWDKPlO6kZUCQ
TpbvXo1sbGxlC9f3rAsPj4e+OdagBIlShiNP3LkCD16\n9GD06NFMnz6d/Pnzs3PnTv773/8axnTp0gVPT0
927drF3r17ady4MUOHDmXs2LGGMY0bN2b9+vX8\n9NNPNGrUyLD88uXL+Pj40KVLF8aNG0fBggX55Zdf6Nm
zJzExMcn28nyweBM9fPhQfb5hskqvb1Kf\nKb1QZZW7MmZ2nzpenI6ePn3KunXrmDRpEqGhoYavAwcOUK5c
OYKCghJsc+jQIYoWLcqoUaOoUqUK\nTk5OXLlyJcG44sWL061bN1atWsW4ceP4/PPPjdZ36dIFPz8/PvjgA
0JCQgzLjx8/TkxMDH5+ftSo\nUQNnZ2euX7+e/s2LiMhrTUcI0tF3333HnTt36Nq1KwULFjRa17ZtWwIDA4
2uFwAML9AbN26kRo0a\n7NmzJ8E7CEaPHs27776Ls7Mz9+/fZ/fu3bi6uibYf7du3YiPj+eDDz4gKCiIhg0
b4uTkRFxcHAEB\nAbRo0YKjR4+yZMmS9G9eREReazpCkI7WrFlD3bp1E4QBgFatWnH58mWjv94B3nvvPQYN
GsTYsWOp\nU6cOISEhjBtn/KFCcXFxjBo1ipo1a9K6dWtsbGxYvHhxojV0796djz76yHCkoHz58syYMYOAg
ABq\n1arF6tWrmTZtWvo1LSIibwSzqKio+MwuQl5NPgOnZ3YJJvcmnYdNTlbpE7JOr29Snyl9smpmn1vP\n
KJndp44QiIiIiAKBiIiIKBCIiIgICgQiIiKCAoGIiIigQCAiIiIoEIiIiAgKBCIiIoICgYiIiKBA\nICIiI
igQiIiICAoEIiIiggKBiIiIoEAgIiIiKBCIiIgICgQiIiKCAoGIiIigQCAiIiIoEIiIiAgK\nBCIiIoICgY
iIiKBAICIiIigQiIiICAoEIiIiggKBiIiIoEAgIiIiKBCIiIgICgQiIiKCAoGIiIgA\n2TO7AHl1bfAfl9k
lmNy5c+dwcXHJ7DJMLqv0CVmn16zSp2QcHSEQERERBQIRERFRIBAREREUCDJM\nv3798PHxeel5goKCKF68
eLJjFi5ciLu7+0vvS0REsg4FgnTUr18/rK2tE3ydPHky3fbRpk0bTpw4\nkW7ziYiIgN5lkO4aNGjA0qVLj
ZYVKlQoXeZ+8uQJlpaWWFpapst8IiIiz+gIQTqzsLDA1tbW6Ct7\n9oS56++//2bMmDG4uLhga2vLO+
+8Q1hYmGF9aGgo1tbWfP/99zRq1IgiRYqwZ8+eRE8ZzJ8/n7fe\neovixYvTp08fHjx4YLT+559/pnXr1pQ
uXRp7e3uaNm3K4cOHTfMNEBGR11KaA8Fvv/3GsmXLmDFj\nBjdv3gQgIiKCv/76K92Le5NNnDiRL7/8En9/
f/bv30/ZsmVp164dN27cMBo3efJkJkyYwJEjR6hW\nrVqCeb788ks+
+ugjxo4dy759+3BxcSEgIMBozF9//YWPjw/ffPMNe/bswd3dHW9vb+7evWvSHkVE\n5PWR6lMGf//9N76+v
uzYsYP4+HjMzMxo2rQptra2TJw4EWdnZyZPnmzCUl8Pu3fvNvoL3sPDg82b\nNxuNefjwIYGBgSxYsIAmTZ
oAMG/ePPbv38+KFSuYMGGCYezo0aNp1KhRkvtbvHgxHTt2pHv37gCM\nGDGC0NBQIiIiDGPq169vtM2sWbM
IDg5m165dyV7o+H738anoWEQkY80b1y2zSzCZc+fOmWzulG5k\nlepAMG3aNPbu3cvSpUtp2LCh0cTvvvsu
K1asUCAAateuzfz58w2Pc+XKlWDMH3/8wZMnT6hVq5Zh\nWbZs2ahRowZnzpwxGlu5cuVk9xceHk7nzp2Nl
lWvXt0oEERGRvLxxx8TGhpKZGQksbGxPH78mKtX\nryY7d548eZJd/yZ4+PCh+nzDZJVes0qfkLDXN/UOjZ
l998lUB4ItW7YwYcIEvL29iY2NNVpXsmRJ\nLl+
+nO7FvY5y585N6dKlX3h7MzMzo8fp8YTv168ft27dYvr06Tg4OGBhYYGXlxcxMTEvPbeIiLwZ\nUn0Nwd27
d3nrrbcSXRcXF6cXlzQoVaoUOXPm5NChQ4ZlsbGxHD58GFdX1zTN5erqytGjR42WPf/4\n0KFD+Pr60qRJE
9zc3MibN6/h+g8RERFIwxGCkiVLcuTIkQTnowGOHTuGs7Nzuhb2JsuTJw89evRg\n8uTJFCpUiJIlSxIQEE
BkZCS9evVK01x9+/alb9+
+VKlShbfffpvt27dz7NgxrK2tDWOcnJzYuHEj\n1apV49GjR0ycOJGcOXOmd1siIvIaS3Ug6NChA3PnzsXB
wQEvLy/gn8Pb+/fvJyAggDFjxpisyDfR\nlClTABgwYAD37t2jQoUKbN68GTs7uzTN06ZNGy5evMi0adN4/
Pgx7733Hv3792ft2rWGMf7+/gwZ\nMoQGDRpgZ2fHmDFjuHPnTrr2IyIirzezqKio+NQMjI2NpXfv3nz55Z
dYWFjw999/Y2lpSXR0NG3b\ntmX58uWmrlUymM/A6ZldgslllQuzskqfkHV6zSp9QsJe39SPZn9tLirMli0
bgYGB9OrVix9+
+IHI\nyEgKFiyIp6cnb7/9tilrFBERERNLdSC4cuUKdnZ21K5dm9q1axute/r0KdevX8fe3j7dCxQRERHT\
nS/W7DCpWrJjkh/T89ttvVKxYMd2KEhERkYyV6kAQH5/0pQZPnjzB3FwfiyAiIvK6SvaUQVRUFFFR\nUYbH
f/75Z4JP7nv8+DHr1q3D1tbWNBWKiIiIySUbCJYsWcLMmTMxMzPDzMyMrl27JjouPj6esWPH\nmqRAERERM
b1kA0Hz5s1xcHAgPj6egQMHMmLECEqVKmU0xsLCAldXV8qXL2/SQkVERMR0kg0E7u7u\nuLu7Axg+3bBgwY
IZUpiIiIhknFS/7bBTp06mrENEREQyUaoDAcDp06dZvXo158+fJzo62midmZkZ\nwcHB6VqciIiIZIxUB4K
jR48arim4cOEC5cqVIyoqiqtXr1K8ePEE1xaIiIjI6yPVNw+YOnUqLVq0\n4NChQ8THx7Nw4UJ+/fVXtm3b
RmxsLCNGjDBlnSIiImJCqQ4Ep06don379piZmQEQFxcHQP369Rkx\nYgRTp041TYUiIiJicqkOBE+ePCF37
tyYm5tToEABbty4YVjn7OzM6dOnTVKgiIiImF6qA0GpUqW4\nfv06AOXKleOLL74gLi6OuLg4goKCsLGxMV
mRIiIiYlqpDgRNmzblwIEDAAwfPpzdu3djb2+Po6Mj\nmzdvZsCAASYrUkREREwr1e8y+PetiRs0aMCuXbv
YsWMHjx494p133qFRo0YmKVBERERML033Ifi3\nihUr6iOPRURE3hCpPmVQsGBBjh07lui6EydO6JbGIiIi
r7FUB4L4+Pgk18XGxhrejigiIiKvnxRP\nGcTFxRnCwLN3Ffzb48eP2bVrF4UKFTJNhSIiImJyyQaCGTNmM
GvWLOCfzypo0qRJkmN79uyZvpWJ\niIhIhkk2ELz99tvAP6cLZs2aRefOnSlWrJjRGAsLC1xdXWnatKnpqh
QRERGTSjEQPAsFZmZmdO3a\nlaJFi2ZIYSIiIpJxUv22wzFjxhg9vnfvHhEREdjY2FC8ePF0L0xEREQyTrL
vMtizZw+TJ09OsHzO\nnDm4uLjg6emJu7s7vXr14unTp6aqUUREREws2SMEgYGBCd5OGBISwscff0zZsmXp
0qULZ8+eZeXK\nlVSsWJEPP/zQpMWKiIiIaSQbCE6ePMnIkSONlgUFBZErVy62bt2Kra2tYfnmzZsVCERER
F5TyQaC\n27dvU6pUKaNlISEh1KpVyygMNG7cmA0bNpimQsk0G/zHZXYJJnfu3DlcXFwyuwyTyyp9QtbpNa
v0\nCVmr18yU7DUEefPm5dGjR4bHFy5c4O7du1SrVs1onJWVFbGxsaapUEREREwu2UDg4uLCzp07DY93\n7
tyJmZlZgk82vHTpEkWKFDFNhSIiImJyyZ4y6N+/P507d+Z///sfNjY2rF27lrJly1KrVi2jcbt2\n7aJ8+f
ImLVRERERMJ9kjBO+//z5+fn78/PPPrF+/nmrVqvH5558bvfPg5s2b7N27l8aNG5u82Jfl\n7u7OwoULM7u
MNGvevLnRxZ3PPxYREXlZKd6YqG/fvvTt2zfJ9ba2tkRERKRqZ7dv38bPz4/vv/
+e\nmzdvkj9/ftzc3Bg6dCgNGzZMfdUpCAoKYtSoUVy7di1d5ouJiWHJkiVs2rSJ8+fPY2FhgbOzMx98\n8
AGdOnXCwsIiXfaTWl988QXZs6f6nlIiIiIpytBXlc6dO/P48WP8/f0pVaoUt2/f5uDBg9y9ezcj\ny0iTmJ
gY2rRpw8mTJxk3bhweHh7kz5+f48ePs2jRIpydnalbt+4Lzf3kyRNy5MiR5u0KFCjwQvsT\nERFJSrKnDNJ
TVFQUYWFhTJ48mfr16+Pg4ECVKlX48MMPadu2rdG4vn37UrJkSezs7GjZsiWnT582\nrA8KCkpwq+TQ0FCs
ra25c+cOoaGhDBgwgIcPH2JtbY21tTV+fn6GsdHR0QwZMgR7e3vKli3LggUL\nkq178eLFHDx4kO3bt9O3b
18qVqyIo6MjrVu35vvvv6dixYoA7N69m/fee4+SJUvi6OhImzZtCA8P\nN8xz6dIlrK2t2bx5My1atMDOzo
6VK1cCEBwcTO3atbGxsaFcuXLMmTPH8JHTiXn+lIG7uzuzZ89O\nti9/f39q165NsWLFcHNz48MPPyQqKir
Z3kVEJOvIsECQN29e8ubNy86dO4mOjk5yXL9+/Th27Bhr\n165lz549WFpa0q5dOx4/fpyq/dSsWRM/Pz9y
585NeHg44eHhRjdMCggIoGzZsuzbt4/BgwczceJE\nDh8+nOR8GzdupEGDBlSuXDnBOnNzc/LlywfAw4cP6
du3Lz/88ANfffUV+fLlo0OHDsTExBhtM2XK\nFHr16sWhQ4do3rw5J06coFu3brz//vv8+OOPTJo0iXnz5r
Fs2bJU9ZvavszNzfHz8yMsLIzly5dz\n7NgxRo0alaZ9iIjImyvDThlkz56dRYsWMXjwYD7//HMqVKhAzZo
1adWqleG+BhcuXOCbb77h66+/\npk6dOgAsXboUd3d3Nm3aRJcuXVLcT86cOcmXLx9mZmZGN096plGjRvj6
+gLQp08fli5dyr59+6hR\no0ai80VERBg+8TE5LVu2NHq8aNEi7O3tOXbsGB4eHoblvr6+RmMnT55MnTp1G
Dfun5sAOTs7c+HC\nBebPn0+fPn1S3G9q+
+rfv79hbMmSJZk6dSqdOnViyZIlmJsnngvf7z4+1fsXEZGkzRvXLVXjzp07\nZ7IaUrq5U4ZeQ9CyZUuaNG
lCWFgYhw8fZs+ePfj7+/Pf//6X4cOHEx4ejrm5udGLc/78+Slbtixn\nzpxJlxrKlStn9NjOzo7IyMgkxyd
36P7f/vjjDz7+
+GOOHj3KnTt3iIuLIy4ujqtXrxqNe/5IQ3h4\neIJ3aHh4eDBz5kzu379vOAKRkpT62rdvH/PmzePs2bPcv
3+f2NhYYmJiuHnzZpIfaZ0nT55U7ft1\n9vDhQ/X5hskqvWaVPuHN6DU1d1rM7DsyZtgpg2dy5cpFw4YNGT
16NN9//z2dO3dmxowZCQ6tP+/Z\nWx3Nzc0TvEin5ZMWn7+Iz8zMLNkXfScnJ86ePZvivD4+Pty+fZtPP/2
U3bt3s3//frJnz56gr7T8\np37+g6WSk1xfly9fxsfHh7feeotVq1axd+9e/P39AVL8vouISNaQ4YHgea6u
rjx9+pTo6GhcXV2J\ni4szOvd9//59fv/9d1xdXQEoXLgwjx494v79+4Yxv/76q9GcOXPmTLdbKXt7e7N37
16OHz+eYF1c\nXBz379/n7t27nD17lmHDhtGgQQNcXV3566+/UhVUXF1d+emnn4yWhYWFUbx4caysrNKlh+
PHjxMT\nE4Ofnx81atTA2dmZ69evp8vcIiLyZsiwQHD37l1atGjBhg0b+O2337h48SLbtm1jwYIF1K9fn3z
5\n8uHk5ESzZs0YOnQoP/74I6dOncLX1xcrKyu8vb0BqFatGnny5GHq1KlERESwfft2VqxYYbQvBwcH\noq
OjCQkJ4c6dO0afx5BW/fr1o1atWrRq1YolS5Zw8uRJLl68SHBwME2bNuWXX37B2tqaQoUKs
Xr1\naiIiIjhw4ADDhg1L1b0CBgwYwMGDB/Hz8+P8+fNs3LiRRYsWMWjQoBeu+XlOTk7ExcUREBDAxYsX\n
2bx5M0uWLEm3+UVE5PWXYYEgT548VK9enSVLltC8eXM8PDyYOnUq7dq1M7z9Dv65Wr5KlSp07NgR\nT09PH
j9+zObNm7G0tAT+eQ/+smXLCAkJoXbt2nz+
+eeMH2988VvNmjXp0aMHPXv2xMnJifnz579w\n3RYWFmzbto2hQ4eyZs0aGjduTP369VmwYAEdO3akZs2am
JubExgYyKlTp/Dw8GDkyJGMHz8+VTcs\nqlSpEqtWrWLHjh14eHgwZcoUhgwZYrhAMD2UL1+eGTNmEBAQQK
1atVi9ejXTpk1Lt/lFROT1ZxYV\nFZW6q+Yky/EZOD2zSzC5N+FipdTIKn1C1uk1q/QJb0avqfk4+Sx3UaG
IiIi8ehQIRERERIFARERE\nFAhEREQEBQIRERFBgUBERERQIBAREREUCERERAQFAhEREUGBQERERFAgEBER
ERQIREREBAUCERER\nQYFAREREUCAQERERFAhEREQEBQIRERFBgUBERERQIBAREREUCERERAQFAhEREUGBQ
ERERFAgEBER\nERQIREREBAUCERERQYFAREREUCAQERERFAhEREQEBQIREREBzKKiouIzuwiRzHLu3DlcXF
wyuwyT\nyyp9QtbpNav0CVmn18zuU0cIRERERIFAREREFAjeSJcuXcLa2prjx49ndikiIvKaUCB4Abdu3WL
s\n2LFUqVIFW1tbnJ2dady4MUuXLuXBgweZXR4lSpQgPDwcd3f3zC5FREReE9kzu4DXzaVLl2jatClW\nVl
aMHz+ecuXKkStXLs6cOcPq1aspWLAg3t7eJtl3TEwMOXPmTHFctmzZsLW1NUkNIiLyZtIRgjQa\nPnw45ub
mhISE0LZtW8qUKYOjoyNNmzZl7dq1tGvXDoB79+4xePBgnJ2dKVGiBM2aNUtwCD84OJja\ntWtjY2NDuXLl
mDNnDvHx//
+mD3d3d/z8/BgwYAAODg707t0bgKNHj1KvXj1sbW2pW7cu33//PdbW\n1oSGhgIJTxnExsYycOBAKlSogJ2
dHVWqVGH+/PnExcVlxLdMREReAzpCkAZ3795lz549TJw4kTx5\n8iQ6xszMjPj4eHx8fMiXLx8bNmygQIEC
rF27Fi8vL44cOYKdnR0nTpygW7dujBgxgvbt2/Pzzz8z\ndOhQrKys6NOnj2G+gIAARowYwd69e4mPj+fBg
wf4+PjQsGFDli5dyo0bNxg7dmyydcfFxVG0aFFW\nrVpFoUKrVyxGAAAVsElEQVSF+Pnnnxk8eDAFChSgS5
cu6fo9EhGR15MCQRpEREQQHx+Ps7Oz0fKy\nZcty7949ANq3b0+rVq349ddfOX/
+PJaWlgBMmDCBb7/9lg0bNjB48GAWLVpEnTp1GDduHADOzs5c\nuHCB+fPnGwWC2rVrM3jwYMPjlStXEhsb
y8KFC7G0tMTNzY3hw4cbjh4kJkeOHIwfP97wuGTJkvzy\nyy9s2bIl2UDwfvfxSa4TEZGMM29ct5eeI6V7H
CgQpIOdO3cSFxfH4MGDiY6O5pdffuHRo0cJgkN0\ndDR//PEHAOHh4TRu3NhovYeHBzNnzuT+/fvky5cPgM
qVKxuNOXv2LG5uboagAVCtWrUUawwMDGT1\n6tVcuXKF6Ohonjx5gr29fbLbJHUU5E3y8OFD9fmGySq9ZpU
+Iev0mlyfGXHDIgWCNChdujRmZmac\nO3fOaLmjoyMAuXPnBv45RG9jY8M333yTYA4rK6sU92NmZmb4d3o8
CbZu3crYsWOZNm0aNWrUIF+
+\nfCxfvpyvvvrqpecWEZE3gwJBGhQsWJBGjRqxfPlyfH19yZs3b6LjKlasyK1btzA3NzeEhee5urry\n00
8/GS0LCwujePHiyYaGt956i3Xr1vH48WPDUYJjx44lW3dYWBhVq1bF19fXsOzZkQoRERHQuwzS\n7JNPPiE
uLo4GDRqwefNmzpw5w/nz59m8eTO//fYb2bJlo0GDBtSqVYtOnTqxa9cuLl68yOHDh5k+\nfTo//vgjAAMG
DODgwYP4+flx/vx5Nm7cyKJFixg0aFCy+2/Xrh3ZsmVj8ODBnDlzhr179zJ37lzA\n+MjCvzk7O3Py5El27
drFhQsXmDVrlqEOERERUCBIM0dHR/bv34+npycff/wx9erVo379+ixatIie\nPXvi5+eHmZkZGzdupG7dug
wePJjq1avTvXt3zp8/T9GiRQGoVKkSq1atYseOHXh4eDBlyhSGDBli\n9Fd8YqysrFi/fj2nT5+mXr16/Pe
//2X06NEA5MqVK9FtunfvTqtWrejVqxcNGzbk8uXLDBgwIH2/\nMSIi8lrTpx2+Ab7+
+mv+85//cP78eQoVKpRu8/oMnJ5uc72qdLHSmyer9JpV+oSs02tyfW7wH2fy\n/esagtfQ2rVrcXR0pHjx4
pw+fZqxY8fStGnTdA0DIiKStSgQvIYiIyPx8/Pj5s2b2NjY0KRJEyZP\nnpzZZYmIyGtMgeA1NHjwYKObFY
mIiLwsXVQoIiIiCgQiIiKiQCAiIiIoEIiIiAgKBCIiIoICgYiI\niKBAICIiIigQiIiICAoEIiIiggKBiIi
IoEAgIiIiKBCIiIgICgQiIiKCAoGIiIigQCAiIiIoEIiI\niAgKBCIiIoICgYiIiKBAICIiIigQiIiICAoE
IiIiggKBiIiIoEAgIiIiKBCIiIgICgQiIiKCAoGI\niIgAZlFRUfGZXYRIZjl37hwuLi6ZXYbJZZU+Iev0m
lX6hKzTa2b3qSMEIiIiokAgIiIiCgQiIiKC\nAoGIiIigQCAiIiIoEIiIiAgKBCIiIoICgYiIiKAbE4mIiA
g6QiAiIiIoEIiIiAgKBCIiIoICgYiI\niKBAICIiIigQZEkrVqygQoUK2NraUr9+fX788cdkxx84cID69et
ja2tLxYoVCQwMzKBKX8zcuXNp\n2LAh9vb2ODk54ePjw+
+//57sNpcuXcLa2jrB1+7duzOo6hfj5+eXoOa33nor2W1OnTpFs2bNsLOz\nw83NjZkzZxIf/2q/2cjd3T3
Rn0/79u2T3Cax8a/i/92DBw/SoUMH3NzcsLa2JigoyGh9fHw8fn5+\nlClTBjs7O5o3b87p06dTnHf79u3U
rFkTGxsbatasyY4dO0zVQqol1+uTJ0+YNGkStWvXplixYri6\nutKrVy+uXLmS7JyhoaGJ/qzPnj1r6naSl
NLPtF+/fgnqfeedd1Kc19S/ixUIspitW7cyZswYhg8f\nzv79+6lRowbe3t5JPukuXrxI+/btqVGjBvv372
fYsGGMGjWK7du3Z3DlqXfgwAF69uzJd999R3Bw\nMNmzZ6dVq1b873//S3HbLVu2EB4ebviqV69eBlT8clx
cXIxqTi7g3b9/n9atW2NjY8MPP/zAjBkz\nWLhwIf7+/hlYcdqFhIQY9bhv3z7MzMxo1apVststWLDAaLuO
HTtmUMWp9/DhQ8qWLcuMGTOwtLRM\nsH7+/PksWrSImTNn8sMPP1CkSBFat27NX3/9leSchw8fpkePHnh7e
xMaGoq3tzfdunXj6NGjpmwl\nRcn1+ujRI3755RdGjBjBvn37WLt2LdeuXaNdu3Y8ffo0xbkPHTpk9LN2cn
IyVRspSulnCtCgQQOj\nejdt2pTsnBnxuzh7us0kr4VFixbRqVMnunbtCsDs2bPZs2cPgYGBTJo0KcH4lSt
XYmdnx+zZswFw\ndXXl6NGj+Pv707JlywytPbW2bt1q9Hjp0qU4ODhw6NAh3nvvvWS3LViwILa2tqYsL91l
z5491TVv\n2rSJx48fs3jxYiwtLSlbtixnz54lICCAgQMHYmZmZuJqX0zhwoWNHq9ZswYrKytat26d7Hb58
+d/\n5X+ejRs3pnHjxgD079/faF18fDyLFy9myJAhhufb4sWLcXFxYfPmzXTv3j3RORcvXkzdunUZMWIE\n
8M/zNjQ0lMWLF/PZZ5+ZsJvkJddr/vz52bZtm9GyefPmUatWLcLDwylXrlyycxcpUoRChQqlb8Ev\nKLk+n
7GwsEjT/82M+F2sIwRZSExMDCdOnKBRo0ZGyxs1asRPP/2U6DaHDx9OMN7T05Pjx4/z5MkT\nk9Wanh48eE
BcXBzW1tYpju3cuTPOzs40adLklT4K8m8XL16kTJkyVKhQgR49enDx4sUkxx4+fBgP\nDw+jv1o8PT25fv0
6ly5dyoBqX158fDxr1qzBx8cnyb+
+nhkzZgylS5emYcOGBAYGEhcXl0FVpo9L\nly5x8+ZNo+egpaUltWvXTvI5C3DkyJFEn7fJbfMqenYUJDXP
3QYNGuDq6oqXlxf79+83dWkvLSws\nDGdnZ6pWrcqgQYOIjIxMdnxG/C5WIMhC7ty5Q2xsLEWKFDFaXqRIE
W7dupXoNrdu3Up0/NOnT7lz\n547Jak1PY8aMwd3dnRo1aiQ5Jm/evEybNo2VK1eyadMm6tWrR/fu3dmwYU
MGVpp21apVIyAggM2b\nN7NgwQJu3rxJ48aNuXv3bqLjk/p5Plv3OggJCeHSpUt06dIl2XHjxo0jMDCQbdu
20aZNGyZMmMAn\nn3ySQVWmj5s3bwKk6Tn7bLu0bvOqiYmJYcKECTRt2pTixYsnOc7Ozo65c+eyZs0a1qxZ
g4uLCy1b\ntkzx2qjM9M4777BkyRK2b9/ORx99xLFjx/Dy8uLvv/9OcpuM+F2sUwbyRhs3bhyHDh3i22+/J
Vu2\nbEmOK1SoEB9++KHhceXKlbl79y7z58/Hx8cnI0p9Ie++
+67R42rVqlGpUiXWrl3LwIEDM6kq0/r8\n88+pUqUK7u7uyY4bNWqU4d8VKlQgLi6OTz75hJEjR5q6RHlJT
58+xdfXl3v37rFu3bpkx7q4uODi\n4mJ4XKNGDS5fvsyCBQuoXbu2qUt9IW3btjX8u1y5clSqVAl3d3e++
+47vLy8Mq0uHSHIQgoVKkS2\nbNkSHJqKjIzExsYm0W1sbGwSHZ89e/ZX5nxdUsaOHcuWLVsIDg7G0dExzd
tXrVqViIiI9C/MhPLm\nzUuZMmWSrDupn+ezda+6yMhIdu7cabgGJi2qVq3K/fv3X6u/kp+dY07Lc/bZdmn
d5lXx9OlTevbs\nyalTp9i+fTsFCxZM8xyv23O3aNGiFCtWLNmaM+J3sQJBFpIzZ04qVapESEiI0fKQkBBq
1qyZ6DY1\natRIdHzlypXJkSOHyWp9WaNHjzaEgZTehpeUX3/99ZW/IO150dHRnDt3Lsm6a9SoQVhYGNHR0
YZl\nISEhFC1alJIlS2ZUmS9s7dq1WFhYGP2FlVq//voruXLlIn/
+/CaozDRKliyJra2t0XMwOjqasLCw\nJJ+zANWrV0/T8/xV8eTJE7p3786pU6fYsWPHCz//Xrfn7p07d7h+
/XqyNWfE72KdMshiBgwYQJ8+\nfahatSo1a9YkMDCQGzduGK5W7tOnD/DPlfkA3bt3Z/ny5YwZM4bu3bvz0
08/sXbtWlasWJFpPaRk\nxIgRbNiwgS++
+AJra2vDedg8efKQN29eAKZMmcKxY8cIDg4G/nmhyZEjBxUqVMDc3Jxvv/2WFStW\nMHny5MxqI1WenWMtU
aIEt2/fZvbs2Tx69Mjw9rrn+2zXrh0zZ86kf//
+jBgxgvPnz/Ppp58yatSo\nV/YdBs/Ex8ezevVq2rRpY/g5PrNs2TKWL1/OkSNHAPjmm2+4desW1atXx9LS
ktDQUPz8/OjatSsW\nFhaZUX6SHjx4YPjLMC4ujqtXr3Ly5EkKFCiAvb09/fr1Y+7cubi4uODs7MycOXPIk
ycP7dq1M8zh\n5eVF1apVDe8U6tu3L82aNWPevHk0b96cr776itDQUL799ttM6fGZ5HotWrQoXbt25fjx46
xbtw4z\nMzPDczdfvnyGC0if/x0VEBCAg4MDbm5uxMTEsHHjRr7+
+mtWr16dCR3+I7k+CxQowIwZM/Dy8sLW\n1pbLly8zdepUihQpwvvvv2+YIzN+FysQZDFt2rTh7t27zJ49m
5s3b+Lm5sbGjRtxcHAA4OrVq0bj\nHR0d2bhxo+ECLTs7O2bOnPnKvuUQMDxBnq9x9OjRjB07FoAbN27wxx
9/GK2fM2cOV65cIVu2bDg5\nOeHv7/9KXz8A8Oeff9KrVy/u3LlD4cKFqVatGrt27TL8PJ/vM3/+/Hz55Ze
MGDGChg0bYm1tzYAB\nA16L6w1CQ0O5cOECy5YtS7Duzp07nDt3zvA4R44crFixgvHjxxMXF4ejoyNjx46l
d+/eGVlyqhw/\nfpwWLVoYHvv5+eHn50fHjh1ZvHgxgwcP5vHjx4wcOZKoqCiqVq3K1q1bsbKyMmzzxx9/G
F149yzs\nf/TRR0yfPp1SpUoRGBhItWrVMrS35yXX65gxY9i5cyfwzzsG/m3RokV88MEHQMLfUU+ePGHixI
n8\n+eef5MqVy/A77dnb/jJDcn3OnTuX33//nfXr13Pv3j1sbW2pW7cuK1euNPqZZsbvYrOoqKhX+xZl\nI
iIiYnK6hkBEREQUCERERESBQERERFAgEBERERQIREREBAUCERERQYFARF5CUFAQ1tbWWFtbc/78\n+QTrDx
w4YFi/d+/eDKnJ3d2dfv36mXw/fn5+ht6sra2xsbGhZs2aLFiw4IU/VTEoKIg1a9akc6Ui\nqaNAICIvzcr
KivXr1ydYvm7dOqObrbyJvv32W3bt2sUXX3yBm5sbEydOZNGiRS8019q1awkKCkrn\nCkVSR4FARF7a++
+/z8aNG4mP///7nD1+/Jjg4GCjO7alh+Q+Ija9pWZf1apVo3r16jRu3JjAwEBc\nXFwy9ba5Ii9KgUBEXlq
HDh24cuUKYWFhhmVfffUVcXFxiX6ca/PmzWnevHmC5c8f7n92SuLgwYN0\n7doVBwcHPD09DesXL16Mu7s7
tra2NGjQgB9//DHR+i5evEjv3r1xcnLCxsaGt99+mx07dhiNeXYK\n4Pfff6dNmzYUL16cbt26pen7YG5uT
vny5RPcdjYiIgJfX18qVKiAnZ0dFStWZNiwYURFRRl9Tw4e\nPMihQ4cMpyH+/T1KTQ8iL0OfZSAiL83e3p
7atWuzYcMGw2fQr1+/nubNm5MnT56Xnt/X15e2bduy\nevVqnj59CsDq1asZO3YsnTp1ok2bNkRERNCrVy8
ePHhgtO3Vq1d55513KFKkCNOnT6dw4cJs3bqV\nLl26EBQURLNmzYzGd+rUic6dOzN48GDMzdP+N9Ply5cp
VaqU0bLr169TokQJQ+i4ePEic+fOxdvb\nm127dgHwySef4OvrS2xsLJ9+
+imA4XRLWnsQeREKBCKSLjp06MCECROYOXMmUVFR7N27l82bN6fL\n3F5eXkydOtXwOC4ujpkzZ+Lp6UlAQ
IBheeHChenRo4fRtjNmzCA+Pp6vv/6aggULAuDp6cm1a9eY\nPn16ghfTPn36pOmixNjYWACioqJYvXo1J0
6c4PPPPzcaU6dOHerUqWN4XLNmTUqXLs17773HL7/8\nQsWKFSlTpgxWVlbExsZSvXr1l+pB5EXolIGIpIt
WrVoRExPDt99+y6ZNm7C1taV+/frpMve/PxYW\n4Nq1a1y7do1WrVoZLffy8iJ7duO/c/bs2cO7775Lvnz5
ePr0qeHL09OT3377jfv37ye7r5TY2tpS\nuHBhnJ2dmTp1KpMmTUowR0xMDJ988gnVq1fHzs6OwoUL89577
wEk+u6M56W1B5EXoSMEIpIurKys\naN68OevXr+fy5ct4e3u/0CH3xNjZ2Rk9vnnzJgA2NjZGy7Nnz274C/
qZyMhI1q9fn+i7IADu3r1L\nvnz5ktxXSnbv3o25uTl//vkns2fPZvLkyVSuXJm6desaxkyZMoVly5YxatQ
oatSogZWVFdeuXaNz\n585ER0enuI+09iDyIhQIRCTddOjQgfbt2xMXF8dnn32W5LhcuXLx119/JVj+74vs
/s3MzMzosa2t\nLQC3bt0yWv706VPu3r1rtKxgwYJ4eHgwZMiQROcuWrRosvtKSaVKlciePTtVqlTBw8OD6
tWrM3r0\naA4cOGAIRFu3bqVDhw6MHDnSsN3z1zokJ609iLwIBQIRSTcNGzakdevW5M+fHzc3tyTH2dvbEx
wc\nTExMDDlz5gTg4MGDiYaExBQvXpwSJUqwbds2OnfubFgeHBxsuOjwGU9PT44cOUKZMmWwtLR8ga5S\nr
1ChQowaNYoxY8YQHBxsOKXx6NEjcuTIYTQ2sfsNWFhYcOfOnQTLM7IHyboUCEQk3WTLli3ZIwPP\ntGnThl
WrVjFw4EA6derEpUuXWLRoUaoPe5ubmzNq1CgGDRpE//79adu2LREREXz66acJ5hg3bhye\nnp40a9aM3r1
74+DgQFRUFKdPn+bixYsvfBOhpHTv3p2FCxcye/ZsWrZsiZmZGe+88w7r1q2jbNmy\nlC5dmh07dnD48OEE
27q6uvLZZ5+xdetWSpUqRd68eXFxccnwHiRrUiAQkQxXr1495s2bx8KFCwkO\nDqZChQosW7bM6K/9lHTp0
oWHDx+yaNEitmzZgpubGytWrMDX19donL29PSEhIcyYMYNp06Zx+/Zt\nChYsiJubGx07dkzv1rCwsGDkyJ
EMGTKEr776ihYtWjBr1izi4+OZNm0aAI0bN+azzz6jUaNGRtsO\nGTKE8+fPM2jQIB48eECdOnX4+uuvM7w
HyZrMoqKi4lMeJiIiIm8yve1QREREFAhEREREgUBERERQ\nIBAREREUCERERAQFAhEREUGBQERERFAgEBER
ERQIREREBPg/OPb9ldrmtXQAAAAASUVORK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc5081d5240>"
]
},
"metadata": {},
},
{
"data": {
"image/png":
27cvQ4cOZd+
QYbH3bp1Y//
T+vbty+
bgYGB9OrVix9+
36P7f/vjjDz7+
mDNnDvHx//
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc4c1fe0c18>"
]
},
"metadata": {},
}
],
"source": [
"_ = ok.grade(\"q1_3\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"**Question 1.4.** How many more people were murdered in California in 1988
than in 1975? Assign `ca_change` to the answer.\n",
"\n",
"*Hint*: Make sure you understand how murder rate is calculated. Recall the
formula given at the beginning of the project:\n",
"\n",
"$$\\text{murder rate for state X in year Y} = \\frac{\\text{number of murders
in state X in year Y}}{\\text{population in state X in year Y}}*100000$$"
]
},
{
"metadata": {},
"source": [
"Certain mistakes would make your answer to the previous question way too small
or way too big, and the automatic tests don't check that. Make sure your answer
looks reasonable before moving on."
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"726.0"
]
},
"metadata": {},
}
],
"source": [
"ca = murder_rates.where('State', are.equal_to('California'))\n",
"ca\n",
"ca_change =
(ca.where('Year',1988).column(3).item(0)*ca.where('Year',1988).column(2).item(0)-
ca.where('Year',1975).column(3).item(0)*ca.where('Year',1975).column(2).item(0))/10
0000\n",
"np.round(ca_change)"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/backups/XDZ8PA\n",
"\n"
]
}
],
"source": [
"_ = ok.grade('q1_4')\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"# 2. Changes in Murder Rates\n",
"\n",
"In this section, we'll see how to test null hypotheses such as this: \"For
this set of U.S. states, the murder rate was equally likely to go up or down each
year.\"\n",
"\n",
"Murder rates vary widely across states and years, presumably due to the vast
array of differences among states and across US history. Rather than attempting to
analyze rates themselves, here we will restrict our analysis to whether or not
murder rates increased or decreased over certain time spans. **We will not concern
ourselves with how much rates increased or decreased; only the direction of the
change** - whether they increased or decreased."
]
},
{
"metadata": {},
"source": [
"The `np.diff` function takes an array of values and computes the differences
between adjacent items of a list or array as such:\n",
"\n",
" [item 1 - item 0 , item 2 - item 1 , item 3 - item 2, ...]\n",
"\n",
"Instead, we may wish to compute the difference between items that are two
positions apart. For example, given a 5-element array, we may want:\n",
"\n",
" [item 2 - item 0 , item 3 - item 1 , item 4 - item 2]\n",
" \n",
"The `diff_n` function below computes this result. Don't worry if the
implementation uses unfamiliar features of Python, as long as you understand its
behavior."
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([ 99, 990, 9900])"
]
},
"metadata": {},
}
],
"source": [
"def diff_n(values, n):\n",
" return np.array(values)[n:] - np.array(values)[:-n]\n",
"\n",
"diff_n(make_array(1, 10, 100, 1000, 10000), 2)"
]
},
{
"metadata": {},
"source": [
"**Question 2.1.** Implement the function `two_year_changes` that takes an
array of murder rates for a state, ordered by increasing year. For all two-year
periods (e.g., from 1960 to 1962), it computes and returns **the number of
increases minus the number of decreases.**\n",
"\n",
"For example, the array `r = make_array(10, 7, 12, 9, 13, 9, 11)` contains 3
increases (10 to 12, 7 to 9, and 12 to 13), 1 decrease (13 to 11), and 1 change
that is neither an increase or decrease (9 to 9). Therefore, `two_year_changes(r)`
would return 2, the difference between 3 increases and 1 decrease.\n",
"\n",
"*Hint*: Consider using the `diff_n` function."
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"Alaska: -5\n",
"Minnesota: 6\n"
]
}
],
"source": [
"def two_year_changes(rates):\n",
" \"Return the number of increases minus the number of decreases after two
years.\"\n",
" return np.count_nonzero(diff_n(rates,2)>0)-
np.count_nonzero(diff_n(rates,2)<0)\n",
"\n",
"print('Alaska:', two_year_changes(ak.column('Murder rate in Alaska')))\n",
"print('Minnesota:', two_year_changes(mn.column('Murder rate in Minnesota')))"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/backups/1wXJMP\n",
"\n"
]
}
],
"source": [
"_ = ok.grade(\"q2_1\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"We can use `two_year_changes` to summarize whether rates are mostly increasing
or decreasing over time for some state or group of states. Let's see how it varies
across the 50 US states.\n",
"\n",
"**Question 2.2.** Assign `changes_by_state` to a table with one row per state
that has two columns: the `State` name and the `Murder Rate two_year_changes`
statistic computed across all years in our data set for that state. Its first 2
rows should look like this:\n",
"\n",
"|State|Murder Rate two_year_changes|\n",
"|-|-|\n",
"|Alabama|-6|\n",
"|Alaska|-5||\n",
"\n",
"<center>... (48 rows omitted)</center>\n"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAAbEAAAEdCAYAAACCDlkkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAL
EgAACxIB0t1+/AAAIABJREFUeJzt3XdYFOe+B/DvAlbUrFI90iwrSNCoiFgAO4omYjmIYDTR\nKNYYywHRG
DVGBSKxwiEhiD3WoLHkWhIbiqg5N3ajKAE7YlkVUIns3j+87HEF1gF2mR3y/TyPzyPv\nzM77m5dlvztdpl
Qq1SAiIpIgE7ELICIiKiuGGBERSRZDjIiIJIshRkREksUQIyIiyWKIERGRZDHE\niIhIshhiREQkWQwxPUp
LSxO7BEniuJUex6xsOG5lY8zjxhAjIiLJYogREZFkMcSIiEiyGGJERCRZ\nDDEiIpIshhgREUkWQ4yIiCSL
IUZERJJlJmbnx44dw/Lly3HmzBncuXMHsbGxGDJkiGa6Wq1GZGQk\nVq9eDaVSCXd3d0RHR6NZs2YiVk1EU
jV5wSqYm5uL0vemmBmi9FvZibollpubC1dXV0RGRqJGjRpF\npi9duhSxsbGIiorCgQMHYGVlhf79+
+Pp06ciVEtERMZG1BDz9fXFrFmz4O/vDxMT7VLUajXi4uIw\nadIk+Pv7w9XVFXFxccjJycHWrVtFqpiIiI
yJ0R4Ty8zMRFZWFrp27appq1GjBjp06IATJ06IWBkR\nERkLUY+J6ZKVlQUAsLKy0mq3srLCnTt3Snyd2De
qFLt/qeK4lR7HrGxyc3NF6Vfqvy+x6lcoFDqn\nG22IldXbVtiQ0tLSRO1fqjhupccxKzuxTuyQ8u/LmN9v
Rrs70cbGBgCQnZ2t1Z6dnQ1ra2sxSiIi\nIiNjtCHm6OgIGxsbHDx4UNP2/PlzHD9+HJ6eniJWRkRExkLU3
Yk5OTlIT08HAKhUKty8eRNnz55F\n3bp1YW9vj7Fjx2LRokVQKBRo0qQJoqOjYW5ujn/
+859ilk1EREZC1BD7/fff8cEHH2h+joiIQERE\nBIKCghAXF4fPPvsMz549Q2hoqOZi56SkJNSuXVvEqomI
yFiIGmLe3t5QKpUlTpfJZJg+fTqmT59e\ngVUREZFUGO0xMSIiordhiBERkWQxxIiISLIYYkREJFkMMSIik
iyGGBERSRZDjIiIJIshRkREksUQ\nIyIiyWKIERGRZDHEiIhIshhiREQkWQwxIiKSLIYYERFJFkOMiIgkiy
FGRESSxRAjIiLJYogREZFk\nMcSIiEiyGGJERCRZDDEiIpIshhgREUkWQ4yIiCSLIUZERJLFECMiIsliiBE
RkWQxxIiISLIYYkRE\nJFmCQywqKgoXL14scfqlS5cQFRWll6KIiIiEEBxikZGRuHDhQonTGWJERFTR9LY7
MScnB1WqVNHX\n4oiIiN7KTNfE8+fP49y5c5qfjx8/jpcvXxaZT6lUIjExEQqFQv8VEhERlUBniO3atUuzi
1Amk2Hl\nypVYuXJlsfPK5XLEx8frv0IiIqIS6Ayxjz/
+GL169YJarUbXrl0xY8YM9OjRo8h85ubmaNiwIczM\ndC6u1AoKChAREYHNmzcjKysLNjY2GDRoEMLDw/Xe
F/09BU5YIFrfm2JmiNY3UWWhMwlsbW1ha2sL\nANi5cyecnZ1hZWVVIYUBwJIlS5CQkIC4uDi4urriwoULG
Dt2LKpWrYqwsLAKq4OIiIyT4M0ZLy8v\nQ9ZRrJMnT6JXr17w8/MDADg6OsLPzw//
+c9/KrwWIiIyPiWG2Pjx4yGTybB06VKYmppi/Pjxb12Y\nTCZDTEyM3opr164dVqxYgStXrqBp06b4448/k
JycjMmTJ+utDyIikq4SQ+zIkSMwMTGBSqWCqakp\njhw5AplMpnNhb5teWpMmTUJOTg48PT1hamqKly9f4l
//
+hdGjhxZ4mvS0tL0WkNpid2/VIk1brm5\nuaL0C5R/nfleKxuxfudS/32JVf/bznovMcReP7W+uJ8rQlJSE
jZu3IiEhAS4uLjg3LlzCA8Ph4OD\nA4YNG1bsa8Q8zT8tLY2XGZSBmONmbm4uSr9A+d6rfK+VnVi/cyn/vo
z5/WbUp/jNmjULEyZMwMCB\nAwEA7777Lm7cuIHFixeXGGJERPT3UaYQy8nJgVKphFqtLjLN3t6+3EUVysv
Lg6mpqVabqakpVCqV\n3vogIiLpEhxiz58/R1RUFNauXYuHDx+WOJ+uaaXVq1cvLFmyBI6OjnBxccHZs2cR
GxuLwYMH660P\nIiKSLsEhNnXqVGzYsAF9+vRB+/btIZfLDVkXAODrr7/G/PnzMXXqVNy/fx82Njb46KOPe
I0YEREB\nKEWI7dy5E8OGDcOSJUsMWY+W2rVrIzIyEpGRkRXWJxERSYfgu9jLZDK89957hqyFiIioVASHWO
/e\nvXHo0CEDlkJERFQ6gkNs6tSp+PPPPzFx4kT89ttvuHv3LrKzs4v8IyIiqiiCj4l5eHgAeHXR87p1\n6
0qcT59nJxIREekiOMTCwsL0flspIiKi8hAcYtOnTzdkHURERKUm+JgYERGRsRG8JRYVFfXWeWQy\nGS9EJi
KiCiM4xHRdcCyTyaBWqxliRERUoQSH2KNHj4q0qVQqXL9+HQkJCUhJScHWrVv1WhwREZEu\n5TomZmJiAic
nJ8ybNw+NGzfmVhgREVUovZ3Y0aFDB+zbt09fiyMiInorvT0U8/fff4eJCU92JBIq\ncMKCMr82Nze3XE8o
3hQzo8yvJTImgkNsw4YNxbY/fvwYKSkpmrvcExERVRTBITZu3LgSp1lYWGDy\n5Mk8JkZERBVKcIidOXOmS
JtMJoNcLkft2rX1WhQREZEQgkPMwcHBkHUQERGVGs/EICIiyWKIERGR\nZDHEiIhIshhiREQkWQwxIiKSLE
EhlpeXh3r16iE6OtrQ9RAREQkmKMRq1qwJS0tL1KlTx9D1EBER\nCSZ4d2K/fv2wbds2qFQqQ9ZDREQkmOC
Lnd9//30kJyejV69eGDZsGJycnFCjRo0i87m7u+u1QCIi\nopIIDjF/f3/N/0+dOgWZTKY1vfDJzg8fPtRf
dURERDoIDrHY2FhD1kFERFRqgkMsODjYkHUQERGV\nWpmuE7t27RpSU1Px+PFjfddDREQkWKlCbMuWLXBzc
4OHhwd69+6N06dPAwAePHgAd3d3bNu2zSBF\nEhERFUdwiP30008ICQlB06ZNMXfuXKjVas00CwsLNG3aFB
s3bjRIkURERMURHGLffPMNOnfujKSk\npGKPj7Vp0wbnz5/Xa3EAcPfuXYwZMwaNGzeGjY0NPD09cfToUb3
3Q0RE0iP4xI4rV65g/vz5JU63\nsrLC/fv39VJUIaVSiZ49e6Jdu3bYvHkzLCwskJmZCSsrK732Q0RE0iQ4
xGrWrInc3NwSp//555+w\nsLDQS1GFli1bBltbW3z33XeaNicnJ732QfR3FDhhgWh9b4qZIVrfVPkI3p3o4
+ODH374Afn5+UWm\n3blzB6tXr0bXrl31Wtzu3bvh7u6O4cOHo0mTJvDy8kJ8fLzW8TgiIvr7Erwl9sUXX6
Bbt27o3Lkz\n+vXrB5lMhv379+PgwYNYvXo1TE1NMW3aNL0Wl5GRgRUrVmDcuHGYNGkSzp07p+kjJCSk2Ne
kpaXp\ntYbSErt/qRJr3HTtXTB2Uq1d7L8RscZN7PUuL7HqVygUOqcLDrHGjRtj7969CA8PR2RkJNRqteYu
\nHt7e3li0aBHs7e3LV+0bVCoVWrVqhdmzZwMA3nvvPaSnpyMhIaHEEHvbChtSWlqaqP1LlZjjZm5u\nLkq
/5ZWbmyvZ2sX+GxFr3MRe7/Iw5s82wSEGAM7Ozti2bRuUSiXS09OhUqng5OQES0tLgxRnY2MD\nZ2dnrbam
TZvi5s2bBumPiIikpVQhVkgul6N169b6rqWIdu3a4erVq1ptV69e1fsWHxERSVOp7tih\nVCoxf/58+Pj4w
MnJCU5OTvDx8cH8+fOhVCr1Xty4ceNw6tQpREdHIz09Hdu3b0d8fDxGjhyp976I\niEh6BIdYeno6vLy8EB
0djZcvX8Lb2xve3t54+fIloqOj0bFjR1y7dk2vxbVu3Rrr16/Htm3b0L59\ne3z11VeYMWMGQ4yIiACUYnd
iaGgonjx5gp9+
+gk+Pj5a0w4fPoyhQ4di2rRp2Lp1q14L7NmzJ3r2\n7KnXZRIRUeUgeEvs+PHjGDNmTJEAA4BOnTph9OjRS
ElJ0WtxREREuggOsXfeeQdyubzE6XK5HO+8\n845eiiIiIhJCcIgNHToU69atw9OnT4tMe/z4MdatW4dhw4
bptTgiIiJdBB8TUygUkMlkaNOmDYKC\ngtCoUSMArx6QuXHjRlhZWUGhUBR5plj//v31WzEREdH/Exxir98
hY+nSpUWm37t3DyEhIVr3NZTJ\nZAwxIiIyGMEhtnPnTkPWQUREVGqCQ8zLy8uQdRAREZVaqe7YQUREZEwY
YkREJFkMMSIikiyGGBER\nSRZDjIiIJEtwiEVFReHixYslTr906RKioqL0UhQREZEQgk+xj4yMRKNGjeDq6
lrs9MIQmzZtmt6K\nI6LKJ3DCArFLoEpEb7sTc3JyUKVKFX0tjoiI6K10bomdP38e586d0/x8/PhxvHz5ss
h8SqUSiYmJ\nUCgU+q+QiIioBDpDbNeuXZrjXDKZDCtXrsTKlSuLnVculyM+Pl7/FRIREZVAZ4h9/PHH6NW
rF9Rq\nNbp27YoZM2agR48eReYzNzdHw4YNYWYm+BAbERFRuelMHVtbW9ja2gJ4dQNgZ2dnWFlZVUhhRERE
\nb8MbABMRkWSVav/fr7/+irVr1yIjIwNKpVLr2WHAq+Nmp0+f1muBREREJREcYsuWLcOcOXNgbW2N\n1q1
bl3i9GBERUUURHGLffvstfHx8sGXLFl4PRkRERkHwxc5KpRL+/v4MMCIiMhqCQ8zd3R1paWmG\nrIWIiKhU
BIdYdHQ0du3ahc2bNxuyHiIiIsEEHxMbNmwY8vPzMWbMGEyePBn169eHqamp1jwymQyp\nqal6L5KIiKg4g
kPM0tISVlZWaNKkiSHrISIiEkxwiO3evduQdRAREZUan+xMRESSVaoQe/jwIebN\nm4eePXuidevWOHnypK
Y9KioKly9fNkiRRERExRG8OzEzMxN+fn54+PAhXF1dkZGRgWfPngEA6tWr\nh6SkJNy/fx8LFy40WLFERES
vExxis2fPhlqtRmpqKmrXrl3kBI/evXvzuBkREVUowbsTDx06hFGj\nRsHJyQkymazIdEdHR9y+fVuvxb1p
0aJFkMvlCA0NNWg/REQkDYJD7MWLF5DL5SVOf/z4MUxMDHee\nyKlTp7Bq1Sq8+
+67BuuDiIikRXDqNGvWDMeOHStx+u7du9GiRQu9FPWmx48fY9SoUYiJidEZpERE\n9PciOMTGjh2Lbdu2IT
o6Go8ePQIAqFQqXLlyBSNHjsRvv/2G8ePHG6TISZMmwd/fHz4+PgZZPhER\nSZPgEzsCAgJw8+ZNLFiwAAs
WLAAADBw4EABgYmKCL7/8En5+fnovcPXq1UhPT0d8fLyg+cW+SbHY\n/UuVWOOWm5srSr/6IOXaxSTWuEn9
s0Gs+hUKhc7ppXqy8+TJkxEQEIAdO3YgPT0dKpUKDRs2xAcf\nfAAnJ6fy1FmstLQ0zJ07F3v27BH8CJi3r
bAhpaWlidq/VIk5bubm5qL0W165ubmSrV1MYo6blD8b\njPmzrVQhBgB2dnYYN26cIWop4uTJk3jw4AHatW
unaSsoKEBKSgoSExNx+/ZtVKtWrUJqISIi4yM4\nxFJTU5GSkoIpU6YUO33x4sXo2LEj2rZtq7fi+vTpg1a
tWmm1jR8/Ho0bN8aUKVNQtWpVvfVFRETS\nIzjEoqKidJ4ZeP78eRw9ehQ//vijXgoDALlcXqTPmjVrom7d
unB1ddVbP0REJE2Cz048e/aszq0s\nDw8PnDlzRi9FERERCSF4SywvL6/YO3W8Licnp9wFvQ1vbUVERIUEb
4k1adIEBw4cKHH6L7/8gkaN\nGumlKCIiIiEEh9iwYcOwf/9+hIWFaS52Bl49hiU0NBQHDhzA0KFDDVIkER
FRcQTvThw1ahTOnTuH\n77//HgkJCbC2tgYA3Lt3D2q1GsHBwRg7dqzBCiUiInpTqa4TW7ZsmeZi54yMDAC
Ak5MT/P394eXl\nZYj6iIiISiQoxPLz83Hq1CnY2trC29sb3t7ehq6LiIjorQQdEzMzM0O/fv10nthBRERU
0QSFmImJ\nCRwcHCrkFHoiIiKhBJ+dOGbMGKxatQrZ2dmGrIeIiEiwUl3sXLNmTbRu3Rp9+vSBk5MTatSoo
TWP\nTCbDxIkT9V4kERFRcQSH2Jw5czT/37RpU7HzMMSIiKgiCQ4x3heRiIiMjeAQc3BwMGQdREREpVbq\n
h2Jeu3YNR48eRXZ2NgICAuDo6Ij8/HxkZWXBxsaGz/giIqIKIzjEVCoVJk+ejLVr10KtVkMmk8HD\nw0MTY
h07dkRoaCg+/fRTQ9ZLBhI4YYFofYv5yHgikjbBp9h/8803WLduHT7//HPs378farVaM61W\nrVr44IMPsG
vXLoMUSUREVBzBIbZ+/Xp8+OGHmDp1arGPXHF1dcW1a9f0WhwREZEugkPs9u3bcHd3\nL3F6jRo1eEcPIiK
qUIJDzNraGtevXy9x+unTp2Fvb6+XooiIiIQQHGJ9+/ZFYmKi1i5DmUwGANi/\nfz82btyIfv366b9CIiKi
EggOsfDwcNjZ2cHHxwejRo2CTCbDokWL0L17dwQGBsLNzQ1TpkwxZK1E\nRERaBIdYnTp1sG/fPkyZMgX37
t1D9erVkZqaitzcXISHh+Pnn38uci9FIiIiQyrVxc7Vq1fH1KlT\nMXXqVEPVQ0REJNhbQ+z58+f4+eefkZ
mZiXr16qFnz56wtbWtiNqIiIh00hlid+7cQe/evZGZmam5\nuLlmzZrYuHEjvL29K6RAIiKikug8JjZv3jx
cv34d48aNw6ZNmxAREYHq1atj2rRpFVUfERFRiXRu\niR06dAhBQUGYN2+eps3a2hojR47ErVu30KBBA4MX
SEREVBKdW2JZWVnw9PTUamvXrh3UajVu3rxp\n0MKIiIjeRmeIFRQUoHr16lpthT8/f/7ccFUREREJ8NazE
zMyMvCf//xH8/OTJ08AAGlpaahVq1aR\n+XXdX5GIiEif3hpiERERiIiIKNIeFham9XPhM8YePnyov+qIiI
h00BlisbGxFVUHERFRqekMseDg\n4Iqqg4iIqNQE3ztRDIsWLUKXLl1gb2+Pxo0bIzAwEBcvXhS7LCIiMhJ
GHWJHjx7FJ598gr1792LH\njh0wMzNDv3798OjRI7FLIyIiI1CqGwBXtKSkJK2fv/vuOzg4OCA1NRV+fn4i
VUVERMbCqLfE3pST\nkwOVSgW5XC52KUREZASMekvsTeHh4WjevDnatm1rkOUHTlhQrtfn5ubC3Ny8TK/dF
DOjXH0TkXEr\n7+eLmIz5s00yITZjxgykpqZiz549MDU1LXG+tLS0MveRm5tb5teWdxnlqVsf9LHuUu5fij
hmZcNx\nKxuxPtsUCoXO6ZIIsenTpyMpKQk7d+6Ek5OTznnftsK6lPWbRqHyfFspT936UN51L4/yjNvfFce
s\nbDhuZWPMn21GH2LTpk3Dtm3bsHPnTjRt2lTscoiIyIgYdYj961//wqZNm7Bu3TrI5XJkZWUBeLXV\nUN
x9G4mI6O/FqM9OTEhIwNOnT+Hv7w9nZ2fNv+XLl4tdGhERGQGj3hJTKpVil0BEREbMqLfEiIiI\ndGGIERG
RZDHEiIhIshhiREQkWQwxIiKSLIYYERFJFkOMiIgkiyFGRESSxRAjIiLJYogREZFkMcSI\niEiyGGJERCRZ
DDEiIpIshhgREUkWQ4yIiCTLqJ8n9ncSOGGB2CUQEUkOt8SIiEiyGGJERCRZDDEi\nIpIshhgREUkWQ4yIi
CSLIUZERJLFECMiIsliiBERkWQxxIiISLIYYkREJFkMMSIikiyGGBERSRZD\njIiIJIshRkREksUQIyIiyW
KIERGRZDHEiIhIsiQRYgkJCWjRogVsbGzQqVMnpKSkiF0SEREZAaMP\nsaSkJISHh2Pq1Kk4cuQI2rZti4C
AANy4cUPs0oiISGRGH2KxsbEIDg7GRx99BGdnZyxcuBA2NjZI\nTEwUuzQiIhKZmdgF6JKfn4/Tp0/j008/
1Wrv2rUrTpw4off+NsXM0PsyiYjIcIx6S+zBgwcoKCiA\nlZWVVruVlRXu3bsnUlVERGQsjDrEiIiIdDHqE
LOwsICpqSmys7O12rOzs2FtbS1SVUREZCyMOsSq\nVq2Kli1b4uDBg1rtBw8ehKenp0hVERGRsTDqEzsAYP
z48Rg9ejTc3d3h6emJxMRE3L17F8OHDxe7\nNCIiEplRb4kBwIABAxAREYGFCxfC29sbqamp2Lx5MxwcHMQ
uTWPVqlV4//334eDgALlcjszMzCLz\nKJVKhISEwMHBAQ4ODggJCYFSqRShWuPVp08fyOVyrX8jRowQuyyj
w4v/SyciIqLI+6pp06Zil2VU\njh07hsGDB6NZs2aQy+VYv3691nS1Wo2IiAi4uLjA1tYWffr0waVLl0SqV
pvRhxgAjBw5EufOncO9\ne/dw+PBhdOzYUeyStOTl5aFr164IDw8vcZ6RI0fi7Nmz2Lp1K7Zu3YqzZ89i9O
jRFVilNAwZMgSX\nL1/W/Fu8eLHYJRkVXvxfNgqFQut9xeDXlpubC1dXV0RGRqJGjRpFpi9duhSxsbGIior
CgQMHYGVl\nhf79+
+Pp06ciVKvN6HcnSsG4ceMAAL///nux0y9fvoxffvkFe/bsQdu2bQEAixcvhp+fH9LS0qBQ\nKCqsVmNXs2
ZN2NjYiF2G0Xr94n8AWLhwIX799VckJiZi9uzZIldnvMzMzPi+0sHX1xe+vr4A/vt5\nVkitViMuLg6TJk2
Cv78/ACAuLg4KhQJbt24V/dCOJLbEpO7kyZOoVauW1sko7dq1g7m5uUEu2pay\nH3/8EY0aNUK7du0wc+ZM
o/imZywKL/7v2rWrVruhLv6vTDIyMuDi4oIWLVpgxIgRyMjIELskycjM\nzERWVpbW+65GjRro0KGDUbzvu
CVWAe7duwcLCwvIZDJNm0wmg6WlJS/afk1AQADs7e1ha2uLP/74\nA19+
+SUuXLiAbdu2iV2aUeDF/2XTpk0b/Pvf/4ZCocD9+/excOFC+Pr6IjU1FfXq1RO7PKOXlZUF\nAMW+7+7cu
SNGSVoYYiWYN28eoqOjdc6zc+dOeHt7V1BF0lSacfz44481be++
+y6cnJzQrVs3nD59\nGi1btjRwpVRZ9ejRQ+vnNm3aoGXLlvjhhx8wYcIEkaoifWGIlWDs2LEYNGiQznns7
OwELcva2hoP\nHjyAWq3WbI2p1Wrcv3+/0l+0XZ5xbNWqFUxNTZGens4QAy/
+15datWrBxcUF6enpYpciCYXHErOz\ns2Fvb69pN5b3HUOsBBYWFrCwsNDLstq2bYucnBycPHlSc1zs5MmT
yM3NrfQXbZdnHC9cuICCggIe\nkP9/r1/8369fP037wYMH0bdvXxErk5bnz58jLS2Ne1EEcnR0hI2NDQ4eP
IjWrVsDeDWGx48fx9y5\nc0WujiGmF1lZWcjKysLVq1cBvDob8fHjx7C3t0fdunXh7OyM7t27Y/LkyViyZA
kAYPLkyejZsyfP\nTPx/f/75JzZv3gxfX1/Uq1cPly9fxsyZM9GiRQu0a9dO7PKMBi/
+L72ZM2eiV69esLOz0xwTy8vL\nQ1BQkNilGY2cnBzNlqlKpcLNmzdx9uxZ1K1bF/b29hg7diwWLVoEhUKB
Jk2aIDo6Gubm5vjnP
/
8p\ncuWATKlUqsUuQuoiIiIQFRVVpD02NhZDhgwB8Opi57CwMPzP//wPAMDPzw9ff/015HJ5hdZqrG7e\nv
ImQkBBcunQJubm5aNCgAXx9fREeHo66deuKXZ5RSUhIwNKlS5GVlYVmzZphwYIFRnftpDEZMWIE\nUlJS8O
DBA1haWqJNmzb4/PPP4eLiInZpRiM5ORkffPBBkfagoCDExcVBrVYjMjISq1atglKphLu7\nO6Kjo+Hq6ip
CtdoYYkREJFm8ToyIiCSLIUZERJLFECMiIsliiBERkWQxxIiISLIYYkREJFkMMYlb\nv3695kF/hRdbv+7o
0aOa6YcOHaqQmpo3b46xY8cavJ83H3ZobW0NT09PLFu2DCqVqkzLXL9+Pdau\nXavXOpOTkxEREVHmmkiY5
OTkCn2fk3FgiFUStWvXxsaNG4u0b9iwAbVr1xahooqzZ88e7N+/H+vW\nrUOzZs0wa9YsxMbGlmlZP/zwQ5
Gn2pbX0aNHERUVxRAjMgCGWCXx/vvvY/PmzVCr/3vt+rNnz7Bj\nx45ir8QvjxcvXuh1eeXtq02bNvDw8IC
vry8SExOhUCiwZs2aCqiOykutViM/P1/sMkjCGGKVxODB\ng3Hjxg0cP35c07Zr1y6oVKpibw7bp08f9OnT
p0j7m7sCC3dXHjt2DB999BEcHBzQrVs3zfS4uDg0\nb94cNjY26Ny5c4mPfc/IyMCoUaPQuHFjWFtbw8vLC
zt37tSap3D34MWLFzFgwAA0aNBA6/EsQpiY\nmMDNzQ03b97Uak9PT0dISAhatGgBW1tbvPfee5gyZQqUSq
XWmBw7dgypqamaXZSvj5GQdXjT67ck\ns7S01CwXADp06IBPP/1UM+/jx49hYWFR5FY+PXv21DzJGQCePHm
C0NBQuLi4wNraGm3atEFsbKzW\nFxhdXrx4gcaNG2P69OlFphX+vq9cuaJpO3r0KPr27Qs7Ozv84x//wIAB
A3Dx4kWt1x04cAABAQFw\ndnZG/fr10b59eyxfvhwFBQVa8zVv3hwhISFYu3YtPDw8YGVlhb179wqq+
+XLl1iyZAk8PT1hY2OD\nxo0bY+DAgVq1AkBeXh5CQ0PRqFEjNGrUCCEhIVq/ZwCIj49Hjx494OTkBAcHB3
Tv3r1IHZmZmZDL\n5Vi5ciXmz58PZ2dnODg4IDAwELdu3SrS55QpU9CwYUM0aNAAQ4YMwYkTJyCXy4ts2Qs
Zz19//RW+\nvr5wcHBAgwYN0KZNm2JvbUe8AXClYW9vjw4dOmDTpk3o0KEDAGDjxo3o06cPzM3Ny738kJAQ
DBw4\nEGvWrMEH0gfXAAANYElEQVTLly8BAGvWrMH06dMRHByMAQMGID09HSNHjkROTo7Wa2/evInu3bvD\
nysoKCxYsgKWlJZKSkjBs2DCsX78evXv31po/ODgYQ4cOxWeffQYTk9J/z7p+/ToaNmyo1Xbnzh3Y\n2dlp
gjIjIwOLFi1CQEAA9u/fDwD45ptvEBISgoKCAs2Nmgt3xZZ2HQoNGzYMt2/fxtq1a7Fnzx6Y\nmppqpnl5e
Wl9cB49ehRVq1bF7du3cfXqVTRp0gQ5OTn43//9X0RGRgJ4dXPWwMBAnDlzBtOnT8e7\n776LvXv34vPPP8
eDBw8wa9ast45PtWrVMGTIEKxduxazZ89G9erVNdNWrVqFjh07omnTpgCAvXv3\nIjg4GL6+vvjuu+8AAEu
XLoWfnx+OHTumeYxORkYGfHx8EBISgmrVquH06dOIiorCgwcPMGfOHK3+\nk5OTce7cOUybNg1WVlZwcHB4
a83Aq3sg7t69G2PHjkXnzp3x/PlzpKSk4O7du5p6ASA8PBw9e/ZE\nQkIC0tLSMHv2bJiYmODbb7/VzHP9+
nUMHToUjo6OePnyJfbs2YPAwEBs3boV3bt31+p30aJF8PT0\nRExMDLKzszFz5kyEhIRg9+7dmnkmTZqE7d
u3Izw8HK1atcLhw4cxatSoIusgZDwzMjIQFBQEf39/\nhIWFoUqVKkhPT+fTqEvAEKtEBg8ejJkzZyIqKgp
KpRKHDh3C1q1b9bLsvn37aj12QaVSISoqCt26\ndcO///1vTbulpSVGjBih9drIyEio1Wrs3r1b8yTdbt26
4datW1iwYEGRABg9enSpTgwp/LavVCqx\nZs0anD59GqtXr9aap2PHjlo3yfX09ESjRo3g5+eHM2fO4L333
oOLiwtq166NgoICeHh4lGsdCjVo\n0AD/
+Mc/ALza7Wlm9t8/OW9vb8THx+P69etwcHBAcnIyOnXqhCtXriA5ORlNmjRBamoq/vrrL81j\nQ/bt24fjx
49r3Vy6a9euyMvLQ0xMDMaPHy/o0TcjRoxATEwMtm/fjsGDBwMAzp8/j1OnTmHFihWa\n+cLDw9GxY0ds2L
BBq+6WLVsiJiZGE66v/87VajU6dOiA/Px8LF++HLNmzdL6MlL43izNI3YOHz6M\nHTt2IDIyEmPGjNG0v//
+
+0Xm7dChAxYuXAjg1dhcvXoVa9asQVxcnOZ5fvPmzdPMr1Kp0KlTJ1y9\nehUrVqwoEmIODg5ISEjQ/Pzgw
QN88cUXuHPnDurXr4+0tDRs2bIFc+bMwWeffQYA6NKlC/Ly8hAf\nH6+1LCHjeebMGeTn5+Obb75BnTp1AA
CdOnUSPFZ/N9ydWIn069cP+fn52LNnD7Zs2QIbGxu9vfnf\n/LC4desWbt26pfVcK+BV2L3+QQ282jXSo0c
P1KlTBy9fvtT869atG86fP48nT57o7OttbGxsYGlp\niSZNmmDu3LmYPXt2kWUUfih4eHjA1tYWlpaW8PPz
A4Biz+p8U2nXQQhvb2+YmJjgyJEjAIAjR47A\nx8cHPj4+Wm22traaLY2UlBSYmJggICBAa1mDBg1Cfn4+T
p48Kajvwqdmr1q1StO2atUqWFpaao6h\nXrt2DX/+
+ScCAgK01rlmzZrw8PDQ2nV89+5dTJo0CW5ubrCysoKlpSXmzZuHx48fF3mIZ5s2bUr9\njLiDBw9CJpNp7
VYtSc+ePbV+dnV1xYsXL3Dv3j1N2+nTpxEYGAiFQgELCwtYWlri4MGDxb4XfH19\niywPgGaX9W+//Qa1Wg
1/f3+t+d78Weh4Nm/eHFWqVMEnn3yCn376qcj4kTZuiVUitWvXRp8+fbBx\n40Zcv34dAQEBZdodVxxbW1u
tn7OysgCgyJNdzczMNFsqhbKzs7Fx48Ziz54EgIcPH2q+cRbX19v8\n8ssvMDExwe3bt7Fw4ULMmTMHrVq1
0nro4Zdffon4+HiEhYWhbdu2qF27Nm7duoWhQ4fi+fPnb+2j\ntOsghFwuh5ubG5KTk+Hn54dLly7B29sbN
jY2CA8PB/Bq19vr6/Ho0SPUrVsXVatW1VpWYSg8evRI\ncP+ffPIJBg8ejIsXL8LR0RGbN2/G8OHDNcsu/P
D89NNPtY7dFSrclahSqRAUFIS7d+8iPDwcCoUC\nNWrUwO7duxEdHV1kfEv7+wVejW/dunVRo0aNt8775qN
7CtensI6bN2+ib9+
+cHFxwddffw07OzuY\nmZlh/vz5uHz5cqmXV/i3YGVlpTXfm38bQsezUaNG+PHHH7F06VKMHj0aL168gLu7
O+bMmQMvL6+3\nrv/fDUOskhk8eDAGDRoElUqltVvoTdWrV8fTp0+LtL95ALxQ4W6YQoUfmq9/uwVeHXx/
+PChVlu9\nevXQvn17TJo0qdhl169fX2dfb9OyZUuYmZmhdevWaN+
+PTw8PDBt2jQcPXpUE+JJSUkYPHgwQkND\nNa9789idLqVdB6G8vb2xfft2JCcno169enBzc4OtrS2ys7OR
mpqKs2fPaj3wsm7dunj06BHy8/O1\ngqzwg7Q0z14rPHFg5cqVaN68OZ4+fap1Ik3hl5HZs2ejc+fORV5fp
UoVAK8eaPr777/ju++
+Q2Bg\noGZ64bPz3lTa3y/w6gnhjx49wrNnzwQFmS6//vornjx5gpUrV6JBgwaa9ry8vDItr/BvITs7W+v4
\n85t/G0LHE4Bmi/zFixdITU1FREQEAgMDcfbsWb09cb6y4O7ESqZLly7o378/RowYgWbNmpU4n729\nPa5
evap1evOxY8eKDbbiNGjQAHZ2dti+fbtW+44dOzQnfhTq1q0bLly4ABcXF7Rq1arIv2rVqpVi\nDXWzsLBA
WFgYLl68iB07dmja8/LytD4kABR7PVi1atXw7NmzIu3lWYfCacUt18fHB7du3cLKlSvh\n5eUFmUwGKysrN
GvWDBERESgoKNDaEuvYsSNUKlWRcd+yZQuqVq2Ktm3blljHm0xMTDB8+HBs2rQJ\n8fHx6Ny5s9YJMQqFAg
4ODrh06VKx6+zm5gbgvx/
+r4/vX3/9hS1btgiu5W26dOkCtVqtl0sniqv3\n6tWrOHHiRJmW5+7uDplMhp9+
+kmr/c3fkdDxfF21atXQqVMnTJw4Ebm5ucjMzCxTjZUZt8QqGVNT\nU51bYIUGDBiAVatWYcKECQgODkZmZ
iZiY2MF7xIzMTFBWFgYJk6ciHHjxmHgwIFIT0/HkiVLiixj\nxowZ6NatG3r37o1Ro0bBwcEBSqUSly5dQk
ZGRpkvTC7J8OHDsXz5cixcuBD+/v6QyWTo3r07NmzY\nAFdXVzRq1Ag7d+4s9viRs7MzVqxYgaSkJDRs2BC
1atWCQqEo1zo4OzsDAGJiYtCjRw+YmpqiVatW\nAID27dvD1NQUhw8fRnR0tOY1Xl5e+P7772FnZ6cVLD16
9ED79u0xZcoU3L9/H82aNcO+ffuwZs0a\nTJkypdTf0ocOHYrIyEicP3+
+SEDIZDJER0cjODgYf/31F/r16wcLCwtkZ2fjxIkTsLOzw4QJE+Ds\n7Ax7e3t89dVXMDU1hZmZmdbJPvrg
4+ODvn374vPPP8etW7fg4+ODv/76CykpKfD19dUK+rfp3Lkz\nzMzMMGbMGEyYMAF3795FREQE7OzsynRBe
tOmTREQEID58+dDpVKhZcuWOHLkCPbs2QMAmr0BQscz\nMTERKSkp6NGjBxo0aIAHDx5g8eLFqF+/vs4vpn
9X3BL7m/Lx8cHixYvx22+/YfDgwVi/fj3i4+Px\nzjvvCF7GsGHDEBERgSNHjiA4OBjr169HQkJCkWXY29v
j4MGDcHNzw1dffYX+/ftj6tSpOHbsGHx8\nfPS9aqhWrRpCQ0Nx4cIF7Nq1CwDw9ddfw8/PD1999RWGDx+O
nJycYsN+0qRJmm+
+Xbp00ew+LM86\n9OrVCyNHjsSKFSvQo0cPdOnSRTOtTp06aNmyJQBoLafw/29+OJuYmGDTpk0ICgrC0qVL
MWjQIOzb\ntw/z58/HF198UeqxsrS0RMeOHWFra1vsGZa+vr74+eefkZeXh4kTJ2LgwIGYNWsW7t27p9nqq
1q1\nKtavXw8bGxuMGTMGoaGh6NChAyZPnlzqenRJTExEeHg4du/ejaCgIEyYMAF//PFHqY+xNWvWDN9/\n
/z1u3LiBoKAgLFu2DHPmzNFcmlIWS5YswYcffoilS5fiww8/xKVLlzRfSl7/UidkPN3c3JCbm4u5\nc+diw
IABCAsLg6OjI3bs2FHuXamVkUypVAq7QpKIKh2lUgk3NzeMGTMGM2fOFLucSqXw8oKzZ8/C\n3t5e7HIqLe
5OJPobun//PtLS0vDtt99CpVJh5MiRYpckaXv27MGlS5fQvHlzmJiYICUlBTExMejf\nvz8DzMAYYkSVTEF
Bgc5bUJmYmGDv3r0YP3487OzsEBcXV6bT3vVFSL36ulTEUGrVqoXdu3dj8eLF\nyMvLQ/369TF69Ohib+1F
+sXdiUSVTPPmzXHjxo0Sp0+bNs2oPlwL71lZkqCgIMTFxVVgRSQlDDGi\nSubChQs67wxva2tb5uvaDCEtL
U3nNXv16tWDo6NjBVZEUsIQIyIiyTLuHc1EREQ6MMSIiEiyGGJE\nRCRZDDEiIpIshhgREUnW/wEwey0xMM
2/RAAAAABJRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc4c1ee2630>"
]
},
"metadata": {},
}
],
"source": [
"states = murder_rates.sort('State',distinct= True).column(0)\n",
"change = make_array()\n",
"for i in np.arange(len(states)):\n",
" c = two_year_changes(murder_rates.where('State',states[i]).column(3))\n",
" change = np.append(change,c)\n",
"changes_by_state = Table().with_columns('State',states,'Murder Rate
two_year_changes',change)\n",
"# Here is a histogram of the two-year changes for the states.\n",
"# Since there are 50 states, each state contributes 2% to one\n",
"# bar.\n",
"changes_by_state.hist(\"Murder Rate two_year_changes\", bins=np.arange(-11,
12, 2))"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" <thead>\n",
" <tr>\n",
Rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
],
"text/plain": [
"Alaska | 1960 | 226,167 | 10.2\n",
"Alaska | 1961 | 234,000 | 11.5\n",
"Alaska | 1962 | 246,000 | 4.5\n",
"Alaska | 1963 | 248,000 | 6.5\n",
"Alaska | 1964 | 250,000 | 10.4\n",
"Alaska | 1965 | 253,000 | 6.3\n",
"Alaska | 1966 | 272,000 | 12.9\n",
"Alaska | 1967 | 272,000 | 9.6\n",
"Alaska | 1968 | 277,000 | 10.5\n",
"Alaska | 1969 | 282,000 | 10.6\n",
]
},
"metadata": {},
}
],
"source": [
"murder_rates"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/backups/31ZL3x\n",
"\n"
]
}
],
"source": [
"_ = ok.grade(\"q2_2\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"Some states have more increases than decreases (a positive number), while some
have more decreases than increases (a negative number). \n",
"\n",
"**Question 2.3.** Assign `total_changes` to the total increases minus the
total decreases for all two-year periods and all states in our data set. For
example, if the murder rate in Ohio went up 23 times and fell 17 times, the total
change for Ohio would be 6. We want the total value for all the states together."
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"Total increases minus total decreases, across all states and years: 45.0\n"
]
}
],
"source": [
"total_changes = sum(change)\n",
"print('Total increases minus total decreases, across all states and years:',
total_changes)"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/backups/5y2NMv\n",
"\n"
]
}
],
"source": [
"_ = ok.grade(\"q2_3\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"\"More increases than decreases,\" one student exclaims, \"Murder rates tend
to go up across two-year periods. What dire times we live in.\"\n",
"\n",
"\"Not so fast,\" another student replies, \"Even if murder rates just moved up
and down uniformly at random, there would be some difference between the increases
and decreases. There were a lot of states and a lot of years, so there were many
chances for changes to happen. If state murder rates increase and decrease at
random with equal probability, perhaps this difference was simply due to
chance!\"\n",
"\n",
"**Question 2.4.** Set `num_changes` to the number of distinct two-year periods
in the entire data set that could result in a change of a state's murder rate for
all states. Include both those periods where a change occurred and the periods
where a state's rate happened to stay the same.\n",
"\n",
"For example, Alaska during 1968 to 1970 would count as one distinct two-year
period - how many of these periods are there total? "
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" <thead>\n",
" <tr>\n",
Rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>Alabama</td> <td>1960</td> <td>3,266,740 </td> <td>12.4
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
],
"text/plain": [
"Alabama | 1960 | 3,266,740 | 12.4\n",
"Alabama | 1961 | 3,302,000 | 12.9\n",
"Alabama | 1962 | 3,358,000 | 9.4\n",
"Alabama | 1963 | 3,347,000 | 10.2\n",
"Alabama | 1964 | 3,407,000 | 9.3\n",
"Alabama | 1965 | 3,462,000 | 11.4\n",
"Alabama | 1966 | 3,517,000 | 10.9\n",
"Alabama | 1967 | 3,540,000 | 11.7\n",
"Alabama | 1968 | 3,566,000 | 11.8\n",
"Alabama | 1969 | 3,531,000 | 13.7\n",
]
},
"metadata": {},
}
],
"source": [
"murder_rates.where('State',states[0])"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"2100.0"
]
},
"metadata": {},
}
],
"source": [
"pds = make_array()\n",
" pd = murder_rates.where('State',states[i]).num_rows-2\n",
" pds = np.append(pds,pd)\n",
"num_changes = sum(pds) \n",
"num_changes"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/backups/73gPMr\n",
"\n"
]
}
],
"source": [
"_ = ok.grade(\"q2_4\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"We now have enough information to perform a hypothesis test.\n",
"\n",
"> **Null Hypothesis**: State murder rates increase and decrease over two-year
periods as if \n",
"\"increase\" or \"decrease\" were sampled at random from a uniform
distribution, like a fair coin flip.\n",
"\n",
"Murder rates can be more likely to go up or more likely to go down. Since we
observed 45 more increases than decreases for all two year periods in our dataset,
we formulate an alternative hypothesis in accordance with our suspicion:\n",
"\n",
"> **Alternative Hypothesis**: State murder rates are more likely to increase
over two-year periods.\n",
"\n",
"If we had observed more decreases than increases, our alternative hypothesis
would have been defined accordingly (that state murder rates are more likely to
*decrease*). This is typical in statistical testing - we first observe a trend in
the data and then run a hypothesis test to confirm or reject that trend.\n",
"\n",
"*Technical note*: These changes in murder rates are not random samples from
any population. They describe all murders in all states over all recent years.
However, we can imagine that history could have been different, and that the
observed changes are the values observed in only one possible world: the one that
happened to occur. In this sense, we can evaluate whether the observed \"total
increases minus total decreases\" is consistent with a hypothesis that increases
and decreases are drawn at random from a uniform distribution.\n",
"\n",
"*Important requirements for our test statistic:* We want to choose a test
statistic for which large positive values are evidence in favor of the alternative
hypothesis, and other values are evidence in favor of the null hypothesis. This is
because once we've determined the direction of our alternative hypothesis, we only
care about the tail in that direction. If, for example, our p-value cutoff was 5%,
we'd check to see if our observed test statistic fell within the largest 5% of
values in our null hypothesis distribution. \n",
"\n",
"Our test statistic should depend only on whether murder rates increased or
decreased, not on the size of any change. Thus we choose:\n",
"\n",
"> **Test Statistic**: The number of increases minus the number of decreases"
]
},
{
"metadata": {},
"source": [
"The cell below samples increases and decreases at random from a uniform
distribution 100 times. The final column of the resulting table gives the number of
increases and decreases that resulted from sampling in this way. **Using
`sample_from_distribution` is faster than using `sample` followed by `group` to
compute the same result.**"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" <thead>\n",
" <tr>\n",
" <th>Change</th> <th>Chance</th> <th>Chance sample</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>Increase</td> <td>0.5 </td> <td>45 </td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>Decrease</td> <td>0.5 </td> <td>55 </td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"Change | Chance | Chance sample\n",
"Increase | 0.5 | 45\n",
"Decrease | 0.5 | 55"
]
},
"metadata": {},
}
],
"source": [
"uniform = Table().with_columns(\n",
" \"Change\", make_array('Increase', 'Decrease'),\n",
" \"Chance\", make_array(0.5, 0.5))\n",
"uniform.sample_from_distribution('Chance', 100)"
]
},
{
"metadata": {},
"source": [
"**Question 2.5.** Complete the simulation below, which samples `num_changes`
increases/decreases at random many times and forms an empirical distribution of
your test statistic under the null hypothesis. Your job is to\n",
"* fill in the function `simulate_under_null`, which simulates a single sample
under the null hypothesis, and\n",
"* fill in its argument when it's called below."
]
},
{
"metadata": {
"for_assignment_type": "student",
"manual_problem_id": "changes_in_murder_rates_5"
},
"outputs": [
{
"data": {
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAAbUAAAEcCAYAAABAuSr7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAL
EgAACxIB0t1+/AAAIABJREFUeJzt3XlcTfn/B/DXraRkubRaSiQpe8k2CmUkW5jB2GNkZ0SI\nMcQgyb4MM
5pk3zMKw/CTNVkGYx31sI6tkIsiTXV/f3h0v+7cuk51r9s9vZ6Px308umf5nPf9uA+v\ne875nHMkMplMDi
IiIhEw0HUBREREmsJQIyIi0WCoERGRaDDUiIhINBhqREQkGgw1IiISDYYaERGJ\nBkONiIhEg6H2CUlJSbo
uoVhhf6hinyhjfyhjf6jSZp8w1IiISDQYakREJBoMNSIiEg2GGhERiQZD\njYiIRIOhRkREosFQIyIi0WCo
ERGRaBjpugDSL4HzomBmZlakNravnKahaoiIlHFPjYiIREPvQm3x\n4sVo27YtbG1t4eDggN69e+PGjRu6L
ouIiIoBvQu1U6dO4dtvv8WhQ4cQExMDIyMjdOvWDS9fvtR1\naUREpGN6d04tOjpa6f3PP/8MOzs7JCQkwN
fXV0dVERFRcaB3e2r/lZaWhpycHEilUl2XQkREOiaR\nyWRyXRdRFP7+/rh9+zaOHTsGQ0PDPJfhox80J3B
eVJHbWDLNv8htEFHJ5ejomO88vTv8+LFp06Yh\nISEBBw8ezDfQAPUd8ClJSUlFWl+MijqkX2z9ye+IMvaH
MvaHKm32id6G2tSpUxEdHY3Y2FjY29vr\nuhwiIioG9DLUpkyZgj179iA2Nha1a9fWdTlERFRM6F2oBQUFY
fv27di0aROkUimSk5MBfDgkVrZs\nWR1XR0REuqR3ox8jIiLw5s0b+Pn5wcnJSfFasWKFrksjIiId07s9NZ
lMpusSiIiomNK7UKPC6z1m\nnq5LICLSKr07/EhERJQfhhoREYkGQ42IiESDoUZERKLBUCMiItFgqBERkWg
w1IiISDQYakREJBoM\nNSIiEg2GGhERiQZDjYiIRIOhRkREosFQIyIi0WCoERGRaDDUiIhINBhqREQkGgw1
IiISDYYaERGJ\nBkONiIhEg6FGRESiwVAjIiLRYKgREZFoMNSIiEg0GGpERCQaDDUiIhINwaEWFhaGGzdu5
Dv/5s2b\nCAsL00hRREREhSE41ObPn4/r16/nO5+hRkREuqaxw49paWkoVaqUppojIiIqMCN1M69du4arV6
8q\n3p85cwZZWVkqy8lkMkRGRsLR0VHzFRIREQmkNtT27dunOKQokUiwbt06rFu3Ls9lpVIpfvnlF81X\nS
EREJJDaUPP390eHDh0gl8vh5eWFadOm4csvv1RZzszMDDVq1ICRkdrmiIiItEptCtnY2MDGxgYA\nEBsbCy
cnJ1haWn6WwoiIiApK8K5Vq1attFkHERFRkeUbaqNHj4ZEIsGyZctgaGiI0aNHf7IxiUSC\nlStXarRAIiI
iofINtRMnTsDAwAA5OTkwNDTEiRMnIJFI1Db2qflERETalG+ofTyUP6/3RERExQ3v\n/UhERKJRqDH4aWlp
kMlkkMvlKvNsbW2LXBQREVFhCA61jIwMhIWFYePGjUhNTc13OXXziIiItElw\nqE2cOBFbt25Fp06d0KJFC
0ilUm3WRUREVGCCQy02NhYDBw7E0qVLtVkPERFRoQkeKCKRSNCwYUNt\n1kJERFQkgkOtY8eOOHbsmEY3fv
r0aXzzzTdwdnaGVCrF5s2b1S5///59SKVSldeRI0c0WhcREemn\nAp1TGzJkCMaNG4eBAweiWrVqMDQ0VFm
uIPeGTE9Ph4uLC/r06YMRI0YIXm/37t2oV6+e4n3FihUF\nr0tEROIlONTc3d0BfLgIe9OmTfkuV5DRj+3b
t0f79u0BAKNGjRK8XqVKlWBtbS14eSIiKhkEh9rk\nyZOLzW2wBgwYgIyMDDg4OGDUqFHw8/PTdUlERFQMC
A61qVOnarMOQcqWLYsff/wRzZs3h5GREQ4c\nOIDBgwdj9erV6N27d77rJSUlFWm7RV2/uEhPTy8W7YilPz
8mxs9UFOwPZewPVUXpE0dHx3zn6dVT\nPc3NzTF27FjF+8aNGyM1NRXLli1TG2rqOuBTkpKSirR+cWJmZlb
kNtLT04vcjlj6M5eYviOawP5Q\nxv5Qpc0+ERxqYWFhn1xGIpFg8uTJRSqooNzc3D45apKIiEoGwaE2f/78
fOdJJBLI5XKdhNrVq1c5\naISIiAAUINRevnypMi0nJwcPHjxAREQE4uPjsWvXrgJtPC0tDXfu3FG09fDhQ
1y5cgUVK1aEra0t\nZs2ahT///BMxMTEAgC1btqBUqVJo0KABDAwMcPDgQURERCAkJKRA2yUiInEq0qNnDA
wMYG9vjzlz\n5sDBwaHAe2mXLl2Cp6cnPD098e7dO4SGhsLT0xPz5s0DADx9+hR3795VWmfhwoVo27YtvLy
8sHv3\nbqxcuVLQU7mJiEj8NDZQpGXLlpg5c2aB1vHw8IBMJst3/urVq5Xe9+3bF3379i1UfUREJH4ae0jo
\npUuXYGDAZ44SEZHuCN5T27p1a57TX716hfj4eMVd/ImIiHRFcKipu42Vubk5AgMDP/vIRyIioo8J\nDrW
//vpLZZpEIoFUKkW5cuU0WhQREVFhCA41Ozs7bdZBRERUZBzZQUREosFQIyIi0WCoERGRaDDU\niIhINBhq
REQkGoJC7e3bt6hUqRIWLlyo7XqIiIgKTVColSlTBhYWFihfvry26yEiIio0wYcfu3Xr\nhj179iAnJ0eb9
RARERWa4IuvO3fujJMnT6JDhw4YOHAg7O3tYWpqqrKcm5ubRgskIiISSnCo+fn5\nKf4+f/48JBKJ0vzcJ1
+npqZqrjoiIqICEBxqq1at0mYdRERERSY41PhwTiIiKu4KdZ3a7du3kZCQ\ngFevXmm6HiIiokIrUKjt3Lk
T9erVg7u7Ozp27IjLly8DAF68eAE3Nzfs2bNHK0USEREJITjU9u7d\ni2HDhqF27dqYPXs25HK5Yp65uTlq
166Nbdu2aaVIIiIiIQSH2qJFi9CmTRtER0fneX6tSZMmuHbt\nmkaLIyIiKgjBoZaYmIjOnTvnO9/S0hLPn
z/XSFFERESFITjUypQpg/T09Hzn3717F+bm5hopioiI\nqDAEh5qnpye2bNmCzMxMlXlPnjzB+vXr4eXlpd
HiiIiICkLwdWo//PADvL290aZNG3Tr1g0SiQSH\nDx9GXFwc1q9fD0NDQ0yZMkWbtRIREakleE/NwcEBhw4
dgrW1NebPnw+5XI5Vq1Zh2bJlqF+/Pg4e\nPAhbW1tt1kpERKSW4D01AHBycsKePXsgk8lw584d5OTkwN7e
HhYWFtqqj4iISLAChVouqVQKV1dX\nTddCRERUJAUKNZlMhlWrVuHQoUN48OABAMDOzg4+Pj4YPXo0pFKpV
ookIiISQvA5tTt37qBVq1ZY\nuHAhsrKy4OHhAQ8PD2RlZWHhwoX44osvcPv2bW3WSkREpJbgPbVJkybh9e
vX2Lt3Lzw9PZXmHT9+\nHAMGDMCUKVOwa9cujRdJREQkhOA9tTNnzmDEiBEqgQYArVu3xvDhwxEfH6/R4oi
IiApCcKhVqFBB\n7TkzqVSKChUqaKQoIiKiwhAcagMGDMCmTZvw5s0blXmvXr3Cpk2bMHDgQI0WR0REVBCC
z6k5OjpC\nIpGgSZMm6NOnD2rWrAngwwNDt23bBktLSzg6Oqo8U6179+6arZiIiCgfgkNt2LBhir+XLVumM
j8l\nJQXDhg1Tes6aRCJhqBER0WcjONRiY2O1WQcREVGRCQ61Vq1aabMOIiKiIhM8UISIiKi4Y6gREZFo\n
MNSIiEg0GGpERCQaDDUiIhINwaEWFhaGGzdu5Dv/5s2bCAsL00hR6pw+fRrffPMNnJ2dIZVKsXnz\nZq1vk
4iI9IPgUJs/fz6uX7+e7/zPFWrp6elwcXHB/PnzYWpqqvXtERGR/ijUk6/zkpaWhlKlSmmq\nuXy1b98e7d
u3BwCMGjVK69sjIiL9oTbUrl27hqtXryrenzlzBllZWSrLyWQyREZGwtHRUfMVEhER\nCaQ21Pbt26c4pCi
RSLBu3TqsW7cuz2WlUil+
+eUXzVeoAUlJSTpdv7hIT08vFu2IpT8/JsbPVBTs\nD2XsD1VF6RN1O1BqQ83f3x8dOnSAXC6Hl5cXpk2bh
i+//FJlOTMzM9SoUQNGRho7mqlRRdmDTEpK\nEs0eqJmZWZHbSE9PL3I7YunPXGL6jmgC+0MZ+0OVNvtEbQ
rZ2NjAxsYGwIcbGjs5OcHS0lIrhRAR\nERUVb2hMRESiUaDjhf/3f/
+HjRs34t69e5DJZErPTgM+nHe7fPmyRgv8r7S0NNy5cwcAkJOTg4cP\nH+LKlSuoWLEibG1ttbptIiIq3gS
H2vLlyxESEgIrKyu4urrCxcVFm3Xl69KlS+jSpYvifWhoKEJD\nQ9GnTx+sXr1aJzUREVHxIDjU1qxZA09P
T+zcufOzXI+WHw8PD8hkMp1tn4iIii/BdxSRyWTw8/PT\naaARERGpIzjU3NzceK0FEREVa4JDbeHChdi3b
x927NihzXqIiIgKTfA5tYEDByIzMxMjRoxAYGAg\nKleuDENDQ6VlJBIJEhISNF4kERGREIJDzcLCApaWlq
hVq5Y26yEiIio0waG2f/9+bdZBRERUZHzy\nNRERiUaBQi01NRVz5syBj48PXF1dce7cOcX0sLAw3Lp1Syt
FEhERCSH48OP9+/fh6+uL1NRUuLi4\n4N69e3j37h0AoFKlSoiOjsbz588RHh6utWKJiIjUERxqM2fOhFwu
R0JCAsqVK6cyYKRjx44870ZE\nRDol+PDjsWPHEBAQAHt7e0gkEpX51atXx+PHjzVaHBERUUEIDrX3799DK
pXmO//Vq1cwMOC4EyIi\n0h3BKeTs7IzTp0/nO3///v1o0KCBRooiIiIqDMGhNnLkSOzZswcLFy7Ey5cvAX
x4nlliYiKGDh2K\nCxcuYPTo0VorlIiI6FMEDxTp2bMnHj58iHnz5mHevHkAgK++
+goAYGBggFmzZsHX11c7VRIREQlQ\noCdfBwYGomfPnoiJicGdO3eQk5ODGjVqoEuXLrC3t9dSiURERMIUK
NQAoFq1ahg1apQ2aiEiIioS\nwefUEhISsHjx4nznL1myRHGHESIiIl0QvKcWFhamdkj/tWvXcOrUKezevV
sjhRERERWU4D21K1eu\noGnTpvnOd3d3x19//aWRooiIiApDcKi9ffs2zzuJfCwtLa3IBRERERWW4FCrVas
Wjh49mu/8I0eO\noGbNmhopioiIqDAEh9rAgQNx+PBhTJ48WXHxNfDhsTOTJk3C0aNHMWDAAK0USUREJITg
gSIBAQG4\nevUq1q5di4iICFhZWQEAUlJSIJfL0bdvX4wcOVJrhRIREX1Kga5TW758ueLi63v37gEA7O3t4
efn\nh1atWmmjPiIiIsEEhVpmZibOnz8PGxsbeHh4wMPDQ9t1ERERFZigc2pGRkbo1q2b2oEiREREuiYo\n
1AwMDGBnZ8ch+0REVKwJHv04YsQIREVF4dmzZ9qsh4iIqNAEDxR5+/YtypQpA1dXV3Tq1An29vYw\nNTVVW
kYikWDcuHEaL5KIiEgIwaEWEhKi+Hv79u15LsNQIyIiXRIcaryvIxERFXeCQ83Ozk6bdRAR\nERVZgR8Sev
v2bZw6dQrPnj1Dz549Ub16dWRmZiI5ORnW1tYwNjbWRp1ERESfJDjUcnJyEBgYiI0b\nN0Iul0MikcDd3V0
Ral988QUmTZqEsWPHarNeIiKifAke0r9o0SJs2rQJ33//PQ4fPgy5XK6YV7Zs\nWXTp0gX79u3TSpFERERC
CA61zZs3o3///pg4cWKej5hxcXHB7du3NVocERFRQQgOtcePH8PNzS3f\n+aamprzjCBER6ZTgULOyssKDB
w/ynX/58mXY2tpqpCgiIqLCEBxqXbt2RWRkpNIhRolEAgA4fPgw\ntm3bhm7dumm+QiIiIoEEh1pwcDCqVa
sGT09PBAQEQCKRYPHixWjXrh169+6NevXqYcKECdqslYiI\nSC3BoVa+fHn88ccfmDBhAlJSUmBiYoKEhAS
kp6cjODgYBw4cULkXJBER0edUoIuvTUxMMHHiREyc\nOFFb9RARERXaJ/fUMjIyEB0djSVLlmD9+vV4+vSp
RguIiIhAgwYNYG1tjdatWyM+Pj7fZU+ePAmp\nVKrySkxM1GhNRESkn9TuqT158gQdO3bE/fv3FRdblylTB
tu2bYOHh0eRNx4dHY3g4GAsWrQIzZs3\nR0REBHr27ImEhAS1IykTEhJQsWJFxXsLC4si10JERPpP7Z7anD
lz8ODBA4waNQrbt29HaGgoTExM\nMGXKFI1sfNWqVejbty8GDRoEJycnhIeHw9raGpGRkWrXs7S0hLW1teJ
laGiokXqIiEi/qd1TO3bs\nGPr06YM5c+YopllZWWHo0KF49OgRqlatWugNZ2Zm4vLlyyr3ivTy8sLZs2fV
rtumTRtkZmbCyckJ\nQUFB8PT0LHQdREQkHmpDLTk5Gc2aNVOa1rx5c8jlcjx8+LBIofbixQtkZ2fD0tJSa
bqlpSVSUlLy\nXMfGxgaLFy+Gq6srMjMzsX37dvj5+WH//v1o2bJlvttKSkoqdJ2aWL+4SE9PLxbtiKU/Py
bGz1QU\n7A9l7A9VRekTR0fHfOepDbXs7GyYmJgoTct9n5GRUeiCCsvR0VHpwzRt2hQPHjzA8uXL1Yaaug7
4\nlKSkpCKtX5yYmZkVuY309PQityOW/swlpu+IJrA/lLE/VGmzTz45pP/evXv4888/Fe9fv36tKKps\n2b
Iqy6u7P+THzM3NYWhoiGfPnilNf/bsGaysrAS1kbu96OhowcsTEZF4fTLUQkNDERoaqjJ98uTJ\nSu9zn7G
WmpoqaMPGxsZo1KgR4uLilG6vFRcXh65duwpqAwCuXr0Ka2trwcsTEZF4qQ21VatWaXXj\no0ePxvDhw+Hm
5oZmzZohMjIST58+xeDBgwEAw4cPBwD8/PPPAICffvoJdnZ2cHZ2RmZmJnbs2IH9\n+/djw4YNWq2TiIj0g
9pQ69u3r1Y33qNHD6SmpiI8PBzJyclwdnbGjh07YGdnBwB4+PCh0vL//vsv\nZsyYgcePH8PExESxfPv27b
VaJxER6YcC3SZLG4YOHYqhQ4fmOW///v1K77/77jt89913n6MsIiLS\nQ4JvaExERFTcMdSIiEg0GGpERCQ
aDDUiIhINhhoREYkGQ42IiESDoUZERKLBUCMiItFgqBERkWgw\n1IiISDQYakREJBoMNSIiEg2GGhERiQZD
jYiIRIOhRkREosFQIyIi0WCoERGRaDDUiIhINBhqREQk\nGgw1IiISDYYaERGJBkONiIhEg6FGRESiwVAjI
iLRYKgREZFoMNSIiEg0GGpERCQaDDUiIhINhhoR\nEYkGQ42IiESDoUZERKLBUCMiItFgqBERkWgw1IiISD
QYakREJBoMNSIiEg2GGhERiQZDjYiIRIOh\nRkREosFQIyIi0WCoERGRaDDUiIhINBhqREQkGnobahEREWj
QoAGsra3RunVrxMfH67okIiLSMb0M\ntejoaAQHB2PixIk4ceIEmjZtip49e+Kff/7RdWlERKRDehlqq1at
Qt+
+fTFo0CA4OTkhPDwc1tbW\niIyM1HVpRESkQxKZTCbXdREFkZmZicqVK+PXX39Ft27dFNODgoJw48YNHDhw
QIfVERGRLundntqL\nFy+QnZ0NS0tLpemWlpZISUnRUVVERFQc6F2oERER5UfvQs3c3ByGhoZ49uyZ0vRnz
57ByspKR1UR\nEVFxoHehZmxsjEaNGiEuLk5pelxcHJo1a6ajqoiIqDgw0nUBhTF69GgMHz4cbm5uaNasGS
IjI/H0\n6VMMHjxY16UREZEO6d2eGgD06NEDoaGhCA8Ph4eHBxISErBjxw7Y2dkVqr2oqCh07twZdnZ2kEq
l\nuH//vsoyMpkMw4YNg52dHezs7DBs2DDIZDKlZa5fv46OHTvCxsYGzs7OCAsLg1yuV4NL1SopF7yf\nPn
0a33zzDZydnSGVSrF582al+XK5HKGhoahTpw5sbGzQqVMn3Lx5U2kZId8XfbF48WK0bdsWtra2\ncHBwQO/
evXHjxg2lZUpSn6xduxYtW7aEra0tbG1t8eWXX+LQoUOK+SWpL/KyePFiSKVSTJo0STHt\nc/aJXoYaAAwd
OhRXr15FSkoKjh8/ji++
+KLQbb19+xZeXl4IDg5Wu70rV65g165d2LVrF65cuYLh\nw4cr5r9+/Rrdu3eHlZUVjh49ivnz52PFihVYu
XJloesqTkrSBe/p6elwcXHB/PnzYWpqqjJ/2bJl\nWLVqFcLCwnD06FFYWlqie/fuePPmjWKZT31f9MmpU6
fw7bff4tChQ4iJiYGRkRG6deuGly9fKpYp\nSX1SpUoVzJo1C8ePH0dcXBw8PT3Rr18/XLt2DUDJ6ov/On/
+PKKiolC3bl2l6Z+zT/TuOjVtunTp\nEtq2bYu//voL1atXV0y/desWmjVrhoMHD6J58+YAgDNnzsDX1xfn
z5+Ho6Mjfv31V4SEhCAxMVHx\nH2F4eDgiIyNx48YNSCQSnXwmTfH29kbdunWxfPlyxTRXV1f4+flh5syZO
qxMu6pWrYoFCxagX79+\nAD784qxTpw4CAgIQFBQEAHj37h0cHR3x448/YvDgwYK+L/osLS0NdnZ22Lx5M3
x9fdknAOzt7TFz\n5kz4+/uX2L549eoVWrdujeXLlyMsLAwuLi4IDw//7N8Pvd1T+5zOnTuHsmXLKg1Ead6
8OczMzHD2\n7FnFMi1atFD6Ze/t7Y0nT57keThTn2RmZuLy5cvw8vJSmu7l5aX4/CXF/fv3kZycrNQXpqam
aNmy\npdJ34VPfF32WlpaGnJwcSKVSACW7T7Kzs7F7926kp6ejadOmJbovxo8fDz8/P3h6eipN/9x9opcD\
nRT63lJQUmJubK+1tSSQSWFhYKC74TklJQZUqVZTWy71APCUlBfb29p+tXk3jBe//k5ycDAB59sWT\nJ08A
CPu+6LPg4GDUr18fTZs2BVAy+
+T69eto3749MjIyYGZmhk2bNqFu3bqK/4BLUl8AwPr163Hn\nzh388ssvKvM+9/dDtKE2Z84cLFy4UO0ysb
Gx8PDw+EwVEem/adOmISEhAQcPHoShoaGuy9EZR0dH\nnDx5Eq9fv8bevXsxcuRI7Nu3T9dl6URSUhJmz56
NgwcPolSpUrouR7yhNnLkSPTq1UvtMtWqVRPU\nlpWVFV68eAG5XK74JSGXy/H8+XPFBd9WVlZ5XhCeO0+f
8YL3/7G2tgbw4bPb2toqpn/cF0K+L/po\n6tSpiI6ORmxsrNKRh5LYJ8bGxqhZsyYAoFGjRrh48SJ+
+uknxTmjktQX586dw4sXLxTnwoAPh2Xj\n4+MRGRmJhIQEAJ+vT0R7Ts3c3By1a9dW+ypTpoygtpo2bYq0t
DScO3dOMe3cuXNIT09XHANu2rQp\nzpw5g4yMDMUycXFxqFy5stKgE33EC97/p3r16rC2tlbqi4yMDJw5c0
bpu/Cp74u+mTJlCnbv3o2Y\nmBjUrl1baV5J7ZOP5eTkIDMzs0T2RadOnRAfH4+TJ08qXo0bN8ZXX32Fkyd
PolatWp+1TwyDg4ND\nNPLJ9FhycjLu3LmDpKQkxMbGwsvLC+np6TA2NoapqSksLCxw4cIF7Nq1C/Xr18ej
R48QGBgIV1dX\nxZBTBwcHrFu3DlevXoWjoyPOnDmDGTNmYPz48Xr5Rf2vcuXKITQ0FDY2NjAxMUF4eDji4
+Oxc
uVK\nVKhQQdflaVRaWhr+/vtvJCcnY+PGjXBxcUH58uWRmZmJChUqIDs7G0uXLoWDgwOys7Px/fffIzk5\n
GUuXLkXp0qUFfV/0SVBQELZt24aoqChUq1YN6enpSE9PB/DhB49EIilRfRISEgJjY2Pk5OTg0aNH\nWL16N
Xbs2IGQkBDF5y8pfQEAJiYmsLS0VHrt3LkTdnZ26Nev32f/fnBIP4DQ0FCEhYWpTF+1apVi\nKLdMJsPkyZ
Px++
+/AwB8fX2xYMECxQgw4MPJ46CgIFy8eBFSqRSDBw/GlClT9H44f66IiAgsW7YM\nycnJcHZ2xrx584p0fWB
xdfLkSXTp0kVlep8+fbB69WrI5XLMnz8fUVFRkMlkcHNzw8KFC+Hi4qJY\nVsj3RV/kV/OUKVMwdepUAChR
fTJy5EicPHkSKSkpKF+
+POrWrYtx48bB29sbQMnqi/x06tRJMaQf\n+Lx9wlAjIiLREO05NSIiKnkYakREJBoMNSIiEg2GGhERiQZD
jYiIRIOhRkREosFQI42SSqWffNWv\nX1+j29y7dy/WrFmjkbaysrIQGhqK06dPF7qNFStW4MCBAyrTQ0JCF
LeU0kVbula7dm0EBgbquowC\nS0xMhFQqxe7duxXThgwZAnd3dx1WRfkR7b0fSTcOHz6s9L5///6oV6+e0g
NYjY2NNbrNvXv34tKl\nSxgxYkSR28rKykJYWBiMjIwKfWH5ihUr4OPjg44dOypNHzp0aJ4XdX+utohKAoY
aadR/f70aGxvD\n3Nycv2rx4QbaQm+i/Tnb0kfv379H6dKldV0GFUM8/Eg6dezYMXTq1AlVq1ZF1apV0atX
L9y6dUtp\nmYMHD6Jdu3awtbVF1apV0bRpUyxZsgTAh8NA0dHRuHv3ruLwproA/ffffzFr1iw0bNgQ1tbWq
Fmz\nJnx9fXHhwgVkZGTAxsYGADB37lxFe7nbOnfuHPr16wcXFxfY2NjA3d0d8+bNw/v37xXt165dGykp\n
Kdi4caNi/dxDbnkdMlyxYgXc3d1hY2MDe3t7eHl54eDBg4Vq699//0V4eDjc3d1hZWUFBwcH9OrV\nC3fv3
s23P44cOQKpVIrz588rTY+MjIRUKlU8Cyu3nrFjx2Lr1q1o0qQJqlSpAm9vb1y4cEGl3RUr\nVqBevXqwtr
aGt7e3Svu57ty5gyFDhqBmzZqwtrZG69atcejQIaVlQkJCYG5ujhs3bqBr166oWrWq\n2r3yIUOGoHHjxrh
48SLat2+PypUrw83NDRs3blRpN69DuDy0qN+4p0Y6ExMTA39/f3Tu3Blr165F\ndnY2liyML7jwAAAI0klE
QVRZgo4dO+L06dOwsbFBYmIiBgwYgK+//hpTp06FkZERbt+
+jUePHgEA\npk+fjtTUVCQlJSEqKgrAhxus5icsLAwRERGYMWMGnJ2d8fr1a1y8eBEvX75E6dKlsX//fnTq
1AmD\nBw9G3759AfzvEUUPHjyAq6srBgwYADMzM9y4cQMLFizAP//8g9WrVwMAduzYge7du6N58+aYMGEC\
nANWHI+basGEDZs+ejeDgYLi7u+Pdu3e4du0aXr58WeC25HI5+vfvj6NHj2L06NHw8PDA27dvcerU\nKSQn
J6NGjRoF+afJ17Fjx/D3339jxowZMDIywpw5c9CrVy9cuXIFZcuWBQCsXbsWP/zwAwYNGoSu\nXbsiMTER/
v7+ipsg57p37x68vb1RtWpVhIWFoVKlSti+fTv69OmDnTt3Ku6lmPv5+vbtC39/fwQF\nBX3yWW6pqakYMW
IExowZg2rVqiEqKgpjx46Fk5OT4uGmJE4MNdKJnJwcTJ06Fd7e3tiwYYNieqtW\nrdCwYUOsWbMGISEhuHT
pErKyshR38waA1q1bK5avWbMmKlWqBGNjY0G/rs+fPw8fHx8EBAQopn18\nvsrNzQ0AUKVKFZX2vv76a8Xf
crkcLVq0gKmpKQIDA7FgwQKUK1cOjRo1QqlSpWBhYfHJes6fP4/G\njRtj4sSJimk+Pj6KvwvS1uHDh3Ho0
CEsXboU/v7+iumaPu/29u1b7N69G+XLlwcAVKxYEb6+vjh6\n9Ci6du2q2Fvs2LEjli1bBgDw9vZGhQoVMG
rUKKW25s6dq/ghkfukB29vb/zzzz8IDQ1VCrWcnBx8\n9913GDx4sKA6X716hZ07dyoCrHnz5jh27Bh27dr
FUBM5Hn4knbh58yYePXqEXr16ISsrS/EqV64c\nXF1dER8fDwBo2LAhDAwMMGjQIMTExODFixdF2q6rqyv2
79+PuXPn4uzZs/j3338FryuTyfD999+j\nYcOGsLKygoWFBcaNG4fs7Gy1h/jU1XLhwgVMnToVx48fx7t37
wrcRq6jR4/CyMgI/fv3L3QbQrRo\n0UIRaAAUd1l/
+PAhAOD+/ftISUlB9+7dldbr0aOHytMqjhw5gg4dOsDMzEzpO+Dl5YWLFy8qPZsQ\nADp37iy4TqlUqhReZ
cqUQfXq1RV1kngx1Egnnj9/DgAICAiAhYWF0uvYsWNITU0FANSpUwe7du3C\n+/fvERAQAEdHR/j4+Ciepl
tQwcHBmDhxImJiYuDj4wMHBweMGzcOMpnsk+sOGzYMmzdvxqhRo/Db\nb78hLi4Oc+fOBQCl82pCDRo0CGF
hYThz5gy6deuGGjVqYNCgQYpDqwWRmpoKKysrGBlp9+BLxYoV\nld7n7j3nfv6nT58CUH3au4mJCcqVK6d4
n52djZcvXyIqKkrl33/u3LnIyclR+jcxMDDI99CrkDpz\nay3MvxPpFx5+JJ3I/U9nzpw5eQ6d/3hkW9u2b
dG2bVtkZGQgISEBP/74I3r16oWrV68W+AGlpUuX\nRlBQEIKCgvD06VP8/vvvmD59OjIzM9Ve6/b69WscPn
wYs2fPVnpo4cWLFwu0/Y8ZGBggICAAAQEB\nSE1NxZEjRzB9+nQEBATkeW2aOubm5khJSUFWVlaBgi23nzM
zM5Wm5/6oKKjcgTYpKSlK0zMyMvDm\nzRvFe0NDQ5QvXx4+Pj4qhyVzmZubK/7WxjMJS5cujaysLOTk5MDA
4H+/7wv72al44J4a6UTdunVR\nuXJlJCYmonHjxiqvjx8emMvExARt2rTBmDFj8Pr1a8WhJGNjY5VDVULY2
Nhg8ODBaNmyJW7evKlo\nSyKRqLSXkZEBuVyuFBhyuRxbt25Vabcw9VSqVAm9evVCly5dFLUUpC0vLy9kZW
Vh8+bNBdqura0t\nAChtE1C93lCo6tWrw8rKCnv27FGaHh0dDblc+dGN7dq1w7Vr1+Di4pLnd6BUqVKFqkE
oW1tbZGdn\nIzExUTHtxYsXRfqhQrrHPTXSCUNDQyxYsAD+/v549+4dunTpgkqVKiElJQUJCQmoVasWhg0b
hjVr\n1uDixYto164dqlSpghcvXmDRokWoVq0aateuDeDDIcpt27Zhw4YNqFevHkxNTeHs7Jzndr/+
+mu4\nubmhQYMGqFChAi5duoQTJ04o9hYMDAzg6OiIAwcOwNPTE+XLl0eVKlVgbW2N+vXrY+nSpTA3N0eF\
nChUQFRWV5zm+OnXq4OTJk/jjjz9gaWkJCwsLRXh8bOTIkbCwsECTJk1gYWGBpKQk7N69W2mAhNC2\n2rVr
Bx8fH0yaNAn3799Hq1atkJGRgVOnTsHPzw/NmjXLsz/s7e3RpEkTLFiwAOXLl0fFihWxZcsW\nPH78+NP/i
HkoVaoUJk2ahEmTJmH8+PHo2rUrbt26hZUrV8LMzExp2RkzZsDb2xudO3fGt99+i2rV\nqkEmk+H69et4+v
Sp4lIKbfH19YWZmRnGjBmDyZMn4+3bt1iyZInSOUPSP9xTI53p0qULYmNj8fLl\nS4wdOxZfffUVQkJCkJq
aqhiF2KBBA7x69QohISHo0aMHpkyZAicnJ8TExCh+yQ8ZMgR+fn6YPn06\nvLy8MHDgwHy32bJlSxw5cgSj
R49Gz549sWHDBgQFBWH69OmKZRYtWgRDQ0P07NkTbdu2xZYtWwAA\n69evh4uLCwIDAzFmzBhUr14ds2fPV
tnGrFmzUL16dQwaNAht27bF4sWL86ylRYsWuHDhAiZMmIAe\nPXpgyZIlGDBggGLUYEHakkgk2LhxIyZMmI
DffvsNvXv3xrhx43D79m2V81v/FRkZiYYNGyIoKAhj\nxoyBo6Mjxo0bp3YddQICAjB79mwcPnwYffr0wa5
du7B+/XqVULO3t0dcXBwcHR0REhKC7t27Iygo\nCGfPnkWrVq0KvX2hzM3NsXXrVmRmZmLQoEGYN28exo8f
z9GRek4ik8nkn16MiIio+OOeGhERiQZD\njYiIRIOhRkREosFQIyIi0WCoERGRaDDUiIhINBhqREQkGgw1I
iISDYYaERGJxv8D+ab30p3PhHEA\nAAAASUVORK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc4c160a668>"
]
},
"metadata": {},
}
],
"source": [
"def simulate_under_null(num_chances_to_change):\n",
" \"\"\"Simulates some number changing several times, with an equal\n",
" chance to increase or decrease. Returns the value of our\n",
" test statistic for these simulated changes.\n",
" \n",
" num_chances_to_change is the number of times the number changes.\n",
" \"\"\"\n",
" return uniform.sample_from_distribution('Chance', 100).column(2).item(0)-
uniform.sample_from_distribution('Chance', 100).column(2).item(1)\n",
"\n",
"uniform_samples = make_array()\n",
"for i in np.arange(5000):\n",
" uniform_samples = np.append(uniform_samples,
simulate_under_null(num_changes))\n",
"\n",
"Table().with_column('Test statistic under null', uniform_samples).hist(0,
bins=np.arange(-100, 400+25, 25))"
]
},
{
"metadata": {},
"source": [
"**Question 2.6.** Looking at this histogram, draw a conclusion about whether
murder rates basically increase as often as they decrease. (Remember that we're
only concerned with the *postive direction* because it supports our alternative
hypothesis.) You **do not** need to compute a P-value for this question.\n",
"\n",
"First, set `which_side` to `\"Right\"` or `\"Left\"` depending on which side
of the histogram you need to look at to make your conclusion. \n",
"\n",
"Then, set `reject_null` to `True` if rates increase more than they decrease,
and we can reject the null hypothesis. Set `reject_null` to `False` if they do not
systematically increase more than they decrease."
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"False"
]
},
"metadata": {},
}
],
"source": [
"which_side = \"Right\"\n",
"if np.count_nonzero(uniform_samples>0)-
np.count_nonzero(uniform_samples<0)>0:\n",
" reject_null = True\n",
"else:\n",
" reject_null = False\n",
"reject_null"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 2\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/backups/lYBr0r\n",
"\n"
]
}
],
"source": [
"_ = ok.grade(\"q2_6\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"### Congratulations: Checkpoint Reached\n",
"\n",
"You have reached the project checkpoint. Please submit now in order to record
your progress. If you go back and revise your answers in the section above after
the checkpoint is due, that's ok. Your revised answers will be graded. **However,
you will only get credit for your checkpoint submission if you have passed the
tests provided for every question above.**\n",
"\n",
"If you are working with a partner, only one of you needs to submit. For both
of you to receive credit, the person who submits must invite the other to be their
partner on [okpy.org](http://okpy.org). Please invite your partner now and tell
them to accept the invitation **before** the checkpoint deadline!"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"Submit... 100% complete\n",
"Submission successful for user: isabellin105@berkeley.edu\n",
"URL: https://okpy.org/cal/data8/fa17/project2/submissions/o2Gxm3\n",
"\n"
]
}
],
"source": [
"_ = ok.submit()"
]
},
{
"metadata": {},
"source": [
"# 3. The death penalty\n",
"\n",
"Some US states have the death penalty, and others don't, and laws have changed
over time. In addition to changes in murder rates, we will also consider whether
the death penalty was in force in each state and each year.\n",
"\n",
"Using this information, we would like to investigate how the death penalty
affects the murder rate of a state."
]
},
{
"metadata": {},
"source": [
"**Question 3.1.** Describe this investigation in terms of an experiment. What
population are we studying? What is the control group? What is the treatment group?
What outcome are we measuring? Be precise!"
]
},
{
"metadata": {
"manual_problem_id": "death_penalty_1"
},
"source": [
"*Write your answers below.*\n",
"\n",
"- Population: All states in the United States\n",
"- Control Group: States without the death penalty in force during a given
years\n",
"- Treatment Group: States with the death penalty in force during a given
years\n",
"- Outcome: Increase or decrease in murder rate of a state during a given
years"
]
},
{
"metadata": {},
"source": [
"**Question 3.2.** We want to know whether the death penalty *causes* a change
in the murder rate. Why is it not sufficient to compare murder rates in places and
times when the death penalty was in force with places and times when it wasn't?"
]
},
{
"metadata": {
},
"source": [
"Murder rates could be overall higher/lower in certain years across all states.
Therefore, comparing states with the death penalty in one year vs without the death
penalty in another year could give a biased estimate. In addition, some states will
have an overall higher/lower murder rate due to confounding variables like time,
population size, location, types of people, etc so we must control for this."
]
},
{
"metadata": {},
"source": [
"### A Natural Experiment\n",
"\n",
"In order to attempt to investigate the causal relationship between the death
penalty and murder rates, we're going to take advantage of a *natural experiment*.
A natural experiment happens when something other than experimental design applies
a treatment to one group and not to another (control) group, and we have some hope
that the treatment and control groups don't have any other systematic
differences.\n",
"\n",
"Our natural experiment is this: in 1972, a Supreme Court decision called
*Furman v. Georgia* banned the death penalty throughout the US. Suddenly, many
states went from having the death penalty to not having the death penalty.\n",
"\n",
"As a first step, let's see how murder rates changed before and after the court
decision. We'll define the test as follows:\n",
"\n",
"> **Population:** All the states that had the death penalty before the 1972
abolition. (There is no control group for the states that already lacked the death
penalty in 1972, so we must omit them.) This includes all US states **except**
Alaska, Hawaii, Maine, Michigan, Wisconsin, and Minnesota.\n",
"\n",
"> **Treatment group:** The states in that population, in the year after
1972.\n",
"\n",
"> **Control group:** The states in that population, in the year before
1972.\n",
"\n",
"> **Null hypothesis:** Each state's murder rate was equally likely to be
higher or lower in the treatment period than in the control period. (Whether the
murder rate increased or decreased in each state was like the flip of a fair
coin.)\n",
"\n",
"> **Alternative hypothesis:** The murder rate was more likely to increase.\n",
"\n",
"Our alternative hypothesis is in keeping with our suspicion that murder rates
increase when the death penalty is eliminated. \n",
"\n",
"*Technical Note:* It's not clear that the murder rates were a \"sample\" from
any larger population. Again, it's useful to imagine that our data could have come
out differently and to test the null hypothesis that the murder rates were equally
likely to move up or down.\n",
"\n",
"The `death_penalty` table below describes whether each state allowed the death
penalty in 1971."
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" <thead>\n",
" <tr>\n",
" <th>State</th> <th>Death Penalty</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>Alabama </td> <td>True </td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>Alaska </td> <td>False </td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>Arizona </td> <td>True </td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>Arkansas </td> <td>True </td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>California </td> <td>True </td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>Colorado </td> <td>True </td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>Connecticut</td> <td>True </td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>Delaware </td> <td>True </td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>Florida </td> <td>True </td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>Georgia </td> <td>True </td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
],
"text/plain": [
"State | Death Penalty\n",
"Alabama | True\n",
"Alaska | False\n",
"Arizona | True\n",
"Arkansas | True\n",
"California | True\n",
"Colorado | True\n",
"Connecticut | True\n",
"Delaware | True\n",
"Florida | True\n",
"Georgia | True\n",
]
},
"metadata": {},
}
],
"source": [
"non_death_penalty_states = make_array('Alaska', 'Hawaii', 'Maine', 'Michigan',
'Wisconsin', 'Minnesota')\n",
"def had_death_penalty_in_1971(state):\n",
" \"\"\"Returns True if the argument is the name of a state that had the
death penalty in 1971.\"\"\"\n",
" # The implementation of this function uses a bit of syntax\n",
" # we haven't seen before. Just trust that it behaves as its\n",
" # documentation claims.\n",
" return state not in non_death_penalty_states\n",
"\n",
"states = murder_rates.group('State').select('State')\n",
"death_penalty = states.with_column('Death Penalty',
states.apply(had_death_penalty_in_1971, 0))\n",
"death_penalty"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"44"
]
},
"metadata": {},
}
],
"source": [
"num_death_penalty_states = death_penalty.where(\"Death Penalty\",
are.equal_to(True)).num_rows\n",
"num_death_penalty_states"
]
},
{
"metadata": {},
"source": [
"**Question 3.3.** Assign `death_penalty_murder_rates` to a table with the same
columns and data as `murder_rates`, but that has only the rows for states that had
the death penalty in 1971.\n",
"\n",
"The first 2 rows of your table should look like this:\n",
"\n",
"|State|Year|Population|Murder Rate|\n",
"|-----|----|----------|-----------|\n",
"|Alabama|1960|3266740|12.4|\n",
"|Alabama|1961|3302000|12.9|"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" <thead>\n",
" <tr>\n",
Rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
],
"text/plain": [
"Alabama | 1960 | 3,266,740 | 12.4\n",
"Alabama | 1961 | 3,302,000 | 12.9\n",
"Alabama | 1962 | 3,358,000 | 9.4\n",
"Alabama | 1963 | 3,347,000 | 10.2\n",
"Alabama | 1964 | 3,407,000 | 9.3\n",
"Alabama | 1965 | 3,462,000 | 11.4\n",
"Alabama | 1966 | 3,517,000 | 10.9\n",
"Alabama | 1967 | 3,540,000 | 11.7\n",
"Alabama | 1968 | 3,566,000 | 11.8\n",
"Alabama | 1969 | 3,531,000 | 13.7\n",
]
},
"metadata": {},
}
],
"source": [
"states = death_penalty.where('Death Penalty', True).column(0)\n",
"death_penalty_murder_rates =
murder_rates.where('State',are.contained_in(states))\n",
"death_penalty_murder_rates"
]
},
{
"metadata": {},
"source": [
"The null hypothesis doesn't specify *how* the murder rate changes; it only
talks about increasing or decreasing. So, we will use the same test statistic we
defined in section 2."
]
},
{
"metadata": {},
"source": [
"**Question 3.4.** Assign `test_stat_72` to the value of the test statistic for
the years 1971 to 1973 and the states in `death_penalty_murder_rates`. As before,
the test statistic is, \"the number of increases minus the number of decreases.\""
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"Test statistic from 1971 to 1973: 22\n"
]
}
],
"source": [
"t = death_penalty_murder_rates.where('Year', are.between(1971,1974))\n",
"states = t.sort('State', distinct = True).column(0)\n",
"stats = make_array()\n",
" s = diff_n(t.where('State',states[i]).column(3), 2)\n",
" stats = np.append(stats,s)\n",
"test_stat_72 = np.count_nonzero(stats>0)- np.count_nonzero(stats<0)\n",
"print('Test statistic from 1971 to 1973:', test_stat_72)"
]
},
{
"metadata": {},
"source": [
"Look at the data (or perhaps a random sample) to verify that your answer is
correct."
]
},
{
"metadata": {},
"source": [
"**Question 3.5.**: Draw an empirical histogram of the statistic under the null
hypothesis by simulating the test statistic 10,000 times.\n",
"\n",
"*Hint:* In Part 2 of this project, you have already written a function that
runs such a simulation once."
]
},
{
"metadata": {
},
"outputs": [
{
"data": {
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAAagAAAEhCAYAAAAqDTTQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAL
EgAACxIB0t1+/AAAIABJREFUeJzt3XlcTfn/B/DXrSSyXFotKVLILhGTrZB9nRjGEiNDxVcK\nWWYmfdOii
MGXoSH7npHly2Roxtbgi5G9sY5BIRdFmur+/vDo/uZOi3N1r3tu9/V8PHo86pxzP+f9\ncZp5dc75nPORyG
QyOYiIiETGQNsFEBERFYcBRUREosSAIiIiUWJAERGRKDGgiIhIlBhQREQkSgwo\nIiISJa0FVH5+PsLCwtC
iRQtYWVmhRYsWCAsLQ15enrZKIiIiETHS1o6XLFmCuLg4rFy5Ek5OTrhy\n5QomT54MY2NjzJw5U1tlERGR
SGgtoM6cOYNevXqhd+/eAABbW1v07t0b//vf/7RVEhERiYjWLvG5\nurrixIkTuHnzJgDg+vXrOH78OHr06
KGtkoiISES0dgY1bdo0ZGVloX379jA0NEReXh6CgoIwYcIE\nbZVEREQiorWASkhIwLZt2xAXF4fGjRsjNT
UVwcHBqFevHsaMGaOtsoiISCS0donv66+/hr+/P4YO\nHYqmTZvis88+g5+fH2JjY1VqJy0tTUMVak957BN
QPvtVHvsElM9+sU+6R2sB9fr1axgaGiotMzQ0\nREFBgZYqIiIiMdHaJb5evXphyZIlsLW1RePGjXHp0iWs
WLECn332mbZKIiIiEdFaQC1cuBALFixA\nYGAgnj59CisrK4wdO5bPQBEREQAtBlTVqlURGRmJyMhIbZVAR
EQixnfxERGRKDGgiIhIlBhQREQk\nSgwoIiISJa0NkqCSBYTHw9TUVO3tbl8+R+1tEhFpCs+giIhIlBhQRE
QkSgwoIiISJQYUERGJEgOK\niIhEiQFFRESixIAiIiJRYkAREZEoMaCIiEiUGFBERCRKDCgiIhIlBhQREYk
SA4qIiESJAUVERKLE\ngCIiIlFiQBERkShxwsIyGu4fru0SiIjKJZ5BERGRKPEMSo9o4myP08gTkabwDIqI
iERJr86geL+I\niEh38AyKiIhEiQFFRESixIAiIiJRYkAREZEoMaCIiEiUGFBERCRKDCgiIhIlBhQREYkSA
4qIiESJ\nAUVERKLEgCIiIlFiQBERkSgxoIiISJQYUEREJEoMKCIiEiUGFBERiRIDioiIRElwQEVFReHq1a
sl\nrr927RqioqLUUhQREZHggIqMjMSVK1dKXM+AIiIidVLbJb6srCxUqFBBXc0REZGeMypt5eXLl5Ga\nm
qr4+fTp08jLyyuynUwmw9q1a+Hg4KD+ComISC+VGlD79+9XXLaTSCRYt24d1q1bV+y2UqkUq1ev\nVmnnjx
8/RkhICJKSkpCVlQU7OzssWrQIbm5uKrVDRETlT6kB5e3tjV69ekEul8Pd3R1z5sxBjx49\nimxnamqK+vX
rw8io1OaUyGQyeHp6wtXVFTt27ICZmRnu3bsHCwsL1XtBRETlTqmJYm1tDWtrawDA\nvn370KhRI7UFyLff
fgtra2t89913imV2dnZqaZuIiHSf4EESbm5uaj27OXDgAJydnTFu3Dg0bNgQ\nbm5uWL16NeRyudr2QUREu
qvEMyg/Pz9IJBIsXboUhoaG8PPze29jEokEy5cvF7Tju3fv4vvvv4ev\nry+mTZuG1NRUzJo1CwAwceJEge
UTEVF5JZHJZMWesjRv3hwGBgY4d+4cKlSogObNm0MikZTemESC\n3377TdCOLSws0Lp1a/z444+KZaGhodi
/fz/OnDlT4ufS0tIEtV+cgPD4D/4sFS92jre2SyAiHfW+\nkd8lnkH9fXh5cT+XlZWVFRo1aqS0zNHREQ8e
PCj1c//sUFpamuDh7aampqoVqSXZ2dk6U6sqjxao\ncqx0RXnsE1A+
+8U+6R7hw+7UzNXVFb///rvSst9//x02NjZaqog+xHD/cMHbCg3e7cvnlKUkIion\nPiigsrKyIJPJih3QI
DRgfH190bNnT8TExGDIkCG4dOkSVq9eja++
+upDSiIionJGcEDl5OQgKioK\nGzduRGZmZonblbbu79q0aYPNmzcjNDQU0dHRqFu3LubMmYMJEyYILYmIi
MoxwQEVGBiIrVu3om/f\nvujQoQOkUmmZd+7p6QlPT88yt0PliyqXDVXBS4dEukVwQO3btw9jxozBkiVLNF
kPERERABUe1JVI\nJGjZsqUmayEiIlIQHFB9+vRBcnKyBkshIiL6f4IDKjAwEHfu3MHUqVNx7tw5PH78GE+
ePCnyRURE\npA6C70G5uLgAePfA7qZNm0rcTugoPiIiotIIDqiZM2e+91VHRERE6iI4oGbPnq3JOoiIiJQI
vgdF\nRET0MQk+gyqc+r00EokEM2fOLFNBREREgAoBFRkZWeI6iUQCuVzOgCIiIrURHFDPnz8vsqygoAD3\
n799HXFwcTp06hV27dqm1OCIi0l9lugdlYGAAOzs7hIWFwd7enmdPRESkNmobJNGxY0el2XGJiIjK\nQm0B
deHCBRgYcFAgERGph+B7UFu3bi12+YsXL3Dq1CnF286JiIjUQXBA+fr6lrjOzMwMAQEBvAdF\nRERqIzigf
vvttyLLJBIJpFIpqlatqtaiiIiIBAdUvXr1NFkHERGREo5qICIiUWJAERGRKDGgiIhI\nlBhQREQkSgwoIi
ISJUEB9fr1a9SsWRMxMTGaroeIiAiAwICqXLkyzM3NUa1aNU3XQ0REBECFS3yD\nBg3Cnj17UFBQoMl6iIi
IAKjwoG6/fv1w/Phx9OrVC2PGjIGdnR0qVapUZDtnZ2e1FkhERPpJcEAN\nHDhQ8f3Zs2chkUiU1hfOqJuZ
mam+6oiISG8JDqgVK1Zosg4iIiIlggNq5MiRmqyDiIhIyQc9B3Xr\n1i2kpKTgxYsX6q6HiIgIgIoBtXPnT
jRr1gwuLi7o06cPLl68CAB49uwZnJ2dsWfPHo0USURE+kdw\nQO3duxcTJ06Eo6MjQkNDIZfLFevMzMzg6O
iIbdu2aaRIIiLSP4IDatGiRejatSsSEhKKvR/Vtm1b\nXL58Wa3FERGR/hIcUDdv3kS/fv1KXG9hYYGnT5+
qpSgiIiLBAVW5cmVkZ2eXuP7OnTswMzNTS1FE\nRESCA6pz587YsmULcnNzi6x79OgR1q9fD3d3d7UWR0RE
+kvwc1BfffUVPDw80LVrVwwaNAgSiQRJ\nSUk4duwY1q9fD0NDQ8yaNUuTtRIRkR4RfAZlb2+Pw4cPw8rKC
pGRkZDL5VixYgWWLl2K5s2b49Ch\nQ7CxsdFkrUREpEcEn0EBQKNGjbBnzx7IZDLcvn0bBQUFsLOzg7m5ua
bqIyIiPaVSQBWSSqVo06aN\numshIiJSUCmgZDIZVqxYgcOHD+P+/fsAgHr16sHT0xN+fn6QSqUaKZKIiPS
P4HtQt2/fhpubG2Ji\nYpCXl4dOnTqhU6dOyMvLQ0xMDD755BPcunVLk7USEZEeEXwGNWPGDLx8+RJ79+5F
586dldb9/PPP\nGD16NGbNmoVdu3apvUgiItI/gs+gTp8+jUmTJhUJJwDo0qULvvzyS5w6dUqtxRERkf4SH
FDVq1cv\n9R6TVCpF9erV1VIUERGR4IAaPXo0Nm3ahFevXhVZ9+LFC2zatAljxoxRa3FERKS/BN+DcnBwgE
Qi\nQdu2bTFixAg0aNAAwLvJC7dt2wYLCws4ODgUmRNq8ODB6q2YiIj0guCAmjhxouL7pUuXFlmfkZGB\ni
RMnKs0TJZFIBAfU4sWLERoaCh8fH0RHRwsti4iIyinBAbVv3z6NFXH27FnEx8ejadOmGtsHERHp\nFsEB5e
bmppECXrx4AR8fHyxfvhxRUVEa2QcREekewYMkNGXatGkYOHBgscPXiYhIf33Qu/jUZf36\n9bh9+zZWr14
t+DNpaWmClhWntAkXxUaXalWFNvsl9PdELO1qW3nsF/skLg4ODqWu11pApaWlITQ0\nFIcOHUKFChUEf+6f
HUpLS3tvJwuZmpqqVKO2ZGdn60ytqtB2v4T+nqhCld8/XVIe+8U+6R6tBdSZ\nM2fw7NkzuLq6Kpbl5+fj1
KlTWLt2LR4+fIiKFStqqzwiItIyrQVU37590bp1a6Vlfn5+sLe3x/Tp\n02FsbKylyoiISAwED5KIiorC1a
tXS1x/7do1lUbhSaVSODk5KX1VrlwZNWrUgJOTEyQSieC2iIio\n/BEcUJGRkbhy5UqJ61UNKCIiotKo7RJ
fVlaWSoMdinPgwAE1VUNERLqu1IC6fPkyUlNTFT+fPn0a\neXl5RbaTyWRYu3ZtuR5NQkREH1epAbV//37F
ZTuJRIJ169Zh3bp1xW4rlUpVep6JiIioNKUGlLe3\nN3r16gW5XA53d3fMmTMHPXr0KLKdqakp6tevDyMjr
T73S1Sq4f7ham8z7F9eam+TiN4pNVGsra1h\nbW0N4N3LYhs1agQLC4uPUhgREek3rb8sloiIqDgqXZP76a
efsHHjRty9excymUxp7ifg3X2qixcv\nqrVAIiLST4ID6ttvv0VISAgsLS3Rpk0bODk5abIuIiLSc4IDatW
qVejcuTN27txZ5uediIiI3kfw\nmyRkMhkGDhzIcCIioo9CcEA5Ozvr9LwjRESkWwQHVExMDPbv348dO3Zo
sh4iIiIAKtyDGjNmDHJz\nczFp0iQEBASgVq1aMDQ0VNpGIpEgJSVF7UUSEZH+ERxQ5ubmsLCwQMOGDTVZD
xEREQAVAopvGici\noo9J8D0oIiKij0mlgMrMzERYWBg8PT3Rpk0bnDlzRrE8KioKN27c0EiRRESkfwRf4r
t37x569+6N\nzMxMODk54e7du3jz5g0AoGbNmkhISMDTp08RHR2tsWKJiEh/CA6ob775BnK5HCkpKahatWq
RwRJ9\n+vThfSoiIlIbwZf4kpOT4ePjAzs7O0gkkiLrbW1t8fDhQ7UWR0RE+ktwQL19+xZSqbTE9S9evICB
\nAcdcEBGReghOlCZNmuDkyZMlrj9w4ABatGihlqKIiIgEB9TkyZOxZ88exMTE4Pnz5wCAgoIC3Lx5\nExM
mTMC5c+fg5+ensUKJiEi/CB4k4eXlhQcPHiA8PBzh4eEAgKFDhwIADAwMMH/
+fPTu3VszVRIR\nkd5RaUbdgIAAeHl5ITExEbdv30ZBQQHq16+P/v37w87OTkMlEhGRPlIpoACgbt268PX1
1UQtRERE\nCoLvQaWkpGDx4sUlro+NjVW8WYKIiKisBJ9BRUVFlTrM/PLlyzhx4gR2796tlsKIiEi/CT6Du
nTp\nEtq1a1fiehcXF/z2229qKYqIiEhwQL1+/brYN0j8XVZWVpkLIiIiAlQIqIYNG+Lo0aMlrj9y5Aga\n
NGiglqKIiIgEB9SYMWOQlJSEmTNnKh7UBd5NtTFjxgwcPXoUo0eP1kiRRESkfwQPkvDx8UFqairW\nrFmDu
Lg4WFpaAgAyMjIgl8sxcuRITJ48WWOFEhGRflHpOahvv/1W8aDu3bt3AQB2dnYYOHAg3Nzc\nNFEfERHpKU
EBlZubi7Nnz8La2hqdOnVCp06dNF0XERHpOUEBZWRkhEGDBiE8PBz29vaarolIZwSE\nx8PU1FStbW5fPke
t7RHpKkGDJAwMDFCvXj0OIycioo9G8Ci+SZMmIT4+Hk+ePNFkPURERABUGCTx\n+vVrVK5cGW3atEHfvn1h
Z2eHSpUqKW0jkUgwdepUtRdJRET6R3BAhYSEKL7fvn17sdswoIiISF0E\nBxTfs0dERB+T4ICqV6+eJusgI
iJSovKEhbdu3cKJEyfw5MkTeHl5wdbWFrm5uUhPT4eVlRWMjY01\nUScREekZwQFVUFCAgIAAbNy4EXK5HB
KJBC4uLoqA+uSTTzBjxgxMmTJFk/USEZGeEDzMfNGiRdi0\naRPmzp2LpKQkyOVyxboqVaqgf//
+2L9/v0aKJCIi/SM4oDZv3oxRo0YhMDCw2Gk1nJyccOvWLbUW\nR0RE+ktwQD18+BDOzs4lrq9UqRLfNEFE
RGojOKAsLS1x//79EtdfvHgRNjY2aimKiIhIcEANGDAA\na9euVbqMVzgFfFJSErZt24ZBgwYJ3vHixYvRr
Vs32NjYwN7eHsOHD8fVq1dVKJ2IiMozwQEVHByM\nunXronPnzvDx8YFEIsHixYvRvXt3DB8+HM2aNcP06d
MF7/jEiRP44osvcPjwYSQmJiremP732XqJ\niEh/CQ6oatWq4ccff8T06dORkZEBExMTpKSkIDs7G8HBwTh
48GCRd/OVJiEhAaNGjYKTkxOaNm2K\n7777Dk+fPkVKSsoHdYSIiMoXlR7UNTExQWBgIAIDA9VeSFZWFgoK
CiCVStXeNhER6R6JTCaTl7ZB\nTk4ODh48iHv37qFmzZrw9PSEtbW12gvx9vbGrVu3kJycDENDwxK3S0tL+
+B9BITHf/BniT6W2Dne\n2i6B6KNwcHAodX2pZ1CPHj1Cnz59cO/ePcWDuZUrV8a2bdvUOu37nDlzkJKSgk
OHDpUaTkDRDqWl\npb23k4XUPfOppmRnZ+tMraooj/3SRJ+E/j5rkir/XekK9kn3lHoPKiwsDPfv34evry+
2b9+OiIgI\nmJiYYNasWWorYPbs2di9ezcSExNhZ2entnaJiEi3lXoGlZycjBEjRiAsLEyxzNLSEhMmTMCf
f/6J\nOnXqlGnns2bNwp49e7Bv3z44OjqWqS0iIipfSj2DSk9PR/v27ZWWubq6Qi6X48GDB2XacVBQELZs\
n2YI1a9ZAKpUiPT0d6enpfBsFEREBeE9A5efnw8TERGlZ4c85OTll2nFcXBxevXqFgQMHolGjRoqv\nZcuW
laldIiIqH947zPzu3bv43//+p/j55cuXAN7dnKtSpUqR7Ut7X9/fyWQyoTUSEZEeem9ARURE\nICIiosjym
TNnKv1cOEdUZmam+qojIiK9VWpArVix4mPVQUREpKTUgBo5cuTHqoOIiEiJ4HfxERER\nfUwMKCIiEiUGFB
ERiRIDioiIREml6TaISPOG+4drpN3ty+dopF0iTeEZFBERiRIDioiIRIkBRURE\nosSAIiIiUWJAERGRKDG
giIhIlBhQREQkSgwoIiISJQYUERGJEgOKiIhEiQFFRESixIAiIiJRYkAR\nEZEoMaCIiEiUGFBERCRKDCgi
IhIlBhQREYkSZ9Ql0hOqzNSbnZ0NU1PT927HWXpJk3gGRUREosSA\nIiIiUWJAERGRKDGgiIhIlBhQREQkS
gwoIiISJQYUERGJEgOKiIhEiQFFRESixIAiIiJR4quOiOiD\nqfL6JFXwFUoE8AyKiIhEigFFRESixIAiIi
JRYkAREZEoMaCIiEiUGFBERCRKDCgiIhIlPgdFRKKj\nieerwv7lpfY2SbN4BkVERKLEgCIiIlHSekDFxcW
hRYsWsLKyQpcuXXDq1Cltl0RERCKg1XtQCQkJ\nCA4OxqJFi+Dq6oq4uDh4eXkhJSUFNjY22iyNiMqZgPB4
mJqaqrVNvjNQs7QaUCtWrMDIkSMxduxY\nAEB0dDR++uknrF27Ft988402SyMiei+
+LFezJDKZTK6NHefm5qJWrVr4/vvvMWjQIMXyoKAgXL16\nFQcPHtRGWUREJBJauwf17Nkz5Ofnw8LCQmm5
hYUFMjIytFQVERGJhdYHSRARERVHawFlZmYGQ0ND\nPHnyRGn5kydPYGlpqaWqiIhILLQWUMbGxmjVqhWOH
TumtPzYsWNo3769lqoiIiKx0OooPj8/P3z5\n5ZdwdnZG+/btsXbtWjx+/Bjjxo3TZllERCQCWr0HNWTIEE
RERCA6OhqdOnVCSkoKduzYgXr16qnc\nVt+
+fSGVSpW+xo8fr4GqNas8PbgcERFR5Jg4OjpquyyVnTx5Ep999hmaNGkCqVSKzZs3K62Xy+WI\niIhA48aN
YW1tjb59+
+LatWtaqlaY9/Vp8uTJRY5d9+7dtVStMIsXL0a3bt1gY2MDe3t7DB8+HFev\nXlXaRteOlZA+6eKxEkrrgy
QmTJiA1NRUZGRk4Oeff8Ynn3zywW19/vnnuHHjhuIrNjZWjZVqXuGD\ny4GBgfjll1/Qrl07eHl54Y8//tB
2aR/MwcFB6ZjoYuBmZ2fDyckJkZGRqFSpUpH1S5cuxYoVKxAV\nFYWjR4/CwsICgwcPxqtXr7RQrTDv6xMA
dO3aVenY7dy58yNXqZoTJ07giy+
+wOHDh5GYmAgjIyMM\nGjQIz58/V2yja8dKSJ8A3TtWQpWrt5lXrlwZVlZW2i7jg5XHB5eNjIx0+pgAQM+e
PdGzZ08AgK+v\nr9I6uVyOlStXYtq0aRg4cCAAYOXKlXBwcMCuXbtEe7m6tD4Vqlixok4du4SEBKWfv/vuO
9SrVw8p\nKSno3bu3Th6r9/WpkK4dK6G0fgalTrt370aDBg3g6uqKefPmifavouLk5ubi4sWLcHd3V1ru7u
6O\nX3/9VUtVld3du3fRuHFjtGjRAuPHj8fdu3e1XZJa3bt3D+np6UrHrVKlSujYsaNOHzcAOH36NBo2\nb
AhnZ2dMnTq1yIhbscvKykJBQQGkUimA8nGs/tmnQrp+rEpSbs6gvLy8YGNjA2tra1y/fh3z58/H\nlStXsG
fPHm2XJkh5fHC5bdu2+M9//gMHBwc8ffoU0dHR6NmzJ1JSUlCzZk1tl6cW6enpAFDscXv0\n6JE2SlKL7t2
7o3///rC1tcX9+/cRFhaGAQMGIDk5GRUrVtR2eYIEBwejefPmaNeuHYDycaz+2Seg\nfByrkog6oMLCwhAT
E1PqNvv27UOnTp3g7e2tWNa0aVPY2dnBw8MDFy9eRKtWrTRcKRWnR48eSj+3\nbdsWrVq1wpYtW+Dv76+lq
kiIoUOHKr5v2rQpWrVqhebNm+Pw4cMYMGCAFisTZs6cOUhJScGhQ4dg\naGio7XLUoqQ+6fqxKo2oA2ry5M
kYNmxYqdvUrVu32OWtW7eGoaEhbt+
+rRMBpQ8PLlepUgWNGzfG\n7du3tV2K2hRe93/y5InSG/jL03EDgFq1aqF27do6cexmz56NhIQE7Nu3D3Z2
dorlunysSupTcXTp\nWL2PqO9BmZmZwdHRsdSvypUrF/vZK1euID8/X2duHOrDg8s5OTlIS0vTmWMihK2tL
aysrJSOW05O\nDk6fPl1ujhvw7hL0o0ePRH/sZs2ahd27dyMxMbHIIw26eqxK61NxdOVYCWEYHBwcou0iyu
rOnTtY\nvXo1TE1NkZubizNnzmDatGmoU6cO5s2bBwMDUeewQtWqVREREQFra2uYmJggOjoap06dwvLly1G
9\nenVtl6eyefPmwdjYGAUFBfj9998xY8YM3L59G7GxsTrVn6ysLFy/fh3p6enYuHEjnJycUK1aNeTm\n5q
J69erIz8/HkiVLYG9vj/z8fMydOxfp6elYsmSJaO8BlNYnQ0NDhIaGokqVKsjLy0NqaiqmTJmC\n/Px8REd
Hi7ZPQUFB2LZtG+Lj41G3bl1kZ2cjOzsbwLs/ACUSic4dq/f1KSsrSyePlVBam25DnR48\neICJEyfi2rVr
yM7ORp06ddCzZ08EBwejRo0a2i5PJXFxcVi6dCnS09PRpEkThIeHl+nZMG0aP348\nTp06hWfPnsHc3Bxt2
7bF3Llz0bhxY22XppLjx4+jf//
+RZaPGDECK1euhFwuR2RkJOLj4yGTyeDs\n7IyYmBg4OTlpoVphSuvT4sWL8fnnn+PSpUt48eIFrKys0KlT
J8ydO7fES+pi8M+RbYVmzZqF2bNn\nA4DOHav39enNmzc6eayEKhcBRURE5Y9uXPsiIiK9w4AiIiJRYkARE
ZEoMaCIiEiUGFBERCRKD
Cgi\nIhIlBhSV6J+ToBX31bx5c7Xuc+/evVi1apVa2srLy0NERAROnjz5wW0sW7YMBw8eLLI8JCRE5Sf1\n
1dmWtjk6OiIgIEDbZajs5s2bkEql2L17t2LZ+PHj4eLiosWqqCSifhcfaVdSUpLSz6NGjUKzZs0Q\nHBysW
GZsbKzWfe7duxcXLlzApEmTytxWXl4eoqKiYGRk9MEPOy9btgyenp7o06eP0vIJEyYU+6Dr\nx2qLSB8woK
hE//yr0tjYGGZmZvxrE+9eUqyuJ/XV2ZYuevv2rc6/koc0g5f4SG2Sk5PRt29f1KlT\nB3Xq1MGwYcNw48Y
NpW0OHTqE7t27w8bGBnXq1EG7du0QGxsL4N2lloSEBNy5c0dxCbG0MPzrr78w\nf/58tGzZElZWVmjQoAF6
9+6Nc+fOIScnB9bW1gCABQsWKNor3NeZM2fw+eefw8nJCdbW1nBxcUF4\neDjevn2raN/R0REZGRnYuHGj4
vOFl7WKuyy3bNkyuLi4wNraGnZ2dnB3d8ehQ4c+qK2//voL0dHR\ncHFxgaWlJezt7TFs2DDcuXOnxH+PI0
eOQCqV4uzZs0rL165dC6lUqpgPqbCeKVOmYOvWrWjbti1q\n164NDw8PnDt3rki7y5YtQ7NmzWBlZQUPD48
i7Re6ffs2xo8fjwYNGsDKygpdunTB4cOHlbYJCQmB\nmZkZrl69igEDBqBOnTqlni2PHz8erVu3xvnz59Gz
Z0/UqlULzs7O2LhxY5F2i7tMyst3uo1nUKQW\niYmJ8Pb2Rr9+/bBmzRrk5+cjNjYWffr0wcmTJ2FtbY2bN
29i9OjR+PTTTzF79mwYGRnh1q1b+PPP\nPwG8e7lsZmYm0tLSEB8fDwAwMTEpcZ9RUVGIi4vD119/jSZNmu
Dly5c4f/48nj9/jooVK+LAgQPo\n27cvxo0bh5EjRwL4/+lZ7t+/jzZt2mD06NEwNTXF1atXsXDhQvzxxx9
YuXIlAGDHjh0YPHgwXF1d\nMX36dABFJ7srtGHDBoSGhiI4OBguLi548+YNLl+
+jOfPn6vcllwux6hRo3D06FH4+fmhU6dOeP36\nNU6cOIH09HTUr19flUNTouTkZFy/fh1ff/01jIyMEBYW
hmHDhuHSpUuoUqUKAGDNmjX46quvMHbs\nWAwYMAA3b96Et7e34oWlhe7evQsPDw/UqVMHUVFRqFmzJrZv3
44RI0Zg586d8PDwUOrfyJEj4e3t\njaCgoPfO15SZmYlJkybB398fdevWRXx8PKZMmYJGjRopTdxH5Q8Dis
qsoKAAs2fPhoeHBzZs2KBY\n7ubmhpaDel0LAAAHSElEQVQtW2LVqlUICQnBhQsXkJeXp/Tm6C5duii2b9C
gAWrWrAljY2NBf/We\nPXsWnp6e8PHxUSz7+/0dZ2dnAEDt2rWLtPfpp58qvpfL5ejQoQMqVaqEgIAALFy4
EFWrVkWrVq1Q\noUIFmJubv7ees2fPonXr1ggMDFQs8/T0VHyvSltJSUk4fPgwlixZojQRp7rvU71+/Rq7d
+9GtWrV\nAAA1atRA7969cfToUQwYMEBxFtenTx8sXboUAODh4YHq1avD19dXqa0FCxYo/igofFO9h4cH/v
jj\nD0RERCgFVEFBAf71r39h3Lhxgup88eIFdu7cqQgjV1dXJCcnY9euXQyoco6X+KjMrl27hj///BPD\nh
g1DXl6e4qtq1apo06YNTp06BQBo2bIlDAwMMHbsWCQmJuLZs2dl2m+bNm1w4MABLFiwAL/+
+iv+\n+usvwZ+VyWSYO3cuWrZsCUtLS5ibm2Pq1KnIz88v9TJaabWcO3cOs2fPxs8//4w3b96o3Eaho0eP\
nwsjICKNGjfrgNoTo0KGDIpwAKN7o/eDBAwDAvXv3kJGRgcGDByt9bsiQIZBIJErLjhw5gl69esHU\n1FTp
d8Dd3R3nz59HTk6O0vb9+vUTXKdUKlUKosqVK8PW1lZRJ5VfDCgqs6dPnwIAfHx8YG5urvSV\nnJyMzMxMA
EDjxo2xa9cuvH37Fj4+PnBwcICnpydSUlI+aL/BwcEIDAxEYmIiPD09YW9vj6lTp0Im\nk733sxMnTsTmzZ
vh6+uLH374AceOHcOCBQsAQOk+lFBjx45FVFQUTp8+jUGDBqF+/foYO3as4vKl\nKjIzM2FpaQkjI81e4Pj
nVDSFZ7WF/X/8+DEAFJlt1sTEBFWrVlX8nJ+fj+fPnyM+Pr7I8V+wYAEK\nCgqUjomBgUGJlzeF1FlY64cc
J9ItvMRHZVb4P5CwsLBih3P/fYRWt27d0K1bN+Tk5CAlJQX//ve/\nMWzYMKSmpqo8iWHFihURFBSEoKAgP
H78GP/9738xb9485Obmlvos1cuXL5GUlITQ0FB8+eWXiuXn\nz59Xaf9/Z2BgAB8fH/j4+CAzMxNHjhzBvH
nz4OPjU+yzT6UxMzNDRkYG8vLyVAqpwn/n3NxcpeWF\nfyCoqnCQSUZGhtLynJwcvHr1SvGzoaEhqlWrBk9
PzyKX/gqZmZkpvv/n2Zc6VKxYEXl5eSgoKFCa\noPRD+07iwDMoKrOmTZuiVq1auHnzJlq3bl3kq7jJ4ExM
TNC1a1f4+/vj5cuXiss1xsbGRS4HCWFt\nbY1x48ahY8eOuHbtmqItiURSpL2cnBzI5XKl//nL5XJs3bq1S
LsfUk/NmjUxbNgw9O/fX1GLKm25\nu7sjLy8PmzdvVmm/NjY2AKC0T6Do82xC2drawtLSEnv27FFanpCQAL
lceRq57t274/Lly3Bycir2\nd6BChQofVINQNjY2yM/Px82bNxXLnj17VqY/Okj7eAZFZWZoaIiFCxfC29s
bb968Qf/
+/VGzZk1k\nZGQgJSUFDRs2xMSJE7Fq1SqcP38e3bt3R+3atfHs2TMsWrQIdevWhaOjI4B3lwG3bduGDRs2
oFmz\nZqhUqRKaNGlS7H4//fRTODs7o0WLFqhevTouXLiAX375RfFXvIGBARwcHHDw4EF07twZ1apVQ+3a\
ntWFlZYXmzZtjyZIlMDMzQ/Xq1REfH1/sPbHGjRvj+PHj+PHHH2FhYQFzc3NFEPzd5MmTFbMGm5ub\nIy0t
Dbt371YaHCC0re7du8PT0xMzZszAvXv34ObmhpycHJw4cQIDBw5E+/bti/33sLOzQ9u2bbFw\n4UJUq1YNN
WrUwJYtW/Dw4cP3H8RiVKhQATNmzMCMGTMwbdo0DBgwADdu3MDy5cthamqqtO3XX38N\nDw8P9OvXD1988Q
Xq1q0LmUyGK1eu4PHjx4rh/ZrSu3dvmJqawt/fHzNnzsTr168RGxurdI+NdA/P\noEgt+vfvj3379uH58+e
YMmUKhg4dipCQEGRmZipG07Vo0QIvXrxASEgIhgwZglmzZqFRo0ZITExU\n/IU9fvx4DBw4EPPmzYO7uzvG
jBlT4j47duyII0eOwM/PD15eXtiwYQOCgoIwb948xTaLFi2CoaEh\nvLy80K1bN2zZsgUAsH79ejg5OSEgI
AD+/v6wtbVFaGhokX3Mnz8ftra2GDt2LLp164bFixcXW0uH\nDh1w7tw5TJ8+HUOGDEFsbCxGjx6tGP2mSl
sSiQQbN27E9OnT8cMPP2D48OGYOnUqbt26VeR+0D+t\nXbsWLVu2RFBQEPz9/eHg4ICpU6eW+pnS+Pj4IDQ
0FElJSRgxYgR27dqF9evXFwkoOzs7HDt2DA4O\nDggJCcHgwYMRFBSEX3/9FW5ubh+8f6HMzMywdetW5Obm
YuzYsQgPD8e0adM4yk/Hccp3IiISJZ5B\nERGRKDGgiIhIlBhQREQkSgwoIiISJQYUERGJEgOKiIhEiQFFR
ESixIAiIiJRYkAREZEo/R+SZ+Jm\nUcr4IAAAAABJRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc4c0fc4ac8>"
]
},
"metadata": {},
}
],
"source": [
"samples = make_array()\n",
"for i in np.arange(10000):\n",
" sample = simulate_under_null(len(states))\n",
" samples = np.append(samples, sample)\n",
"Table().with_column('Test statistic under null',
samples).hist(bins=np.arange(-4, 28+2, 2))"
]
},
{
"metadata": {},
"source": [
"### Conclusion\n",
"**Question 3.6.** Complete the analysis as follows:\n",
"1. Compute a P-value.\n",
"2. Draw a conclusion about the null and alternative hypotheses.\n",
"3. Describe your findings using simple, non-technical language. Be careful
not to claim that the statistical analysis has established more than it really
has."
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.0015"
]
},
"metadata": {},
}
],
"source": [
"p = np.count_nonzero(samples>=test_stat_72)/10000\n",
"p"
]
},
{
"metadata": {
},
"source": [
"**P-value:** .0018\n",
"\n",
"**Conclusion about the hypotheses:** Because the p-value is less than 1%, it
is highly statistically significant at the 1% level and we can reject the null
hypothesis that each state's murder rate was equally likely to be higher or lower
in the treatment period than in the control period and accept the alternative
hypothesis. \n",
"\n",
"**Findings:** The statistical analysis shows that the murder rate was more
likely to increase after the death penalty was removed. However, no causation can
be proved, only correlation."
]
},
{
"metadata": {
"for_assignment_type": "student"
},
"outputs": [],
"source": [
"# Use this cell to compute the P-value, if you wish (ungraded)"
]
},
{
"metadata": {},
"source": [
"# 4. Further evidence\n",
"\n",
"So far, we have discovered evidence that when executions were outlawed, the
murder rate increased in many more states than we would expect from random chance.
We have also seen that across all states and all recent years, the murder rate goes
up about as much as it goes down over two-year periods. \n",
"\n",
"These discoveries seem to support the claim that eliminating the death penalty
increases the murder rate. Should we be convinced? Let's conduct some more tests to
strengthen our claim.\n",
"\n",
"Conducting a test for this data set requires the following steps:\n",
"\n",
"1. Select a table containing murder rates for certain states and all
years,\n",
"2. Choose two years and compute the observed value of the test statistic,\n",
"3. Simulate the test statistic under the null hypothesis that increases and
decreases are drawn uniformly at random, then\n",
"4. Compare the observed difference to the empirical distribution to compute a
P-value."
]
},
{
"metadata": {},
"source": [
"This entire process can be expressed in a single function, called
`run_test`.\n",
"\n",
"**Question 4.1.** Implement `run_test`, which takes the following
arguments:\n",
"\n",
"- A table of murder `rates` for certain states, sorted by state and year like
`murder_rates`, and\n",
"- the year when the analysis starts. (The comparison group is two years
later.)\n",
"\n",
"It prints out the observed test statistic and returns the P-value for this
statistic under the null hypothesis.\n",
"\n",
"Keep in mind that `run_test` should work **regardless of the direction of
association in your alternative hypothesis.** Therefore, you'll need to account for
if òbserved_test_statistic` is negative or positive.\n",
"\n",
"*Hint 1*: You can complete most of this question by copying code you wrote
earlier. \n",
"\n",
"*Hint 2*: This problem might seem daunting. Start by writing out the
different steps involved in running a test."
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"Test statistic 1971 to 1973 : 22\n"
]
},
{
"data": {
"text/plain": [
"0.0015"
]
},
"metadata": {},
}
],
"source": [
"def run_test(rates, start_year):\n",
" \"\"\"Prints out the observed test statistic and returns a P-value for
this statistic under the null hypothesis\n",
" Parameters\n",
" ----------\n",
" rates : Table\n",
" A table of murder rates for certain states, sorted by state and year
like murder_rates\n",
" start_year : int\n",
" The year when the analysis starts\n",
" \"\"\"\n",
" states1 = rates.sort('State',distinct = True).column('State')\n",
" end_year = start_year + 2\n",
" year = rates.where('Year',are.between(start_year,end_year+1))\n",
" \n",
" stats = make_array()\n",
" for i in np.arange(len(states1)):\n",
" s = diff_n(year.where('State',states1[i]).column(3), 2)\n",
" stats = np.append(stats,s)\n",
" observed_test_statistic = np.count_nonzero(stats>0)-
np.count_nonzero(stats<0)\n",
" print('Test statistic', start_year, 'to', end_year, ':',
observed_test_statistic)\n",
" num_states = rates.group('State').num_rows\n",
" \n",
" samples = make_array()\n",
" for i in np.arange(5000):\n",
" sample = simulate_under_null(len(states1))\n",
" samples = np.append(samples, sample)\n",
" if observed_test_statistic > 0:\n",
" p = np.count_nonzero(samples>observed_test_statistic)/5000\n",
" return p\n",
" elif observed_test_statistic < 0:\n",
" p = np.count_nonzero(samples<observed_test_statistic)/5000\n",
" return p\n",
" \n",
"run_test(death_penalty_murder_rates, 1971)\n",
"p"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/submissions/zpWM5m\n",
"\n"
]
}
],
"source": [
"_ = ok.grade(\"q4_1\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"### The rest of the states\n",
"\n",
"We found a dramatic increase in murder rates for those states affected by the
1972 Supreme Court ruling, but what about the rest of the states? There were six
states that had already outlawed execution at the time of the ruling.\n",
"\n",
"**Question 4.2.** Create a table called `non_death_penalty_murder_rates` with
the same columns as `murder_rates` but only containing rows for the six states
without the death penalty in 1971. Perform the same test on this table. **Then**,
set reject_null_2 to whether their murder rates were also more likely to increase
from 1971 to 1973."
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"Test statistic 1971 to 1973 : 1\n"
]
},
{
"data": {
"text/plain": [
"0.4248"
]
},
"metadata": {},
}
],
"source": [
"non_death_penalty_murder_rates =
murder_rates.where('State',are.contained_in(non_death_penalty_states))\n",
"run_test(non_death_penalty_murder_rates, 1971)"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" <thead>\n",
" <tr>\n",
Rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
],
"text/plain": [
"Alaska | 1960 | 226,167 | 10.2\n",
"Alaska | 1961 | 234,000 | 11.5\n",
"Alaska | 1962 | 246,000 | 4.5\n",
"Alaska | 1963 | 248,000 | 6.5\n",
"Alaska | 1964 | 250,000 | 10.4\n",
"Alaska | 1965 | 253,000 | 6.3\n",
"Alaska | 1966 | 272,000 | 12.9\n",
"Alaska | 1967 | 272,000 | 9.6\n",
"Alaska | 1968 | 277,000 | 10.5\n",
"Alaska | 1969 | 282,000 | 10.6\n",
]
},
"metadata": {},
}
],
"source": [
"murder_rates"
]
},
{
"metadata": {},
"outputs": [],
"source": [
"reject_null_2 = False"
]
},
{
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/submissions/BBw3pN\n",
"\n"
]
}
],
"source": [
"_ = ok.grade(\"q4_2\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"### The death penalty reinstated\n",
"\n",
"In 1976, the Supreme Court repealed its ban on the death penalty in its
rulings on [a series of cases including Gregg v. Georgia]
(https://en.wikipedia.org/wiki/Gregg_v._Georgia), so the death penalty was
reinstated where it was previously banned. This generated a second natural
experiment. To the extent that the death penalty deters murder, reinstating it
should decrease murder rates, just as banning it should increase them. Let's see
what happened."
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"Increases minus decreases from 1975 to 1977 (when the death penalty was
reinstated) among death penalty states: -18\n",
"Test statistic 1975 to 1977 : -18\n"
]
},
{
"data": {
"text/plain": [
"0.0066"
]
},
"metadata": {},
}
],
"source": [
"print(\"Increases minus decreases from 1975 to 1977 (when the death penalty
was reinstated) among death penalty states:\",\n",
" sum(death_penalty_murder_rates.where('Year',
are.between_or_equal_to(1975, 1977))\n",
" .group('State', two_year_changes)\n",
" .column(\"Murder Rate
two_year_changes\")))\n",
"run_test(death_penalty_murder_rates, 1975)"
]
},
{
"metadata": {},
"source": [
"*Hint:* To sanity check your results, figure out what your test statistic
should be when there are 18 more decreases than increases, and verify that that's
the test statistic that was printed. Also, you should have found a P-value near
0.005. If your P-value is very different, go back and inspect your `run_test`
implementation to make sure that it correctly produces low P-values when there are
many more decreases than increases."
]
},
{
"metadata": {},
"source": [
"**Question 4.3.** Now we've analyzed states where the death penalty went away
and came back, as well as states where the death penalty was outlawed all along.
What do you conclude from the results of the tests we have conducted so far? Does
all the evidence consistently point toward one conclusion, or is there a
contradiction?\n",
"\n",
"1) Our results point toward the conclusion that the death penalty moratorium
increased murder rates.\n",
"\n",
increased murder rates, but we have not accounted for time as a confounding
factor.\n",
"\n",
"3) Our results don't allow us to make any conclusion about murder rates and
death penalties.\n",
"\n",
didn't influence murder rates.\n",
"\n",
"5) None of these conclusions are valid, or multiple of these conclusions are
valid\n",
"\n",
"Below, set we_conclude to a single number, corresponding to your answer."
]
},
{
"metadata": {},
"outputs": [],
"source": [
"we_conclude = 2"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/submissions/G6B3x8\n",
"\n"
]
}
],
"source": [
"_ = ok.grade(\"q4_3\")\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"## 5. Visualization\n",
"\n",
"While our analysis appears to support the conclusion that the death penalty
deters murder, [a 2006 Stanford Law Review paper]
(http://users.nber.org/~jwolfers/papers/DeathPenalty%28SLR%29.pdf) argues the
opposite: that historical murder rates do **not** provide evidence that the death
penalty deters murderers.\n",
"\n",
"To understand their argument, we will draw a picture. In fact, we've gone at
this whole analysis rather backward; typically we should draw a picture first and
ask precise statistical questions later!\n",
"\n",
"What plot should we draw?\n",
"\n",
"We know that we want to compare murder rates of states with and without the
death penalty. We know we should focus on the period around the two natural
experiments of 1972 and 1976, and we want to understand the evolution of murder
rates over time for those groups of states. It might be useful to look at other
time periods, so let's plot them all for good measure."
]
},
{
"metadata": {},
"source": [
"**Question 5.1.** Create a table called àverage_murder_rates` with 1 row for
each year in `murder_rates`. It should have 3 columns:\n",
"* `Year`, the year,\n",
"* `Death penalty states`, the average murder rate of the states that had the
death penalty in 1971, and\n",
"* `No death penalty states`, the average murder rate of the other states.\n",
"\n",
"àverage_murder_rates` should be sorted in increasing order by year. Its
first three rows should look like:\n",
"\n",
"|Year|Death penalty states|No death penalty states|\n",
"|-|-|-|\n",
"|1960| | |\n",
"|1961| | |\n",
"|1962| | ||\n",
"\n",
"*Hint:* It's easiest to use `pivot`. We don't expect you to account for
differences in population."
]
},
{
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
" <thead>\n",
" <tr>\n",
" <th>Year</th> <th>Death penalty states</th> <th>No death
penalty states</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>1960</td> <td>5.27955 </td> <td>3.55
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>1961</td> <td>4.77727 </td> <td>3.68333
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>1962</td> <td>4.61591 </td> <td>2.33333
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>1963</td> <td>4.61364 </td> <td>2.75
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>1964</td> <td>4.71136 </td> <td>3.4
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>1965</td> <td>4.82727 </td> <td>3.18333
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>1966</td> <td>5.43182 </td> <td>4.51667
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>1967</td> <td>5.875 </td> <td>3.73333
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>1968</td> <td>6.27045 </td> <td>4.73333
</td>\n",
" </tr>\n",
" </tbody>\n",
" <tr>\n",
" <td>1969</td> <td>6.50227 </td> <td>4.73333
</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
],
"text/plain": [
"Year | Death penalty states | No death penalty states\n",
"1960 | 5.27955 | 3.55\n",
"1961 | 4.77727 | 3.68333\n",
"1962 | 4.61591 | 2.33333\n",
"1963 | 4.61364 | 2.75\n",
"1964 | 4.71136 | 3.4\n",
"1965 | 4.82727 | 3.18333\n",
"1966 | 5.43182 | 4.51667\n",
"1967 | 5.875 | 3.73333\n",
"1968 | 6.27045 | 4.73333\n",
"1969 | 6.50227 | 4.73333\n",
]
},
"metadata": {},
}
],
"source": [
"# For reference, our solution used 5 method calls\n",
"years = murder_rates.sort('Year',distinct = True).column('Year')\n",
"death =
murder_rates.where('State',are.contained_in(states)).group('Year',np.mean).column(3
)\n",
"no_death =
murder_rates.where('State',are.contained_in(non_death_penalty_states)).group('Year'
,np.mean).column(3)\n",
"average_murder_rates = Table().with_columns('Year',years,'Death penalty
states',death,'No death penalty states',no_death)\n",
"average_murder_rates"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n"
]
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
},
{
"name": "stdout",
"text": [
"URL: https://okpy.org/cal/data8/fa17/project2/submissions/J603AP\n",
"\n"
]
}
],
"source": [
"_ = ok.grade('q5_1')\n",
"_ = ok.backup()"
]
},
{
"metadata": {},
"source": [
"**Question 5.2.** Describe in **one short sentence** a high-level takeaway
from the line plot below. Are the murder rates in these two groups of states
related?"
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAAocAAAEfCAYAAAAzyWxRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAL
EgAACxIB0t1+/AAAIABJREFUeJzs3WdcU+fbB/DfyWJDEJEhIiqg4kDFgQMFceHALba2aqtt\n1Wpb7d9Wq
7VDraP2sdUua2uXe1brwslwoyLiYijgRmQqIyHJeV5QAicDAmQwru/n44tz59znvhIF\nr9yTycnJYUEIIY
QQQggAnqkDIIQQQgghtQclh4QQQgghRImSQ0IIIYQQokTJISGEEEIIUaLkkBBC\nCCGEKFFySAghhBBClCg
5JIQQQgghSpQcEkIIIYQQpVqZHCYlJZk6hDqLPruaoc+v+uizqxn6/Agh\ntUWtTA4JIYQQQohpUHJICCGE
EEKUKDkkhBBCCCFKlBwSQgghhBAlgakDIIQQQsqTyWTIz883dRiE\n1FsCgQBWVlbaXzdiLKQeY1kWt5PvQ
65QoG0rdwgEfFOHRAipg2QyGV68eAGxWAyGYUwdDiH1Un5+\nPiQSCczMzDS+Tskh0Yu/957AodMxAACxrR
UGBfghuHdniG21fzMhhBBV+fn5lBgSYmCWlpbIy8uj\n5JAYTurDp8rEEABy8vKx81AU9oafQc8uPgjp1xW
tmruaMEJCSF1CiSEhhlXZzxglh6TGtu6P0Fgu\nkykQfekGoi/dgJeHK0ICu6FHpza1csiZZVmkPHiKl/mF
pg6FEEIIMSlKDkmN3EhMRdzte5Xel5T6\nGEl/7Ecj8SnMmRIKH6/mRohON4/TM7F2017cf5QBWbEEX3xoi
/beHqYOixBCCDEJ2sqGVBvLsti6\n/zSnrK1nM0wdNxDOjvYa62TlvMDPWw6BZVljhFipy9cTsWjN77j/KA
MAIJHKsO6P/ch9QSslCSF1\nS1paGsRiMWJjY00dSrXNnDkTYWFhpg6jwaPkkFTbxWt3cDftCads0sj+CAn
shm+XzMCCmRPg27al\nWr305zl4lJ5prDA1UigU2HEwEl//shsFhVLOa7l5+di47UitSWAJIbXfzJkzIRaL
IRaL0bhxY3h6\nemL48OHYuHEjiouLDdJeQ0iihg0bhvnz5xu0jZok1WKxGPv37zdAVKZFySGpFplMjh0HI
zllPTq1\nhleLpgBKJrt2bueJT96diP9b/DY83Jw4995MTDVWqGpe5Bdi1c87sffoWa33xFxPROTF60aMih
BS\n1wUGBiIhIQHXr1/H3r17MWTIEKxYsQIhISG0byOpUyg5JNUScSEOj9OzlNcMA4QN76fx3qbOjdG7\na
ztO2c3ENIPGp03qw3Qs+vp3XLvFnSfJ5/Pg6GDHKft91zE8y8wxZniEkDrMzMwMTk5OcHV1RceO\nHTF79m
wcPHgQcXFx+O6775T3SaVSfPbZZ/Dx8YGLiwuCgoJw8uRJ5etyuRyzZ89Gx44d4ezsjC5d\nuuC7776DQqE
AAKxYsQLbtm1DeHi4srcyOjpaWf/
+/fsYNWoUXFxc0KNHD5w+zZ3+o2rYsGGYO3cu\nPv74YzRv3hzNmzfHp59+qmxPl5ijo6MhFosRGRmJ4OBg
uLi4IDAwENeuXVPek5WVhWnTpsHHxwfO\nzs7w9/fH5s2btcY1c+ZMnD17Fhs3blS+z9TUVHTu3Bnr16/n3
Hv37l2IxWJOe+U9fPgQr7zyCjw8\nPODi4oJu3bphz549AABfX18AQFBQEMRiMYYNGwYAuHr1KkaPHo2WLV
uiWbNmGDJkCC5duqR8ZocO\nHQAAU6ZMgVgsVl4DwJEjR9CvXz84OTmhY8eOWLp0KaTSslGqAwcOoFevXnB
2doaHhweGDh2KZ8+e\naf0sjI0WpJAqK5JIsfvIGU5ZUE9fNHVurLVOe2/uApSbiWlgWdaoW1acuXwTG7Yc
grRYxim3s7XC\nB2+MgtjWGu8uLvsFXiQpxvd/HsDnH7wGHo+
+RxFiSmGzvzJqezu+/0Qvz/Hx8UFwcDD+/fdffPJJ\nyTPfffddpKSkYOPGjWjatCmOHTuGiRMn4tSpU+jQ
oQMUCgVcXFzwxx9/wMHBAVevXsX7778Pe3t7\nTJ48GXPmzEFiYiKys7OxYcMGAIC9vT2ePCmZ5rNs2TJ8+
eWX+Oabb/D111/jzTffRHx8PKytrbXG\nuWvXLrzyyis4fvw4bt68iffffx9OTk6YPXu2TjGX+uKLL/D555
/D2dkZCxYswNtvv42LFy+CYRgU\nFRXB19cX77//PmxtbREREYG5c+eiWbNm6NdPvXNh5cqVuHv3Lry8vLB
kyRIAQOPGjfH6669jy5Yt\nmDNnjvLezZs3o0OHDujUqZPG9/fhhx9CIpHg33//hY2NDZKTk5WvnTp1Cv37
98eePXvQvn17iEQi\nAMCLFy8QFhaGlStXgmEYbNy4EePHj0dsbCwaNWqE06dPw9PTE+vWrcPgwYPB55fsx
HHy5Em8/fbb\nWLFiBXr37o0HDx5g3rx5kEgkWLZsGdLT0zFt2jQsWbIEoaGhyM/Px+XLlyv5l2RclBySKj
sSEYPs\n3JfKa5FQgPFD+1ZYx8PNCVaWZsgvkAAAXhYUIe1ROjzcnA0aa6ldh6LUEloA8PJwxbzpY9FIbAM
A\nGBncDUfOxCtfT7j3EAdOXMCoQb2MEichpP5p06YNIiNLpuGkpKRg9+7duH79Opo1awYAePvttxER\nEY
E//vgD33zzDYRCIRYtWqSs37x5c8TFxWHPnj2YPHkyrK2tYW5uruypVDVr1iyEhIQAAJYsWYLt\n27cjPj4
ePXv21Bqjk5MTVq9eDYZh4O3tjeTkZPz444+YPXu2TjGXWrRoEfr2Lfn/4KOPPsKQIUPw\n+PFjNG3aFK6u
rnjvvfeU906dOhVRUVHYvXu3xuTQzs4OQqEQlpaWnPc5adIkfPXVV4iJiUG3bt0g\nl8uxfft2zJ07V+v7e
/DgAUJDQ5WJrIeHh/I1BwcHAECjRo047ajGtHr1ahw4cADHjx9HWFgYGjdu\nrIyzfL01a9Zgzpw5eO211w
AALVq0wOeff4533nkHS5cuxZMnT1BcXIyRI0fC3d0dQMmXiNqEkkNS\nJS/yC3HgxHlOWUhgN2VypQ2Px4O
PZ3PEXE9UlsUnpBolOUxOfawxMRwU0AWTxwyAUFj2Y9CrS2s8\nycrnDDvvPBSFTj4tjZbIEkLql/KjJHFx
cWBZFv7+/px7JBKJMqkCgE2bNuGvv/7CgwcPUFRUhOLi\nYmViVpl27cqm8bi4uAAAMjIyKqzTtWtXzkhO9
+7dsXz5cuTl5ekcs2rbzs7OyrabNm0KuVyOtWvX\nYu/evXjy5AmkUimkUin69Omj0/sq5eTkhMGDB2Pz5s
3o1q0bTpw4gezsbEyYMEFrnRkzZmDevHk4\nefIk+vXrh+HDh2vtZSyVkZGB5cuXIzo6GhkZGZDL5SgsLMT
Dhw8rrBcXF4erV69yphIoFAoUFhYi\nPT0dHTp0QGBgIHr16oWgoCAEBgZi5MiRymSzNqDkkFTJvvCznNW9
1pbmCB3oX0GNMu28ucnhzcQ0\njAjWrW5NHDp1kXMtFPIxPWwIAv191e5lGAYzJg3D/K9+xYv/NsSWyxVY/
8d+rPj4TYiEQoPHSwip\nX+7cuaPsqVIoFGAYBqdOnYJQ5feJubk5AGDv3r1YuHAhli5diu7du8PW1hYbN2
7EwYMHdWqv/HNL\nE76a7L6gS8y6tL1+/Xp8//33WLlyJXx8fGBtbY0vv/yy0sRVk8mTJ+Ott97CihUrsHn
zZgwfPhxi\nsbjC+4ODg3H8+HFERERg0KBBmDt3LhYuXKi1zsyZM/Hs2TN89dVXcHd3h5mZGUJDQzlzBzVR
KBT4\n+OOPMWrUKLXXGjduDD6fj3379iEmJganTp3C33//jS++
+AKHDh3iDNGbEiWHRGcZmTkIj+LOixg5\nqBesLS10qt+
+tQfn+nbyfchkcoOemPI8KxcXrt3hlH3wxmh07eittY69nQ3efnUovtm4R1n28Gkm\ntu4/janjBhksVkKI
dvqaA2hst27dwsmTJ/G///0PANCxY0ewLIv09HS1XrdS58+fh5+fH95+
+21l\nWUpKCucekUgEuVyutzivXLnC6eGMiYmBi4sLbG1tdYpZF+fPn8eQIUMwceJEACVJY3JyMuzs7LTW\
n0fY+BwwYABsbG2zatAlHjx7Frl27Km2/adOmmDp1KqZOnYpvv/0WP//8MxYuXKicY6jazoULF7By\n5UoM
HjwYAPDs2TOkp6dz7hEKhWr1fH19kZiYiJYt1bdyK8UwDLp3747u3bvj448/hr+/P/bt21dr\nkkOaZU90t
utwNGSystVrDvY2GNLPT+f6bs6NYWdrpbwukhTj7v0nFdSouSORl6FQlH1jdnN2gF8H\nr0rrdfdtjUD/jt
xnRVzG9TspWmoQQho6iUSC9PR0PHnyBPHx8fj+++
+Vw5eliyc8PT0xYcIEzJo1\nC/v370dqaipiY2Oxfv16HDhwQHnP9evXcfz4cdy9exerV6/GuXPnOG25u7v
j9u3bSEpKQmZmZo33\nUnz69CkWLFiApKQk7N+/H+vWrcOsWbN0jlkXnp6eiIqKwvnz55GYmIj58+fj/v37
FdZxd3fHlStX\nkJaWhszMTOUKaj6fj0mTJuHLL7+Ei4uLxjmL5X388cc4ceIEUlNTcf36dZw4cQKtW7cGA
Dg6OsLC\nwgInT57Es2fPkJubCwBo1aoVdu7ciTt37uDq1at48803lYlk+fgiIyORnp6OnJyS3S0+
+ugj7N69\nG8uXL8etW7eQmJiI/fv3KxfVxMTE4Ouvv8bVq1fx4MEDHD58GI8ePVLGUxtQckh0kvboGaIux
XPK\nxg8NqNIwK8MwaO+lumo5VR/haVQkkeL0ee62BkODuuu8QnrK2IFq29v8+Pe/yuFmQggpLyIiAq1b\n
t0b79u0xcuRIHDlyBAsWLMDhw4dhZVX2xfiHH37ApEmTsGTJEnTr1g1hYWE4e/ascnHCG2+8gVGj\nRmH69
OkICgrC/fv38e6773LamjJlCry9vREUFIRWrVrhwoULNYp9/PjxUCgUCA4OxnvvvYfXX39d\nmRzqErMu5s
+fjy5dumD8+PEYOnQoLC0tMX78+ArrzJkzByKRCP7+/mjVqhUePHigfO21116DVCrF\npEmTKv29rlAo8NF
HH6FHjx4YPXo0mjRpgp9+
+gkAIBAIsGrVKvz9999o06YNXn31VQDA999/j/z8\nfAQGBuLNN9/Ea6+9pvZ+ly1bhujoaLRr1w4BAQEAg
ODgYOzcuRNnzpxBcHAwgoODsXbtWri5uQEA\nbG1tcfHiRYSFhcHPzw+LFy/G/Pnza9Wm5kxOTk6tOwYiKS
kJXl6V9+4QdYb47FiWxYofd3DOUHZz\ndsDqhdOVS/d1dercNWzYelh53d67OT59b5LeYi3vSEQM/th9XHl
ta22BH5bOrjChVf387tx9gM+/\n/Rvlp+sMC+qGyWMHGiTmuox+bmuGPr8Subm5FQ4zEv0bNmwYfHx88PXX
X5s6lCq5fPkyBg8ejGvX\nrum8WIeUqehnrdKeQ7lcjmXLlqFjx47KzRyXLVsGmUxWWVVST0RdusFJDAHgl
dCgKieGQMmilPIS\nUh5CaoCjpRQKBY5GcudHDgzoUuUFJW1aNcPIgdztH05fiENhkaTGMRJCCKk6iUSCR4
8eYfny5Rg+\nfDglhgZQaXL47bff4tdff8WqVatw6dIlrFy5Ehs3bsT//d//GSM+YmLZuS/w555jnDIfL3e
d5u1p\n0sRBzBmqLS6WIzHlUY1i1OTqjWQ8zchWXgsEPAwK0H1+ZHnjQgJgZ2OpvC4olCLyYnwFNQghhBjK
\n7t270aFDB2RmZmL58uWmDqdeqjQ5vHTpEoYMGYKQkBA0b94cQ4cORUhICK5cuWKM+IgJsSyL33aE\nKze
uBko2vH77laHVPtmEYRi0U5l3eCMhtSZhanTo9CXOdW+/dhDbaj8doCJCoQAD+nTmlIVHXa7R\n1hCEEFJb
HDp0qE4NKU+aNAlZWVmIiopSzuMj+lVpcujv748zZ84gMbFkf7o7d+4gOjoaAwfSnKv6\n7vzV25x9CQEgb
EQ/uDRpVKPnqg4t6/uc5ZQHT3EribsCbmhQ9xo9c2CfLuDzy35cHqdnqQ21E0II\nIfVBpfscfvDBB3j58i
V69OgBPp8PmUyG//3vf5g+fbox4iMmkvsiH7/vCueUeXm4Ymhgtxo/u723\nB+c6Oe0xCgolsLQwq/GzAfV
ew/bezeHhpn7EVFXY29mgZ+c2OHP5lrLsSEQMOvm0qtFzCSGEkNqm\n0uRw79692L59O3799Ve0adMG8fHx
WLBgAdzd3TF58mSt9ZKSkmoUWE3rN2T6+Oz+
+icCT9KfK68F\nfB4G926Hu3fv1vjZAGBlzsezzDzl9bGIs2jnWfNJxbkvCnA88hLk5fY27ODlUqXPRNu9b
Vs0QXhk\njPL6bEw8zl7wRBMHWllZin5ua6Y2f360kpqQhqPS5HDJkiWYPXs2xo4dC6Dk3MQHDx5g7dq1FS
aH\nNflFQls6VJ8+PrtLcQlITMvg7Mv1SmggAnrWvNewVO9uvjgWfVV5nVeo0Mvf+fZ/I2BuUbZ4xNWp\nE
UYOCdJ5jmRFn5+XlxciYhKRlPpYWZZwPxO9/bvWLOh6gn5ua4Y+P0JIbVHpnMOCggK1LUv4fL5y\nl3JSv7
zIL8RvO45yylo0c8Lw/j302o7qUXr6mHcokRbjxJlYTllIYLdqL57RZIjKsHrkxevILyjS\n2/MJIYQQU6s
0ORwyZAi+/fZbhIeHIy0tDf/++y9+
+OEHDB8+3BjxESP7a+8J5OTlK6/5fB5mTBqu\n9/OPfVRWLKc+TK/xySNRF+M5z7C2NEff7vo9p9K/UxvY2
5Wtei6SFCPi4nW9tkEIIYSYUqXJ4erV\nqxEaGooPP/wQPXr0wOLFizFlyhR8+umnxoiPGFHszWREqezfN2
pQzxov5tDExspC7bm3kqrfe8iy\nLA5HcBeiBPfuDHMzkZYa1SMQ8DGwTxdOWXjkZepJJ4QYVWxsLMRiMdL
S9LvbgyYzZ86sVUe7VVVa\nWhrEYjFiY2Mrv5kA0CE5tLGxwcqVK3Hjxg08ffoUcXFxWLJkCczNzY0RHzGS
/IIibNx+hFPm7uqI\nMYP7GKxN1S1tarLf4bVbd/E4PUt5zefzMKSfYeYCBvfuDIGg7Ecn/XkOYm/qZ6EOI
aRumjlzJsRi\nMVavXs0pj46OhlgsRmZmpoki011DSaKM9XdS3aR6xYoV6NmzZ+U3GlClySGp/xQKBTZuP4
zM7BfK\nMoYBZkwapvfh5PLa62G/Q5ZlEZ+Qgq0HTnPKe3Zug0ZimxrFp43Y1gq9/Npxyo6UW8VMCGmYzM3
N\nsX79ejx//rzymwmpxSg5bOBYlsXvu47h/NU7nPLQAT3RqrmrQdtu08odPF7ZYpFH6ZnIynlRQY0y\nuS
/ysf/4eXzw5c9Ytn4b7j/K4Lxe002vKxOi0isZfycVD55kaLmbENIQBAQEoFmzZmq9h6rOnj2L\n4OBgODk
5wcvLCwsXLoRUKq2wzokTJ9CtWzc4OTkhJCQEycnJavdcvHgRQ4cOhYuLC9q2bYt58+Yh\nLy+P84zS0848
PDwwZswYJCQkKF/39fUFAAQFBUEsFmPYsGGc5//0009o27YtmjdvjlmzZqGgoEBr\nvKW9c0ePHkWfPn3g5
OSEfv364dq1a1WKediwYfjwww/x5ZdfomXLlvD09MTixYs5U3l27NiBoKAg\nuLm5wdPTE1OmTMHjx4+hSV
paGkaMGAEAaNWqFcRiMWbOnIlt27ahRYsWkEgknPvfeustTJw4Uev7\n/P333+Hn5wcnJye0bNkSY8aMgUw
mw4oVK7Bt2zaEh4dDLBZDLBYjOjoaAPD555+ja9eucHZ2RocO\nHbBkyRIUFZUsbNyyZQtWrVqF27dvK+tt
2bIFAJCbm4v3338fnp6ecHNzw9ChQzm9vLm5uXj77bfh\n6ekJJycn+Pr64scff9Qae0Uq3cqG1G+7Dkdxt
pQBADdnB4wbarjh5FKWFmZo5e7C2RrmRmKq1kUk\nJb2EqTh1LhYx1xMhk2me59fWs5nBE9uW7i5o3dINCf
ceKsuORl7GWxNDDNouIQ2V5YOPjNpeQbOK\nEzxNeDwePv/8c0yaNAkzZ85EixYt1O55/Pgxxo8fj7CwMPz
4449ISUnBe+
+9Bx6Pp/Wc4IcPH2LS\npEmYPHky3nrrLdy8eROLFi3i3HPz5k2MGTMGCxYswPr165GdnY2FCxdi9uzZ+Ou
vvwAA+fn5mDFj\nBtq3b4/CwkKsWbMGEydOxMWLFyESiXDq1Cn0798fe/bsQfv27SESlc3ZPn/
+PJycnPDPP//g0aNH\nmDp1Kjw9PTFv3rwKP5NPP/0UK1euhIuLC1atWoWwsDDExsbC0tJSp5gBYNeuXXjn
nXdw7NgxxMfH\nY/r06ejUqRPGjRsHAJBKpVi4cCG8vb2RmZmJzz77DNOmTcORI0fU4nFzc8Nff/2FyZMn4
8KFC7C3\nt4e5uTlEIhEWLFiAw4cPY/To0QBKkq2DBw/i119/1fjeYmNj8b///Q8//fQT/P39kZubi6ioKA
DA\nnDlzkJiYiOzsbGzYsAEAYG9vDwCwtLTE999/DxcXFyQkJGDevHkQiURYvHgxxowZg9u3byM8PBwH\nD
x4EANja2oJlWYSFhcHW1hY7duyAvb09tm7ditDQUMTExMDZ2RnLli3DrVu3sGPHDjg6OiItLa3a\nQ+eUHD
Zgh09fwp4jZzlljcQ2WDAzDCKh0CgxtG/twUkObyamqSWHRRIpTp+Pw9HIy3iakV3h89yb\nOhotQQsJ7MZ
JDqMuxuOV0EBYW1oYpX1CSO0zaNAg9OjRA0uXLsWmTZvUXv/tt9/g7OyMb775Bjwe\nD61bt8Znn32GuXPn
YtGiRbC0tFSrs2nTJri5uWH16tVgGAbe3t5ITk7mJJPr1q3D6NGjMWfOHGXZ\nN998g759+yIjIwOOjo4YO
XIk57k//PADmjVrhitXrqBnz55wcHAAADRq1AhOTtwFgzY2Nli7di34\nfD5at26NUaNGITIystLkcP78+Q
gODla25+Pjg927d2Py5Mk6xQwArVu3VibDnp6e+PPPPxEZGalM\nDl9//XVlfQ8PD/zf//0funfvjkePHqF
p06acePh8vjJJc3R0VL5nAJgwYQI2b96sTA53794NGxsb\nDB48WON7e/DgAaysrBASEgIbm5JpTB06lPz/
ZW1tDXNzc5iZmal9lh99VPZFp3nz5pg3bx7Wr1+P\nxYsXw8LCAlZWVhAIBJx6kZGRiI+PR3JyMiwsSv6PW
bx4MY4ePYodO3bg/fffx4MHD+Dr6ws/Pz8A\ngLu7u7a/lkpRcthARV2Kx597TnDKbKwssGj2K3B0EBstjv
atPbAv/Jzy+kZiKliWBcMwyMnLx9HI\nGByPvoqXFewlKBDw0MO3DQb06Yy2nu563dewIt06esPB3kY5V1N
aLMOpc3EIHeBvlPYJIbXTF198\ngYEDB+K9995Tey0hIQFdu3YFj1c2q6tnz56QSqW4d+8e2rdvr7VO+d9t
3btzp87ExcXh3r172Ldv\nn7KMZUtOikpJSYGjoyNSUlKwfPlyXL58GZmZmVAoFFAoFHj48CEq07p1a86ex
87Ozrh8+XKl9crH\naW1tjXbt2uHOnTs6xwyUHL5RnrOzMzIyyqbxXLt2DatWrUJ8fDxycnKUz3j48KFacl
iRyZMno1+/\nfsqkcvPmzXjllVcgEGhOlUqHsn19fREcHIygoCCMGDFCmShqs3//fvz000+4d+8e8vPzIZf
LI
ZfL\nK6wTFxeHgoICeHp6csqLioqQkpICAJg2bRqmTJmCa9euISgoCEOGDEGfPtUbBaTksAG6Ep+EnzYf\n
5JSZmwnx8YwJcHNubNRYvFs0hVDIR3FxyQ/G86w8xN2+h5jriYi8eF1ZromrUyP079UJ/Xp0hK21\n+rdtQ
xMI+BgU4IdtByKUZeFRlzEsqJvaxvENWel0gPyCInTr6F3lRU7X76Rg086SjdmnjhtE51mT\nWs/Pzw+hoa
FYsmQJ5s+fr3O9mnyxVSgUmDx5MmbNmqX2mouLCwAgLCwMrq6u+Pbbb+Hi4gKBQIAe\nPXpUOt8RAIQqo0k
MwyiTMEPGXFnb+fn5GDt2LAIDA7FhwwY4OjoiMzMTISEhOr2v8jp06ABfX19s\n3boVw4YNQ2xsLH755Ret
99vY2CAqKgpnz55FREQE1q5di6VLl+LUqVOc+MuLiYnBm2+
+iY8//hhf\nffUV7OzscPjw4Uq3B1QoFGjSpInGofLSZHTgwIGIj4/H8ePHERkZibCwMIwcObJa8w4pOWxg
biWl\n4dtN+6Aod/awQMDDh2+Ng1cL3b9h6YtIKETrFm64UW6l8oofd2i931S9hNr079UJe46cgbRYBqAk\
nub1yIxndfVubNK7agmVZbNoZrpzX2qaVGxbNfkXnaQsPnz7Hml92QSIt+Xy//mUXFs6aiPbeHoYK\nmdRS
1ZkDaEpLlixBjx49cPLkSU5569atsW/fPigUCmXv4fnz5yESiTTOUSytc+DAAeWoClCSZJTn\n6+uL27dvo
2XLlhqfkZWVhcTERKxZswZ9+/YFUNLjJpPJlPeUzjGsrBerKmJiYuDh4QGgJJG7deuW\ncoFHZTHrIikpCZ
mZmfj000+V7Rw4cKDCOhW9zylTpuC7775DZmYm/P39Kz3SUiAQoF+/fujXrx8W\nLlwIT09PhIeHY+rUqRC
JRGptXLhwAS4uLpyh5QcPHqjFp1rP19cXz549A4/HU75PTRwcHDBx4kRM\nnDgRAwcOxLRp07B27VqYmZlV
+D5U0WrlBiT14VN8/csuZSIDlGxZM2fKSHRso/mXkjGo7neoibWl\nOUYP7oUfvpyD994YBR+v5iZPDAHA1
toSvbtyhzzOX7llomhqn2PRVzgLnu7cfag2nUEbaXExvvt9\nnzIxBACZTIE1v+xG6sOneo+VEH1q2bIlpk
6dip9//plTPm3aNDx9+hQffvghEhISEB4eji++
+AJv\nvfWWxvmGAPDGG2/g/v37WLBgAZKSkrB//378/vvvnHvef/99XL16FXPnzlUO1x49ehQffPABAEAs\
nFsPBwQF19Hh2AAAgAElEQVR//fUX7t27hzNnzmDevHmcIVNHR0dYWFjg5MmTePbsGXJzc2v8OaxZ\nswan
T5/G7du3MXv2bIhEIuVcwcpi1oWbmxvMzMywceNGpKamIjw8HF999VWFdZo1awaGYRAeHo7n\nz5/j5cuXy
tfGjh2LZ8+eYdOmTXjttdcqfM7Ro0fx008/IS4uDvfv38euXbvw8uVLeHt7AyiZ83f7\n9m1lAltcXAxPT0
88efIEO3fuRGpqKn777Tfs2bOH81x3d3c8ePAA165dQ2ZmJiQSCQIDA+Hv749X\nX30Vx48fR2pqKi5duoS
vvvoK586VTM1avnw5Dh48iLt37yIhIQH//vsvPDw8qpwYApQcNhhPM7Lw\n1Q/bUVDI7WZ/a2II/Du3NVFU
JdpV0Avk6GCHqeMG4oelszFxRCDEtlbGC0xHQT19OdfxCak1Hm6p\nD24lpWlMBE+ciUWkykk8mmzed0pti
yIAKCySYsWPO/AsM0cvcRJiKB999JHafDVXV1fs2rUL169f\nR0BAAGbPno2xY8diyZIlWp/TrFkz/P333z
h58iT69OmDH3/8EZ999hnnnvbt2+Pw4cO4f/8+hg8f\njj59+uDLL79Uztvj8XjYtGkTbt68iZ49e2L+/Pl
YtGgRJ3EQCARYtWoV/v77b7Rp0wavvvpqjT+D\nzz77DIsWLUK/fv1w9+5d7NixA1ZWVjrFrIvGjRvjp59+
wqFDh9CjRw+sWrVK66rvUq6urli4cCGW\nLVsGLy8vztC/jY0NRo0aBTMzM+XCFG3s7Oxw6NAhjBo1Ct27d
8f333+PdevWoVevXgBKeiG9vb0R\nFBSEVq1a4cKFCwgJCcF7772HhQsXonfv3jh9+jQ+
+eQTznNDQ0MxcOBAjBw5Eq1atcLu3bvBMAx2\n7tyJgIAAvP/++
+jWrRveeOMNJCcnK4ewzczMsGzZMvTp0weDBw/Gy5cvsX37dp0/y/KYnJycWve/\nWFJSUqVduUQzTZ+dQq
HA4m/
+xN20J5zyV0MDMXJQL2OGp5FMJse8ZRuQ/rzsP3sPNyeEDvCHf+c2\nRp2/V51/e3K5HG8t/Bb5BWX7Y634
6A20dNc856S+Kv/ZZWbnYeHqTch9oXkfNJFQgGX/m4rmTZto\nfP1SXAK+2bhH42ulXJrY44u5k2FnU/u+M
FQH/d4rkZubCzs7O1OHQWooOjoaI0aMwN27dzkrguuC\ncePGwdXVFevWrTN1KAZV0c8a9Rw2AEciL6slhs
ODeyB0oGmP5yklEPAxb/pY+Hdug4Du7bFo9itY\n+fGb6N21XZ1Y2MHn89XmwF2/k2KaYGoBaXExvvl1j1p
iWP7IQWmxDGt/24N8DavQn2flYsOWQ5wy\np8ZiDArgnmn95Fk2Vm/YiSJJ1SadE0KIJjk5OTh8+DBOnTqF
GTNmmDock6LksJ7LyMzBjn8jOGXd\nOnrjtVH9a8WcvVIebk6YO20MZk8ORcc2LWpVbLpQnbN5/fY9E0ViW
izL4tftR9W+jIwL6aO2/+ST\nZ9nYsPUQZwheLpdj/Z/7OVsX8fk8vP/GKLw5YTB6+/lwnpGc+gRrf9sLmU
x/E+gJIQ1TQEAA3nnn\nHSxZsgQ+Pj6VV6jHaLVyPcayLH7dcZQzod/K0gzTwgbXueSrtuvYlrvaLiHlIYo
kUpibibTUqJ+O\nRl5Wm0/YtaMXxg0NAMMwSLj3EKfOxSlfu3gtAQdPXcSI4JK9IfccPYM7d7l7rr0SGqg8
8WbW6yOQ\nl1+A+Dupytev3bqHX7YdxszXhtO/a0JqiYCAAOTk1K15wfHxlc+Fbiio57AeO3vlFq7d4vZgT
RrZ\nH/Z2FW/QSaquiYMYzo72ymuZTIFbSWkV1Kh/ktOe4K+93AUork6N8O7rocqk7Y3xg+Dhxj0tYOv+\n
07idfB83ElOx9yj3xJ5OPi0xvH8P5bVAwMe8aWPVnhF5MR7bVXrICSGEVA8lh/XUi/xC/LXnOKfM\nx8sd/
Xt1MlFE9Z/a0HIDmnf4PCsXf+yL4OyfaWEuwv/eGgdLi7LVkCKhEPOmj4GVZVmZQsHiu9//\nwfd/HkD5Rd
5iWyvMen2EWm+gpYUZFs4KQxMH7kTqf46dx4kz3HPCCSGEVB0lh/XU33tPcBYECIV8\nvDUxxHDDbgoJBHm
REOSdBhSSyu+vh3xVhpav324YyaG0uBhrNu7mrNYGgNmTQ9FUw4k7To3tMXty\nKKcsO/clsnPL9hpjGGD2
lFCtK5HFttb45N1XYGfD3Rfu730nkfsiv7pvhdQStBUUIYZV2c8YJYf1\n0PU7KWrzvsYM7g1XJ8NtJyDK2
gVR7iGIco/APOM3oAH+cvfxag4eryz5fpSeiedZNd9Etrbbtj8C\nKQ/SOWXjhwaga0dvrXW6tPfC6MHat1
EaNagXOrSueGN2lyaN8PGMCTA3KzttpUhSjH3hZyuoRWo7\nKysrzvm4hBD9KygogLm5udbXaUFKPSMtluH
XndzhZHdXR4QOMOC2NWwxBIVlyShPmgp+QSzkVl0q\nqFT/WFqYwbtFU86CiviEFAT1rL9D+S8LCnHibCyn
rGtHL4wNqfyw9wnD+iIp5RHn6ESg5LztcSEB\nOrXfqrkrJgzvh7/KbbZ9/MxVhAR2g1Nj+wpqktpKIBDAx
sYGeXl5pg6FkHpLIBBUeHIKJYf1THj0\nNc5m0gwDvP3KUAgEhtsvkJFlAuB+yxflhqPQsiPANKx/Yh3btO
Qkh3G379Xr5DDyYjznOMZGYhvO\nApSK8Hg8vPfGKHy88jflkLKVpRnemzqySv9eB/XpgiMRMcjILOmllck
U2HkoCnOmjKziuyG1hUAg\noI2wCTEhGlauR1IfPkXEpZucssF9/eDVoqlB2+UVP1MrY+TZELy8YNB2ayPV
RSk3EtKgUChMFI1h\nsSyLY1FXOGWDArpwFqBUxs7GCp9/8Bq6dvSCb9uWWPLeJDg6iKsUh1AowIRhfTllZ
2Ju0vnLhBBS\nTZQc1hNyuRwbth7mrBZ1sLfBxBGBBm+bJ1M//xYAhHknAYX6CRj1WavmLpyVuC/yC5HyoH
4mKXG3\n7+FpRrbyWsDnVauX1NmxEea/PR6fvDsRHm7O1YqlT9d2cG/KPY9124GIaj2LEEIaOkoO64lj0Vd
x\n7z43CZk2YQgszHXvxakuplhzcsgo8iF8EWXw9msTHo+ntpCivm5pcyya22vYsU1ziG1Nc84xj8fD\nq6
FBnLJrt+7hRmKqSeIhhJC6jJLDeoBlWRyNvMwp69mlDfw6eBmlfW09hwBKkkN5w5pY3hD2O8zI\nzMHVG8m
csj5+bUwUTYlOPq3g4+XOKdu6/zSteiWEkCqqNDns0KEDxGKx2p8JEyYYIz6ig+TUx9zh\nPQEPU8YONE7j
LAteMXcbE5YptzyelUKUd9I4sdQSqslhwr2HKCyqX3s/Hj8Ty9mtqLlbE3g0bWK6\ngAAwDKPWe3g37QkuX
rtjoogIIaRuqjQ5PH36NBISEpR/IiMjwTAMRo0aZYz4iA6iLnH3NPRr72W0\nI/IYeR7ASpXXLGOOYrtBnH
sELy+BKX5ulHhqA0cHMVydGimv5XIFbiXdN2FE+iUtLsbp89c4ZYMD\n/GrFucZeLZqiuy93f8UdByMhl8t
NFBEhhNQ9lSaHjRs3hpOTk/LP8ePHYWNjg9GjRxsjPlIJmUyO\n81dvc8oCurU3WvuMjLtSmRU6QmbtD5bf
qFypHMLco0aLqTZQH1q+p+XOuudC7B3kvSxUXltZmqF3\n13YmjIhr4ohAlM9TH6dn4fT5ONMFRAghdUyV5
hyyLIu///4bYWFhsLCwMFRMpAqu3bqLF/nl/qO2\nMEPndp5Ga58n4/YIKgSOACOAVDyEUy4ovA6e9IHR4j
K1jm1UjtIz8LzD4mIZHqdnGmV+ner2NYE9\nOsLcTGTwdnXV1Lkxgnr6csp2HzkDibTYRBERQkjdUqXk8PT
p00hLS8PkyZMNFQ+pojOXb3Cufdt6\nGHTDa1VMsXrPIQDILXyhELpyXhPmHG4wx+r5eLmDzy/78XqcnoWM
zJwKalTfk2dZeHfJ95i7dAM+\nW/s3iiTSyitVU8qDp0hKfcwpG9Cn9p2EM35oX4iEZRuwZ+e+xJGIGBNGR
AghdUeVjq/4888/0aVL\nF3To0KHSe5OSkqodlD7qNwSFRVJEnI+FTFa2yXLX9i2N+tm5yu/AEvnK6yeFEu
Snl7RvwbZHU0W5\nWPKv41HOSRQyzY0WX3Xo6/NzFFvi7v2yxTpHTp5Bz86t9fLs8n7ZcRyPn5asGL8an4B
ft+zH4ADD\nnMqy/dBZ5OeX/X17t3BBfl4WkvKyANSun9subd1x8nzZfNzNe4/Bw9kWVlXYpNvYatPnp8rL
yzi7\nHxBCTE/n5DAjIwOHDx/GmjVrdLq/Jr9IkpKS6BeRDk6fvwYzMwuUHo/YxMEOHk2bGPWzs3gsByMv\
n29uuqbMfWKFTyQXrCbOMe+BLyrY88RTeQJFTMFALFi9oos9/e4G9nuFpZqTyOvOFVO9/N6kPn+L+\n0xxY
WZX9HcTcTMXr44fCzka/ew6+LChEYtozTluvjhqkfE+17ef2raZuuJH8GC8LyjZij7+bjtdH\nB5swKu1q2
+dHCGm4dB5W3rp1K8zMzDB27FhDxkOqIOoSd0g5oHt7464YVUjAyMsPlTJgBQ7lLhkU\ni0M4VXjFj8EvbB
iLA1QXpcQnpOj9KL39x86rlRVJivFP+Dm9tgMAEReuc85RbtzIFl3aG29+a1VZ\nW1pg5KBenLJjUVeQnfv
CRBERQkjdoFNyyLIs/vrrL4wZMwbW1taGjono4HlWrtr2KH26Gm+VMgAw\nKotRWEEjgOF2RitEzSCz5C4O
EOYebxBzD1s0c4aNVdnCrfwCCe6mPdHb859mZOF87G2Nrx07c0Wv\ncxxZlsXx6KucsgG9O4PHq9376A/p5
4dG4rJtnaTFMuw/rp5QE0IIKaPTb/bo6GjcvXsXU6ZMMXQ8\nREdnLt/kXHt6uMDVyUHL3YahejKKQqB5E+
Ri28EAyhbJ8GQZalvg1Ec8Hg/tW3PnV+pz1fKBExe0\n5tgymQI7Dunv6EK1c5QFPPTvZZh5jfokEgoxejC
39/DE2Vhk5VDvISGEaKNTcti3b1/k5OTAz8/P\n0PEQHbAsi2iVja8DulW+SEjfeCorlRX/rVRWxQobQ27O
HX7kF94yWFy1iW9b1S1t9LPfYXbuC0Re\nvM4pUx3iPRNzA2mP9JOEq56j7N+5rd7nNBpKkL8vHOzLeg+Li
+XYf1z/w+6EEFJf1O4xIaJR2qN0\nPHyaqbzm83no2aWt0eNQ28ZG4KT1XrmFD+da0ECSww6tufMOE1Meoa
Cw5kfpHTx1ibNKvYmDHeZN\nG4NmLo2VZSwLbP83osZtPc3IUjtHeXDfuvNFUSgUYMzg3pyyE2djkZndsM7
8JoQQXVFyWAdFXeT2\nGvq2bWmSXhy1DbCFjbXcCcjNuckrT3ofkNf/ob3GjezQtNxwv0LB4kZiao2e+SK/
ECfOcOf/jRjg\nD6FQgIkjAjnlV28k487dqm8+nveyAKfPX8PKn3bgw+W/cIavPdyc4OXRtDqhm0ygvy8cH
eyU1zKZ\nAv8co95DQgjRhJLDOkYul+PsFW6vmzGPy1NiWZ3nHAIAKxBDISyfULAQFN4xUHC1S8e23N7Df4
6d\nq9FJJseirqBIUnbah52tFQL9OwIA/Dp4oXVLN879W/ef1qm9rJwXCI+6jKXrtuCdT77Dz1sOI/bm\nX
U4PJVDSa1gbzlGuCoGAr9Z7eOr8NTzPyjVRRIQQUntRcljHxCekIievbBNiC3MRunY0/t5ojDwH\nYMsSFJ
ZnCfAr7r1UHVrmF93Ucmf90suP+77vpj1R6/3VVZFEqnbSx7DAbhAJhQAAhmHw6sggzusJ\n9x6qDQuXl5T
yCEvXbcHMxeuxaecx3EhMg0KhOZls4mBXq85Rroq+3TugiUrv4T7qPSSEEDWUHNYx\nqquUe3Rqo0wMjIkp
TudcsxX0GpaSqSWHyZwEs77ybuGGHp24J6NsOXC6WnMPT527xj1L29IMAwO4\n8//atGqmtjhl24HTanssZ
mbnYf2f+7H4mz9xIzGtwnadHe0xcmBPLP1wCsxExv/3pg8CAR9jhnB7\nD0+fjzPYsYaEEFJXUXJYhxRJpL
h0jTsUG9DdBEPK0LCNjZaVyuWxQlewfHG5AmlJgtgAvD46mHPW\nb25ePvaGn6nSM2QyOQ6eusgpGxTgB0s
Nx8FNHBHIOYTmwZPniP5v03RpcTH2HDmDuUt/xpkY7b23\n7k0dMS6kD1YvnI5vl8zAqyODILat2/ucBnTr
AGdHe+W1XK7A3vCzJoyIEEJqnyqdrUxM61JcAiTS\nshMqHOxt0M7LNOcU84p1n2+oxDCQW7SF4GXZJsT8w
luQWxh/pbWxOTqIMWJAD+w5UpaIHImIQf+e\nnXTen/LM5RvIzC5bxCMSChAS2E3jvc2bNkGfbu2VCSEA7D
wcBb6Aj+3/RiAjU/Ncu1bNXdDDtzW6\nd2oDlyaNdIqrLimde/jj5oPKssiL8Rg1qBecGttXUJMQQhoO6jm
sQ6JjuMfl9e7azmQLAxiVnkNW\nh55DAJCprFrmF91uEKelAEDogJ6c/fZkMgX+2ntCp7oKhULtZI/
+vXwrXKUeNqwvBIKyH/HnWXlY\n/8d+jYmhe1NHfPreq/hq/hsYOahXvUwMS/Xp1g4uTVR6D49S7yEhhJSi
5LCOyM59gXiV0zVMskr5\nPzyVE0506jkEoDD3BBiR8pqR54FX/FCvsdVW5mYivDYqmFMWe/MuYm9WPrQec
z0Rj9OzlNd8Pg/D\n+/eosI6jgxiD+lS8H6GNlQWmhw3Byo/eRHtvj0rjqA/4fD7GDOnDKYu6FI+nGVlaah
BCSMNCyWEd\ncSTiMqeDrblbE7i76paQ6Z2iEAxnj0I+WIGOQ3KMAHJz7uKMhnJaCgD07NIWPl7unLK/9p6
ATCbX\nWodlWbU9+Xp3bQdHB7GWGmVGDe4FczP1BSR8Pg/Dgrrh289mYGBAF/D5fA2166/efj5wdSrrHVUo
\nWOo9JISQ/1ByWAfsP3ZObUjRpL2GavMNHQBG9+RCpjLHkF94Wy9x1QUMw2DK2AGcxSKP07NwJDJG\n4/2
5L/KxYeth3Lv/lFM+cmBPndqzs7FS6yXr3K4Vvl44HZPHDoS1pUXV3kA9wefzMTYkgFMWdSke\nj9MztdQg
hJCGgxak1HL/HDuHbQciOGVWlmbo2934ZymXUp9vWLUeTLl5GwAMgJKuUF7xYzCybN17\nH+s4DzdnBPfuj
BNnYpVle46cQUC39srVwDKZHMeir2D3kWjkF3C3vOnW0RtuztpPo1EVOsAf1pbm\nSHv0DF07eqNjmxaVV2
oAenVpi31HzyiPomRZYG/4WcyeHGriyAghxLSo57AW2xd+Vi0xNBMJ8OH0\ncSY5Lq8Ur1h1vqFui1GU+NZ
QmHFXWTekoWUACBveD1aWZVvQFBZJsXX/aQDA9Tsp+Hjlr/hzzwm1\nxFAkFGDcUG6PV2UYhkFw7854c8Jg
SgzL4fF4ar2HZy/fRPrzbBNFRAghtQMlh7XUvvCz2P5vJKfM\nTCTAgplhaOdtmu1rSqnvcVj1uY8yc+4pG
wZPDlkWTHEGoCis/N6qUhRBkHcKZs82Qph7DGAVlVax\ntbbE+KF9OWWRF+Ox/IdtWP79NmVvVnmuTo2wcF
YYPNyc9BZ6Q9ezS1u4OXPPvv73xAUTRkQIIaZH\nyWEttPfoGbXE0NxMiAUzw+Bjon0Ny2NUeg7ZqvYcQsN
RepJ7hkncWBb8gjiYP/0GFk+/huXj5eAV\nJenn2YoiCPNOwuLJCohyj4IvSYIw7wSEecd1qj6wTxdOYgIA
12+nqN1nYS7Ca6P74+uFb9WKv//6\nhGEYjBzUi1N2+kIcsnNfaKlBCCH1HyWHtcyeI2ew42AUp8woiSHLg
l8QD8HLmIqTNFYOnozbq6XL\n6ShqjxE6qgxHy8EvSqzyc7Q3UJYUmmVuKdt6h5XCLHMbIK/Bf/7lkkJhbj
gYlc9LmBcBpviplspl\nBAI+powbVOE9/Xp0wLdLZmBEsD8Egoa1othYenXxgaPKmcsHT10yYUSEEGJalBz
WIrsPR2PnIfXE\ncOGsiWjr6a6llh6wMphl/gmzzL8hyt4F84xNAKt5axVGlg2g7DWWbwPwqrfiVfVkFL2s
Wi5NCtP/\nj5sUlsMoXsIsa3fVN9+uJCksI//v+ZUPL3ds0wLdfb3Vyj09XLDswymY9fqIOn9kXW0nEPARO
sCf\nU3bizFXOGdaEENKQUHJYS0ReuI5dh6M5ZeZmQnzy7ito06qZ4RpmZTB7vpkz548nTQO/MF7j7dXd\n
/FoTubnK0HLRba1JaaVUk8Li9Apv5xfdhiD/YoX3lCd4eb7ipLDcxt4AwJPe5xwTWJGp4wahyX89\nV3a2V
pj12nAs+3AqvFo01Tk+UjOB/h1hZ1u2yKtIUozwyMsmjIgQQkyHtrKpBV4WFGLzPyc5ZRbm\nIiycNRGtW7
oZruHSxLBIfTGIMC8CcgtfQOV4PkZlj8PqzDcspTBrDpZnCUZRUPJsRSF4kjQozFtW\n7UEsC1HWVggK4rT
cwEBm2Rk82XPwpPeVpaKcg5Cbtar06D9h7jEI8zQfc8fyLCCzDkCxTW+YZe0E\nv/Bm2fNzj0Bu0Q6soOLN
qh3sbbH20xl4/CwTrk0caPjYBERCIYb374Et/5xSlh2JiMGw/t1hYW5W\nQU1CCKl/qOewFth1KAp5L8t6o
0RCAT5513SJIVCy9yCvKEG9XLXnsBorlZUY/n97HpbRFk9FBPkX\ntCSGDGSWXVDo/D9IHSZC0mgit4ePlc
IsazvAyrQ+W1tiyPIsUGw7CIUuC1BsNwDgWUAqHgWWKZdI\nsFKIcv7RafhaIODD3bUJJYYmNLBPZ872Qi8
LinDibGwFNQghpH6i5NDE0h49Q3jUFU7Z6MG94N3C\ndIlhKeGLSLUy9dNRdN+MWRPVVcuCwptVmgvIyHIh
zDmiWgqZZWcUOn8IqcNEZc8gK2wMqXgk506e\n9AGEeaegicbEkBGpJYWlWIEdisVDObfzC29pHaIntYuFu
RmG9OvKKTt48iKkxcUmiogQQkyDkkMT\nYlkWf+w+xsmFnBqLMTy4hwEblcEsUz0xVAgcIWk8lVPGl9wFT3
KfU8ao9ByywprtuSc39wZQ1lvG\nyDLV2qiIKOcAGLaoXIAiFDp9AKnDKxpPbpFZdYXcgrvHojDvlNr71JQ
Ysow5ihzfVksKuc/3h0Lk\noRLjfuC/oXNSu4UEduecRZ2Tl4/IC5TcE0IaFkoOTej81du4lcRNSiaPGQCR
UKilRg2VJoaFGhLD\nJu9AbuEDuVkrzmvCFxFlF/J85fxAAAAjBMuveD5dpXjmkJtz29R11TK/8IZar5zUb
ghYkYv2SgwD\nif1YsDybcoUKmGVtAxQlp5FoSwwljtOhMKtk1TjDQNJoLDgJr/wFRGq9m6Q2srGywIA+XT
hl+0+c\nh1xezYVShBBSB+mUHD59+hQzZsxAq1at4OTkhB49euDMmTOGjq1eK5JI1RahdPJpCb8OXoZpsJL
E\nkOXbAgCKbftzXucX3lRueq2+UtlRbcFKdaiuWha+PA9GlltxJUUhRNn/cItEzSCz7qWlQjl8a0gb\nje
cUMbJMiHIOopHivIbE0Ey3xLD0fqETim2DOGWC/IvgFd3TqT4xreH9u0MgKPvVmJGZi7NXGtbx\njoSQhq3
S5DAnJweDBw8Gy7LYuXMnLl68iNWrV8PRsfqrVAnwz7FzyMwu24hZIOBhytiBYPSQbGki\nzDtVaWIIAAoz
TyiEruXuYpVzD/U937CU6n6HjDwbZhkbwMjztNYR5R5VeZ0Pif04gNGtM1xu0QYy\n656cMkH+RTRiudvbl
CSGb+mcGJYqtg1SO3NalL0HYGn+Wm1nb2eDQH9fTtn+Y+fAVnVfTEIIqaMq\n/Z903bp1cHZ2xoYNG+Dn5w
cPDw/069cPrVu3NkZ89dLTjCz8e5J7fuvQoO5wdXLQUqOGWBaC/BhO\nkabEEADAMBp6va6CkeVqmG9Yg5X
K5Z8jsIfMqhunjCd7DrNnP2tMEHmSVAhecj+/Ypu+FQ8nayC1\nG6aWwHHiqmZiCABghJA2Gssp4skyIMw7
XfVnEaMLHeDP6RR/
+DQTMdf1eIIPIYTUYpUmh4cOHYKf\nnx/eeOMNeHp6ok+fPvjll1/oW3QN/LnnBGSystMz7O2sMWZwb4O1x
8gywcjLDdMyQs2J4X/kFh3A\nCsonqnIIXkar9xzqKTkEAKn9aLWVyxoTRFYGUdZuAGX//liBQ8kikariiS
B1mIjy8wOVz6ziULIm\nCrOWkFlxFxcJ806rnU1Nah+nxvbo3ZW7cOkf6j0khDQQlSaHqamp+O233+Dh4YE
9e/ZgxowZ+OKL\nL7Bx40ZjxFfvxN5MxtUbyZyyV0cGGXSjXb4khXMtF7lrTQwBAAwPxTZ9OUXClxfAK37E
Kauo163K\nGAEkDq9pSRDLhpiFeRFqcx8l9mMBpnqLeBSiZii2DeaUlSWGNT/LWioeWnLEoJIcgnzjn9vLL
7gB\nYe4xtU3MiXYjB3KnHdxNe4Lrd1K03E0IIfUHk5OTU+FXYUdHR3Tu3BnHjh1Tln355Zc4ePAgLl3S\n
/p9cUlKS/qKsJ2QyOVZt/AfPy801bOHWBHNeDzHYXEMAaKI4Blu2bL5hJtMT2byKt8thWBk8FJvA\nh/YtW
O7y3gVbzaRMK1YOF/YQrFju4g0p7JHB6w9XxT9gyp3tnMf44BlvUA3bVMCJPQ4b9jaKYYd0\n3hAUMVUboq
6IjeIWnNiynx8JHPGAP0lvz6+8/ZtwYo8DAOQwRxpvChRM9c7Dbmg27T6F+MSyHQUc\nG9lg7tQRsDAXVVC
rfvLyMtBiOUJIrVPp8XlOTk5q8wu9vb3x8OHDCuvV5BdJUlJSvfxFtP/YORRK\nFbCyKjnDlWGAD98Jg4eb
s97a0PTZWTzeDUZedm4s37EXGutwRJ0gLwSi3KMaX2P5Yni6+mh8rcZY\nT0Y0tEUAACAASURBVLWV1VaQw
h5HAZiX3cazBuP8Buz4lnpotDWgkCAtOQVe3m0qv70q5E1h+fgc\nSofCrVAAc1dXgG9VcT19YBWweML9+2
9tXwSZdUe9N1Uff26nvWKFRWv+UF4XSBQ4fuE25k0fq/cv\ndPXx8yOE1E2VDiv7+/sjOZk7DJqcnIxmzZo
ZLKj6KCvnBfaGn+WUDejdWa+JoSaMLBuMPLtcCR8K\nM93+7mTWPbnHwZWj1yFlVaVDzOYVJ59S+1BAL4nh
f3hmAGOA4+v4llAIuT2RfMld/bejqemiBJW/\nf4AnTTVK2/WBp4crgnt34pRdikvEgRMXtNQghJC6r9Lkc
NasWYiJicGaNWtw7949/PPPP/jll18w\nffp0Y8RXb+w8FIUiSdk2JtaW5ggbEWjwdnmq8w3N3HWfn8ezgM
zaX+NL+lyMohEjgKSx9gRRbt4a\ncgtfja/VRnJzT841vyhZy536pbqqGwB4kjSjtF1fTB03EC3duV/ith0
4jRuJqaYJiBBCDKzS5LBL\nly7YsmUL9u3bh549e2Lp0qX45JNPKDmsgkdPnyPiQhynLGxEP9hYGX7el2oP
lcKs8uHk8mQ2AdC4\nmtfQySGgPUFkRJDaj9HLBtzGIjfjJoc8I/QcMrJs8IvuqJXzZBmAnI7z05VIKMS8a
WM4P68sC6z7\n/R9k5byooCYhhNRNOu0YPHjwYJw9exbp6em4cuUKZsyYYdAFFPXNzkNRnPOTXZ0aIbhXJ+
0V9Ei9\n57BqySHLt4XMqotauUGHlcv7L0GUWZZ+XnxIGo0HK7A3Tvt6ojBrgfJJNk+WAUaWY9A2S3oNNa8
3\n40up97AqHB3EmD0llPN9JPdFAdb+thcyGR2tRwipX+hsZQO7d/8JLsRye28mDOsHPt8Ac9tUMPI8\n8G
TPy5XwoRBVfd+
+YptAANwvA0bpOSzFCCB1eBWFzh+hwHUR5JZ1ZzhZiWcGhYg715MnMeBxeqxM\nbeNzTtuUHFZZJ59WGDuk
D6csMeWR2jGYhBBS11FyaGDb/43kXLdo5gT/znpeDauFavKhELmVLLqo\nIlboyDlqTm7euuJ9Eg2EFTYG+
NZGb1df5OatONd8ieHmHfILb4BRvNT6Os07rJ5xQwPQyYfb+34k\n4jLOXr5poogIIUT/KDk0oFtJaYi7zU
3QJo4INNqQPL+I23ZVh5TLk4pDIXF4FVL7cZA0nlzT0Bok\n1XmH/KJkwEAnbghenue2bc49v5ovfQCwNBx
aVQzDYPaUkXB0sOOUb9h6CPcf08k3hJD6gZJDA2FZ\nVq3X0MfLHb5tq5+gVZVqz6HcrEX1H8bwILfsBJl1
92qfRtLQKVRWijPyHDCyTL23w0ifqJ2Ko3ZS\nCysFr/ip3ttuCGysLDBv2hgIhWVTQyRSGdb+thcFhRITR
kYIIfpByaGBxN5MRsI97kbhxuw1hPyl\nyjFzDBRmHsZpm2jGCCEXcY/kM8TQsjCfu32N3KwVWKETFCpt8y
Spem+7oWjp7oI3xw/mlD1Oz8LO\nQ5FaahBCSN1ByaEBsCyLbf9GcMq6tPdE65ZuRotBteeoZL6huZa7ibG
o7nfI0/d+hwoJ+PlXOUWl\ne1WqJqa0KKVm+vfqhKCe3MVRp8/HIb+gyEQREUKIflByaADnrtzC/UcZnLKw
4f2MGoNeh5SJ3ihU\n5x1K7ul13qGg4CoYtmxok+XbQG7R7r+2VXstKTmsqTcnDIK9XdkiqSJJMaIuxZswI
kIIqTlKDvVM\nJpNj56EoTllvPx94uDkZNQ6+6kplSg5rBYWoKedIQkbxEoy+5v6xrNqJKDKr7gAjULZdfq
9FRp4N\nRp6nn7YbKJFQiAG9O3PKjkVfAWughUaEEGIMlBzqWcSFODzNKDvLlsdjMGF4X+MGIS9QWWzAUM9
h\nbcHw1U6p0de8Q540DbziJ+Ubg8yqR7lL4X8JYrk61HtYY8G9O4HPL/tV+jg9C/EJqaYLiBBCaoiS\nQz
2SFhdj95EznLL+vTrB2bGRUePgS1NQ/mQMhdAF4FkaNQainfo5y/o5Sk+111Bu0RasQMwtU1mU\npPO8Q5Y
FFLQSVxN7Oxv4d+LuXRoeddlE0RBCSM1RcqhH4VFXkJ1btvGwSChQO1HBGNSPzKNew9pE\n/ZzlezXfc1D+
EoIC7vndxVY91W5TXbGsy7xDpvgpLJ58BctHn0OUtRdgZTWLtR4a3K8r5/pKfBIy\nMg17PCIhhBgKJYd6k
l9QhP3HuBsPD+rrh0ZiGy01DEd9vqHx9lYklWOFzmB5Vsprhi0CT/qoRs8U\n5F8GUJZgsgIHKMy91e5TXZ
TCkz4E2OIKgmVhlrUTjDwXgByC/Aswz/gFkOfXKF6jYmXgF94u+dJk\noLmA3i2acuYVsyxw7MzVCmoQQkj
tJTB1APXFibOxeJFfqLy2MBdh5ED1nhtD47EStUSDeg5rGYaB\n3KwVBIXXlUU8SXLJJtmasDIIc4+BX5QI
MEKwPEvlH/AswPKtIFQ5EaXYyh/QsKcmy7cFy7cHIy+d\nFysHT/pI6x6YPOn9kgSyfJkkFRbPvkdR4zfBC
h11ftsmwSpg9vxP8IsSAABSuxDIbIP03gzDMBjS\nzw8/bzmsLDt9Lg7jhwZAJKRN4wkhdQv1HOoBy7KIuM
Ad0hvevwdsrY0/z88cj8GZbyhoUqfPI66v\nFFWYdyjK3g/hiwjwih+DJ00Dv+g2BAVXIHwZDWHeMYiy95V
L9gAwAsisump9nly197CCoWXBy7Ma\nyxlZJsyf/QCeyhGNtY3g5TllYggAwhcRBhsW7921HWysLJTXL/IL
ce7KLYO0RQghhkTJoR7cufsA\nj9OzlNcCAQ+D+vqZJBYLlttrqDBvZZI4SMXUzlmW/n979x0eVZX3Afx77
507JY2EhBQgIZAChF6k\nClIERSygrqJsEUVcX3Uti21XeXWbbeVlUde1go1VFxVRVxQFETAIiIiCQEQCUk
xCSE+m3XvfPwYm\nc6ckIZmZzCTfz/PkeZxzz505c5wMv5zyO8V+p3eluu0w1H15Rs/ttAwGpNiA133WHdo
PB2hkNQz1\ngXP2CWo9zGXP+STdDjrNAUPNJhhqNjU9Be5FcFbCWLVGX6Y2hOxkGKMsY9LYwbqyDz/bzrQ2
RBR1\nGBwGwfpC/ajhWYPz22XUEAAsmn4KUOF6w4ikGZKhSR47iTUHRJs+SBPsR2GqeOcMn1mCI35CkzV8\
n1x0W+12LJ9duhec6RtWQ4mdEUoHp5OuQqz4OzXo+1QZz6dMwVq6GsXI1zKXPtCxA1DQYK94BNLvP\nJanh
+
+C385TpE0boZvOLj5SgqLht60mJiMKNaw7bqL7Bhi1f6/+xmTRmSIDaIabaYEIpgMapLSa/\njlCCAMWce2
ojiYtkO9A40qvWw1z+qj4QEmTYul4JCCIEpQFQ6yF4/GiCBGfMcGheuQy9qXI6IBjd\ngZOg1EBQKqAZPFI
uaU4YvM5odsaNgzNuPDRDMuSqj3TX5OpPkKZlAmo2IBrPvD/80RSYyl/VrXkU\n7YdhPPkf2Lte5XdN5WlS
wy5IVv9BoKFhNxyJFzZ5f2ulJidi+MBcfPVtY+7KjzZsR37v8B2dSUTU\nVhEZHFbV1GPz9t0YP3JAezelW
YU79sBmb1zDlJwUj8H92icgE+2HoUF1P1YNKdCkhHZpCzVPMeXo\ng0PrD3B0me7aIVz+BgRnua6+LelSKD
GDvZ/mzAkGKMZMSLbGdY6irRiKR3AoNezWn54iGF2jhoIA\nR8JUqIZkmE6+qVu/F6/tRcyxB6GY+kAx94V
i7gdNTmldGzUNxopVuvWCpxnqd0KVMwJvLFHrYaxY\nHfCpBeUkBGcJNDm9dW1rxnkTR+qCwy079+JX1bVI
TODaXyKKDhEVHB4rKcfqT7ZgzfotiImNRd8+\nPZHStUt7N6tJ3lPKk8YMhii2z2y9ZDsAz2x5TGET2VSTf
j2oaP8JUG2Qazf5jHo5Y8dAiQ3eOlbV\nmKULDiX7YSixw92P5Rr9RhRn7AhANLsfKzFDYZUSYTqxHIJa31
hRc0Cy7jsV1K2GZkiG09wPirmv\na1RUaNnOXUPNZ02utTRWrYEmp0GxFPheq/wvBLXGo0SCKqfqTo+RGvb
AGaLgcHC/3uie1tW9Dtnp\nVPHp5p24bEb4c54SEbVGxKw51DQNjz+3EusLv4FTUaEoKj5Yt7W9m9Wkn46X
oaj4mK6s3aaU4Zvf\nkOsNI5tmSIRq8BxZUyBXr3Wt3/OgGjNhT7o4qK/tnbrGc5OGYD/qWofowRE3zu9zW
FNvhmoInM5G\ncJZDrt0M84kXEXP0QciVHwKqtcm2SXVfw1j1oa5MkxKhiRbPEpjKV/icSy1af4ShTv+94U
iYDGfc\nGF2ZoSF0u4gFQcD0CfpAfu2mHXA625jonIgoTCImOBQEARdOHa0r+/QLfe7ASOM9ajgwvxdSkxM
D\n1A4xzQHR9pOuiCOHkU/12rUs13wOz1REmhgDW/IvASG4g/yKUZ9TUXQcdx+PJ9d+oa9ryoUmp8Ef\nTU
6BNe0mOOInwolmEr5rdsg162E5/hgMtdsATfWpIlp/dE1Xe94mWmDtdp2rHzy/sjQ7zCdeApRT\nI5eaA8a
Kt3T3qoZUOBKmQDH317+O/SdAqUGoTBw1CGZT4yhpRVUttu3aH7LXIyIKpogJDgHg7JED\nkdSlcV2Oze7E
x59/1Y4tCszpVLBxqz7Nx+RxQ9upNTi109XjhAypq8+5uhR5lCZTDQmwJc+FZkgK\n/gtLsV4jftqpgKkeh
vqduqrO+PFNP5cYA0fihSgWr0VD+h2wd5kJxZQDQPJbXVBrYKz4D8wlS3V5\nEgVHCUzlLwG6xRESbMm/hi
anQTXnwZ54of65nOUwlb/iShRe/SlEZ5nuur3rZYBgcI3SGj03hWgw\nNOxt+n21QWyMGRNHDdKVfbwxMr/
LiIi8RVRwKMsGzJh0lq5szYZtsNlbntssXL76rgjVtY2jmrEx\nJowa4ntcWbj4TCmbOWoYDRRT4ODQ0WU6
VHNeyF7bO6WNZD/kmpL12CGtSUk+o24BCQI0OR3OhHNg\nS70B9T0egC3lN3DGjoYm+o4qio5jMJf9C6YTr
0C0HYK57EUIqn6mwNb1Cl2uTmfceDhj9TMMku0A\nTOUrIFdv0JU7Y0frdusrZv36RMm6u2Xvq5W8c53uKT
qMQ0dLQ/qaRETB0Gxw+NBDDyExMVH3k58f\nuiDo3PHDdNMx1bUNPqePRALvKeXxIwa03zFZql236xXgkXl
RQ4qDKmf4FCvm/nDETwnpS3snwxZt\nxb7H8MWNBYRW/g0pmqBYBsDe9TI0ZNwFR8K5fjekSA3fwlz6lP6U
FwD2LudDiR2mrywIsCdd4vP5\nlhq+g37kPAH2xAt0dZwWfZArWYvOKKn2mcrM6IaB+fo+fnXVp0yKTUQRr
0Xf+nl5edi3b5/754sv\nvmj+plaKjTFj/PB+urL3Pv0SihI5i7lPVtZg5x79cWdT2nFKWa5Z5/UPqwjV1H
6jmHRmvE9L0QzJ\nsCVfGZI8fPrX9Ro5tO7zOoZPhjN2VHBeTDTB0WU6GtIXwhnT/O+KM3Y0nPEBUtUIBti
SfwVNCjzd\nbk+8BNBtYAE0ubtP4nHJ+gNCyXv0cNf3B/H+ujM78YaIKNxaFBwaDAakpaW5f1JSWpm7rIUm
jOwP\ng6GxaWXlVdjydejWB52pDV/u0h0Gkd0zDb0zQ5MWozmCo8xnOs0RNx6aIbJTAFEjZ/x4V1JquDag\
nWJN/CYihP2FHM6R57QD2alfMUEAKbjs0QxLsyVfDmvo/UI2Zfuso5r6wJ81qOjiW4mBNucbdb7r7\nLQVQ
LAN97xEEKN6jhyHctQwAo4b0RUGefvPPv1d/hgOHjgW4g4io/bUoOCwuLka/fv0wePBgXHvt\ntSguLg5po
7rEx+Cc0fpkv+9+UhgR0zGapvnNbdhOjYGxYhU8p9OciIWjy7T2aQ+1imboivqMu2FL\n+TUa0u9o9oSToB
EEqF67lj35S18TLKfT4Ni6XqlL1K4aM0/tzva/mcWTZsyArescfZlggj0xcGDp\n9Fl3+H1ojv07RRAE3Pz
rixEX45EjUlGxdPm7qG+whex1iYjaotngcOTIkfjnP/
+JlStXYunSpSgp\nKcH06dNx8uTJkDbswimjdd/vh46UYtfegyF9zZbYU3QYJScq3Y9lWcLZZ/kZpQgDqWE
XJFuRruyE\nOFGXrJiihBTvGu0K84k23usOG8uzQx+kCgKU2BFoSL8TtuS5sHW9AtbUGwHR1OKnUGIGwp70
C0Aw\nutP+NLVL35WIu3G0UVCqITqOBKwfDMlJCbhh7kxd2c9lFXjxPx8FuIOIqH0JlZWVZ/Rnc21tLYYO\
nHYrbbrsNN998c8B6RUVFAa+11LK312PX3kPux3m90vE/c89v8/O2xWurP8f27xp3Bg8v6I1fzTon\n7O0Q
NRuy1JdhQJ27rB6ZOCZeGvK1atRxWLTD6KG+7VP+szgDtULfdmhRK2laiz/36eoHiNMav59O\nCqNwUmxil
FRTEIOf4EA8HEJyq5u4ck0hNu/QHwc496IJGDmoqXRGbVdT14D42MDLB1oqLy90O+eJ\nKLKccWbduLg49O
vXDz/+
+GOT9dryRVJUVIS8vDxce2Us/vj35e7yYydqIBpjkdOre6ufuy3q6q04\ncKQcsbGx7rLLL5qKvLzw7wyWK
96DXAsAp9siQUy/Diiu5Jd4G5z+7HUaaiZijn4MXeJtKQEZGeef\nceLtaOk7qW4CTCcb1/xZ5JNITg/Qbr
UB5rLnINqPwJV38mooMa07Ben32dk4+dhyHD7WmItxzeZv\nMensUchI7RrU/iuvqMYXO/agcMf3KD5Sgn/
99XdIiAv9OlYi6hjOOEeF1WpFUVER0tL8n5gQTLnZ\n3THAazH36k+2hPx1A/niqz2wO5zux92Su2BQ3+yw
t0OwH4Ncqz/71pFwDjQ58DFmRH6JZqheZww7\nY0cH/USWSKKY+wFoHGUUHcchOCt8K2pOmE68fCowBAANc
vW6Vr+uUZbxu3mzYJQb+9Zqc2Dp8lVB\nOVqvsroWH362DYsWv4z/uf9JvPrOOhw4dByKomLrzsjZ0EdEka
/Z4PC++
+7Dpk2bUFxcjO3bt+M3\nv/kN6uvrcdVVV4Wjfbh42ljd4y937sXx0tCudwxkvVe+xUmjB0MI9xSupsFUsQ
pA49FjmpQU8px4\n1HE5YxsTz2tiHBxe5xB3OFIsFK+zpX12LWsajCdXQrLpU1aJjuNtOnYvM6MbfnPZubq
yHw//jH+/\n99kZP5fVZseeokN4d20h/rz0N
fz2j0uxfOVa7PvRdw1l4Y7vW9tkIuqEmh0eOHbsGObPn4/y8nKk\npKRg5MiRWLt2LbKyAu9yDKYh/fsgq0
c3HD7qmorRNOD9dV/i+jkzwvL6gOsv8tVrC3Hg0HF3mSAA\n54we1MRdoWGo2w7RXqwrsyddAoi+KT2IWsI
ZNxaaaIboKIMzdhggNXNGcgegmAsg2Ro3uEkNe3TH\nBMrVH8NQv8PvvZL1B9/k3Gdg6vhh2LX3IL7c2bj+
8P1Pv0QXixhwWllVVRz5+QQOHDqGouJjKCo+\nip+OlbVoo7UguLIsOJ0KDIbmd4ETETUbHL744ovhaEdAg
iDg4nPH4smXVrvLNny5C7+4YAISE+Ka\nuLPtKqpqsHrtFnyy+WvddDIADOybjW7JYT67WKmHXPWBvshSAM
VSEOAGohYQJCixIxE5aeZDT7EU\nAB6/S5LtR0BtAEQLDLVbIVd/GvBeyVbUpuBQEARcf9UF+OHQMZRXNI5
CPvvGJ1jxQSEkSYQgCBAF\nAaIoQhQFOByKz3dQc/Kyu2PsiAKMHdYfXRM7fsBPRMETFQuLxg3vjzfe34Cy
8ioAgMOh4KF/voFb\nrrkEPdODn5C7oqoG764txKebdwb8Qp5xzll+y9tKUKoBzf8/03L1JxDUeo/KsuskC
CI6I5rcDaqh\nG0Tn6c0hCiTrfmiCGcYK793bEjxzibqO3Wv57mh/4mMtuOU3l+DBf7yqG/3TNMDpVAPf2I
zsnmkY\nN7w/xo4oQGq4/3glog4jKoJDSZIwc/IoLF+51l1WfKQE9zzyAq66eDIumHRWUNb+lVdU471PXSO
F\nDof/AC2pSxzmXHQOhg/M9Xu91ZRa165Ix/Hm657iSJgCzRD4CDEiCkyx9IdY07hzWK7ZDNFxDJ7r\neS
HIsKZcB/OJFwHN7ipSqiA4S6HJbduU1z83C7+4YCLe/ODzVj9H97SuyOnVHbm9umNwv97ontb6\nVDtERKd
FRXAIuM4uXr/lGxw6UuouczgUvPzWJ9jxbRFu/OWFSOl65kfGaZqG3UWH8PHnX2Hbrv1Q\nVf+LeLomxmPW
9LGYPHYIjLLc6vcRiLF67RkFhqqhGxzx4c+vSNRRKJYCyDWNgZn3Wl5AgK3rHKjm\nPlBMvSFZG9cIStYiO
NsYHALA7PPGoaqmDp9t+QZ1dU3XjY+1IDe7O/KyeyCnVwZyenUPSv5CIiJv\nURMcmowy7r9lLl5440MU7t
CnZfhu/yHc+dBzmPeL8zDhrIEtGkVssNqwcdt3+GjDdhz5uTxgveSk\neMyaPg6TxwyBLIeuu0TrmSUNd50
9GzX/
+4gijmrsBU2M0S/V8GBPvAhKjGvTmWLO8w0O489ucxtE\nUcS1V5yHa684D/v370dOTg5UVYMGDarq+jl9b
GiMxRT+7AhE1ClFVXQRH2vBrfNmY8Sg3Vj2n49Q\nV994Nml9gx1Pvfwetu/aj6sungyzSYYguBZzNy7uFn
CiohprN+7A51u/RYPVHvC1kpPiMXv6eEwa\nMzikQSEAQKmF6DzhUSBAk/yPgmqiBc64s6GaIz/ZMFFEEyQ
o5v4w1H/lc8kRN0EX/Ckm/e+bZDsA\naM6g/oEmCAIkSYLEDcVE1M6iKjgEXF+gE84aiILcLDz96vv4dl+x
7vqXO/fpUkScqcyMFJx/zkic\nMzoMQeEpkq1Y91g19oQ17ZawvDZRZ6ZYCnyCQ8UyCI5E/VnImpwOTYqHc
DrHoWaHaP8Jqin8pyMR\nEYVa1AWHpyUnJeCPN1+FDz/bhn+v/uyM0zx4EkUBo4b0xfQJI1CQlxX2qRvvtU
6KMTusr0/UWSnm\nfF3QpxqzYEueAwhe5wMIAhRTni73oWQtYnBIRB1S1AaHgGsU8YLJozC4fx889fJq/Hj
45zO6v0tC\nLM4dPxTnjh/ernnAfEYOvU5vIKIQEU2wplwLuXYzNDEejoTJgOB/w5lizvUJDh1dpjf7ElLd
dsi1\nX0KVM2BPvJAJ64ko4kV1cHhaz/QU/PmO3+CDdV9i01e7UVPbAE1zLeRWVQ2qprr/GwBysjIwdfww\
njB7aL6gnBkh1X0Gy7oNiGQglZnDLblLtEO1HdUWKqVfQ2kRETdOMPWDvekWz9VSvdYei/Sd34uxA\nRFsx
TCf/A0CDaD8ETYqHo8u0tjaZiCikOkRwCAAGg4RLpo/DJdPHtcvriw37YDr5hqst9d/AKiW0\naARQtP8Ez
wS7miEZkBJC1Eoiai3N0AWqIRWi83Q6LRWS7QAUy8CA98jV6wA0pseSGnYzOCSiiCc2\nX4VawtDwjccjDY
a6bS26T/Jeb8g1TEQRSzHn6x5LTaSgEuzHIVn1abdEx3HXaCMRUQRjcBgkoqNE\n91hq2AvduViB7vPZqcw
pZaJI5Z1Cqqn8pHLNZ35KNUi2Q8FtFBFRkDE4DAZN8wkOBbUGouNIM/ep\nEL3+oVC4GYUoYimmPnCdtewi
Ok9AcFb41BOcFTDUf+NTDgCi7WComkdEFBQMDoNAcJa7z131JDV8\n3/R9jhIImtX9WBNjoBlSg94+IgoS0
eSzYUyy/uBTTa7ZAN0ZzZ717QwOiSiyMTgMAtHhP4VOc8Gh\n93pD1ZgN8HgsooimmnJ1j0Xbfn0FpbbJNc
ei7SdAc4SiaUREQcHgMAgCBYei4ygEZ1Xg+7ymlzil\nTBT5fDel/KBbXyzXfqEL/jSpCzQp0fMZINqbWXJ
CRNSOGBwGgRAgOAQAyRp49JDJr4mij2rsAc0j\nt6Gg1kF0HDt10QZD7Re6+o74CT5ZCLjukIgiGYPDIAg0
cgic2rXsh+CsgKBUehQYoBp7BrtpRBRs\nggTVlKMrEq2uqWVD3VYIar27XBMtcMaO9jlmT2JwSEQRjMFhW
2kOiM4TAS9LtiK/64tEu36Xsmrs\nCQgdJic5UYemeKW0kaxFgOaEXLNRV+6MG3dqE4vXyKH9MKD537BCRN
TeGBy2keAoheeuRE1K0q8v\n0hyQrAd87vOeUlaMTH5NFC0Ur6P0JHsxDHXbvWYDZDjixgMANEMqNDGm8ZL
a0ORyFCKi9sTgsI28\n8xuqcjoUS39dmb91hz7Jr7nekChqaIZkaFKSR4ETxsr3dXWcsSMBKc71QBB8fsc5
tUxEkYrBYRuJ\njuO6x6qcDsXsFRw2fK8/LUVt8LlP4ckoRNFDEHymlvW5TkU44s/RXfaeHeCmFCKKVAwO2
8h7M4or\nOMwBBNldJiiVuikk0XYYgOZxTxogxYCIoodPcOjBGTMYmqGrrsxnU4q9uEVHbBIRhRuDwzbyN6
0M\nQfZZk2Sw7nH/t9/k10QUVVy/4/6T1jviJ/mUqcbuXn80VkNQToaodURErXfGweHixYuRmJiIO+
+8\nMxTtiS5qvX4BOiRocjcA8F136HFaivd6Q+
+djEQUBaQYqMYePsWKuS80Y3ff+oIBijFLV8SpZSKK\nRGcUHG7btg3Lly/HgAEDQtWeqOI7pdzNnY5GMff
T17X/BCi1gOaEZD+sv4+bUYiikvcMAeB/1PA0\n33yHxUFuERFR27U4OKyqqsL111+PJ598EomJic3f0An4
nVI+RTN0gSp7jipokKx7IdqPeR2tlaDf\n9UhEUUMx99U9Vo1ZUE19AtfnSSlEFAVaHBzedtttuOSSSzBx4
sRQtieqeI8canKa7rH31LKh4XuI\nXusNFWM2IPhft0REkU019XalrAGgibGwdb28yd9n1ZgFz69d0Vnmml
EgIoogLTqS46WXXsKPlbQ5\nuAAAG3VJREFUP/6IZ599tsVPXFRU1OpGBeP+cOih7IEFde7HxxucqCtpbLd
JsyBTbbyu1u1Ag1CC\nWK2xrKzehKqK4L7XaOi7SMb+a73O2XfDIGl9ocAMFNcAqGmydqYSAxMaZx2OH9iI
OiEXQGT3X15e\n4N3ZRNSxNBscFhUV4U9/+hPWrFkDWZabq+7Wli+SoqKiyP8i0jRYjtkhqLHuoh4Zo6AZP
BPj5sJy\n/DMISuM/FvEoA9B4j5Q2FqlBPFM5KvougrH/Wo991zJyxTDItY3H7PWKc8KRlMf+I6KI0ey08t
at\nW1FeXo4xY8YgOTkZycnJ2Lx5M55//nkkJyfDZrOFo50RR1CqIKgNHgVG/bF5wKlEufqNKZ75DSEY\no
coZIWsjEUUen5NSvJaaEBG1t2ZHDmfOnIlhw4bpym666Sbk5OTgjjvugNFoDFnjIpm/5Nf+1hop\nlv4w1G
3z+xyKsRcgSCFpHxFFJsUrOBTtRwG1c/6RTUSRqdngMDEx0Wd3ckxMDJKSklBQUBCyhkU6\nwSc49D8C6Ep
1IQFQfK6pJh6ZR9TpSPFQDd1cm1EAACpEr/RWOpoTov2YK1WWaAlLE4moc2vRhhTy\n5TtymBagogmKOReS
dZ/PJSa/JuqcVFO2R3AISLaDAHy/DwRHCcxlyyAoJ6GJ8bCm3ghNTgljS4mo\nM2pVcPjBBx8Eux1Rx+
+0cgCKub+f4FA8ldaCiDobxdRbt9xE9BMcCo4SmEufhaC6NrQJag2MVe/D\nlnJNGFtKRJ0Rz1ZuDc3pJwF
24I0l3vkO3fVFU9CbRkSRz/s8dcl+GNAal554B4bueg17INiPh6OJ\nRNSJRVdwqDkh2g4DSnW7NkNwlsNz
DaEmxQNSbMD6miHJZ2TRe1E6EXUemiEZmpTgUeCACaUAAgeG\np8k168PRRCLqxKJjzaGmQar/GsaqNRCUS
kAwwJoyH6o58DFVoeQzpWwIPKV8mhIzBGJV432KpfNu\n5iHq9AQBijEbhoZd7iKLdqzZwBAADPXfwJEwDZ
rcLRwtJaJOKOJHDkXbYZhLn4Lp5OuuwBAANCfk\nms/ar01nsN7wNEf8OXDGDIUmJcKRMAWqmcluiToz73y
Hcdp+v4GhM3aM17IVjaOHRBRSETtyKDgr\nIVd9CEP9136vi45jYW6R52vr1/yoxuaDQwgG2JOvDlGLiCja
eGcrMKNEd+IS4AoM7UmzITV8A1P5\nCne5oe5r1+ih54lMRERBEnkjh6odXdUtsPz8WMDAEAAEpRpQ6sPYs
Ebem1G0FowcEhF50uQMaII5\n4PXTgSEEAYplMFSDZwobpV1nT4ioY4us4FC1wvLz39FV2wJoDj8V9KeJeE
/vhoVqg+A86VEgQDUE\nyHFIRBSIIAZMhO+MHe0ODE/XdSRM1tUx1G1z/ZFMRBRkkRUcimYoJt9NJqqcAWu
3BXDGDNZXb4fg\n0DVq2Hg+smboCoid8whBImob73WHwOnA8FKf4ziVmGH689s1Jww1n4e4hUTUGUVWcAjA
0WUGVMgA\nAE2Mgz3pUljTboVqzvXZ+NF+wWGjpvIbEhE1xWkZAs8ZkUCBIQBAMPiMHsq1WwClLsStJKLOJ
uI2\npGiGLqgQRsEcnwBHwlTdWaLea/tEZ/iDQ98zlbnekIhaR5NTYE1dAEP9TpTUi0hPuth/YHiKM3Yk\n
5OpPICindjRrdsi1m+Docp7f+oKzAqLjKBTLwFA0n4g6qIgbOQSACvEsOBIv9Dlk3jsQExwlgKYh\nnHx2K
gc6U5mIqAVUU2/Yk2ajRixoMjAEAAgyHHETdUWG2i8AtUFfT9NgqPkClp8fh6n83xAcJ4Lc\naiLqyCIyOA
xEkxIBoXF9n6A2QFCqgvb8orUIxopVkOq/DRh0+uY45LQyEYWPM24MNDHG/VhQG2Co\nLWx87CiBufRpGCt
XAZod0BwwVrwV9j+kiSh6RVVwCEHwM3oYnKll0X4U5rIXYaj9AqbyV2CseBvQ\nVH0lpRaCWuvx4gZohuSg
vD4RUYuIJjjjJ+iK5JqNgNoAueoTWH5eAtFerLsu2Q5Asu4OYyOJKJpF\nV3AI36ll7w0irWWo3QzP85INd
V/CWL4C0Jwer+V9bF4qIOjT6xARhZojbpwuR6Kg1sFy/BHI1R/D\n83vMddEIe9JsKOYB4W0kEUWt6A8OnU
EIDjWHayrZi6FhF0wnXgJUm+u1uBmFiCKBaIEzfpyuSFB9\nDwVQzP3RkL4Qzrixza9nJCI6JQqDQ/0GENF
+PEDNlpMa9kDQbP6vWffBXPYCoNb72YzC9YZE1D4c\ncWfr1mB70sQ42JKvhi3lGmiGRL91iIgCibhUNs3x
DshEZ6lrbaDQ+jjXUOd9TJ8Az0TXor0Y5tJn\nAE0/XcOdykTUbqQ4OGJHQ67dqCt2xoyAPfEiQIoJcCMRU
dOibuQQUhw0Ma7xsebwOs7uDCl1kKz7\ndEXWlHlQ5e66MtFx3BWIetA4ckhE7cjR5Vyocg8AgGZIhjXlOt
iTr2RgSERtEnUjh4BrxE6yNe4a\nFh0/Q5FTmrgjMEPDLngu4FYNqVDNfWE19YLpxHJItoN+79NECzQpoVW
vSUQUFKIF1rTfQVCqXd9H\nXFdIREEQfSOH8LdjufXpbAx1O3SPldhhri9Y0QJbynVQzP0Ct4FfxETU3gQB
mqELv4+IKGiiMjjU\nvNb6tTbXoeAsh2g/pCtzxgxrfCAaYUv5NZwxQ/20gTuViYiIqOOJyuDQZ1NKK4ND7
40oqikbmqGr\nvpJggL3rVa5UEB6c5oJWvSYRERFRJIvaNYeeROcJV7Jq4QzejqZBqtcHh86Y4f7rCgLsib
OgGLMg\nWfdBMedDNeefabOJiIiIIl6zI4fPPfccxo0bh8zMTGRmZmLatGn46KOPwtG2wESz65xlNxWCo+z
M\nnsJxBKLT8x4JTsvgwDcIApTYEbAnXw0ldiTX9xAREVGH1Gxw2L17dzz44IPYsGED1q9fj4kTJ2Lu\n3L
n47rvvwtG+gNq6KUXy3ohi6cv0D0RERNTpNRsczpw5E9OmTUOfPn2Qm5uL++
+/H3Fxcdi2bVs4\n2hdQm4JDTYGh/htdUcApZSIiIqJO5IzWHCqKglWrVqGurg6jRo0KVZtapC3BoWgtgqA
25knUBDMU\nS/+gtY2IiIgoWgmVlZVac5V2796N6dOnw2q1IjY2Fs899xzOO+
+8Ju8pKioKWiP9MWqlyFJXuB87\nkIBD0rUtujdNXYN4ba/7cbUwAKXitKC3kYioo8jLy2vvJhBRmLQoOLT
b7Thy5Aiqq6vx7rvv4qWX\nXsL777+PgoLQpHMpKipq/otIcyDmyH3wPAO5vsefAdHU9H2qDTHH/gxodneR
tdsNUM05bWhx5GhR\n31FA7L/WY9+1DfuPiCJFi/IcGo1G9OnTB0OHDsX//u//YtCgQfjnP/8Z6rY1TZChG
vRH5omOkmZv\nkxp26wJDTUqEauoT9OYRERERRaNWJcFWVRV2u735iiHmfUpJS9YdGnxyGw5lWhoiIiKiU5
rdkPLA\nAw9g+vTp6NGjB2pra7Fy5Ups2rQJb775Zjja1yRVToPU8K37cbPH6Ck1kKz7dUW64/KIiIiIOrl
m\ng8OSkhIsWLAApaWlSEhIwIABA7By5UpMnTo1HO1r0pkeo+dKX9O4RlGVM6AZMwLfQERERNTJNBsc\nPv
300+FoR6v4prNpes2h75QyRw2JiIiIPLVqzWGk0AxddecpC2oNoNT6rSs4SiDaf/IsgRIzNMQt\nJCIiIoo
uUR0cQpCgGlJ1RYGmlo1V+vOgFVMfaIZEv3WJiIiIOqvoDg7RspNSROuPkBr0Z0E748aE\ntF1ERERE0agD
Bode6w41DcaqD/T3GDOhWAaHumlEREREUSfqg8Pmch1K9V97rTUE7IkXMbchERER\nkR9RHxyqcpruseD4G
dBOpavRHDBWrdFdVyyDoJqyw9Q6IiIiougS9cGhJiVCExrPUxY0GwSlEgAg\n13zu/m8XCfYuM8LcQiIiIq
LoEfXBIQTBz9RyCaDUQK5eryt3xI+HJuvPYyYiIiKiRtEfHMJ3U4rg\n+BnGqo8BrfH8Z02MgSNhSribRkR
ERBRVmj0hJRp4rzs0NHwL0X5EV+ZIOBcQY8LZLCIiIqKo00GC\nQ69pZa/dyZohmXkNiYiIiFqgQ04re7N3
mak7Zo+IiIiI/OsQwSGkOGhinN9LiqkPFMuAMDeIiIiI\nKDp1jOAQvusOT3MkzmTCayIiIqIW6kDBYYZPm
TNmOFRjZju0hoiIiCg6dZjg0DvXIQQZji7nt09j\niIiIiKJUhwkOFUs/QJDdjx3xk6EZEtuxRURERETRp8
Ns4dWkBFi7XQ9D3Taocnc448a1d5OIiIiI\nok6HCQ4BQDVlw27Kbu9mEBEREUWtDjOtTERERERtx+CQiIi
IiNwYHBIRERGRG4NDIiIiInJjcEhE\nREREbgwOiYiIiMhNqKys1Nq7EUREREQUGThySERERERuDA6JiIiI
yI3BIRERERG5MTgkIiIiIjcG\nh0RERETkFpLgcPPmzZgzZw769+
+PxMREvPbaa7rrpaWluPHGG9GvXz9kZGTgsssuw4EDB3ye56uv\nvsKsWbPQo0cP9OzZE9OnT0d5ebn7emV
lJRYsWICsrCxkZWVhwYIFqKysDMVbCpu29t2hQ4eQmJjo\n92fp0qXuejabDXfeeSf69OmD7t27Y86cOTh6
9GjY3meoBOOzV1JSggULFiA/Px8ZGRkYP3483nzz\nTV0dfvb8993Bgwcxd+5c5OTkIDMzE9dccw1KS0t1d
Tpi3y1evBiTJ09GZmYmcnJycOWVV2LPnj26\nOpqm4aGHHkK/fv2Qnp6OmTNn4vvvv9fVaUnf7N69GxdccA
HS09PRv39/PPLII9A0Jp0gouAJSXBY\nV1eHgoICPPzww7BYLLprmqZh7ty5+PHHH/Haa6/h888/R2ZmJi6
55BLU1dW5623fvh2zZ8/G2Wef\njbVr1+Kzzz7DzTffDIPB4K4zf/587Nq1CytXrsTKlSuxa9cu3HDDDaF4
S2HT1r7r2bMn9u3bp/t5\n/PHHIQgCLr74Yvdz3XvvvXjvvffwwgsv4L///S9qampw5ZVXQlGUsL7fYAvGZ
+
+3v/0t9u/fjxUr\nVqCwsBBz5szBDTfcgM2bN7vr8LPn23d1dXWYPXs2NE3D6tWrsWbNGtjtdsyZMweqqrq
fqyP23aZN\nm3Ddddfho48+wurVq2EwGDBr1ixUVFS46/zjH//AU089hUceeQTr1q1Dt27dMHv2bNTU1Ljr
NNc3\n1dXVmD17NlJTU7Fu3To8/PDDeOKJJ/Dkk0+G9f0SUccW8jyHPXr0wKOPPoq5c+cCAH744QeMHDkS\
nGzduxKBBgwAAqqoiPz8fixYtwq9//WsAwPTp0zFhwgTcf//9fp933759GD16NNasWYMxY8YAAAoL\nCzFj
xgxs27YNeXl5oXxbYdHavvM2a9YsCIKAd955BwBQVVWF3NxcPPXUU7jiiisAAEeOHMGgQYOw\ncuVKTJ06N
QzvLvRa2389evTAI488gl/
+8pfu5xo4cCBuuOEG3HLLLfzsBei7devW4bLLLsPBgweR\nmJgIwPVZy87OxjvvvINJkyZ1ir4DgNraWmRl
ZeG1117DjBkzoGka+vXrh+uvvx4LFy4EADQ0NCAv\nLw9//vOfMW/evBb1zQsvvIAHHngA+/fvdwfwjz32G
F588UXs2bMHgiC023smoo4j7GsObTYbAMBs\nNjc2QhRhMplQWFgIACgrK8PWrVuRlpaG888/H7m5uZgxYw
Y2bNjgvmfr1q2Ii4vD6NGj3WVjxoxB\nbGwsvvzyyzC9m/BqSd95Ky4uxoYNG3DNNde4y3bu3AmHw4EpU6a
4y3r27Im+fft22L4DWt5/Y8aM\nwapVq3Dy5EmoqooPPvgA5eXlOOeccwDws3ead9/ZbDYIggCTyeSuYzab
IYqiu05n6bva2lqoquoO\nkg8dOoSSkhLd75zFYsG4cePc77slfbN161aMHTtWN7I7depUHD9+HIcOHQrHW
yOiTiDswWF+fj56\n9uyJP/3pT6ioqIDdbseSJUtw9OhRlJSUAHAFNADw
0EMPYe7cuXjrrbcwduxYXHrppfj2228BuNY/\nJScn6/5SFgQBKSkpPmucOoqW9J23l19+GSkpKbjgggvcZ
aWlpZAkCcnJybq63bp167B9B7S8/5Yt\nWwZBENCnTx+kpqZiwYIFeP755zF48GAA/OwF6ruzzjoLcXFxWL
RoEerq6lBXV4f77rsPiqK463SW\nvrvnnnswaNAgjBo1CgDc779bt266ep6/cy3pm9LSUr/PcfoaEVEwhD0
4lGUZr776Kg4ePIjevXsj\nIyMDGzduxLRp0yCKruacXp80b948/OpXv8KQIUOwaNEiDB8+HMuWLQt3kyNG
S/rOk9PpxGuvvYar\nrroKsiy3Q4sjS0v77y9/+QvKy8vx7rvvYv369bjllltw4403uv8w6Yxa0ncpKSlYv
nw51q5di549\neyIrKwtVVVUYMmSI389nR/WHP/wBW7ZswSuvvAJJktq7OUREZ8zQfJXgGzp0KDZt2oSqqi
o4HA6k\npKRg6tSpGDZsGAAgLS0NANC3b1/dfX379sWRI0cAAKmpqSgvL4emae6/tDVNw4kTJ5CamhrGdxN
e\nzfWdpw8//BAlJSU+axFTU1OhKArKy8uRkpLiLi8rK8PYsWND/h7aU3P9d/DgQTz77LO6tXWDBg1C\nYW
Ehnn32WTzxxBP87DXx2ZsyZQp27tyJ8vJySJKExMRE5OfnIzs7G0DH/72999578fbbb+O9995z\nv2eg8Tu
trKwMmZmZ7vKysjL3+25J36SmpqKsrEz3mqcfd4T+I6LI0K5/znfp0gUpKSk4cOAAvv76\na/fUZ69evZCR
kYGioiJd/QMHDri/WEeNGoXa2lps3brVfX3r1q2oq6vTrdnpqAL1naeXX34Z48eP\nR25urq586NChkGUZ6
9evd5cdPXrUvSC+MwjUf/X19QDgM+IjSZJ7RJufveY/e8nJyUhMTMSGDRtQ\nVlaGGTNmAOjYfXf33Xfjrb
fewurVq5Gfn6+71qtXL6Slpel+56xWKwoLC93vuyV9M2rUKBQWFsJq\ntbrrrF+/HhkZGejVq1co3x4RdSL
SPffc80Cwn7S2thZ79+5FSUkJXnnlFRQUFCAhIQF2ux1dunTB\nqlWrUFpaCk3TsHnzZsyfPx8TJ07E73//
ewCudTaiKOIf//gHevfuDaPRiBdffBFvvPEGlixZgrS0\nNKSkpGD79u1YuXIlBg0ahKNHj+L222/H8OHDo
zotRlv77rSffvoJd911F+677z4MGDBAd81sNuPn\nn3/G888/jwEDBqCqqgq33347EhIS8OCDD0b1FGBb+y
8pKQlvvfUWNm/ejP79+8Nms+HVV1/FsmXL\ncO+99yIvL4+fvSY+e6++
+iqsVivsdjs+/vhj3Hzzzbj22mvxi1/8AgA6bN8tXLgQr7/+OpYvX46e\nPXu611wCgNFohCAIUBQFS5YsQ
U5ODhRFwR//+EeUlJRgyZIlMJlMLeqbnJwcLFu2DN9+
+y3y8vJQ\nWFiIRYsW4bbbbov64JqIIkdIUtls3LgRF110kU/5VVddhaeffhr/
+te/8MQTT6C0tBRpaWmYM2cO\n7rrrLhiNRl39JUuW4Pnnn8fJkyfRr18/LFq0CJMmTXJfr6ysxF133YUPP
/wQADBjxgw8+uij7h2C\n0ShYffe3v/0Nzz77LPbu3avbYXqazWbDfffdh5UrV8JqtWLixIl4/PHH0bNnz5
C9t3AIRv8dOHAA\nDzzwALZs2YK6ujr07t0bN910E66+
+mp3HX72/PfdAw88gBUrVqCiogJZWVmYN28ebrrpJt0mi47Y\nd4Hafvfdd+Pee+8F4Joifvjhh7F8+XJUV
lZixIgR+Pvf/46CggJ3/Zb0ze7du7Fw4ULs2LEDiYmJ\nmDdvHu6+
+26msSGioAl5nkMiIiIiih7RO39IREREREHH4JCIiIiI3BgcEhEREZEbg0MiIiIicmNw\nSERERERuDA6Ji
IiIyI3BIRERERG5MTikTumiiy5C7969ceLECZ9rtbW1GDhwIMaPHw+n09kOrSMi\nImo/DA6pU1qyZAkaGh
rwhz/8wefa3/72Nxw7dgxLly6FwWBoh9YRERG1HwaH1Cnl5ORg4cKFePPN\nN7F+/Xp3+TfffINnnnkG8+f
Px4gRI8LWnvr6+rC9FhERUVMYHFKndeutt6KgoAC33347GhoaoKoq\n7rjjDqSnp+P++
+931zt93u2AAQOQmpqKYcOG4f/
+7/+gqqru+RYvXozp06ejT58+SEtLw/jx47Fi\nxQqf183Pz8fVV1+NTz75BJMmTUJaWhqeeeaZkL9fIiKi
luDZytSpbd26Feeffz5uvfVW9OjRAwsX\nLsSKFStwwQUXAHCtP5w2bRpKS0sxb9489OjRA1u3bsXrr7+O+
fPn47HHHnM/V05ODmbNmoW+fftC\nURS8//772Lx5M5566inMnTvXXS8/Px/x8fE4ceIErr32WvTq1QvZ2d
mYNGlSuN8+ERGRDwaH1Okt\nXLgQy5cvh8ViweTJk/Hyyy+7r/31r3/F008/jY0bN6J3797u8r/85S9YvHg
xvv76a/Tq1QuAa2o4\nJibGXUfTNMycORMVFRUoLCx0l+fn56O0tBRvv/02pkyZEoZ3SERE1HKcVqZOb9Gi
RUhOToamaXj0\n0Ud111atWoXx48cjISEB5eXl7p9JkyZBVVVs3rzZXfd0YOhwOFBRUYGTJ09iwoQJ2Lt3L
6xWq+55\n+/Tpw8CQiIgiErdiUqeXkJCA3NxclJaWIj093V2uaRoOHDiAoqIi5OTk+L3XMxXOqlWrsHjxYu
ze\nvRuKoujq1dTUwGw2ux9nZ2cH900QEREFCYNDogA0zbXi4txzz8XNN9/st06fPn0AABs2bMA111yD\nC
RMmYMmSJUhPT4csy/jggw/w3HPP+Wxe8QwUiYiIIgmDQ6IARFFEVlYW6urqmt0ssmrVKiQkJODt\nt9+GLM
vu8rVr14a4lURERMHFNYdETbj00ktRWFiIDRs2+FyrqqqCw+EAAEiSBAC66eQTJ07g9ddf\nD09DiYiIgoQ
jh0RNuOOOO/Dxxx/j8ssvx9VXX40hQ4agrq4Oe/bswerVq7Fjxw6kpaXh/PPPx/PP\nP49LL70Ul19+OU6e
PIlly5ahe/fuKC8vb+
+3QURE1GIMDomaEBcXhw8//BCLFy/GqlWr8O9//xvx\n8fHIzc3FPffcg6SkJACudYlLly7F0qVLce+996J
nz5743e9+B1mWcccdd7TzuyAiImo55jkkIiIi\nIjeuOSQiIiIiNwaHREREROTG4JCIiIiI3BgcEhEREZEb
g0MiIiIicmNwSERERERuDA6JiIiIyI3B\nIRERERG5MTgkIiIiIjcGh0RERETk9v//200+R/Qr1gAAAABJR
U5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc4c14ceda0>"
]
},
"metadata": {},
}
],
"source": [
"average_murder_rates.plot('Year')"
]
},
{
"metadata": {
"manual_problem_id": "visualization_2"
},
"source": [
"Murder rates seem to rise and fall together with a similar trend across all
states, both with and without the death penalty, but those states without the death
penalty consistently have a lower murder rate during this time period."
]
},
{
"metadata": {},
"source": [
"Let's bring in another source of information: Canada."
]
},
{
"metadata": {},
"outputs": [
{
"data": {
"image/png":
"iVBORw0KGgoAAAANSUhEUgAAAocAAAEfCAYAAAAzyWxRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAL
EgAACxIB0t1+/AAAIABJREFUeJzs3XdgzPf/wPHnjVz2EpFhRSYhgiCJFam9KYqaRRWlftWi\nWqVVSn211
VKqWlqjrb333iNFUCsxIoktkiDrcrn7/ZG65JNNxoW8H3+592e9cjJe9x6vtywuLk6H\nIAiCIAiCIAByQw
cgCIIgCIIglB4iORQEQRAEQRD0RHIoCIIgCIIg6InkUBAEQRAEQdATyaEgCIIg\nCIKgJ5JDQRAEQRAEQU8
kh4IgCIIgCIKeSA4FQRAEQRAEPZEcGlh4eLihQ3gtife16In3tHiI91UQ\nhNJGJIeCIAiCIAiCnkgOBUEQ
BEEQBD2RHAqCIAiCIAh6IjkUBEEQBEEQ9JSGDkAQBEEQMtNoNCQk\nJBg6DEF4bSmVSszNzXM/XoKxCKVUY
lIK4RG3sbGyoIqzPTKZzNAhCYJQRmk0Gp4+fYqNjY34XSQI\nxSQhIYGUlBSMjY1zPC6SwzLucdxTvvxhOf
cexgLgVMGWwHreBNarQRXnCgaOThCEsiYhIUEkhoJQ\nzMzMzHjy5IlIDoXsdDodC//cqk8MAe4+iGXdjqO
s23GUSo52NPKrSWC9Gjg72BkwUkEQyhKRGApC\n8crvZ0wkh2XYvmOhhF66kevx6HsxrNp6iFVbD1G1UgUa
1/OmdTM/TE1y/qRRGlwKv8Xeo2dJTHjG\nSOdKWJqbGjokQRAEQXiliOSwjHoYE8fSdXsKfP6t6Afcin7Ai
dArTP94EHJ56Vro/jQhieXr93Lg\nxHkgfWgq5ukKvhjTHzPT0pvMCoIgCEJpU7r+wgslQqfTsWD5FpJTUv
VtJsZGzJwwmJH9OlLH2xWF\nIudvjRuR97h0LbKkQs2XTqfj4MkLjP3qZ31i+Nyt6Ad899taNJo0A0UnCIJ
Qcm7duoWNjQ1nz541\ndCgvbcSIEfTq1cvQYZR5Ijksg3Yc/IeL4dIEr1/XFlSr7EhQQG0mjuzNwq/HMKxP
O3y8XMg6NeHk\n2SslGG3u7tyPYdrcP5m/bDNPniXleM6FKxH88tc2dDpdCUcnCEJZMmLECGxsbLCxsaF8+
fK4u7vT\nsWNHFi1aRGpqav43eInnlYUkqkOHDowbN65Yn1GYpNrGxoaNGzcWQ1SGJZLDMubO/Rj+3Lhf0u
ZT\n3YWWTepK2izNTWnRuC6TRr/NR0O7S46dOnfVoMlWaqqGtduPMH7mr/wbdivbcaVS+m198OQFVm87\nV
FLhCYJQRjVv3pyrV69y/vx51q1bR9u2bZkxYwbt2rUTdRuFV4pIDssQrVbLguVbUKdq9G1mpipG\n9O2Y58
olX29XTIyN9K/jniRw9UZ0scaam8vXIpkw8zdWbT1Eaqp0uNjISEHvTkH8OGUkdrYWkmNr\ntx9l37HQkgx
VEIQyxtjYGAcHB5ydnalduzajRo1iy5YtnDt3jh9+
+EF/nlqtZsqUKXh7e+Pk5ERw\ncDB79+7VH09LS2PUqFHUrl0bR0dH6tWrxw8//IBWqwVgxowZ/PXXX+zcu
VPfW3n48GH99ZGRkXTt\n2hUnJyf8/f3Zv1/aIZBVhw4d+PDDD5kwYQJVq1alatWqfP755/rnFSTmw4cPY2
Njw8GDB2nRogVO\nTk40b96c0NCM37uPHz9myJAheHt74+joSEBAAMuXL881rhEjRnD06FEWLVqk/zojIiK
oW7cuc+fO\nlZx7/fp1bGxsJM/LLDo6mj59+uDi4oKTkxMNGjRg7dq1APj6+gIQHByMjY0NHTp0AODMmTN0
69YN\nV1dXKleuTNu2bTl16pT+nj4+PgAMHDgQGxsb/WuA7du3ExQUhIODA7Vr1+arr75CrVbrj2/atIlG\
njRrh6OiIi4sL7du358GDB7m+FyVNLEgpQzbvPUnYzduStkHdW2Nna5XndSojI/xqeXD09CV926nQ\nK1R3
q1wsceYm9NJ1vvl5FVpt9l5Ln+ouDO3VFkf7cgC816s1i9cd4mlCxnDzor+3U87GkjrebiUW\nsyAIRaPXq
K9L9Hkr531aJPfx9vamRYsWbN68mU8/Tb/n++
+/z82bN1m0aBEVK1Zk165d9O7dm337\n9uHj44NWq8XJyYnff/8dOzs7zpw5w5gxY7C1tWXAgAGMHj2asLA
wYmNjWbhwIQC2trbcvXsXgGnT\npjF16lS+/fZb/ve//zF48GAuXLiAhYVFrnGuXr2aPn36sHv3bi5evMiY
MWNwcHBg1KhRBYr5uS+/\n/JIvvvgCR0dHPvnkE4YNG8bJkyeRyWQkJyfj6+vLmDFjsLKy4sCBA3z44YdUr
lyZoKCgbDHNnDmT\n69ev4+HhweTJkwEoX748/fv3Z8WKFYwePVp/7vLly/Hx8aFOnTo5fn0fffQRKSkpbN
68GUtLS65d\nu6Y/tm/fPt544w3Wrl1LrVq1UKlUADx9+pRevXoxc+ZMZDIZixYtomfPnpw9e5Zy5cqxf/9
+3N3d\n+fHHH2nTpg0KhQKAvXv3MmzYMGbMmEHjxo2Jiopi7NixpKSkMG3aNO7fv8+QIUOYPHkynTt3JiEh
\ngX/+
+Sef76SSJXoOy4iouw9ZtfWgpM3Px51m/j65XCHlX7e65PWJ0CslOrSsTk3l15U7siWG1pZm\njBrYmc/e7
6NPDAHsy1kxfnhPVEYZn3+0Wh3f/7aOG5F3SyxuQRCE6tWrExERAcDNmzdZs2YNS5Ys\noXHjxri4uDBs2D
BatWrF77//DoCRkRGfffYZ9erVo2rVqnTr1o3Bgwfre7osLCwwMTHR91Q6ODjo\nExqAkSNH0q5dO9zc3Jg
8eTKxsbFcuHAhzxgdHByYNWsWnp6edOvWjdGjRzN//vwCx/zcZ599RrNm\nzfD09GT8+PGEhYVx584dAJyd
nfnggw+oXbs2Li4uDBo0iE6dOrFmzZocY7K2tsbIyAgzMzP916lQ\nKOjbty/Xrl0jJCQESO9p/fvvv+nfv
3+uX19UVBQBAQH4+Pjg4uJCy5YtadmyJQB2dul1fMuVK4eD\ngwO2trYABAUF0bt3b7y8vPD09GTWrFmYmJ
iwe/duID1RfR6ng4OD/vXs2bMZPXo0/fr1o1q1ajRr\n1owvvviCJUuWoNPpuHv3LqmpqXTp0oWqVavi7e3
NgAEDqFCh9Gw8IXoOywCNJo2flm5Co8kYIrA0\nN2VYn/YFLjZbx9sNY5WSFHX6kHRM7FOu37qLu4tzscSc
1fb9ITyMiZe0vdHIl7e7vJFrLUPPapUY\nPagL3/26lud5bHJKKjN/XsX0jwZib2dT3GELgiCg0+n0v2vPn
TuHTqcjICBAck5KSgrNmjXTv168\neDFLly4lKiqK5ORkUlNTqVy5YKM1NWvW1P/byckJgIcPH+Z5Tf369S
V/Dxo2bMj06dN58uRJgWPO\n+mxHR0f9sytWrEhaWhrff/8969at4+7du6jVatRqNU2aNCnQ1/Wcg4MDbdq
0Yfny5TRo0IA9e/YQ\nGxvLW2+9les1w4cPZ+zYsezdu5egoCA6duyYay/jcw8fPmT69OkcPnyYhw8fkpaW
RlJSEtHReU+r\nOnfuHGfOnJFMJdBqtSQlJXH//n18fHxo3rw5jRo1Ijg4mObNm9OlSxd9clkaiOSwDNi4+
zg3o+5L\n2ob0aouNVe5DDFkZq4yo4+3GydCr+raT566USHIY/zSBDbuPSdraN2/AwB6t8r22oa8XA7u34v
c1\nuzPu9ySBr+f/zdSxA0WRbEEQit2VK1dwcXEB0pMEmUzGvn37MDIykpxnYmICwLp165g4cSJfffUV\nD
Rs2xMrKikWLFrFly5YCPS/zfZ8nfIUZ6SlIzAV59ty5c5k3bx4zZ87E29sbCwsLpk6dmm/impMB\nAwbw7r
vvMmPGDJYvX07Hjh2xscn9A/
+AAQNo0aIFu3fv5sCBA7Ru3ZoPP/yQiRMn5nrNiBEjePDg\nAV9//TVVqlTB2NiYzp07S+YO5kSr1TJhwgS
6du2a7Vj58uVRKBSsX7+ekJAQ9u3bx7Jly/jyyy/Z\nunWrZIjekERy+Jq7GXWPtTuOSNoC61UnsF6NF76X
f53q0uTw7BXe7hxc7Ftdrd1+hMSkjB9GczNj\n3mxX8E+a7Zo34FHsE7bsPalvu3P/MbN/Wc3no/uiVCqKN
F5BEIpeUc0BLGmXLl1i7969fPzxxwDU\nrl0bnU7H/fv3s/W6PXf8+HH8/PwYNmyYvu3mzZuSc1QqFWlpRV
fD9fTp05IezpCQEJycnLCysipQ\nzAVx/Phx2rZtS+/evYH0pPHatWtYW1vnek1uX2fLli2xtLRk8eLF7Ni
xg9WrV+f7/IoVKzJo0CAG\nDRrEnDlz+Pnnn5k4caJ+SD7rc06cOMHMmTNp06YNAA8ePOD+fWlHi5GRUbbr
fH19CQsLw9XVNddY\nZDIZDRs2pGHDhkyYMIGAgADWr19fapLDfOccpqWlMW3aNGrXrq1fdTNt2jQ0Gk1+l
woG9jQhiTmL\n15OWljGcbG1lzuC32r7U/erVcsfIKCORuv8ojlu37+dxReHdvveI3UfOSNrebNvkhXv8+n
V9g8B6\n0nmTV65Hs/Pw6ULHKAiCAOnDrPfv3+fu3btcuHCBefPm6Ycvny+ecHd356233mLkyJFs3LiRiIg
I\nzp49y9y5c9m0aZP+nPPnz7N7926uX7/OrFmzOHZMOnpSpUoVLl++THh4ODExMYWupXjv3j0+
+eQT\nwsPD2bhxIz/+
+CMjR44scMwF4e7uzqFDhzh+/DhhYWGMGzeOyMi8N1WoUqUKp0+f5tatW8TExOhX\nUD+fezh16lScnJxyX
NCS2YQJE9izZw8RERGcP3+ePXv24OXlBYC9vT2mpqbs3buXBw8eEB+fPoXJ\nzc2NVatWceXKFc6cOcPgwY
Mlczufx3fw4EHu379PXFwcAOPHj2fNmjVMnz6dS5cuERYWxsaNG/WL\nakJCQvjf//7HmTNniIqKYtu2bdy
+fVsfT2mQb3I4Z84cfv31V7755htOnTrFzJkzWbRoEd99911J\nxCe8JI0mjR8Wr+few1hJ+7De7bCyMHup
e5qaGFO7ejVJ24liLoi9YuM+ySIUh/I2tGnq98L3kclk\njOzfCW+PKpL29TuOkpCYXOg4BUEQDhw4gJeXF
7Vq1aJLly5s376dTz75hG3btmFubq4/76effqJv\n375MnjyZBg0a0KtXL44ePUqVKum/n9555x26du3K0K
FDCQ4OJjIykvfff1/yrIEDB+Lp6UlwcDBu\nbm6cOHGiULH37NkTrVZLixYt+OCDD+jfv78+OSxIzAUxbtw
46tWrR8+ePWnfvj1mZmb07Nkzz2tG\njx6NSqUiICAANzc3oqKi9Mf69euHWq2mb9++
+Y5gabVaxo8fj7+/P926daNChQosWLAAAKVSyTff\nfMOyZcuoXr06b7/9NgDz5s0jISGB5s2bM3jwYPr16
5ft6502bRqHDx+mZs2aNG3aFIAWLVqwatUq\njhw5QosWLWjRogXff/89lSpVAsDKyoqTJ0/Sq1cv/Pz8mD
RpEuPGjStVRc1lcXFxeU5E6NWrF7a2\ntvz888/6tuHDhxMbG8vKlSuLPcDXXXh4OB4eHkV+399W7mDXYWm
P2xuNfHnv7Q6Fuu/BkxeYv2yz\n/rWzQzm+m/ResQwt/xsWwVc//ilp+3BINwLq5j8kntv7GvckgTFfzpds
Hdi1dSB9OgcXPuDXXHF9\nr5Z14n2Vio+Pz3OYUSh6HTp0wNvbm//973+GDuWF/PPPP7Rp04bQ0NACL9YRM
uT1s5Zvz2FAQABH\njhwhLCwMSJ9Ye/jwYVq1yn8xgGAYuw6fzpYYerlWYnDPNoW+t5+Pu2Tf5Tv3HxN971
Gh75uVTqdj\n2bq9kjYv10r416meyxUFY2NlTueWgZK2bftDeBz3tFD3FQRBEEpGSkoKt2/fZvr06XTs2FE
khsUg\n3+Tw//7v/+jVqxf+/v6UL1+egIAA+vTpw9ChQ0siPuEF/RsWwZLVuyRt9nbWfPRud4yMCr/
+yMLM\nFB8vF0nbqUyLVIrKoZMXiIiWzmfs361FkfRQdnijITZWGUM86lQNq7aK7fUEQRBeBWvWrMHHx4eY
\nmBimT59u6HBeS/kOK69du5bJkyczdepUqlevzoULF/jkk0+YOnUqAwYMyPW68PDwIg9WyNvDx0+Y\n8/s
WEpMzVvYaq5R8MKA9zhXK5XHlizkRGsbKbRmTo50r2DJuaJciu786VcPXP68j/mmivq2utwsD\nujYvsmcc
O3uV1duP61/LZDB+aBcc7W2L7BmC8LooyWFvMawsCCUjr5+1fLuSJk+ezKhRo+jevTuQ\nXuAyKiqK77//P
s/kUMyhKZiimm+UkJjM/L9/R6Ywwtw8vc6UTAYfv9uD+rU9C33/zBycKrLt8Hn9\nQpH4BDXmVuVwdrArkv
uv23EEjVamn8CtVMoZPbgnFV6gaHV+76urqyuhV6O5c/
+xvu3Y+QgmDG/4\n8oG/5sTcuOIh3ldBEEqbfIeVExMT9fsFPqdQKCQbcguGlZaWxg9LNkgSHYA+nZoXeWI
IYGVhhre7\ndMXWqXNFM7Qc9+QZG3cfl7S1a97ghRLDglAoFLydZRHKmX+vcSn8VpE+RxAEQRBeNfkmh23b
tmXO\nnDns3LmTW7dusXnzZn766Sc6duxYEvEJBbBiwz7OXb4haWvasBadWwXmckXhZd1r+WRo0ZS0WbX1\
nkGQlsaW5Kd1aNy6Se2dVv7YnXq6VJG0rNu4r0T2jBUEQBKG0yTc5nDVrFp07d+ajjz7C39+fSZMm\nMXDg
QD7//POSiE/Ix75joWzdHyJp83BxZlifdsW6c0lDXy8y3/5G5D0exsQV6p6Rdx6w71iopK1H\n+6aYm5nkc
kXhyGQy+nZ9Q9J2LeJusdduFARBEITSLN/k0NLSkpkzZ/Lvv/9y7949zp07x+TJk7Pt\npyiUvIMnzvPryh
2SNjtbSz4e1gNVlv0vi5qNlQXV3aTlA068ZO/h3QeP2bj7ON/9upbMnXbODuVo\n2bhuYcLMl5drJRr6Sof
e/958AI2m6LalEgRBEIRXidhb+RWk0+lYueUg63dKt1MyVikZ/15PbKws\nSiSOhr5eXL6WUa3+VOhVOrUI
yPc6nU5HRPR9Tp27Ssi5q0TdzblOYt8ub5TIvsd9Ogfzz4Vw/QKb\new9j2XvsLG2a1S/2ZwuCIAhCaZNvz
6FQuqhTU/lxyYZsiaFMBiP7d8KlkmOJxZK1IHXYzdvExD7J\n8VydTsfla5H8sWY3o7+YzyffLGbdjqO5Jo
Y1Parg51MyKzidHex4o1EdSdva7UdITEopkecLgiC8\nqLNnz2JjY8OtW8W/iG7EiBGlamu3F3Xr1i1sbGw
4e/asoUN5ZYjk8BUS/zSBr378k2NnLkvajYwU\njHmnYNvKFSU7Wys8XJwlbVlXLd+5H8Pfmw8w+ov5fDFn
OdsOhPAwJj7P+3p7VGFk/07FOmcyqx7t\nmmCsyuhIj3+ayJZ9hdurVBCEsmPEiBHY2Ngwa9YsSfvhw4exs
bEhJibGQJEVXFlJokrq/
+Rlk+oZ\nM2YQGFh8C0oLQgwrvyJu33vENz+v4v4j6aIPa0szxg3riUe1igaJq2Gd6oRH3NG/PnXuKo38vD
l2\n+hKHQ/7l+q27+d5DLpfh7V6FBr5eNKjtiZ2tVXGGnCNba0s6tvBn7faj+rYte0/Sqkk9bK0tSzye\nV
41Op+PK9SisLc1fut7lzah7rNl+GBNjFT3bN8XRvugKtwtCSTAxMWHu3LkMHjyY8uXLGzocQXhp\noufwFf
BvWASff/dHtsSwooMd0z4eZLDEEMC/jpfk9eVrkYyYNJff1+zOMzFUGSmpX9uDkf068suM\n/
+PzD/rSNqi+QRLD5zq1CMDa0kz/OkWtYc32IwaL51WRkJjMlz8s54s5yxk7bSEbdx3L/6IsrkXc\n4Ys5y/
jnfDhHQi4yafYfhN+8XQzRCkLxadq0KZUrV87We5jV0aNHadGiBQ4ODnh4eDBx4kTUanWe\n1+zZs4cGDRr
g4OBAu3btuHbtWrZzTp48Sfv27XFycqJGjRqMHTuWJ0+eSO7Rrl07qlatiouLC2+
+\n+SZXr2aM9vj6+gIQHByMjY0NHTp0kNx/wYIF1KhRg6pVqzJy5EgSExPJzfPeuR07dtCkSRMcHBwI\nCg
oiNFRakSK/mDt06MBHH33E1KlTcXV1xd3dnUmTJklqLa9cuZLg4GAqVaqEu7s7AwcO5M6dO+Tk\n1q1bdOr
UCQA3NzdsbGwYMWIEf/31F9WqVSMlRTqd6N1336V37965fp1LlizBz88PBwcHXF1defPN\nN9FoNMyYMYO/
/vqLnTt3YmNjg42NDYcPHwbgiy+
+oH79+jg6OuLj48PkyZNJTk4GYMWKFXzzzTdc\nvnxZf92KFSuA9B1NxowZg7u7O5UqVaJ9+/aSXt74+HiG
DRuGu7s7Dg4O+Pr6Mn/
+/Fxjz4voOSzl\nDp44z8K/tpGWJi06XsuzKmOHdi+2Mi8F5VDeFpdKDvp9kHU6ssX6nMpISX0fDwLq1cC3
hismxqqS\nDDVfpibGdG/XhMWrMvamPnTyAv26voGpibEBIyu9EhKTmf7TX/oPAjod/LnpADK5nM4t81+cB
BB9\n7xEzF6yU1Ld8mpDE1B9X8MGgLjTw9crjaqGsMIsaX6LPS6ycd4KXE7lczhdffEHfvn0ZMWIE1apV\n
y3bOnTt36NmzJ7169WL+/PncvHmTDz74ALlcnus+wdHR0fTt25cBAwbw7rvvcvHiRT777DPJORcv\nXuTNN
9/kk08+Ye7cucTGxjJx4kRGjRrF0qVLAUhISGD48OHUqlWLpKQkZs+eTe/evTl58iQqlYp9\n+/bxxhtvsH
btWmrVqoVKlfE7+vjx4zg4OLBhwwZu377NoEGDcHd3Z+zYsXm+J59//jkzZ87EycmJ\nb775hl69enH27Fn
MzMwKFDPA6tWree+999i1axcXLlxg6NCh1KlThx49egCgVquZOHEinp6exMTE\nMGXKFIYMGcL27duzxVOp
UiWWLl3KgAEDOHHiBLa2tpiYmKBSqfjkk0/Ytm0b3bp1A9KTrS1btvDr\nr7/m+LWdPXuWjz/
+mAULFhAQEEB8fDyHDh0CYPTo0YSFhREbG8vChQsBsLVN357VzMyMefPm4eTk\nxNWrVxk7diwqlYpJkybx
5ptvcvnyZXbu3MmWLVsAsLKyQqfT0atXL6ysrFi5ciW2trb8+eefdO7c\nmZCQEBwdHZk2bRqXLl1i5cqV2
Nvbc+vWrZceOhfJYSm2cfdx/ty4P1t7cKAvQ3u1LZGVvAURULe6\nPjnMSU2PKjRtWIuGvtUNnszmp0Wjum
zcfZyY2KdA+j7P/1wIp2mDWgaOrPR5lpjE1z/9nWMP8YoN\n+1Aq5LQPzns7wocxcUyf9xdPE5KyHVOnavj
217UM6tGatkFi5bjwamjdujX+/v589dVXLF68ONvx\n3377DUdHR7799lvkcjleXl5MmTKFDz/8kM8+
+wwzM7Ns1yxevJhKlSoxa9YsZDIZnp6eXLt2TZJM\n/vjjj3Tr1o3Ro0fr27799luaNWvGw4cPsbe3p0uXL
pL7/vTTT1SuXJnTp08TGBiInV36lJBy5crh\n4OAgOdfS0pLvv/8ehUKBl5cXXbt25eDBg/kmh+PGjaNFix
b653l7e7NmzRoGDBhQoJgBvLy89Mmw\nu7s7f/zxBwcPHtQnh/3799df7+LiwnfffUfDhg25ffs2FStKR9Y
UCoU+SbO3t9d/zQBvvfUWy
5cv\n1yeHa9aswdLSkjZt2uT4tUVFRWFubk67du2wtEyffuTj4wOAhYUFJiYmGBsbZ3svx4/P+KBTtWpV\n
xo4dy9y5c5k0aRKmpqaYm5ujVCol1x08eJALFy5w7do1TE1NAZg0aRI7duxg5cqVjBkzhqioKHx9\nffHz8
wOgShXpTmYvQiSHpdQ/58NyTAz7dG5Ol1aBJbpYIz9N6tdk3Y6jqFM1+rZKjnY0behDk/o1\nKV8u5429Sy
OlUkGT+rUkW/gdO31JJIdZPE1IYvq8P7kZlfuHgj/W7kGpVNC6qV+Ox+OeJDD9p794\nHPc013vodLBk9S4
ePo6nX9c3StX3vSDk5ssvv6RVq1Z88MEH2Y5dvXqV+vXrI5dnzOoKDAxErVZz\n48YNatXK/rvm+TWZv/8b
NpR+8Dp37hw3btxg/fr1+rbnuz3dvHkTe3t7bt68yfTp0/nnn3+IiYlB\nq9Wi1WqJjo7O92vy8vKSbKXr6
OjIP//8k+91meO0sLCgZs2aXLlypcAxA9SsWVNyT0dHRx4+fKh/\nHRoayjfffMOFCxeIi4vT3yM6Ojpbcp
iXAQMGEBQUpE8qly9fTp8+fVAqc06Vng9l+/r60qJFC4KD\ng+nUqZM+UczNxo0bWbBgATdu3CAhIYG0tDT
S0vKurXvu3DkSExNxd3eXtCcnJ3Pz5k0AhgwZwsCB\nAwkNDSU4OJi2bdvSpEmTAn/9mYnksBSKvveIuX9s
lLQZGSl4v39nAuuV7IrkgrC3s+GTEb3Yd+ws\ntjaWNPariUslh1f2D3kjvxqS5PD8lRs8TUjC0tzUgFGVH
k8Tkpg2989svcXVKjtw+16M5EPCbyt3\nYqRUEBwoLRWUkJjMjPl/c/dBrKS9VZO6VKvsyK8rd+jrTkL64q
DHsU8Y2b8TRkbi15ZQuvn5+dG5\nc2cmT57MuHHjCnxdYX5narVaBgwYwMiRI7Mdc3JyAqBXr144OzszZ84
cnJycUCqV+Pv75zvfEcAo\ny8YKMpms0FuNFiTm/J6dkJBA9+7dad68OQsXLsTe3p6YmBjatWtXoK8rMx8f
H3x9ffnzzz/p0KED\nZ8+e5Zdffsn1fEtLSw4dOsTRo0c5cOAA33//PV999RX79u2TxJ9ZSEgIgwcPZsKEC
Xz99ddYW1uz\nbdu2fHed02q1VKhQIceh8ufJaKtWrbhw4QK7d+/m4MGD9OrViy5durzUvEPxW7aUSUhMZv
YvqyXz\nr+RyGROGv4WPV/b5K6VFTc+q1PSsaugwikTVig5UdLDj9v30uRoajZaQc1ez1UIsi+KfJjBt3p9
E\n3n4oafdehwCKAAAgAElEQVT2qMKE4W8RdvM2sxauIjU141Pwwj+3oVAoaNYwfbhFnZrK7EVrsiWX\nje
rVYPBbbZDL5ZSzsWTO4vWSn4NjZy4T9zSBj97tjoWZSNTLmpeZA2hIkydPxt/fn71790ravby8\nWL9+PVq
tVt97ePz4cVQqVY5zFJ9fs2nTJnQ6nT6BDAmRbpvq6+vL5cuXcXV1zfEejx8/JiwsjNmz\nZ9OsWTMgvcdN
o8n4MPd8jmF+vVgvIiQkBBcXFyA9kbt06ZJ+gUd+MRdEeHg4MTExfP755/rnbNq0\nKc9r8vo6Bw4cyA8//
EBMTAwBAQF4eORdb1epVBIUFERQUBATJ07E3d2dnTt3MmjQIFQqVbZnnDhx\nAicnJ8nQclRUlOScnK7z9f
XlwYMHyOVy/deZEzs7O3r37k3v3r1p1aoVQ4YM4fvvv8fY+MXmzYvV\nyqWIVqtl7h8bs/WmDHizZalODF8
3MpmMRn7ekrZjpy8ZKJrS49l/PYZZE8NanlWZMPwtTIxV1K5e\njY+GdkepzPjVotPB/GWbOXb6EhpNGnMW
r+dSeKTkHr41XHl/QGf9H8u6Nd2ZMqYf1lbmkvMuhUcy\n5bulhd7HWxCKm6urK4MGDeLnn3+WtA8ZMoR79
+7x0UcfcfXqVXbu3MmXX37Ju++
+m+N8Q4B33nmH\nyMhIPvnkE8LDw9m4cSNLliyRnDNmzBjOnDnDhx9+qB+u3bFjB//3f/8HgI2NDXZ2dixd
upQbN25w\n5MgRxo4dKxkytbe3x9TUlL179/LgwQPi4/OuSVsQs2fPZv/
+/Vy+fJlRo0ahUqn0cwXzi7kgKlWq\nhLGxMYsWLSIiIoKdO3fy9ddf53lN5cqVkclk7Ny5k0ePHvHs2TP9
se7du/PgwQMWL15Mv3798rzP\njh07WLBgAefOnSMyMpLVq1fz7NkzPD3Tt2StUqUKly9f1iewqampuLu7c
/fuXVatWkVERAS//fYb\na9euldy3SpUqREVFERoaSkxMDCkpKTRv3pyAgADefvttdu/eTUREBKdOneLrr7
/m2LH0ChHTp09n\ny5YtXL9+natXr7J582ZcXFxeODEEkRyWKqu2HuLsxeuStiB/HzEZ3wCyJof/hkUQ9+R
ZLme//uKe\nJDBvxQ4i70gTQx8vF8b/lxg+V7emOx8OfhOFQpogzv1jI9N/
+ovTF6QlODyrVWTs0DezLbByreLE\ntI8G4uwgrXcYfS+Gz79bmudcRUEoDcaPH59tvpqzszOrV6/m/PnzN
G3alFGjRtG9e3cmT56c630q\nV67MsmXL2Lt3L02aNGH+/PlMmTJFck6tWrXYtm0bkZGRdOzYkSZNmjB16l
T9vD25XM7ixYu5ePEi\ngYGBjBs3js8+
+0ySOCiVSr755huWLVtG9erVefvttwv9HkyZMoXPPvuMoKAgrl+/zsqVKzE3Ny9Q\nzAVRvnx5FixYwNatW
/H39+ebb77JddX3c87OzkycOJFp06bh4eEhGfq3tLSka9euGBsb6xem5Mba\n2pqtW7fStWtXGjZsyLx58/
jxxx9p1KgRkN4L6enpSXBwMG5ubpw4cYJ27drxwQcfMHHiRBo3bsz+\n/fv59NNPJfft3LkzrVq1okuXLri
5ubFmzRpkMhmrVq2iadOmjBkzhgYNGvDOO+9w7do1/RC2sbEx\n06ZNo0mTJrRp04Znz57x999/F/i9zEwW
FxdXuEkDQqGEh4fj4eHBydArfPfrOskxt6pOfPF//VBl\nmW9R1Izid6FMOE2acRXUtt1BXrpXFBfE8/e1M
CbM/E0y9DmoRyvaNW9Q2NBeOfFPE5j6w3KuXo/U\n/1IH8Knuwvj3eub6/Xn8zGV+WLKevKYlVXG2Z/KYfn
nO53yakMTsX1Zz5bp00nwdb1c+GdHrlZ3b\n+lxRfK+
+TuLj47G2fnUWsQk5O3z4MJ06deL69euSFcGvgh49euDs7MyPP/5o6FCKVV4/a6LnsBSI\nvPOA+cs2S9qs
rcz5aGj3Yk8M5ck3MHqyB1laLMrEcxg/Xk2ef83LkKy9h8ezbFtYVvyxZjfR96S1\nsnxruOaZGAIE1qvBq
IFdyC13q2Bnzafv9853oY+luSmfjepDQF3pXt6hl26w71hoLlcJgiC8mLi4\nOLZt28a+ffsYPny4ocMxKJ
EcGlhCUgqzf1kjmXivVMr5aGj3EtktRJESLn2ddAFF0rlif+6roFGW\nleFXb0SXubluEdH3OJplvmXdmm5
8PKxgH1ya1K/JiL4ds7VbW5nz2ag+Bd6aUGVkxJh3uuLtIa3b\ntXTdnjL3fyIIQvFo2rQp7733HpMnT8bb
2zv/C15jIjk0IK1Wy7INB7Ntizeoe2u8XCuVSAxydfYt\nylSx65GlPcnh7LLF3s4m2//DsTLWe7hyyyHJ6
yoV7V+4RzsooDbv9m6r70G0NDfl05G9X3jvZLlc\nzvC+HTAxznh2ckoqC5ZvKXRJDUEQilbTpk2Ji4t7pY
aUL1y4QFRU1AstiHldieTQgP7afICrN6X7\nP7ZoXIeWTeqWWAzy1OzJoUybhOrxWjG8DNnqSpalVctXb0R
z5l/p4pG3Owe/VJ3Blk3qMWviUEb2\n78S3k4bhUskh/4ty4FDeln5dW0jaLoZHsuNg/sV4BUEQhIIRyaGB
nLt8g027T0jaPKtV5J0erUts\ngr0s7QmytJxXfCqSL6NIFH9wA+vVkMyZi4i+z537L7dX5atEp9Px1ybpD
j3VKlWgjrfbS9+zinMF\ngvx9sLY0z//kPLRsUhef6i6Stj837i8T/y+CIAglQSSHBrJ2+xHJa1trC8YOfb
NEd3/IaUg5M1Xs\nJmSa2DzPed3ZWFlQy9NF0lYWeg/PXb7B5WvSwqwdmtcrFSuDZTIZI/p2xMw0o3yOOlX
DguVb0Gq1\nBoxMEATh9SCSQwMIuxnN1RvSshwfDnmzwJPzi0rW5DDNxAtkGX9wZboUVI9Xlfnh5ayrlo+e
vvha\nz3FL7zU8IGmr4+2KWxVHwwSUAztbKwZ1by1pC7t5m817TxooIkEQhNeHSA4NYEuWP2C1a1QrsQUo\
nmclTpQlqmmlt1NbtJG2KlOsonx2nLGvg6yXZ8ePO/cfcun0/jytebSfOXsm2tV2fzs0NE0wemvn7\n4Ocj
3YR+1daDRN19mMsVgiAIQkGI5LCE3X3wmFPnrkraOrUIMEgscrV0MUyayhmNRSPSjKXzylTx\n25ClPirJ0
EoVS3NTaleX7v157HTJrFqOe5LAgxIs1ZKWlsaqrQclbYH1quNSqfT0Gj4nk8kY1qe9\npE6iRqPlp6Wb0G
iKbm9YQRCEskYkhyVs2/5TklHaig7l8PFyKflA0p4hS8ucdCjQGTmATIa63Fvo\nZJn2YtSpMX68CnRldz5
X4/o1Ja+PnblU7EPLR/
+5yPuT5zJ6ynz+WLO7RIayD568wJ37j/Wv5XIZ\nb3UIKvbnviwbKwsGv9VG0nYz6j4bd5ft3m5ByElgYCA
zZswwdBjCK0AkhyUo/mkCB06cl7QF+9c0\nyCT/rPMNtUaOIEtfDKNT2pJq0znL+REonx4usfhKm/o+Hqgy
LRZ6GBNPeETeC3oKIyb2CQv/3IpG\nk56QbzsQwuGQf4vteQDq1FTWbJf+HzcPqI2zQ+muU9bIz5vAetLdU
9buOMLNqHsGikgoyx48eMCE\nCROoU6cOFSpUoEaNGvTo0YNdu3YZOjRBKDCRHJagXYdOo07V6F/b2VriW8
PFILFkrW+oVUnnPGrM\n65NmIq3xp4rfgSy1bP7BNTFWZZvfVpyrlpet30OKWiNp+33NLh7H5Vx6qCjsPnK
WmNiM+xsZKejR\nrmmxPa8oDX6rLdaWZvrXaWla5i/fLIaXhRJ169YtgoKC2LdvH1OmTOHo0aNs2LCB1q1b
M3bsWEOH\nJwgFJpLDEpKiTmXnodOStvbBDVEqFAaJR5G151DlLD1BJkNdrjs6eeZ9b9PK9N7LjfykQ8vHz
1wu\nltIpF67e5PiZK9naExJTWPjn1mIZXk5KTmHDzqOSttZN6pXIFo5FwcrCjHd7SxdTRd5+yOa9J3K5\n
QhCK3scffwzA/v376datGx4eHnh5eTFs2DCOHEkvXzZv3jwaNWqEs7MzNWrUYPTo0cTFZUzxWbFi\nBRUrV
uTgwYMEBgbi7OxMx44diYiI0J9z8+ZN+vTpg6enJ87OzjRr1owdO3ZIYnn48CF9+vTB0dGR\nWrVqsWzZsm
zx5heLUHaVXFG9Mu7gyfM8TUjSvzY3M6ZFozpER0UaJB55qnQxitaoYrZzdAor1Lbd\nMI75M+M6dRTylOt
oTdyznf+6q+PtiqmJiqRkNZC+WOTStchsdRALQ6NJ4/fVuQ8/hV66wYET5wgO\nrFNkzwTYuu8UT55lfH+a
GBvRpXWjIn1GcWvg60XThrU4fCpj+H3tjiP416le6ofGhfz1OlCyoxYr\nm7/YIqzY2Fj27NnDpEmTsLCwy
HbcxsYGSN8GcsaMGbi4uBAVFcX48eMZP348v/zyi/7clJQUvvvu\nO+bNm4exsTEjRoxg7NixrFu3DoBnz5
7RqlUrJk2ahKmpKevWraN///4cPXoUT09PAEaOHElUVBQb\nNmzA1NSUTz/9lMhI6d+bgsQilE2i57AEaLV
atu47JWlr2bgepibGuVxR3AElItNk3k1CjlbllOOp\naaa+pJlI6/wpE8rmzikqIyMa+HpJ2op6aHn7wRCi
70l3+qjkKE1s/li7h4dFuIL5ybNEtuyTllfq\n8EbDQu9kYggD3myJlUVGb3dqahqL/t7+WtelFEqHGzduo
NPp9MlZbkaOHElQUBBVq1alSZMmTJ06\nlQ0bNkhGITQaDbNnz8bPz49atWoxevRojhw5ov8+9vHxYfDgwd
SsWRNXV1c+/vhjfH192bhxIwDX\nrl1j9+7dzJkzh4CAAHx9fVmwYAFJSUkvHItQNonksASEnA/j3sOMnUa
USjntmtc3WDxZS9hojRxA\nZpTzyTIZqZaNJU3KpAugTcr5/Ndc4ywFsU+evVJk89pi45+yZpt0QUhwoC/j
3uuJsSqjkz8pWc3C\nP7cVOuHR6XTcuR/D0nV79L2hkF66p+MbhimvVFhWFmb0f7OlpO1SeCT7j58zUERCW
VHQn8eDBw/S\ntWtXvL29qVSpEv3790etVnP/fkZtUWNjYzw8PPSvHR0dUavV+iHfhIQEJk+ejL+/P1WrVq
VixYqc\nPXuW6Oj02rVXr15FLpfj5+env0eVKlVwcpJ2AhQkFqFsEslhMdPpdGzeI5331NivZonvhpJZtpX
K\nquxDypLjxu7oFDYZDbpUlIll849tLU8XSV29Z4nJnAjNPj/wZSxfv5fklFT9a3MzY/p0bo6jfTn6\ndn
1Dcu6FqxHsPnLmhZ/xICaO/cdDmfvHRkZMmsuHXy2UDMMCdGkdiJmpgXq1i0DTBrXwrSGtS7l8\nw17injw
zUERCWeDm5oZMJiMsLCzXcyIjI+nVqxeenp78/vvvHDhwgHnz5gGgVmd8QFMqpTO+nle0\neN6j9/nnn7Nh
wwY+/fRTtm7dyuHDh/Hz85PcI/N1hYlFKJvEnMNidvVGNOER0p66Ti0N2yuTbaWy\nkXMuZ/5HJkNjXh+jJ
3v0TcqEEDQWr2bvUmEolQoC6lZn95Gz+rYlq3ZSw61yoRZvXAq/xZF/pEPU\nvToG6Yd2Wzf141ToVf4Nu6
U/vmLDPnxruOJQ3jbX+2o0aYScDyP00nUuht/iYUx8nnGUs7GkTTO/\nPM8p7WQyGe/2bstH03/Rr/hOSEz
h9zW7+L/Bbxo4OuFlvegcwJJma2tLixYtWLRoEe+99162eYdx\ncXGcPXsWtVrNjBkzUPy3GDHrQpKCOHHi
BL1796ZLly4AJCcnc/PmTdzc0jcw8PT0RKvVcvr0afz9\n/QGIiori7t27+nsUVSzC60n0HBazrKsl63i7U
tnJ3kDRpMvec5j/1n0a8wZAxqdQuToKmfpu7he8\nxlo380OhyPjReZaYzA9LNpCW9nLDy2lpaSzJsgilaq
UKtGxcV/9aJpMxvG8HTIwzhv+TU1L5eUXO\nq5cTk1LYsu8kH3w5nzmL13PgxPl8E0OZDAb1aIXKKJcpBq8
Qezsb3uooLd59/MwV/jmfe6+OIBTW\n7Nmz0el0BAcHs2HDBsLDwwkLC+O3336jSZMmuLm5odVqmT9/PhER
EaxZs4aff/75hZ/j5ubGli1b\nCA0N5eLFiwwbNoyUlBT9cQ8PD1q2bMmHH37IqVOnOH/
+PCNHjsTU1FRyj6KIRXg9ieSwGN2+94h/\nzodL2gzda4g2Bbkm81Z4MrRGOS9GyUyntCXNWLpCuawuTKni
XIHenZpL2q7eiGbN9iMvdb+dh04T\neUe6H/CQt9rqP80/Z29nw4Ac5tNtPxCifx0b/5QVG/cxaso8lq3bK
6lbmBOVkZLaNarxdufmfPvZ\nMPzrVM/z/FdJu6D6uFWVfm//tmoniUkpuVwhCIXj4uLCwYMHad68OVOmTK
Fx48Z07tyZ7du3M2fO\nHGrVqsXMmTOZP38+AQEBLF26lK++
+uqFnzN9+nTs7e1p3749PXv2pEGDBgQGBkrOmT9/PlWqVKFz\n58706dOHnj17UqVKFf3xoopFeD3J4uLix
DK+YvLLX9vYezRU/9q1iiNfj3tHMg8kPDxcMvG4uMlT\nbmDyIOPToVZZgWSnjwt0rSIxVFLWRic3J8n5M/
3OKqVJcb+vOp2OmQtWEnrphr5NJoNJo99+odI2\ncU+e8eFXP5OYlDHHp5m/D+/375Trc2fMX8m5yxnPVRk
p+b/B3TgZeoWjpy/qd1XJiZGRAk+XitT0\ndKGmZ1XcqzqjVBas1mZJf68WhYjo+0yctRitNuPXXJtmftm2
3DOkV/F9LU7x8fFYW1sbOgxBeO3l\n9bMmeg6LSdyTBA6duiBp69QiwCBb5WWWbaVyPotRMkszrSkpii3TJ
qBIulxksb1KZDIZI/t3wsYq\no9yLTgdzf99I/NOEAt9nxcb9ksTQzFRF3y7BeT73vbfbY26WsWBEnaph1s
LVHDx5IcfEUGWkpFWT\nunz+wdssnjWWyWP60b1dE6q7VS5wYviqcqnkQKcW0t76XYdPE3Yz2kARCYIglH4
iOSwmOw6GkJqa\nMQfN3s4a/zpeeVxRMl50pbKEzIg0s7qSJmVCSC4nv/6sLc0ZNbAzmfP9uCcJzF+2uUBl
La7eiObQ\nSekHiB7tm2Fjlb2AbmZ2tlYMfLNVvve3sjClZ/umzJv6PkN7t6OWp8trMZ/wRfVo3wRH+4xFO
zod\nLFyxVWytJwiCkAuRHBYxnU7Hln0n2bj7uKS9Q3DDbHPIDCH7SuUXSA55vjAlgyL5KjJN3gsdXmc+\n
XtXo1kZaBzL00o1sRaWzioi+z6K/tknaqjjb07aAK4Wb+ftk2+v5OUd7W4b2asu8qaPo0b7pK1nM\nuiipj
Ix4t490a73oezHZfkYFQRCEdKVvstgrLDlFzcIVWzl2RjrUamFmQnCgr4GiykSrRp4qLW6a\nbU/l/G5h5I
zWyDnT9ns6FImn0Vi9ked1r7Me7ZpwMewWV29kDFX+tekA1V0r41EtI/nW6XRcCo9k\n057jkrmKz73Ts3W
BP0Ckl2tpR0T07/pFJ57VKtKpZQD1fTyQy8XnvsxqebrQPKA2B06c17et23mE\ngLrVqehY3oCRCYIglD4i
OSwidx885ttFa4i6+yjbsYE9WmFirDJAVFLy1HtAxnCnTmkHmeYQFsh/\nNQ9VcZv0TUYJIWgsg8HA8ykNR
aFQ8MGgLkyY+RvPEpMBSEvT8sPvG/hmwhBMTVSEnA9j4+7jXL+V\nc/mfxn7eeHtUfaHn2lpbMnPCEC5cuY
lThXK4Vsl/1XlZ1q9bC85evEb800QANBotS1bv4rNRfQw+\nF1gQBKE0EclhETh9IZx5SzdKFhZA+g4XowZ
0pl6t0rESMeuQctoLDik/pzGrhypuK5A+Z0umiUGe\nchOtiWveFxYBWeo9ZJo4tCZuuW/5VxhpiSgTz6Qv
tJEbobbuiM4o/56l8uWsGdGvI//7ZY2+7WFM\nPP/7ZTVxT55x90FsrtdWd6vEOy+5etbKwozG9Wu+1LVlj
aW5KYN6tOaHJRv0bReuRnDi7BUC69Uw\nYGRCVjqdTiTsglCM8psXL5LDQtDpdKzedoi1249mO1aloj0fDe
2Oo305A0SWM7laukLzhRajZKYw\nQ2NaE2VSxhCdMvEf1MWVHGqTUSaeRfnslD7B1SntSLZ/D53SJp+LC0C
nQ55yE2XCyfR9o3Ua/SET\ndTTJDh+gU+S/
+0n92p60a16f7Qcy6j9evhaV6/lerpXo3DIAPx8P8YewhATWq8G+46FcuBKhb/tj\n7W7qeLtiavLqbhn4O
jE3NycuLg4bGxvxcyEIxSQxMRETE5Ncj4vk8CU9S0xi3h+bOHvxerZjjf28\nGfZ2+
+IfStamYBS/C0XyFbQmHqhtOuZZc/BldkbJjca8QZbk8Dxqm84gz/2b7YXodMjVUekJW+I5\n0GXZM1QTg/
Gj30iuMPLFh8afS3uGMuE0yoRTyDUPczxFlvYE40dLSa4wvED1HN/uEszla1FEROe+\ncb2fjztdWjXCy/X
l33/h5chkMgb3bMO4GYv0ZX9i45+xZvsR+ndrYeDoBEjfV9jS0pInT54YOhRB\neG0plUqMjXP/QCySw5fw
6HE8X839k3sPpUOFcrmMft1a0L55g2L/xCtLfYRxzDLkqelz2OTPHqKT\nm5JqncvwpE6TfTFKfnsq50Fr4
oFOYYMsLe6/+6tRJp5DY+H/0vdMv3EiyoQzKBNC9F9bbuSp9zF+\ntJQU+yEvVIhbnnIL5bMjKBP/5fnQeJ
7nqyNRxW5Abds933mVKiMjxrzTlYmzFpOckqpvVyjkNKlf\nk04tAwy+fWJZ5+xgR8c3/NmwK2O18vYDITQ
PqC3+b0oJpVIpCmELggGJJY0vSKNJ4/vF67IlhtaW\nZnw+
+m06BDcs9sRQnnQFkwdzsyVPRk8PItPE5HxN6j0yJ0I6hQ0oClHiRCZHY15f0lTYmofKp0cw\nuzMdVdymf
BPD5xQp11E9XpVevC4/Oi1G8TsxefBTem9kLomhTlEuW6+qMuEUyoQTOZ6flbODHePf\newtHe1vs7azp8E
ZD5n4xkpH9O4nko5To1qYxdraW+tdpaVqWrNpZoPqUgiAIrzvRc/iC/tp8gGsR\n0sTFw8WZsUO7U87GMpe
riohOh9HTfRjF7yLzquOM4xpUcZtJKT8o26GiHFJ+TmPuh9GTPZmeEYks\n9T46I4cXvpci4bRkBXRWOoUN
GvP6aMzqYvx4FXL1Lf0xZWIoOoUtqTbtcr0ebSLGMX+hSL6aWwRo\nTGuisfBHa+wOuiRM78+VJNuq2E1oj
ZzQGrvk+/XU9KzKD1NG5HueYBgmxioGdm/Fd7+u07ddDI/k\n2OlLYoGPIAhlnug5fAFn/g1ny15pceN6td
yZMqZf8SeG2mSMY/7AKH4nOSaG/1EkXUKedCVbe6F2\nRsmFTmlHmrGbpO1leg/l6iiMY9fmcERGmqk3KeX
fIclpAqnWrdEZ2ZNcfhBapbQHzujpfpTPci5q\nLFPfxfT+3BwTQ62yPGrrDiQ6f4a6fD+0Jh7pQ8dyM5LL
DwRZ5nmjaRg/Wlami36/Thr6euFbQ7qI\natn6vSQmpRgoIkEQhNJBJIcFFBP7hPnLtkja7GwtGdm/E0ZGx
dsBK0u9j8n9uSiSLmU9gtq6A1qV\ntD6eKm6zZMUtFH5nlNxk3TFFmXAm27PzlPYU40fLpNfIjEi1ak2S06
eklB9EmmkNkGUqDq0wJ8V+\nMDq5dJs5VewGFEkXJW2KxHOYPvgp23C7Tm5BcvnBJDuOQ2MVBIrsW9bpjBx
JKddL0ibTPsU4Zino\nUrOdL7xaZDIZ7/RsjVKZ8WswfXHKYQNGJQiCYHgFSg7v3bvH8OHDcXNzw8HBAX9/
f44cOVLcsZUa\nGk0aPyzZwNOEJH2bXC5jzDvdsDR/yZWyBaRI/BfT+3OzrabVyc1Ith+KxioItW1XIGOeo
1zzEOXT\nTOV1dJpsc/jSXnBnlNykmfmgy7RaWKZ9hiLxXMEu1mkwjlmRsajlPym23Um1bolOmfuEdJ3Sjh
T7\nd7L07OkwjvkTeUpk+vzCuC0Yx6zIttJZq6pCssMYtKbV811gkmbmQ2qW3V/k6ihUsRsKNs9RKNWc\nK
pSjc8tASdv2AyFE3nlgoIgEQRAML9/kMC4ujjZt2qDT6Vi1ahUnT55k1qxZ2NuXnYn1q7cdkmyN\nBtC7Y1
CxlyJRJIT810uVNbmplJ7cmHj897oiGvOGknNUT3YjS0svBSFLfSjpmdMprKAAdfsKRGZE\nmql0a0Djx6t
QPjmYb/KkituCIkW6jVyqRVPSzOsV6NFaVWVS7PqSOTFGl4rxoyVU1K7F6OmhbNdo\nzP1JrjA8z8Qzq1Sr
1qSZSIskKxNCch3GFl4tXVs3wt4u4/tBq9WxZPUusThFEIQyK9/k8Mcff8TR\n0ZGFCxfi5+eHi4sLQUFBe
Hl5lUR8Bhd66bqk5AVAHW9XOrcKzOWKIqJVo4rNvkBDY16f5Aoj0Clt\nJe1q6zaSHjx0aozitgHFN6T8XK
qFP5IEDR2q+K2oHv8F2pznbykSQlA+OyZpSzN2I9Wm/Qs9O820\nBmrbbpI2mTYBU25nOVOB2rYH6nLdX6j
sTfoN5aTY9UarlO6UoorbjDw5+x7JwqvFWGXEoO6tJG2X\nwiM5HPKvgSISBEEwrHyTw61bt+Ln58c777yD
u7s7TZo04ZdffikTn6pj458yf9lmSZuttQUj+3cq\n9nI1ipRwZLrMiZUCtW031LY9c942TmFBqlVrSZMy8
QzylIhiWYySmU5VMb0AN9L3RJkYismD+chS\npftNy1MiMX68TtKmU9iSYtdPOrewgDQWAaRa5V7AWKewJr
nCCDQWDXM9J19yU1JyWqASsxzSnr38\nfYVSwc/Hg7o1pYurlm/YR8J/e2ULgiCUJfkmhxEREfz222+4uLi
wdu1ahg8fzpdffsmiRYtKIj6D\n0WRde1QAACAASURBVGq1zP19I/FPE/VtMhl8MKgL1paFqA9YQFkXn2gs
/NFYBOY5R05jEYDWyEnS\npordgEIt3cKtqJNDAI1lU1LKvyPtvQTkqXfTazI+X0Gd9iR9qDxzjUGZEcnlB
xSq7mKqVWs0Zn7Z\n2tOMXUly+ACtcZWXvvdzOiMHUux6S9pk2mcYZekBLUmKpMsYP1qG0ZO9oMu/oLeQM5
lMxqAerTAy\nyvhwEv8kgb83HzBcUIIgCAYii4uLy7ML0N7enrp167Jr1y5929SpU9myZQunTp3K9brw8PC
ii9IA\ndhw+y87D0oUV7ZrVoXWTOsX/cJ2WatpFKMhYAHNb/iZJsvwTHBNdNJW0a/I8J0I+BI2seErvGOni
\ncNJuRkXWYtwyYmQBmOtuYcIdyZF78nY8kxXBNAVdGk66rZjr0od642R1eSRr8lK9kXkppz1GOV3G\n974
aOyIV/Yv0GQVhrLtHJe0qZKRvA/dI1ow4ecHmawo5237oLLuOSH/u2wfVpVVj31yuKBs8PDwM\nHYIgCCUo
38lXDg4O2eYXenp6Eh0dncsV6V7lXyb/hkVw9Ow1zM0zerJ8vFwYMbA7cnnRVv8JDw/P\n9l7JU25i8kAOp
D9fJzelknNQAefKeaCKufPfDiDZ6eTmVHOum+8q3ULR1kb1eLVk72UAc87r//Vc\nqmUznGw6Ft2zdV7IU6
O5EXEPF88G2OZ/xYtLq4jZncvwX1JmTjImjlYvVfy7MIwfHECRktFTa2p0\nB3vHXnlcUTg5fa+
+bqq6uBAe+ZAHMRm1LA/
+E0alSpXo3DKgWJ5ZFt5XQRBeLflmOgEBAVy7dk3S\ndu3aNSpXrlxsQRnS04Qk5v2xSbLQ1trSjFEDOxd5
YpibrLX60ky8XmgRRap1hyxz4zJoVZWKNzEE\nkBujtuuL2roDWechZpZm7EGqdR67mrwMmQytqjKpMpuiv
W9mCrPsxb+TSnbxgjz5OooUae+8PPWu\nfoW68HLS98buhomxdF7vig372Lo/95ESQRCE10m+2c7IkSMJCQ
lh9uzZ3Lhxgw0bNvDLL78wdOjQ\nkoivxP2xdjex8RkLDGQyGDWwCzZW2YskFwudDmXW5ND0xbbz0iltSLU
KzvGY1qho6hvmSyZDYxVE\nsv1QdHKzbId1inLpZWiKeMi3pKSZ+UheKxIvlNzDdTpU8TtzPKRIym17QKGg
3F2cmTiyd7YEcena\nPew4+I+BohIEQSg5+SaH9erVY8WKFaxfv57AwEC+
+uorPv3009cyOTx9IZzDp6Q9QF1bN6J29Wol\nFoNM8yDLbh6K9J7DF5Rq2Qyd0i5be3EsRsmL1sQjvSZj5
vI5MlX61nSK7Enjq0JjWgtJ4fHUO9lW\nZRcXefJV5OqIHI8pkrNvnSi8uOpulZkw/C1UWXY/WrJ6F3uOnD
FQVIIgCCWjQGOVbdq0oU2bNsUd\ni0E9S0xi0d/bJW1VKtrTo13TEo0j+5CyO8hNXvxGMiPUNh0xfvSHpLm
kk0MAndKWZIeRKJ8dR655\nTKpFADojxxKPo0gpLEgzdkWRcj2jKekCGqOce2yLTB69hgDylGvpq5Zf0R7Z
0sTboyrjh/dk1s+r\nUadmFJFf9PcOFAo5wYElsDhNEATBAMTeyv9ZunaPZDhZLpcxom9HlMqS/SOrzFLCJ
s3U+6XvlWbi\nTZppxvBnmnE1dIpyL32/QpEZobFshtq266ufGP4n83sLJTPvUJH0b7ai5pnnl8q0ScjVt4
o9jrLC\nx6saH73bXbL/MsDCP7dx8MT5XK4SBEF4tYnkEDh78RoHT0rnjHVpFYhrFadcrigesrQnyNWRkrY
X\nnW8ovaGMFLs+qG06o7ZuR4rdwOJfjFKGpJllGVpWRyHTxBbfA3VajLL0GqaZ+qDJ8j0i5h0WrTre\nbn
z8bg9JgqjTwYIVW8QuKoIgvJbKfHKYkJjML39Jh5MrO5Wne9smJR5L1sLXWlXl9H2QC0OmRGPZ\nBI1V8Cs
9x6800ims0KqqStoUScW3MEWRGIpc8yBTiwy1detsc1IVySI5LGp1a7rz4eA3USikCeJP\nSzfxb1iE4QIT
BEEoBmU+OVy2fi+P/7+9Ow+Pqjr/AP692+wzmWSyQjaWhH0TZBEFBDdExb0qtpW6\nVe2mxQXrz/q01qq11
GptrdVqVXCpVQQVFAURkU1lk0XCTliyT5LZ5957fn8MmeTOkgUyySTzfp7H\nR+bMuZMzlzB5c5b3dTaGH/
M8hztuvASS1MH6u50gar/haSwpk64hR5xaFj0JmkliMnQNKyK+9hlg\nUs7J4DDicAyltOl040aW4pdzLwf
PN99rxkIZDlKhnCghJHWkdHC4Zec+rFqnTRZ92XkTMaCoi9K9\ntKT6Ifi0+SQjlwtJ8lGMwzWP+cBBcHJ9
nN6nTnR/HXWKPZh23sk/mkP5K1uOg2YPE2LC6MH4xU2X\na9oOH63Cl1/viHMFIYT0PCkbHIaWkz/StOXnO
rr8dHKT0FJgc21cJjrAxK6tuEE6jonpUHXasoad\nvrTMgqHayS3I5jM1qYqilpZp32HCTDpjCM4ep53Vf/
uD1ZBlqm1NCOkdUjY4fH3xZ6ipa15O5jjg\njhsv7ZblZCB6SVk2DqPDIz2EHHFqWejkU8uiaz04pcVsJCc
haJuh6aMYBmvH4C8LpbQhCXHNrCma\n/YeVNfX4dO3mbhwRIYR0npQMDrfu2o+VX0UuJ0/CwOJuWE4GACZH
JS9WDLTfsKcInVpuJvgPAEpj\nnN4dpPohNazSNAUtk8DENG03Xb6mEk0opc2Rdn0J3n8Qupo3IdV/Aqje0
x9zCsjNysCMs7R5Dt9d\n/iV8/kA3jYgQQjpPygWHHq8f/1z0oaatb44DV1/c9aeTm/D+g+Ba/FBmvBmqvq
iVK0gyYaJDWwEG\nrNNyHkquL8Gpzfk3wekQtE6L7sjxUAylmqb2VEvhgtUwVL0I0fMtpIZPYTyxAHwPX5L
mgtVdUq3m\nqplnQ69rXmmob/TgI6q/TAjpBbpnDbUbvfPRFzGWky+BTpJauSqxok8pD6EKFz2MYhoOvr45
ObXg\n2Q7ZMin+BYxBdK+H4NkKgAN4PRhnAHgDGG84+Wc9xMYvNJcFrecAQuw634phMETPluYxeL9HMO2i\
nVsctNXwCsObZLk6ph6H6JcjmCQjYLwF4favXJxvJuQxSY2imNZh2YdTye2ey2yy4+NzxeO/jr8Jt\nSz5d
j/POPgM2C6WNIoT0XCk1c+hscGPFl9p9QZfMmICSfl1fUi6MMYiUwqbHk40jNY8F/35Accfu\nzBik+uXQ1
b0Hwb8fgn8fBO9OiJ5vIbq+gtSwErr6j6Crey9iRtmIoHVK3DFEzhzywaNAKyltuMBR\nTTDZkujeAOOJv4
D37Y97fbIRXRvDgSEASPWfxv876CSXzpgIq9kYfuz1BbD4k69auYIQQpJfSgWH\nH67aoKmRmmG34tpZ8X/
YdgUdqsApzuYGToKiL+m+AZFTwqQsqFLLijpqVCnEJlLDJ5ogpr2C1qkA\nb4zfQbBA1RVom3x74nbX1S9v
9etxSi0MVf+EVLcUYMEOjfVU8L690Fc+D33Vy+CCFR271n8Iurr3\nIloViJ7EHhIxmwyYfYF2hviTNd+gu
rbz0xkRQkhXSZngsNHtxSdffKNpu+y8id26nAwAFqadmVEM\nJT1uKY+EROY8FLzRtXel+k+j0tK0BxPskC
2T2x5DO6ul8L69Uc8F0y6EKmZFfmVIrjUwnPgr9OxE\nh8bcEYL7axiqXgzNpPp2wVD5j3YfqOGUBuhrXkP
LVFBNRPemUKbqBLpwylg40q3hx8Gggv9+tCah\nX5MQQhIpZYLDZZ9vhM/fPPuRZjVhxuTRrVzRNcxsn+ax
YqDE1z1VZLUUwbcXUD3hx2LDytAevxYY\nb4TfMQd+xw/hz7gGAftlCNouQNA6BbJ5PGTjSMiWs+DLuq1dv
zREB4d7olPaMAZdvbZkpKLvj6B1\nOnw5v0QwRhDKy5XIV9+CvupliA2rQsvNaieczGUMYsMq6GvfBqCGmz
nVA33lv8D7D7ZxvQx99Wtx\nK8LwwePgg+WnP85W6CQJ11yszY+6esM2lJ9I/KEYQghJhJQ4kOL2+LB89de
atktmdP+sISfXQY8q\nAOamFsjGId05JHIamJgDVcxuUf9YgeDdBcU8FmLD6qhlXMYZ4M+8Gaq+MPrFTpGq
KwDjTeBOBqVN\nKW1UfXG4j+D9LmpWLph2ceh0FqdDMH02FOMw6Gv/C06pC/fhwCD4dkHw7Wp6Jai6PlB0R
VD1RVB1\nRWCivf2DZQyS8wNIrtizbBzzwVD1InyZN0E1DIzZR1f3PvjAIe3LcnpwzB9+LLq/RiBiub2zTR
k/\nAks/3YCjFaEqNowBby39HL+
+9eqEfl1CCEmElJg5/GTNN3B7mn9YWM1GXHDOGd04opDIU8qqriju\nSVTSA3AclKhay9shNq6Brv7DiL46
+LM6NzAMvW6slDYt9h0yBVJEkKoYh0WNQzUMhDf3bsjmCa18\nMQV84Agk15fQ1yyE8fhjMBz/E8TGLwHV3
8p1CNWKrn0jRmAYkfidBWCofhm8Nzotj+haD9G9QTsi\nQykCGddo2gTPloTvmRQEAT+4dKqmbePWPSg7cD
TOFYQQkrx6fXDo8wfw4Upt7rFZ08fDoNd104ia\nCREHFqiWcs8nR+479O2CzrlU24nTwZf1k4Tlsmxt36H
o/ga8XNVyMAjES3fDGxDIuAq+zJ+ACRnt\n+tq8XAWdcwmMxx8LBaGxlntVf2h5OuKkNOMM8GXdhqDtAm1/
FoSh+j+ayjO8/yB0de9ru4kO+DNu\ngGIcCsY3/5LFqV4Ink4uaRjD+FGDMLA4T9O2aMkqsATveSSEkM7W6
4PDFV9+i0Z3czoQs0mPC84Z\n240jOkn1hNKdtKBQcNjjMamPpuYxEBEYcBJ8mXOh6vsnbAxRKW0CRwDFdb
JG8wrNc7J5HJjUeg1v\n1TgY3rz7cJi/EYH0KyCbzoh4j9E41QupYSVMx/4IXe1/m08fKy4Yql4IlfdrgQl
W+LJ/CtUwAMG0\n8xBImxX5rqCvfh2CZys4uR766ogDKJwOPsePAMEEcCJks3ZlQHRvanW8nYHjOFx/2bma
tp1lh7F1\nV89JB0QIIUAv33MYCAax9DPtstNFU8fBbDJ004iaiZ6taLkBXxWzwaTM7hsQ6RwcB9k4MnaqG
k46\nuX9uQGLHIFih6vLBB5oPYgi+PeCUhogazSKCtvPb95ocjwCXCdlSAjQl91YaIQQOgfcfguA/dHIf\n
Y+SJYQWiexNE9yYohiHg5CrwsvagBhMd8GXdCiY2z07KtqkAJ0LnbDk7qEJfswhMzACnassT+jOu\nBdM1z
9rJ5nGQWiQQF/z7wMm1mq+RCMNLizFySD9s23Ug3LZw8UoMHlCQFKsVhBDSHr165vCztVtQ\n39CcBNeglz
Bz2vhuHFEIFzwBnVO7B41mDXuPyFrLIQJ8jh9BNXRNDsvIpWXRszkqYA1azurYAZJI\nghWKcTiC9lnw5dw
JT5/5CNqmg8XJxSj4dkUFhqquAN7su2IGbbJ1MgLp10C7D5GBk2u078M2HYpJ\nm4ScSblQddp9lKJbeygt
UW6ImD08fKwKf3npXchydKodQghJRr02OAwGZSz5dL2m7YIpYzXVDLqF\n6g8tibUoWRZaBjuz+8ZEOpUq5
UPVLNUK8Gf+CKpxUNxrOlusfYfR1Vamd+4XFWwIpl0Eb96DCNhn\nt7lPUdGXhFL0tHIIS7acCX/GdYj3Ua
UYBkXvUWy6NuLflOj+GmBqzL6dqV9BLs4+U/vL3pad+/H3\n15bS/kNCSI/Qa4PD1Ru2odbZvPSkk0RcMr2
1k5ddgDHoav8bcSAACNivoCXl3oTj4HfMgaIvgaor\nhi/r5lC97C4USmkT/xehoHVqaH9eIvB6yNbJ8Obd
B7/jxqgZPACQTaPhz5rbvtyN5jHwO+YA0NYb\nV8VM+B03AFzsjzHZNArgmtNVcYoTvH9vx97LKbr52otQn
K/dy7n2m534z/9WUIBICEl6vTI4lGUF\ni1es07SdN3kM0qzmOFd0DdG1FmJE1YwGbihk87huGhFJFCblwp
99K3w5d8bN0ZdQnBC3DCMTbJAt\nZ3fBGHgoppHwZd8FX/adkE2joEp9EEibhUDG9QDX/i3PimkE/Jk/Arj
Qvj3GW+HP/HHr5QR5Q1TN\n6644mAIAJqMe8+
+8DrlZ6Zr2ZZ9/jXeXr+2SMRBCyKnqlcHh2q93oKqmeeO9KPK49LyJ3TgigPcf\njtpnqEp5qOLODSUfJqS
TKcbBMduDthkA34WHIzgOqr4YAccc+HJ/dfKwSce/5xXjEHjy7oc/cy68\nuXe3ecoaiLG07PkOUDxxep8c
ruyEVPf+yVPWla32bY3dZsZDP7se6WnaZfO3P/wCn6z5Js5Vncft\n8WHj1u/x5tLPE/61CCG9S687rayqK
t77RPub+bkTRyHDbo1zRRdQ3NDXvI6WJzkZZ4Df8UOwxrr4\n1xFyGiJT2gChpdgevb9VsHZoiV7V9wMTHS
0OsSgQPd9CtsaeOeUCx2CofgmcEtqSwvsPwpd7d4dm\nOVvKctjx4F3X4ZGnX9Mk4v/32x/DajZh0hmdt91
AlhXsPXQM23bvx7ZdB7D30LFwWekZZ41GluM0\nDh8RQlJKrwsO1327C8crmwMuQeAx+/xJ3TcgpkJf+wY4
xalpDmRcc3KfIQWHJEEEW1RKm2Dahacc\n6PRIHBdKa1P/cbhJdH8dMzjkffuhr34FHPM1t8lV4H37TuswU
WGfbNz/0x/g0WcXIRCUAYTK6/3t\n1fdhMuphOsW/jka3F+XHq3CwvALbvz+AnWWH4fXFrne9bfcBzJg85l
TfAiEkxfSanxKNbi/WbNwe\ndUJ5yvgR3fobs9TwmbZ8GYCgdUpUmTVCEiGQNhOG6lcAFoRsGgMlYg9eKpB
NYyHVf4KmhOR88Bi4\nwFEwXd9wH8GzHfraNwAmR10vercicJonzQf1z8c9t1yJP73wDhQldGJallUsePF/
mHPJJBQVF4Pn\neHAcwPOh3T7cyaV3j9ePoyeqceR4FcqPV+Hw8SqUH69GXb2r3V9/+/cUHBJC2q9HB4eMM
ewsO4yV\nX23Ghq3fIxjU5hHjOODyC7pv1pD37YHU8KmmTdUVIxivXBkhnUw1lMDT5zfgVG8otUwK7m9loh
2K\noVRTRlByb0LgZHAoutZBV7cYUdVsThK8O0JB42nOuI4ZNhB33HgJ/vafJeE2nz+IZ15dhpf+90VU\nf
44LBYiqeuqnm/NzHRg1pD/OG
NE1+TUJIb1DjwwOnQ1urF6/FSvXbcWJqvjLsmefORy5WYmpiMAF\nqyD49wIsXmJbBqnhM7T8gcN4SyglRy
ot65Hux5vA+ASlrekhZPN4TXAoeDYD9lmQGj6PKikIIJQC\nhwVDf1S9EHxlnZKO6Jwzh6PR5cF//vdpm30
ZQ4fT3qRZTRgxuB9GDuqHEYP7de9ea0JIj9VjohSf\nP4Bvtpdh3be78O2OveGlmVh4nsPE0YPx46vaWRqs
g3j/IRgq/454Mw2xcfA7rgcT0xIyJkJIfIpx\nCBhvBqeGKiZxqheGyudPlvxriYc/4yoIgXKIruZ0WIJna
6flqrz43PFocHnw3sdfndbriCKPPjkO\nFORmoV9hLkYM6oeivtnh5WhCCDlVSR0cen1+fPvdXqzfvAtbdu
4Pb+aOJ9uRhulnjca0iSORnpa4\n35ilhpXoWGAIBNMu6LLSaYSQCJwI2XQGJNeacFNUYMhJ8DtuDAWSQoY
2OPTuCM0ktkiqfTp+cMlU\nSKKIj7/4GgG/D6LIg7FQtoXIyUKe55CXlYGCPlnIz81Efl4WCvpkITczHaIo
xP4ChBByGpIuOPT6\n/Pjmu71Y/
+0ubNm1L2ofYSRR5DF+5CBMnzwaw0uLE/9bMwuGlpM7QDEM7fxSZYSQDpHN4zTBYUuM\nN8KfOReqvhjAyR
Q4gjWc0oZjfgje7+PUze44juNw1cyzcdXMs1FWVoaSEu0vjk3LyaqqguO48CEV\nQgjpCkkXHD684FUcPlb
VZr++OQ5MnzwaU8aPgM3SdfupBN+
+8F4kILSPUDaNitufiVmQLeNT8iAA\nIcmE6fKg6gqiZgyZYIcv62ZtUm2Oh2wcCcnVnDNV8G7ttOCwLU2/
5AoCzQwSQrpe0gWHZwwfGDc4\nzHKkYeKYwZg4eggGFOV1y94awbdL81gxDkcwfXaXj4MQ0nGyeSJ0LYJDV
cyGP+sWMDE63ZViGqUJ\nDkXvLgRUf7vqQQM4eaIk2LXVaAghpBMkXXA46YwhWPxJ816fpoBw0pgh6F/YSQ
EhUwEWAHhDB69j\nELyRwWHnVTgghCSWbB4HPngUgvc7KPqBCNgvA4TYKw+qrghMsDcnsGcBCL7dUFpZKWj
C+w9BX/0f\ncKoXgbTzIdtoWwkhpOdIuuCwqG8ORgwuRr+CXEwcPbjzAsKTuGAVDFUvglOckM3jEUi/st1L
vpxc\noa10wklQ9AM6bWyEkATjOATSLwfSL29XX9k0ElJjcw5C0bOt7eBQ9UNfsxCcGkpSrav/GIppFJjo\
nOJ2RE0JIl0m64JDjODz0sxsS9vpSwwpwSig3oujeANk4DKpxcLuujZo11A+gJSNCejHFqA0OBd9u\noI2l
ZalxVUS5TAbBuxOy9ZwEjpQQQjpPah2BYyx0oKQF0f11uy8Xo/Yb0pIyIb2ZqisAE9KbG1gw\nlNYmDi5YD
alhdVR75C+WhBCSzFIqOOSUOnBqo6ZN9O4AVE/bFyse8P5D2iZD+2YcCSE9FMdFZSMQ\nPdvidtc5PwAQnX
5L8B8AVG9nj44QQhIipYJDPnA4RqsC0bO1zWsF/x60THytSrlgYnr8CwghvULk\nHkPB933MQI/37obg2xn
vVSD49iRgdIQQ0vlSKziMmPlr0p6lZcGr/dBXDLSkTEgqUKU+EYdJlOil\nZSZD51wScaX2oBstLRNCeoqU
Cg6FmDOHoTJaXLAi/oVMjfqtX2nnIRZCSA8Xc2lZu9ogNn4JXq5u\neREC9ks0fQTf7lAaLUIISXKpExyyI
PjAsbhPtzZ7yAcOg2uxL5HxRqi6wk4dHiEkecnGyKXlvYAS\n+kzglAboGj7V9jePh2yZBMYbw22c6omztY
UQQpJLygSHfOAoYm0UbyJ6vgVY7OejUtgYBgEclbUi\nJFUwKReqmN2iRYHo/Q4AIDk/DCXVb+rLGxFIuwj
gxNBnRQu0tEwI6QlSJziMPGlsHAbGNecq45RG\nCL6ymNcKvt3aa2m/ISGpheOgmEZqmgTPVvD+gxA9mzXt
QduFgGAGEP1ZEf/ACiGEJI+UCQ4j9xsq\n+gHRpxBjLC1zch344PGWLVGzAYSQ3i9y36Hg3wtd7TuaNlXKg
2yZEH4c+qxo/pjlgxXg5NqEjpMQ\nQk5XagSHjIEPaGcOVX0RZPM4TZvo3RHeR9QkctZQ1RXFrcVKCOm9mJ
QDVcpr2QJertT0Cdhna7ec\nCCYo+mJNn8jMB4QQkmxSIjjklHpwSkOLBgmqlAdVVxSVokL0ak8hCl5tcCh
TVRRCUlbk0nJLsmk0\nVEP/6Gsil5Zp3yEhJMl1ODhcsGAB7HY77r333kSMJyGiZg11fQFODKWoiJw9bLm0
rAYg+Pdqnqeq\nKISkrshTy2GcDsG0i2M+pRiHah4L/v2A6uvsoRFCSKfpUHC4adMmvPLKKxg2bFiixpMQv
D9iv2GL\nNDSy6Qy0TFYbynl4AgAg+PcBLBh+jgl2MCk3sYMlhCQtJmVClfpGtQdt54KJ9tjXiJnRSbTjHH
4j\nhJBk0O7gsL6+Hrfeeiv+9re/wW6P/SGYrISomcOi8J+ZmA5FP1DzfNPsYfQp5cEAp616QAhJLZEH\nU
5joQNA6Nf4FHAfZEDF76KOlZUJI8mp3cPirX/0Ks2fPxpQpUxI5ns7H5JM5Dpup+iLNY9k8VvNY\ndG8GmB
yd35D2GxKS8mTLeDAhLfSAk+BPvyq0TaUVkZ8dgncXVUshhCSt1j/RTvrPf/6D/fv344UX\nXmj3C5eVJce
yiZ4dR4HafBhFhhUH91cAaC6XxzED+qlB8GhKZOtGzZ634WDNQSWDiP1eBsZ1/vtK\nlnvV29B97Xx0T0N4
NhsmHIYfmQgeYQDauC9MQX9VBg//yQY3ysu+hI8LnX5O9vtaUlLS3UMghHSh\nNoPDsrIy/O53v8Py5cshS
VK7XzhZPkzExhPQOc3hx7JxOEoyo8emqz0bontD+LEZ2wE0X6cYBmNg\n1tCo605XWVlZ0tyr3oTua+ejex
ppeId662rGamoy97e6EbSX0H0lhCSdNpeVN27ciJqaGkycOBEO\nhwMOhwNr167Fiy+
+CIfDAb/f39ZLdKvIyiiRS8pNIpeWI0vt0ZIyIeR0RFdL2R2nJyGEdK82Zw5n\nzZqFMWPGaNruuusuDBgw
APfccw90Ol3CBtcZIiujtDyMEtmuipng5eqYz1MKG0LI6Qh9hnAAGACA\nDx4HJ9e1eg0n14GT66DqCwCu/
Ss3hBByOtoMDu12e9TpZJPJhPT0dAwd2vnLrJ2JUxrAKc4WLQJU\nXZ84nTko5rHg6z+OekqVcsHE9MQMkh
CSGgQTVH0ReP/B5ibvLgBZ0X2ZCqlhBaSGlQAYVH0xfFm3\nUoBICOkSvbpCStSSclPy6zhk01i0zHnYJHI
5iBBCTkW7UtqoHuirX4bU8BnCs4z+g5AaVnfBCAkh\npJ2nlSN9+OGHnT2OhIisjKLEWVJuwkQ7FP1ACH7t
yUHFSEvKhJDTpxiHAPUfhR8Lvr3g2MTwYy5w\nHIaaV8HJNVHXSo0rIZtGg0mZXTJWQkjq6tUzh1H7DfWFc
Xo2iyynx3gjVF3b1xFCSFuYmB1VLcWE\n0OeU4NkKY+VzMQPD0MUydM4lAGOJHyghJKX13uAwVvLrNmYOAU
AxDYcqZocfy5azAE7o9OERQlIQ\nx0GO2KZiYfsgOT+AvmYhwAKa55ig3e8t+HZD8O5I+DAJIamt1waHfPB
4RF1kW3NVg9ZwEvxZcNd5\nigAAIABJREFUtyCYdiH8GdcgaJuRwFESQlJNZFosK9sFqfGLqH6yeQK8efdC
0ffTtOucSwA1uVOI\nEUJ6tt4bHEYdRilqd11kJtoRtM2AYj6zzbJYhBDSEaq+Hxinb6WHgED6VQhkXAVwE
gLpV6DlRzWn\nOE8eViGEkMTovcFhxH5DhfYNEkKSASdCNZTGfIoJafBl3wHZMqG5TcpF0Hq2pp/UuAZc8E
RCh0kI\nSV29NjgU/JGHUdreb0gIIV1BNkbniFX0/eHN+UXMg3NB2/kR22IU6OoW0+EUQkhC9M7gUGkEp9S
2\naBBCOQ4JISQJKKaRmoNvQcvZ8GfdAgjW2BfwegTsl2maBP9+CJ7NrX8h1Qcu4mAeIYS0pVduqIsu\nmd
eHKgsQQpIHJ8GXcxcE3x4c9npRlD6xzUsU43AohkEQfN+H23TOD+A1DgF4o7az6ofo+gpS42qA\n08Gbdx/
tnyaEtFvPmjlkQUj1H0NX+zZ4/4G43Xg/7TckhCQ53gjFNAoBztF2XwDgOATsszVBHqe6\noGtZ8pMFITZ+
AePxJ6CrXwZO9YBTnBDdmzp58ISQ3qxH/Sqpq1sC0b0BACC6v0HQdi6CtvOj8hBG\nVkah/YaEkN6ASZkIW
qdBavg03Ca61kE2jQYfKIfUuAqc0hh1ndSwMpTgn1ZQCCHt0GOCQ06ui/jt\nl0FqWAnBtx9+x/VgYvrJZg
VCoFxzLVU4IYT0FkHbuRA9m1tUUmEwVP49bn/GGSCbxwNMjVU6nhBC\novSYZWXRtRaAGtXOBw7CUPE0BO9
3ABBK79CiygDjrWBCelcNkxBCEouT4LfPbkc/HYK26fD2eQDB\ntPMBvrXcioQQ0qxnzByqXkiu9XGf5lQv
9NWvImiZDCZmaC/VF7Q7+TUhhPQEqnEwFOMICN7t0U9y\nEoKWyQhapwKCuesHRwjp8XpEcCi6NkbNBqq6P
ppTewAgudYict1EaUc9ZUII6WkC9kth8O8Fp3pD\nDZyIoHkSgrZp8VPiEEJIOyR/cMhkSK4vNU2y9SwErd
MhNn4BXf1yAErLCzR9VQoOCSG9EBPt8GXd\nBsn1FZiQBtkyEUywdfewCCG9QNIHh4JnGzilvrmBkxA0TwI
4DrJtKlR9P+hrFoJT6mJczVPya0JI\nr8V0fRHIuKa7h0EI6WWS+0AKY6Ekri3I5jMBwRR+rOoL4c39FWTj
yKjLVSmXNmETQgghhHRAUgeH\nvH8v+ODxFi0cgpazY3Q0IuCYg0D6lZo8XrJlcuIHSQghhBDSiyT1srLU+
IXmsWIcDiZlxu7McZAt\nE6EYSiB4toNJ2VAMQ7pglIQQQgghvUfSBodc4HjUaeSgdWqb1zHRAdk2LUGjSk
2HXUH8fXc9nAEV\nM/JMmF1ohk7oeHogxhj8KoNBSOoJa0IIISSlJW1wKLnWaB6rumKoeqp00tVcQRVPbK9
DtT+UgPyd\nQy6sqfDiJyU2jHa0bz+nT1GxvNyDj8o9aJRVTMkxYm6JlYJEQgghJAklZXDIyfUQ3Zs1bUHb
lG4a\nTepijOGf39eHA8MmFT4Ff9xehwmZevx4oA0OgxDzer/C8MkxD5YcdqMh2Pwan5/w4oAriHuHpyMr\
nzrWEEEII6R5JGRyKrq/QMnehKmZCMQztvgGlqBXHvNhY7Y/7/IZqP7bWVePqYgtm9jVB5ENLzQGF\n4bPj
Hiw+7IYzEF3yEAAOuWT85psa/GqYHUPtuoSMnxBCCCEdl3zBoeqH6NaWypOt5wAcLUF2pYOu\nIF7d16BpS
9fxcAZUTZpxn8Lw+r5GfHHCix8PtOKYR8F7h12o9ccOCluqD6p4dGst5g604fy+pjb7\nE0IIISTxki44FN
0bm8tBAWC8CbJpbDeOKPX4FBV/3eFEi5VgGAUOj4zJgEdmeHFPA/Y1BjXXHHbL\n+P3WWInIQwwCh4vzTTj
qlrGhxWykwoAXyxpwyB3ETQNt4dlHQgghhHSP5AoOmQKpUXsQRbacBfC0\n7NiV/l3WiGNeRdN2a6kNucbQ
t8ujZ2Tgs2NevHGgEW6ZxXqJMD3P4aJ8Ey4pMMMm8WCM4d1Dbrx9\n0KXpt+KYF0fdCn41zI40Hc0SE0III
d0lqX4KC97t4BRncwMnImg5q/sGlIK+OOHF6hNeTdu5uUZM\nzjGGH/Mch/P7mrBgfCam5Bhivo6OB2blm/
DsxCzc0N8KmxT6VuM4DlcVW/DrYXYYItLh7KwP4MFv\nqnEwYlaSEEIIIV0neWYOGYtKei2bxgKCpZsGlHq
OeWS8VKbdZ5hvEnFTiTVmf7tOwF1D7Dg3L4CX\n9jSg3CND5IDz+4RyIabr459EHp9lQI5RwFPfOVHpa56l
rPar+L/NNZiVb8YlBWZYpKT6/YUQQgjp\n9ZIoOAxClXLBB46j6aRy0Erpa7pKUGX4604nfErzMrGOB34xN
K3NfIRD7To8daYD5R4FGXoeZrF9\nAV2RRcIfxjrw1x1OfOcMhNsDKvDeYTc+PurBrAIzZuab2v2aXSWoMv
gUBovIgeM6tk9SZQxbav1Y\nccyLsvoAhth1uGtI2/c52QUUBolHh+8HIYSQ5JI8wSGvQyDjWgTTLoLYuBa
c0gAmZXX3qFLGwn2N\nOOiSNW0/HmhDkUWKc4UWx3EoMHf828km8Zg/Mh2v7WvE8qMezXMeheG/B11YVu7G
JQVmXNTXBGMX\nBIkBheGYR0a1X0GtX0VdQEHdyf/X+lXU+RU0ntxrma7jMS5Tj3EOA4bada1WjnH6Faw87
sWnxz2o\naXGae2O1Hxn7XZhbYkv4e0sExhjeOODCB0fckHgOE7IMmJpjxFC7RIEiIYT0QMkTHJ7EBBuC9p
nd\nPYyU8nW1D8siArOJWQbMyDPGuaJziTyHuSU29LdKWLivEfVBbRocl8zw5gEXPir34NICMy7sa4L+\nF
Mr3RZJVhqMeGeVuGUfcMso9of9XeBW0fsymWV1AxYpjXqw45oVB4DAqXYexmQac4dDDevIAzg5n\nACuOeb
Gp2gclzguvOObBzHxT+NBPT8EYw6v7GvFReej7R1EYVp/ct5plEDA1x4gpuQbk9LD3RQgh\nqYw+sVMYYwx
rK314aY92n2GWQcBtg2xdPuszNdeICVl6fHzUg6WH3eHZuSYNQRUL9zfigyNuXNvP\nghl5xg6P0aeoWHzI
jU3VfhzzylDbGwW267UZNlT7saHaDw7A4DQJ9QE16uR3LAoD3tzvwq+G2Ttv\nQF3g7YOucGAYqcqn4J1DL
rxzyIWhaTpMzTVgQpahS2Z/CSGEnDoKDlNUfUDFS3vqNTkHAUDggF8O\nTeu2PX4GgcfsQgvO72PC8nIPPi
h3R6XLqQ+q+NeeBqyv8uGOQWlxy/dF2ukM4B+76zUHYE4Vh9C9\nipfJhwHYVR//1LWOBwal6bC9rnmv5bo
qH2Y1BFBi6xmpm94/7MK7h9zt6ruzPoCd9QH8u6wRVxWb\ncVmBmZacCSEkSVFwmII2Vfvwr+8bopZvAeC6
ftakCE5MIo8riy24MN+ED4+48VG5B96INdntdQHM\n21SNm0psmJJjiBtsBBSGNw+Elj7bO1GYYxCQZxKQr
hOQoeeRrhOQfvL/GXoeaToeshoKOL+u8eHr\naj/q4pQKbKmvScB5fUyYkmOEWeTw4Lc12N/YvNdz0T4XHh
6dnvSB0ydHPVi0X5ur0iJy+NFAG7bW\n+rGp2odYt8OvMiza74LIcZhVYO6i0RJCCOkICg5TiFtW8XJZA9Z
U+KKek3jg+n5WXJyfXGXszCKP\na/tZMTPfjA+OuLGs3AN/i7Vgj8Lw99312Fjlw62lNtgj0ufsawjiud1O
HPXEni106HkUmEXkm0UU\nmiXkm0T0NQvtOjmsE4DRDj1GO/S4uYRhf6OMb2p82FTtx2F3c8AncsD4TAPO6
2OKOqQxp79VU1lm\nZ30Am2v9OMMRO39kMlh9whuV8sggcJg/Mh0DbTpMzTXCLatYX+nD6hNefN8QPYO6cH
8jStOkpPhF\nhBBCiBbndDo7cdcV6aiysjKUlJQk/OtsqfXjn9/Xx6x5PMAq4c7Bacg/hdPGXa3Kp+D53fW
a1DdN\nrCKHm0vTMCnbgF17yrBNysXiw+6Y+wpn9jXh6mJLwvIoVvkU7HQGwAEYmaGDXRd/6fuP22qxpbb5
\n/eSbRDw5zgEhyUoJlpWVodZegL/scGpmYHU8MH9kBobaYwd6xzwyvjjhxfKj2tnfTD2Px8dlwpri\nuSy
76jOAEELai4LDbpbIHwyMMRx2y/j4qAefHfdGPS9wwFVFFswuNPeomsaMMSw/6sGi/Y0xly4n\nZRmw63g1
nGJ0AvUsg4CfDrJheLq+C0baPodcQdz/dY0m4PrpIBvOzWt7FrfcLWN9lQ9FFhHjHPqE\nLkcv2VKGt+qtm
n2WIgfcOzwdox1t38+NVT78eYdT0zbWoce9w+1Jv4yeSBQcEkKSTfJPFZEOkVWG\n3fUBfFPjx9fV/riHLw
rNIu4anIZia/vyGCYTjuMwM9+MURl6/H13Pcoili3XVfng9nOInAidnmfE\nDwdYYUqy07JFFglTco2asoV
vHXDhrGxjqyl71lR48fzu+nCwdmEfE+aWWDsUaDHG8M5BNz4+6gbH\ncbDr+PAey5Z7Lf0Kw8vHeOhaxKsc
gF8MtbcrMARCVXFm5ZvwYYvTzd/U+PHByRRFhBBCkgMFh72A\nW1axtTYUDG6p9Ued7m2JA3BZoRnXFFsg9
aDZwlj6mET8bkwGlh5x4+0Drrgnh9N1PG4flIYx7Qxi\nusO1xRZ8VelF0xmhuoCKj8rduKIoevaTsVBy8P
9FnBT+
+JgHPpXh9lJbu5akAyf3a66ratqDytAQ\nVHE4zgHkIANaLhzfMTgNE7I6tjfyhv5WfF8fxN4W9bMX7W9Eq
U3CoDTaf0gIIcmAgsMezBlQ8Pq+\nRqyr9MUNjFrqYxRw55C0XnUIgOc4zC60YPTJWcTIKi9nZxtwU4kt6f
e1ZRoEzOxrxpIjzZHZ+4fd\nmJ5nQpqueewBheH57+uxtjL6UBEQOiwSUBh+NiSt1a0CjUEVf/6urtV0O62
5ucSGqbkdT5Iu8hx+\nNcyOB76uhuvkN63KgL/udOLxcZmwJfnfEyGEpAL6JO6BGAtVofj1xmqsqWg9MJR4
4AyHHrcPsuGJ\ncZm9KjBsqcgi4Q9nOHBNsQV2HY88HcPdQ+34+VB70geGTWYXmmERmwM6r8Lw3qHmdDH1A
RW/31ob\nNzBssu7k3r5AnHIsVT4Fj2yuPeXA8Ib+FlzQ99RPtWcZBNw5OE3TVuNX8dwuJxijLdCEENLd6E
BK\nN+voZvRKr4wX9jRokidHskk8xjj0GOfQY2SGrl1pWXoTxhj27t3bIzf5f3DEjdf2NYYfixzw5/GZ\nC
KrAE9vrUBWxh9Qm8fjRQCve2N+oqdcMAMPtOtw7wq75+z/YGMQft9fBGXGSJ98k4udD0qAwNNeQ\njqwp7X
Ti2qF9TiswbOm1fQ344Ii2usr1/Sy4PMZSem9GB1IIIcmGlpV7CJUxLCv34K0DLk2evya5\nRgFnZhowLlO
PUpsEPoVPf/bkk68X9jVh+VFPOAiUGfDcrnqUu2V4ImYC800i7hthR45RxJA0HX6/\ntRYnWpTq+84ZwB+2
1uGBkekwizy21vqxYIcTvojXGZIm4dfD01vMsMY+pFRWVoeSTgoMgVBezbL6\noCYP4psHXChN08VNi0MII
STxhAceeOCR7h5EqtpS48fyww2oUHWoCygIKICO56CLOKF6xC3jqe+c\nWHXCi8iVQh0PXN/fip8NTsNohx
6ZBqFHB0edpba2Fg6Ho7uH0WECx8Eq8djYoqxhjV9FMOLvfUS6\nDg+OSkf6yaTfJpHHxCwDttYG0NCi8k2
NP3RYSVZDh08ii+JMyjLgnmHp7TrB3dn3lOc4jEzX44sT\nXk1Kom21fkzIMnRbCceu1lO/VwkhvRctK3eT
ZeVuvLK3EW63G2azNo2HReSQbRSQYxBhEDisqfDG\n3Fc43K7DrYNsyDXSBHCknrxUxxjDA9/URB2uaXJen
hFzS2wxD5w0BlU8tq1WU5Ivnln5JvxwQPtT\n3yTqnm6p8eOP2+s0bQIHTMo2YFa+Gf07Od0SYwwN
QQabxCXFL1I9+XuVENI7UVTRDdZX+vCfvY1x\nn3fJDK5GOe4PeLPI4cYBVpyba0yKH26kc3Echzn9rfjDN
m3AxAG4cYAVs/JNcf/erRKPh0Zl4Ilt\ndTHL1jW9zg8HWJOmtvFohx6XF5qxuEUOHYUBX1b48GWFD0PSJM
wqMGOsQ39a2yW8sopVJ7xYXu5B\nhU9BH6OAHw20JXWKI0II6Q4UHHaxnc4A/rZbW36sI87M1OPmElt4OZH
0TiMz9Bjr0OObmtDyskHg\n8PMhaRiX2XZeQbPI48FR6XjqO2fUwSWJB+4abMek7OSq3XxtsQUHXUFNGcEm
u+qD2FXvRI5BwMx8\nE6blGmHswJJzlU/BsnI3Vh33avZtHvMqeHx7HSZk6vHjgTY4DPRvihBCgHYsKy9Ys
ABLly7F3r17\nodPpMG7cOPz2t7/F0KFDu2qMvcYRt4zfbq7RJKn2ut24ZGAm6gIqKrwyKn1K1L4wAEiTeP
ykxIYJ\nWYktkdZb9IalOp+i4v3DbriCDBflm9DX1LHf5QIKw193OvH1yQDTInKYNzwdQ07xsEei76miMnx
2\n3Itl5W4c88au7AMAJoHDiHQd8s0iCswSCswico1C1DL7nvoAPir3YH2Vr81fxgwCh6uLLZjZ19Tl\npS
R7w/cqIaR3aTM4vPLKK3HllVfijDPOAGMMjz32GDZt2oQNGzYgPT29q8bZ49X4FPzf5pqodCOX\nWRoxZ1z
zDwbGGGr9Kip8Ciq9Mip8CowCj3PzjD0mX18yoB+4ISpjWFPhQ61fwZQc42nNjnXVPWWM\nYXOtHx8d8WC7
M37KppZELlQxJ98kIs8kYFtdIKqsYnsUmkXcXGrD4C6s1kLfq4SQZNPhAykulwuF\nhYVYuHAhZs6cmahx9
SpuWcUjm2tx2K3dQ3hdPwuGB47TD4YEoB+4na877ukhVxAflXvwZZxDWR2V\nJvE4v48JQ+wS3tjv0pTxa2
larhE39LdqqtMkCn2vEkKSTYf3HLpcLqiqCrvdnojx9DpBleGp7c6o\nwPCCPiZcXmjG3r3dNDBCeoAii4Q
7Bqfh+v4WrDjqxYpjHtTH2nfRhgKTiFkFJkzONoZTRf3+DB1W\nHvdi0f7GqHrkn5/w4ptqH2b0MWFqrhF9
OrikTwghPVmHZw5vuukm7Nu3D59//jkEIf4SVVlZ2WkP\nrqdjDHj1OIctLu0ephEWhpvyGLp4axMhPZ7Mg
HIfUBEAjvs5HA8AFX6gXon9j2mIiWFqOkOpCYi3\nVdclA0uqOWxqiP8PstjAcKaNYYwVMKbguRWa2SQktX
QoOHzwwQfx7rvvYvny5SguLk7gsHqHV/c2\n4MNybXmwQTYJD43KCM9e0JJSYtB97XzJfE9dQRXlHhnlbhn
HPDLMIo8JWQbkm9s/47fTGcBLexpQ\n7omfI1LigfGZBkzJNWJkuq5TKhEl830lhKSmdn9yzp8/H+++
+y6WLl1KgWEExhiqfArKPTKOuEP/\nHXbLOBSRxLivScC9I9KjKqAQQk6PReIxOE13WgdJhtp1eGKcAx+Wu
/HuIXdUmUEACKrA2kof1lb6\nkK7jMSnbgJHpegyxS11Ww5wxhoMuGdvq/NhWG8AhVxBpOgFn5xhwbq4Rdk
pzRQg5Te0KDu+//368\n9957WLp0KUpLSxM9pqSnqAwbqn3YWhvAEbeMox455g+SltJ1POaPzKATx4QkMZH
nMLvQggv6mLCx\n2o/Pj3uxsz72iem6gIqPyj34qNwDkQMGp+kwIl2HkRl69LOInZpyqsanYHudH9vqAthe
py2RCACN\nsow3D7jw34MujM804Lw+Rgyz6yjtFSHklLQZHM6bNw9vvfUWXn/9ddjtdlRUVAAAzGYzLBZLw
geY\nTFTGsK7Sh3cOulrNwxbJKHB4YEQ6sijJLiE9glHkMTXXiKm5RlR6ZXxR4cPqE15U+mL/u5cZ8J0z\n
gO+cAbxxwAWryGFEuh4DbRJUAEGFIaCG/guqgF9l4baaGg4OX13M12UAKrxKq0vdLSkMWFflw7oq\nH/oYB
ZzXx4QpuZQGixDSMW3uOYx3Kvn++
+/H/PnzEzKoZMMYw4YqP9456MKRdn5INym2iLil1IYS\nW+zlLtpvlBh0Xztfqt9Txhh21Qex+oQX66t8ba
4WtFes+uqdSccDZ2UbcfsgW6fskSSE9H5tzhw6\nnc6uGEdSYozhmxo/3j7oito/GMkscigwh5LwFpjFcPW
GrsiTRghJPI7jMNSuw1C7DnNLrNhWG1ri\n3Vbnx4kOrCR0BpPAYXi6DiPT9ShNk7DDGcCnxzw46okeR0AF
av0KBYaEkHaj5F0xMMawpTaAtw82\nYn9j7KCQ54CpOUZMzDagyCzCruNpfw8hKcIg8BifZcD4rFCN6gqvH
AoUa/34zhmIypt4ungOKLFK\nGJmhx8h0HQZYJQgtcmEVWSTM7GvCTmcQK455sLHah5YTm+f3MXXqeAghvR
sFhxEYY/jH9w1YfcIb\n83kOwNk5BlxVZEEeJcYlhADIMYrIMYo4r48Jisqw3xXEd3UB1PpVSDyg4znoeA6
SwJ38MyDxHCSe\nw7HyRhQUxC8qoOM5DLBJMIutr0JwHIdh6ToMS9fB6Vew6oQXnx33QlYZxjr0nf2WCSG9
GEU3EZYf\n9cQMDDkAk7IMuKrY0qHcaYSQ1CLwHEpsurj7jCOVOYGSTEOnjsGuF3BFkQWzC82o9CmaWUZCC
GkL\nRTktHHIF8fq+xqj2CZl6XFVsQZFF6oZREULIqeE5DrlG+pgnhHQMfWqcFFAYntlZj5ZbhUwCh4dG\n
ZWCAjYJCQgghhKQGOkp70mv7GqNyid1SaqPAkBBCCCEphYJDAF9X+/DJMW0N5Ck5BkzOMXbTiAgh\nhBBCu
kfKB4d1fgXP767XtOUYBPykxNZNIyKEEEII6T69Zs9hUGXYWuvHukofdtYHkGMIndYblRE/\nhQNjDM/trk
dji42GAgf8YmgajG2kjSCEEEII6Y16dHAoqwzf1QXwVZUPX1f7NIlna/0qdm2rw4h0\nHW7sb0WxNXrv4Af
lHmyvC2jarim2YGA7U1AQQgghhPQ2SRccOv0KyhqDkHhtstiWSWQPNgaxrsqH\nTVU+zaxfLNvrArj/mxqc
nWPAdf2syDIIAIADjUG8uV+btmZomg6zCxNX45QQQgghJNklXXC4tzGI\np77r/HrOX1b4sL7Shwv7mjAr3
4xndjo1aWssIoefDUmj+qOEEEIISWlJFxwG1FOvSZom8ZiQZcBQ\nuw6fHvPgO6d2yVhmwIflHnxU7kHkV7
ltUBocJ2cVCSGEEEJSVdIFh0G1Y/2tIoczswyYlGXAMLsu\nXCZqYpYeW2sDWLi/EYfd2vyFkYHh9DwjJmR
1bvkqQgghhJCeKOmCw3Qdj7EOPQIqQ1Blof8roRnF\npjaJ5zAyQ4+zsgwYnq6DGKNuKMdxGO3QY2SGDmsq
fHjrQCNq/NGRZx+jgB8PtHbFWyOEEEIISXpJ\nFxyOzNBjZCvpZzqK5zhMzTViUpYBy4668f5hd/hUs8gBv
xhqh0GgtDWEEEIIIUASBoeJohM4zC60\nYHqeCSuOenDCp2BGnhH9YqS4IYQQQghJVSkTHDaxSjyuLLZ09z
AIIYQQQpISracSQgghhJAwCg4J\nIYQQQkgYBYeEEEIIISSMgkNCCCGEEBJGwSEhhBBCCAmj4JAQQgghhIR
xTqfz1IsZE0IIIYSQXoVm\nDgkhhBBCSBgFh4QQQgghJIyCQ0IIIYQQEkbBISGEEEIICaPgkBBCCCGEhFFw
eJrWrl2L6667DkOG\nDIHdbsfChQs1z1dWVuKOO+7A4MGDkZeXh6uuugr79u0LP3/o0CHY7faY/z3zzDPhf
n6/H/feey/6\n9+
+PPn364LrrrsPRo0e77H12tdO9rwBQUVGB2267DaWlpcjLy8PkyZPx9ttva/o4nU7cdtttKCws\nRGFhIW6
77TY4nc6Ev7/u0Bn39MCBA5gzZw4GDBiAgoIC3HTTTaisrNT0SaV7umDBApx77rkoKCjA\ngAED8IMf/AA7
d+7U9GGM4Y9//CMGDx6M3NxczJo1C7t27dL0ac8927FjBy6+
+GLk5uZiyJAheOKJ\nJ8AYJZsghHQ+Cg5Pk9vtxtChQ/H444/DaDRqnmOMYc6cOdi/fz8WLlyIL774AgUFB
Zg9ezbcbjcA\nID8/H99//73mvz//
+c/gOA6XXXZZ+LXmz5+PpUuX4qWXXsJHH32ExsZG/OAHP4CiKF36frvK6d5X\nAPjpT3+KPXv2YNGiRVi3b
h2uu+463H777Vi7dm24zy233IJt27bhnXfewTvvvINt27bh9ttv77L3\n2ZVO95663W5cccUVYIxhyZIlWL
58OQKBAK677jqoqhp+rVS6p19+
+SVuvvlmfPzxx1iyZAlEUcTl\nl1+Ourq6cJ+//vWveO655/DEE09g5cqVyMrKwhVXXIHGxsZwn7buWUNDA
6644gpkZ2dj5cqVePzx\nx/Hss8/ib3/7W5e+X0JIaqA8h52ob9+
+ePLJJzFnzhwAwN69ezFu3DisWbMGI0aMAACoqorS0lI8\n/PDD+NGPfhTzdS6//HJwHIf33nsPAFBfX4+B
Awfiueeew7XXXgsAKC8vx4gRI/DOO+9gxowZXfDu\nus+p3te+ffviiSeewI033hh+reHDh+P222/Hz3/+c
3z//feYMGECli9fjokTJwIA1q1bh5kzZ2LT\npk0oKSnp4nfadU7lnq5cuRJXXXUVDhw4ALvdDiD0vVlcXI
z33nsP06ZNS+l7CgAulwuFhYVYuHAh\nZs6cCcYYBg8ejFtvvRXz5s0DAHi9XpSUlOD3v/895s6d26579tJ
LL+GRRx7Bnj17woH9n/70J/z7\n3//Gzp07wXFct71nQkjvQzOHCeT3+wEABoMh3MbzPPR6PdatWxfzmoMH
D2L16tW46abOu7EJAAAJ\n8ElEQVSbwm1btmxBMBjE9OnTw235+fkYNGgQNmzYkJjBJ7H23teJEydi8eLFq
K2thaqq+PDDD1FT\nU4OpU6cCADZu3AiLxYIJEyZorjGbzSl3X9tzT/1+PziOg16vD/cxGAzgeT7cJ9Xvqc
vlgqqq4eD5\n0KFDqKio0PzbNRqNOOuss8L3oz33bOPGjZg0aZJmxnfGjBk4fvw4Dh061BVvjRCSQig4TKD
S0lLk\n5+fjd7/7Herq6hAIBPD000/j6NGjqKioiHnNq6+
+iszMTFx88cXhtsrKSgiCAIfDoemblZUVtd8r\nFbT3vr788svgOA79+/dHdnY2brvtNrz44osYOXIkgNB9
dTgcmlkXjuOQmZmZcve1Pff0zDPPhMVi\nwcMPPwy32w23242HHnoIiqKE+6T6PX3ggQcwYsQIjB8/HgDC9
yUrK0vTr+W/3fbcs8rKypiv0fQc\nIYR0JgoOE0iSJLz+
+us4cOAA+vXrh7y8PKxZswbnn38+eD761suyjIULF+L666+HJEndMOKeob33\n9dFHH0VNTQ3ef/99rFq1C
j//
+c9xxx13YPv27d04+uTUnnuamZmJV155BStWrEB+fj4KCwtRX1+P\nUaNGxfx+TjUPPvgg1q9fj9deew2CI
HT3cAgh5JSJ3T2A3m706NH48ssvUV9fj2AwiMzMTMyYMQNj\nxoyJ6rts2TJUVFRE7UXMzs6GoiioqalBZm
ZmuL2qqgqTJk1K+HtIRm3d1wMHDuCFF17Q7KEbMWIE\n1q1bhxdeeAHPPvsssrOzUVNTA8ZYeNaGMYbq6mp
kZ2d323vrLu35Xp0+fTq2bNmCmpoaCIIAu92O\n0tJSFBcXA0DK3tP58+fj3XffxdKlS8P3AgBycnIAhP6t
FhQUhNurqqrC96M99yw7OxtVVVWar9n0\nuDffV0JI96Bf97tIWloaMjMzsW/fPmzevFmzbNzk1VdfxeTJk
zFw4EBN+
+jRoyFJElatWhVuO3r0\naHgjeyqLd189Hg8ARM3gCIIQPlk7fvx4uFwubNy4Mfz8xo0b4Xa7U/q+tud71e
FwwG63Y/Xq1aiq\nqsLMmTMBpOY9vf/+
+/G///0PS5YsQWlpqea5oqIi5OTkaP7t+nw+rFu3Lnw/2nPPxo8fj3Xr1sHn\n84X7rFq1Cnl5eSgqKkrk2
yOEpCCaOTxNLpcL+/fvBxA63VleXo5t27YhPT0dBQUFWLx4MTIyMlBY\nWIgdO3bggQcewKxZszQb1AHgyJ
Ej+Oyzz/D8889HfY20tDT88Ic/xG9/+1tkZWUhPT0dv/nNbzBs\n2DBMmzatK95mlzvd+1paWor+/fvj17/
+NR599FFkZGTggw8+wKpVq7Bo0SIAwKBBg3Deeefh7rvv\nxtNPPw0AuPvuu3HhhRf2ylO1nfG9+vrrr6O0
tBRZWVnYuHEjHnjgAdx5553h+5Vq93TevHl46623\n8Prrr8Nut4f3GJrNZlgsFnAchzvuuAMLFixASUkJB
g4ciKeeegpmsxlXX301gPbds6uvvhpPPPEE\n7rzzTsybNw979+7F008/jfvuu49OKhNCOh2lsjlNa9aswa
WXXhrVfv311+Mf//gHnn/
+eTz77LOo\nrKxETk4OrrvuOtx3333Q6XSa/o899hheeOEF7N69W3NitInf78dDDz2Ed955Bz6fD1OmTMGf
//xn\n5OfnJ+y9dafOuK/79u3DI488gvXr18PtdqNfv3646667cMMNN4T7OJ1O3HfffVi2bBkAYObMmXjy\
nySfDp017k864p4888ggWLVqEuro6FBYWYu7cubjrrrs0AUoq3dN47+n++
+/H/PnzAYSWiB9//HG8\n8sorcDqdGDt2LJ566ikMHTo03L8992zHjh2YN28evv32W9jtdsydOxf3338/BY
eEkE5HwSEhhBBC\nCAmjPYeEEEIIISSMgkNCCCGEEBJGwSEhhBBCCAmj4JAQQgghhIRRcEgIIYQQQsIoOCS
EEEIIIWEU\nHBJCCCGEkDAKDklKuvTSS9GvXz9UV1dHPedyuTB8+HBMnjwZsix3w+gIIYSQ7kPBIUlJTz/9
NLxe\nLx588MGo5x577DEcO3YMzzzzDESRKkwSQghJLRQckpQ0YMAAzJs3D2+//TZWrVoVbt+6dSv+
+c9/\n4pZbbsHYsWO7bDwej6fLvhYhhBDSGgoOScr65S9/iaFDh+Luu+
+G1+uFqqq45557kJubi//7v/8L\n92uqezts2DBkZ2djzJgx+Mtf/gJVVTWvt2DBAlxwwQXo378/cnJyMHn
yZCxatCjq65aWluKGG27A\np59+imnTpiEnJwf//Oc/E/5+CSGEkPag2sokpW3cuBEXXXQRfvnLX6Jv376Y
N28eFi1ahIsvvhhA\naP/h+eefj8rKSsydOxd9+/bFxo0b8eabb+KWW27Bn/70p/BrDRgwAJdffjkGDRoER
VHwwQcfYO3a\ntXjuuecwZ86ccL/S0lJYrVZUV1fjJz/5CYqKilBcXIxp06Z19dsnhBBColBwSFLevHnz8M
orr8Bo\nNOLcc8/Fq6+
+Gn7uD3/4A/7xj39gzZo16NevX7j90UcfxYIFC7B582YUFRUBCC0Nm0ymcB/GGGbN\nmoW6ujqsW7cu3F5a
WorKykq8+
+67mD59ehe8Q0IIIaT9aFmZpLyHH34YDocDjDE8+eSTmucWL16M\nyZMnw2azoaamJvzftGnToKoq1q5dG+
7bFBgGg0HU1dWhtrYW55xzDnbv3g2fz6d53f79+1NgSAgh\nJCnRUUyS8mw2GwYOHIjKykrk5uaG2xlj2Ld
vH8rKyjBgwICY17ZMhbN48WIsWLAAO3bsgKIomn6N\njY0wGAzhx8XFxZ37JgghhJBOQsEhIXEwFtpxcd55
5+FnP/tZzD79+/cHAKxevRo33XQTzjnnHDz9\n9NPIzc2FJEn48MMP8a9//Svq8ErLQJEQQghJJhQcEhIHz
/MoLCyE2+1u87DI4sWLYbPZ8O6770KS\npHD7ihUrEjxKQgghpHPRnkNCWnHllVdi3bp1WL16ddRz9fX1CA
aDAABBEABAs5xcXV2NN998s2sG\nSgghhHQSmjkkpBX33HMPPvnkE1x99dW44YYbMGrUKLjdbuzcuRNLliz
Bt99+i5ycHFx00UV48cUX\nceWVV+Lqq69GbW0tXn75ZfTp0wc1NTXd/TYIIYSQdqPgkJBWWCwWLFu2DAsW
LMDixYvxxhtvwGq1\nYuDAgXjggQeQnp4OILQv8ZlnnsEzzzyD+fPnIz8/H7/4xS8gSRLuueeebn4XhBBCS
PtRnkNCCCGE\nEBJGew4JIYQQQkgYBYeEEEIIISSMgkNCCCGEEBJGwSEhhBBCCAmj4JAQQgghhIRRcEgIIY
QQQsIo\nOCSEEEIIIWEUHBJCCCGEkDAKDgkhhBBCSBgFh4QQQgghJOz/AXuzynNXK3ZnAAAAAElFTkSuQmC
C\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc4c13f05f8>"
]
},
"metadata": {},
}
],
"source": [
"canada = Table.read_table('canada.csv')\n",
"murder_rates_with_canada = average_murder_rates.join(\"Year\",
canada.select(\"Year\", \"Homicide\").relabeled(\"Homicide\", \"Canada\"))\n",
"murder_rates_with_canada.plot('Year')"
]
},
{
"metadata": {},
"source": [
"The line plot we generated above is similar to a figure from the [paper]
(http://users.nber.org/~jwolfers/papers/DeathPenalty%28SLR%29.pdf).\n",
"\n",
"<img src=\"paper_plot.png\"/>\n",
"\n",
"Canada has not executed a criminal since 1962. Since 1967, the only crime that
can be punished by execution in Canada is the murder of on-duty law enforcement
personnel. The paper states, \"The most striking finding is that the homicide rate
in Canada has moved in\n",
"virtual lockstep with the rate in the United States.\""
]
},
{
"metadata": {},
"source": [
"**Question 5.3.** Complete their argument in 2-3 sentences; what features of
these plots indicate that the death penalty is not an important factor in
determining the murder rate? (If you're stuck, read the [paper]
(http://users.nber.org/~jwolfers/papers/DeathPenalty%28SLR%29.pdf).)"
]
},
{
"metadata": {
},
"source": [
"We cannot attribute the increases to U.S. homicide rates between 1972-76 to
the abolition of the death penalty; prior to the abolishment, murder rates had been
steadily increasing for about 9 years (1963-1972) both in the U.S. and Canada.
After the death penalty was reestablished in the U.S. until 2001, we see U.S.
murder rates slowly decrease overtime with spikes around 1982 and 1992. In Canada,
although they abolished the death penalty much earlier in 1967, murder rates also
follow the same general trend: a decrease in this time period with spikes around
1982 and 1992. Murder rates seem to follow a similar trend across differnt
countries, unrelated to whether or not the region had the death penalty estabished
as law."
]
},
{
"metadata": {
},
"source": [
"**Conclusion**. The authors that created this visualization argue that even
though murder rates increased when the death penalty was taken away, and decreased
when it was reintroduced, these changes were probably not caused by the death
penalty itself. Based on your analysis, what conclusion can you make? Address the
steps you took throughout the project in your answer as well."
]
},
{
"metadata": {},
"source": [
"The plot shows that neither the abolishment nor the institution of the death
penalty is the direct cause for changes in murder rates. Evidence from the project
also supports this. Firstly, variables such as location and time prevent us from
assuming causation. Although we controlled for differences among states by using a
natural experiment, our study was limited to the United States, and did not account
for trends in other countries. Moreover, trend lines in groups of U.S. states with
and without the death penalty follow the same pattern, further emphasizing possible
confounding factors that could have an effect on murder rates other than the death
penalty. There does not seem to be a causal relationship between increases and
decreases to murder rates and whether or not a state has the death penalty.\n"
]
},
{
"metadata": {},
"source": [
"**You're done! Congratulations.**"
]
},
{
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
],
"text/plain": [
]
},
"metadata": {},
}
],
"source": [
"# Submit the project!\n",
"_ = ok.submit()"
]
},
{
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": [
"Running all tests...\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 2\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"Running tests\n",
"\n",
"---------------------------------------------------------------------\n",
"Test summary\n",
" Passed: 1\n",
" Failed: 0\n",
"\n",
"Finished running all tests.\n"
]
},
{
"data": {
"image/png":
27cvQ4cOZd+
QYbH3bp1Y//
T+vbty+
bgYGB9OrVix9+
36P7f/vjjDz7+
mDNnDvHx//
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc4c12eb978>"
]
},
"metadata": {},
},
{
"data": {
"image/png":
27cvQ4cOZd+
QYbH3bp1Y//
T+vbty+
bgYGB9OrVix9+
36P7f/vjjDz7+
mDNnDvHx//
"text/plain": [
"<matplotlib.figure.Figure at 0x7fc4c1302ef0>"
]
},
"metadata": {},
}
],
"source": [
"# For your convenience, you can run this cell to run all the tests at
once!\n",
"import os\n",
"print(\"Running all tests...\")\n",
"_ = [ok.grade(q[:-3]) for q in os.listdir(\"tests\") if q.startswith('q')]\n",
"print(\"Finished running all tests.\")"
]
},
{
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.1"
}
},
"nbformat": 4,
"nbformat_minor": 1
}

Lab 01 Datascience

Hochgeladen von

Dokumentinformationen

Copyright

Verfügbare Formate

Dieses Dokument teilen

Dokument teilen oder einbetten

Freigabeoptionen

Stufen Sie dieses Dokument als nützlich ein?

Sind diese Inhalte unangemessen?

Copyright:

Verfügbare Formate

Lab 01 Datascience

Hochgeladen von

Copyright:

Verfügbare Formate

{

Das könnte Ihnen auch gefallen