Skip to content

Instantly share code, notes, and snippets.

@psychemedia

psychemedia/apacheDrill_hansard.ipynb

Last active June 13, 2017 14:07
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save psychemedia/a53bb6816f38e69ae5a5c7c9404e3ee9 to your computer and use it in GitHub Desktop.
Save psychemedia/a53bb6816f38e69ae5a5c7c9404e3ee9 to your computer and use it in GitHub Desktop.
Download ZIP
Example of Using Apache Drill to query Hansard data
Display the source blob
Display the rendered blob
Raw
apacheDrill_hansard.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Apache Drill - Hansard Demo\n",
"\n",
"Download and install Apache Drill.\n",
"Start Apache Drill in the Apache Drill directory: `bin/drill-embedded`\n",
"\n",
"Tweak the settings as per [Querying Large CSV Files With Apache Drill](https://blog.ouseful.info/2017/06/03/querying-large-csv-files-with-apache-drill/) so you can query against column names."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Download data file\n",
"!wget -P /Users/ajh59/Documents/parlidata/ https://zenodo.org/record/579712/files/senti_post_v2.csv"
]
},
{
"cell_type": "code",
"execution_count": 114,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: pydrill in /usr/local/lib/python3.6/site-packages\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.6/site-packages (from pydrill)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/site-packages (from requests->pydrill)\n",
"Requirement already satisfied: urllib3<1.22,>=1.21.1 in /usr/local/lib/python3.6/site-packages (from requests->pydrill)\n",
"Requirement already satisfied: idna<2.6,>=2.5 in /usr/local/lib/python3.6/site-packages (from requests->pydrill)\n",
"Requirement already satisfied: chardet<3.1.0,>=3.0.2 in /usr/local/lib/python3.6/site-packages (from requests->pydrill)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.6/site-packages\n",
"Requirement already satisfied: pytz>=2011k in /usr/local/lib/python3.6/site-packages (from pandas)\n",
"Requirement already satisfied: numpy>=1.7.0 in /usr/local/lib/python3.6/site-packages (from pandas)\n",
"Requirement already satisfied: python-dateutil>=2 in /usr/local/lib/python3.6/site-packages (from pandas)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.6/site-packages (from python-dateutil>=2->pandas)\n",
"Requirement already satisfied: matplotlib in /usr/local/lib/python3.6/site-packages\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.6/site-packages (from matplotlib)\n",
"Requirement already satisfied: six>=1.10 in /usr/local/lib/python3.6/site-packages (from matplotlib)\n",
"Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=1.5.6 in /usr/local/lib/python3.6/site-packages (from matplotlib)\n",
"Requirement already satisfied: numpy>=1.7.1 in /usr/local/lib/python3.6/site-packages (from matplotlib)\n",
"Requirement already satisfied: python-dateutil in /usr/local/lib/python3.6/site-packages (from matplotlib)\n",
"Requirement already satisfied: pytz in /usr/local/lib/python3.6/site-packages (from matplotlib)\n"
]
}
],
"source": [
"#Install some dependencies\n",
"!pip3 install pydrill\n",
"!pip3 install pandas\n",
"!pip3 install matplotlib"
]
},
{
"cell_type": "code",
"execution_count": 139,
"metadata": {},
"outputs": [],
"source": [
"#Import necessary packages\n",
"import pandas as pd\n",
"from pydrill.client import PyDrill\n",
"\n",
"#Set the notebooks up for inline plotting\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Get a connection to the Apache Drill server\n",
"drill = PyDrill(host='localhost', port=8047)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Make things faster\n",
"\n",
"We can get a speed up on querying the CSV file by converting it to the `parquet` format.\n",
"\n",
"In the Apache Drill terminal, run something like the following (change the path to the CSV file as required):\n",
"\n",
"``CREATE TABLE dfs.tmp.`/senti_post_v2.parquet` AS SELECT * FROM dfs.`/Users/ajh59/Documents/parlidata/senti_post_v2.csv`;``\n",
"\n",
"(Running the command from the notebook suffers a timeout?)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>afinn_sd</th>\n",
" <th>afinn_sentiment</th>\n",
" <th>age</th>\n",
" <th>as_speaker</th>\n",
" <th>date_of_birth</th>\n",
" <th>dods_id</th>\n",
" <th>gender</th>\n",
" <th>government</th>\n",
" <th>hansard_membership_id</th>\n",
" <th>house_end_date</th>\n",
" <th>...</th>\n",
" <th>pims_id</th>\n",
" <th>proper_name</th>\n",
" <th>sentiword_sd</th>\n",
" <th>sentiword_sentiment</th>\n",
" <th>speakerid</th>\n",
" <th>speech</th>\n",
" <th>speech_date</th>\n",
" <th>time</th>\n",
" <th>url</th>\n",
" <th>word_count</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>NA</td>\n",
" <td>0</td>\n",
" <td>61</td>\n",
" <td>FALSE</td>\n",
" <td>1955-08-11</td>\n",
" <td>25175</td>\n",
" <td>Female</td>\n",
" <td>Opposition</td>\n",
" <td>NA</td>\n",
" <td>NA</td>\n",
" <td>...</td>\n",
" <td>943</td>\n",
" <td>Sylvia Hermon</td>\n",
" <td>NA</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>rose—</td>\n",
" <td>2017-03-21</td>\n",
" <td>13:58:00</td>\n",
" <td></td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.8788192423620312</td>\n",
" <td>0.6074156578823847</td>\n",
" <td>61</td>\n",
" <td>FALSE</td>\n",
" <td>1955-08-11</td>\n",
" <td>25175</td>\n",
" <td>Female</td>\n",
" <td>Opposition</td>\n",
" <td>NA</td>\n",
" <td>NA</td>\n",
" <td>...</td>\n",
" <td>943</td>\n",
" <td>Sylvia Hermon</td>\n",
" <td>0.156473588352448</td>\n",
" <td>0.06187180921605654</td>\n",
" <td>NA</td>\n",
" <td>There is a competition going on here over who ...</td>\n",
" <td>2017-03-21</td>\n",
" <td>13:58:00</td>\n",
" <td></td>\n",
" <td>119</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.7491414925035998</td>\n",
" <td>-0.15584597470090075</td>\n",
" <td>61</td>\n",
" <td>FALSE</td>\n",
" <td>1955-08-11</td>\n",
" <td>25175</td>\n",
" <td>Female</td>\n",
" <td>Opposition</td>\n",
" <td>NA</td>\n",
" <td>NA</td>\n",
" <td>...</td>\n",
" <td>943</td>\n",
" <td>Sylvia Hermon</td>\n",
" <td>0.26867964867304406</td>\n",
" <td>-0.03330528415064781</td>\n",
" <td>NA</td>\n",
" <td>The Minister is commenting on the need to work...</td>\n",
" <td>2017-03-21</td>\n",
" <td>13:58:00</td>\n",
" <td></td>\n",
" <td>85</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3 rows × 33 columns</p>\n",
"</div>"
],
"text/plain": [
" afinn_sd afinn_sentiment age as_speaker date_of_birth \\\n",
"0 NA 0 61 FALSE 1955-08-11 \n",
"1 0.8788192423620312 0.6074156578823847 61 FALSE 1955-08-11 \n",
"2 0.7491414925035998 -0.15584597470090075 61 FALSE 1955-08-11 \n",
"\n",
" dods_id gender government hansard_membership_id house_end_date ... \\\n",
"0 25175 Female Opposition NA NA ... \n",
"1 25175 Female Opposition NA NA ... \n",
"2 25175 Female Opposition NA NA ... \n",
"\n",
" pims_id proper_name sentiword_sd sentiword_sentiment speakerid \\\n",
"0 943 Sylvia Hermon NA 0 NA \n",
"1 943 Sylvia Hermon 0.156473588352448 0.06187180921605654 NA \n",
"2 943 Sylvia Hermon 0.26867964867304406 -0.03330528415064781 NA \n",
"\n",
" speech speech_date time \\\n",
"0 rose— 2017-03-21 13:58:00 \n",
"1 There is a competition going on here over who ... 2017-03-21 13:58:00 \n",
"2 The Minister is commenting on the need to work... 2017-03-21 13:58:00 \n",
"\n",
" url word_count \n",
"0 1 \n",
"1 119 \n",
"2 85 \n",
"\n",
"[3 rows x 33 columns]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Test the setup\n",
"drill.query(''' SELECT * from dfs.tmp.`/senti_post_v2.parquet` LIMIT 3''').to_dataframe()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The Hansard data gives the date of each speech but not the session. To search for speeches within a particular session, we need the session dates. We can get these from the Parliament data API."
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>uri</th>\n",
" <th>display name</th>\n",
" <th>end date</th>\n",
" <th>parliament &gt; parliament number</th>\n",
" <th>session number</th>\n",
" <th>start date</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>http://data.parliament.uk/resources/377309</td>\n",
" <td>2005-2006</td>\n",
" <td>2006-11-08</td>\n",
" <td>54</td>\n",
" <td>1</td>\n",
" <td>2005-05-11</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>http://data.parliament.uk/resources/377310</td>\n",
" <td>2006-2007</td>\n",
" <td>2007-10-30</td>\n",
" <td>54</td>\n",
" <td>2</td>\n",
" <td>2006-11-15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>http://data.parliament.uk/resources/377311</td>\n",
" <td>2007-2008</td>\n",
" <td>2008-11-26</td>\n",
" <td>54</td>\n",
" <td>3</td>\n",
" <td>2007-11-06</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>http://data.parliament.uk/resources/377312</td>\n",
" <td>2008-2009</td>\n",
" <td>2009-11-12</td>\n",
" <td>54</td>\n",
" <td>4</td>\n",
" <td>2008-12-03</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>http://data.parliament.uk/resources/377313</td>\n",
" <td>2009-2010</td>\n",
" <td>2010-04-12</td>\n",
" <td>54</td>\n",
" <td>5</td>\n",
" <td>2009-11-18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>http://data.parliament.uk/resources/377314</td>\n",
" <td>2010-2012</td>\n",
" <td>2012-05-01</td>\n",
" <td>55</td>\n",
" <td>1</td>\n",
" <td>2010-05-18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>http://data.parliament.uk/resources/377315</td>\n",
" <td>2012-2013</td>\n",
" <td>2013-04-30</td>\n",
" <td>55</td>\n",
" <td>2</td>\n",
" <td>2012-05-09</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>http://data.parliament.uk/resources/377316</td>\n",
" <td>2013-2014</td>\n",
" <td>2014-05-14</td>\n",
" <td>55</td>\n",
" <td>3</td>\n",
" <td>2013-05-08</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>http://data.parliament.uk/resources/377317</td>\n",
" <td>2014-2015</td>\n",
" <td>2015-03-30</td>\n",
" <td>55</td>\n",
" <td>4</td>\n",
" <td>2014-06-04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>http://data.parliament.uk/resources/377318</td>\n",
" <td>2015-2016</td>\n",
" <td>2016-05-15</td>\n",
" <td>56</td>\n",
" <td>1</td>\n",
" <td>2015-05-18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>http://data.parliament.uk/resources/519398</td>\n",
" <td>2016-2017</td>\n",
" <td>2017-05-03</td>\n",
" <td>56</td>\n",
" <td>2</td>\n",
" <td>2016-05-18</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" uri display name end date \\\n",
"0 http://data.parliament.uk/resources/377309 2005-2006 2006-11-08 \n",
"1 http://data.parliament.uk/resources/377310 2006-2007 2007-10-30 \n",
"2 http://data.parliament.uk/resources/377311 2007-2008 2008-11-26 \n",
"3 http://data.parliament.uk/resources/377312 2008-2009 2009-11-12 \n",
"4 http://data.parliament.uk/resources/377313 2009-2010 2010-04-12 \n",
"5 http://data.parliament.uk/resources/377314 2010-2012 2012-05-01 \n",
"6 http://data.parliament.uk/resources/377315 2012-2013 2013-04-30 \n",
"7 http://data.parliament.uk/resources/377316 2013-2014 2014-05-14 \n",
"8 http://data.parliament.uk/resources/377317 2014-2015 2015-03-30 \n",
"9 http://data.parliament.uk/resources/377318 2015-2016 2016-05-15 \n",
"10 http://data.parliament.uk/resources/519398 2016-2017 2017-05-03 \n",
"\n",
" parliament > parliament number session number start date \n",
"0 54 1 2005-05-11 \n",
"1 54 2 2006-11-15 \n",
"2 54 3 2007-11-06 \n",
"3 54 4 2008-12-03 \n",
"4 54 5 2009-11-18 \n",
"5 55 1 2010-05-18 \n",
"6 55 2 2012-05-09 \n",
"7 55 3 2013-05-08 \n",
"8 55 4 2014-06-04 \n",
"9 56 1 2015-05-18 \n",
"10 56 2 2016-05-18 "
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Get Parliament session dates from Parliament API\n",
"psd=pd.read_csv('http://lda.data.parliament.uk/sessions.csv?_view=Sessions&_pageSize=50')\n",
"psd"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('2015-05-18', '2016-05-15')"
]
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def getParliamentDate(session):\n",
" start=psd[psd['display name']==session]['start date'].iloc[0]\n",
" end=psd[psd['display name']==session]['end date'].iloc[0]\n",
" return start, end\n",
"\n",
"getParliamentDate('2015-2016')"
]
},
{
"cell_type": "code",
"execution_count": 140,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['afinn_sd', 'afinn_sentiment', 'age', 'as_speaker', 'date_of_birth', 'dods_id', 'gender', 'government', 'hansard_membership_id', 'house_end_date', 'house_start_date', 'hu_sd', 'hu_sentiment', 'id', 'jockers_sd', 'jockers_sentiment', 'ministry', 'mnis_id', 'nrc_sd', 'nrc_sentiment', 'party', 'party_group', 'person_id', 'pims_id', 'proper_name', 'sentiword_sd', 'sentiword_sentiment', 'speakerid', 'speech', 'speech_date', 'time', 'url', 'word_count']\n"
]
},
{
"data": {
"text/plain": [
"afinn_sd NA\n",
"afinn_sentiment 0\n",
"age 61\n",
"as_speaker FALSE\n",
"date_of_birth 1955-08-11\n",
"dods_id 25175\n",
"gender Female\n",
"government Opposition\n",
"hansard_membership_id NA\n",
"house_end_date NA\n",
"house_start_date 2001-06-07\n",
"hu_sd NA\n",
"hu_sentiment 0\n",
"id uk.org.publicwhip/debate/2017-03-21b.801.1\n",
"jockers_sd NA\n",
"jockers_sentiment 0\n",
"ministry May\n",
"mnis_id 1437\n",
"nrc_sd NA\n",
"nrc_sentiment 0\n",
"party Independent\n",
"party_group Other\n",
"person_id 10958\n",
"pims_id 943\n",
"proper_name Sylvia Hermon\n",
"sentiword_sd NA\n",
"sentiword_sentiment 0\n",
"speakerid NA\n",
"speech rose—\n",
"speech_date 2017-03-21\n",
"time 13:58:00\n",
"url \n",
"word_count 1\n",
"Name: 0, dtype: object"
]
},
"execution_count": 140,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Check the columns in the Hansard dataset, along with example values\n",
"df=drill.query(''' SELECT * from dfs.tmp.`/senti_post_v2.parquet` LIMIT 1''').to_dataframe()\n",
"print(df.columns.tolist())\n",
"df.iloc[0]"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>number</th>\n",
" <th>proper_name</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2967</td>\n",
" <td>Nick Brown</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4062</td>\n",
" <td>Nigel Spearing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>908</td>\n",
" <td>Gerald Malone</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>544</td>\n",
" <td>Michael Grylls</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>258</td>\n",
" <td>Vernon Booth</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" number proper_name\n",
"0 2967 Nick Brown\n",
"1 4062 Nigel Spearing\n",
"2 908 Gerald Malone\n",
"3 544 Michael Grylls\n",
"4 258 Vernon Booth"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Example of count of speeches by person in the dataset as a whole\n",
"q='''\n",
"SELECT proper_name, COUNT(*) AS number \n",
"FROM dfs.tmp.`/senti_post_v2.parquet`\n",
"GROUP BY proper_name\n",
"'''\n",
"\n",
"df=drill.query(q).to_dataframe()\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Number of Speeches</th>\n",
" <th>gender</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>294552</td>\n",
" <td>Female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1939677</td>\n",
" <td>Male</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Number of Speeches gender\n",
"0 294552 Female\n",
"1 1939677 Male"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Example of count of speeches by gender in the dataset as a whole\n",
"q=\"SELECT gender, count(*) AS `Number of Speeches` FROM dfs.tmp.`/senti_post_v2.parquet` GROUP BY gender\"\n",
"drill.query(q).to_dataframe()"
]
},
{
"cell_type": "code",
"execution_count": 71,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Number of Speeches</th>\n",
" <th>gender</th>\n",
" <th>session</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>18319</td>\n",
" <td>Female</td>\n",
" <td>2015-2016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>52974</td>\n",
" <td>Male</td>\n",
" <td>2015-2016</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Number of Speeches gender session\n",
"0 18319 Female 2015-2016\n",
"1 52974 Male 2015-2016"
]
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Query within session\n",
"session='2015-2016'\n",
"\n",
"start,end=getParliamentDate(session)\n",
"q='''\n",
"SELECT '{session}' AS session, gender, count(*) AS `Number of Speeches`\n",
"FROM dfs.tmp.`/senti_post_v2.parquet`\n",
"WHERE speech_date>='{start}' AND speech_date<='{end}'\n",
"GROUP BY gender\n",
"'''.format(session=session, start=start, end=end)\n",
"\n",
"drill.query(q).to_dataframe()"
]
},
{
"cell_type": "code",
"execution_count": 85,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Number of Speeches</th>\n",
" <th>gender</th>\n",
" <th>mnis_id</th>\n",
" <th>session</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>137</td>\n",
" <td>Female</td>\n",
" <td>1437</td>\n",
" <td>2015-2016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>35</td>\n",
" <td>Male</td>\n",
" <td>650</td>\n",
" <td>2015-2016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>23</td>\n",
" <td>Female</td>\n",
" <td>4409</td>\n",
" <td>2015-2016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>32</td>\n",
" <td>Female</td>\n",
" <td>4422</td>\n",
" <td>2015-2016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>35</td>\n",
" <td>Male</td>\n",
" <td>4059</td>\n",
" <td>2015-2016</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Number of Speeches gender mnis_id session\n",
"0 137 Female 1437 2015-2016\n",
"1 35 Male 650 2015-2016\n",
"2 23 Female 4409 2015-2016\n",
"3 32 Female 4422 2015-2016\n",
"4 35 Male 4059 2015-2016"
]
},
"execution_count": 85,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Count number of speeches per person\n",
"start,end=getParliamentDate(session)\n",
"q='''\n",
"SELECT '{session}' AS session, gender, mnis_id, count(*) AS `Number of Speeches`\n",
"FROM dfs.tmp.`/senti_post_v2.parquet`\n",
"WHERE speech_date>='{start}' AND speech_date<='{end}'\n",
"GROUP BY mnis_id, gender\n",
"'''.format(session=session, start=start, end=end)\n",
"\n",
"drill.query(q).to_dataframe().head()"
]
},
{
"cell_type": "code",
"execution_count": 143,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>average</th>\n",
" <th>gender</th>\n",
" <th>session</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>96.41578947368421</td>\n",
" <td>Female</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>117.72</td>\n",
" <td>Male</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" average gender session\n",
"0 96.41578947368421 Female 2016-2017\n",
"1 117.72 Male 2016-2017"
]
},
"execution_count": 143,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Example of finding the average number of speeches per person by gender in a particular session\n",
"q='''\n",
"SELECT AVG(gcount) AS average, gender, session\n",
"FROM (SELECT '{session}' AS session, gender, mnis_id, count(*) AS gcount\n",
" FROM dfs.tmp.`/senti_post_v2.parquet`\n",
" WHERE speech_date>='{start}' AND speech_date<='{end}'\n",
" GROUP BY mnis_id, gender)\n",
"GROUP BY gender, session\n",
"'''.format(session=session, start=start, end=end)\n",
"\n",
"drill.query(q).to_dataframe()\n",
"\n",
"#Note - the average is returned as a string not a numeric"
]
},
{
"cell_type": "code",
"execution_count": 129,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>average</th>\n",
" <th>gender</th>\n",
" <th>session</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>86.153846</td>\n",
" <td>Female</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>96.222717</td>\n",
" <td>Male</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" average gender session\n",
"0 86.153846 Female 2016-2017\n",
"1 96.222717 Male 2016-2017"
]
},
"execution_count": 129,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#We can package that query up in a Python function\n",
"def avBySession(session):\n",
" start,end=getParliamentDate(session)\n",
" q='''SELECT AVG(gcount) AS average, gender, session FROM (SELECT '{session}' AS session, gender, mnis_id, count(*) AS gcount\n",
"FROM dfs.tmp.`/senti_post_v2.parquet`\n",
"WHERE speech_date>='{start}' AND speech_date<='{end}'\n",
"GROUP BY mnis_id, gender) GROUP BY gender, session\n",
"'''.format(session=session, start=start, end=end)\n",
" dq=drill.query(q).to_dataframe()\n",
" #Make the average a numeric type...\n",
" dq['average']=dq['average'].astype(float)\n",
" return dq\n",
"\n",
"avBySession(session)"
]
},
{
"cell_type": "code",
"execution_count": 146,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>average</th>\n",
" <th>gender</th>\n",
" <th>session</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>135.100000</td>\n",
" <td>Male</td>\n",
" <td>2005-2006</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>114.837398</td>\n",
" <td>Female</td>\n",
" <td>2005-2006</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>94.674556</td>\n",
" <td>Male</td>\n",
" <td>2006-2007</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>85.080645</td>\n",
" <td>Female</td>\n",
" <td>2006-2007</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>112.407045</td>\n",
" <td>Male</td>\n",
" <td>2007-2008</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" average gender session\n",
"0 135.100000 Male 2005-2006\n",
"1 114.837398 Female 2005-2006\n",
"2 94.674556 Male 2006-2007\n",
"3 85.080645 Female 2006-2007\n",
"4 112.407045 Male 2007-2008"
]
},
"execution_count": 146,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Loop through sessions and create a dataframe containing gender based averages for each one\n",
"overall=pd.DataFrame()\n",
"for session in psd['display name']:\n",
" overall=pd.concat([overall,avBySession(session)])\n",
"\n",
"#Tidy up the index\n",
"overall=overall.reset_index(drop=True)\n",
"\n",
"overall.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The data is currently in a long (tidy) format. To make it easier to plot, we can reshape it (unmelt it) by casting it into a wide format, with one row per session and and the gender averages arranged by column."
]
},
{
"cell_type": "code",
"execution_count": 147,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>gender</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" </tr>\n",
" <tr>\n",
" <th>session</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2005-2006</th>\n",
" <td>114.837398</td>\n",
" <td>135.100000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2006-2007</th>\n",
" <td>85.080645</td>\n",
" <td>94.674556</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-2008</th>\n",
" <td>106.231405</td>\n",
" <td>112.407045</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-2009</th>\n",
" <td>83.491803</td>\n",
" <td>94.362550</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-2010</th>\n",
" <td>40.939130</td>\n",
" <td>49.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2010-2012</th>\n",
" <td>181.833333</td>\n",
" <td>236.386139</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2012-2013</th>\n",
" <td>83.358621</td>\n",
" <td>103.818913</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-2014</th>\n",
" <td>99.455172</td>\n",
" <td>113.828283</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2014-2015</th>\n",
" <td>77.568493</td>\n",
" <td>84.784990</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-2016</th>\n",
" <td>96.415789</td>\n",
" <td>117.720000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2016-2017</th>\n",
" <td>86.153846</td>\n",
" <td>96.222717</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"gender Female Male\n",
"session \n",
"2005-2006 114.837398 135.100000\n",
"2006-2007 85.080645 94.674556\n",
"2007-2008 106.231405 112.407045\n",
"2008-2009 83.491803 94.362550\n",
"2009-2010 40.939130 49.500000\n",
"2010-2012 181.833333 236.386139\n",
"2012-2013 83.358621 103.818913\n",
"2013-2014 99.455172 113.828283\n",
"2014-2015 77.568493 84.784990\n",
"2015-2016 96.415789 117.720000\n",
"2016-2017 86.153846 96.222717"
]
},
"execution_count": 147,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Reshape the dataset\n",
"overall_wide = overall.pivot(index='session', columns='gender')\n",
"#Flatten the column names\n",
"overall_wide.columns = overall_wide.columns.get_level_values(1)\n",
"overall_wide"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now we can plot the data - the session axis should sort in an appropriate way (alphanumerically)."
]
},
{
"cell_type": "code",
"execution_count": 137,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAawAAAD8CAYAAAArMZDvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n3sXn1zYAAAAASUVORK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x14797f898>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"overall_wide.plot(kind='barh');"
]
},
{
"cell_type": "code",
"execution_count": 138,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAZMAAAEKCAYAAADXdbjqAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngiAozP8AtHcfVsFni2UAAAAASUVORK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x137e72208>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"overall_wide.plot();"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can generalise the approach to look at a count of split by party."
]
},
{
"cell_type": "code",
"execution_count": 150,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>average</th>\n",
" <th>party</th>\n",
" <th>session</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>45.25</td>\n",
" <td>Independent</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>129.25</td>\n",
" <td>Democratic Unionist Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>78.76923076923077</td>\n",
" <td>Labour</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>19.0</td>\n",
" <td>SNP</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>135.3684210526316</td>\n",
" <td>Conservative</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>55.0</td>\n",
" <td>UKIP</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>79.5</td>\n",
" <td>Labour (Co-op)</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>108.05555555555556</td>\n",
" <td>Scottish National Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>117.25</td>\n",
" <td>Liberal Democrat</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>85.0</td>\n",
" <td>Ulster Unionist Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>128.66666666666666</td>\n",
" <td>Social Democratic &amp; Labour Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>101.66666666666667</td>\n",
" <td>Plaid Cymru</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>176.0</td>\n",
" <td>Green Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" average party session\n",
"0 45.25 Independent 2016-2017\n",
"1 129.25 Democratic Unionist Party 2016-2017\n",
"2 78.76923076923077 Labour 2016-2017\n",
"3 19.0 SNP 2016-2017\n",
"4 135.3684210526316 Conservative 2016-2017\n",
"5 55.0 UKIP 2016-2017\n",
"6 79.5 Labour (Co-op) 2016-2017\n",
"7 108.05555555555556 Scottish National Party 2016-2017\n",
"8 117.25 Liberal Democrat 2016-2017\n",
"9 85.0 Ulster Unionist Party 2016-2017\n",
"10 128.66666666666666 Social Democratic & Labour Party 2016-2017\n",
"11 101.66666666666667 Plaid Cymru 2016-2017\n",
"12 176.0 Green Party 2016-2017"
]
},
"execution_count": 150,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Example of finding the average number of speeches per person by party in a particular session\n",
"# Simply tweak the query we used for gender...\n",
"q='''\n",
"SELECT AVG(gcount) AS average, party, session\n",
"FROM (SELECT '{session}' AS session, party, mnis_id, count(*) AS gcount\n",
" FROM dfs.tmp.`/senti_post_v2.parquet`\n",
" WHERE speech_date>='{start}' AND speech_date<='{end}'\n",
" GROUP BY mnis_id, party)\n",
"GROUP BY party, session\n",
"'''.format(session=session, start=start, end=end)\n",
"\n",
"drill.query(q).to_dataframe()\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Make a function out of that, as we did before."
]
},
{
"cell_type": "code",
"execution_count": 157,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>average</th>\n",
" <th>party</th>\n",
" <th>session</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>26.800000</td>\n",
" <td>Independent</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>114.404908</td>\n",
" <td>Conservative</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>27.000000</td>\n",
" <td>UKIP</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>61.786408</td>\n",
" <td>Labour</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>100.907407</td>\n",
" <td>Scottish National Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>70.925926</td>\n",
" <td>Labour (Co-op)</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>115.000000</td>\n",
" <td>Plaid Cymru</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>87.777778</td>\n",
" <td>Liberal Democrat</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>88.666667</td>\n",
" <td>Social Democratic &amp; Labour Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>80.000000</td>\n",
" <td>Ulster Unionist Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>94.000000</td>\n",
" <td>Democratic Unionist Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>142.000000</td>\n",
" <td>Green Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" average party session\n",
"0 26.800000 Independent 2016-2017\n",
"1 114.404908 Conservative 2016-2017\n",
"2 27.000000 UKIP 2016-2017\n",
"3 61.786408 Labour 2016-2017\n",
"4 100.907407 Scottish National Party 2016-2017\n",
"5 70.925926 Labour (Co-op) 2016-2017\n",
"6 115.000000 Plaid Cymru 2016-2017\n",
"7 87.777778 Liberal Democrat 2016-2017\n",
"8 88.666667 Social Democratic & Labour Party 2016-2017\n",
"9 80.000000 Ulster Unionist Party 2016-2017\n",
"10 94.000000 Democratic Unionist Party 2016-2017\n",
"11 142.000000 Green Party 2016-2017"
]
},
"execution_count": 157,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def avByType(session,typ):\n",
" start,end=getParliamentDate(session)\n",
" q='''SELECT AVG(gcount) AS average, {typ}, session\n",
" FROM (SELECT '{session}' AS session, {typ}, mnis_id, count(*) AS gcount\n",
" FROM dfs.tmp.`/senti_post_v2.parquet`\n",
" WHERE speech_date>='{start}' AND speech_date<='{end}'\n",
" GROUP BY mnis_id, {typ})\n",
" GROUP BY {typ}, session\n",
"'''.format(session=session, start=start, end=end, typ=typ)\n",
" dq=drill.query(q).to_dataframe()\n",
" #Make the average a numeric type...\n",
" dq['average']=dq['average'].astype(float)\n",
" return dq\n",
"\n",
"def avByParty(session):\n",
" return avByType(session,'party')\n",
"\n",
"avByParty(session)"
]
},
{
"cell_type": "code",
"execution_count": 172,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>party</th>\n",
" <th>Alliance</th>\n",
" <th>Conservative</th>\n",
" <th>Democratic Unionist</th>\n",
" <th>Democratic Unionist Party</th>\n",
" <th>Green Party</th>\n",
" <th>Independent</th>\n",
" <th>Labour</th>\n",
" <th>Labour (Co-op)</th>\n",
" <th>Liberal Democrat</th>\n",
" <th>Plaid Cymru</th>\n",
" <th>Respect</th>\n",
" <th>SNP</th>\n",
" <th>Scottish National Party</th>\n",
" <th>Social Democratic</th>\n",
" <th>Social Democratic &amp; Labour Party</th>\n",
" <th>UKIP</th>\n",
" <th>Ulster Unionist Party</th>\n",
" </tr>\n",
" <tr>\n",
" <th>session</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2005-2006</th>\n",
" <td>NaN</td>\n",
" <td>132.668394</td>\n",
" <td>144.0</td>\n",
" <td>127.625</td>\n",
" <td>NaN</td>\n",
" <td>67.142857</td>\n",
" <td>134.061538</td>\n",
" <td>132.200000</td>\n",
" <td>119.063492</td>\n",
" <td>202.000000</td>\n",
" <td>34.0</td>\n",
" <td>NaN</td>\n",
" <td>124.857143</td>\n",
" <td>24.0</td>\n",
" <td>95.333333</td>\n",
" <td>123.5</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2006-2007</th>\n",
" <td>NaN</td>\n",
" <td>92.744792</td>\n",
" <td>39.0</td>\n",
" <td>47.625</td>\n",
" <td>NaN</td>\n",
" <td>62.833333</td>\n",
" <td>94.736196</td>\n",
" <td>104.947368</td>\n",
" <td>90.841270</td>\n",
" <td>64.333333</td>\n",
" <td>50.0</td>\n",
" <td>NaN</td>\n",
" <td>99.000000</td>\n",
" <td>28.0</td>\n",
" <td>67.333333</td>\n",
" <td>89.5</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-2008</th>\n",
" <td>NaN</td>\n",
" <td>117.302083</td>\n",
" <td>11.0</td>\n",
" <td>30.375</td>\n",
" <td>NaN</td>\n",
" <td>80.666667</td>\n",
" <td>112.253086</td>\n",
" <td>122.700000</td>\n",
" <td>106.206349</td>\n",
" <td>86.000000</td>\n",
" <td>15.0</td>\n",
" <td>NaN</td>\n",
" <td>104.125000</td>\n",
" <td>19.0</td>\n",
" <td>32.666667</td>\n",
" <td>148.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-2009</th>\n",
" <td>NaN</td>\n",
" <td>95.910526</td>\n",
" <td>1.0</td>\n",
" <td>36.500</td>\n",
" <td>NaN</td>\n",
" <td>53.777778</td>\n",
" <td>92.212025</td>\n",
" <td>101.600000</td>\n",
" <td>96.603175</td>\n",
" <td>60.333333</td>\n",
" <td>8.0</td>\n",
" <td>NaN</td>\n",
" <td>92.000000</td>\n",
" <td>24.0</td>\n",
" <td>65.333333</td>\n",
" <td>77.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-2010</th>\n",
" <td>NaN</td>\n",
" <td>53.518325</td>\n",
" <td>3.0</td>\n",
" <td>17.375</td>\n",
" <td>NaN</td>\n",
" <td>50.000000</td>\n",
" <td>46.870748</td>\n",
" <td>46.950000</td>\n",
" <td>44.650794</td>\n",
" <td>29.333333</td>\n",
" <td>5.0</td>\n",
" <td>NaN</td>\n",
" <td>35.125000</td>\n",
" <td>6.0</td>\n",
" <td>23.666667</td>\n",
" <td>17.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"party Alliance Conservative Democratic Unionist \\\n",
"session \n",
"2005-2006 NaN 132.668394 144.0 \n",
"2006-2007 NaN 92.744792 39.0 \n",
"2007-2008 NaN 117.302083 11.0 \n",
"2008-2009 NaN 95.910526 1.0 \n",
"2009-2010 NaN 53.518325 3.0 \n",
"\n",
"party Democratic Unionist Party Green Party Independent Labour \\\n",
"session \n",
"2005-2006 127.625 NaN 67.142857 134.061538 \n",
"2006-2007 47.625 NaN 62.833333 94.736196 \n",
"2007-2008 30.375 NaN 80.666667 112.253086 \n",
"2008-2009 36.500 NaN 53.777778 92.212025 \n",
"2009-2010 17.375 NaN 50.000000 46.870748 \n",
"\n",
"party Labour (Co-op) Liberal Democrat Plaid Cymru Respect SNP \\\n",
"session \n",
"2005-2006 132.200000 119.063492 202.000000 34.0 NaN \n",
"2006-2007 104.947368 90.841270 64.333333 50.0 NaN \n",
"2007-2008 122.700000 106.206349 86.000000 15.0 NaN \n",
"2008-2009 101.600000 96.603175 60.333333 8.0 NaN \n",
"2009-2010 46.950000 44.650794 29.333333 5.0 NaN \n",
"\n",
"party Scottish National Party Social Democratic \\\n",
"session \n",
"2005-2006 124.857143 24.0 \n",
"2006-2007 99.000000 28.0 \n",
"2007-2008 104.125000 19.0 \n",
"2008-2009 92.000000 24.0 \n",
"2009-2010 35.125000 6.0 \n",
"\n",
"party Social Democratic & Labour Party UKIP Ulster Unionist Party \n",
"session \n",
"2005-2006 95.333333 123.5 NaN \n",
"2006-2007 67.333333 89.5 NaN \n",
"2007-2008 32.666667 148.0 NaN \n",
"2008-2009 65.333333 77.0 NaN \n",
"2009-2010 23.666667 17.0 NaN "
]
},
"execution_count": 172,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Create a function to loop through sessions and create a dataframe containing specified averages for each one\n",
"# Note that this just generalises and packages up the code we had previously\n",
"def pivotAndFlatten(overall,typ):\n",
" #Tidy up the index\n",
" overall=overall.reset_index(drop=True)\n",
" overall_wide = overall.pivot(index='session', columns=typ)\n",
" \n",
" #Flatten the column names\n",
" overall_wide.columns = overall_wide.columns.get_level_values(1)\n",
" return overall_wide\n",
"\n",
"def getOverall(typ):\n",
" overall=pd.DataFrame()\n",
" for session in psd['display name']:\n",
" overall=pd.concat([overall,avByType(session,typ)])\n",
"\n",
" return pivotAndFlatten(overall,typ)\n",
"\n",
"overallParty=getOverall('party')\n",
"\n",
"overallParty.head()"
]
},
{
"cell_type": "code",
"execution_count": 236,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>party_group</th>\n",
" <th>Conservative</th>\n",
" <th>Labour</th>\n",
" <th>Liberal Democrat</th>\n",
" <th>Other</th>\n",
" </tr>\n",
" <tr>\n",
" <th>session</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2005-2006</th>\n",
" <td>132.668</td>\n",
" <td>133.954</td>\n",
" <td>119.063</td>\n",
" <td>112.303</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2006-2007</th>\n",
" <td>92.745</td>\n",
" <td>95.299</td>\n",
" <td>90.841</td>\n",
" <td>66.938</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-2008</th>\n",
" <td>117.302</td>\n",
" <td>112.860</td>\n",
" <td>106.206</td>\n",
" <td>68.394</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-2009</th>\n",
" <td>95.911</td>\n",
" <td>92.771</td>\n",
" <td>96.603</td>\n",
" <td>59.314</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-2010</th>\n",
" <td>53.518</td>\n",
" <td>46.876</td>\n",
" <td>44.651</td>\n",
" <td>30.833</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2010-2012</th>\n",
" <td>256.076</td>\n",
" <td>182.669</td>\n",
" <td>254.714</td>\n",
" <td>200.323</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2012-2013</th>\n",
" <td>114.723</td>\n",
" <td>77.504</td>\n",
" <td>120.407</td>\n",
" <td>92.333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-2014</th>\n",
" <td>124.583</td>\n",
" <td>89.545</td>\n",
" <td>127.946</td>\n",
" <td>109.419</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2014-2015</th>\n",
" <td>98.923</td>\n",
" <td>63.945</td>\n",
" <td>84.018</td>\n",
" <td>81.867</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-2016</th>\n",
" <td>135.368</td>\n",
" <td>78.850</td>\n",
" <td>117.250</td>\n",
" <td>107.632</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2016-2017</th>\n",
" <td>114.405</td>\n",
" <td>62.845</td>\n",
" <td>87.778</td>\n",
" <td>95.724</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"party_group Conservative Labour Liberal Democrat Other\n",
"session \n",
"2005-2006 132.668 133.954 119.063 112.303\n",
"2006-2007 92.745 95.299 90.841 66.938\n",
"2007-2008 117.302 112.860 106.206 68.394\n",
"2008-2009 95.911 92.771 96.603 59.314\n",
"2009-2010 53.518 46.876 44.651 30.833\n",
"2010-2012 256.076 182.669 254.714 200.323\n",
"2012-2013 114.723 77.504 120.407 92.333\n",
"2013-2014 124.583 89.545 127.946 109.419\n",
"2014-2015 98.923 63.945 84.018 81.867\n",
"2015-2016 135.368 78.850 117.250 107.632\n",
"2016-2017 114.405 62.845 87.778 95.724"
]
},
"execution_count": 236,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Note that the function means it's now just as easy to query on another single column\n",
"getOverall('party_group')"
]
},
{
"cell_type": "code",
"execution_count": 166,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABLkAAARiCAYAAABIwiUhAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAQAAADC8/wPOxRc2cm55AQAAAABJRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x1193279e8>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"overallParty.plot(kind='barh', figsize=(20,20));"
]
},
{
"cell_type": "code",
"execution_count": 169,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAZMAAAEKCAYAAADXdbjqAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x14a293ef0>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"parties=['Conservative','Labour']\n",
"\n",
"overallParty[parties].plot();"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can write another query to look by gender and party."
]
},
{
"cell_type": "code",
"execution_count": 175,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>average</th>\n",
" <th>gender</th>\n",
" <th>party</th>\n",
" <th>session</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>32.000000</td>\n",
" <td>Female</td>\n",
" <td>Independent</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>111.386100</td>\n",
" <td>Male</td>\n",
" <td>Conservative</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>27.000000</td>\n",
" <td>Male</td>\n",
" <td>UKIP</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>19.000000</td>\n",
" <td>Male</td>\n",
" <td>Independent</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>66.265487</td>\n",
" <td>Male</td>\n",
" <td>Labour</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>126.074627</td>\n",
" <td>Female</td>\n",
" <td>Conservative</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>56.344086</td>\n",
" <td>Female</td>\n",
" <td>Labour</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>95.583333</td>\n",
" <td>Male</td>\n",
" <td>Scottish National Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>74.823529</td>\n",
" <td>Male</td>\n",
" <td>Labour (Co-op)</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>100.000000</td>\n",
" <td>Female</td>\n",
" <td>Plaid Cymru</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>96.750000</td>\n",
" <td>Male</td>\n",
" <td>Liberal Democrat</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>111.555556</td>\n",
" <td>Female</td>\n",
" <td>Scottish National Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>79.000000</td>\n",
" <td>Male</td>\n",
" <td>Social Democratic &amp; Labour Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>64.300000</td>\n",
" <td>Female</td>\n",
" <td>Labour (Co-op)</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>122.500000</td>\n",
" <td>Male</td>\n",
" <td>Plaid Cymru</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>80.000000</td>\n",
" <td>Male</td>\n",
" <td>Ulster Unionist Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>94.000000</td>\n",
" <td>Male</td>\n",
" <td>Democratic Unionist Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>108.000000</td>\n",
" <td>Female</td>\n",
" <td>Social Democratic &amp; Labour Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>142.000000</td>\n",
" <td>Female</td>\n",
" <td>Green Party</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>16.000000</td>\n",
" <td>Female</td>\n",
" <td>Liberal Democrat</td>\n",
" <td>2016-2017</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" average gender party session\n",
"0 32.000000 Female Independent 2016-2017\n",
"1 111.386100 Male Conservative 2016-2017\n",
"2 27.000000 Male UKIP 2016-2017\n",
"3 19.000000 Male Independent 2016-2017\n",
"4 66.265487 Male Labour 2016-2017\n",
"5 126.074627 Female Conservative 2016-2017\n",
"6 56.344086 Female Labour 2016-2017\n",
"7 95.583333 Male Scottish National Party 2016-2017\n",
"8 74.823529 Male Labour (Co-op) 2016-2017\n",
"9 100.000000 Female Plaid Cymru 2016-2017\n",
"10 96.750000 Male Liberal Democrat 2016-2017\n",
"11 111.555556 Female Scottish National Party 2016-2017\n",
"12 79.000000 Male Social Democratic & Labour Party 2016-2017\n",
"13 64.300000 Female Labour (Co-op) 2016-2017\n",
"14 122.500000 Male Plaid Cymru 2016-2017\n",
"15 80.000000 Male Ulster Unionist Party 2016-2017\n",
"16 94.000000 Male Democratic Unionist Party 2016-2017\n",
"17 108.000000 Female Social Democratic & Labour Party 2016-2017\n",
"18 142.000000 Female Green Party 2016-2017\n",
"19 16.000000 Female Liberal Democrat 2016-2017"
]
},
"execution_count": 175,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def avByGenderAndParty(session):\n",
" start,end=getParliamentDate(session)\n",
" q='''SELECT AVG(gcount) AS average, gender, party, session\n",
" FROM (SELECT '{session}' AS session, gender, party, mnis_id, count(*) AS gcount\n",
" FROM dfs.tmp.`/senti_post_v2.parquet`\n",
" WHERE speech_date>='{start}' AND speech_date<='{end}'\n",
" GROUP BY mnis_id, gender, party)\n",
" GROUP BY gender, party, session\n",
"'''.format(session=session, start=start, end=end)\n",
" dq=drill.query(q).to_dataframe()\n",
" #Make the average a numeric type...\n",
" dq['average']=dq['average'].astype(float)\n",
" return dq\n",
"\n",
"\n",
"gp=avByGenderAndParty(session)\n",
"gp"
]
},
{
"cell_type": "code",
"execution_count": 206,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>party</th>\n",
" <th colspan=\"2\" halign=\"left\">Conservative</th>\n",
" <th colspan=\"2\" halign=\"left\">Labour</th>\n",
" </tr>\n",
" <tr>\n",
" <th>gender</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" </tr>\n",
" <tr>\n",
" <th>session</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2005-2006</th>\n",
" <td>134.312500</td>\n",
" <td>132.519774</td>\n",
" <td>111.188889</td>\n",
" <td>142.821277</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2006-2007</th>\n",
" <td>91.875000</td>\n",
" <td>92.823864</td>\n",
" <td>85.844444</td>\n",
" <td>98.127119</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-2008</th>\n",
" <td>101.812500</td>\n",
" <td>118.710227</td>\n",
" <td>110.696629</td>\n",
" <td>112.842553</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-2009</th>\n",
" <td>84.294118</td>\n",
" <td>97.052023</td>\n",
" <td>88.090909</td>\n",
" <td>93.802632</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-2010</th>\n",
" <td>42.823529</td>\n",
" <td>54.563218</td>\n",
" <td>44.262500</td>\n",
" <td>47.845794</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2010-2012</th>\n",
" <td>204.458333</td>\n",
" <td>265.792157</td>\n",
" <td>172.067568</td>\n",
" <td>185.692308</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2012-2013</th>\n",
" <td>98.333333</td>\n",
" <td>117.845238</td>\n",
" <td>74.200000</td>\n",
" <td>77.326667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-2014</th>\n",
" <td>113.340426</td>\n",
" <td>126.671937</td>\n",
" <td>90.263158</td>\n",
" <td>86.265306</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2014-2015</th>\n",
" <td>105.000000</td>\n",
" <td>97.794466</td>\n",
" <td>64.350649</td>\n",
" <td>61.986395</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-2016</th>\n",
" <td>131.833333</td>\n",
" <td>136.276265</td>\n",
" <td>72.155556</td>\n",
" <td>83.813559</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2016-2017</th>\n",
" <td>126.074627</td>\n",
" <td>111.386100</td>\n",
" <td>56.344086</td>\n",
" <td>66.265487</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"party Conservative Labour \n",
"gender Female Male Female Male\n",
"session \n",
"2005-2006 134.312500 132.519774 111.188889 142.821277\n",
"2006-2007 91.875000 92.823864 85.844444 98.127119\n",
"2007-2008 101.812500 118.710227 110.696629 112.842553\n",
"2008-2009 84.294118 97.052023 88.090909 93.802632\n",
"2009-2010 42.823529 54.563218 44.262500 47.845794\n",
"2010-2012 204.458333 265.792157 172.067568 185.692308\n",
"2012-2013 98.333333 117.845238 74.200000 77.326667\n",
"2013-2014 113.340426 126.671937 90.263158 86.265306\n",
"2014-2015 105.000000 97.794466 64.350649 61.986395\n",
"2015-2016 131.833333 136.276265 72.155556 83.813559\n",
"2016-2017 126.074627 111.386100 56.344086 66.265487"
]
},
"execution_count": 206,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gp_overall=pd.DataFrame()\n",
"\n",
"for session in psd['display name']:\n",
" gp_overall=pd.concat([gp_overall,avByGenderAndParty(session)])\n",
"\n",
"#Pivot table it more robust than pivot - missing entries handled with NA\n",
"#Also limit what parties we are interested in\n",
"gp_wide = gp_overall[gp_overall['party'].isin(parties)].pivot_table(index='session', columns=['party','gender'])\n",
"\n",
"#Flatten column names\n",
"gp_wide.columns = gp_wide.columns.droplevel(0)\n",
" \n",
"gp_wide"
]
},
{
"cell_type": "code",
"execution_count": 208,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABKAAAAJQCAYAAAC5GxyfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzs3Xl8VfWd//HXSdj3fSlbECOQBULYpMoAKmCrQg2DWMe2\n4IxWGPl12mprR6dlqp2qo6WbltaqtJUqLgWUTqtFwRYTZRNKwr4lgBgWZSeQ5fz+uHALCiFgkpvl\n9Xw8eJzce875fj/3msdDHm++388JwjBEkiRJkiRJqihxsS5AkiRJkiRJNZsBlCRJkiRJkiqUAZQk\nSZIkSZIqlAGUJEmSJEmSKpQBlCRJkiRJkiqUAZQkSZIkSZIqlAGUJEmSJEmSKpQBlCRJkiRJkiqU\nAZQkSZIkSZIqVJ1YF3BKmzZtwoSEhFiXIUmSJEmSVGMsX758bxiGbWNdR5UJoBISEli2bFmsy5Ak\nSZIkSaoxgiDIjXUN4BY8SZIkSZIkVTADKEmSJEmSJFUoAyhJkiRJkiRVqCrTA0qSJEmSpJqusLCQ\nHTt2UFBQEOtSVMM0aNCAzp07U7du3ViXclYGUJIkSZIkVZIdO3bQtGlTEhISCIIg1uWohgjDkH37\n9rFjxw66d+8e63LOyi14kiRJkiRVkoKCAlq3bm34pHIVBAGtW7eu0ivrDKAkSZIkSapEhk+qCFX9\n98oASpIkSZIkSRXKAEqSJEmSJFWYuXPnsmbNmliXAcCiRYu4/vrrY11GrWQAJUmSJEmSKkRRUVGV\nCqAuVFFRUaxLqDEMoCRJkiRJ0jlt27aNXr168S//8i/07t2bf/7nf+bo0aN8//vfZ+DAgaSkpHDH\nHXcQhiEAw4cP5z/+4z8YMGAADz/8MK+88gr33HMPaWlpbN68mfT09OjYGzduPOP1KUuXLqVPnz6k\npaVxzz33kJKSAkBxcTH33HMPAwcOpE+fPvzyl78EIiubhg8fzj//8z9Haz1Vz5///Gd69epFeno6\nf/jDH6JzHDlyhNtuu41BgwbRr18/5s2bB8DMmTMZM2YMV111FVdffXXFfKm1kAGUJEmSJEkq1fr1\n65kyZQpr166lWbNmPPHEE9x1110sXbqU7Oxsjh07xvz586PXnzhxgmXLlnHfffcxZswY/vd//5eV\nK1fSo0cPmjdvzsqVKwF45plnmDRp0ifmmzRpEr/85S9ZuXIl8fHx0fefeuopmjdvztKlS1m6dClP\nPvkkW7duBeC9997jxz/+MWvWrGHLli28/fbbFBQUcPvtt/Pqq6+yfPlyPvjgg+hYP/jBD7jqqqtY\nsmQJCxcu5J577uHIkSMArFixgpdeeom33nqrQr7P2sgASpIkSZIklapLly5cccUVANx6660sXryY\nhQsXMnjwYFJTU3nzzTfJycmJXj9hwoRzjvVv//ZvPPPMMxQXFzN79mxuueWWM87v37+fQ4cOMWTI\nEIAzzr/++uv89re/JS0tjcGDB7Nv3z42btwIwKBBg+jcuTNxcXGkpaWxbds21q1bR/fu3UlMTCQI\nAm699dYzxnrooYdIS0tj+PDhFBQUkJeXB8DIkSNp1arVp/zWdLo6sS5AkiRJkiRVbUEQfOL1lClT\nWLZsGV26dGHatGkUFBREzzdu3PicY40bN47//u//5qqrrqJ///60bt26zHWEYcjPfvYzRo8efcb7\nixYton79+tHX8fHx5+3fFIYhL7/8Mj179jzj/XfffbfU+nVxXAElSZIkSZJKlZeXR1ZWFgC///3v\nufLKKwFo06YNhw8f5qWXXjrnvU2bNuXQoUPR1w0aNGD06NFMnjz5jO133/nOd5gzZw4tWrSgadOm\nvPvuuwA8//zz0WtGjx7NL37xCwoLCwHYsGFDdNvc2fTq1Ytt27axefNmAJ577rkzxvrZz34W7RX1\n3nvvle3L0EUxgJIkSZIkSaXq2bMnjz/+OL179+ajjz5i8uTJ3H777aSkpDB69GgGDhx4zntvvvlm\n/vd//5d+/fpFg6B/+Zd/IS4ujlGjRkWvW716NR06dAAivZ5uv/120tLSOHLkCM2bNwci2/eSkpJI\nT08nJSWFr371q6WudGrQoAG/+tWvuO6660hPT6ddu3bRc//1X/9FYWEhffr0ITk5mf/6r//6VN+R\nShecSvpibcCAAeGyZctiXYYkSZIkSRVm7dq19O7dO9ZlXJBt27Zx/fXXk52dXW5jPvrooxw4cIAH\nHngg+t7o0aN57bXXADh8+DBNmjQB4KGHHmLXrl385Cc/Kbf5a6qz/X4FQbA8DMMBMSopyh5QkiRJ\nkiSp0tx4441s3ryZN99884z3T4VPAH/84x/54Q9/SFFREd26dWPmzJmVXKXKmyugJEmSJEmqJNVx\nBZSqj6q8AsoeUJIkSZIkSapQBlCSJEmSJEmqUAZQkiRJkiRJqlAGUJIkSRdi85vwwpehpDjWlUiS\nJFUbBlCSJEkXYsXvYM08yH071pVIknRRjh07xrBhwygujvxjyoYNG/j85z9PYmIi6enp3HTTTeTn\n58e4yvNbtGgRmZmZ0dczZszgt7/9bbnOMXPmTNq2bUtaWhppaWl8+ctfLtfxP2748OGc7wFtN998\nMxs3bqzQOipCnVgXIEmSVG2EIeRlRX7Ofhm6/1Ns65Ek6SI8/fTTZGRkEB8fT0FBAddddx0/+tGP\nuOGGG4BIsLNnzx7at29faTUVFRVRp86FRRSLFi2iSZMmfPaznwXgzjvvrIjSmDBhAj//+c8rZOyL\nMXnyZB555BGefPLJWJdyQVwBJUmSVFYfbYNDu6BuI1jzChQXxroiSZIu2KxZsxg7diwAv//97xky\nZEg0fILIKpyUlBQKCgqYNGkSqamp9OvXj4ULFwKRVUEZGRlce+21JCYm8q1vfQuA4uJiJk6cSEpK\nCqmpqUyfPh2AzZs3c+2119K/f3+GDh3KunXrAJg4cSJ33nkngwcP5lvf+hYJCQns378/WkdiYiL5\n+fm8+uqrDB48mH79+nHNNdeQn5/Ptm3bmDFjBtOnTyctLY2//e1vTJs2jUcffZR169YxaNCg6Djb\ntm0jNTUVgOXLlzNs2DD69+/P6NGj2bVr10V9h6V9psmTJ3P55ZdzySWXsGjRIm677TZ69+7NxIkT\no/dPnjyZAQMGkJyczPe+972zzvH6668zZMgQ0tPTGT9+PIcPHwZg6NChLFiwgKKioouqPVZcASVJ\nklRWp1Y/XfkNWPggbH0LLr0mtjVJkqqt/341hzXvHyzXMZM+04zv3ZB8zvMnTpxgy5YtJCQkAJCd\nnU3//v3Peu3jjz9OEASsXr2adevWMWrUKDZs2ADAypUree+996hfvz49e/Zk6tSp7N69m507d5Kd\nnQ0QDZPuuOMOZsyYQWJiIu+++y5TpkzhzTffBGDHjh1kZmYSHx9PcXExc+bMYdKkSbz77rt069aN\n9u3bc+WVV/LOO+8QBAG//vWveeSRR3jssce48847adKkCXfffTcAb7zxBgC9evXixIkTbN26le7d\nuzN79mwmTJhAYWEhU6dOZd68ebRt25bZs2dz33338fTTT5f6nc6ePZvFixcD8LWvfY1JkyaV+pk+\n+ugjsrKyeOWVVxgzZgxvv/02v/71rxk4cCArV64kLS2NH/zgB7Rq1Yri4mKuvvpq/v73v9OnT5/o\nnHv37uXBBx9kwYIFNG7cmIcffpgf/ehHfPe73yUuLo5LL72UVatWnfO/XVVkACVJklRWuZnQoDl8\n9i7I/ClkzzGAkiRVK3v37qVFixZlunbx4sVMnToViIQ63bp1iwZQV199Nc2bNwcgKSmJ3NxckpOT\n2bJlC1OnTuW6665j1KhRHD58mMzMTMaPHx8d9/jx49Gfx48fT3x8PBDZ6vb973+fSZMm8fzzzzNh\nwgQgElJNmDCBXbt2ceLECbp3737e2m+66SZmz57Nvffey+zZs5k9ezbr168nOzubkSNHApEVWx07\ndjzvWB/fgne+z3TDDTcQBAGpqam0b98+uvoqOTmZbdu2kZaWxgsvvMCvfvUrioqK2LVrF2vWrDkj\ngHrnnXdYs2YNV1xxBRAJDocMGRI9365dO95//30DKEmSpBopLwu6XA51G0Kv62Ddq1A0HerUi3Vl\nkqRqqLSVShWlYcOGFBQURF8nJyfz1ltvXfA49evXj/4cHx9PUVERLVu2ZNWqVbz22mvMmDGDF154\ngR//+Me0aNGClStXnnWcxo0bR38eMmQImzZtYs+ePcydO5f7778fgKlTp/KNb3yDMWPGsGjRIqZN\nm3be+iZMmMD48ePJyMggCAISExNZvXo1ycnJZGVlXfDnPV1JSUmpn+nUdxMXF3fG9xQXF0dRURFb\nt27l0UcfZenSpbRs2ZKJEyee8d8EIAxDRo4cyXPPPXfWOQoKCmjYsOGn+hyVzR5QkiRJZXF4N+zb\nBN1O/utjcgYUHIDNb8a2LkmSLkDLli0pLi6OBh633HILmZmZ/PGPf4xe89e//pXs7GyGDh3KrFmz\ngMiT8vLy8ujZs+c5x967dy8lJSWMGzeOBx98kBUrVtCsWTO6d+/Oiy++CESClVWrVp31/iAIuPHG\nG/nGN75B7969ad26NQAHDhygU6dOAPzmN7+JXt+0aVMOHTp01rF69OhBfHw8DzzwQHQlVc+ePdmz\nZ080gCosLCQnJweAn//852VuNH4hn+lsDh48SOPGjWnevDn5+fn86U9/+sQ1l19+OW+//TabNm0C\n4MiRI9HVZxD575GSklLmOasCAyhJkqSyONX/qWvkSTtcMhwatICcP8SqIkmSLsqoUaOiPY0aNmzI\n/Pnz+dnPfkZiYiJJSUk88cQTtG3blilTplBSUkJqaioTJkxg5syZZ6zo+bidO3cyfPhw0tLSuPXW\nW/nhD38IRJqeP/XUU/Tt25fk5GTmzZt3zjEmTJjAs88+Gw2NAKZNm8b48ePp378/bdq0ib5/ww03\nMGfOnGgT8nONddNNNwFQr149XnrpJb797W/Tt29f0tLSyMzMBGDdunXRwKssLuQzfVzfvn3p168f\nvXr14pZbbolusztd27ZtmTlzJl/84hfp06cPQ4YMiTY6z8/Pp2HDhnTo0KHMc1YFQRiGsa4BgAED\nBoTLli2LdRmSJEln96d7YfkzcO/2f2y5m3cX5MyFezZGtuVJknQea9eupXfv3jGtYcWKFUyfPp3f\n/e53Ma2jKrn++uv5wx/+QL16VX9b/fTp02nWrBn/+q//+olzZ/v9CoJgeRiGAyqrvnNxBZQkSVJZ\n5GVC54Fn9ntKyYATh2DjX2JXlyRJFyg9PZ0RI0ZQXFwc61KqjPnz51eL8AmgRYsWfOUrX4l1GRfM\nAEqSJOl8Cg7CB6uh65Az30/4J2jUxm14kqRq57bbbos+fU7Vy6RJk6hTp/o9U84ASpIk6Xx2LIGw\n5B8NyE+JrwNJY2HDa3DiSGxqkyRJqgYMoCRJks4nNwuCeOg86JPnUjKg8Chs+HPl1yVJklRNGEBJ\nkiSdT14WdOwD9Zt88lzXIdCkA2S7DU+SJOlcDKAkSZJKU3QcdiyDrp89+/m4eEj+QqQRecHByq1N\nkiSpmjCAkiRJKs3770Hx8U/2fzpdckbkmvV/qry6JEm6SMeOHWPYsGHRp+Bt2LCBz3/+8yQmJpKe\nns5NN91Efn5+jKs8v0WLFpGZmRl9PWPGDH7729+W6xwzZ84kCAIWLFgQfW/u3LkEQcBLL71U6r0T\nJ0487zV33303b775ZrnUWtUZQEmSJJUm9+RfbD/+BLzTdR4IzTr7NDxJUrXw9NNPk5GRQXx8PAUF\nBVx33XVMnjyZjRs3smLFCqZMmcKePXsqtaaioqILvufjAdSdd97Jl7/85fIsC4DU1FSef/756Ovn\nnnuOvn37lsvYU6dO5aGHHiqXsao6AyhJkqTS5GVBm8ugcZtzXxMXF9mGt+kNOPZR5dUmSdJFmDVr\nFmPHjgXg97//PUOGDOGGG26Inh8+fDgpKSkUFBQwadIkUlNT6devHwsXLgQiq4IyMjK49tprSUxM\n5Fvf+hYAxcXFTJw4kZSUFFJTU5k+fToAmzdv5tprr6V///4MHTqUdevWAZEVQnfeeSeDBw/mW9/6\nFgkJCezfvz9aR2JiIvn5+bz66qsMHjyYfv36cc0115Cfn8+2bduYMWMG06dPJy0tjb/97W9MmzaN\nRx99lHXr1jFo0D8eHLJt2zZSU1MBWL58OcOGDaN///6MHj2aXbt2nff7Gjp0KEuWLKGwsJDDhw+z\nadMm0tLSoue///3vM3DgQFJSUrjjjjsIw/ATY5xr3m7durFv3z4++OCDMvyXq97qxLoASZKkKquk\nGPLejYRL55MyDrJ+DmvnQ/qXKr42SVL196d74YPV5Ttmh1T43LlX1Jw4cYItW7aQkJAAQHZ2Nv37\n9z/rtY8//jhBELB69WrWrVvHqFGj2LBhAwArV67kvffeo379+vTs2ZOpU6eye/dudu7cSXZ2NkA0\nTLrjjjuYMWMGiYmJvPvuu0yZMiW67WzHjh1kZmYSHx9PcXExc+bMYdKkSbz77rt069aN9u3bc+WV\nV/LOO+8QBAG//vWveeSRR3jssce48847adKkCXfffTcAb7zxBgC9evXixIkTbN26le7duzN79mwm\nTJhAYWEhU6dOZd68ebRt25bZs2dz33338fTTT5f6lQZBwDXXXMNrr73GgQMHGDNmDFu3bo2ev+uu\nu/jud78LwJe+9CXmz59/RqB3vnnT09N5++23GTduXKl1VHcGUJIkSeeyew0cPwDdztGA/HSf6Qct\nEyLb8AygJElV1N69e2nRokWZrl28eDFTp04FIqFOt27dogHU1VdfTfPmzQFISkoiNzeX5ORktmzZ\nwtSpU7nuuusYNWoUhw8fJjMzk/Hjx0fHPX78ePTn8ePHEx8fD8CECRP4/ve/z6RJk3j++eeZMGEC\nEAmpJkyYwK5duzhx4gTdu3c/b+033XQTs2fP5t5772X27NnMnj2b9evXk52dzciRI4HIiq2OHTuW\n6bu4+eab+elPf8qBAwd47LHH+J//+Z/ouYULF/LII49w9OhRPvzwQ5KTk88IoM43b7t27Xj//ffL\nVEd1ZgAlSZJ0LrlZkWNp/Z9OCYJIM/K3fwJH9pa+ZU+SJCh1pVJFadiwIQUFBdHXycnJvPXWWxc8\nTv369aM/x8fHU1RURMuWLVm1ahWvvfYaM2bM4IUXXuDHP/4xLVq0YOXKlWcdp3HjxtGfhwwZwqZN\nm9izZw9z587l/vvvByJ9kr7xjW8wZswYFi1axLRp085b34QJExg/fjwZGRkEQUBiYiKrV68mOTmZ\nrKysC/68gwYNYvXq1TRq1IjLLrss+n5BQQFTpkxh2bJldOnShWnTpp3x/QKEYVjqvAUFBTRs2PCC\na6pu7AElSZJ0LnmZ0KwTtOhatutTMiAshrWvVGxdkiRdpJYtW1JcXBwNSW655RYyMzP54x//GL3m\nr3/9K9nZ2QwdOpRZs2YBkSfl5eXl0bNnz3OOvXfvXkpKShg3bhwPPvggK1asoFmzZnTv3p0XX3wR\niIQxq1atOuv9QRBw44038o1vfIPevXvTunVrAA4cOECnTp0A+M1vfhO9vmnTphw6dOisY/Xo0YP4\n+HgeeOCB6Eqqnj17smfPnmgQVFhYSE5ODgA///nP+fnPf17qd/fQQw+dsfIJiH6Pbdq04fDhw2d9\n6l1p80Lku01JSSl17prAAEqSJOlswjCyAqrrkMjqprJonwKtEyHbp+FJkqquUaNGsXjxYiCyImr+\n/Pn87Gc/IzExkaSkJJ544gnatm3LlClTKCkpITU1lQkTJjBz5swzVj593M6dOxk+fDhpaWnceuut\n/PCHPwQiTc+feuop+vbtS3JyMvPmzTvnGBMmTODZZ5+NhkYA06ZNY/z48fTv3582bf6xwviGG25g\nzpw50Sbk5xrrpptuAqBevXq89NJLfPvb36Zv376kpaVFn6K3bt26aOB1Lp/73OcYMWLEGe+1aNGC\n22+/nZSUFEaPHs3AgQM/cV9p8xYWFrJp0yYGDBhQ6tw1QXC27uyxMGDAgHDZsmWxLkOSJCniwy3w\n035w3WMw8N/Kft/C/4G3HoFvroOmHSquPklStbR27Vp69+4d0xpWrFjB9OnT+d3vfhfTOqqS66+/\nnj/84Q/Uq1evUuedM2cOK1as4IEHHiiX8c72+xUEwfIwDGOecLkCSpIk6Wyi/Z/K0ID8dMkZQAhr\nzv2vu5IkxVJ6ejojRoyguLg41qVUGfPnz6/08AmgqKiIb37zm5U+bywYQEmSJJ1NXiY0aAFte13Y\nfe16Qbskt+FJkqq02267Lfr0OcXO+PHjy/xUwurOAEqSJOlsTvV/iruIvy6lZMD2d+DAjvKvS5Ik\nqRoygJIkSfq4Q/nw4WboNuTi7k/OiBxz5pZfTZIkSdWYAZQkSdLH5V1k/6dTWveAjn0hx214kiRJ\nYAAlSZL0SXlZUKdhJES6WMkZsHM5fLSt3MqSJEmqrgygJEmSPi43EzoPgDqf4mk4yTdGjjlzyqcm\nSZLKybFjxxg2bBjFxcVs27aNlJSUMt87ceJEXnrppQqs7pOmTZtGp06dSEtLIy0tjXvvvbdC50tI\nSGDv3r2lXnPNNdfw0UcfVWgdNU2ZAqggCLoEQbAwCII1QRDkBEHwtZPvTwuCYGcQBCtP/vn8afd8\nJwiCTUEQrA+CYHRFfQBJkqRyVXAQ8rOh20VuvzulZTfoNMCn4UmSqpynn36ajIyMKvUUvOLi4lLP\nf/3rX2flypWsXLmShx56qJKqOrcvfelLPPHEE7Euo1op6wqoIuCbYRgmAZcD/x4EQdLJc9PDMEw7\n+ef/AE6euxlIBq4FngiCoOr8ZkuSJJ3L9iUQlkSegPdppWTAB3+HvZs+/ViSJJWTWbNmMXbs2FKv\nefLJJxk4cCB9+/Zl3LhxHD16NHpuwYIFDBgwgMsuu4z58+cDUFBQwKRJk0hNTaVfv34sXLgQgJkz\nZ3LXXXdF773++utZtGgRAE2aNOGb3/wmffv2JSsr64I/x/Llyxk2bBj9+/dn9OjR7Nq1C4Dhw4fz\n9a9/nQEDBtC7d2+WLl1KRkYGiYmJ3H///dH7v/CFL9C/f3+Sk5P51a9+ddY5nn32WQYNGkRaWhpf\n/epXo0HZmDFjeO655y645tqsTlkuCsNwF7Dr5M+HgiBYC3Qq5ZaxwPNhGB4HtgZBsAkYBFz4b5Qk\nSVJlyn0bgnjoPPDTj5X0BXjtPyPNyId969OPJ0mqUR5e8jDrPlxXrmP2atWLbw/69jnPnzhxgi1b\ntpCQkFDqOBkZGdx+++0A3H///Tz11FNMnToVgG3btrFkyRI2b97MiBEj2LRpE48//jhBELB69WrW\nrVvHqFGj2LBhQ6lzHDlyhMGDB/PYY4+d93NNnz6dZ599FoCHH36Yq666iqlTpzJv3jzatm3L7Nmz\nue+++3j66acBqFevHsuWLeMnP/kJY8eOZfny5bRq1YoePXrw9a9/ndatW/P000/TqlUrjh07xsCB\nAxk3bhytW7eOzrl27Vpmz57N22+/Td26dZkyZQqzZs3iy1/+Mi1btuT48ePs27fvjHt0bmUKoE4X\nBEEC0A94F7gCuCsIgi8Dy4iskvqISDj1zmm37aD0wEqSJKlqyMuKNB+v3+TTj9W8U+RJetkGUJKk\nqmHv3r20aNHivNdlZ2dz//33s3//fg4fPszo0f/orHPTTTcRFxdHYmIil1xyCevWrWPx4sXRgKpX\nr15069btvAFUfHw848aNK1PdX//617n77rvPqC87O5uRI0cCkS18HTt2jJ4fM2YMAKmpqSQnJ0fP\nXXLJJWzfvp3WrVvz05/+lDlzIr0at2/fzsaNG88Ik9544w2WL1/OwIGRf5Q6duwY7dq1i55v164d\n77//vgFUGV1QABUEQRPgZeA/wjA8GATBL4AHgPDk8THgtgsY7w7gDoCuXbteSCmSJEnlr7Ag8uS6\nQXeU35gpGfB/d8PutdCud/mNK0mq9kpbqVRRGjZsSEFBwXmvmzhxInPnzqVv377MnDkzum0OIAiC\nM679+OvT1alTh5KSkujr0+du0KDBRfehCsOQ5OTkc27dq1+/PgBxcXHRn0+9LioqYtGiRSxYsICs\nrCwaNWrE8OHDP/G9hGHIV77yFX74wx+edY6CggIaNmx4UfXXRmV+Cl4QBHWJhE+zwjD8A0AYhvlh\nGBaHYVgCPElkmx3ATqDLabd3PvneGcIw/FUYhgPCMBzQtm3bi/0MkiRJ5eP9FVB8onz6P52SNBaC\nOJuRS5KqhJYtW1JcXHzeEOrQoUN07NiRwsJCZs2adca5F198kZKSEjZv3syWLVvo2bMnQ4cOjV63\nYcMG8vLy6NmzJwkJCaxcuZKSkhK2b9/OkiVLzjnnd77zneiKpPPp2bMne/bsiQZQhYWF5OTklOle\ngAMHDtCyZUsaNWrEunXreOeddz5xzdVXX81LL73E7t27Afjwww/Jzc0FIuHUBx98cN6tjPqHsj4F\nLwCeAtaGYfij097veNplNwLZJ39+Bbg5CIL6QRB0BxKBc/+WSZIkVQW5mZFjeQZQTdpBwpWRPlBh\nWH7jSpJ0kUaNGsXixYujr9evX0/nzp2jf1588UUeeOABBg8ezBVXXEGvXr3OuL9r164MGjSIz33u\nc8yYMYMGDRowZcoUSkpKSE1NZcKECcycOZP69etzxRVX0L17d5KSkvh//+//kZ6efs66Vq9eTYcO\nHcr0GerVq8dLL73Et7/9bfr27UtaWhqZmZll/g6uvfZaioqK6N27N/feey+XX375J65JSkriwQcf\nZNSoUfTp04eRI0dGG50vX76cyy+/nDp1LrizUa0VhGX4i1AQBFcCfwNWA6fWzv0n8EUgjcgWvG3A\nV082LCcIgvuIbMcrIrJl70+lzTFgwIBw2bJlF/cpJEmSysOz42D/drirnP/dbNkzMP8/4Kt/g459\nyndsSVK1snbtWnr3ju2W7BUrVjB9+nR+97vfxbSOjxs9ejSvvfZarMsok6997WuMGTOGq6++Otal\nnOFsv18bRHnBAAAgAElEQVRBECwPw3BAjEqKKutT8BYDZ9vU+X+l3PMD4AcXWZckSVLlKimG7Usi\nPZvKW+8x8MdvRlZBGUBJkmIsPT2dESNGUFxcfNE9mCpCdQmfAFJSUqpc+FTVlbkHlCRJUo2Wnw3H\nD0aeWlfeGreGS4ZD9stuw5MkVQm33XZblQqfqpvbb7891iVUOwZQkiRJALknn6LTrRz7P50uJQP2\n58HOFRUzviRJUhVmACVJkgSQlwnNOkOLrhUzfq/rIa5uZBueJElSLWMAJUmSFIaRFVAVtfoJoGEL\nuPQayJkDJSXnv16SJKkGMYCSJEn6cAsc2Q1dKzCAgsg2vIM7YUc5P2VPkiSpijOAkiRJys2MHLtV\nQAPy0/X8HNRpANluw5Mkxc6xY8cYNmwYxcXFbNu2jZSUlDLfO3HiRF566aUKrO6Tpk2bRhAEbNq0\nKfrej3/8Y4IgYNmyZaXeO3z48PNec/PNN7Nx48ZyqVXnZgAlSZKUlwUNW0KbnhU7T/2mkDgS1syF\nkuKKnUuSpHN4+umnycjIqFJPwSsuLv3/i6mpqTz//PPR1y+++CLJycnlMvfkyZN55JFHymUsnZsB\nlCRJUm4mdP0sxFXCX42SM+Bw/j9WXUmSVMlmzZrF2LFjS73mySefZODAgfTt25dx48Zx9OjR6LkF\nCxYwYMAALrvsMubPnw9AQUEBkyZNIjU1lX79+rFw4UIAZs6cyV133RW99/rrr2fRokUANGnShG9+\n85v07duXrKysUuv5whe+wLx58wDYvHkzzZs3p02bNtHzkydPZsCAASQnJ/O9733vrGO8/vrrDBky\nhPT0dMaPH8/hw4cBGDp0KAsWLKCoqKjUGvTp1Il1AZIkSTF16AP4aCsM/NfKme+y0VC3EWS/DN2H\nVs6ckqQq6YP/+R+Or11XrmPW792LDv/5n+c8f+LECbZs2UJCQkKp42RkZHD77bcDcP/99/PUU08x\ndepUALZt28aSJUvYvHkzI0aMYNOmTTz++OMEQcDq1atZt24do0aNYsOGDaXOceTIEQYPHsxjjz12\n3s/VrFkzunTpQnZ2NvPmzWPChAk888wz0fM/+MEPaNWqFcXFxVx99dX8/e9/p0+fPtHze/fu5cEH\nH2TBggU0btyYhx9+mB/96Ed897vfJS4ujksvvZRVq1bRv3//89aii+MKKEmSVLudWonUtYL7P51S\nrzFcdi2sfQWK/ZdWSVLl2rt3Ly1atDjvddnZ2QwdOpTU1FRmzZpFTk5O9NxNN91EXFwciYmJXHLJ\nJaxbt47Fixdz6623AtCrVy+6det23gAqPj6ecePGlbn2m2++meeff565c+dy4403nnHuhRdeID09\nnX79+pGTk8OaNWvOOP/OO++wZs0arrjiCtLS0vjNb35Dbm5u9Hy7du14//33y1yLLpwroCRJUu2W\nlxVZkdSxz/mvLS8p4yDnD7D1Lbj06sqbV5JUpZS2UqmiNGzYkIKCgvNeN3HiRObOnUvfvn2ZOXNm\ndNscQBAEZ1z78denq1OnDiUlJdHXp8/doEGDC+pDdf3113PPPfcwYMAAmjVrFn1/69atPProoyxd\nupSWLVsyceLET3zGMAwZOXIkzz333FnHLigooGHDhmWuRRfOFVCSJKl2y82CzgMhvm7lzXnpNVC/\nWSSEkiSpErVs2ZLi4uLzhlCHDh2iY8eOFBYWMmvWrDPOvfjii5SUlLB582a2bNlCz549GTp0aPS6\nDRs2kJeXR8+ePUlISGDlypWUlJSwfft2lixZcs45v/Od7zBnzpxznm/UqBEPP/ww99133xnvHzx4\nkMaNG9O8eXPy8/P505/+9Il7L7/8ct5+++3ok/SOHDlyxgqtDRs2XNDTAHXhXAElSZJqr2P7IT8b\nht9bufPWbQA9Pw9rX4XrpkOdepU7vySpVhs1ahSLFy/mmmuuAWD9+vV07tw5en769Ok88MADDB48\nmLZt2zJ48GAOHToUPd+1a1cGDRrEwYMHmTFjBg0aNGDKlClMnjyZ1NRU6tSpw8yZM6lfvz5XXHEF\n3bt3Jykpid69e5Oenn7OulavXs2YMWNKrf3mm2/+xHt9+/alX79+9OrViy5dunDFFVd84pq2bdsy\nc+ZMvvjFL3L8+HEAHnzwQS677DLy8/Np2LAhHTp0KP2L06cShGEY6xoAGDBgQLhs2bJYlyFJkmqT\nDa/D78fDl1+BS4ZV8tyvwe9vglteiDQmlyTVCmvXrqV3794xrWHFihVMnz6d3/3udzGt4+NGjx7N\na6+9VunzTp8+nWbNmvGv/1pJDySpQGf7/QqCYHkYhgNiVFKUW/AkSVLtlZcJcXUiW/Aq2yUjoEEL\nyHYbniSpcqWnpzNixAiKi4tjXcoZYhE+AbRo0YKvfOUrMZm7NnELniRJqr1ys6BjGtRrVPlz16kH\nva+HnHlQWBDZlidJUiW57bbbYl1ClTFp0qRYl1AruAJKkiTVToUF8P4K6DYkdjUkZ8CJQ7DpL7Gr\nQZJU6apKKxzVLFX998oASpIk1U47l0PxCej62djV0H0YNGrtNjxJqkUaNGjAvn37qnxYoOolDEP2\n7dtHgwZVd0W1W/AkSVLtlJcZOXa9PHY1xNeBpLGw6nk4cQTqNY5dLZKkStG5c2d27NjBnj17Yl2K\napgGDRqc8TTDqsYASpIk1U65WdC2NzRqFds6kjNg2dORp+KlZMS2FklShatbty7du3ePdRlSpXML\nniRJqn1KimH7ktj2fzql22ehSXvIcRueJEmquQygJElS7fPB6kjz71j2fzolLh6SvgAb/wLHD8W6\nGkmSpAphACVJkmqfvKzIsSqsgILI1ruiAlj/p1hXIkmSVCEMoCRJUu2TmwnNu0LzKtKos/MgaNYJ\nsl+OdSWSJEkVwgBKkiTVLmEYWQFVVVY/AcTFQfKNsOkNOPZRrKuRJEkqdwZQkiSpdtm3GY7sga5V\nKICCyDa8kkJY98dYVyJJklTuDKAkSVLtkpcZOXarAg3IT/eZdGiZANk+DU+SJNU8BlCSJKl2yc2C\nRq2hzWWxruRMQRDZhrdlERzZF+tqJEmSypUBlCRJql3yMiPb74Ig1pV8UnIGhMWw9pVYVyJJklSu\nDKAkSVLtcXAXfLSt6vV/OqVDKrS+FHLchidJkmoWAyhJklR7RPs/VdEAKggiq6C2LYZD+bGuRpIk\nqdwYQEmSpNojNwvqNoYOfWNdybmlZEBYAmvmxboSSZKkcmMAJUmSao+8LOgyEOLrxLqSc2vXG9r2\ndhueJEmqUQygJElS7XDsI8jPga6fjXUl55cyLhKWHdgZ60okSZLKhQGUJEmqHfLeBcKq2//pdCkZ\nkeOaubGtQ5IkqZwYQEmSpNohLxPi6kKnAbGu5Pxa94AOfSDbbXiSJKlmMICSJEm1Q24WfCYN6jWK\ndSVlk5IBO5fBR7mxrkSSJOlTM4CSJEk1X+ExeP896FoNtt+dknxj5JgzJ7Z1SJIklQMDKEmSVPPt\nWAYlhdCtGjQgP6VlAnTq79PwJElSjWAAJUmSar68rMixy+DY1nGhkjNg1yrYtznWlUiSJH0qBlCS\nJKnmy82EdknQqFWsK7kwyV+IHG1GLkmSqjkDKEmSVLMVF8GOpdWr/9MpzTtH6nYbniRJquYMoCRJ\nUs32wd/hxOHq1f/pdMkZsHsN7F4X60okSZIumgGUJEmq2U71f6qOK6AAksZCEOcqKEmSVK0ZQEmS\npJotNxNadIXmnWJdycVp2h66XRHpAxWGsa5GkiTpohhASZKkmisMIe+dSIBTnaVkwL6NkJ8d60ok\nSZIuigGUJEmqufZuhKN7q+/2u1N6j4UgHrJfjnUlkiRJF8UASpIk1Vx5mZFjdW1Afkrj1nDJMLfh\nSZKkassASpIk1Vy5WdC4LbS+NNaVfHrJGbA/F95fEetKJEmSLpgBlCRJqrnyMqHr5RAEsa7k0+t9\nPcTVjayCkiRJqmYMoCRJUs10YCfsz4Ou1Xz73SkNW8KlV0POXCgpiXU1kiRJF8QASpIk1Ux5WZFj\nt2regPx0yRlwcAfsWBrrSiRJki6IAZQkSaqZcjOhXhNonxrrSspPz89BfH3IcRueJEmqXgygJElS\nzZSXBV0GQXydWFdSfho0g8SRJ7fhFce6GkmSpDIzgJIkSTXP0Q9h95qa0//pdCkZcPiDyAovSZKk\nasIASpIk1Tzb340ca1L/p1MuuxbqNnIbniRJqlYMoCRJUs2TmwlxdaFT/1hXUv7qNYbLRsOaV6C4\nKNbVSJIklYkBlCRJqnnysqBTOtRtGOtKKkbKODi6F7b9NdaVSJIklYkBlCRJqllOHIX334OuNXD7\n3SmXjoR6TSHbbXiSJKl6MICSJEk1y85lUFIE3WpgA/JT6jaAXp+Hta9C0YlYVyNJknReBlCSJKlm\nyc0CAugyONaVVKzkDCjYD1sWxboSSZKk8zKAkiRJNUteJrRPhoYtYl1JxepxFTRo7tPwJElStWAA\nJUmSao7iIti+tGb3fzqlTj3odQOsnQ+FBbGuRpIkqVQGUJIkqeb4YBUUHoFutSCAAki5EU4cgk0L\nYl2JJElSqQygJElSzZGbFTl2rcENyE/XfRg0bOU2PEmSVOUZQEmSpJojLwtaJkCzjrGupHLE14Wk\nsbD+z3DiaKyrkSRJOicDKEmSVDOEYSSAqi2rn05JyYhsO9z4WqwrkSRJOicDKEmSVDPs3QBH99We\n/k+ndLsCmrSHbLfhSZKkqssASpIk1Qy5mZFjbVsBFRcf2Ya38XU4fijW1UiSJJ2VAZQkSaoZ8rKg\ncVto3SPWlVS+5AwoKoj0gpIkSaqCDKAkSVLNkJsFXYdAEMS6ksrXZTA0/QxkvxzrSiRJks7KAEqS\nJFV/B3bAgTzoVsu2350SFwfJN8KmBXBsf6yrkSRJ+gQDKEmSVP3lZkWOXWtZA/LTpWRASSGs+2Os\nK5EkSfoEAyhJklT95WVCvabQITXWlcROp/7Qoivk+DQ8SZJU9RhASZKk6i83C7oMijwRrrYKgkgz\n8i2L4OiHsa5GkiTpDAZQkiSpejv6IexZC91q8fa7U1IyoKQI1r4S60okSZLOYAAlSZKqt7xT/Z9q\naQPy03XoA616QLbb8CRJUtViACVJkqq33EyIrxfpgVTbBUFkFdS2v8Hh3bGuRpIkKcoASpIkVW95\nWfCZdKjbINaVVA3JGRCWwJp5sa5EkiQpygBKkiRVXyeOwK5V9n86XfskaNvLbXiSJKlKMYCSJEnV\n146lkabb9n86U3JGZGXYwfdjXYkkSRJgACVJkqqz3CwggC6DYl1J1ZKSAYSQMzfWlUiSJAEGUJIk\nqTrLy4T2KdCwRawrqVraJEKHVMhxG54kSaoaDKAkSVL1VFwIO5bZ/+lckjMiWxT358W6EkmSJAMo\nSZJUTe1aBYVHoZv9n84q+cbIMWdObOuQJEnCAEqSJFVXuZmRow3Iz65Vd/hMOmS/HOtKJEmSDKAk\nSVI1lZcFrS6Bpu1jXUnVlZIRWSm2b3OsK5EkSbWcAZQkSap+SkoiAZSrn0oX3YZnM3JJkhRbBlCS\nJKn62bsejn1kA/Lzad4ZulwO2faBkiRJsWUAJUmSqp9o/ycDqPNKyYDdObBnfawrkSRJtZgBlCRJ\nqn7ysqBJ+0gPKJUuaSwQQLbb8CRJUuwYQEmSpOonNyuy+ikIYl1J1de0AyRcGekDFYaxrkaSJNVS\nBlCSJKl62Z8HB3dANxuQl1nyjbB3A+TnxLoSSZJUSxlASZKk6iU3K3K0/1PZJY2FIB6yX451JZIk\nqZYygJIkSdVLXibUbwbtk2NdSfXRuA10/ye34UmSpJgxgJIkSdVLbhZ0GQxx8TGZ/rWcD7j5V1kU\nFBbHZP6LlpIBH22D99+LdSWSJKkWMoCSJEnVx5F9sHc9dIvd9rtn38nlnS0f8vKKHTGr4aL0uh7i\n6kZWQUmSJFUyAyhJklR95J3q/xSbBuQHjhWStXkfAL98awtFxSUxqeOiNGoFPa6CnLluw5MkSZXO\nAEqSJFUfeVkQXx86pcdk+kXrd1NUEnLnsB7kfXiUP67eFZM6LlpKBhzYDjuWxroSSZJUyxhASZKk\n6iM3Ezr1hzr1YzL96zn5tG1an7tHXUZiuyY8sXAzJSXVaDVRz89HArxst+FJkqTKZQAlSZKqh+OH\nYdeqmPV/Ol5UzKL1uxmZ1J468XFMHt6D9fmHeHPd7pjUc1EaNIPEkZAzB0qqWRN1SZJUrRlASZKk\n6mHHUgiLY9b/KXPzPo6cKGZkUnsAbuj7GTq1aMjjizYRVqeeSsk3wuEP/tFPS5IkqRKUKYAKgqBL\nEAQLgyBYEwRBThAEXzv5fqsgCP4SBMHGk8eWJ98PgiD4aRAEm4Ig+HsQBLFp1CBJkmqOvCwI4qDL\noJhM/3pOPo3rxfPZHq0BqBsfx53DLuG9vP28s+XDmNR0US67Fuo0dBueJEmqVGVdAVUEfDMMwyTg\ncuDfgyBIAu4F3gjDMBF44+RrgM8BiSf/3AH8olyrliRJtU9uJrRPiWwjq2QlJSEL1uYzvFc76teJ\nj74/fkAX2jSpxxOLNlV6TRetfhO4bDSsmQfFRbGuRpIk1RJlCqDCMNwVhuGKkz8fAtYCnYCxwG9O\nXvYb4Asnfx4L/DaMeAdoEQRBx3KtXJIk1R5FJ2DHMugWm+13K3fsZ8+h44w6uf3ulAZ14/nXKy/h\nbxv3snrHgZjUdlFSxsHRvbDtb7GuRJIk1RIX3AMqCIIEoB/wLtA+DMNTzx/+ADj1t7JOwPbTbttx\n8j1JkqQLt2sVFB2DrrFpQP56Tj514gKG92z3iXO3Xt6Vpg3qVK9VUIkjoV4TyHEbniRJqhwXFEAF\nQdAEeBn4jzAMD55+Lox037ygDpxBENwRBMGyIAiW7dmz50JulSRJtUleZuQYoxVQr6/5gCE9WtO8\nYd1PnGvaoC5fGZLAn3M+YNPuwzGo7iLUbQg9Pw9rX4XiwlhXI0mSaoEyB1BBENQlEj7NCsPw1D+X\n5Z/aWnfyeOo5xDuBLqfd3vnke2cIw/BXYRgOCMNwQNu2bS+mfkmSVBvkZkGrHtDkkyuQKtqm3YfZ\nsufIJ7bfnW7SFQnUrxPHjLc2V2Jln1JKBhz7CLYsinUlkiSpFijrU/AC4ClgbRiGPzrt1CvAV07+\n/BVg3mnvf/nk0/AuBw6ctlVPkiSp7EpKIk/A6xab7Xd/WZMPwDWlBFCtm9Tn5oFdmfveTnbuP1ZZ\npX06Pa6C+s19Gp4kSaoUZV0BdQXwJeCqIAhWnvzzeeAhYGQQBBuBa06+Bvg/YAuwCXgSmFK+ZUuS\npFpjzzoo2A9dY7f9rk/n5nRs3rDU627/p0sAePKvWyqjrE+vTn3ofT2smw+FBbGuRpIk1XBlfQre\n4jAMgzAM+4RhmHbyz/+FYbgvDMOrwzBMDMPwmjAMPzx5fRiG4b+HYdgjDMPUMAyXVezHkCRJNVa0\n/1Plr4DafbCA9/L2l7r97pROLRryhX6deH5pHnsPH6+E6spBcgYcPwib34h1JZIkqYa74KfgSZIk\nVarcLGjSAVp2r/Sp/7I2sv1uVHKHMl1/57AeHC8q4Zm3t1ZkWeXnkmHQsJXb8CRJUoUzgJIkSVVX\nGP6j/1MQVPr0f1mTT0LrRiS2a1Km6y9t14Rrkzvw26xcDhZUg6fLxdeFpDGw/k9w4misq5EkSTWY\nAZQkSaq69ufBwZ0x6f90qKCQzE37GJnUnuACwq8pwy/lUEERz76TW4HVlaPkDCg8Ahtfj3UlkiSp\nBjOAkiRJVVdeVuQYg/5Pb23Yw4nikjJvvzsltXNzhia24enFWykoLK6g6spRwpXQuB3kuA1PkiRV\nHAMoSZJUdeW+DfWbQ7ukSp/69Zx8WjeuR3rXlhd877+PuJS9h0/wwrLtFVBZOYuLh6SxsOF1OH4o\n1tVIkqQaygBKkiRVXblZ0HVwJCSpRCeKSli4fjfX9G5PfNyF954a3L0V6V1b8Mu3tlBYXFIBFZaz\nlAwoOgbr/xzrSiRJUg1lACVJkqqmw3tg30boWvnb797duo9DBUWMTGp/UfcHQcC/j7iUnfuP8crK\n98u5ugrQ5XJo+hm34UmSpApjACVJkqqmaP+nym9A/npOPg3rxnNlYpuLHuOqXu3o1aEpv3hrMyUl\nYTlWVwHi4iD5C7BpARzbH+tqJElSDWQAJUmSqqa8LIivD5/pV6nThmHIX9bkM+yytjSoe/Fb/4Ig\nYPLwHmzafZjX1+SXY4UVJDkDik/A+v+LdSWSJKkGMoCSJElVU24mdB4AdepX6rSrdx7gg4MFF739\n7nTXpXaka6tG/GLRJsKwiq+C6jwAmneFbLfhSZKk8mcAJUmSqp7jh+CDv8ek/9PrOfnExwVc1avd\npx6rTnwcXx12Cat2HODtTfvKoboKFASQciNsWQhHP4x1NZIkqYYxgJIkSVXP9iUQlsSm/9OaDxiU\n0IqWjeuVy3jj0jvTrml9nli0qVzGq1DJGVBSBGtfjXUlkiSphjGAkiRJVU9eFgRx0GVQpU67be8R\nNuQfZlTyp99+d0qDuvH829DuZG7ex3t5H5XbuBWiY19odYlPw5MkSeXOAEqSJFU9uVnQoQ/Ub1qp\n0/7lZLPw8uj/dLpbBnejecO6PLFoc7mOW+6CILIKautf4fDuWFcjSZJqEAMoSZJUtRQdh53LYrb9\nLqljMzq3bFSu4zapX4evfDaBv6zJZ0P+oXIdu9ylZES2P66ZF+tKJElSDWIAJUmSqpb3V0JRQaU3\nIN97+DjLcj8q1+13p5v02QQa1YvnF1V9FVS7JGjTE3LmxLoSSZJUgxhASZKkqiUvM3Ks5ADqjbX5\nhCGMSupQIeO3bFyPLw7qyiur3mf7h0crZI5yEQSRVVC5mXBwV6yrkSRJNYQBlCRJqlpys6B1IjRp\nW6nT/mVNPp1aNKR3x4rrO3X70EuIC+CXf63iq6CSM4AQ1syNdSWSJKmGMICSJElVR0kJbH8HulXu\n6qcjx4v468a9jEpuTxAEFTZPh+YNGJfemReW7WD3oYIKm+dTa3sZtE+FbJ+GJ0mSyocBlCRJqjp2\nr4GCA9C1chuQ/23jHk4UlVTY9rvTfXVYD4qKS3hq8dYKn+tTSbkRdiyB/dtjXYkkSaoBDKAkSVLV\nkZcVOVbyCqjXc/Jp0aguAxNaVvhc3ds05vOpHZn1Th4HjhZW+HwXLTkjcrQZuSRJKgcGUJIkqerI\nzYSmn4EW3SptyqLiEt5Yt5urerWjTnzl/NVoyvBLOXy8iN9mbauU+S5Kq+7wmX6Q/XKsK5EkSTWA\nAZQkSaoawjCyAqrbkMiT2CrJkm0fcuBYYaVsvzsl6TPNGNGzLc9kbuPoiaJKm/eCJWfArpWwr4o3\nTZckSVWeAZQkSaoaPtoGh3ZB18rffle/Thz/dFmbSp13yohL+fDICZ5fUoV7LCXfGDm6DU+SJH1K\nBlCSJKlqiPZ/qrwG5GEY8pc1+QxNbEujenUqbV6AgQmtGJTQiif/toUTRSWVOneZtegCnQcZQEmS\npE/NAEqSJFUNuZnQoAW07V1pU67ZdZCd+48xKql9me8pOXqUgg0bymX+ySN6sOtAAXNX7iyX8SpE\nyjjIz4Y95fOZJUlS7WQAJUmSqoa8LOh6OcRV3l9PXs/JJy6Aq3u3K/M9e376M7ZmjOPE9k+/dW74\nZW1J6tiMGYs2U1wSfurxKkTSWCCAnD/EuhJJklSNGUBJkqTYO7wb9m2q/P5Pa/IZ0K0VrZvUL9P1\nYVERB159FYqK+PCZZz71/EEQMGVED7bs/f/s3Xl8lGWa7//PU1XZl8pCAiFAIGFP2BRXFAEFRZAg\n2La2Gwq2it1npuecPjNzTs/8zpw5M3N6ZnqbEVwAl3ZrbUATFDEgICIBBFkkYUuAhC0J2Sr7VvWc\nP0r710pSKainkiDf9+vlq+iq+7nuS//Q6qvu67ob+bigLOB4QRGbAmlT4NBa76B4ERERkcugApSI\niIj0vl6Y/3S6uonD5+uYlel/+13j55/jrqoiNC2N2jVr6aiuDjiP2VkpDOsXxbItRZh9tcCTdS9U\nHoWKwt7ORERERK5QKkCJiIhI7yvJB0cEpEzssS03FpYDMPMS5j+5cnKwx8WR+h//gdnWRs0bbwSc\nh91m8PRt6RScq2Pb8cqA4wXFmGwwbHBoTW9nIiIiIlcoFaBERESk95XugEGTwRHaY1vmFZYxqn8M\naYlRfq1319dT/8lmYufMIXzUSKJvn0H1m2/haWwMOJd7Jw0ixRnOsi1FAccKiugkGDZVbXgiIiJy\n2VSAEhERkd7VUgdlX/Xo/KeaxjZ2n6y+pPa7+o8/xmxtxZk9D4B+S5bgcbmoXb064HxCHTaW3JrO\n7pPV7DkVeFtfUGQugJqTcH5/b2ciIiIiVyAVoERERKR3ndkNpgfSeq4A9cmRCjwmzBo7wO9nXDm5\nhA4bRvi4cQBETJxI5OTJVL36GmZ7e8A5PXj9YOIjQ1i+tTjgWEEx5h6wObynoEREREQukQpQIiIi\n0rtK8sGww6Dre2zLjYVlpDjDyUqN9Wt925mzNH3xBc7seRiG8af3E59cQsf587g+/DDgnCJDHTw+\nZRibj1RQeK4u4HiWi0yAjBlQ8L7a8EREROSSqQAlIiIivas0H1LGQ1h0j2zX3Obm02MXmDm2/7eK\nSb7UfbAOAOc993zr/aipUwkbOZLqVaswPZ6Ac3vspqFEhdp5/tM+egoqcwG4SuHMnt7ORERERK4w\nKkCJiIhI7+lo9RYzhtzcY1tuL6qkpd3jd/udaZq43s8h8rrrCElN/dZnhmGQuGQxrceLaPj004Bz\nc0aG8PCNaXx48BynKgMfbm650XeDPRQK1IYnIiIil0YFKBEREek95/aBu7VH5z/lFZQRE+7ghvQE\nv9a3fPUVbadO4Zyf3ennsbNn4xiYQtXKVZbkt/iWYTjsNl7c1gdPQYU7YfhMKHgPLDjxJSIiIlcP\nFVHtbNoAACAASURBVKBERESk95Ts8L720A14bo/JJ0cqmDE6mRC7f1+DXO/nYISFEXPnnZ1+boSE\nkLjocZr37qXpy30B55gcG84Prh3Emr1nKXO1BBzPclkLoP68t3VSRERExE8qQImIiEjvKc2HfiMh\nql+PbLe3pIbqxjb/2+/a2qhbv56Y22/HHt31jKq4+xZij4ujauVKS/J8amoGHR4PKz87YUk8S428\nCxwRasMTERGRS6IClIiIiPQOjxtKd/XY6Sfwtt+F2m3cNirJr/UNn32Gu7YWZ/Y8n+tskZHEP/QQ\nDZs301pUFHCeQxIjmTdhIG/tLqWmsS3geJYKi4aRs6AwB9wdvZ2NiIiIXCFUgBIREZHeUVEIrS5I\n65kB5KZpkldYzpThiUSHOfx6xpWTiz0xkagpU7pdG//wQxjh4VStejnQVAF4ZtpwmtrcvJZ/ypJ4\nlspcAI0XoGR7b2ciIiIiVwgVoERERKR3lHw9Q6iHTkAdK2+gtLqJmX6237ldLhq2bME5dw6Go/uC\nlSM+nrj77sP1wQe0l5UFmi6jBsRwx5j+vPL5KRpb+9hJoxGzIDQaDqkNT0RERPyjApSIiIj0jtId\nEJsKcUN6ZLu8gjIMA+4Ym+zX+rqPNmC2t+PM7vz2u84kLFoEHg/Vr752mVl+29LpGbia23l7d6kl\n8SwTGgmjZsPhXHC393Y2IiIicgVQAUpERER6nml6T0ANuQkMo0e2zCssZ9LgOJJjwv1a78rJIWzE\ncMLGjPF7j9BBqcTOnk3tu+/idrkuN9U/uWZIPDelJ7LisxO0drgDjmepzAXQXAMnPu3tTEREROQK\noAKUiIiI9Lyak9BQBmk90353rraZr866mJXpX/tdW0kJzfv24czOxrjEAlniksV4mpqoefvty0n1\nIkunZ1Be18raL89aEs8yw2+HMCccWtPbmYiIiMgVQAUoERER6XklO7yvQ3pmAPmmw+UAzBzb36/1\nrtx1YBjEzp17yXuFjx5N1K23Uv371/G0tFzy8991y/B+jB/k5IVPi+lwewKOZxlHGIyeA0c+hI7W\n3s5GRERE+jgVoERERKTnleRDeBwkje6R7fIKyslIiiIjKbrbtaZp4srNJeqmGwkZ4N+Jqe9KXLIE\nd3U1rvfeu6zn/5xhGCydlkFJVRPrDwU+3NxSWQu8NxkWfdLbmYiIiEgfpwKUiIiI9LzSHd75T7bg\nfxVxNbWz80SV3+13zfv20X76NLHz5l32npHXX0f4+PFUvfwKZkfgN9jNGjuAjKQolm8pwjTNgONZ\nJn0aRMRDgW7DExEREd9UgBIREZGeVV8O1Sd6bP7TlqMVdHhMZvnbfvd+DkZEBLEzZ172noZhkLhk\nMe2nT1Ofl3fZcb5hsxk8M204R8rq2XK0IuB4lrGHwJh5cPQjaG/u7WxERESkD1MBSkRERHpW6dfz\nn9Km9Mh2GwvLSY4JY8KguG7XelpbqduwgZiZd2CLigpo35jbbyd06FAqV6605NRS9sSBpMZFsGxL\ncd86BZW1ANoa4HjghTYRERH5/lIBSkRERHpWST6ERELKhKBv1dLuZuvRCu4Y2x+brfvb7Bq2bMVT\nV4czOzvgvQ27nYTFT9BaeJim/PyA44XYbfx4ajp7S2rYfbI64HiWSbsFopLgkNrwREREpGsqQImI\niEjPKt0BgyZ727eCLL+4isY2t//td7m5OJKTibrxRkv2d2Zn40hKomrlSkvi3T95MIlRoSzbWmxJ\nPEvYHTA2G459DK0NvZ2NiIiI9FEqQImIiEjPaXFB2SEYcnOPbJdXWEZ0mIObMhK7XdtRXU3Dtm3E\n3jMXw263ZH9baCgJjz1K4458mg8VBBwvItTOE7cMY9uxCxw667IgQ4tkLoCOZji2obczERERkT5K\nBSgRERHpOad3A2aPDCD3eEw2FlZw26gkwhzdF5Tq1n8EHR045wXefvfn4n74Q2zR0VStsuYU1CM3\npRET5uD5vnQKashNEJOiNjwRERHpkgpQIiIi0nNKdoDNAYOuC/pW+07XUtnQ6n/7XU4OYWPGED5q\npKV52GNiiH/wAeo/zqOttDTgeLHhITxyUxrrD52n+EIfaXmz2WDsfCja6D3lJiIiIvIdKkCJiIhI\nzynN9w4fDw3shjl/5BWWEWI3mD46udu1rSdO0PLVVziz53W71jRNWjpaLimX+EcewbDbqXr55Ut6\nritP3DKMULuNFz/tQ6egshaAuw2OrO/tTERERKQPUgFKREREekZ7C5zd623X6gEbC8q5MT2R2PDu\nh527cnLBZsM5Z063a18reI07Vt9BVXOV37mEJCfjnD8f19r36Kis9Pu5rvSLDuOB6waz9suznKtt\nDjieJQZdB84hUKA2PBEREbmYClAiIiLSM8596T0hkxb8AeRFFQ2cqGz0q/3O9Hhwrcsl6pYpOJKS\nfK51e9y8deQtXK0uXj50aaeZEp54HLO9nerX37ik57ry5NR0AFZ8dsKSeAEzDMicD8Wboam6t7MR\nERGRPkYFKBEREekZJTu8rz1wAiqvsAyAO/woQDV9sYeOc+f9Gj6+8/xOzjeeZ1D0IN45+g4VTRV+\n5xQ2bBgxM2dS8/bbuBsa/X6uK4PiI8memMrbu0upamgNOJ4lshaApwOOfNDbmYiIiEgfowKUiIiI\n9IzSfEgaDZEJQd8qr6CcCYOcpDgjul3rys3BFhVFzO0zul275vgaEsITWHbHMtweNysOrrikvBKf\nXIKnro7ad9+9pOe68sy0dFo7PLy645Ql8QKWMhHih+k2PBEREbmIClAiIiISfB43nN7dI6efyuta\n2H+6llmZA7pPq7mZ+g0fE3PnndgifBerKpsr2VK6hXkZ80h3pjN/xHxWH1/NuYZzfucWMW4ckTfc\nQPVrr2G2tfn9XFeGJ8dw59gBvLrjFPUt7QHHC5hheE9BnfwUGi70djYiIiLSh6gAJSIiIsFXfgha\n63pk/tOmw+UAzPSj/a5+82Y8jY04s7tvv8stzqXD7ODeEfcC8NT4pzAweOngS5eUX+KSJXSUl+Na\nZ02b2tLpGdS3dPDmrlJL4gUscwGYHjic09uZiIiISB+iApSIiIgEX0m+97Un5j8VlDM0MZIRydHd\nrnXl5OAYmELkdZN9rjNNk7XH13JN8jWkO73DvwdEDeAHI3/A+0XvU1rnf/En6pYphI0ZQ9WqVZge\nj9/PdWX8oDhuGd6PlZ+dpKXdHXC8gPXPhH4j4dB7vZ2JiIiI9CEqQImIiEjwle4A52CIGxzUbepb\n2tlRXMmszAEYhuFzbceFCzR+vgPnPfMwbL6/Eu0p30NJXQn3jbzvW+8vGbeEEFsIzx943u8cDcMg\ncfFi2k6coGHLFr+f82Xp9AwqG1r5494zlsQLiGF4T0GVfA5153s7GxEREekjVIASERGR4DJN7wmo\nHjj9tPXoBdrdJrP8aL9zffghuN04s+d1u3b1sdXEhMYwM23mt95PikziwdEP8uGJDymuLfY7z9i7\n7iQkNZWqFSsxTdPv57pyU3oiEwfH8eKnxXS4Az9VFbCsBYAJhWrDExERES8VoERERCS4qk9AYwWk\nBb8AtbGwnMSoUCYNie92rSs3l/Bx4whLT/e9rtXFppJNzE2fS7gj/KLPH896nAhHBMv3L/c7T8Ph\nIOHxx2nev5/mvXv9fq7LeIbBs9OHc6ammXUH/R+KHjRJo6B/FhToNjwRERHxUgFKREREgqtkh/d1\nSHAHkLd1eNhypII7xvTHbvPdftdy7BithYdxzuv+9NMHJz6gzdPGwhELO/08Pjyeh8c+TF5JHkeq\nj/idb9zCBdjj46lasdLvZ3y5fXQyI/tHs3xLMR5P4KeqApZ5L5zeBbWnezsTERER6QNUgBIREZHg\nKs2HiATvqZgg2nmiivrWDmZldt9+V5ebCw4HsXPu9rnONE1WH1vNuH7jGJXQdf6PZT5GTGgMy/Yt\n8ztfW0QE8Q8/RMOnn9Jy7Jjfz3UZz2awdNpwjlc0/OkmwF6VtcD7WqBh5CIiIqIClIiIiARbyQ7v\n/KduhoIHKq+wjMhQO1OG9/O5znS7ceWuI/rWW3EkJPhce7DyIEW1RSwYscDnutjQWBZlLmLrma18\ndeErv3OO/9GPMCIiqF61yu9nfJk7PoXBCREs21psyWypgCSkQ8pEteGJiIgIoAKUiIiIBFN9GdSc\nDPr8J4/HZFNhBVNHJBEeYve5tmnXLjoqKnBmZ3cbd82xNUQ4Ipg9bHa3ax8a8xBxYXE8t/85v/N2\nxMcT94P7cH24nvZzgc9ucthtPDU1gwOna8kvrgo4XsCyFsC5fd45YCIiInJVUwFKREREgqeH5j99\nddZFWV2LX+13rpwcbDExRE+f5nNdQ1sDG05t4O5hdxMVEtVt3KiQKBZnLWbHuR3sKdvjb+okLloE\nQNWrr/r9jC/3XTuIpJgwlm/1/1a+oMm81/uqNjwREZGrngpQIiIiEjyl+RASCSnjg7pNXmEZdpvB\njNHJPtd5Ghup27iJ2NmzsYWF+Vy7/uR6mjuauxw+3pkfjv4h/SL68dz+5/xugQsZOBDnnLup/eNq\nOmpq/N6rK+EhdpbcMoztRZUcOF0bcLyAxA2BQdfBIRWgRERErnYqQImIiEjwlOR7CxD2kKBuk1dQ\nzg3DEoiLDPW5rn7TJsymJpzZ3d9+t/b4WkbGjySrX5bfeUQ4Inhy3JPsLd/LzvM7/X4uYfFizOZm\nat5+2+9nfHnoxjRiwx0s31pkSbyAZC2E8q+g8nhvZyIiIiK9SAUoERERCY7mWig/BGnBbb87WdnI\n8YoGZo71p/0ul5BBg4i45hqf645UH6GgqoCFIxZiXOLw9PtG3seAqAE8t8//U1DhI0cSfdtt1Lz+\nBp7m5kvarzPRYQ4W3TyUjwvKOV5eH3C8gIydDxhwSMPIRURErmYqQImIiEhwnN4NmN4b8IJoY2EZ\nQLcFqPbychrz83HOm9dtUWn1sdWE2cOYkz7nkvMJtYfy1PinOFh5kG1ntvn9XOKTS3DX1FC71ppC\nzaIpw4gIsfP8p708Cyo2xVuEPLQGevtmPhEREek1KkCJiIhIcJTuAJvD24IXRHkF5WQOjGVQfKTP\ndXUffACm2W37XXNHM+tPrGdm2kycYc7Lyil7eDaDogexbP8yPKbHr2cirr2WiIkTqX75FcyOjsva\n988lRIXywPWDydl/jtPVTQHHC0jmvVB5FCoKezcPERER6TUqQImIiEhwlORDykQI9V0YCsSF+lb2\nltYwa+wAn+tM08T1fg4REycSmpbmc23eqTzq2+svafj4d4XYQnhm4jMcrj7MJ6Wf+PWMYRgkPrmE\n9rNnqdvw8WXv/eeevDUdmwErPjthSbzLNjYbDJva8ERERK5iKkCJiIiI9dpb4NyXkBbc9rvNR8ox\nze7b71qPHKH1+HGc87O7jbnm+BqGxg7l2v7XBpTbnGFzGOYcxrJ9y3B73H49Ez19OqEZGVStXOn3\n/ChfBsZFcO+kVN754jQX6lsDjnfZopNh6K1QsFZteCIiIlcpFaBERETEemf3grsNhgR3AHleQTmD\n4iMYkxLjc53r/RyMkBBi77rL57ri2mL2Vey7rOHj32W32Vk6cSnFrmI+OvWRX88YNhuJTzxB65Ej\nNG7/PKD9v/H0bRm0uT28/PlJS+JdtqwFUH0Czh/o3TxERESkV6gAJSIiItYr3eF9HXJj0LZobO3g\ns6JKZo0d4LNYZHZ04PrwQ6KnTcMeF+cz5trja3HYHMwb7ntOlL9mpc1iZPxInt//PB0e/+Y6Oe+Z\ni6N/f6pWrrQkh/SkaO7OSuH1/BJcze2WxLwsY+Z5Z4IVqA1PRETkaqQClIiIiFivJB+SxkBkQtC2\n2HbsAm0dHmZl+m6/a9yxA3dlZbfDx9vcbeQW5zJj8AwSwq3J22bYeHbis5TWl7KueJ1fzxihoSQ8\n9hhNu3bR/NVXluTxzLQMGlo7eGNniSXxLktkAqRPh4L31IYnIiJyFVIBSkRERKzlccPp3UGf/7Sx\nsJy4yBAmp8X7XOfKycXudBI9darPdZtLN1PbWsvCkZc/fLwz0wdPJzMxkxcOvEC7278TSHH3348t\nNpaqFdacgspKdXLbyCRe3n6S5jb/5lEFRdYCqC31tmiKiIjIVUUFKBEREbFW2VfQVh/U+U/tbg+f\nHKng9tH9cdi7/jrjbmigftMmYufcjREa6jPm6uOrSY1O5cYUa9sGDcPgp5N+yrnGc6w97l/7mT06\nivgHH6R+40ZaT1ozu+nZ6cOpamzjnS9KLYl3WUbPAXuobsMTERG5CqkAJSIiItYqzfe+BvEE1Bcn\nq3E1t3fbflf/cR5mayvObN+3352uO82u87u4d/i92Azrvx7dPPBmJiVP4qWDL9HS0eLXMwmPPIwR\nEkL1y69YksP1wxKYnBbPS9tO0NbhsSTmJQt3wvA7vG14nl7KQURERHqFClAiIiJirZId4BwCzkFB\n2yKvsJzwEBtTRyT5XOfKySE0LY3w8eN9rltbtBabYWP+8PlWpvkn35yCqmiu4N2j7/r1jKNfP5wL\n7sX1/vu0V1RYksez04dzztVCzv6zlsS7LJkLoP4cnN7ZezmIiIhIj1MBSkRERKxjmt4TUEE8/WSa\nJhsLy7lleBIRofYu17WfPUvT7t0452f7vCWv3dPO+0XvMzV1Kv2jfJ+oCsR1A67jhpQbWHVoFU3t\nTX49k/jEE5huNzWvv25JDtNGJTEmJZbnPy3G7emlQeCj7gJHuNrwRERErjIqQImIiIh1qoqg8QIM\nCV4BquBcHWdrm7ttv3Ot+wCA2Ht833732ZnPqGyutHz4eGd+MvEnVLdU89aRt/xaHzpkCDF3zqLm\n7T/grq8PeH/DMFg6LYMTFxrJKygLON5lCYuBEbOgMMc7sF5ERESuCipAiYiIiHVKdnhf06YEbYu8\nwnJsBtw+OrnLNaZp4srNJXLyZEIHpfqMt+b4GpIjkrkl9RarU73IxOSJ3Jp6K68ceoX6Nv8KSomL\nl+BpaKD2nXcsyeHucSkMTYxk+dZiTLOXTkFlLYDGCji1vXf2FxERkR6nApSIiIhYpzQfIvtBvxFB\n2yKvoIzJQxNIjA7rck3LoUO0nThBbLbv009ljWVsP7ud+SPm47A5rE61U89Oepa6tjpeL/SvrS4i\nK5PIm26k+rXf42lrC3h/u83gqdsy+Oqsi8+OVwYc77KMuBNCoqBAbXgiIiJXCxWgRERExDolO2DI\njeBj5lIgTlc3caSsnllju2m/y8nFCA0l9q67fK57r+g9PKaHe4ffa2WaPmUmZnLHkDt4vfB1altq\n/XomcckSOi5cwJWTY0kOC65JpX9sGMu3FlkS75KFRsKo2VCYC+723slBREREepQKUCIiImKNunNQ\nWwJpNwdti7zCcgBm+ihAmW1t1H34IdG3z8AeE9PlOrfHzXvH3+OmlJsYFBO8G/s6s3TiUhrbG3m1\n4FW/1kfdfDNhY8dQveplTHfgc5PCHHaevDWdnSeq2VtSE3C8y5K1AJqr4eSnvbO/iIiI9CgVoERE\nRMQa38x/CuIA8ryCMkYPiCEtMarLNQ3bt+OuqcGZne0zVv75fM43nu+R4ePfNSJ+BHcNu4u3jrxF\nZXP3bXCGYdBvyRLaTp2i/pNPLMnhweuHEBcZwvO9dQpq+B0QFqvb8ERERK4SKkCJiIiINUrzITQa\nBowPSvjqxja+OFXtV/udPSGB6Cm+B6GvObaGhPAEZgyeYWWafls6YSmt7lZePvSyX+tjZs0iZPBg\nqlausmR4eFSYg0U3D2XT4QqOlNUFHO+SOcJg9Bw4/AF0tPb8/iIiItKjVIASERERa5Tkw6DrwB6c\nYd6bj1TgMWHm2AFdrnG7XDRs3kzs3DkYISFdrqtsrmTr6a3My5hHiL3rdcE01DmUe9Lv4Z0j71De\nWN7tesPhIPGJx2k5eJCmL76wJIdFNw8lMtTO81uLLYl3yTIXQKsLijf3zv4iIiLSY1SAEhERkcA1\n10BFYXDnPxWUkeIMJys1tss1dRs+xmxvxznPd/tdbnEuHWYHC0YssDrNS/L0hKfxmB5WfLXCr/XO\ne+/FnphI1cqVluwfFxnKQzcMYd2Bc5RUNVoS85KkT4PwOLXhiYiIXAVUgBIREZHAle4CzKDNf2pu\nc7Pt+AVmje2P4eOGPVdODqHDMwjPHNvlGtM0WXt8Ldf2v5ZhzmHBSNdvg2IGsWDEAtYcX8PZhrPd\nrreFh5PwyMM0bvuMlqNHLclhya3pOGw2Xtx2wpJ4l8QRCmPugaProb255/cXERGRHqMClIiIiASu\ndAfYQmDQ5KCE/+z4BVraPczK7Lr9rq20lOYvv8Q5L9tnkWpP+R5K6kpYOKLnh4935snxT2LDxosH\nXvRrffyDD2KLjKRq5SpL9u8fG87Cawexes8ZKupaLIl5SbIWQlsDHN/Y83uLiIhIj1EBSkRERAJX\nkg8DJ0FIRFDCbywsJzbcwfXDErpc48pdB4aB8565PmOtPraamNAYZqbNtDrNyzIgagD3j7qf3OJc\nTrlOdbve7nQSd//91K1fT9uZ7k9N+ePp29Lp8HhYuf2kJfEuydBbIbIfFKgNT0RE5PtMBSgREREJ\nTHsznNsHacFpv+twe9h0uJwZo5MJsXf+1cU0TVy5uUTecAMhKSldxnK1uthUsom56XMJd4QHJd/L\nsXjcYkLtoTx/4Hm/1icsegxsNqpffdWS/dMSo5g7fiBv7iyhtqnNkph+sztgbDYc3QCtDT27t4iI\niPQYFaBEREQkMGf2gKcdhgRnAPnekhpqmtp9tt8179tPe2kpzmzfw8fXFa+jzdPWZ9rvvtEvoh8P\njn6Qj05+RFFNUbfrQwYMwDl3LrWrV9NRU2NJDs9My6Cxzc1rO0osiXdJshZARzMc29Dze4uIiEiP\nUAFKREREAlOaDxgw5IaghM8rLCfUYWPqyKQu17hyczDCw4mZ2XVbnWmarDm+hnH9xjEqYVQwUg3I\n45mPExkSyfIDy/1an7hkMWZLCzVvvGnJ/mNSYrl9dDKv7DhJY2uHJTH9NuQmiB4ABe/17L4iIiLS\nY1SAEhERkcCU7IDksRARb3lo0zTZWFjOlIxEosMcna7xtLVR99EGYmbOxB4d1WWsg5UHKaot6nOn\nn74RFx7HI2MfYWPJRgqrCrtdH5aRQfSMGdS88QaepiZLclg6PYPapnbe3l1qSTy/2eyQOd87iLyl\nrmf3FhERkR7hVwHKMIyXDcOoMAzj0J+9978MwzhrGMb+r/+6+88++1vDMIoMwzhqGMadwUhcRERE\n+gB3B5z5Imjzn46W11Na3eSz/a5h61Y8LhfOefN8xlpzbA2RjkhmD5ttdZqWeWTsI8SGxrJs/zK/\n1icuWYLb5aJ29RpL9r82LYEbhiWw8rOTtHa4LYnpt8wF4G6Fo+t7dl8RERHpEf6egHoVuKuT939j\nmubEr/9aD2AYxljgASDz62eWG4ZhtyJZERER6WPKDkJbg7eFKgjyCsoxDLh9THKXa1w5uTiSkoi6\n6cYu1zS0NbDh1AZmD5tNZEhkMFK1RGxoLI9nPc62M9s4cOFAt+sjr5lExLXXUvXqK5jt7ZbksHT6\ncMrqWnjvS2tu2PPboOsgdhAc0m14IiIi30d+FaBM09wGVPsZMxv4g2maraZpngSKgOsvMz8RERHp\ny0rzva9pwRlAnldYxjVD4kmO6fzGuo6aGhq2bSN27lwMR+ctegDrT66nuaO5z7bf/bkfjf4RCeEJ\nPLfvOb/WJy5ZTMe589R99JEl+08d0Y+s1Fhe+LQYt8e0JKZfbDbIuheKN0OzNYPVRUREpO8IdAbU\nTwzDOPh1i943gx9SgdN/tubM1++JiIjI903JDohLg9iBloc+V9vMobN1zBzbv8s1devXQ3s7zvm+\nb79bc3wNI+NHktUvy+o0LRcZEskTWU+w8/xOvij7otv10bfdRtiI4VStXIVpBl4wMgyDpdOGc6qq\nifVfnQ843iXJXOC9UfHwBz27r4iIiARdIAWo54EMYCJwHvjVpQYwDOPHhmHsMQxjz4ULFwJIRURE\nRHqcaULpzqCdftpYWA7ALB8FKFduLmGjRhE+qutb7Q5XHaawqpCFIxZiGIbleQbDD0f9kKSIJJ7b\n91y3RSXDZiNh8WJajx2jcds2S/a/M3MA6UlRLN9abElRy28DJ0H8UDhkzUwrERER6TsuuwBlmma5\naZpu0zQ9wAr+/za7s8DgP1s66Ov3Oovxkmmak03TnJyU1PXVyiIiItIHVR6HpsrgzX8qLGN4cjTp\nSdGdft564iQtBw7izO7+9FOYPYw56XOCkWZQhDvCeXL8k3xZ8SX55/K7Xe+cMwdHSgpVK1Zasr/d\nZvD0bRkcPl/H1qM9+COhYXhPQZ3cBo2VPbeviIiIBN1lF6AMw0j5s/95L/DNDXm5wAOGYYQZhjEM\nGAHsvvwURUREpE8q3eF9DcIJKFdTOztPVPs+/bQuF2w2Yud2XVhq7mhm/Yn1zEqbhTPMaXmewbRw\nxEJSolL4z33/2f0pqJAQEhc9RtOePTTv32/J/vMnpjLQGc7yrUWWxPNb1gIw3VCY07P7ioiISFD5\nVYAyDONtIB8YZRjGGcMwFgP/ahjGV4ZhHASmAz8DME2zAHgXKAQ2AM+aptnD9/iKiIhI0JXkQ1QS\nJA63PPSWoxW4PWaX859Mj4e6nFyibr6ZkOSub8jLO5VHfXs9C0f2/eHj3xVqD+XpCU9zqOoQW09v\n7XZ93H33YXM6qVxpzSmoUIeNJ6em88WpGnaf9PcuGgv0z4LEEVDwXs/tKSIiIkHn7y14D5qmmWKa\nZohpmoNM01xlmuYjpmmOM01zvGma80zTPP9n6//JNM0M0zRHmaZpzZUsIiIi0reU7oAhN3rbpiyW\nV1hGckwYEwbFdfp58969tJ8751f73dDYoVyTfI3lOfaEezLuYUjMEJbtX4bH9Phca4uKIv5HUWau\nTwAAIABJREFUD9LwyWZaT5ywZP8HrhtCQlRoz56CMgzvKahT26G+rOf2FRERkaAK9BY8ERERuRq5\nzkJtKQyxvv2upd3N1qMXmDm2PzZb58Wt2pwcbJGRxNxxe5dximuL2Vex74oaPv5dIbYQnp7wNEdr\njrKxZGO36xMefhgjNJSqVass2T8i1M4TU4ay9egFCs65LInpl8wFgKk2PBERke8RFaBERETk0pV+\nPRg7zfoB5DuKK2lqczMrc0Cnn3taWqjf8DExd96JLSKiyzhrjq/BYXMwb/g8y3PsSXcPu5t0ZzrL\n9y/H7fE91cCRmEjcwgW4ctfRXl5uyf6P3DSU6DAHy7cWWxLPL8mjITkTDq3tuT1FREQkqFSAEhER\nkUtXsgNCo6H/OMtDbywsJzrMwY3pCZ1+3rB5M56GBpzZXReW2txtrCtex4zBM0gI7zzOlcJus/Ps\nxGc54TrB+pPru12f8Pjj4HZT/drvLdnfGRHCwzemsf6r85y40GBJTL9k3Qund4LrTM/tKSIiIkGj\nApSIiIhcutJ8GHw92B2WhnV7TDYWljNtVBJhDnuna1w5uThSUoi8/vou42wu3Uxta+0VOXy8M3ek\n3cGo+FE8f+B52j3tPteGDh5M7F13UfvOO7jr6izZ/4lbhhJit/Hip9bMlvJL5gLvq4aRi4iIfC+o\nACUiIiKXpqkaKgqDMv9p/+kaKhvaumy/66ispGH7dpxz52LYuv4as/r4alKjU7kx5UbLc+wNNsPG\nTyb9hNP1p8ktyu12feKSxXgaG6n5wzuW7J8cE84PJw9m7b4znHc1WxKzW4kZkDJBbXgiIiLfEypA\niYiIyKU5vcv7GoT5T3kF5YTYDaaNSur087r168Ht9tl+d7ruNLvO72LBiAXYjO/PV53bBt3GuH7j\nePHgi7S523yuDR87lqgpU6j+/e/xtLZasv+Pp6bjMWHFtpOWxPNL5gI49yVU9+CeIiIiEhTfn29l\nIiIi0jNKdoAtBFKvtTSsaZrkFZZzY3oiseEhna5xvZ9DeGYmYcOHdxlnbdFabIaN7IxsS/PrbYZh\n8JNJP+F843nWHF/T7frEJ5fgrqzE9b41N8kNTogke8JA3t5dSnWj7wKYZTLv9b6qDU9EROSKpwKU\niIiIXJrSfEi9BkK6voHuchRfaOBkZWOX7Xetx4/TUliIM7vrwlK7p533i95naupU+kf1tzS/vuCm\nlJu4JvkaXjr4Es0dvlvhIm+4gfCsLKpeXoXp9n17nr+enpZBc7ubVz/voRNJ8WmQOhkK1IYnIiJy\npVMBSkRERPzX1gTn9sEQ69vvPi4oB2DmmM4LR67cXLDbiZ1zd5cxtp3ZRmVz5fdm+Ph3GYbBTyf9\nlMrmSt49+m63axOXLKG9pJT6jZss2X9k/xhmje3PqztO0dDaYUnMbmUthLKvoLKoZ/YTERGRoOgz\nBShPfX1vpyAiIiLdObsHPB2QZv0A8rzCciYMjmOAM/yiz0y3G9e6D4i+9VYciYldxlhzbA3JEcnc\nknqL5fn1FZMHTOamlJtY9dUqmtqbfK6NmXkHoWlpVK1ciWmaluy/dPpw6lo6eHNniSXxupU5HzB0\nCkpEROQK12cKUG0lpVS98mpvpyEiIiK+lOQDBgy+wdKw5XUtHDhdy6yxnZ9+atq9m46yMp/Dx8sa\ny/j83OfMHzEfh81haX59zU8m/YSa1hrePPymz3WG3U7CE0/QcugQTbt2WbL3xMFxTBmeyMrtJ2lp\nt6a1z6fYgd4Td7oNT0RE5IrWZwpQNmcsFb/8JeX/8i+YHk9vpyMiIiKdKd0B/TMhIs7SsBsLve13\nXRWgXDm52GJiiJ4+vcsY7xW9h2maLBixwNLc+qLxSeO5bdBtvFLwCnVtdT7XOudnY+/Xj6oVKy3b\nf+m04Vyob2XNl2csi+lT1gK4cBjKC3tmPxEREbFcnylAhQ4eTMJjj1L92u85+1f/1bIrg0VERMQi\n7g44/UVQ5j/lFZYzrF8Uw5OjL/rM09REXV4esXfdiS384vY8ALfHzXvH3+OmgTeRGp1qeX590bMT\nn6W+rZ7XC1/3uc4WFkbCo4/S+PnntBRaU8C5OSORCYPjeOHTYjrcPfDD4dhsMGxqwxMREbmC9ZkC\nFED/v/1bkv/6r6nfsIHTi5fgdrl6OyURERH5RtkBaG+ENGsLUHUt7eQXVzJrbH8Mw7jo8/pPPsFs\navJ5+13++XzON56/Kk4/fWNM4hhmps3k9cLXqWmp8bk2/oEfYouKomrlKkv2NgyDpdMyOF3dzIdf\nnbckpk/RyTD0Fm8bnkWzrERERKRn9akCFEDi44sY+Kt/p/nAAU499BDt5871dkoiIiICX89/AoZY\nO4D806MXaHebzOyq/e79HEJSU4m45pouY6w5toaE8ARmDJ5haW593dIJS2lqb+KVgld8rrPHxhL3\nwA+p27CBttOnLdl75pj+jEiOZvmWYjyeHigKZS6A6mIoOxj8vURERMRyfa4ABeCcM4fBK1fSUV7B\nqQcepOXo0d5OSURERErzIX4YxKZYGjavsJx+0aFMGhJ/0Wft5RU05ufjzJ6HYev8a0tlcyVbT29l\nXsY8QuwhlubW1w2PH87d6Xfz9uG3qWyu9Lk24dHHMOx2ql/xXazyl81m8My0DI6W17P5SIUlMX0a\nMw8Mu4aRi4iIXKH6ZAEKIOqG60l74w0wDEoeepjGnTt7OyUREZGrl8cDJTsgzdrTT60dbrYcqeCO\nMf2x2y5uv6v74APweHDO6/r2u5yiHDrMjquq/e7PPTPhGdo97az6ynd7XUj/ZGKz51G7Zi0dVVWW\n7H3PhIEMio9g2dYizGC3xkUlQsZ07xwoteGJiIhccfpsAQogfNRIhr7zB0JSUih98se41n3Q2ymJ\niIhcnSqPQXO15QPId56opqG1g1mZXbTf5eYSMWECoUOHdvq5aZqsPb6Wa/tfyzDnMEtzu1KkxaYx\nL2Me7xx9h7LGMp9rE59YjNnWRvUbb1iyd4jdxlNT09lXWsvOE9WWxPQpcwHUlsLZL4O/l4iIiFiq\nTxegAEIGDCDtzTeInDiRcz//OVUrVwb/FzYRERH5ttId3leLT0BtLCwjMtTOzRn9Lvqs5cgRWo8e\nJTa769NPe8r3UFpfysIRCy3N60rz1ISnMDF56eBLPteFpQ8j5o7bqXnrbTyNjZbs/YPJg+kXHcry\nrUWWxPNp9Bywh8KhNcHfS0RERCzV5wtQ4B2cOXjVSmLvnk3Fv/+K8n/6Z0y3u7fTEhERuXqU5ENU\nMiSkWxbS4zHZWFjObSOTCA+xX/S5KycXQkKInT27yxirj60mJjSGmWkzLcvrSpQancrCEQt57/h7\nnKk/43Nt4pIleFwuav74R0v2Dg+xs/iWdD47XsnBM7WWxOxSRBxk3A4F73nbQkVEROSKcUUUoABs\noaEM/Pd/J+Hxx6l54w3O/uXP8LS09HZaIiIiV4fSfEi7CYyL5zRdroNnXZTXtXbafmd2dOD6YB3R\nt03FEX/xcHIAV6uLTSWbmJs+l3BHuGV5Xal+PP7H2G12Xjjwgs91ERMmEDl5MtWvvobZ1mbJ3g/f\nOISYcAfLtxRbEs+nrAVQfw5O7wr+XiIiImKZK6YABWDYbPT/6/9O/7/9G+o3baL0icW4a4P8S5uI\niMjVrvY0uE7DEGvb7/IKyrDbDKaPSr7os8b8nbgvVOLMzu7y+XXF62jztF317XffSI5M5v5R97Pu\nxDpOuk76XJv45BI6yspwfbjekr1jwkN47KahfFxYRlFFvSUxuzRqNjjCvcPIRURE5IpxRRWgvpHw\n2GOk/ubXtHz1Fad+9BDtZ8/2dkoiIiLfX6X53tc0aweQbyws54ZhCcRFhl70mSsnB5vTSfRtt3X6\nrGmarDm+hnH9xjEqYZSleV3JFmctJswexvP7n/e5LmrqVMJGjqRq1UpMi1rZHp8ylDCHjee3nrAk\nXpfCYmDETCjMAY9GMoiIiFwprsgCFEDsXXcxeNVKOiorOfnAA7QcPtzbKYmIiHw/leyAsFjon2VZ\nyBMXGjhe0cCssRe337kbGqnftInYu2djC724OAVw4MIBimqLdPrpOxIjEnlozENsOLWBYzXHulxn\nGAaJSxbTVlRMw9ZPrdk7OowHrhtCzv6znKlpsiRmlzIXQEM5lHwe3H1ERETEMldsAQog6vrrGfrm\nGxiOEEoefoSGz/UlRERExHKl+TD4erBdPCj8cm0sLAdgZuaAiz6rz8vDbGnBOa/r2+/WHF9DpCOS\n2cO6HlB+tVqUuYiokCiW71/uc13s7Nk4BqZQtXKlZXs/OdU7pH7FtiCfghp5J4REwSG14YmIBF1l\nEbz9IGz/LbQ29HY2cgW7ogtQAGEjRjD0D28TkprK6aeexpWT09spiYiIfH80VcOFIzDE2va7vMJy\nMgfGkhoXcdFnrtxcQtKGEDFxYqfPNrQ18PGpj5k9bDaRIZGW5vV94Axz8ujYR/mk9BMKqgq6XGeE\nhJC46HGav/ySpi+/tGTv1LgI7p2Uyh++OE1lQ6slMTsVGgWj7oLDueBuD94+IiJXu4L34KVpULwF\nNv1/8Ntx8NmvoDXI8/7ke+mKL0ABhPTvT9qbbxA5eTLn/vpvqHzxJUzT7O20RERErnx/mv9k3QDy\nC/WtfFlaw6yxF59+aj9/nqZdu3DOm4fRxY1760+up7mjmftG3mdZTt83D499GGeYk2X7lvlcF3ff\nQuxxcVStXGXZ3k9Py6DN7eGVz30PQg9Y5gJoqoKT1rQQiojIn+log4/+Gv64CJLHwE/3wOKNkHot\nfPK/vYWoT/8NWly9nalcQb4XBSgAe0wMQ156kdi5c7nwm99Q/o//iOnWYEoREZGAlOwAeygMvMay\nkJ8cLsc0YVbmxfOfXOs+ANPstv1uZPxIMhMzLcvp+yYmNIbHMx/ns7Ofsb9if5frbJGRxD/0EA2b\nN9NaVGTJ3hlJ0czOGsDvd5RQ1xLE00nD7/DOJjv0XvD2EBG5GtWehldmw64X4MalsOhDcA7ytuM/\nvBqWbIbBN8CW/+MtRG39JTTrdnrpXp8pQFU2tAZ8askIDWXgv/6ShMVPUPPW25z5i7/A09JiUYYi\nIiJXodJ876+dIeGWhcwrLGdwQgSjB8R8633TNHHl5BBx7bWEDh7c6bOHqw5TWFXIwhELuzwhJV4P\njn6QhPAEntv3nM918Q8/hBEeTtWqly3be+m04dS3dvDGzhLLYl4kJBxG3Q1H1nl/qRcRkcAd3wQv\n3goXjsL9v4e7/gUc37kQZNC18KN34MdbIe0W2PrP8NvxsOWfva37Il3oMwWo864W/vvqg7R1BHYV\nsGGz0f/nP6f///yfNHyymdJFj9NRU2NRliIiIleRtkY4f8DS+U+NrR1sL6pk5pgBFxWQWg4V0FZc\njDPb9+mnMHsYc9LnWJbT91VkSCRLxi1hV9kudp/f3eU6R3w8cffdh+uDD2gvK7Nk76xUJ1NHJvHy\n9pO0tAfxRHrWAm/7R/Hm4O0hInI18Lhh8/+BN++D2FR46lMYm+37mYGT4MG34KnPIH0qfPpLbyHq\nk39UIUo61WcKUMkxYfxx7xkeXrWL6sbAf8VKeORhUn/7W1oKCyl58Ee0nTljQZYiIiJXkTNfgKfD\n0vlP245doK3D03n7XW4uRmgosXfd1emzTe1NfHjiQ2alzcIZ5rQsp++z+0fdT3JkMs/tf87nSfOE\nRYvA46H61dcs23vptAwqG9p4d89py2JeJH06hMdBgW7DExG5bA0X4PV7Ydu/waSHYMkmSMzw//mU\n8fDDN+Dpz2H47d4h5b8dB5v+FzRWBi1tufL0mQJU/9hwfvfARPafruXe5Z9TVBH49Y6xd85iyCsv\n01FTw6kHHqS5oOubYEREROQ7SvIBwzvzwSJ5heXER4YwOS3+W++b7e3Uffgh0TNmYI+N7fzZkjwa\n2htYOHKhZfl834XZw/jxuB+zr2Ifn5/7vMt1oYNSib37bmrffRe3y5qBsjcMS+CaIXG8+OkJ2t2B\nnXDvkiMUxsyFI+uhXWMXREQuWUm+t+Xu9C7IXub9K+TiG2r9MiAL7n8NlubDyDth+2+9J6Ly/s5b\n5JKrXp8pQNFQQfb4FN5+8kYaWzu4d/nnbD8eeLU08tprGfrWmxihIZQ+8igNn223IFkREZGrQOkO\n75fJcGtOG7W7PXxyuJzbx/THYf/2V5CG7dtxV1f7HD6+9vhahjmHcU2ydQPRrwYLRixgYNRAntvn\n+xRU4pLFeJqaqHn7bUv2NQyDZ6cP52xtM7n7z1kSs1NZC6GtHoo2Bm8PEZHvG9OEz/8DXp3jLTgt\n2QSTHrYmdvIYuO9leHYXjJ4D+c95T0R9/D+hvtyaPeSK1HcKUHVn4d1HuLa/nfefncJAZwSPvbLb\nkuGVYRkZDH37D4QMGcLpZ56hdq1uSxEREfHJ3Q5n9sAQ69rvdp+spq6lg5ljO2m/y8nFHh9P9K23\ndPpscW0x+yr2afj4ZQixh/D0hKcpqCpgy+ktXa4LHzWKqKm3Uv371y27xGXG6GRGD4jh+U+L8XgC\nu2ymS0OnQmQ/OKQ2PBERvzTXwjsPw8a/8xaIfrwVBoyzfp+kUbBwBTy7GzLnw87l8Lvx8NHfQN15\n6/eTPq/vFKCcg+DoR7BiOoPaS1mz9GZuG5nEL94/xD+sK8Ad4JeWkP7JpL3xOlHXX8f5//E/qHzh\nhYBv3RMREfneOn8A2psgzboB5BsLywkPsTF1RNK33nfX1dGweTOxc+ZghIR0+uya42tw2Bzck3GP\nZflcTe7JuIe02DSe2/8cHrPrdrjEJUtwV1fjes+aH+sMw+CZaRkUVTSQVxikX73tDhg7D45t8A7O\nFxGRrp3bDy/d5v135p3/4r3pzsdJ57YOD6/tOMXUf93C9H/fykMrd/Lf/niAX+cd5e3dpXx67ALH\ny+tpaO3oes9+I+DeF+AneyDrPtj9EvxuAqz/ObjOBuFvUvoqR28n8CdRSfDYW/DHx2Dl7UTPX86K\nR+fxz+sPs2r7SU5VNvIfD04iJrzzL6b+sEdHM/iFFzj3i19w4be/o/18GQP+7hcYjr7zj0FERKRP\nKNnhfbXoBJRpmuQVlHHriCQiQu3f+qxuwwbMtjac2Z3fttPmbmNd8TpmDJ5BQniCJflcbRw2B89M\neIa/+exvyDuVx13DOh/0HnnddYRPGE/Vy68Q94MfWPIdac64FH6Vd4zlW4u4M7N/cE6wZS6APS97\n/w9VlmaEiYhcxDRh76vw0V9DVD9YtB6G3NDlco/HJOfAWX6Vd4wzNc1cPzSBpNgwztc2s/14JRX1\nLXz3jEhsuIOBcRGkOMNJiYsg9Zs/OyMYGBfOAOdQwuYvg6n/Dbb/2vvv7b2vwqRH4JafQdzgoP4j\nkN7XtyovQ6fAU9vg3Ufh3UexT/kL/m7235OeFMXf5xRw3/P5rHxsMoMTIi97CyM0lIG//CUh/QdQ\ntWIFHRUVpP76V9giLnPQmoiIyPdRaT4kpEPMxe1yl6PgXB3nXC38bObIiz5z5eYSmp5OeFZmp89+\nUvoJta21Gj4eoLuG3sXKr1aybP8y7ki7A4ft4q+BhmGQuGQJZ3/6X6jPyyP27rsD3tdht/H0bRn8\nj/e+4vOiKm4Z0S/gmBdJuxmi+3vb8FSAEhH5trZG+OCv4OAfIGMGLFjhLUJ1wjRNthyt4F83HOVI\nWT2ZA2P5p3vHMXVEv2/9gNDu9lBR38q52mbO1TZz3tXC+dpmzta2cN7VzIEzrk5vt+8XHcbAuHBS\nnI8xZmw2d1a/xai9v4cvf09L5oOETf+v2BOGBuufhPSyvlWAAogdCIs+hA1/C5//Ds7t56H7XiYt\n4XqWvrmX+cs+56VHJ3Ptd27PuRSGYZD8X/8KR8oAyv/x/1CyaBGDn38eR4J+VRUREcHj8RagRs2x\nLGReQRk2A24f8+2CVtuZMzTv2UvSz37W5cmYNcfWkBqdyo0pN1qWz9XIbrPz7MRn+dnWn7H+5Hrm\nZXQ+8D3m9tsJHTaMypUriZk925ITSwuvTeW3m46xbEtRcApQNjuMne/9Jb2lDsI7v0lRROSqc+GY\n94DHhSMw7W9h6s+9/87sxJ5T1fzrhqPsPlVNWmIk//HgJOaOS8Fmu/i/AyF2G6lfn3LqSnObm/Mu\nb3HKW6jyFqfOuVoovtDI9toOftu2kIHcxjOOXO4/+Baeg2/yoWM6H8f/CHtiOilx4V+fpPKephoY\nF0F8ZIjmQV6h+l4BCsARBnN/DanXeCu1L03jlvt/z9qlU1j82hc8uGIn/3bfeLInpga0TcKPfoQj\nKYlz/+3nnHrwQYasWEHokCEW/U2IiIhcoSqPQnONpfOf8grLmTw0gYSo0G+978rNBcB5z9xOnztd\nd5pdZbv46aSfYjP6zujKK9XtQ25nTMIYlu9fzuxhswmxXTzawLDZSFz8BOd/8Xc07thB9JQpAe8b\n5rDz5K3p/NP6w+wrrWHSkMv/IbFLWQtg94vemaITfmh9fBGRK81Xq2HdX3j///Uja72nnzpxtKye\nf/v4CJsOV5AUE8Y/zs/igesGE2IP7L+7EaF20pOiSU+K7vRz0zSpa+nwFqVq7+LDslMMPbKC2eU5\nzKnczIaa6fym5R6K3Mnfei48xMZAZwQpcd+090Uw8E9tf973osL6Zqnjamf0lUHckydPNvfs2XPx\nB+f2wTuPQEMFzPkVNaN+yFNv7GX3yWr+y4zh/OUdIzutyF6Kpi/3ceaZZ8DhYPALLxAxLiugeCIi\nIle0L1bBh38FP/0SEjMCDlda1cTUf9vCL+aMYcmt6X963zRNiu+6i5ABKaS99mqnz/7uy9/xyqFX\nyLsvj+TI5E7XyKXZdmYbz37yLH9/09/zg5E/6HSNp62N4jtmEpqRTtorr1iyb0NrB1P+72auH5bA\nikcnWxLzWzwe+G2W9yanH71jfXwRkStFRyvk/cI77HvwDXDfK+C8+PDGmZomfr3xGO/tO0t0qIOn\np2Xw+JShRIb2cvGm7ry3G2rvK5judlrGLOTU2GcoIcXb4vd1y985l7f9r6K+le+WNb6ZR/XNTCrv\nn78uWDkjGOAMJ9Rx9fywZRjGXtM0g/Af30vT98uCAyfBjz+FNU9A7k+Iv3Yvbzz2L/zig2P8x+Yi\niisb+dUPJhAe0vkxQn9EXjOJtLff5vSTT1Ly2GMM+u1viJ461cK/CRERkStIab53nk5Cevdr/ZBX\nWAbArLEDvvV+y4EDtJeU0u/HT3X6XLunnfeL3ufWQbeq+GShW1NvZXzSeF488CLzMuYRZg+7aI0t\nNJSExx6l4t/+neZDBUR0MZ/rUkSHOVh081B+98lxjpbVM2pATMAxv8Vmg8x7YdeL3hN8EUE4ZSUi\n0tfVlsK7j8G5L+Gmn8Ad/wvs3z7tWtXQynNbinhzZykY8ONb03n6tgziv3NKudfEpsDs/wu3/CXG\njv8k4otVjDm8mjFZ93kHmCeN/dbydreH8rqWi1v9vv7zvtIaapraL9omKSbMe3Lq69NUf2r1+/rP\n/aLDsAd42EW+re+fgPqGxw2b/xG2/wZSJ2Pe/xov7W/l/244wvhBcax49FqSY8IDyqHjwgVKn3qK\n1qPHSPnf/0DcQg2xFBGRq9CvM2HQZLj/NUvC3f9iPnXN7Wz4y2//uHP+H/4B13vvM2L7Z9ijLz6e\n/0npJ/zllr/kP2f8J9MGT7MkF/HaeX4nT+Y9yd9c/zc8NOahTte4Gxoomj6DqClTGPTb31iyb01j\nG1N+uZk7Mwfwmx9OtCTmt5zdCytmQPYymPSw9fFFRPqyY3mw9kkwPd5/D4799qy/htYOVn52ghXb\nTtDc7ub+yf+PvfuOr+n8Azj+uTd7h2wkyEIQtfeKvYlRe29ao6Wttr9u1dJWWyqo3Zq11V4Re29B\nkAiy984d5/fHsSJR3FwyPO9/0rrnPOcJed2c+z3f4cqEll642BTygVyp0XD0dzj1J6gy5JLrJlPA\nsdJLL5GRreFBUgYRiU8ypx7996PAVXq2Jsc5hkoFTtamlLI1fZhJ9VQWla0ppWzMsC0i/ahEBtSr\nUhrI0dtS1WHTWBQLmjGq51LK9a/JxNXn6TrnCH8Oqo1PKd2bTho6OFB2+QruT5hAxKefoYqIxH7c\n2CLxAyUIgiAIepF4F5LvQdn39bJcfFo2p0PjGd/cM8efa7OzSdm+A6sWLfIMPoHcfNzRzJFGpRvp\nZS/CE3Wd61LLqRYLLy7E38sfM8PcHz4MLC0p0bs3cYsWkR0WhnHZsvm+bgkLY/rWcWPJ0VAmt/LO\n12TjPJWqASXKweX1IgAlCMLbQ6OGg9Mh6Cdwqio/QHqqhD5LrWHlibvM2R9CXFo27ao480HrCng6\n5v37t9CxdITW30DDCXBsDpxcKE899ekCTaeC04uzdM2MDfBwsMTjv/pRZagfB6ceJD0p9bufmMHZ\nuwlEJkWg0uRM4DE1Uj7sQSWX+j3dh6qU6EeVS9H7m/DpAg4VYXU/WNaZNq2/Yd2ofgxffoYeAUf5\nrXd1WvroPjLawNIC14B5RHz2ObFz5qCOisT5iy9QGBa9vypBEARBeGVhx+SvbvppQL7vWhRaCVpX\nzll+lxoYiCYpCZuuXfI8LzItkiMPjjC86nAMleJ3sL4pFArGVx/P4J2DWRO8hsFVBud5XIkB/Ylf\nupS4xUtw+epLvVx7eGN3lh0LZf6hW3zbtape1nxMoZDL8I78Bmmxzx0zLgiCUGykRMH6YRAaBNUH\nQPuZYCQ/VNBoJTafv8/Pe25wLyGD+u52fNSuIu+42hbwpnVkYS8npTR4H47NlUuur26CSp2gyVRw\n8dV5aYVCgY25ETbmRlRyyTupRauViE3NehycevAwc0ou98sk8EYMMam5+1HZmBnl7kP18GtpWzOc\nrN+eflRF847OoQKM2A+bxsCuaVSpcobNo2YyYtU1Rqw4zbR2lRjeuLzOmUsKIyNcZnwjbwj0AAAg\nAElEQVSPoYszcQHzUUfHUPqXn1Ga6/kpnSAIgiAUNnePgon1Sz1NfBm7r0ZRysaUys9kKCdv2YKB\nvT0W9fMOdG28uRFJkvD38tfLPoTcajrVpGGphiy6vIieFXpiYWSR6xgjR0dsunYlaeNGHMaPw9DB\nId/XdbYxpXuNMqw9fY/3W3jlu4VCLpX95ZYN17ZAraH6XVsQBKEwCT0C/wyBzGTo8gdUl0uqJUli\nf3A0P+68zvWoFKqUtuZ7/6o08rQvHtU95iWhxedQfxycCIDjAXBtK1ToIGdElXoNJd6AUqnA0doU\nR2vT5wbxstXP9KN6VPb3MGB19m4Cic/0o1IowN7S5Mk0v0clfk81UHewNMn38LXCoOj0gMqLJMk3\nGPu/AYeKZPovZ/K+ZLZfiqR3bVe+7lIl35HEhNVriPz6a0wrV8Y1YB6Gdnb5Wk8QBEEQCrU5dcDW\nDfr/k++lMrI1VP9mN+/WcuWrLk8mzKoTErjZpCkl+/XD6eOPcp2n0Wpou6Et7jbuzG81P9/7EJ7v\nUswl+m7vy/h3xjOqWt7N4LPu3OF2+w7YjRiB4+RJernundg0Wvx0kBFN3Pmk3cv38HgpkgRzaoGV\nCwzept+1hYKhUUHsTYi+KveC8e0lstuEt5tWC0d/g31fy2XH7654/ODoVGg8P+wI5nRYAuXszPmw\nTQXaV3EpFsGL58pIlLOhjs+FzCTwbisHokrXLOid5Sk9W/24UXpEolziF/FUL6oHiZlkqHL3o3K2\nkftOuTwMTj3bQN3G7Pn9qEQPKH1QKKDxZHCpBuuHYbqkBXO6LeAXB09+3x9CWFw68/rXwNZc927+\nJXq/i6GjA/cnf0Bon764LVyglx4IgiAIglDopMVB7HWo9q5elgu6GUOmSpur/C5l505QqbDp0jnP\n845FHCMyLZIptaboZR/C81V1qEoz12Ysu7KM3hV7Y2Nik+sYk/LlsWrVioRVq7AbOeK5PbteRXl7\nC9pXdeGvY2GMbeqJjbnRi096WQqFnAUVNEsuTbHSvTWD8IZJEiSFQ/Q1iLoiB5yirkLsDdA+lTFw\ncIb84bLOSDAsJFO7BOFNyUiAjWPgxg7w6QqdfwdTa4Ijk5m58zr7gqNxtDLhu25V6FXLFSODt6C0\ny8wWmn0E9UbDyQVyed5CP/BsBc0+lgerFCLmxoZ4Olo+tweXJEkkZahyTvN7VPaXmMmZsAT+vRiB\nWpszmcjMyEAOTj3bLN228DSZL9oZUE9LCIM1/SHyIjT7hA1Wffl4wxVKlzBj0aBauD+n2djLyjh/\nnvDRY0CpxDVgHma+uteXCoIgCEKhdG0brOkHQ3ZC2fz3gPpw3QV2X4nkzOetctwAh77bG21GBuU3\nb8rzSd2kA5M4G32WvT32YmSgx8CEkKfr8dfpsbUHI31H8l719/I8JuPSJUJ79sJx6lTshg7Ry3Wv\nPkim/W9BfNDKm/daeOllzceir8Ef9aDdTKg7Ur9rC/qRkSAHl6KvPgk2RV+DrOQnx9i4ylOuHH3k\n7A5HHznAuOcLCNkDJT2gzXdytkNxKCsShBd5cA7WDoTkCGj9LdQdRXhCBr/sucHG8/exNDFkTDMP\nhjQoj5mxQUHvtuBkpciBqKNzICMePPyg6cfgVregd6Y3j/pR3U/MmTkVkfQkWPV0P6qwHzoWigyo\n4hOAAnkk47bJcGEleLXhXK0fGLY2BI1WYl6/GjTwzF+qbtadO4SPGIk6Lo7SP/+EVfPm+duvIAiC\nIBQmuz6VJ8t8Eg6GJvlaSq3RUvu7vTSr4Mgv7z7pxZAdGsqttu1wnPIhdsOG5TovNiOWVuta0d+n\nPx/U+iBfexBe3oeBHxJ0L4gd3XdQ0rRknseEDRpMdmgonnt2ozDWT9bJkCUnOR+eyJGP/TA31nNi\n/h/1wdQGhu7U77rCq1FlypmVUVch+srD7KarkPLgyTGmNuBYGZx8ngo2VZL//Hlu7oFd0+TsKPfm\n0Pb7VxrJLghFiiTB6cWw82OwcISeS4kt4cuc/SH8fSIMpULB4IblGNPUI1/VP8VOViqc+hOO/g7p\nsVC+qZwRVbZBQe/sjXjUj+pBYgb1POwLRQCqaJfgPcvIDLr+AWVqwo6PqR7bje3vLmLAtlQGLj7J\nt12r0LuOm87Lm5QvT7nVqwgfNZp748bj/OUXlOjVS4/fgCAIgiAUoLCjcr+EfAafAE6HJZCQrqLV\nM5Npk7ZsAaUS646d8jxvc8hm1JJaNB9/w8ZWG8uesD0subzkuYE/u+HDCR8xgqSt27Dtrp9/n3HN\nPekRcIzVJ8MZ2qi8XtZ8rLI/HPgWku6BTRn9ri3kptVCwh05wPR0VlPcLZAe9jIxMJaHCZVv8jDY\n9DDQZF3q1TOYvFqBezM4tUgePz+vodx0vvk0uUGxIBQXWamwbRJcWgseLUjt8AcLziTzZ9ABstRa\netVyZUILL5xt9DzQoTgwsYRGE6HOCDmAd+RXWNIOyjWGph9B+cYFvcPXythQiWtJc1xLFp5hasUr\nA+ppd0/I6YlZyaS3+4Ux590JvBHDiMbl+bhdJQzy0YRNm5bGvUmTSDsUhP3YMdi/917xmCYgCIIg\nvL2yUmGGm3yj1uJ/+V7um21XWXE8jLOft8LSRH7eJWm13GrVGuOyZXFbvCjXOZIk0XFjRxzMHVja\ndmm+9yC8mmlB09gTtoft/ttxMM897U6SJO74d0fKysJ921YUSv30FekVcIzwhHQCpzTX7xjquFvw\new1o/R00GK+/dQVIjZGzmR5lNUVdhZhgUKU/PEAhN0Z+lMn0KKuppAcYvIbn3+nxcGC6/AHTxBKa\nfQK1h4Mo4RWKupjrsGYAxN5A3fQTlhn2YO7B28SnZdOhqguTW3vjkc9WM2+V7HQ4sxSOzIbUKCjb\nUO4nV75psS/jLSxNyItvRzK3ujDqELhUw3zLKJa4bGRo/TIsDLrDyOWnSc1S67y00sIC17lzsfH3\nJ/aPeUR8+hmSSvXiEwVBEAShsLp3Ss5ScMt/WrokSey+GkkjT/vHwSeAjLNnUd2/j03XLnmedyry\nFHdT7tLdq3u+9yC8ujHVxqDSqvjz0p95vq5QKLAbNozs27dJPXBAb9cd29yDiKRMNp27r7c1AbDz\nAGdfuLJBv+u+TbLT4N4ZOLscdnwMyzrBTE+Y5QnLu8CuT+D6TjnoU2OQ3Ax5+H6Ydh8mnIfef4Pf\nZ1DFX858eh3BJ5AznjrMgjFHoFQNuUxpXgO5TE8QiqpL/8CC5kjpcRyqt5CmJ2rzzb/BVHKxYvO4\nhsztV0MEn16VsTnUHwsTLkC7HyH+tvxetrgthOyDQpKcU5wVrxK8Z1k5waCtsPszlCf+4H9lL1Cp\n7Td8vDuKHvOOsmhwbUrr2BFeYWSEy3ffYuTsTOwff6COiaHM7F9QWljo+ZsQBEEQhDfg7jFQKMG1\nTr6XCo5MITw+g3HNPHP8edLmLSjMzbFq2TLP8/65+Q9Wxla0Ktsq33sQXp2rtStdPbuy7sY6Blce\njIulS65jrNu2IWb2bOIW/omln59eMsCbejtQuZQ18wJv0b1mmXxlqedSxR/2fgkJoXJGjpA3jRri\nbz2ZOveohC4hFHj4gczIHBwqgnebnP2aLB0Lcuc5OVaCARvhxi65P9TfPeQpWG2mg4N3Qe9OEF6O\nOkv++T31Jwn2NRmbNZ5jB02oWtqYH7r70sgrf32NBeTWPXVHyYHzcyvg8C/wlz+UqS2X5nm2LPYZ\nUQWl+JbgPevCGtg6AcxsOVf/NwbukjAxMmDhwJpUdyuRr6UT1q4l8suvMK1UCdf5ARjaizcFQRAE\noYhZ2lGePjXqUL6X+nXvTWbvu8HJaS1xsJL7SWmzsrjZqDFWfn6U+mFGrnMSMxPxW+dHT++efFL3\nk3zvQdBNRGoEHTZ2oLNHZ75s8GWex8T//TdR33xL2b9WYF5LP9n8/16MYNzKs8ztW4MOvrkDXzpL\nCIVfq0HLL6HRJP2tW1RJEqRE5Cydi74CMTdAkyUfo1CCnefD0rmnAk0lyoOeyi7fCHW2PAUr8EdQ\npUHtEfKYdrP83fcLwmuVEAbrBsGDc2w2784H8V1wtbfhw9YVaF/VWbR9eV3UWXD+bwj6GZLC5X6Y\nTT8Cr9bFJhBVWErw3p4AFEDkJVjdD5IfENXoG3qc8iY6JZtZPavRqVqpfC2dcuAA9yd/gKGdHa4L\nF2BSXs+NNAVBEAThdVFny/2fag6GdrmDQ6+q4+9BmBgasH7Mk3K+5J07uT9xEm5LFmNRv36uc/66\n+hc/nPqBfzr9Q4WSFfK9B0F3009MZ931dWzpugVXa9dcr2szMgjxa4GZry+u8wP0ck2NVqLVz4GY\nGRuw7b1G+v2QtdAPNCoYHaS/NYuCzKSHE+eu5Mxsykx8coyVy8P+TD5Pgk32FcCoGDUzTouF/d/C\n2WXyVL3mn0LNIa+vHFAQdHV9J5oNI8nKVjMxayQXLBsxsaU3PWqWwcigCAV/izJ1NlxYBUGzIPEu\nuLwjB6IqtCvygajCEoB6u36SnavCyIPg3hSnQx+zx+MfapY2471V5/h1703yE4yzat6cssuWok1L\nI6xPXzLOn9fbtgVBEAThtYq4AOoMKJs7MPSq7idmcPl+Mq2fnX63aTOGTk6Y18ld4idJEutvrqeq\nfVURfCoERlQdgYHSgICLeQeXlGZmlBjQn9TAQDJv3NDLNQ2UCkY39eDKg2QCb8ToZc3HKvtD5EW5\nKXlxpM6GyMtwca1cbvh3L/ilihxUXtwG/p0sVwJIGqjcDdrPgsH/wtQ78EEwDNgArb+Fd/qAS7Xi\nFXwCsLCHTrNhVJD8WWD7hxDQCG7tL+idCYJMoyZp62ew6l2uZZSgh/Q9NdoM4OCHzelTx00En94k\nQ2OoOQjeOwtd5sqB/NV9YH5juLZVnvYp5Mvb99NsXhL6roUmUzG9vJK/lF8wrIoBv+y9wYTV58lU\naXRe2szXl3KrV6G0tiZs8BBS9otfbIIgCEIRcPeo/NUt/wGoPVciAWhd2fnxn6nj4kg9fBibzp1Q\nGBjkOudCzAVCEkNE8/FCwsHcgd4VerPt9jZuJ93O85iSffuiMDcnflHuaYa66lq9NC42pvxxUM+B\nosrd5K+Xi3gzcq1WLs+5vgMOzYJ/hsLcejDdBQIawoYRcPR3uXzEta48zbLPGph4CT4Jh2G75UBM\nnRFQrpF8T/w2ca4CA7fAu3/LAfcV3WBlb4gNKeidCW+x2Mi73PmlJTZnfmeNtgU76y1n1dS+jG7q\ngZlx7t+XwhtiYATV+8P409A1QJ6et6a/HIi6skkEovLh7SrBe9b1HbBhJJLSkK1e3/L+SVuqu9my\nYECtxz0rdKGOiyN89Bgyr1zB+X+fU6J3bz1uWhAEQRD0bOW7EBcC753J91J9Fx4nOiWLvZObPv6z\n+OUriJo+HfetWzDx8sp1zudHPmd36G4O9DqAuZF5vvcg5F98Zjxt17elaZmmzGw6M89jor7/nvi/\nV+K5exdGpfLXyuCRRYfv8M22q/wzuj61yukxQLK4LWQkwrjj+lvzdUqPf6p07uHX6GuQnfrkGBu3\nJ/2ZnCrLX+085Sf4wn9TZ8HxeXIgT50pNyNuMgXMbAt6Z8JbIiVTxY6t/9D88sdYks42tyk06fk+\nTtbFLAOxuNCo5YmqgT9C3E1wqARNp4BPV1AWjUBhYSnBe7sDUCA/9VjTH2Kvc73KZLqcr4mdhSmL\nBteiorO1zstq09O5N2kSaYGHsBs9CocJE0TTOEEQBKHw0Wrhx/JQqRN0mZOvpZLSVdT4dg+jmrgz\ntW3Fx39+p0dP0Gopv2F9rnNSs1PxW+dH+/Ltn9v0WigYv539jYWXFj63L5cqIoKQVq0p0bcPztOm\n6eWa6dlqGs7YT3W3EiweXFsvawJwYgHsmAJjj8vNtQsLVQbEBD/pz/SoV1Nq5JNjzErkbAbuVFme\nRmeq+32q8FBqNOz7Gs79JWeE+X0mT8UqIh8ohaInU6Xhr2N3SD/wE+O0q4g1LoOq+1LKVCzwuIDw\nMrQauLJRDkTFXpd75jWZIk9cLeTvG4UlAPX2leA9y94Thu8Fny5UuDSLEx7LMdak0f2Po+wPjtJ5\nWaW5Oa5z52LbswdxAfOJ+GQakkqlx40LgiAIgh7EXJObEpdt8OJjX2D/9Sg0WilH+V3WrVtkXr6M\nTZfOeZ6z/c52MtQZ9PDuke/rC/o1qPIgrIysmHt+bp6vG7m4YNOhA4nr/kGdkKCXa5obGzKkYXn2\nB0dz9UGyXtYEwKeLPN2toMrwtBq5B9XVLXBwBqwZAL/XhOmlYEEz2DwWTv0J6XHg0RxafQP918Pk\nYLlX05B/of1MqDUEXOuI4JO+WDrKgfdRgXJQb9skmN8EbgcW9M6EYkajlVh3Opyus7ZRbs9w3pdW\nkuLeAacPj4ngU1GiNICqPeSHGT2WyP+/YTjMrQMXVsuZUsJ/EuMfAEws5R+g0jWx2fMFe0rcYrzF\nJIYvO82nHXwY2rCcTtlLCkNDnL/+GkNnZ2J/n4M6JobSv/6KgaXFa/gmBEEQBEEHYfrr/7T7ShRO\n1ib4lrZ5/GdJm7eAgQHWHTrkec76m+upUKICle0q5/v6gn7ZmNgwsPJA5p6fy5XYK1S2z/1vZDd8\nGEmbN5OwciUO48bp5bqD6pdjfuAt5gXe4vc+1fWyJlZOULahXELRfNrrm2YkSXJWTfSVJ1lNUVcg\n5rrcdwgABZQsL2czVen+JKuppHuhf4JebLlUkxuzX90Mez6H5Z2hYkdo/Y387yIIOpIkid1Xo5i1\n6zqmMRdZZvYbDkYJ0GYmtnVGFPnJam8tpVLOevLpCsFb5YyojaMg8Ado/CH49pL7SAm5iBK8Z905\nBOuGIKkzmVdyCj+GetG3rhtfda6crwkEievXE/G/LzCp4I3b/PkYOjjocdOCIAiCoKN/hspBqMnX\n8nUjnKnSUOObPXSrXprvulUFQNJqCWnREhNvL9zmz891zrW4a/Ta1otpdafRp2Ifna8tvD6p2am0\n29COyvaVCWiZ91S88NFjyLhwAc/9+1Camenlut9vv8bCoNvs/6AZ5ez19ODu9GI5w2VUELj45n+9\nrFS5L9PTwaboq3IW0yMWjg9L5x6V0FWSM22MxcPIQkuVCcfmQNDPoFVBvTHyB0qRdSa8ouO34/hh\nZzDn7iYw0SaI91WLUFg5oei5DMqIrKdiRauF69vlAFTkRShRDhp/ANX6FJpAlCjBK6zKN4FRgSjs\nvRkb+QUr3Xez+kQog5ecJCld9xI62+7dcZ33B9l3Qgnt3Yes23f0uGlBEARB0IEkQdgxOfspn09h\nj96KJT1bk6P8Lv3kKdQREdh26ZLnOetvrsfEwIT25dvn69rC62NpbMnQKkM5cv8IZ6PO5nmM3Yjh\naBISSFyvv/K2YY3KY2igZP4hPU7Eq9QFFAZyFtSr0KggOhgur4d938CqPjDbF74vDYtawtYJcg8h\nVTpUaA9tZ8jT1qbcgik3YeBmaDtdnqhUuqYIPhV2RqbQ5EN5KEOVHnDkV/i9BpxZJpdSCsILXHmQ\nxOAlJ+m94DiJCQkElv+LiVkBKN2boRgVJIJPxZFSCZU6wqhD0Ge13Ltvy3vye8fpJaDOLugdFhoi\nA+p5VJmwYyqcXUakQwM6PRiMVUknFg+qna8ncRmXLhM+ejSo1ZSZNw/zGnpKLReEV5WdLvebCN4G\nXq2h5hCwsCvoXQmC8CYlhMKv1aD9LHk0ez58vP4i/16M4MznrTA2lJ9vPfhkGil79uB1OAilac7J\nPumqdFqsa0Fz1+ZMbzw9X9cWXq8MdQbt1rfD3dadxW0W53lMaJ++qKOj8di1E4Whfjo8fLrxEmtP\nhxM01Q9nGz1NhlrRTe7FNOFC7qCrJEHy/YfZTE9lNcXeAM3DDw8KA3nSXI6sJh+wLSt/ABGKn/tn\nYecnEH4cnH3lAGO5hgW9K6EQCotL46fdN9hy4QE2ZkZMq62g5+1pKONC5NLfRh+I94m3hSTBzT0Q\nOAPunwHrMtB4ElQfAIYmBbKlwpIBJXpAPY+RKXT+DUrXwHn7FIJK3GVI6nt0/SObgP41qeeu2wd1\ns6pVKLdqJeEjRnJ3yBBKzZqJdatWet68IPwHdRacWQpBP0FqFNh5wf5v5Npl355QZ5R+ShMEQSj8\nwo7JX/PZ/0mjldh7LYpmFR0fB5+0GRmk7NqFVft2uYJPALvDdpOqSqW7d/d8XVt4/cwMzRjhO4IZ\nJ2dwIuIEdV3q5jrGbsRw7o0dR/KOndh06qiX645q4sHqU+H8GXSbzzr66GVNqnSHzePg9kH5Q0DU\nlSeT56KvQVbSk2OtS8vBJc8W8ldHH7D3lu8RhbdH6RowdKecAbfnC1jaXm5q3+prucxGeOtFp2Qy\nZ38IK0/cxdBAwdhmHoy3P4v5rg/kjMcBm8C9aUFvU3iTFArwbg1ereDWPjj4A/z7ARz6CRpNghoD\n39rfJSID6mXcOwNrB6BNi+NHo1EsSqnHd92q0quWq85LquPjCR8zhsyLl3D67FNK9uunxw0LQh40\nKrlE4NBM+Qlv2UbyuOGy9eXSgpPz5ekNqnS5UWvdUVChAxiIOLUgFFtb3pOb7k4NzddT2dOh8fQI\nOMZvfarTuVopAJK2buPBlCm4LV+GRZ06uc4ZsH0ASdlJbO6yWadBH8KblaXJosOGDjhbOLOi3Ypc\n/2aSVsvtTp1RGBlRfuMGvf2bTlx9jt1XozjykR8lLIzzv2BGAsz0knv7PGJi86Q/06OG4I6V5BIK\nQXhadjoc/R2OzJbL8eqPg8aTwcSqoHcmFIDkTBULAm+z6PAdVBotveu48n4TVxyPfiX3nHNrAD0W\ng7VLQW9VKGiSJD/4CPwB7h4DKxdoOBFqDgIj/fROfJHCkgElAlAvKzUG/hkCoUHssezM2NgeDG3q\nzUdtKqJU6naTpc3I4P7kD0g9cAC7EcNxmDQJhUjLFPRNo4ZLa+U3vIRQKFNbDjyVb5q7/CAjQQ5S\nnVwAiXfldNE6w6HGIDAvWSDbFwThNfq9ljzhqd/afC3z/fZrLD5yhzOft8LaVG62eXfESLJv3cJj\n755cv9tCEkLotqUbH9b6kEGVB+Xr2sKbs/b6Wr45/g1zW8ylSZkmuV5PXL+BiE8/xXXhAiwbN9bL\nNa9HptBm9iEmtPBiUitvvazJxXWQfO9JCZ11aTGJSng1Sfdh31dwcQ1YOkGLL+Rmw+I+/q2QqdKw\n4lgYcw+GkJiuolO1UnzQyptyBjGwdiBEXICGE8Dvf+JBrpCTJEFokJwRFXZYfv9oOEFuhWJs/lov\nLQJQzyj0ASiQP8jv+xKO/k6YRVV6xo2mmk9FZr/7DhYmur25SGo1kd98S+KaNVh37kSpb79FYayH\nJ3yCoNXKjVYPzoC4m3LfAr/P5VTQF91oazVwYyecCJAnQxqayuNE646WnwwLglD0pcbALE9o+aWc\nDq4jSZJoPusgbnYWLB8qZzqpoqMJadYcu5EjcJw4Mdc5P576kVXBq9jXcx8lTUVwu6hQaVR02tQJ\na2Nr1nRckzsLKjubkFatMS5blrLLl+ntusOXneZUaDxHPvbDUsf7LUF4LcJPwc6P4f5pKFVd7g/l\nVq+gdyW8JmqNlg1n7/PL3htEJGXSxNuBqW0qUKW0DQRvh02jQQK6BUBFMVxDeIHQw3KCwJ1DYOEA\nDd6H2sNe26CKwhKAEmH6V2FgCK2/hR5LcMu+zUHrL0gKDqRnwDEikjJ0WlJhaIjzl1/gMHECyVu2\nEj56NJrUVD1vXHirSBJc2wYBjWD9MFAawrt/yVMZvFu/3FNepQFU7ACDtsKYo+D7rvzEeF4DWNpR\nXl9MghGEou3uo/5PDfK1TEh0KqFx6bT2cXr8Z8n/bgetFpvOuaffZWuy2XprKy3cWojgUxFjZGDE\nmGpjuBZ/jf139+d6XWFsTMlBg0g/eZKMixf1dt2xzT1IylCx6sRdva0pCHrhWhuG7QH/hZASBYvb\nwD9DITG8oHcm6JEkSey8HEnbX4OYuv4ijtamrBxRl+VD61DF2QL2/A9W95F7go0KFMEn4eWUayR/\n1hqyE5yqwJ7PYXZVOPwLZKUU9O5eGxGA0kUVfxTD92JuacNqk+k0il9Pl98Pc/Feok7LKRQK7EeP\nxmX6dNJOniKs/wBUUdF63rRQ7D2atrCgGazpB+pM6L4IxhyBSp10Ly9wqiw35J98FVp+JZfxrekH\nv70DR36Ty/YEQSh67h6TsxtL5W8a6+6rUQC0eioAlbR5M6a+vpi4l891/L67+0jMSsTfyz9f1xUK\nRgf3DpSzLsec83PQ5PEgwrZXL5TW1sT9uUhv16zhVoL67nYsDLpNllo8/BAKGaVSzhJ/7zQ0/QiC\n/4U5tWD/d5CdVtC7E/Lp2K04uv1xlNF/nUGSJAL612TT2AY08LCHlEhY3hmO/CqXUA3dDSVz/94T\nhP9Utj4M3CQHs0tVh71fyoGoQ7MgM7mgd6d3IgClKycfGHkApXdrpimW8LX0OwPnH2T7pQidl7T1\n74brvHlk371LaJ/eZN26pccNC8XanUPyU7e/e0BGPHT5A8adhKo95GwmfTAvCY0mwvvnodcKsHGT\nI/U/+8DWifL0IEEQio6wo1C6Fhjmr+x799Uoqrna4mQtT3PJvH6drOBgbLp0zvP49TfWU9qyNPVc\nRJlKUWSoNGTsO2MJSQxhV+iuXK8bWFpQok8fUvbsIevOHb1dd2xzD6JTslh/5r7e1hQEvTK2gObT\nYPxpOYv80I9yn70La+S2CEKRcvl+EgMXn6TPwuNEJWfyY3dfdk1sQtsqznL58Z1DENAYHpyDbgug\n0+y3dqqZoCeudaD/ehi+D8rUkaeUz64qTyrPTHrx+UWECEDlh6kNvPs3NP+MNppDbDT5iu9X7mDO\n/pvo2lvLsnEjyq5YjpStIrRvP9LPnNHzpoVi5e5xuSRuWSc53bvDzzD+DFTv99Z5wvcAACAASURB\nVPqaHhoYgk9nGPIvjD4MVfzh/Er4ox4s6yzXwIvyPEEo3LJSIPKi/NQtHyKTMrkQnpij/C5p8xYw\nNMS6fe4ShPDkcE5EnsDfyx+lQtyCFFVtyrXB09aTeRfmodaqc71eckB/FEZGxC9eordrNvK0x7eM\nDfMP3UKtER/mhULM1lWefDZ0F1g5wcaRsKgV3CvkvW4FAEJj03hv1Tk6Pqxu+bR9JQ582IxetV0x\nNFDKwcRDs2B5FzCzhRH7odq7Bb1toTgpU0seDjPiAJRtAAe+g1+qwoHvi0Xlibj7yy+lEppOQdFv\nHeUM49hp9j9O7V3H5LUXdE4TN6tcmXKrV2FYogR3hwwledduPW9aKPLun4W/ustZTzHX5aaX75+T\nG9flM5vhlThXhS5zYfI1aPE/iL0p18D/XgOOzYUM3cpSBUF4zcJPgqQFt/wFoPZck8vv2lSWA1CS\nRkPy1q1YNm2KYYncI+zX31yPgcKArp5d83VdoWApFUrGVx9PaHIo225vy/W6ob09Nv7dSNq0CVW0\nfloKKBQKxjbzICwunX/zkW0uCG+MWz0Yvh+6zoOke/BnC9gwUp6gJxQ60cmZfLbpEi1/DmTv1SjG\nN/fk0NTmjGjijqnRw2qC9HhY9a6cmVK5mxwgcKxUsBsXiq/SNaDPKrmPb/nGEDgDZvvC/m/ln8Ui\nSgSg9MWrFYqRBzF3cGOp8Y+UvjiH/guOEZeapdNyxmXKUHbVSkx9fLg/cSLxK/7S736FoinyMqzu\nBwubw/0zck+mCeeh3piCTfu1sIPGH8DEi9BzKVi5wK5pcnnevx9AzI2C25sgCLndPQYKpZzunQ+7\nr0RS3t4CDwdLANKOHUcdE4NN59zldyqtik0hm2hcpjGO5o75uq5Q8Pxc/fCx8yHgQgAqjSrX63ZD\nhyJpNCSsWKG3a7b2ccbDwYJ5B2/pnGkuCG+UUgnv9IX3zsj3SVc2yf2hDv4A2ekFvTsBSMpQMXNX\nME1nHmT1yXD61HEjcGozPmxTAWtToycH3jsD85vArQPQfpbcZ9XEsuA2Lrw9XKpB77/lyhOP5nBo\nplyat/crSIsr6N29MhGA0qeS7iiG7UVRtScfGq1jdOT/6Dd3NzeidOtib1iiBG5LFmPZwo+o774j\nauZMJFFD/naKuQHrhkBAQ7nmvPmnMOGi3JPpNY3q1ImBkfxEaOhOGBkIlbvC2eUwtzas6AY3dok+\nCIJQGIQdA2dfMLHSeYnkTBXHb8fR2sdJ7ocBJG3ZjNLaGsvmzXIdf+jeIeIy4+jh1UPnawqFh0Kh\nYPw747mfep+NIRtzvW7s5oZVm9YkrFqNJkU/03yUSgVjmnkSHJnC/mAxrEUoQkws5Uzx8SfBqzUc\nnA5zasOlf+QhMsIbl6nSsODQLZr8eIC5B27RyseJfR805ZuuVXC0euqhriTBiQVy1QEKGLYL6ozQ\nfbiPIOjKuSr0Wg5jjsnvI4d/kQNRe/4HabEFvbuXpigsT5Bq1aolnT5dTGqjJQlOLkDaOY27kgMT\npA+Z2LczzSro9sRX0miI+u47ElauwrpDB1y+n47S+A2WWQkFJ/623Hju4howNJMznRqMB7PcpS2F\nVmoMnF0KpxZBSgSUdIc6o+QngqbWBb07QXj7qLNghhvUGgptv9d5mS0XHvD+qnOsH1OfmmVLoklN\n42bjxth07ozLV1/mOn7s3rFcT7jOru67MFS+ph51whslSRIDdwzkQdoDtvtvx8TAJMfrGVeuENq9\nB44ffoDd8OF6uaZKo6XZzIM4WZuwfkyDx8FPoXiLTMpkf3A0+4OjOB+eSClbM7wcrfByssTL0RJv\nJytK25qhVBaRn4fQI7DzY7kXn2td+b24dM2C3tVbQa3Rsv7sPWbvvUlEUibNKjgwpU0FKpeyyX1w\nVgpseR+ubACvNtAtQB7KIwiFQXQwBM2Cy+vlqca1hkLDCWCZd8xBoVCckSSp1hveZe59iADUaxR2\nFM2agWSnp/ChaiR1OgxjUINyOi0lSRJxC/8k5uefMa9blzJzfsfASvcn10Ihlxgup1ee/xuUhlB7\nODSaBBb2ellem5ZG2vHjpB4MJDM4GItGDbHt1g1jNze9rJ8njQquboYT8+HeSTC2hHf6QZ2RYO/5\n+q4rCEJOd0/A4tbyNEufvCfVvYzxK89y/HY8J6a1wECpIHHjJiI++YSyK1diXqN6jmMj0yJps74N\nw6sO573q7+X3OxAKkZMRJxm2exgf1f6I/j79c71+d+hQsm6G4LFvr94eni07GsoXW66wemQ96rnb\n6WVNoXDRaiUu3U9iX3A0+65FceWBPIrctaQZdcrZEZWcyc3oFKKSn7S6MDMywNNRDkh5Olni/TBA\n5VrCvHAGprQa+T5v39eQFgPV+spZUtYuBb2zYkmSJHZejmTm7uvcjkmjupstH7Wt+Pz3kKirsHYg\nxN8Cv8+h4US5pFIQCpvYm3Jj/EtrwcAEag2RA1FWzjkOEwGoZxTLABRAcgSaNQMwuH+K+eoORNSa\nymedfOUpCjpI2ryZB59+hom7O64LF2Dk5PTik4SiIyUSgn6CM0vl/685WO4Z8MwbiC6yw8JIDTxE\namAg6SdPIqlUKC0sMPb0IPPiJZAkzGvVwqZbN6zbtkFp8RpL++6fkdOZL68HrQo8W0Hd0eDhJ365\nC8LrdvgX2PslfBgClg46LZGl1lDzm7109HVhRndfAMKGDEF1/wEeu3bmykqZd34e8y7MY0f3HZS2\nLJ3f70AoZIbtGkZIYgg7/HdgbmSe47W0o0e5O3QYzt98TYmePfVyvUyVhkY/7MenlA3Lh+avj5lQ\neKRlqTkcEsu+a1HsD44hNjULpQJqli1Bi0pOtKjoiKejZY73l6QMFSHRKdyMSuVGVCo3H/53ZHLm\n42NMjZR4OMiBKS8nq8cZU64lzTEoDIGpzGQ5i+H4PFAaQePJUH8cGJkV9M6KjaMhsfywM5gL95Lw\ndLRkSpsKOcrHc7mwGrZOlMvUeyyWG0ALQmEXd0v+HHlhtZzAUHOw3K7FuhQgAlC5FNsAFIA6G+3O\nT1Ce/pOjGh/+cv2SGQP9cja2ewWpR45w//0JKK2tcVswHxMvLz1vWHjj0mLhyGw4uVDOFKreH5pM\nkUf56kjKzib9zBlSDwaSGhhIdmgoAMbu7lg2bYpl06aY16iOwtgYVWQkSZu3kLRhA9lhYSjMzbFu\n0wZb/26Y1ar1+kocUqLkYNvpRZAaBXaeD8vz+uSrN40gCP/h715yee97uv/ODbwRw6DFJ1k8uBZ+\nFZ1QRUYS0twP+3HjcBg/LsexGq2Gthva4m7jzvxW8/O7e6EQOhd9joE7BjKp5iSGVhma4zVJkgjt\n3gNtejru/25DYWCgl2vOPRDCzF3X2Tq+EVXL5FE6IxQJ9xLS2R8czd5r0Ry/FUe2RouVqSHNKjjS\noqIjTb0dKGHx6plzyZkqQqJTuRklB6RuPvzvB0lPAlMmhg8DU045g1Nl7SwKJjAVfxt2fw7B28DG\nDVp/DT5dRa+hfLh8P4kfdgYTdDOWUjamTGrljX+NMs//91Vlwo6pcHYZlG0EPRbp5SGwILxR8bch\n6Ge4sEoeOFNjIDSahMLWVQSgnla1elXp0rlLBb2N1+v8StRbJhKtseQ7y2l8NLQvbnbmLz4vD5nX\nrnF35EikrGzKzPkdizriCWCRlJEAR+fIT73UGeD7LjSdKvdJ0oEqOpq0Q3KWU9qRo2jT01EYG2Ne\nty6WTZpg2awpxq7PD2pJkkTGuXMkbthAyvYdaNPTMXJzw7ZbV2y6dMGoVCldv9P/ps6Gq5vkv4cH\nZ8HEWg7C1R4Odh6v55qC8DbSauHHcuDTBTr/rvMyn268xMZz9zn7eStMjQyIXbiQmJ9+xmP3rlyl\nvEH3ghi7byw/Nf2J1uVa5/MbEAqrMXvHcCn2Ejv9d2JpnHMyVPKOHdyfNJnSv/2KdWv9/AwkZ6po\n+P1+Gnvb80c/0TunqNBoJc6HJ7DvWjT7rkVz/eGgHnd7C1pUcsSvohO1ypXASMdKgRdJeRSYehSc\nik7lZlQq9xMzHh9jbKjE3d4CLycrvB0fBqicrChb0lznCoZXcjtQniQcdRnKNpT7Q7lUe/3XLUbu\nxKbx0+7rbLsYQQlzI8Y196R/vbKYGv1HADz+jlxyF3lRbnvR/DMwEP0KhSIsIVTOej/3NwCKL+JE\nAOpp5uXNpfHLxjPadzTutrp9+C4SHpwn8+++KNOi+F4xnHYDP6JOed2a2WXfu0/4yJGowsMp9eMP\nWLdrp+fNCq9NZjKcCJCDT1lJUNkfmn0CDt6vtIyk0ZB56RKphw7J/ZyuXgXA0Nn5cZaTRb26KM2f\nH+hUa9V5NgTWpqeTsmcPiRs2kn7iBCgUWNSvh003f6xatURpaprHanpw77T8d3Nlo9wfwbsN1B0F\n7s3FU0BByK/Iy/I0za4BcqahDrRaiXrf76NWuRL80a8mkiRxu1MnDKxtKLfy71zHTzwwkXPR59jb\nYy9GBrpl/gqF35XYK/T+tzdj3xnLmGpjcrwmaTTcatceA1tbyq1Zrbes2h93BjMv8BZ7JjXF01GM\nQy+skjNVBN2QS+sOXI8mIV2FoVJBnfIl8avoiF9FR9wdCvbfLzVLza3oVG5EpTwOUN2ISuFewlOB\nKQMl5e0tHmZMWeHtJAenytpZ6D9gptXIWTj7v4X0eKjeD/z+B1ai9cZ/iUrO5Nd9N1lzKhwTQyXD\nG5VneBP3F1edBP8LG8eAAug2HyqIz1RCMZJ4Fw7/gqLTbBGAepqrj6vk8qkLmepM2pVvx+hqoylv\nU76gt/V6pMeTsWoQZuGHWK1pgUmnWXSro1vQTZOYSPjYcWScO4fTxx9RctAgPW9W0KvsNLnM7shs\nOfupQgdoPg2cq7z0EprkZNIOHyY1MJDUQ0FoEhJAqcSsevWHQacmmHh7v/AG/2LMReZdmMeR+0do\nXKYxg3wGUdu5dp7nZd+7R9LGTSRt3IjqwQOUVlZYt2+PrX83TH19X0+JXnIEnFkCpxfLzTntK0Dd\nkeDbWx5nLAjCqzu5ELZ/CBMuQIlyOi1x7m4C3f44yi/vVqNb9TKPJ505f/klJXq/m+PY2IxYWq1r\nxQCfAUyuNVkP34BQmE3YP4GTkSfZ2X0nNiY5y+ISVq8m8suvcFu2DIu6+snajk3NouGM/XSuVoqZ\nPUWGSGESGpv2uIH4yTvxqLUSJcyNaF7BEb9KjjT2csDGrPAHpNOz1Q9L+XJmTYUnpPPoI5SRgUIO\nTD2eyid/LWdngbFhPgNTGYnyUJoTAfI05CYfQL2xYGjy4nPfIkkZKgICb7HkyB00Wom+ddwY7+eF\ng9UL/p40KrkJ/NHfwOUd6LVM59+NglDYiR5Qz6hVq5a05/Aell5ZyqrgVWRpsmhfvj2jfEdRzqZc\nQW9P/7QaMnd/jenx2ZzXenCs5i+M6tREpykd2sxMHkyZSsqePZQcPBjHqVNQiEbOhYsqUw6mBP0M\nadHg2VIOPL3EyF1Jksi6eVMuqws8RPq5c6DRYGBri0XjxnLQqVFDDGxtX2or56PPM+/CPI4+OIqN\niQ0t3Vqy/+5+ErISqFSyEgMrD6RNuTYYKXPfGEpaLeknT5G0cQPJu3YjZWZi7OGBbbeuWHfujJFj\n3mM/80WdJWdDHZ8HEefBxAZqDIA6I8RNgiC8qnVD4O5xmHxV54zCH3cGM//Qbc5+1gobcyMip08n\ncdVqvA4HYWCTM+iw6NIiZp+dzdauW4vn73IhhxsJN+ixpQfDqw7n/Rrv53hNm5lJSIuWmPr44LZw\ngd6u+cXmy/x94i6BU5tT2lY0bS4oKo2WM2EJ7LsWxb7gaG7HpAHg7WT5uIF4dbcShaPptx5kZGu4\nFSM3Pb8R9ShAlcLd+CeBKUOlgnL2Fng7WeLp+KT5eTl7c0wMX7EXWmwI7P4MbuyQ731afwsVO771\nmeGZKg1Lj4Yy7+AtkjNVdKlWismtKrxci5PkCPhnCNw9BrWGQZvpYPSasvsFoRAQAahnPN2EPD4z\nnqWXl7L6+mqyNFl0dO/ISN+RlLUuW8C71D/1lS2o148iVWPI8tJfMHrwYMyNX73eWNJoiPp+Bgl/\n/YV1+3a4zJiht3HHQj6os+HcCnk0ZsoDKNcY/D4Dt3r/eZo2I4O0EyfkLKfAQNQPIgAwqVQJy6ZN\nsGzaFDNf31dq5no68jQBFwM4EXGCkqYlGVR5EO9WeBcLIwsy1Zlsvb2V5VeWE5ocipO5E/0q9aO7\nd3esja3zXE+Tmkryjh0kbdhIxrlzYGCAZaNG2Pj7Y9m8mf5//iQJwk/KTwGvbgZJCxXay+V55Zu8\n9TdhgvBCkgQ/V4KyDeSpPjpq+XMgTtYm/D28HpJKxc1mzTGvWZMyv/36zOUkOm7siIO5A0vbLs3n\n5oWiYmrgVA7eO8gO/x3YmeUcbx4bMJ+Y2bMpv2kjphUr6uV69xLSaTbzIP3rleXLzpX1sqbwchLT\nswm8EcPea9EEXo8mOVONsYGSeh52tHhYWudaUrdep0VVpuphYCrqSXAqJDqVsLg0tA8/chkoFZSz\nM39cxuf5sPm5u4PFiwNTIftg16cQc02+p2w745Wy6IsLtUbLujP3mL33BlHJWTSv4MCUNhXxKZX3\nPWsutw/C+uFyZUKn38BXPxM6BaEwEwGoZ+Q1BS8uI44ll5ew5voaVFoVHdw7MNp3NK7Wuk8GK4yk\nmOskLXkXy7QwlloMoePI73DW4SmeJEnEL15M9MxZmNeuTZm5czCwfsk3YkG/NGq4uAYCZ8h1t651\nofmn4N70uadk37tPauBBUgMDST9xEikrC4W5ORb16z8OOhk5vVrtvyRJnIo8xbwL8zgddZqSpiUZ\nWmUoPb175hqVDaCVtBy+f5hlV5ZxMvIk5obm+Hv509+n/3+OTs+6c0cu0du8GXVUFAa2tlh37CiX\n6Pn4vNKeX0rSfbk078wSSI8Dh0pyIMr3XTB+u252BeGlxd+B396B9rPkDEId3IpJpcVPgXzVuTKD\nGpQj5eBB7o0eQ5k/5mLl55fj2JMRJxm2exjTG02nk0cnfXwHQhFwJ+kOXTd3pX+l/kypPSXHa5qk\nJEKa+2Hp50fpWTP1ds0P1l7g30sPOPKRH3aWojTpdZEkiVsxqY8biJ8Oi0crgb2lCX4VHfCr6EQj\nL3ssTUTj5mdlqjTcjknjZnTK4+DUzehUwuLS0TyMTCkVUM7OIkcZn5ejFe4OFjmbZ2vU8v3Pge8g\nM0mecNX8M7B0KKDv7s2RJIkdlyOZtes6t2PTqOFmy0dtK1LX3e7FJ4M8iCPoJzg4Hey8oNdycNRP\nMFwQCjsRgHpGXgGoR2IzYll8eTFrr69FrVXTyaMTI31H4mpVjAJRWSlErxiK473d7FE2pPTAP/Ep\np9vEsaSt23gwbRom5criumABRi4uet6s8FxaLVzZAAe/h7gQuZ7c7zO55O6ZDB1JpSL97LmHvZwC\nyQ65BYBRWbfHDcTNa9fWKZNIkiSORxwn4EIAZ6PPYm9mz9AqQ+nh3QMzw5cLbl6Nu8ryq8vZdWcX\nWrS0KtuKQT6DqOpQ9fnX1WhIO3qUxA0bSN27D0mlwqRiRWz9u2HdsSOGJXVruP9cqky4vB5OzIPI\nS2BqK9+I1RkBtm4vPl8Q3ibnV8KmMTDmKDjplikSEHiLGTuCOfKxH6Vtzbg/eTJpR4/hdSgQxTPv\nVVMPTeXw/cPs77kfU0NR1vA2+fTwp+wK3cV2/+04mucszY764Ufily/HY9cujMs8/8HGqwiJTqHV\nL4cY18yTD9tU0MuagixbreXknXj2Xotif3A0d+PTAahcylrOcqrkhG9pG51aSAiQpdZwJzZNzpSK\neljOF51C6DOBqbJ2Fng6Wj4u4/N0tMTTSoXpkVlwaiEYmctTlOuMAsPiWQFxJCSWH3YGc/FeEt5O\nlkxpU5GWlRxfvg9pejxsGAkhe6BqT+g4W/QUFd4qIgD1jP8KQD0SmxHLokuLWHdjHRqths6enRlR\ndQRlrMq8oV2+ZpJE9M4fsDvxA7elUkS0XUST+v9dqvU8aceOce+991FaWOC6YAGmFV5tuprwiiQJ\nrm2FA9PltGjHynKPp4odcgSe1HFxpB4Kkvs5HTmCNiUFjIywqF1LnljXpAkm5XVvvi9JEkcfHGXe\nhXlciLmAo7kjw6oMw9/LX+cPgJFpkay8tpJ1N9aRqkqlhmMNBlYeSLMyzTBQPj9VXJOYSNL27SRt\n2Ejm5ctgZIRVs6bYdPPHskljFIZ6fEIqSXIN/4kAuLYNkOTyvHpj5BHGojxPEGDzePl9auod0LFP\nYPd5R8lSa9j2XmM0KSncbNgI2549cf78sxzHJWYm4rfOj57ePfmk7if62L1QhISnhNN5Y2d6ePfg\n03qf5nhNFRlJSKvWlOjVK9fPTX6MXnGGI7diOfqxH1Yvmngl/KfY1CwOXo9h37Uogm7GkpqlxsRQ\nSSNPe/wqyaV1Ljai39brlK3Wcic27akyPjlz6k5sGuqHgSmFAtxKmtPYNp4haQvxSDxGlnV5aPMd\nJj7ti829z6V7SfywM5jDIbGUtjVjUitvulUv/Wr9xO6dhrWD5D6sbWdAraHF5u9HEF6WCEA942UC\nUI/EpMew6PIi1l1fh1bS0sWzCyN8R/xniVBRknB5Fwbrh4NWxeGq02nXfYhOU8Yyr18nfMRItOnp\nlJkzB4t6dV/Dbt9ykgQ3d8tp0BEX5HTe5p+ATzdQKpG0WjKvXH3cyynz8mWQJAwdHLB4WFZnUb8B\nBpYW+dyGRND9IAIuBHAp9hLOFs4MrzKcbl7dMDbQz5OwNFUaG25u4K+rf/Eg7QFuVm709+lPF48u\neZbzPS3zxg2SNmwkaetWNHFxGNjbY9O5M7b+3TDx9NTL/h5LDIfTi+DMUnnSoFMVuTyvak8wEjfM\nwlvs95pg5wl91+h0enRKJnWn72NSS2/eb+FF4j//EPHZ55RbuwYzX98cx664uoIfT/3I+s7r8S4h\nHoC8jb469hWbQjbxb7d/KWWZM6P7wSfTSN6xA8/9+/SWGXvxXiKd5xzho7YVGdPMQy9rvi0kSSI4\nMuVxA/Hz4YlIEjhbm+JXyZEWFR1p4GGPmfErNs4W9C5brSUsLo2b0anceDiR72ZUCndi02goneMz\nw7/wVD7glLIaW53HY+ZaFe+H5XyejpY69ZktKLdjUvlp9w3+vRRBSQtjxjX3pH89t1dr4C5JcHKB\n3DfL2gV6LoPSNV7fpgWhEBMBqGe8SgDqkai0KBZdXsQ/N/5BQqKrZ1dGVh2Ji2XRLznLjA0lemFP\n3LJusNt+ME1HzcLE6NWf6KkePODuyJGowu7iMuN7bDp0eA27fQtJktzA8MB3cO8U2JaFZp9A1Z5o\nMjJJO3yE1EOHSD10CE1sLCgUmPn6YtlMLq0zqVRJp6Bi7m1IHAw/SMDFAK7GXaWURSmG+w6nq0dX\njAxezxNgtVbN3rt7WX5lOZdiL2FjYkMv7170qdgHB/P/7j8gqVSkBgXJJXoHA0GtxrRqVblEr337\nXBO08kWVAZfWwYn5EHUZzEpAzcFQezjYFJOsSUF4WanRMMsLWn4FjSbqtMSqk3f5ZMMldk5sTEVn\na8L6D0AdF4f79n9zvJ9JkoT/Fn/MDc35u8Pf+voOhCImMi2S9hva09mjM182+DLHa1m3bnG7Q0fs\nx47F4f339HbNAYtOcC0ihcMfNc/ZM0fIJVOl4ditOPYFR7H/WjQPkjIBqOZq+7iBeOVS1nq5VxFe\nP5VGS1hcOiER8ZhdWEbt0ABMtOms1rRklsqfBOSesGVKmOUo43v01aIQ9e2KTMrk1303WXs6HBND\nJcMbuzOicflXz2zMTIYt78HVTeDdFroFyPeCgvCWEgGoZ+gSgHokMi2SRZcWsf7meiQk/D39GeE7\nAmcLZz3v8s2SstO5+ucIKkdv46xJbcqPXEkJu1cfc69JSiJ83DgyTp/BcepUSg4ZLG4o8iPsKOz/\nDsIOg3VppCZTyLZpSGrQEbmB+JkzoFajtLbGslEjLJs2waJxY732P9JKWg7cPUDAxQCC44MpY1mG\nkb4j6ejRESPlmyk9kCSJc9HnWHZlGQfCD2CoNKR9+fYMrDzwpTIe1HFxJG3dStKGjWTduIHC2Bir\nli2x8ffHon69V5rw94KNQtgRuTwv+F9AAZU6Qt3R4FZfpGALb4erm2HtQBi2B1zr6LTEkCUnCYlJ\n5dCU5qjuP+BWy5Y4TJyA/ejROY47H32eATsG8FWDr/D38tfH7oUiasbJGawOXs2Wrltws87Zly98\n7DgyzpzB88B+lOb6GR5x9FYsfRee4JsulRlQv5xe1ixOopIz2R8sNxA/EhJLhkqDubEBjTztaVnJ\niWYVHXC0Ev3aioX0eDgwHen0YrTGltyoOI79lp25HpvJjaj/s3efYVGe6d/Hv0PvgyBFEKwgRUVN\n1GisYC8o2KLGksSWsptk/4kx2eTZTTFt04uCJjF2o7Fh7z12BUSwgIh0kDIwtBlm7ufFrRhIEXBo\nen2OY49NmLtcEMrMb67zPAu5kV2ERqevONzd3vJO03MbvO5M5WvvbFOv5ayqYi2LjySw7EQiekli\nas9WvBTYnua1GSyQeVn+m5d7A4L+H/R+udal54LwsBABVBUPEkDdlVGUwQ+XfmDj9Y0oUBDqFcqs\nTrOadhAlSURt/RLfix+QbdQc3YSVePrVvJROX1ZG2vw3KNyzh2bTp+GyYAEK8Yu4ZlLOw6EPIOEg\negsXih3HoU4zR338N7TJyQCYe3lV7HKy7NLFsH2OkIOn/Un7CY8O51reNTxtPZnTeQ4j2o6ot+Dp\nzyQVJLEydiVb47dSqiult1tvZvjNoJdbr/uGnZIkURobi2rTZgq2b0enUmHi6opyzBjsQ8Zi1rq1\n4RaalwRnf4ALy+XJMa6d5CCq43gwFU+6hYfYrgVyWeqCW7VqUKsuK6fbMwUIDgAAIABJREFU+/uY\n9kQr3hnlx+3Fi8n++hvaH9iPqXvl8vd3TrzD3pt7OTTx0H3Lc4WH2+2S2wzfOJxBrQbxUd+PKj1W\nfOEiSVOm4PLWWzhMn2aQ+0mSROji38guLOPQawMwNX60n+fo9RIxaSoOxGVx8EoWl1JVgBw2DPKV\nG4j3bOMgdos9zLLiYPebcOOQ3CZi6IfgPYRynZ7kvBKuZRYSf7ecL1NNQraasvJ7wZSb0oL2LrZ4\nO9vcKeOTy/nsDBhMlWh0/PzbTRYfjqewrJyQLu68OtgbD4da/v2IXAPb/wUWdjD+J2jdx2BrFYSm\nTARQVRgigLorXZ3O0ktL2Ry/GQUKxnmNY1anWbhY12yEfWNy9dx+mm2fjS1qknp/jM+Q52p8DUmv\nJ/Pjj8lbsRLboUNx+/QTjMzFuOL7So+GQx+ivbgHdY4j6qL2FF3NRCotRWFhgfUTT8ihU79+mLrV\nbnLh/ej0OvYm7SU8KpwEVQKt7Vozp/MchrcZjolR49k2nV+az4ZrG1hzZQ23S27j1cyL6X7TGdFm\nRLV6Uek1GtQHD5K/eTNFx46DXo/lY49hHxqC7dBhD9wrq4KmCKLXy+V52XFg5QiPPQPdnwO7uvlv\nKAgNKrwfmNvBzO21On3npXReWH2BX+Y8QY82DtwYPgITJydarVxR6Ti1Rk3ghkBGtBnxh7Ir4dH0\nxbkv+Pnyz2wes5l29pV7M92c+jTa9DTa79mDohZtBv7MvthMZq84xxcTAwjt9uiVWxdryjl+/TYH\nr8ihU1ZhGQoFdPNsRpCvM0E+Lni72Iid8I8SSYJru+U+SLkJ8mTmoR+C0x8nRur0Esm5xRU9puKz\n5Kl88VlqSrX3gilXO4s7O6Zs8Xa5F04pLav/c6zV6Vl/Lpmv918nq7CMIB9nXhvaAd8WdrX7PLUl\nsGs+XFgBrfvCuB/Btum+9hMEQxMBVBWGDKDuSlOnsSR6CVvjt2KkMGK893ie6/TcH0YCNxVpKTe5\nvWwKnXWXiWs1Fd/pX0Mt+vzkLPuZrE8+wfLxx/D4/nvD9t15iEhplylZ/Q7q386gzrCmLE9+J9XU\n3R2b/v2xGdAfqx49MLKou50z5fpydt/czZLoJSSqEmmnbMfcgLkMaTXkbyfQNTSNTsPOxJ0sv7yc\n+Px4mls2Z4rPFCZ2mIjSvHrfb9rMLFQRW1Ft2owmMRGFpSV2Q4agDA3FqvvjhtnBJ0mQeFQOoq7u\nBCNj8A2Wd0V59BDlecLDobQAPmkF/V6Xp3PWwivrLnL0+m3OvBWENuYSNyc9RYuFH2A/blyl49Zf\nXc/7p95n7ci1dGze0RCrF5q4vNI8hm0cRh/3Pnw+4PNKjxUeOkTK8y/g9uknKIODDXI/vV5i+NfH\n0EsSe17ph1FNJmU1Uan5JRy800D8t4QcNOV6bM1N6OftRJCvMwM6OONgbZiBJEITVq6RG3If+RQ0\naugxG/q/AVb3bxGh00uk3tkxdf1OKHU9U018lpoSra7iOBc7c7zu7JK6+//ezrYore69XtHrJXbG\npPP53msk3i7i8VbNeGO4D91bP0CritwbcsldxiXo+38w4C0wbjxv0ApCYyACqCrqIoC6K6UwhR8u\n/cDW+K0YGxkzwXsCz3Z89r4NkxsjdXEJv4W9wJCCTSTZBOA++xdMlDVvuq7asYP0BW9i6umJ59Il\ndbZzp6kpz8ujaNdG1FtWoL6SiV5jBEYKrLp1xWZgEDYD+mPWtm2dv3NYri9nZ+JOlkQvIakgifb2\n7ZkXMI/BrQZjpGg6JQWSJHEy7STLY5fzW9pvWJpYMqbdGKb5TftDP5C/u0ZJZCSqzVso2LkTvVqN\nacuWKEPGohwzFrOWBpp+mZt4pzxvJZSpoEWXO+V5oWAidgoKTVj8flg1DqZtgXYDa3y6Vqfnsff3\nMcTflc8mBJDx3vvkb9yI14njGNvYVDp24raJ6CU9G0ZvEDsshArfXfyO8OhwNozegI+DT8XHJb2e\nxDFjQGFEm61bDPY9s+ViKq/8Ekn4tMcY6t+E2zD8BZ1eIjI5n4NXMjkQl8WVjEIAWjtaEeTrQpCP\nM4+3dsDMpOk8XxDqUdFtOPiB3I7AQimHNY8/W6vARq+XSM0vqQikrmWqic+SQ6pizb1gysnWHG8X\nG9o72XDhVj6XUlV0cLHl9aEdCPJ1frCf/bhtsOUFUBhB6BLwHlr7awnCQ0wEUFXUZQB1V3JhMkuj\nlxKREIGJkQkTvCfwXKfnaG7ZvE7va2g6vUTEyq8YduNDSk1sMZuyCut2vWt8naLTZ0h56SWMLC3x\nWBKOhY/P/U96yEiSRFlcnDyx7sBeSmLiQAJjCz02AW2xCXkW66BhGNva1st6tHot2xO2syR6CSnq\nFDo068C8gHkEegY2qeDpz1zLu8aKyyvYkbgDnV7HQI+BzPCfQVfnrtV+4qEvKaFw/37yN22i+NRp\nkCSsnnhCLtEbPBgjS8sHX2iZGqLXybuibl8Dayf5idnjz4Ltw/dCRngEHHgfjn8p938yt7n/8VWc\niL/N1B9Os2TaYwz2cuB6335YP/kk7l9U3s0SmxPLpO2TeKvnW0z2mWyo1QsPgQJNAcM2DuMx58f4\nNujbSo/lb9lC+oI38QgPw6Z/f4Pcr1ynZ+Dnh3GwNmfLC70fijC0sFTLseu3ORCXxeGrWeQUaTA2\nUvB4q2YM8nUh0NeZts2tH4rPVagnGTGwewHcPAZOPnJZXvsgg1xar5dIU5XIu6Xu9Je6lqUmPrOQ\nZtZmvDrIm7Fd3TF+kB2KOi3s/y+c/A7cusGEn6FZK4OsXxAeRiKAqqI+Aqi7kguSCY8OZ/uN7Zga\nmTKxw0Se6fhMkwuidu7bR8fjL9BCkUvhgA9w6D+vxiVDpVevkTxnDnq1mpbffYt1r151tNrGQ6cu\novjUSdRHjqA+cpTyrCwALBy02LhrsRk0FIun3kVRi51ltaXVadmasJUfLv1AqjoVXwdf5gXMY6DH\nwIfuyWR2cTZrr6zll6u/UKApoFPzTkz3n84gz0E16melTU0lf+tWVJu3oE1OxsjGBrvhw1GGhGDZ\ntcuDf90kSW7aeTocru2Ry/P8Q+RdUS0b/He3IFTfshFyb4w5h2p1+n+2xvDLuWQuvjOE8mOHSXnx\npT8NCz449QFb47dyYOIB7Mxq2cNDeGgtiV7Ctxe/Zc2INXRy6lTxcUmrJX7IUMzc3Wm1aqXB7rfq\nVBJvb4lhzaye9G7ftJ7f3ZWUU1TRQPx0Yg5anYTS0pSBHZwI9HWhv5dTpdImQagxSZInBO/9N+Td\nBO9hMGQhNG9fR7eTX3c+8HO0gjTY8Awkn4Lus2HoQrFbXRDuQwRQVdRnAHXXrYJbFUGUmZEZT/k8\nxUz/mThaOtbrOh7EqcsJaDY8Rz8ucrv9eJpP+g5Ma7YLRJueTvKcOZTdTMLtw4UoR4+uo9U2HM3N\nm3cCpyMUnz2HpNViZG2NdXslNlbXsHEtxaT3VOj3Gijrr2mpRqdhS/wWfrj0A+lF6XR07MjzXZ6n\nr3vfhy54qqpYW8zWhK2sjF1JcmEy7jbuTPWdSqhXKNam1W82Lun1FJ87J0/R27MHqaQEszZtUIaE\noBwzBlMXA/R8y0mQy/MuroKyAnB/TA6i/MbWaqKYINSb8jL4yEPu9TF0YY1PlySJ3h8fpJO7kiXT\nHyflH/+k+MIFvI4crjTls1hbTNCGIAI9A1nYp+b3ER5+Rdoihm8cjq+jL+GDwys9lrt8OZkffUzr\ndWux7NLFIPcr1ero++khvF1sWD3rCYNcs66V6/ScT8rj4JUsDlzJIj5LDUB7Z5uKBuLdPO0xecSn\n+wl1oLwMTi2Go59BeQn0mAv954OlfUOv7I8SDsHGWfIbK8HfQKfxDb0iQWgSRABVRUMEUHclFSQR\nHhXOjsQdmBub81SHp5jZcSYOFg/QDK8eJWQVcGzpa8zU/kK+0g/7metqvAVVV1BAyosvUXz2LM6v\n/R8Ozz3XpAMQvUZD8dmzqI8coejIUTRJSQCYtWuHTe8e2DTLwCpnCwp9CQRMlpvzOrSpt/WV6crY\neG0jP8b8SFZxFp2dOvN8wPM86fZkk/6614ZOr+NwymFWXF7BhawL2JraMt57PFN8p+BqXbOSN526\niMI9e8jfvImSc+fByAjrPk9iHxKCTVAQRmYPGBaVFULkWjgTDjnxYONyrzzPpmkONxAecrdOwU9D\nYdJq8B1V49MvpagY/d1x/je+M6Htbbnetx/NpkzG5c03Kx23JX4L75x4h+XDltPNpZuhVi88ZJZf\nXs5n5z7j52E/85jLYxUf1xcVcT0wCKvuj+Px3XcGu1/4kQQ+2nWFLS8+SRePRvhCGlAVazl8Td7l\ndPhqNqoSLabGCnq2cSTI15lAH2daORpoAqwg3E9hJhx8X37DzcoBBv4bus1oHA299Xo4+j84/JE8\nwW/iij+d5CcIwp8TAVQVDRlA3ZWoSiQ8OpxdibswNzZnss9kZvrPpJlFswZdV3XkFWlY8sMins/9\nBFNTE8wnLcfIK7BG19BrNKQvWEDBzl00mzoVl7feRGHceCetVaXNzEJ99M4up99Ooi8uRmFmhlXP\nnvLUuie6YpYSASe/l4OEjqEw4E1o7lVvaywtL+XXa7/yU8xPZJdk09W5K/MC5tGrRa9HLnj6M5ey\nL7E8djn7kvZhhBFD2wxlht8MfB19a3wtTVIS+Zs3o9qylfKMDIyUSpQjR6IMDcXC3+/Bvt56PSQc\nhNNhEL8PjEyh4zjoORfcxYtvoRE59jkceA9evwHWNd/d+8Xeq3x3KJ5zbw9GsW0TGf99lzabNmLh\n51fpuGk7p6HSqNg6Zqv4XSb8pZLyEkZsGkEru1YsG7qs0vdK9jffcHtxGG13bMe8bVuD3E9dVk7v\njw7wRFtHlkxv8OfcgLyrMCG7qKKB+LmkPHR6CUdrMwb6OBPk40wfr+bYWojSOqEBpUfB7jch6QQ4\n+8Owj6CtYXq01UpRDmyaDQkHoPMkGPUlmIlgVhBqQgRQVTSGAOquG6obhEWFsTtxN5YmlkzxncIM\nvxnYWzTOd8/u0pTr+eqXnQRfXYC3USq6AW9j2v9fNeoLJen1ZP3vM3KXLcN28CDc/vc/jCws6nDV\ntSfpdJRER1f0ciqLiwPApEULbPr3w6Z/f6x79sTIRJL7+Jz4GkrzwWeUPIrcxb/e1lqsLWbDtQ0s\ni1lGTmkOj7s8zvMBz9Pdtbt4sfYnUtWprIpdxabrmyguL6a7a3dm+M2gb8u+NW7GLul0FJ06hWrT\nZgr37UPSaDD39pZL9IJHY+L4gCW3t+PlscaRq+Wxxi17yEGU3xgwFi8ghAa2ajzk34KXztTq9GFf\nHUVpacovc3txc/IU9OpC2kREVPq9FZ8XT0hECK89/hoz/GcYauXCQ2pN3Bo+OvMRSwYvoZfbvb6T\n5bm5xAcGYTdyBG4LDVfG+cXeq3xzMJ59r/bDy6V+BopUpSnXc/Zm7p1+TpnczCkGwMfVtqKBeEBL\n+wdryCwIhiZJELsV9r0j/x3xGQWD3wPHdvW7juQzsGEmFGXD8E/hsZk17nkrCIIIoP6gMQVQdyXk\nJxAeFc7um3IQNdV3KjP8Z6A0Vzb00v6SJEksO3yZ5gdfI9j4JKXtR2IxPgwsatYQNnf5cjI//gTL\nrl1p+f13mDRrHLvAdPn5qI+fQH30CEXHjqPLywMjIyy7dpV3OfXvj7m3l/ziSFsK536C41/If7S8\nhsjBk1vXeltvsbaYdVfXsfzycnJLc+np2pO5AXPp7tq93tbwl2vTlBObVkBqfgm92jribNf4gsYC\nTQEbr21kddxqMoszaaNswzS/aYxuOxoLk5qvV1dQQMHOneRv2kxpdDSYmGDTvz/2oSHY9OuHwvQB\nAqPSAjmEOh0OeYlg2wIefw4efwasm2YDXKGJ0+vgk9bybs/RX9f49KScIvr/7zDvjPJjmocRCUOH\n4fza/+E4a1al4z458wnrrq7jwIQDTaZ0XWg4Gp2GkZtH4mzpzKoRqyqFmRnvvU/ehg20378PUxcX\ng9wvt0jDkx8fZHhHV76YZJj+UtWRoy7j8NVsDl7J4ui1bArLyjEzMeLJdo4E+roQ6OOMu70BJrcK\nQl3TlsqT5o59AXqt3AOz3+s1fm1RY5Ik7zTf+zbYucsld2719zMsCA8bEUBV0RgDqLvi8+IJiw5j\n7829WJlaMdV3KtP9pjfqIGrf5QzO/7KQ14xWobNvi/nUteDkXaNrFOzeTdrr8zFt2RKPpUsxa+le\nR6v9a5IkUXbtekUD8ZKLF0Gvx9jeHut+feXQqU8fjJW/+29RroGLK+RGioXp0KY/BL4NHj3qbd1F\n2iLWXlnL8svLyS/Lp7dbb+Z2nttgvVHUZeVcTlURk1ZATKqKS6kqbmSr0d/58TdSwBNtHQkOcGN4\nxxaNbqqOVq9lz809rLi8grjcOBwsHJjUYRKTOkyq9dCAsvh4uUQvIgJd9m2MHRxQjh4tl+h1qNnP\nSiV6vVyWdzpMLtMzNpcbZPaYI544CfUrPRrC+0LIEgiYVOPTfzh2gw92xHFs/kAsVv/E7UWLaH/o\nIKau93qzlenKCNoQxBMtnuCz/p8ZcvXCQ+zXa7/y7sl3+S7wO/p73Cvr0aSkkDB0GA4zZuAy/3WD\n3e+9bbEsP3mTw68NwMPBymDX/T1JkriaWVgxte7CrTwkCZxtze/0cnLhyfaOWJk1gl46glAbBely\nSXfUGrB2gsB3oOvT8pRgQystgK0vQlwEdBgBYxeBZeN4M1wQmqomF0ApFIqfgFFAliRJHe98zAH4\nBWgN3AQmSpKUp5DfzvoaGAEUAzMlSbrwd9dvzAHUXdfzrrM4ajH7kvZhY2rD035PM81vWqMdN305\nTcX3y37mfc1nKE11mISGgV9wja5RdOYMKS/9A4W5GZ5LlmDhW/NePDWlLy6m6NRpOXQ6epTy9HQA\nzH19K0rrLDt3/mN/Kl05RK2FI5+C6hZ4PAGB/4Y2/ep8zXcVagpZE7eGlXErUZWp6OPeh7md59LF\nuf6CB1WJlstpKmJSVcSkyoFTYk4Rd3/UXezM6eSuxN9NSSd3Jc525uyPyyIiMpWbOcWYGivo7+3E\n6AA3Bvu5NKony5IkcTbjLMtjl3M05ShmRmaMbjea6f7TaausXc8Qqbwc9bFjcone4cOg1WLh748y\nNATlyJEY2z9A6W321TvleWtBWwSeveTyPJ9RojxPqHunw2HXfHjlEth71vj0ieEnKSjRsuvlviQM\nGYqZR0s8f/qp0jG7Encx/+j8P5RTCcLf0eq1BG8OxtbMlnWj1lUqrU79v9dQHz5M+0MHMbYzzPOr\ndFUJ/T49xFPdPXl/bEeDXBPkSXunbuTIU+viskjNLwGgc0slgT7y1Dp/NzuMRGmd8DBJvSD3h0o+\nBa6dYNgn0PpJw10/IwbWT4e8mzDoP9D7n6LkThAMoCkGUP0ANbDidwHUp0CuJEkfKxSKBUAzSZLe\nUCgUI4B/IAdQPYGvJUnq+XfXbwoB1F1Xc68SHh3OvqR92JraMs1vGk/7PY2tWcP0Fvg7WQWlLFi2\nm3/mvEcXowSkJ19FEfROjd6tKLt+nVtz5qJXqXD/9htsnjTgH5k7NMnJqI8clRuInz6NpNGgsLLC\nuncveZdTv35/vR1fr4OYjXD4Y8hNkEvsAt+GdkH19gerQFPA6tjVrIxbSaGmkP4t+zMvYB4dmxvu\nie6fySvSEJN2L2iKSVORdKe3BICb0oKO7ko6usthk7+7Hc62f166JkkSl1JVRESmsT06nYyCUixN\njRnk50JwgBv9vZ0wM2k8o59v5N9gRewKtiVsQ6PX0K9lP2b4zXigvlrleXkUbNtO/ubNlMXFoTA1\nxSYoCPvQEKyffLL2TflL8u+V5+UnyVvJuz8H3WbWqjG0IFTL+hmQcg7+dbnGp+aoy+i+cD8vBXox\nz1FN0pSptPj4I+zHjq103Kw9s0hRp7AzdGeN+7MJj7ZtCdt46/hbfDHgCwa3Glzx8dK4OBJDQnF6\n9VWaz51jsPu98Ws0myNTOf7GwL/8O1gdWQWlHLoqB07H429TrNFhaWpMH6/mBPk4M9DHGZdGWNIu\nCAYlSfJz733/gYIUue/l4PegWesHu+7FVbDj/8DCHiYsg1a9DbJcQRCaYAAFoFAoWgPbfxdAXQUG\nSJKUrlAoWgCHJUnqoFAowu/889qqx/3VtZtSAHXX1dyrLI5azIFbB7A1uxNE+Ta+IKpEo2PBL2fp\ncfVTppocQN9mIEbjf6zRC19tZibJs+dQduMGbgs/QDlmzAOtSdJqKT5/oaK0TnPjBgBmrVphM6A/\n1v36YdW9O0ZmZn99Eb0ermyDQx9C9hVw6SiPi+0wvN6CJ1WZipWxK1kdtxq1Vk2gRyBzA+bi5+h3\n/5NrKEddxqXUezubLqWqKt5tBfBwsKSjm7IicOroZoejjXmt7qXXS5y5mUtEVBq7LqWTV6xFaWnK\n8I6uBAe40bOtY6NplppTksP6q+tZd3UduaW5+Dr4Mt1/OkNbD8XUqPa7jErj4sjftJmCbdvQ5edj\n4uyMcswYlCEhmLdtU7uL6nVwfS+cWgyJR+TyvM4T5H4Krp1qvVZB+ANJgs87yDtAx/1Q49PXn0tm\n/q/RbP9HHxzDv0C1bRvex49hZH1v6lByQTIjNo/gn13/yezOsw25euERoNPrCIkIwQgjNgZvxPh3\nb4zdmjWb0itXaH9gP0bmtfs7VtWNbDVBXxxhbr92LBjuU+3zJEniclpBRQPxqBQVIL/BE3SngXiv\nto5YmDadqcGCYDCaYvjtWzjxlfwcp9eL0PdfYF7D10LaEtj5mhxAte4L438CG+e6WbMgPKIelgAq\nX5Ik+zv/rADyJEmyVygU24GPJUk6fuexA8AbkiSdq3K9OcAcAE9Pz8eSkpIe/DNqAHE5cSyOWsyh\n5EPYmdkx3W86U32nYmNm09BLq6DXS3y5/xqZR5ay0PRnjO1cMXpqVY160ugKC0l56R8Unz6N06uv\n4jhndo12mpRnZ6M+egz1kSMU/fYberUaTE2x7v54RQNxs9at738hSYJre+DQB5BxCZp7w4A3wW8s\nGNXPO/B5pXmsiF3Bmrg1FJcXM7jVYOZ0noOPQ/Wf1P6drIJSYtJUXEopuLPDSUW6qrTi8daOVpV3\nNrnZYW/1N2HdA9Dq9By/fpuIqDT2Xs6gSKPD2dackZ1bEBzgRhcP+0Yxya+0vJTtN7azInYFiapE\nXKxcmOo7lXHe4x6oTFbSaCg8fBjVps2ojx0DnQ7LLl1QhoZgN2IExja1/DnPipN3REWtg/ISaNVH\nLs/rMAKMG0/Zo9BE5STAt91g5BfybrsamrX8HHHpBRx9pTfx/fpjM6A/7p9+WumYr85/xc+Xf2bv\n+L04W4kXCkLN7b65m9ePvM7HfT9mZNuRFR8vOnWaWzNn4vrf/9LsqZr3L/srL665wJGr2ZxYEIjS\n8q/foCjR6DgRf5sDV+TQKbOgDIUCunrYy6GTjzM+rraN4m+fIDQKqlQ48C5E/wI2LhD0HwiYXL3n\n5TkJcsldZgz0fU0eGFQXfaUE4RH30AVQd/49T5KkZtUNoH6vKe6Aqio2J5bFUYs5nHwYpbmSGX4z\nmOI7BWtT6/ufXE82X0xh1cYtLDL9EiejQoxGfQldp1b7fL1GQ/qbb1GwYwf2k5/C9e23/7IsSdLr\nKY2JqSitK42JAcDE2bmil5PVE70wtqnm10eS4MYhOLgQUs9BszYwYAF0mlBvf6hySnJYHrucdVfW\nUVpeypDWQ5jTeQ7ezWrXtFqSJDIKSrmUcq9BeEyqiqzCMkDeyNW2ufXvgia5jM7OomH6B5VodBy8\nkkVEVCqHrmSj0enxdLBidEALggPc6eDa8Lv/9JKe46nHWX55OWcyzmBlYkWoVyhP+z2Nu82DNdLX\nZmVRsG0b+Zs2o0lIQGFhge2QwdiHhmLVoweK2gSgxbnyO35nlsq9y5Qe0H0WdJsOVmKimFBLF1fJ\nDVxfOAXONevdV6LR0fX9vTzV3ZN/maWQ+sorePz4Q6Xya61ey+ANg+nk1IlvA7819OqFR4Re0jNh\n2wRKy0vZOnYrJkZy+C5JEjcnTkJXoKLdzp21L3+uIiZVxahvj/PaEG9eCvSq9FhafgkHr8gNxE/E\n36asXI+NuQn9vJsT6OPCgA5ONK/lrmJBeGQkn4XdC+Tn6S26wLCPodXf9AeM3QpbXpTfeAtZAt5D\n6m+tgvCIeVgCqEe6BO+vXM65zOLIxRxJOYLSXMlM/5lM9pncaIKoczdzeWPFQT7Uf0lPYuRR8cM+\nBpPq7aCR9HqyPv+c3B9/wmZQEO6ffYaRhdzvQFdYSNGJE6gPH0F97Bi6nBxQKLAMCKgIncx9fWv+\nruHNE3BoISSdALuW0H8+dJlSb42cb5fc5ueYn1l/bT2l5aUMazOMuZ3n0s6+XbWvIUkSKXklXE5T\n3SmlkwOnnCINIE+ia+9sc6d8Tkmnlkp8W9hhY944d8MUlGrZE5NBRFQaJ+Jvo5egg4stwV3cGN3Z\nDU/Hupk0VBOxObGsiF3BnsQ96NEzuNVgZvjNoJPTg5W7SZJEaXQ0+Zs3U7BjJ/rCQkzd3FCOHYsy\nNASzli1rflG9Dq7ukqfn3TwGJpbQeaK8K8rF/4HWKzyCtrwIV3fA6zdqvDN0z+UM5q48z5pZPfH4\n4j+UxsTQ/tDBSiHAgaQDvHL4lT9MMROEmjp06xD/PPRP3uv9HiFeIRUfL9izl9SXX8b9qy+xGzbM\nYPebuewM0Skqjs0fyLXMwooG4rHpBQB4OlgR5Cs3EO/RxqFR9T4UhCZBr4dLG2D/f6EwDfxD5f5Q\n9h73jtFp5f5Rp74H98dgws+1GpYhCEL1PSwB1P+AnN81IXeQJGm+QqEYCbzEvSbk30iS1OPvrv0w\nBVB3xdyOYVHkIo6lHsPe3L4iiLIybfgX5sm5xcz++RSheT8yx3gxkFCRAAAgAElEQVQ7tOwBE5eD\nnVu1r5G7chWZH36IZUAAtoMHoT5ylOILF6C8HCM7O2z69JH7OfXti0mzWo5OTTkHBz+Qdz7ZuEK/\n1+SdISb18y5kVnEWy2KWseHaBrR6LSPbjGRW51n3nbgmSRK3cosrejXdnUqXV6wFwNhIgZezDZ3c\n7/Vs8mthh6VZ09xynF1Yxs5L6UREpXE+KQ+ALh72BAe4MapzC5wbuCFrRlEGa+LW8Ou1XynUFtLN\nuRvT/aYzwGNApb4jtaEvLaVw/wFUmzZRdPIkSBJWPXrIJXpDhmBkVYuf94wYOBMO0euhvFTuh9Bz\nntzfTGxLF6rjm67g5AOT19b41P9bH8X+uExOv9CNxIEDcZgxHZfXX690zPP7n+da3jX2jNtTsWtF\nEGpDkiSm7JhCbmku20O2Y3rnjSVJp+PGiJEY2djQ+tcNBit3O5OYy8Twk1iaGlOi1WGkgMdbOxDk\n40yQrzPtnGxEaZ0gGIKmCE58Lf8P5Gl2fV6RB7P8+gwkn4Yec2HIB9V+E1wQhNprcgGUQqFYCwwA\nmgOZwH+ALcB6wBNIAiZKkpR7px/Ud8AwoBh45u/K7+DhDKDuis6OZlHUIk6knqCZeTOe6fgMkzpM\navAgqrBUy0trLmIdv42vLJZiammLYsLPNRqlWrBnL2mvv46k0WDu7S33chrQH8uAABQmD/CiJD1K\nbi5+bTdYOUKff8l9TEwta3/NGsgoyuCnmJ/YeG0jOknHqLajmN15Nq3sWv3hWL1e4mZO0Z2gqeBO\nOZ2KwtJyAEyNFXRwta3UINzH1fahbViaklfMtig5jIpLL8BIAb3aORIc4MYw/xYorRqmfBCgSFvE\n5uubWRW3ilR1Kp62njzt9zRj2o0xyM+jNi0N1dat5G/egvbWLYysrbEdPgz7kBAsu3Wr+Yua4ly4\nsBzO/CBPmbH3hB5zoOvTYFnLUFd4+BVmwufeMPh9ePKfNTq1XKfn8YX7GdjBmXe0l8n84APaRGzF\nwvtemXFGUQZDfpXLj1/q+pKhVy88gk6knmDe/nm83fNtJvnc6/mUt349Gf/vP3gu+wnrXn9TxlND\n72yJIb9EyyBfZ/p7O9VZD0VBEID8ZNj/H3lqnm0L0GmgvAyCv4GO4xp6dYLwyGhyAVRde5gDqLsi\nsyIJiwrjRNoJHCwceMb/GSb5TMLSpH5ClT9TrtPzwY44Tpw8zkrrb3DRpaMYulDebVHNF8vazCzQ\nlWPqVv3dU38pK04OnuIiwEIpv1vScx6Y109D93R1Oj/G/Mim65uQJIng9sHM6jQLD1t527BOL3Ej\nW12pQXhsWgHqMjlsMjMxwtfVtlKDcC8XG8xNHs6w6X7iswqJiEwjIiqNmznFmBor6O/tTHAXNwb5\nOmNl1jA7J8r15Ry4dYAVl1cQfTsapbmSid4TmewzGScrpwe+viRJlJw/L0/R270bqbgYs1atUIaE\noBw7BlNX15pdUFcul1OdDpfLUE2tIOAp+Z1DZ8M0vhceIpc3w4aZMOsAtKzZ84xTN3J4askpFk/t\nhs97LyOVl9N286ZKxyyOXMziqMXsHrcbNxsD/N4XHnmSJDFz90xSClPYEboDCxN516y+rIz4oEFY\neHvj+dOPDbxKQRAeyK1TsOctKNfAhGXQ3Ov+5wiCYDAigKriUQig7orMimRR5CJOpp/EwcKBZzs+\ny8QOExs0iFp58iafbTvHYqsl9C4/LTf2Hv0NmNXTLq2cBDj8EVz6FcxsoNcL8MQLYGl//3MNIFWd\nytLopWxN2ArA2PZjecbvWYpLlFxKubOzKVUOm0q0OgAsTI3wbWF3r4zOTQ6bTI1Fv4iqJEniUqqK\niMg0tkenk1FQiqWpMYP9XAgOcKOft1OD9NmQJInI7EiWX17OwVsHMTEyYUSbEUz3n17rxvJV6YuK\nKNizF9XmzRSfPQtGRlj37o19aAg2QUE1HzGeHn2nPG8D6MrAbwyM+b7mI4+Fh9fO+XBxJSy4VeM+\nee9ti2XV6STOPN2O9LFjcF7wBo4zZ1Y8rtPrGLZpGO2U7QgbHGbghQuPsrMZZ3l2z7O8/vjrTPef\nXvHx20uWkv3FF7Te+CuW/qIfniA0eZJU7Te5BUEwHBFAVfEoBVB3Xci8wKKoRZxOP01zy+Y82/FZ\nJnhPqHjnr74du57Ni6vPMc9oK8/r16Fw8YdJK8Hh7/sdPZC8JDj6KUSulfs69ZgDT75cb9O/kguS\nWXppKREJ21CgIMB+CI7lw0hINyUuvYCycj0AVmbG+LvZ4e+mrAic2jlZYyLCphrT6yXO3MwlIiqN\nnZfSyS/WorQ0ZXhHV4ID3OjZ1hFjo/p/YnKr4BYrY1eyNWErJeUl9HbrzQy/GfRy62WwfiCaW7dQ\nbdlC/pYtlKelY2Rnh93IEdiHhmLRsWPN7lN0W56cd/R/cq+fKetEA09BFtZHLtGcsa1Gp0mSRN9P\nD9HBxZaP8k6Qs3QpXkcOY+J0b1fgsZRjvHDgBT7v/zlDWotpRYJhzdo7i+t519kVuquiLFpXUED8\nwEBs+vfH/YvPG3iFgiAIgtA0iQCqikcxgLrrfOZ5Fkcu5nTGaZwsnXiu03OM9x6PuXH9j/uNzyrk\n2Z/P0b7wNGEWizAzBkJ/MPxY1II0OPoZXFgBCiO5v1OfV8HG2bD3+RNl5TqO3Ijl58s/ElNwCCQj\ntPk9Kb3dD6lcia25CX5udpUahLdpbt0gocjDTqvTc/z6bSKi0thzOYNijQ5nW3NGdm5BcIAbXTzs\n670ZrKpMxfqr61lzZQ23S27j1cyL6X7TGdFmBGbGhukTIun1FJ86Rf7mLRTu3YtUVoa5V3uUIaEo\ng0dj0rx59S8Wf0AutzKxkBtO17DkSnjIlKrg41bQ/w0Y+GaNTo1NK2DEN8f4eKw/j731LObt2+O5\nZEmlY1459AoXsy6yf/z+imbRgmAokVmRTNs1jZe7vcysTrMqPp75v/+Ru+xn2u3ZjZmHx99cQRAE\nQRCEPyMCqCoe5QDqrrMZZ1kctZizGWdxtnTm2U7PNkgQlVukYd7K86QnxbHRYTFORddRDHwL+r5W\n43Hef6DOguNfwtkfQdLLE+36/h8o3Q2z+CpKtTri0guISVURk1rAhfSrpEjbMLaLBMkYRWEvfK2C\n6erWqiJsauVghZEIm+pdiUbHgSuZRESmcfhqNhqdHk8HK4ID3Aju4oa3S/2WmGl0GnYm7mRF7Aqu\n512nuWVzJvtMZqL3ROwtDFcaqisspGDnLlSbNlESFQXGxtj064cyNATb/v1RmFUj9Mq6AmsnQUE6\nhCwWTT0fZdf3werxMH0rtB1Qo1O/3n+drw5c4/hQJQXzZuP22WcoR42sePx2yW0GbxjMNL9p/Ovx\nfxl23YJwx4sHXiQyK5Ld43Zjayb/3tdmZpEwaBD2E8bj+v/+XwOvUBAEQRCaHhFAVSECqHvOZpzl\n+8jvOZ95HmcrZ2Z1msU4r3EG231RHWXlOt7aFMOOCwmscF5Lj4K94D0cQsJq15epOFcew3pmiTz5\nImAy9H8dmrU22JqLNeXEpslh06XUAi6nqbiepUanlzAyy8TG9RCSVRTGCjOedB7NnIBn6dyipRi3\n3AipSrTsuZzBtqg0TsTfRi+Bj6stowPcCA5ww8Oh/iZISpLEybSTLI9dzm9pv2FpYklwu2Cm+03H\n086wJW9lCQmotmxBtWUr5dnZGDdrhjJ4NMqQECx87tNsvCgHfpkKt07CgLeg/3zRY+FRtP9d+O0b\nuf+TmXWNTh35zTEsTY35JmUHhbv34HX8GEaW93oT/nDpB76+8DXbxm6jtbK1gRcuCLLYnFgmbZ/E\nCwEv8HyX5ys+nvb22xRs2077gwcwcXRswBUKgiAIQtMjAqgqRABVmSRJnMk4w6LIRVzIuoCLlQuz\nO80mxCuk3oIoSZIIO3KDT3bH8Vbz48wuXorC3hMmrQYXv+pdpFQFJ7+Hk4tAo4ZO46H/Amje/oHW\npi4r53KqipiKwEnFjWw1+jvfzs1tzOjorqSlcz6Juq1cyjuGhYkFk30mM91vOo6W4slrU5FdWMbO\nS+lERKVxPikPgK6e9gQHuDGycwucbeuvZ9r1vOusiF3Bjhs7KNeXM9BjIDP8Z9DVuatBg0ypvJyi\nEyfI37QZ9cGDSFot5n6+2IeEYjdqJCbNmv35ieVlsO1liFoLHcfLzclNG6annNBAfhomj7iefbBG\np6XkFdPnk0O8HdSavgtmYDt0KG4fLqx4XJIkRm4eiYuVC8uGLTP0qgWhklcPvcqp9FPsCt1VseO0\n7EYiN0aOxHHeXJxffrmBVygIgiAITYsIoKoQAdSfkySJU+mnWBS5iMjsSFytXeUgqn1IvfXf2B2T\nziu/RDLA8gbfmXyFiVYNY777+zKfMjWcDoPfvoXSfPANhoFvgbNvje+vKtFyOU1VUUYXk6oiMaeI\nu9+6LnbmdHJXVmoQnleeyJLoJey/tR9rU2um+Exhmt80mln8xQt3oUlIzi1me7QcRsWlF2CkgF7t\nHAkOcGOYfwuUVvXzM3G75DZr4taw/tp6VGUqOjXvxHT/6QzyHISJkYlB71Wel0fBjp2oNm2iNDYW\nhakpNoGBKEPGYtOnDwqTKveTJLnM9cC70LIHPLW6XnqrCY2AthQ+9pCHOQxdeP/jf2fZiUTe3RbL\n/i5laP/7bzyXL8e6Z4+Kx8+kn+G5vc/xUd+PGNV2lKFXLgiVXM+7zriIcTzb8VleeeyVio+n/OMf\nFJ05i9fBAxhZ12yHnyAIgiA8ykQAVYUIoP7e3TKg76O+Jzo7mhbWLZjdeTZj242tlyDqUoqKWSvO\nYlGazVbnJdjfvgC9XoJB74Lx714Aa0vk/k7Hv4Ti2+A9TA6eWgRU6z55RRpi0u4FTTFpKpJyiise\nd7e3xP93DcL93e0q7YC5nHOZsKgwDicfxtbUlql+U3na92mU5kqDfS2ExuF6ZiHbotKIiErjZk4x\npsYK+ns7E9zFjUG+zliZGTYI+jPF2mIiEiJYGbuSW4W3cLdxZ6rvVEK9QrE2NfyLo9KrV1Ft2oQq\nYhu6vDxMnJxwmDkTh2ef+eMOrNitsGkuWDvBlF+qv2tRaLqSfoNlw+GpNeAz8v7H/86UpafILizj\nxyurKYuPp/3+/Sh+1/Nv/tH5nEg9wcGJBxtkQIbw6Hnj6BscSj7EztCdNLeUBzOUREVxc9JTOC94\nA8eZMxt2gYIgCILQhIgAqgoRQFWPJEn8lvYbiyIXEX07GjdrN+Z0nkNw+2BMjeo2iMpQlTJrxVmu\np+Wyqd0O/FN+gdZ9YfwysLCTJ9od/QzUGdB2IAz8N3h0/8vr5ajLuJR6b2fTpVQVqfklFY97OFhW\n2tnk72aHo82fv/C5lH2JsOgwjqYcxdbMlml+05jqOxU7MzuDfx2ExkWSJKJTVEREpbE9Oo3MgjKs\nzIwZ7OdCcIAbfb2cMDN5wOb596HT6ziccpgVl1dwIesCtqa2jPcezxTfKbhauxr8fpJGg/roUfLW\nrqPoxAnsJ0zA9b//QWFsXPnA1AuwdjJoimD8T4afZik0Lkc/g4Pvw/xEsHKo9mn5xRoe+2A/L3dt\nxuD/zsZx1iycX7236yS/NJ/ADYFM8J7Amz1rNllPEGrrpuomY7aOYarvVOZ3n1/x8aRp09EkJ9N+\n757qDWkQBEEQBEEEUFWJAKpmJEnieOpxFkUuIiYnBncbd+Z2nsuodqPqNIgq1pTzr1+i2H05g0+9\nLjMh/XMUlg5gZAyqZPDsDYH/htZ9Kp2XVVBKTJqKSykFd3Y4qUhXlVY83qa5daWdTR3dlNUqp4rM\niiQsOowTqSdQmiuZ7jedyT6TKybnCI8WnV7iTGIuEVFp7IpJJ79Yi9LSlBGdXBkd4EbPNo4Y1/GE\nw0vZl1gRu4J9SftQoGBom6HM8JuBr2PNy0/vR5Iksr/+mpywcGwHD8Lts88wMq8S0qpSYe1TkBkD\nQz+CnnNFc/KH1apxoEqBF0/X6LRNF1L41/ootrnewiTsG9ru3IF527YVj6+MXcmnZz9lY/BGvJt5\nG3rVgvCX3jnxDjtv7GRn6E5crF0AUB89SvKcubT46CPsQ8Y28AoFQRAEoWkQAVQVIoCqHUmSOJZ6\njEWRi7icc5mWNi2Z03kOo9uNNngvmrv0eonP9l5l0eEEJnvk8YH2M4ytHSHw30htBpBRWMallHsN\nwmNSVWQVlgHy6962za3p6K6s2N3k726HnUXNQrMLmRcIiwrjZPpJmpk3Y4b/DJ7yeapOyp6EpklT\nrud4fDYRkWnsjc2kWKPD2dacUZ3dCO7iRkBLZZ1OQExVp7I6bjUbr22kuLyY7q7dmeE3g74t+2Kk\nMOyOrNwVK8n88EOsunen5aLvMbatEsCWqWHTHLi6Ax5/DoZ/AvXUQ06oJ3odfNJa7s03+qsanTpv\n5XkuJuex9uwiFCYmtNmwvuIxSZII2RqCtak1q0euNvCiBeHvpapTGbV5FOO8xvH2E28D8vdk4tgQ\nJF05bSMiKpWKCoIgCILw50QAVYUIoB6MJEkcTTnK95HfE5cbh4etB3M7z2Vk25F1FkT9ej6FNzdF\n42FvyfDOLSr6NuUUaQAwUkB7Z5uKHU2dWirxbWGHjXnt13M24yxhUWGcyTiDg4UDz/g/w8QOE7Ey\ntTLUpyU8hEo0Og5cySQiMo3DV7PR6PS0crRi9J0wytul7nbMFWoK2XhtI6viVpFZnEkbZRum+U1j\ndNvRWJgYbkKdatt20t58E3MvLzyXhGPi5FT5AL0eDvwXTnwtl8hO+Bks7Q12f6GBpUdBeD8IXQqd\nJ1b7tFKtjm7v7+MZNx2jvnoNl3//G4dpT1c8HpkVybRd03i397uEeoXWxcoF4W+9f/J9NsVvYnvI\ndtxt3AFQbdtG2uvzabloEbaBAxt4hYIgCILQ+IkAqgoRQBmGJEkcTj7M4qjFxOXG0cquFXM7z2V4\nm+F1EkSdScxl3qrzFJRo8XKxpaObHZ1ayjub/FrYYWlmfP+L3IckSZzJOMPiqMWczzxPc8vmPOP/\nDBM6TMDSxNIAn4XwKFGVaNlzOYNtUWmciL+NXgIfV1tGB7gRHOCGh0PdhJlavZa9N/ey/PJy4nLj\ncLBwYFKHSUzqMAlHS0eD3EN97Bgp/3wZk+bN8fzxB8w8Pf940IWVsP0VcGgrNyd3aPvHY4Sm51QY\n7H4DXokBe49qn3YgLpPnlp9jo9F5rCI24HX0CCYO9/pHvXPiHfbe3MuhiYdE0C80iIyiDEZuGsnI\ntiN578n3AJDKy0kYMhQTV1darxE78wRBEAThfkQAVYUIoAxLkiQOJh9kceRiruZdpbVda+Z0nsOI\nNiMwNnrwUOj3NOV69JKEhalhr3t38l9YdBgXsy7ibOnMs52eZZzXOIPuHBEeXdmFZeyIlifpXbiV\nD0BXT3vGBLgxsrMbTraGn/YlSRLnMs+x/PJyjqQcwczIjNHtRjPdfzptlQ8eBpVERZE8Zy6YmuK5\ndAkWvn/SeyrxGKyfBijgqdXQqvcD31doYOuny03nX42p0Wlv/BrNrqhUfj3yMZb+/ngsXlTxmFqj\nJnBDICPbjuQ/vf5j6BULQrV9cuYT1l5Zy5YxW2itbA1A7spVZC5cSKs1q7Hq1q1hFygIgiAIjZwI\noKoQAVTd0Et6Dt06xKKoRVzLu0Zru9bMC5jHsNbDDB5EGcrdButh0WFEZ0fjYuXCc52eI9QrVIz/\nFupMcm4x26LTiIhM40pGIUYK6N2uOcEBbgzt6IrS0vA9k26obrAydiXbErZRpiujX8t+zPCbQXfX\n7g/Un6osIYFbz81Cr1bTctH3WPfo8ceDchJgzUTIS4Lgb6DLlAf4TIQGJUnwmTe0HQDjllb7NJ1e\nosfC/UxUpBO86iPcv/oKu2FDKx5ff3U97596n3Uj1+Hf3N/w6xaEarpdcpsRm0Yw0GMgn/T7BAB9\ncTHxgUFYdu1aKTgVBEEQBOGPRABVhQig6pZe0nPg1gEWRS4iPj+etsq2zAuYx5BWQxpNEHW3j1VY\nVBgxOTG0sG7BrE6zGNt+LGbGYtSyUH+uZxYSESXvjErKKcbM2Ij+HZwIDnBjkK+LQUpLfy+3NJdf\nrvzCuqvryC3NxdfBl+n+0xnaemitp1pq09O5NWs22uRk3D7/DLvBg/94UEmevHMm8Sj0+RcEvgOi\noW/Tk5MA33aDUV/C489W+7RzN3MZH3aSX3L2YB95Cq/jxypNUZy4bSJ6Sc+G0RvqtGG/IFTHl+e/\nZFnMMjYFb6J9s/YAZH/3Pbe/+4622yIw9/Jq4BUKdUkv6Ym5HcP+W/u5knOF0e1G18mufkEQhIeV\nCKCqEAFU/dBLevYl7SMsKoz4/HjaKdvJQVTrIQafzFVdd8sFw6PCicuNw93GndmdZhPcLhhTMalL\naECSJBGdoiIiKo3t0WlkFpRhZWbMYD8XggPc6OvlhJmJ4X5uSstL2X5jOytiV5CoSsTFyoWpvlMZ\n5z0OOzO7Gl+vPC+P5HnzKL0Ug+u7/6XZhAl/PEinhZ2vwfmfwXc0hISDmZgm2aRcWAkRL8ELp8HZ\np9qnfbgzjrVHrrBhz3sog4Np8d67FY/F5sQyafsk3ur5FpN9JtfFqgWhRvJL8xm2aRi93XrzxYAv\nAPl3XHxgEHZDh+L28UcNvELB0Mr15ZzPPM/+pP0cvHWQrJIsTBQmuFi7kKpOpa2yLS90eYHBrQY3\n2HNYQRCEpkIEUFWIAKp+6SU9e2/uZXHUYm6obtDevj3zAubV6x/xu7uywqPCuZp3FQ9bD2Z3ms2o\ndqNqvetDEOqKTi9xJjGXiKg0dsWkk1+sxd7KlOEdXRkd4EbPNo4YGxlml4he0nM89TgrLq/gdMZp\nrEysCPUK5Wm/pyumQFX7WsXFpLz8CkXHjuH06qs4zpn9x90skgSnFsGef0OLAJi8DuxaGORzEerB\nlhfg6i6YfwOquVNJkiQGfHaYkRmRjN6xhFarV2H12GMVj79/8n0iEiI4MPFArcJPQagLiyIXsThq\nMetHrcfXUe5vl7HwQ/LWrqX9vr2YthC/t5q6Ml0ZJ9NOsj9pP4dTDqMqU2FhbEEf9z4EtQqiX8t+\n2JjacPDWQb67+B0JqgQ6NOvAi11eZIDHALFbUxAE4S+IAKoKEUA1DJ1ex94kOYhKVCXi1cyL5wOe\nJ8gzqM6CKJ1ex75b+wiPCic+P76iQXpdTeoTBEPTlOs5Hp/N1sg09sVmUqzR4WxrzqjObgR3cSOg\npdJgT4LjcuJYEbuC3Ym70aNnkOcgZvjPoLNT52pfQ9JqSXvr3xRs20az6dNwWbAAxZ+V2l3dBRtn\ngbkdTF4Lbl0M8jkIdezrLuDsB5PXVPuUa5mFDPnyKL9cX42jKpt2+/ZWfM8Wa4sJ3BBIkGcQC/ss\nrKtVC0KNFWoKGbZxGF2du/Jd0HcAaFNTiR8yFIenn8blzQUNvEKhNtQaNcdSj7E/aT/HUo9RUl6C\nrZktA1oOIKhVEL3dev/p1GOdXsfum7tZFLmIW4W36OjYkX90/Qe93HqJIEoQBKEKEUBVIQKohnX3\nj3hYVBg3C27i3cybFwJeYKDnQIMFUTq9jj039xAeHc4N1Q3aKNswt/PcRt0QXRDup0SjY39cJhFR\naRy5mo1Gp6eVoxXBAW4EB7jh5WJrkPtkFGWw5soafr36K4XaQro6d2WG3wwGeAyo1s+PpNeT9ckn\n5C5fgd2oUbh9uBCF2Z/0VsuIgTWToCQXQpeC7yiDrF+oI4UZ8HkHGLIQer9U7dO+PxTPT1vOsGrv\nBzR//nmc/vmPise2xG/hnRPvsHzYcrq5iOliQuPyw6Uf+PrC16wasYoApwAAUufPp3D/AbwOHsDY\n3r6BVyhUR25pLoeTD7M/aT+n0k+h1WtpbtmcQI9AgloF0d21e7V3w5fry9mWsI2wqDDSitLo5tyN\nl7q+RHfX7nX8WQiCIDQdIoCqQgRQjYNOr2Nn4k7Co8NJKkjCx8GHeQHzCPQIrPW7SeX6cnYl7mJJ\n9BJuFtykvX175naey+BWg0XwJDxUVCVa9sRkEBGVxm8Jt9FL4ONqS3AXN0Z3dsPDweqB71GkLWLz\n9c2siltFqjoVP0c/vg38Fmcr5/ueK0kSOUt/IPuLL7Du04eW33yNkdWfrKkwE9ZNhtQLMOi/8OTL\n1S7tEupZzCb49RmYfRDcH7v/8XeM+e44/S/sZvhvG2m3ZzdmrVpVPDZt5zQKNAVsGbNF7CIQGp1i\nbTHDNw3Hu5k3S4fIUx9Lr14jccwYnF7+J82ff76BVyj8lXR1OgeTD7I/aT8Xsi6gl/S427gzyHMQ\ng1oNorNT5wd601Or07Lp+iaWRC8hqySLJ1o8wUtdX6oIKgVBEB5lIoCqQgRQjcvd0CgsKoxbhbfw\ndfDl+YDna1Rfr9Vr2XFjB0ujl3Kr8BbezbyZFzCvTsv7BOH/s3ffcVXW/R/HXxz2OshQBFkOMCfO\ncg/AUlFLzZmY5h5Z2bD6te67bNytuxy5Uyn3SgUXw1GaW3GCKHIYKvucAwfOvH5/UJQo405Z+n0+\nHj3i4fleF59LxXOd9/X9fr61RYa6iMi4W+w8n84ZRR4AHXzqMSTQk9C2ntR3tK7gDOUzmAzsvbmX\nj499jNxazuLgxfg7V24XqNzNm7n94UfYtGmN95IlWDg73ztIXwg7ZsCl7dBuXPEOaxZiN8paJ/JN\nOPszvK0A88otYb6lLKTrp9FsPrmA+g1c8NuwvuS1xNxEhu4cyhud3uDFVi9WVdWC8EDWXlrLl6e+\nZNUzq0pmuSimTqXo4iWaxUQjs7Gp4QqFP91Q3iBGURw6Xcq+BECzes0I8Q0hxCeEAOeAhx50FxmK\n2JywmRUXVpBTlEMvr17Mbje7pG+YIAjC40gEUKWIAKp2MpgMRNyIYGncUlLUKbR0bcnMwJn08upV\n5g2D3qhn141dLI9bTmp+Ki1cWjAtcBp9vR/ecj5BqEtScjDgrDYAACAASURBVDTsiktn57l0rt5W\nIzODbk3dGBLoyTOtG+Jk+8+b7l/JvsLs6NloDBq+7fstXTy6VOo4dVQUaXNfx9LbG58Vy+/fvNdk\ngkOfw6EvwLcHjAoHO5d/XKtQBX7oAfauMP6XSh8Sfuwmq9fsZ+HBb2n40Yc4jx5d8toXJ75gQ/wG\nokdE42Ij/qyF2qnIUETotlC8HL1Y3X81ZmZmFJw4gWL8izT88AOcx4idG2uKJElczrlMdHI00Ypo\nbihvANDWrS3BvsEE+wTjK/et4CwPh0avYd3Vdfx48UdUOhX9fPsxM3AmzZybVcv3FwRBqE1EAFWK\nCKBqN71Jz+7ru1kat5S0/DRaubZiZruZ9GzUsySI0hl17EjcwcoLK0kvSKeVayumB06nt1dvsYxD\nEP5w7Y6anefT+eVcOoocDVbmMno3r8+QQE9CWrhja/W/L0u9XXCbGVEzuKm8yUfdPuLZZs9W6riC\nEydInTkLmYMDPitXYN206f0Hxm2CX2aBvBG8sBncKjfTSqhihXnwhR/0eQf6zKv0YWErj/PUnnBC\n4g/jf+RwSc8crVFL8OZgunh04aveX1VR0YLwcGy4uoH5x+ezNGQp3Rp1Q5Ikbo4ejTEnl6Z7IjGz\nEJuaVBejycjZjLNEK4pDp1sFtzA3M6eTeyeCfYMJ8g7C3d69xupT69SEXw5n7eW1xUs4Gw9gZruZ\n1RaECYIg1AYigCpFBFB1g96kZ9f1XSyLW0Zafhpt3NowPXA66fnprLy4ktsFt2nr1pZpgdPuCqcE\nQbibJEmcT1Wy81w6u+PSyVBrsbMy5+mW7gxp50mPZvWxsqj8jEG1Ts3cg3P5/dbvzAicwYzAGZX6\n+Su6ehXF5Cmg1+O9dAm27crY+U5xHDaMBZMeRq6FJn0qXZtQRRL2w7oR8OIuaNyrUocoC/V0/tde\nNkZ/Sv0unfFa8H3Ja5E3Ipl3ZB7L+i2jq2fXqqpaEB4KnVHH4O2DcbFxYV3oOszMzFAdOEDay3No\n9M3XyAcOrOkSH2k6o47jt44TrYgmNiWWnKIcrGRWdPPsRrBvMH28+lDP5sEbwhtyc9HGJ6BNSKAo\nIR5twjUMmZk4DRqEy4QXsXB1rfS58oryWH1pNeuurkNn1DGk6RCmBU6jkUOjB65TEAShthMBVCki\ngKpb9EY9O6/vZFncMtIL0gFoV78dMwJniO1vBeF/ZDRJHE/KZtf5dCIv3EZZqKeenSUDWnswJNCT\nJxu7YC6r+GdKb9Lzr6P/4pfrvzCk6RA+6voRluYVL+/TpaSgmDQZQ2YmXt9/h0PPnvcfmJtcvENe\nVgKEfg2dJv6vlyo8TFEfwdGFxf2frCrX4P6Xc2mEf7eej4+txGvhAhxDQkpem7RvEmn5aUQOixTL\npYU6Ydu1bXx49EMWBC2gj3cfJJOJG6GDMLO1ofHWreJe5CHT6DX8mvYr0YpoDqceJl+fj72lPb0a\n9SLYN5iejXpiZ/nPNtsw6XTorl8vDpr+CJy08fEYMjNLxpg7O2MdEIDMxob8w4cxs7am3sgRuL70\nEpYNG1b6e2UVZrHywko2xW/ChInh/sOZ0mZKjc7SEgRBqGoigCpFBFB1k96oJ0oRhauNK50bdhY3\ne4LwgHQGE0euZbLzfDoHLt9BozPiLrdmUFtPhgR60tbLqdyfM0mSWBq3lEXnFvFUw6f4pu83yK3k\nFX5fQ1YWiilT0V67hudnn+I0ePD9BxapYMtLkHgAusyCpz8GsZtlzVj5DEhGmBxV6UNmrTtDxzVf\n0z3vOgFHDmNmVdxYXqFSELo9lDnt5zCl7ZSqqlgQHiq9Sc9zO57D1sKWTYM3ITOTkbdlC7feex/v\nlStw6N69pkus85RaJQdTDhKtiOZo+lG0Ri3O1s709elLsE/xkl0r88pvUCFJEob09L9CpoR4ihIS\n0CXdBKMRADNLS6z8m2HjH4B18+ZYBwRg0zwAcze3kvc/7Y0bZC9bjnLXLpDJqDd0KK5TJmPl7V3p\nWu4U3GH5heVsvbYVGTJGPTGKSa0n4Wpb+VlVgiAIdYUIoEoRAZQgCMLdNDoD0Vcy2Hk+nUPxmeiM\nJvxc7RgcWBxG+bs7lnnsruu7+ODoB/jJ/VgUvAhPB88Kv59RrSZ11mw0J07g/u47uIwfX8ZAA+z/\nPzi+BAL6w/AVYF12LUIV0BfC5z7w1PTiELAStAYjPT7Yzaqd71N/5PM0/OCDktf+e/q/rL60mgPP\nH6C+Xf2qqloQHrrdN3bzzpF3+Kr3Vzzj9wwmnY7rIf2watoE3x9/rOny6qQMTQYxihiiFdGcvH0S\no2SkoX1Dgn2Km4i3b9AeC1nFPbaMavUfM5ri/wibrqFNSMCUn18yxrJRoz9CJn9sAooDJytf30r3\n8NKlppK9YgXKrduQTCacBoXiOnVq2T0N7yNVncrSuKXsur4LK3MrXmjxAhNaTcDJ2qnS5xAEQajt\nRABVigigBEEQyqYs1LPv4m12nk/n6PUsTBI80dCRid39GNnJ+76zoo7fOs5rsa9hbWHNouBFtHRt\nWeH3MWm1pL/xJuoDB3CdOpX6r71a9oyrE8thzzyo/wSM3Qj1Kv/kWXhAN3+F1aEwZgM0H1CpQw7G\nZ7Duo0W8dnYTfhs3YBsYCBTPIum3uR9t67fl+6DvKziLINQuRpOR4TuHIyGxbcg2zGXmZK9cScaX\nX+G3ZQu2rVvVdIl1gkKlKGkifj7zPAB+cj9CfEMI8QmhpWvLMt8LJL0e3c2bdy2dK7qWgCH9VskY\nmaMj1s0DikOmgOJZTdYB/pg7ODyU+vV3MshZtYrcTZuQiopwfPpp3KZNxaZlxe97f7qpvMkP539g\nT9Ie7C3tGd9yPONajsPRSjxgEQSh7hMBVCkigBIEQaicDHURkXG32HY2jbhUJSM7efHxc62xtrh3\nKVxibiIzo2eSp83jq95f0cur4mbVktHI7X/9m7xNm3B6fjgeH31U9tPoxGjYPAEsbGDMevCq8fe1\nx8OhLyH2E3grCexcKnXIu9sv0P6bd2lnp6fZ3j0lHyajk6N59eCrLAxaSG/v3lVZtSBUif039/P6\nodf5tMenDG46GGN+Pol9g7Dv3h2v/35b0+XVSpIkkZCbQLQimihFFNdyrwHQ0rUlwT7BhPiE0KRe\nk3uOMWRk/BUy/TGrSXf9OpJeXzzIwgLrxo1Lls5ZB/hj07w5Fg0bVkubBkNODjlr15L708+Y8vOx\n790Lt+nTsWvfvtLnuJZ7jcXnFhOliMLJ2okJrSYw9omx/7i/lSA8CvQZGaj37ce6WVPsnnwSM3PR\nfqGuEQFUKSKAEgRB+N+YTBLfRiWwICaRTr7OLAnriJuD9T3jMjWZzIqeRXxuPO8++S6jnhhV4bkl\nSSJrwQKyFv+AQ0gwjb76CpmNzf0HZ1yFdSNBfRuG/gCthz/opQkVCR9a/Ps981ilhptMEgP/bzPf\nbv+Q+q/MwW3GjJLXZkTNICE3gX3D91VqWY0g1DYmycSo3aMo0Bfwy3O/YCmzJOPrb8heuZKmeyKx\n8vWt6RJrBZNkIi4zrjh0So4iNT8VM8zo4N6hZHndn8u1TQUFaBMT/1g+dw3tH8vojEplyfks3N3/\nmtX0Z+DUuHFJb7maZFSpyF23jpzVazDm5WH31FO4zZiO3VNPVToIu5x9mUXnFnE49TAuNi5MbjOZ\nkc1HYm1+7/usIDyqCi9cIGdtOKq9e+GPoNm8vhvy/gNwCh2ITWCg6AFcR4gAqhQRQAmCIPwzu86n\n8+aW87jaW7NsfEdaed7bt0Kj1/Dm4Tc5nHqYia0m8mrHVyu101lO+E/c+fRT7Dp2xOuHxZg7lrEU\noSALNo4DxTHo8y70fgvEDUnVMBrgC19oOwoGfVOpQ84qctnwysdMuLKHplFRWHkVbzt+K/8Wz2x9\nhqltpzK7/eyqrFoQqtShlEPMjpnNR10/YnjAcAyZmSQGh+A0dCge//qopsurMXqTnlO3TxGtiCZG\nEUNmYSYWMgu6eHQh2CeY3p49kWdo7moIro1PQJ+SUnIOmZ0d1v7+dzUEt/b3x7xevRq8ssoxFRSQ\nu2kzOatWYcjMxDYwENcZ03Ho3bvSH5rPZZxj4bmFHL91nAZ2DZjaZirD/IdVapdZQaiLJL0e1f79\n5Ib/ROG5c8js7XEaPgznESPQXr+BKiKC/EOHkHQ6LL29kQ8ciDx0IDYBATVdulAOEUCVIgIoQRCE\nf+5CqpKp4afI0+j5ZmQgA9p43DPGYDLw+YnP2Ri/kWf8nmF+j/mVepKrjIgg/e13sG7aFO9lS7Fs\n0OD+Aw1a2PUKnF8PbUbAkIVgWcasKeGfSz8Ly/rA8JXQ5vlKHfLFnit0eH8aTQJ8aLrup5JfX3xu\nMUvOL2Hv8L2ValQvCLWVJEmMixxHZmEmu4fuxsrcilsffIhyxw6aRUdhUf/xaa5fZCjiaPpRohXR\nHEw5iEqnwtbClhDHzoTom/FEnh1cVxTPakpMRNJqiw+UybDy87tr6Zx1QACWjRphJqv4gUVtZtJq\nUW7bRvbyFejT07Fu0QK3adNwfLpfpa/t5O2TLDy7kDMZZ2jk0IhpbacxuOlgMXNUeGQYcnPJ27iJ\n3PXrMdy5g6WvDy4vjMNp2NB7+rUZ1WrUB6JQRURQcOwYmExY+/sjHzQIeehArLy8augqhLKIAKoU\nEUAJgiA8mAx1EdPCT3NWkcerIf7MCfJHJrv7Ca8kSay5tIavT39N+wbt+a7vdzjbOFd47vxffyN1\nzhwsXF3xWbkCKx+f+w+UJPj1G4j+N3g9CaN/BocyAivhnzm2GPa9A69dBqdGlTpk4tureWvHFzT8\n+N84jxgBFDdv7r+tP02dmrKk35KqrFgQqsXR9KNMOzCNd596lzFPjEF38ybXBwzEdcoUGsx9rabL\nq1JqnZrDqYeJVkRz/OYRXG8X0jzXhq4aD5pkWWCbnIEpJ6dkvLmbGzYB/n81BG8egHXTpmUvtX5E\nSHo9yl27yV62DN3Nm1g1aYLbtKnIQ0MrtfOeJEkcTT/KgrMLuJR9CV+5LzMCZ9Dfrz/mMtETR6ib\niuITyAlfi2rXbiStFvtuXXEOCyueKViJgNaQlYVq7z5UEREUnj0LgG1gIPLQUOQD+j9WDwBqMxFA\nlSICKEEQhAdXpDfy7vYLbDuTxsA2DflqRCB2VvfeVO+7uY93j7yLh4MHi4MX4yMvI1D6m8K4OFKm\nTgNzc3yWLyt/d6FLO2D7dLCvX7xDnnvldyISKrBxHNw6D69eqNTw65n5bBn/KoNSTvDEsd9KllEe\nST3CzOiZfNPnG/r59qvKigWhWkiSxMR9E1GoFEQOi8TGwobUV16l4OhRmsXGPLQd12qLrIJMfju9\nnfiT+ymKj8crw0jjLBnu2SbM/ri/N7O2Ll4+9+fSuYDi/yxcXWu4+polGY2o9+0ja+kytPHxWHp5\n4Tp5Mk7DhiKrRA8rSZI4mHKQhecWkpCbQLN6zZjVbhbBPsGiH45QJ0hGI/kHD5KzNhzN8eOY2djg\nNGQILmHjsPb3/8fn1aeloYyMRBURifbqVZDJsO/yFPLQUBz79cNcLn+IVyH8L0QAVYoIoARBEB4O\nSZJYfuQGn+25SksPOcvGd6JRPdt7xp3NOMucmDmYYcb3Qd/TrkG7Cs+tvXEDxeTJmJQqvBYvxv6p\nJ8senHYG1o8BXQGM+BH8RcjxwCQJvmwGzUJg2NJKHbI0+iqBr43DrWc3mi36vuTXX419lbMZZ4l6\nPkr0MhEeGadun2Livom80ekNXmz1IoUXLnJzxAgavPkmrpNequny/jFjXh5FCQlkxJ0k5fyv6BKu\n4ZpegM0fm89JZoCnO44t2hQ3Bf9jVpOVj4/YraockiSRH3uQrCVLKIqLw8LdHdeXJlJv5Ehktve+\nb5ZmkkzsT97P4nOLSVIm0cKlBbPbz6Zno54iiBJqJaNaTd7WreT+vA59SgoWHh44jx2D84gRD72v\nmzYxEWVEBKqISPQKBWaWltj36oXToFAc+vSp1M+Y8PCIAKoUEUAJgiA8XLFXM5iz/izWljKWhnWk\no6/LPWOSVcnMiJpBhiaDz3p+VqmZMPrbt1FMnow+WYHn118hf/rpsgcr02D9KLhzCZ75DJ6aJpqT\nP4isa7CwEwz+DjpOqNQh776xiLDdC/Fa8gOOffoUn6Ywi36b+xHWMoy5neZWXb2CUAOm7p/K1Zyr\n7B2+FztLO5InTER34wZNow5UanZLTZJ0OrRJSSW7zhXFJ1Bw9TJkZpeMUdtApqcdVgH+eLfrgU+7\nHtj4+yOzt6/Byus2SZLQHDtG1g9L0Jw8ibmLCy4vvojzC2MrNXPOaDISmRTJ4nOLSc1PpW39trzc\n/mWealj5XfcEoSppk5LI/elnlNu3Y9JosO3QAZfxYTiGhFRq+emDkCSJoosXUe2OQBUZiSEzE5md\nHQ7BwchDB+LQvTtmluJBWFUTAVQpIoASBEF4+BIz1Exec4r0vCLmD23NiE7e94zJKcphTswc4jLj\neL3T64xvOb7CG2ZjXh4p02dQGBdHww8/xHnUyLIHa/Nh21SIj4BOk2DAFyBm3Pwzp9fArjkw6yTU\nr3i3mQxVETuee5GnVMm0PXak5AZvxYUVfHfmO3Y9tws/J78qLloQqldcZhwvRL7AnPZzmNJ2Cvm/\n/kbK5Ml4zP+EesOH13R5QPEHMsOtWyW7zv25C5026SYYDACYLGTcrm/BNVc9ivpmWPg3oXmnp+kZ\n+Cw+ThUvmxb+Gc3p02QtWUrBkSPI5HJcxr2Ac1gYFs4V90vUm/T8kvgLS+OWcrvgNp0bdmZ2u9l0\ncO9QDZULwt0kSaLgt6PkhK+l4NBhsLTEaeAAnMPGY9u6Vc3UZDSiOXkKVUQEqv37MSmVmDs54di/\nP/LQgdh16lTnNz2orUQAVYoIoARBEKpGnkbH7HVn+TUxi0k9GvPOgCewML/7zb3IUMS7v77LgeQD\njHliDPM6z6uwoaqpsJDUV1+l4NBh6r8yB9fp08sOrkwmiP4IfvsOmvSFEavBtvZv4V3rbJ8O1w7A\nm4mVmkm2MeYSLWaPwnLo87SY/xFQvGRk0PZBuNu582P/H6u4YEGoGS9Hv8zpjNPsHb4XR0tHkoYP\nRyosoknE7mr/cGPMz0ebcK04YPpjVpM2IQGTWl0yxsLDgyI/d264GTlqm0acXEmGqzkdGj1JiE8I\nfX360sBObOhQnQovXiJ76VLUBw5gZmeH8+jRuE6cUKmGyjqjji0JW1h+YTlZhVl09+zO7Pazae3W\nuhoqFx53Jo0G5c6d5IT/hO76dcxdXXEePRrn0aNqVUNwSacj/9ffUEVEoI6JQSosxMLdHfmAAcgH\nDcKmVUsxg/AhEgFUKSKAEgRBqDoGo4lPIq6w+uhNegXUZ8GY9jjZ3j0LySSZ+ObUN6y5vIY+3n34\noucX2FnalXteSa/n1nvvofxlJ87jxuH+7jvlf7g7Ew67XwWXpsXNyV0aP4zLe3z8ty00bFO8u2Bl\nhr/yBc/sW43fls3Yti7+4HP81nEm75/MZz0/Y1CTQVVZrSDUmKs5VxmxawTTA6czq90slBERpL/+\nBl4LF+AYElIl31MyGNDdvHlXyKSNj0efnl4yRubgUNKfyaJZU6656oixuMb+rN/I1eZibW5NN89u\nhPiG0NurN07WTlVSq1B52mvXyFq2HFVEBGYWFtR7/nlcJ0/C0tOzwmMLDYVsvLqRVRdXkavNpY93\nH2a3m01zl+bVULnwuNGnpZGzbh15m7dgUqmwadkS5/FhyAcOrPXLj00aDerYWFQRkeQfOQJ6PVa+\nvsU76Q0KxbpJk5ousc4TAVQpIoASBEGoeutPKPjgl4t4u9ixYnwnmtS/t7fF+qvr+fzE57RwacHC\n4IW42bqVe07JZCLjP1+Ss3o18oED8fz8M8zKu9FJOgKbwgCz4iDFt9sDXtVjQpUO37SAZz6FrrMq\nHJ6vNbAvaAheFnqePLi/5CniW4fe4rf034gZGYO1uXVVVy0INWbuwbkcTT/KnmF7qGfhyPX+A7Bw\ndcV3w/oHeqouSRKGzMy/LZ1LoCghAd3160g6XfEgc3OsmzTG2v+vhuA2AQFo6zvxa/qvxCTHcDjt\nMAX6AhwsHejl1YsQ3xC6e3avMPgXaoYuOZnsFSvI2/ELSBJOzw7BbcoUrPz8Kjy2QF/Az1d+ZvXF\n1aj1ap7xe4aZgTNpUk98qBYejCRJFJ4+Tc7acNRRUWBmhmO/friMD8O2ffs6OYPIqFSi2r8fVUQk\nmuPHQZKwbtECp0GhyAcOxNLDo6ZLrJNEAFWKCKAEQRCqx/Eb2cz4+QwGo4mFYzvQK+De6dgHUw7y\n1uG3cLFxYXHw4gpvkiVJImflSjK++hr77t3x+v678hviZl+HdSMhNxmGLIB2Yx70sh59F7bA1kkw\nJRYaVdxPZN/+U/jMCaNowjTav/0qAHlFeQRtDmJk85G8/eTbVV2xINSo63nXGfrLUCa0nsDcjnPJ\nWbeOO//+GN/wtdh17lypc5g0GrSJiffMajLm5ZWMsWjQ4K6Qybp5c6yaNCmZcZBXlEdsSiwxihiO\nph9FZ9LhYuNCX+++hPiG8GTDJ7Eyr92zE4S/6G/dInvlKvI2b0bS65H374/rtGnYNK+4L59Sq2Tt\n5bX8dPknioxFhDYOZUbgDLzl9/ZnFITymHQ6VBGR5ISvRXv5CjInJ5xHjsB5zJhKzc6rK/QZGaj3\n7kW5O4KiuDgAbDt2RB46EHn//li43LvBjnB/IoAqRQRQgiAI1SclR8OUtadIuKPmvdCWTOzud89T\nsktZl5gVPQudScd3fb+jc8OKP7Dlbd3Grfffx6Z1a7yXLim/aWthLmwaD0mHocdcCHofROPJskW8\nDuc3wLxkMK94x5q109+j48FtNIk6gK1XIwDCL4fzn5P/YeuQrQQ4V/xhSRDqurePvE10cjR7hu/B\nxcyBxKBgbNq0xmfp0rvGSUYj+pSUv0KmhHiKEhLQK1Lgj3tlM1tbrAP8i0OmgObFoVOA/33/nbtd\ncJsYRQwxihhO3TmFUTLiYe9BsE8wIb4htKvfrsI+e0LtZsjKImf1anLXrcek0eAQHIzb9GnYtmlT\n4bG5Rbn8ePFH1l9dj96k57lmzzGt7TQ8HMTMDqF8hsxMctdvIHfjRozZ2Vg1a4pL2HichgxGZmtb\n0+VVKZ1CgSoyEuXu3egSr4O5OfbduiEPHYhjSEildqx8nIkAqhQRQAmCIFSvAq2B1zaeY//lO4zq\n5M2/n2uFtcXdH4jS8tOYGTUThVrBx90/rlTPIHVMDGmvzcXS0xOflSvKfxJn1BcHK2fWQIvBMHQZ\nWInlJ/e1uBs4NIDxOyocqjMY+a1LH0wN3AmO3AIUz1Ib+stQ7C3t+Tm0cj2kBKGuS1Yl8+yOZ4s3\nV3hyHpmLF5P1/QI8v/gco1JJUXx8cYPwa9eQioqKDzIzw8rXt2RWk3VAADbNm2Pp5VVuj7tkVTJR\nyVHEKGKIyyp+Ut/EqUlJ6NTCpUWdXA4jlM+Yl0dO+E/khIdjUqmw794dt+nTKjXLLlOTyYoLK9ic\nsBmA5wOeZ0qbKdS3qz2NooXaofDCRXLC16LasxcMBhx698ZlfBh2Xbs+dv+uSJKENiEB1e4IVJGR\n6NPSMLO2xqF3b+SDQnHo3RuZtWgxUJoIoEoRAZQgCEL1M5kkvo1KYEFMIp18nVkS1hE3h7vftJVa\nJa8dfI2Tt08yu91spradWuHNjubUKVJmzERmZ4fPiuVY+/uXPViS4PfFsO//wCMQxmwAuXgKfJfC\nXPiiMfR9F3q/VeHw33fG4vTWTHJefpvus14E4FzGOcL2hPGvbv9imP+wqq5YEGqND49+yK7ru4gc\nFkl9vQ3XgoKRNBoAzF1c/lo69+espmZNKzWTQJIk4nPjiUqOIloRTWJeIgCtXFsR4htCkE8QTZxE\nj5/HhTE/n9z168lZvQZjdja2nTriNm069j26V/ieeSv/FssuLGPHtR2Yy8wZ88QYJraeiIuNWF70\nOJP0etRRUeSsWUvhuXPI7O1xGjYMl3EvYOXrW9Pl1QqSJFF47hyqiEhUe/dizMpC5uCAY0gI8tBQ\n7Lt2wcyi4lnjjwMRQJUiAihBEISas+t8Om9uOY+rvTXLxneklefdOy/pjDo+PPohu2/sZpj/MN7r\n8h6WMssyzlasKD6elMlTMOl0eC/5Abv27csvIn4PbJkENk4wdkNxGCUUi98L60fBi7uhcc8Kh++c\nMAefkwfx//VX7J3lALz363scSD5A7MhY0eRYeKyk56cTuj2Uoc2G8kHXDyi8dAljXh42zZtj4Vb+\nJgulmSQT5zPPl4ROaflpyMxkdGjQoTh08g4Sy6gec6bCQvI2byF71SoMt29j07o1btOn4RAUVP4u\nsUCKKoUlcUvYfWM3NuY2vNDiBV5s9aLYDfExY8jNJW/zFnLXrcNw+zaWPj64jHsBp2HDxDKzckgG\nAwXHj6OKiER94AAmtRpzFxfk/fsjHxSKbbt2Ff4MPspEAFWKCKAEQRBq1oVUJVPDT5Gn0fPtqED6\nt777Q5QkSSw8t5Blccvo5tmNr3t/jYNV+TdCutRUFJMmYbiTgdd3/8Whd+/yi7h9AdaNhsIcGLYc\nWlS85O+xcOADOLYY3kkBy/JnZhi1Ws507kaKfzuGbV0JgFqnJmhTEIOaDuLDrh9WR8WCUKt88vsn\nbE3Yyq6hu/By9PqfjtUb9Zy8fZIoRRSxKbFkFWZhKbOki0cXQnxD6OPdR8xUEe5h0ulQ7thB9vIV\n6FNSsPb3x3XaNOQD+mNmXn7/rxvKG/xw7gf23tyLo6UjL7Z6kXEtx2FvWc7mHkKdV5SQQG54OMqd\nu5C0Wuy6dsElbDwOvXtV+HdGuJtJq6XgyBGUuyPIj41F0mqx8PTAaeBA5KGhWD/xxGO3dFEEUKWI\nAEoQBKHmZaiLmBZ+mrOKPF4LCWBOcLN73qC3X9vOwU0LTwAAIABJREFUv4/9myb1mrAoeBEN7RuW\ne05DdjYpU6ZSFB+P56fzcXr22fKLUN+BDWMg7Qz0+xd0mwOP2U3CPVb0K/7/5AMVDr24fgfm/3qH\nm/M+ZcDEoQBsvLqRT45/wobQDbRya1WVlQpCrZShyWDgtoH09+vPJz0+qXB8oaGQo2lHiVJEcSjl\nEGq9GlsLW3o26kmIbwg9G/WsMIAXBCielaHas4esJUvRXb+Ola8vrlOn4DR4MGZW5e9+GJ8Tz6Jz\ni4hNiaWedT0mtZ7EqCdGYWvxaDebfpxIRiP5hw6RszYcze+/Y2ZtjdOQITiHjcMmQGwW8jAY8wvI\nj4lGGRFBwW9HwWDAqmlT5KEDcQoNfWyWM4oAqhQRQAmCINQORXoj726/wLYzaYS28eDLEW2xs7p7\n/fzRtKPMPTQXe0t7FgcvprlL83LPaczPJ3X2y2h+/50G8+bhOnFC+UXoC2HHDLi0HdqPg9BvweIx\n3aZcXwifeUPXmdDv3xUOjx3xIpbXrtLyUCwuTsVL7UbuGomExKZBmx67J36C8KcvT37JT1d+Ysez\nO2js1Pie11U6FYdSDhGtiOa3tN8oMhbhZO1EH68+hPiG0MWjCzYWNjVQufAokEwm1FFRZC1Zgvby\nFSw8PXCdNIl6w4cjsyn/79XFrIssPLeQ39J+w83WjcltJjMiYARW5o/p++IjwJifj3LrVnJ++hl9\nSgoWDRviPHYs9UY8X/4OwsIDMeTmot63H9Xu3Wj+yB5sWrdGPigU+YCBWLo3qOEKq44IoEoRAZQg\nCELtIUkSy4/c4LM9V2npIWfZ+E40qnf3E9f4nHhmRs+kQF/A172/pnuj7uWe06TTkf7mW6j37cN1\nymTqz51bfhhiMsGhz+HQF+DbA0aFg91juMwl6QisGQRjNkLz/uUONeTmcqV7T060D2HSz/8F4HL2\nZUbtHsX/PfV/jH5idHVULAi1UnZhNgO2DaCPdx/+0+s/AGQVZhGjiCFaEc2JWycwSAYa2DUgyDuI\nEN8QOrp3xEImGtgKD48kSRQcOULWD0soPHsW8/puuE6YiPPoUcjsy19id+bOGRacXcCpO6doaN+Q\nqW2n8lyz5yrsySjUHrqbN8n56WeU27Zh0miwbd8el/FhOIaEYGYp/hyrk/72bVSRe1BFRFB06RKY\nmWHXuTPy0FDkzzyNeb16NV3iQyUCqFJEACUIglD7xF7NYM76s1hbylga1pGOvncHQHcK7jArehaJ\neYl80PWDCndXk4xGbn/8MXkbNuI0fBge//pXxbuTxG2CX2aBkxeM3QRu5eyo9yg69B+I/RTmJYFt\n+U9FE5f9iP6b/3Duw0WMGRMEwMfHPmbn9Z1Ej4xGbiWvjooFodb67sx3rLywkiltp3Dy9knOZZxD\nQsLH0Ydg32BCfEJo7dYamdnj26hWqB6SJKE5cZLspUsoOHoMcycnnF8cj8u4cZjLy/63WpIkjt8+\nzoKzC4jLjMPLwYsZ7WYQ2jgUc5noE1QbSZJEwdGj5K4NJ//wYbCwQD6gPy5h47Ft07qmyxMAbVJS\n8U56ERHokpLA0hKH7t2Rh4biGNS3wnC4LhABVCkigBIEQaidEjPUTF5zivS8IuYPbc2ITt53vV6g\nL+D1Q6/zW9pvTGkzhZfbv1zuzCZJkshauIisRYtwCAqi0TdfV7j8AMVx2DAWTHoYuRaa9HnwC6sr\n1j4H+Rkw82iFQ08MeI6MbDWBe3fh7WKHRq8haHMQwT7BzO8xvxqKFYTaTalVMmDrANR6NU+4PEGQ\nTxAhPiE0q3dvvztBqC6F58+TtWQp+bGxyOztcX7hBVwmvIiFS9mzfiVJ4kjaERaeXciVnCs0dmrM\nzMCZPO33tAhQawlTYSHKX3aS81M4usTrmLu64jxqFPVGj8KywaO71KsukyQJ7ZUrKHdHoIqMxHD7\nNma2tjj27YM8NBT7nj2RVdC7rbYSAVQpIoASBEGovfI0OmavO8uviVlM7tGYdwa2wFz214c1vUnP\n/N/ns/XaVgY2HsjH3T+usDdFzs8/c+eT+dh27ID34sXlPvEFIDcZ1o2C7GsQ+jV0nPAQrqyWMxrg\nC18IHF18zeXQ3kjixsCB/NL1ed7+8WOguGH8B0c/YE3/NXRw71AdFQtCradQKTAzM8Pb0bviwYJQ\njYquXiVr6VLUe/dhZm2N86iRuLz0Epbu7mUeI0kSMYoYFp5bSGJeIgHOAcxqN4u+3n1FqFpD9Onp\n5K5bR+7mLZiUSqxbtsAlbDzy0IF1Nrx4HEkmE4VnzqCMiEC9dx/G3FxkcjmOT/fDKTQUuyefrFO7\nE4oAqhQRQAmCINRuBqOJTyKusProTXoH1Of7Me1xsv2rX4EkSay8uJLvznxHR/eOfNf3O5ysnco9\np2rPHtLemod148Z4r1he8RPBIhVsmQiJUdB1dnFT7kd5yUHaGVjeF4avhDbPlzs0+ctvUK9cwaFP\nVjHr+S4AjIsch1qnZsezO8QHEUEQhDpCe+MG2cuWo9y1CzOZDKehQ3GdMhkr77JDU6PJyL6b+1h8\nfjHJqmRaubZidvvZdPfsLv79rwaSJFF45gw5a8NRR0WBJOEYEoLL+DBsO3YUfwZ1nKTXU/D776h2\n70Z9IAqTRoN5fTfkAwbgFBqKTdu2tf7PWARQpYgAShAEoW5Yf0LB+zsu4uNqx4rxnWhS/+6tyCNu\nRPD+b+/j5ejF4uDFeDl6lXu+gqNHSZn9MhbOzvisXIGVn1/5BRgNsO9dOLEUAvrD8BVg7fiAV1VL\nHVtUfK1zr4Dcs8xhkslEXK8g4mT1aL9+Da0bOZGYm8jQnUN5o9MbvNjqxWosWhAEQXgYdKmpZK9Y\ngXLrNiSTCadBobhOnYp106ZlHmMwGdh9YzdLzi8hLT+N9g3a83L7l+ncsHM1Vv74MOl0qCIjyV0b\nTtHly8jkcuqNeB6XsWOxbNSopssTqoCpqIj8g4dQRUSQf+gQkk6Hpbc38oEDcRoUirV/7exVKgKo\nUkQAJQiCUHccv5HNjJ/PYDCaWDi2A70C6t/1+qnbp3gl9hUsZBYsCl5Ea7fym2wWXrhIytSpYGaG\n9/Jl2LZqVXERJ5bDnnnQoAWM2QD1HsHlNBtegNsX4NW4codpTp4kOWw8y3pN4Julb2FmZsYXJ75g\nY/xGokdE42wjtnQWBEGoq/R3MshZtYrcTZuQiopwfPpp3KZPw6ZFi7KPMerZnridpXFLydBk8FTD\np5jdfjbtGrSrxsofXYbMTHI3bCR340aMWVlYNW2KS1gYTkMGI7Ozq+nyHgqNXkOyKpkkZRI3VTdJ\nVafS3KU5QT5BYgnzH4xqNeoDUagiIig4dgxMJqwDAop30gsdiJVX+Q9hq5MIoEoRAZQgCELdkpKj\nYcraUyTcUfNeaEsmdve7a/rxDeUNZkbNJLswmy96fUGQT1C559MmJZEyaTJGpRKvRQux79Kl4iIS\no2DzRLCwgTHrwavG31cfHkmCL5uBfz8YuqTcoSnv/B+ZuyKI+GgV7z/fAa1RS/DmYLp6dOXL3l9W\nU8GCIAhCVTLk5JCzdi25P/2MKT8fh969cZ0+Dbv27cs8RmvUsjl+M8svLCenKIeejXoyu/1sWrq2\nrMbKHx2FFy+RG74WZeQe0Otx6N0b5/Fh2HfrVuuXYN2PJElkaDJIUiVxU3mTJGVSSeB0q+BWyTiZ\nmQwXGxeyCrMA8Hf2J9gnmCDvIJ5weaJOXvvDZsjKQrV3H6qICArPngXANjCwOIwa0B+L+vUrOEPV\nEgFUKSKAEgRBqHsKtAZe23iO/ZfvMKqTNx8/1xori79238kqzOLl6Je5lH2JeU/O44UWL5R7Pv2d\nO6RMnoLu5k08v/wSef9nKi4i4yqsGwn5d+C5H6D1sAe9rNohMwEWdYYhC6DD+DKHmYqKuNKtB1Fu\nLei8+Fu6NXMj8kYk847MY1m/ZXT17FqNRQuCIAhVzahSkbtuHTmr12DMy8OuSxfcpk/D7qmnygwC\nNHoN66+uZ9XFVah0KkJ8QpjZbib+zrVzuVBtIhkMqKOiyFkbTuGZM8js7HAaNgyXcS9U3DagltAa\ntX/NZlLeJEmVVPK1xqApGWdvaY+f3I/GTo1p7NS45GsfuQ/W5takqFOIVcQSrYjmXOY5TJIJT3tP\ngnyCCPIJon2D9ljILGrwSmsHfVoayshIVBGRaK9eBZkM+y5PIQ8NxbFfv4o33qkCIoAqRQRQgiAI\ndZPJJPFtVAILYhLp7OfMD+M64uZgXfK6Rq/h7SNvE5sSS1jLMN7o9Ea5W0QblUpSZsyk8OxZGn74\nAc6jR1dcREEWbBwHimPQ9/+g15tQ15/GnV4Nu16B2afBrVmZw1SRkaTNfZ2P+85izcKZWJrLmLRv\nEmn5aUQOixTbcQuCIDyiTAUF5G7aTM6qVRgyM7Ft1w7X6dNw6N27zCBKrVPz0+WfWHt5LQX6Avo3\n7s/MwJn4OflVb/F1gCE3l7zNW8hdtw7D7dtYenvjMu4FnIYNw9yx9vWelCSJ7KLsu2Yx/fl1en46\nEn997vew97gnZGrs1Jj6tvUrPZspuzCbw6mHiVZEcyz9GDqTjnrW9ejt1Ztgn2C6enbFxsKmqi63\nztAmJqKMiEAVEYleocDM0hL73r1wCg3FoU8fZLa21VKHCKBKEQGUIAhC3bbrfDpvbjmPq701y8d3\noqXnX093jCYjX576kp+v/EyITwif9fys3JsSU2Ehaa++Rv6hQ7i9PBu3mTMrviEyaGHnHIjbAG1G\nwJCFYFmHb3y2TYPr0fDGtXLDtORp01GcPM/2NxfxzZgOKFQKQreHMqf9HKa0nVKNBQuCIAg1waTV\noty2jezlK9Cnp2PdogVu06bh+HQ/zGT3fwih1CpZfWk1P1/5Ga1Ry+Amg5keOL3CjUMeB9pr18hZ\nG45y1y6koiLsunTBZXxYcbBnXvM77+qNelLUKcXh0t9mMiWpklDr1CXjbMxt8HPyo7H8j6DJ6Y/Z\nTI4+2Fk+3D5VGr2GX9N+JSYlhsMph1Hr1dha2NLNsxvBPsH08upV4c7IjzpJkii6eBHV7ghUkZEY\nMjOR2dnhEByM06DQ4mWclpYVn+gfEgFUKSKAEgRBqPsupCqZsvYUykI9344KpH9rj7teD78czpcn\nv6RN/TYsCFqAi41LmeeS9Hpuvf8Byh07cB47Fvf/e7fiGz9JgiNfQ8zH4PUkjF4HDjW75v4f+28b\n8GgHo8LLHGLIyiKhVx82Ne1Nl8/eo39rD749/S1rLq3hwPMHqG9XR69dEARB+J9Jej3KXbvJXrYM\n3c2bWDVpgtu0qchDQzGzuP+yqOzCbFZeXMnGqxsxSSaG+Q9jStspNLRvWM3V1yzJZCL/4CFywtei\nOfY7ZtbWOA0ZjPO4MGyaB9RITXlFeXcHTH8ETqnqVIySsWRcA9sGdwVMfwZO7vbuNTILWm/Uc/LO\nSWIUMcQqYskozMDczJxO7p1Kluo9bn+/SpOMRjQnT6GKiEC1fz8mpRLzevVwfOYZ5KEDsevUqczw\n+J8SAVQpIoASBEF4NGSoipgafppzKXm8FhLAnOBmd81eik6OZt6ReTSwa8Di4MXlTvuXJImML78i\nZ9UqHAf0x/OLL5BZWVVcxKUdsH16cfg0ZiO417Fmq8o0+LYl9P8cuswoc1jOmjXc+exzZj/9Fju/\nDMPKUqLf5n60rd+W74O+r8aCBUEQhNpCMhpR79tH1tJlaOPjsfTywnXKFJyGPlfme+idgjssv7Cc\nrde2IkPGyOYjmdRmEm62btVcffUy5uej3LaNnJ9+Rq9QYOHujvPYsdQbOQIL56rfQdZgMpCWn3bf\nZXN52ryScVYyK3zkPnctm2vi1ARfuS8OVg5VXuc/ZZJMXMq6RExKDNGKaJKUSQC0cm1FkE8QwT7B\nNHFq8lg3MZd0OvJ//Q1VRATqmBikwkIs3N2RDxyIPDQUm1YtH8rvjwigShEBlCAIwqOjSG/k3e0X\n2HYmjdA2Hnw1IhBbq79mL8VlxvFyzMsYJSPf9/2eDu4dyj1f9sqVZHz5FfbdutLo+wWYO9hXXETa\nGVg/BnQFMOLH4t3k6ooLW2DrJJh6CDzL3jL7xrDhxN/JZ8uUT1g5oTPRydG8evBVFgUvopdXr2os\nWBAEQahtJEkiP/YgWUuWUBQXh4W7O66TXqLeiBFl9p1Jy09j6fml7Ly+EytzK8Y8MYaJrSZSz6Ze\nNVdftXTJyeT89DPKbdswFRRg264dLuPDcOzXr0qWQal0qpJZTH8PmRRqBQaToWScq43rXTOZ/vza\n094Tc1nNL/97UDeUN4hVxBKjiCEuKw4AX7kvQd7FM6Pa1m/7WPeuNGk0qGNjUUVEkn/kCOj1WPn6\nFu+kNygU6yZN/vG5RQBVigigBEEQHi2SJLH8yA0+23OVlh5ylo/vhGe9v254U1QpzIyeSXp+OvN7\nzKd/4/7lni9v23Zuvf8+Ni1a4L1sKRYuZS/fK6FMg/Wj4M6l4tlET06tG83Jd8+FuE3wdjKUccOp\nvXaNG4OH8EObZ+n+1kxGdfZhRtQMEnIT2D98/yNxoyoIgiA8OEmS0Bw7RtYPS9CcPIm5iwsuEybg\nPHYM5g73nz2TrErmh/M/EHkjEjtLO8JahjG+5XgcrWpf8+3K+vP3IWdtOPmHDoGFBfL+/XEZH4Zt\nmzYPfH6jycitglv3nc2UXZRdMs7CzAJvuXfJUrk/l8/5yf0eqz5JGZqM4jAqJYYTt05gkAy42brR\n17svQT5BPNnwSazMKzHr/RFlVCpR7d+PKiISzfHjIElYt2yBU2go8oEDsfTwqPgkfyMCqFJEACUI\ngvBoir2awZz1Z7G2NGdpWEc6+v41pT2vKI9XYl/hTMYZXu3wKi+1fqncacbqmFjSXnsNSw8PfFau\nwLJRo4oL0ObDtikQHwmdJ0P/L8C8lm8RvLgrOHpA2LYyh2R8/TWZK1fxQv/3ifr3UPTk8MzWZ5ja\ndiqz28+uxmIFQRCEukJz+jRZS5ZScOQIMrkcl3Ev4BwWVuZys8TcRBafX8yB5APIreRMbD2RsU+M\nfehNrKuSqbAQ5c5d5P4UjvZaIuYuLjiPHkW90aOxbNDgfz6fRq8p6c309wbgycpkdCZdyTgna6e7\nQ6Y/dptr5NgIS1nVNZuui1Q6FUdSjxCjiOHXtF/RGDTYW9rTq1EvgnyC6NGoR61ealjV9BkZqPfu\nRbk7gqK44pljth074jQoFMdnnqnUQ1kRQJUiAihBEIRHV2KGmslrTpGeV8T8oa0Z0cm75DWtUct7\nv77H3pt7GRkwkneeegcLWdkBkeb0aVJmzERmY4P3iuXYBFSiOajJCFEfwdHvoWkQPP8j2NbS5QSa\nHPhPYwh6D3q9ed8hktFIYlAw523c2fDcK2yZ0Y3F5xaz5PwS9g7fi6eDZzUXLQiCINQlhRcvkb10\nKeoDBzCzs8N59GhcJ07Aov79N6+4kn2FRecWcSj1EC42LrzU+iVGNR9V7o62NU1/6xa569aRt2kz\nRqUS6xYtcAkLQx46EJm1dbnHmiQTGZoMbihv3BUyJSmTyNBklIyTmcnwdvQuCZf+HjQ521R9D6lH\nkdao5fit48VNzFNiySnKwVJmyVMeTxHkE0Rf776PfG+y8ugUClSRkagiItBeSwRzc+y7dUMeOhDH\nkJAyZzWKAKoUEUAJgiA82vI0OmatO8NvidlM7tGYdwa2wFxWPNvJJJn47sx3rLq4ip6NevJV76/K\nfbpaFJ9AypQpmIqK8F7yA3Ydyu8hVeLMWtj9Grg0hbEbwaXxw7i0hyt+D6wfDRMiwa/7fYcUHDuG\nYuJLfNp5HD2njGZSDz/6b+tPU6emLOm3pJoLFgRBEOoq7bVrZC1bjioiAjMLC+o9/zyukydh6Xn/\nBxnnM8+z8OxCfr/1O/Vt6zO17VSG+Q+rNUulJEmi8OxZctaGoz5wACQJx+Dg4mV2nTrdM8u60FCI\nQqUomc2UpCoOm26qblJoKCwZ52DpUBIw/T1k8nb0rjXX/igymoyczzxPjKK4iXlqfipmmBFYP7Ck\nibmP3Kemy6wxRfEJxTvpRUSgT0vDzNoahz59kIcOxKF377uCVhFAlSICKEEQhEef3mhifsQVVh+9\nSe+A+nw/pj1Otn9NQ98Uv4n5x+fT3Lk5C4MX0sCu7KnxutQ0UiZNQn/nDo3++y2OffpUroikI7Ap\nDDCD0evAt+uDXdTDtv99OL4E3k4By/s/WU6f9zbZ+6MYHvIe++b1I6XoNLOiZ/FNn2/o51uHmq0L\ngiAItYIuOZms5ctR/rITJAmnZ4fgNmUKVn5+9x1/8vZJFp5dyJmMM3jaezI9cDqDmw4udwZzVTLp\ndKj37CFnbThFly4hk8up9/zzOI8di2UjTzILM0uagP8ZMiUpk0gvSC85hxlmeDp4Fjf+/tvSucZO\njXG1cX2sd2qrDSRJ4lreNaIV0cQqYrmScwWAZvWaEeRT3MS8pcvD2TGurpEkicJz51BFRKLauxdj\nVhYyBwccQ0KQh4Zi37ULMktLEUD9nQigBEEQHh/rTyh4f8dFfFztWPliZxq7/bWr3eHUw7xx6A2c\nrJ1YHLwYf2f/Ms9jyM4mZeo0iq5exWP+J9R77rnKFZB9HdaNhDwFDP4e2o150Et6eJYHg8wCJu27\n78smjYaEHj053aQTa7qPZf9rvXkl5hXOZZ4j6vkoLM1FXwlBEAThn9HfukX2ylXkbd6MpNcjHzAA\n12lT77vcXZIkjqUfY+G5hVzIuoCPow8z2s1ggN+AatsIw5CVRe6GjeRu2IAxKwt8vcgd3JXLT7pz\nXZtasnSuQF9Qcoythe1ds5j+/NpX7lurlxQKd0vPTydGEUNMSgyn75zGJJloaN+wZEe9Du4dHste\nW5LBQMHx46giIlEfOIBJrcbc1ZXmR38TAdTfiQBKEATh8XL8RjYzfj6DwWhi0Qsd6On/V9+JK9lX\nmBU9i0JDId/2/ZYuHl3KPI8xv4DUl2ejOfY7Dd58E9dJL1WuAE0ObBoPN49Az9eh73sgq+Gtf3UF\n8LkPdHsZQj667xDlzp2kvzWPeb1m0XN4CBN7uRGyOYTxrcYzt+Pcai1XEARBeDQZsrLIWb2a3HXr\nMWk0OIQE4zZtOrZtWt8zVpIkDqUeYuHZhcTnxtPUqSmz2s8i2CcYmdnDfV+VJImcohyST8WiXbcV\nxyNxmBtMXAmwZXsHPef9JKQ/ZsA0tG94395M7nbuj+UsmUdZblEuh1IPEaOI4Wj6UbRGLXIrOX28\n+xDkHUS3Rt2wtbCt+ESPGJNWS8GRIygjIvD+739FAPV3IoASBEF4/KTkaJiy9hTXMvJ5L7QFE7r5\nldwU3sq/xczomdxU3uSjbh/xbLNnyzyPSacjfd481Hv24jLpJRq88Ublbi6Neoh4Hc6sgRZDYOhS\nsKrBnX1uHIK1Q2DsZgh4+r5DFJMmk5twnee6zWXH7J6czNvCd2e+Y/fQ3fjKfau5YEEQBOFRZszL\nIyf8J3LCwzGpVNj36IHb9GnYdbr3c6xJMnEg+QCLzi0iSZnEEy5PMLvdbHp59fqfAx+9SU+KOuWv\nZXPKJJJzk3A+nkCf3/NpkQpFlnAk0ILLffxw8G9eHDTJG+Pn5Ief3K9O7dQnPDwavYZj6ceISYnh\nYMpBVDoVNuY2dPXsSpBPEH28+lDPppZuRFOFRA+oUkQAJQiC8Hgq0Bp4beM59l++w6hO3nz8XGus\nLIqfmKp1auYenMvvt35nZuBMpgdOL/MmVjIauTN/Prnr1uM0dCgeH/8bM4tK9KKQJDi2CPa/B57t\nYPR6kHs8zEusvIOfF/837+Z9d+nT38kgsW9fjncbwpImIfw6rw9DfhmMu507P/b/sfrrFQRBEB4L\nxvx8ctevJ2f1GozZ2dh26ojb9BnYd+92z/uy0WQkMimSH87/QIo6hbZubZnVfhZdPbreM1apVd7V\nAPzPHedS1akYJAMA9oUSz16yI+ikFnmeDm0DJ4zDnsF91Fg8G/o/9FlWwqNDb9Jz5s4ZohXRxChi\nuKO5g8xMRkf3jiVL9R6XnYNFAFWKCKAEQRAeX//f3n2HR1Xlfxx/n3QSSEiA0BKaNJFeAiKLhKwK\ngmBFaWJBFFFX94euLrqru7qsouiKUgRlQcCGUlwEwYAuIkqR3gwiJHQCJEBISDu/P+bCBpLABGaY\nAJ/X85xn7txyyujhZr5zzrn5+ZY3v/mFUQu30qZWJGP6taJiWdeTO3Lycnhp6UvM+nUWPa7qwYvX\nvljsOkfWWlLfHU3qO+9QtlMnqr85Er8ybg653jIXpj8IIRHQ52Oo2sxTzXPfpB6uqYGDvy/y8MH3\nP2D/iBEM6fJnruvUgu5tMxg4fyDDfzec7nW6X+TKiojIlSY/M5O0z6Zz8IMPyN27l5DGjak4+BHK\nxsdjzpjGnpOfw+ytsxm7dix7M/bSqnIrOsZ0PPXUue1HtnMo69Cp8wP9AqkZXvPUVLkGaWWImbcW\n//mLsVknCI2LI+re/q6y/C/OGlNy+bDWsvHgRtci5imL2Jq2FYCro64+tYh5vfL1LtvpmQpAnUEB\nKBER+XLNboZ+toaKZYMZf29rGlULB1x/NIxdO5bRq0fTtkpbRsaPJDwovNh8Dn/0EXv/9nfKtGhB\n7JjR+EdEuFeBvetg2j2QeQjumAANu3miWe7Jy3Gt/9SiH9w8oshTtvXoyVEC6NnoASY/EMd/9oxg\nye4lLOy1kGD/4CKvERER8bT87GzSZ87k4PgJ5KSkEFyvHhUefpjwrl0KBYey87L5POlz3lv7HqmZ\nqUSFRJ22NtPJ9Zmqla2GP34c++47Dn/4IRk/LMUEBRHe4xai+vcnpEEDH7VWLkc7juxwLWKevJA1\nB9ZgscSWiz01MqpZpWYXbTH9i0EBqDMoACUiIgDrdqbz0OQVHMnKYWSv5nRpXOXUsdm/zuavS/5K\nrYhajE4YTdWyxU+VOzJvHruffoagWrWInTDx3234AAAgAElEQVSBwMrR7lXg6F74qDfsXgU3vATt\nn4CL8WvYzpUwoTPcOREa317ocNbmzfx2620sveUB3gxtyjdPt6brjBvo1aAXz8Y96/36iYiInMHm\n5nJk7lxSx44j+9dfCapZkwqDHiLillswQUGnnZuTl8Px3ONEBBf+USjvWAbpX3zBoalTyNmRTEB0\nNJF9+lD+7l4EREZerObIFSo1M5VFKYtITE7kpz0/kZufS1RIFPGx8XSu0Zm2Vdte8j/0KQB1BgWg\nRETkpP1Hshj04UpWp6Txxxvq83jnuqeGRP+05yeeWvQUwQHBvJvwLo0qNCo2n4ylS9k55DH8y5cn\n9v0JBNeu7V4FcjJh5mDYMMM1IqnbmxAQdO7rLsQPo1zrUP3fFihXpdDhff98lUNTpvDIrX+n2TU1\nad10HSNWjOCLHl9QL7Ked+smIiJyFjY/n6PffEPq2LGc2LiJgGpVqfDgg5S/4w78QkKKvS47OZlD\nU6aQ/vkX5GdkUKZZMyLv7U/4jTdiAouebi/iTceyj/H9ru9JTE5k8a7FZORkEBoQSofqHehcozMd\nYzpSLqicr6tZYgpAnUEBKBERKSgrJ48/z1jHFz/voluTqrx+VzPKBLmGQm89vJVHEx8l7UQar1//\nOh1jOhabT+b6DaQMGgTWEvvee0U+QrpI+fnw7XD472tQswPc/SGERnmiaUX7qA/s3wh/WF3okM3N\nJSk+nhP1GnFLdA9G9W7O+78NISwojKk3T/VenURERErAWkvG4sWkjhlL5qpV+FeqSIX77ifynrvx\nCws7dc7xH3/k0OQPOfbtt+DvT3iXLkTd258yTZv6tgEiBWTnZfPTnp9YmLKQRcmLOJh1kAC/AOKq\nxJFQI4FOsZ2IDnVzhL2PKQB1BgWgRETkTNZaxi/exvC5m2lUNZzx97amWnnXouIHjh9gSOIQthze\nwrC2w+jVoFex+WRv307ygwPJO3yYmHdGEda+vfuVWPspzBoCETHQ51Oo6IXRRvn5MOIqaNAVbh1d\n6PCxxYtJeWgQP973DP84WplJg6N5OPF+/tb+b9xW7zbP10dEROQCWGs5vmw5B8eNJeOHpfhHRBA5\n4F4CKlbk8IdTOJGUhH9kJOXvuZvIe3q7P01exEfybT5rD6xlYfJCEpMTST6aDEDTik1PLWJeO8LN\nkfY+oADUGRSAEhGR4izavJ8nPlpFcKA/4/q3olVN13oQx3OOM/S7oSzetZj7G9/Pky2fLPZxzDn7\n9pPy0EOc+O03qr/2KuFdu7pfgeQf4eO+kJ8DvT6EOtd7oln/s38zjG4LPd6Blv0LHd419GmOLf4v\nj972d2KiyxNbfzYLdixgUa9FhAaGerYuIiIiHpS5Zg2pY8dxbNEiAIIbNiSqf3/Cu3fDL/jSXldH\nrkzWWn5N+5WFKa5g1MaDGwGoE1HHFYyK7cw1Fa8p9m9SX1AA6gwKQImIyNls3X+UByetYE9aFv+4\nvQl3tooBIDc/l+E/DefTXz6lS60uvNzh5WIXisw7coSUwY+S+fPPVH7heaL69HG/Aoe3w7S74eBW\n6PYGtLrvwht10ooP4D9PweM/Q4WrTq/zsQySOnSAm7rRxVzLCz1qM3bbALpf1Z2/XvtXz9VBRETE\ni04kJZGfkUFIs2aX7aPu5cq0N2PvqSfqrdi3gjybR3Ro9KlFzNtUaUOgn2/XNCstAagAX1dARETE\nHXWjyzFryHUMmfYzQz9bw5a9R3i269UE+AXwfLvniSkXw8iVI9l/fD//iv8X5UPKF8rDPzycGu9P\nYNdTf2Tf3/5O3sFDVHxsiHt/CEfWggfnw/QH4Ms/QGoS3PA38MQjencshbBoiKpT6NDR+fOxWVks\nr9cWtoIN/ZmsvCzurHfnhZcrIiJykQTX0wMz5PJUJawKfa7uQ5+r+5B+Ip3vdn7HwuSFzNo6i0+2\nfEK5oHJ0jOlIQo0Erqt23RU9el0joERE5JKSk5fPK3M28e8ftnN9/UqM6tOC8BDXr0rzts9j2OJh\nVC1blTEJY4gNjy0yD5uby54X/kL6jBmU730PVZ5/HuPvZiApLxe+/jMsGwf1u8AdEyD4Ap+G8mZj\nqN4Sek0udGjHgPvI2buHP3Z/Hj8/P4Jq/AuL5dPun+oXZBEREZFSKjM3k6W7l7IweSHf7vyW9BPp\nBPkF0b5aezrX6Mz1sdcTFeLFB9wUUFpGQCkAJSIil6SPliXzwsz11KgQyvsD2lC7ouvpOqv2r+KJ\nhU9gMIxKGEWzSs2KvN5ay4E33uDghPcp16UL1V57Fb+gIPcrsGw8zP0TRF8NvT+G8kUHu84pLQXe\nagxdXoV2j5x2KGf3brYm/J6QgQ8Tf6Au98cHMH3vUIa1HcY9De85v/JERERE5KLKzc9l1f5VpxYx\n35OxBz/jR4voFnSOdS1iHlMuxmvll5YAVOlZFUtERKQEesfVYOrAtqQdz6HnO9+zOOkAAC2iWzDl\n5imUDSrLg18/yDc7vinyemMM0UOHEv3MMxydN4+Uhx8m71iG+xWIewj6fgppyTC+M+xceX4NSV7q\neq15baFD6V/+B6xlWd04AI4GLiHEP4RudbqdX1kiIiIictEF+AXQpkob/hT3J76+42s+7f4pg5oO\n4kj2EUasGEHXL7py5+w7Gb16NJsPbaa0DBTyNI2AEhGRS1rKoeM8NHkFSfuP8Xy3q7mvfS2MMRzK\nOsTjCx9n3YF1DG09lP6N+hc7ZS1t5kz2DHuekIYNiX1vHAEVKrhfgf2bYVovOLYPbh0DjW8vWQO+\nfBLWfw5/2n7aelLWWrZ1vwX/8uV5ofPj7ExLI7PqX0mokcArHV4pWRkiIiIiUiqlHElhYYprEfNV\n+1dhsVQvW5342HgSaiTQIroF/he45mhpGQGlAJSIiFzyMk7k8uQnq1mwcR/3tInlbz0bExTgR1Zu\nFn/+/s8s2LGAPg378EybZ4q9gR/99lt2PfkUgZUrE/v+BIJiSjAMOiMVPu4LKT9C/DDo+DS4uz7T\nu20hIgb6fX7a7sx169l+111EvPAXOm6IoFPr7fx0dAyTukyiZeWW7tdNRERERC4JqZmpfJfyHQtT\nFrJ091Jy8nOIDI6kU2wnOtfoTLuq7QgJCClxvgpAnUEBKBERuRD5+ZaRC37hnUVbiasVxZh+LalQ\nNph8m88bK95g8sbJdIrtxKu/e7XYp48c/3kVKYMH4xcUROyECYQ0qO9+BXJPwOwnYO3H0KQX9BgF\ngef4A+H4IXitNnR+AToOPe3Q3lf+Qdonn5A05lMe/3IrLdp+SL7JZGbPmVp8XEREROQyl5GTwfe7\nvicxOZHFOxdzLOcYZQLK0KF6B+Jj4+kY05GI4Ai38lIA6gwKQImIiCd8uWY3Qz9bQ8WywYy/tzWN\nqoUDMG3TNF5d/iqNohoxKmEUFctULPL6E0lJJA98iPzMTGLHjCa0VSv3C7cWFr8BC/8OsW3h7qlQ\ntlLx52+eAx/3gfvnQs32/8smJ4ek6zsRGhfH8Lj+LE3eQE7V1xjaeigDrhngfn1ERERE5JKXk5fD\n8r3LSUxOZFHKIg5kHiDABNC6Sms61+hMfGw8VcKqFHu9AlBnUABKREQ8Zd3OdB6avIIjWTmM7NWc\nLo1dN+RFyYv40+I/ERUSxeiE0dQpX6fI63N27SJ54EPk7N5N9TffpFzn+JJVYMNMmPGIK/jU+xOo\n3Kjo874eBsveg2dTThstdXTRInYOfpTK77zD7/6bw1UNE9mZl0jiXYlEhkSWrC4iIiIictnIt/ms\nT11PYnIiC5MXsv3IdgAaV2hM5xqdSaiRQO2I2qeNmC8tASg9BU9ERC47TWIimP3YddSvXI5Hpqzk\n7cQkrLXE14hn4k0TycrNot/cfizfu7zI6wOrV6fmtKkE16/PzscfJ+3zL0pWgWtuhfvnuKblvX8j\nJBX9JD6Sl0L1VoWm6qXPmo1/ZCRrql5NRk4W++wSEmokKPgkIiIicoXzM340rdSUp1o9xZe3fcms\nnrP4Q8s/YIzh7VVv03NWT3rM7MGbK99kzYE15Nt8X1f5FAWgRETkshQdHsLHg9pxe8vqjFzwC499\ntIrM7DyuqXgNU7tNpVKZSjy84GHmbJtT5PUBkZHU/PdEwtq2Zc+wYRycMKFkFajeCh5aCFG1YNpd\n8NO4049nZ8CeNVDj2tN25x05wrGFCwnv1o35Ww4SFrmJ47lHuaP+HSUrX0REREQue3XK12Fgk4FM\n6zaNBXcuYFjbYVQJq8LkDZPp91U/fv/Z731dxVMUgBIRkctWSKA/b9zVjD/f3JCv1u3hrnE/sDst\nk+plqzO562SaVWrGs4ufZfza8RQ1Jd0vLIzYsWMIv7kr+19/g32vvobNL8GvSBExcP88qN8F5j4D\nc4ZCXq7r2M7lkJ972tpPAEfmzcNmZxPeowffbNpHZJVVxJSNIa5K3IV8FCIiIiJymasSVoV7Gt7D\n+BvH8+3d3zL8d8NpHt3c19U6RQEoERG5rBljGNTxKj4Y0IYdqcfp8c4SVu44TERwBONuGEe3Ot14\ne9XbvLT0JXLycwpfHxREtddfJ7JvXw5NnMie5/6MzSl8XrGCy8LdU6D9E7B8vGs0VFY67FgKGIg9\nPbCUPns2QXXqsDmiOqlZu0i3m7i93u34Gd2yRURERMQ9EcERdK/TnZGdRvq6Kqfor1kREbkixDeM\nZsaQ9oQF+9P7vR+ZvnInQf5BDO8wnEFNB/F50uc8nvg4x7KPFbrW+PlR+flhVPrDE6TPmsXOxx4n\nPzPT/cL9/OHGv0OPUfDbf2HCDbBlDlRpDCH/e3xu9s6dZK5YSUTPnszfuJ/gyBX4G39urXurJz4C\nERERERGfUQBKRESuGHWjyzFryHW0qR3J0M/W8MqcjeRbeLzF47zU/iV+3PMjA+YNYG/G3kLXGmOo\nOHgwVV58kWOLF5P8wIPkpaWVrAIt74X+M+HYPti7DmqcPv0uffZsACJu6c7XG3dRJupnOsZ0pFJo\npfNus4iIiIhIaaAAlIiIXFHKhwbx7/vjuK99LcYv/o0H/r2cI1k53F7vdkYnjGbXsV30/aovWw5t\nKfL6yHvupvqbb5K1fj07+vcnZ2/hYNVZ1f6da3HyBjdDi36ndltrSZ81i9C2bdkREE5K1gpyzRHu\nrH/nhTRXRERERKRUUABKRESuOIH+frzY4xqG396EJVtTue3dJfyWmkH76u2Z1GUSAAPmDeCHXT8U\neX34TTcSO348Obv3sL1PH05s+61kFahwFfT+CKo2PbUra80acnYkE9GjBws27iOw/DIqhkRzXbXr\nzrudIiIiIiKlhQJQIiJyxeodV4OpA9ty+HgOt767hO+TUmkQ1YCpN0+letnqPJr4KDOSZhR5bVi7\nttT8cDL2RDY7+vYlc926C6pL2qxZmJAQyt10I3M2bSQgLIk7G9yOv5//BeUrIiIiIlIaKAAlIiJX\ntLZ1KjBryHVUjQhhwMRlTFzyG5VDKzOpyyTaVW3HX374C2///DbW2kLXhjRqRK1pU/ELC2PHgPs4\ntmTJedUhPzubo1/NpVxCAgfzA/glIxEM3Fb3tgttnoiIiIhIqaAAlIiIXPFio0KZPrg9nRtG89KX\nG3nui3UE+YUyKmEUd9S7g/HrxvPc98+RnZdd6NqgmjWpOW0qQbGxpDwymPQ5c0pc/rHvviMvPZ2I\nW3syf+MeAsuvoHmFOKqVreaJ5omIiIiI+JwCUCIiIkDZ4ADG9WvFY/F1+Xh5Cv0m/MSR4/n89dq/\n8kSLJ5izbQ6PfPMI6SfSC10bGB1NzQ8nE9qsGbuHPs2hKVNLVPaR2bPxr1iRsGuv5fNNifgFptO/\ncS9PNU1ERERExOcUgBIREXH4+RmG3tSAUb1bsGZnGj3eWcLmvUd5qOlD/PN3/2T1/tX0n9ufnUd3\nFrrWPzyc2AnjKdu5M/tefpkDbxc9be9MuYcPc/Tb74jo3p1juZYtx78h2EQQHxvvjSaKiIiIiPjE\nBQegjDHbjTHrjDGrjTErnH1RxpgFxpgk5zXywqsqIiJycdzSrBrTH2lPXr7ljjE/MG/9XrrV6ca4\nG8aRmplK36/6sj51faHr/EJCiPnXW0TccTupo8ew98WXsHl5Zy3r6Lx5kJNDRM8efLlhM35hm4iv\nfjOB/oHeap6IiIiIyEXnqRFQ8dba5tba1s77Z4FEa209INF5LyIicsloEhPB7Meuo37lcjwyZSWj\nEpNoXbk1U7pOoUxAGR74+gEWJS8qdJ0JCKDqyy9TYdAg0j75hF1P/ZH8EyeKLSd95iyC69cnuGFD\nPtk0A2PyGdyqjzebJiIiIiJy0XlrCl5PYJKzPQm41UvliIiIeE10eAgfD2rH7S2q88aCX3jso1VU\nDa3JlJunUCeiDk9++yTTNk0rdJ0xhug/PkXl557l6Pz5pAx6mLxjxwqdl719O5lr1hDRswcncvPY\nlrWQKL+rqVO+1kVonYiIiIjIxeOJAJQF5htjVhpjBjn7Kltr9zjbe4HKRV1ojBlkjFlhjFlx4MAB\nD1RFRETEs0IC/XmjVzOe69qQr9bt4a5xP5B9IowPbvqAjjEdGb5sOCOWjyDf5he6NmrAAKqNeI3j\nK1ey4957yU1NPe14+uzZ4OdHePdbmLImEQIP0rWWfrMRERERkcuPJwJQHay1LYGuwBBjTMeCB61r\nBdYiV2G11r5nrW1trW1dqVIlD1RFRETE84wxPHz9VXwwoA07Uo/T450lbNp9grc6vUWfhn2YvHEy\nQ78bSlZuVqFrI265hdjR75K97Te29+lLdkoKADY/n/RZswm79loCK0cz/ZfPsXllGNxGASgRERER\nufxccADKWrvLed0PzADigH3GmKoAzuv+Cy1HRETE1+IbRjNjSHvCgv3p/d6PzFi1h2fjnuWZNs/w\nzY5vGDh/IIeyDhW6rmzHjtSY+AF56els79OHrM2byfz5Z3J27SKiZw8OZR5iV/YyqvlfR0RIqA9a\nJiIiIiLiXRcUgDLGhBljyp3cBm4E1gOzgQHOaQOAWRdSjoiISGlRN7ocs4ZcR5vakQz9bA3D526m\nT8N+jOw0ks2HNtPvq37sOLKj0HWhLVpQa+oUjH8AO/r158Bb/8KEhlLu979n/KrPwORxa907fNAi\nERERERHvu9ARUJWB740xa4BlwBxr7Tzgn8ANxpgk4PfOexERkctC+dAg/n1/HPe1r8V7/93Gg5OW\nE1f5et6/6X2OZR+j31f9WLV/VaHrguvWpda0qQRER3N8xQrCb7gBU6YMX26bSV5mDXo3j/NBa0RE\nREREvO+CAlDW2m3W2mZOusZa+4qz/6C1NsFaW89a+3trbeH5CCIiIpewQH8/XuxxDf+4rQnfJ6Vy\n27tLCDd1mXrzVCKCIxj49UDmbZ9X+Lpq1ag5dQqRffpQ4ZGHWX1gNel5O4kN6ERkWJAPWiIiIiIi\n4n2eWIRcRETkitWnbQ2mDGzLoYxsbn13CTv2lWFK1ylcU/Eanv7uaT5Y/wGu53H8T0BkJFX+8gLB\ntWszad0n2Lxgbq/f3UctEBERERHxPgWgRERELlC7OhWY/VgHqkaEMGDiMmauPMx7N7zHTbVu4s2V\nb/Lyjy+Tm59b6Lqj2Uf5btcCco405+bGNX1QcxERERGRiyPA1xUQERG5HMRGhTJ9cHue+mQ1L365\nkS37jvLyLf+kWtlqTFw/kb3H9zKi4whCA//3lLuvtn1Frs0mJqATsVF6+p2IiIiIXL40AkpERMRD\nygYHMK5fKx6Lr8tHy1K49/3lDGgwhBfavcD3u77nvnn3ceD4gVPnf7LlM/KyqtKtfhsf1lpERERE\nxPsUgBIREfEgPz/D0JsaMKp3C9bsTKPHO0toEt6FUZ1Hsf3Idvp+1Zeth7ey4eAGktK2kJMWx02N\nq/i62iIiIiIiXqUAlIiIiBfc0qwa0x9pT16+5Y4xP3A8rT7/7vJvcvNzuXfuvby+/HX8CKIS19Ko\narivqysiIiIi4lUKQImIiHhJk5gIZj92HfUrl+ORKStJXB3IlK5TqBxWmRX7VpBzpAk3Xl0LY4yv\nqyoiIiIi4lUKQImIiHhRdHgIHw9qx+0tqvPGgl/4x5d7eS9hIvFV7iZzfwI3XlPZ11UUEREREfE6\nPQVPRETEy0IC/XmjVzMaVCnHP+dtZvvBDCqWvZHwgDTiakX5unoiIiIiIl6nEVAiIiIXgTGGh6+/\nig8GtGFH6nG+3XKAhKujCfDXrVhERERELn/6q1dEROQiim8YzYwh7bm+fiUGXFvL19UREREREbko\nNAVPRETkIqsbXY5JD8T5uhoiIiIiIheNRkCJiIiIiIiIiIhXKQAlIiIiIiIiIiJepQCUiIiIiIiI\niIh4lQJQIiIiIiIiIiLiVQpAiYiIiIiIiIiIVykAJSIiIiIiIiIiXqUAlIiIiIiIiIiIeJUCUCIi\nIiIiIiIi4lUKQImIiIiIiIiIiFcpACUiIiIiIiIiIl6lAJSIiIiIiIiIiHiVAlAiIiIiIiIiIuJV\nCkCJiIiIiIiIiIhXKQAlIiIiIiIiIiJepQCUiIiIiIiIiIh4lQJQIiIiIiIiIiLiVQpAiYiIiIiI\niIiIVykAJSIiIiIiIiIiXqUAlIiIiIiIiIiIeJUCUCIiIiIiIiIi4lUKQImIiIiIiIiIiFcpACUi\nIiIiIiIiIl6lAJSIiIiIiIiIiHiVsdb6ug4AGGOOAlt8XQ+RK1BFINXXlRC5Qqn/ifiG+p6Ib6jv\nifhGA2ttOV9XIsDXFShgi7W2ta8rIXKlMcasUN8T8Q31PxHfUN8T8Q31PRHfMMas8HUdQFPwRERE\nRERERETEyxSAEhERERERERERrypNAaj3fF0BkSuU+p6I76j/ifiG+p6Ib6jvifhGqeh7pWYRchER\nERERERERuTyVphFQIiIiIiIiIiJyGTpnAMoYE2uMWWSM2WiM2WCM+YOzP8oYs8AYk+S8Rjr7jTHm\nbWPMVmPMWmNMywJ55RljVjtpdjHlNTfGLHXKWmuMubvAsdrGmJ+cvD8xxgQ5+4Od91ud47UKXNO0\nQH7rjDEh5/thiVxMnup7xpj4Av1utTEmyxhzaxHleazvGWMCjTGTnD63yRjznPc/MRHP8PB971Vj\nzHon3V1MeefT9zoaY342xuQaY+48I78BTh2TjDEDvPEZiXjDefS9hk7fOWGMGXqufNwt7zzLDDHG\nLDPGrHHyeslbn5OIN3iq/xXIz98Ys8oY859iyvP0ve+c3zNFSiNP9j1jTHljzHRjzGbj+g52rbvl\nnU+ZxpgG5vTvmUeMMU+etcHW2rMmoCrQ0tkuB/wCNAJeA5519j8LvOps3wzMBQzQDvipQF7H3Civ\nPlDP2a4G7AHKO+8/Be5xtscCg53tR4GxzvY9wCfOdgCwFmjmvK8A+J+rDkpKpSF5su8VyDMKOASE\nFnHMk32vD/Cxsx0KbAdq+fozVVJyJ3mq7wHdgAXOvSgMWA6EF1He+fS9WkBTYDJwZ4G8ooBtzmuk\nsx3p689UScmddB59LxpoA7wCDD1XPu6W57wvaZkGKOtsBwI/Ae18/ZkqKbmbPNX/CuT3R2Aa8J9i\nyvPYvc85ds7vmUpKpTF5su8Bk4CBznbQyT7lTnnO+/Pq7845/sBeoObZ2nvOEVDW2j3W2p+d7aPA\nJqA60NNp4MmGnhxR0ROYbF1+BMobY6qeq5wC5f1irU1ytncD+4FKxhgDdAamF1PmybpMBxKc828E\n1lpr1zj5HbTW5rlbFxFf8lLfuxOYa609XkR5nux7FggzxgQAZYBs4Mj5fRIiF5cH+14j4L/W2lxr\nbQauH0S6FFFeifuetXa7tXYtkH9GdjcBC6y1h6y1h3EFwAqVKVIalbTvWWv3W2uXAzlu5uNueZxH\nmdZae8x5G+gkLbQqlwxP9T8AY0wMrh9hJpylPE/e+0QuWZ7qe8aYCKAj8L5zXra1Nq0E5VHSMs+Q\nAPxqrd1xtvaWaA0o45pe0wLXrzqVrbV7nEN7gcrOdnUgpcBlO/lfg0KMMSuMMT+aIqYAFVFeHK7I\n3a+4Ri+lWWtzi8j3VJnO8XTn/PqANcZ87QzXfKYk7RUpLTzQ9066B/jIjfIutO9NBzJw/ZqVDLxu\nrT107paKlC4X2PfWAF2MMaHGmIpAPBB7jvLc7XvFceffAZFSz82+V9J8SnJeict0phytxvVFeoG1\n9qxlipRWHuh/bwHP4GagyAP3Pijh90yR0ugC+15t4AAw0Zn+OsEYE1aC8jiPMgty63um2wEoY0xZ\n4HPgSWvtaSMZrGvMlTu/8tS01rbGNT3nLWPMVWcpryrwIXC/tfZ8o9wBQAegr/N6mzEm4TzzEvEJ\nD/W9k32qCfC1G+ddaN+LA/JwDamuDfyfMabOeeYl4hMX2vestfOBr4AfcN2Ql+LqF8WV54m+J3LJ\n8+B9r9h8SnKeu2Vaa/Ostc2BGCDOGNPYnXqKlCYX2v+MMd2B/dbalW6W56l7n9vfM0VKIw/c+wKA\nlsAYa20LXIMBnj2f8kpQ5sm8goAewGfnOtetAJQxJtCp3FRr7RfO7n0np/c4r/ud/bs4/RfeGGcf\n1tqTr9uAb4EWxpi2BRat6uHkFw7MAYY50xkADuKa1hBwZr4Fy3SORzjn78Q1/SHVmXL0Fa7/KCKX\nBE/1PUcvYIa1Nse51pt9rw8wz1qbY63dDywBWl/YpyFy8XjwvveKtba5tfYGXGvE/OKhvlecc/07\nIFKqlbDvlSgfZ+HVk33vkbOUd15lnuRMeViEpr/KJcZD/e86oIcxZjvwMdDZGDPFy/e+Ir9nutNm\nkdLAQ31vJ7CzwOjb6UDLi3Tv6wr8bK3dd64T3XkKnsE1j3CTtXZkgUOzgZNP1xkAzCqw/17j0g5I\nt9buMcZEGmOCnTwr4vrHaaO19ifnj/Pm1trZTvRsBq71NE7O/T0ZgVuEaw2boso8WZc7gYXO+V8D\nTZzpDwHA9cDGc7VZpDTwVN8rcF1vCiIbLLIAAARwSURBVAyL9HLfS8Y1fx9n6Gc7YPN5fhQiF5UH\n73v+xpgKTp5NcS2cOt9Dfa84XwM3OvfcSFxrIZ511KNIaXEefa9E+VhrUwr0vbFnKe98yqxkjCnv\nbJcBbkD3PbmEeKr/WWufs9bGWGtr4ZqSs9Ba28+b977ivme61XARH/Ng39sLpBhjGji7EnDFW7x2\n7yvgtO+ZZ2XPvSp7B1xDr9YCq510M675uYlAEvANEOWcb4B3cc3hXQe0dva3d96vcV4fLKa8frgW\nt1pdIDV3jtUBlgFbcQ3vCnb2hzjvtzrH65yR3wZgPfDaudqrpFRakqf6nnOsFq5fj/zOUp7H+h5Q\n1tm/AdcfAE/7+vNUUnI3efC+F+L8/78R+PFkfyqivPPpe21w/dKVgevX4g0F8nvAOX8rrikNPv9M\nlZTcSefR96o4/eAIkOZshxeXj7vlOcdKWmZTYJWT13rgL77+PJWUSpI81f/OyLMTxT8Fz2P3Ptz8\nnqmkVBqTJ/se0BxY4eQ1kyKehOzJe59zLMzpjxHutNc4F4mIiIiIiIiIiHhFiZ6CJyIiIiIiIiIi\nUlIKQImIiIiIiIiIiFcpACUiIiIiIiIiIl6lAJSIiIiIiIiIiHiVAlAiIiIiIiIiIuJVCkCJiIiI\nXABjTDVjzHRf10NERESkNDPWWl/XQURERERERERELmMaASUiIiJXDGNMmDFmjjFmjTFmvTHmbmNM\nK2PMd8aYlcaYr40xVZ1znzDGbDTGrDXGfOzsu94Ys9pJq4wx5YwxtYwx653jIcaYicaYdc7xeGf/\nfcaYL4wx84wxScaY13z3KYiIiIhcfAG+roCIiIjIRdQF2G2t7QZgjIkA5gI9rbUHjDF3A68ADwDP\nArWttSeMMeWd64cCQ6y1S4wxZYGsM/IfAlhrbRNjTENgvjGmvnOsOdACOAFsMcaMstameLGtIiIi\nIqWGRkCJiIjIlWQdcIMx5lVjzO+AWKAxsMAYsxp4Hohxzl0LTDXG9ANynX1LgJHGmCeA8tba3NOz\npwMwBcBauxnYAZwMQCVaa9OttVnARqCmV1ooIiIiUgopACUiIiJXDGvtL0BLXIGol4E7gA3W2uZO\namKtvdE5vRvwrnP+cmNMgLX2n8BAoAywxBnl5K4TBbbz0Eh0ERERuYIoACUiIiJXDGNMNeC4tXYK\nMAJoC1QyxlzrHA80xlxjjPEDYq21i4A/ARFAWWPMVdbaddbaV4HlwJkBqMVAXyev+kANYMvFaJuI\niIhIaaZf3kRERORK0gQYYYzJB3KAwbim173trAcVALwF/AJMcfYZ4G1rbZox5u/OwuL5wAZc60dV\nLZD/aGCMMWadk+99zhpSF6l5IiIiIqWTsdb6ug4iIiIiIiIiInIZ0xQ8ERERERERERHxKgWgRERE\nRERERETEqxSAEhERERERERERr1IASkREREREREREvEoBKBERERERERER8SoFoERERERERERExKsU\ngBIREREREREREa9SAEpERERERERERLzq/wHqP2R3vu8FhwAAAABJRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x137fa7e80>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"gp_wide.plot(figsize=(20,10));"
]
},
{
"cell_type": "code",
"execution_count": 209,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABLkAAAJCCAYAAAAsvhUtAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x137e54160>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"gp_wide.plot(kind='barh', figsize=(20,10));"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Automating insight...\n",
"\n",
"We can automate some of the observations we might want to make, such as years when M speak more, on average, than F, within a party."
]
},
{
"cell_type": "code",
"execution_count": 225,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>party</th>\n",
" <th>Alliance</th>\n",
" <th colspan=\"2\" halign=\"left\">Conservative</th>\n",
" <th>Democratic Unionist</th>\n",
" <th colspan=\"2\" halign=\"left\">Democratic Unionist Party</th>\n",
" <th>Green Party</th>\n",
" <th colspan=\"2\" halign=\"left\">Independent</th>\n",
" <th>Labour</th>\n",
" <th>...</th>\n",
" <th>Plaid Cymru</th>\n",
" <th>Respect</th>\n",
" <th>SNP</th>\n",
" <th colspan=\"2\" halign=\"left\">Scottish National Party</th>\n",
" <th>Social Democratic</th>\n",
" <th colspan=\"2\" halign=\"left\">Social Democratic &amp; Labour Party</th>\n",
" <th>UKIP</th>\n",
" <th>Ulster Unionist Party</th>\n",
" </tr>\n",
" <tr>\n",
" <th>gender</th>\n",
" <th>Female</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" <th>Male</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" <th>Female</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" <th>Female</th>\n",
" <th>...</th>\n",
" <th>Male</th>\n",
" <th>Male</th>\n",
" <th>Female</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" <th>Male</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" <th>Male</th>\n",
" <th>Male</th>\n",
" </tr>\n",
" <tr>\n",
" <th>session</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2005-2006</th>\n",
" <td>NaN</td>\n",
" <td>134.312500</td>\n",
" <td>132.519774</td>\n",
" <td>144.0</td>\n",
" <td>92.0</td>\n",
" <td>132.714286</td>\n",
" <td>NaN</td>\n",
" <td>95.666667</td>\n",
" <td>45.750000</td>\n",
" <td>111.188889</td>\n",
" <td>...</td>\n",
" <td>202.000000</td>\n",
" <td>34.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>124.857143</td>\n",
" <td>24.0</td>\n",
" <td>NaN</td>\n",
" <td>95.333333</td>\n",
" <td>123.5</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2006-2007</th>\n",
" <td>NaN</td>\n",
" <td>91.875000</td>\n",
" <td>92.823864</td>\n",
" <td>39.0</td>\n",
" <td>10.0</td>\n",
" <td>53.000000</td>\n",
" <td>NaN</td>\n",
" <td>61.000000</td>\n",
" <td>64.666667</td>\n",
" <td>85.844444</td>\n",
" <td>...</td>\n",
" <td>64.333333</td>\n",
" <td>50.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>99.000000</td>\n",
" <td>28.0</td>\n",
" <td>NaN</td>\n",
" <td>67.333333</td>\n",
" <td>89.5</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-2008</th>\n",
" <td>NaN</td>\n",
" <td>101.812500</td>\n",
" <td>118.710227</td>\n",
" <td>11.0</td>\n",
" <td>19.0</td>\n",
" <td>32.000000</td>\n",
" <td>NaN</td>\n",
" <td>85.000000</td>\n",
" <td>79.800000</td>\n",
" <td>110.696629</td>\n",
" <td>...</td>\n",
" <td>86.000000</td>\n",
" <td>15.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>104.125000</td>\n",
" <td>19.0</td>\n",
" <td>NaN</td>\n",
" <td>32.666667</td>\n",
" <td>148.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-2009</th>\n",
" <td>NaN</td>\n",
" <td>84.294118</td>\n",
" <td>97.052023</td>\n",
" <td>1.0</td>\n",
" <td>8.0</td>\n",
" <td>40.571429</td>\n",
" <td>NaN</td>\n",
" <td>31.000000</td>\n",
" <td>60.285714</td>\n",
" <td>88.090909</td>\n",
" <td>...</td>\n",
" <td>60.333333</td>\n",
" <td>8.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>92.000000</td>\n",
" <td>24.0</td>\n",
" <td>NaN</td>\n",
" <td>65.333333</td>\n",
" <td>77.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2009-2010</th>\n",
" <td>NaN</td>\n",
" <td>42.823529</td>\n",
" <td>54.563218</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>19.714286</td>\n",
" <td>NaN</td>\n",
" <td>8.000000</td>\n",
" <td>68.000000</td>\n",
" <td>44.262500</td>\n",
" <td>...</td>\n",
" <td>29.333333</td>\n",
" <td>5.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>35.125000</td>\n",
" <td>6.0</td>\n",
" <td>NaN</td>\n",
" <td>23.666667</td>\n",
" <td>17.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 26 columns</p>\n",
"</div>"
],
"text/plain": [
"party Alliance Conservative Democratic Unionist \\\n",
"gender Female Female Male Male \n",
"session \n",
"2005-2006 NaN 134.312500 132.519774 144.0 \n",
"2006-2007 NaN 91.875000 92.823864 39.0 \n",
"2007-2008 NaN 101.812500 118.710227 11.0 \n",
"2008-2009 NaN 84.294118 97.052023 1.0 \n",
"2009-2010 NaN 42.823529 54.563218 3.0 \n",
"\n",
"party Democratic Unionist Party Green Party Independent \\\n",
"gender Female Male Female Female \n",
"session \n",
"2005-2006 92.0 132.714286 NaN 95.666667 \n",
"2006-2007 10.0 53.000000 NaN 61.000000 \n",
"2007-2008 19.0 32.000000 NaN 85.000000 \n",
"2008-2009 8.0 40.571429 NaN 31.000000 \n",
"2009-2010 1.0 19.714286 NaN 8.000000 \n",
"\n",
"party Labour ... Plaid Cymru Respect \\\n",
"gender Male Female ... Male Male \n",
"session ... \n",
"2005-2006 45.750000 111.188889 ... 202.000000 34.0 \n",
"2006-2007 64.666667 85.844444 ... 64.333333 50.0 \n",
"2007-2008 79.800000 110.696629 ... 86.000000 15.0 \n",
"2008-2009 60.285714 88.090909 ... 60.333333 8.0 \n",
"2009-2010 68.000000 44.262500 ... 29.333333 5.0 \n",
"\n",
"party SNP Scottish National Party Social Democratic \\\n",
"gender Female Female Male Male \n",
"session \n",
"2005-2006 NaN NaN 124.857143 24.0 \n",
"2006-2007 NaN NaN 99.000000 28.0 \n",
"2007-2008 NaN NaN 104.125000 19.0 \n",
"2008-2009 NaN NaN 92.000000 24.0 \n",
"2009-2010 NaN NaN 35.125000 6.0 \n",
"\n",
"party Social Democratic & Labour Party UKIP \\\n",
"gender Female Male Male \n",
"session \n",
"2005-2006 NaN 95.333333 123.5 \n",
"2006-2007 NaN 67.333333 89.5 \n",
"2007-2008 NaN 32.666667 148.0 \n",
"2008-2009 NaN 65.333333 77.0 \n",
"2009-2010 NaN 23.666667 17.0 \n",
"\n",
"party Ulster Unionist Party \n",
"gender Male \n",
"session \n",
"2005-2006 NaN \n",
"2006-2007 NaN \n",
"2007-2008 NaN \n",
"2008-2009 NaN \n",
"2009-2010 NaN \n",
"\n",
"[5 rows x 26 columns]"
]
},
"execution_count": 225,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Go back to the full dataset, not filtered by party\n",
"gp_wide = gp_overall.pivot_table(index='session', columns=['party','gender'])\n",
"\n",
"#Flatten column names\n",
"gp_wide.columns = gp_wide.columns.droplevel(0)\n",
"\n",
"gp_wide.head()"
]
},
{
"cell_type": "code",
"execution_count": 232,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>gender</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" </tr>\n",
" <tr>\n",
" <th>session</th>\n",
" <th>party</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"17\" valign=\"top\">2005-2006</th>\n",
" <th>Alliance</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Conservative</th>\n",
" <td>134.312500</td>\n",
" <td>132.519774</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Democratic Unionist</th>\n",
" <td>NaN</td>\n",
" <td>144.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Democratic Unionist Party</th>\n",
" <td>92.000000</td>\n",
" <td>132.714286</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Green Party</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Independent</th>\n",
" <td>95.666667</td>\n",
" <td>45.750000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Labour</th>\n",
" <td>111.188889</td>\n",
" <td>142.821277</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Labour (Co-op)</th>\n",
" <td>104.200000</td>\n",
" <td>141.533333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Liberal Democrat</th>\n",
" <td>118.777778</td>\n",
" <td>119.111111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Plaid Cymru</th>\n",
" <td>NaN</td>\n",
" <td>202.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Respect</th>\n",
" <td>NaN</td>\n",
" <td>34.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SNP</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Scottish National Party</th>\n",
" <td>NaN</td>\n",
" <td>124.857143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Social Democratic</th>\n",
" <td>NaN</td>\n",
" <td>24.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Social Democratic &amp; Labour Party</th>\n",
" <td>NaN</td>\n",
" <td>95.333333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>UKIP</th>\n",
" <td>NaN</td>\n",
" <td>123.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ulster Unionist Party</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"13\" valign=\"top\">2006-2007</th>\n",
" <th>Alliance</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Conservative</th>\n",
" <td>91.875000</td>\n",
" <td>92.823864</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Democratic Unionist</th>\n",
" <td>NaN</td>\n",
" <td>39.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Democratic Unionist Party</th>\n",
" <td>10.000000</td>\n",
" <td>53.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Green Party</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Independent</th>\n",
" <td>61.000000</td>\n",
" <td>64.666667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Labour</th>\n",
" <td>85.844444</td>\n",
" <td>98.127119</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Labour (Co-op)</th>\n",
" <td>83.000000</td>\n",
" <td>112.785714</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Liberal Democrat</th>\n",
" <td>82.888889</td>\n",
" <td>92.166667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Plaid Cymru</th>\n",
" <td>NaN</td>\n",
" <td>64.333333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Respect</th>\n",
" <td>NaN</td>\n",
" <td>50.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SNP</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Scottish National Party</th>\n",
" <td>NaN</td>\n",
" <td>99.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"13\" valign=\"top\">2015-2016</th>\n",
" <th>Green Party</th>\n",
" <td>176.000000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Independent</th>\n",
" <td>54.000000</td>\n",
" <td>19.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Labour</th>\n",
" <td>72.155556</td>\n",
" <td>83.813559</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Labour (Co-op)</th>\n",
" <td>77.500000</td>\n",
" <td>80.750000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Liberal Democrat</th>\n",
" <td>NaN</td>\n",
" <td>117.250000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Plaid Cymru</th>\n",
" <td>84.000000</td>\n",
" <td>110.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Respect</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SNP</th>\n",
" <td>19.000000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Scottish National Party</th>\n",
" <td>96.555556</td>\n",
" <td>113.805556</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Social Democratic</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Social Democratic &amp; Labour Party</th>\n",
" <td>151.000000</td>\n",
" <td>117.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>UKIP</th>\n",
" <td>NaN</td>\n",
" <td>55.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ulster Unionist Party</th>\n",
" <td>NaN</td>\n",
" <td>85.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"17\" valign=\"top\">2016-2017</th>\n",
" <th>Alliance</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Conservative</th>\n",
" <td>126.074627</td>\n",
" <td>111.386100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Democratic Unionist</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Democratic Unionist Party</th>\n",
" <td>NaN</td>\n",
" <td>94.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Green Party</th>\n",
" <td>142.000000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Independent</th>\n",
" <td>32.000000</td>\n",
" <td>19.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Labour</th>\n",
" <td>56.344086</td>\n",
" <td>66.265487</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Labour (Co-op)</th>\n",
" <td>64.300000</td>\n",
" <td>74.823529</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Liberal Democrat</th>\n",
" <td>16.000000</td>\n",
" <td>96.750000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Plaid Cymru</th>\n",
" <td>100.000000</td>\n",
" <td>122.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Respect</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SNP</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Scottish National Party</th>\n",
" <td>111.555556</td>\n",
" <td>95.583333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Social Democratic</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Social Democratic &amp; Labour Party</th>\n",
" <td>108.000000</td>\n",
" <td>79.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>UKIP</th>\n",
" <td>NaN</td>\n",
" <td>27.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ulster Unionist Party</th>\n",
" <td>NaN</td>\n",
" <td>80.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>187 rows × 2 columns</p>\n",
"</div>"
],
"text/plain": [
"gender Female Male\n",
"session party \n",
"2005-2006 Alliance NaN NaN\n",
" Conservative 134.312500 132.519774\n",
" Democratic Unionist NaN 144.000000\n",
" Democratic Unionist Party 92.000000 132.714286\n",
" Green Party NaN NaN\n",
" Independent 95.666667 45.750000\n",
" Labour 111.188889 142.821277\n",
" Labour (Co-op) 104.200000 141.533333\n",
" Liberal Democrat 118.777778 119.111111\n",
" Plaid Cymru NaN 202.000000\n",
" Respect NaN 34.000000\n",
" SNP NaN NaN\n",
" Scottish National Party NaN 124.857143\n",
" Social Democratic NaN 24.000000\n",
" Social Democratic & Labour Party NaN 95.333333\n",
" UKIP NaN 123.500000\n",
" Ulster Unionist Party NaN NaN\n",
"2006-2007 Alliance NaN NaN\n",
" Conservative 91.875000 92.823864\n",
" Democratic Unionist NaN 39.000000\n",
" Democratic Unionist Party 10.000000 53.000000\n",
" Green Party NaN NaN\n",
" Independent 61.000000 64.666667\n",
" Labour 85.844444 98.127119\n",
" Labour (Co-op) 83.000000 112.785714\n",
" Liberal Democrat 82.888889 92.166667\n",
" Plaid Cymru NaN 64.333333\n",
" Respect NaN 50.000000\n",
" SNP NaN NaN\n",
" Scottish National Party NaN 99.000000\n",
"... ... ...\n",
"2015-2016 Green Party 176.000000 NaN\n",
" Independent 54.000000 19.000000\n",
" Labour 72.155556 83.813559\n",
" Labour (Co-op) 77.500000 80.750000\n",
" Liberal Democrat NaN 117.250000\n",
" Plaid Cymru 84.000000 110.500000\n",
" Respect NaN NaN\n",
" SNP 19.000000 NaN\n",
" Scottish National Party 96.555556 113.805556\n",
" Social Democratic NaN NaN\n",
" Social Democratic & Labour Party 151.000000 117.500000\n",
" UKIP NaN 55.000000\n",
" Ulster Unionist Party NaN 85.000000\n",
"2016-2017 Alliance NaN NaN\n",
" Conservative 126.074627 111.386100\n",
" Democratic Unionist NaN NaN\n",
" Democratic Unionist Party NaN 94.000000\n",
" Green Party 142.000000 NaN\n",
" Independent 32.000000 19.000000\n",
" Labour 56.344086 66.265487\n",
" Labour (Co-op) 64.300000 74.823529\n",
" Liberal Democrat 16.000000 96.750000\n",
" Plaid Cymru 100.000000 122.500000\n",
" Respect NaN NaN\n",
" SNP NaN NaN\n",
" Scottish National Party 111.555556 95.583333\n",
" Social Democratic NaN NaN\n",
" Social Democratic & Labour Party 108.000000 79.000000\n",
" UKIP NaN 27.000000\n",
" Ulster Unionist Party NaN 80.000000\n",
"\n",
"[187 rows x 2 columns]"
]
},
"execution_count": 232,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sp_wide = gp_wide.reset_index().melt(id_vars=['session']).pivot_table(index=['session','party'], columns=['gender'])\n",
"\n",
"#Flatten column names\n",
"sp_wide.columns = sp_wide.columns.droplevel(0)\n",
"\n",
"sp_wide#.dropna(how='all')"
]
},
{
"cell_type": "code",
"execution_count": 235,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>gender</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" </tr>\n",
" <tr>\n",
" <th>session</th>\n",
" <th>party</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">2005-2006</th>\n",
" <th>Conservative</th>\n",
" <td>134.312</td>\n",
" <td>132.520</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Independent</th>\n",
" <td>95.667</td>\n",
" <td>45.750</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2007-2008</th>\n",
" <th>Independent</th>\n",
" <td>85.000</td>\n",
" <td>79.800</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">2010-2012</th>\n",
" <th>Alliance</th>\n",
" <td>158.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Green Party</th>\n",
" <td>320.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"3\" valign=\"top\">2012-2013</th>\n",
" <th>Alliance</th>\n",
" <td>62.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Green Party</th>\n",
" <td>205.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Scottish National Party</th>\n",
" <td>139.000</td>\n",
" <td>110.200</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"4\" valign=\"top\">2013-2014</th>\n",
" <th>Alliance</th>\n",
" <td>115.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Green Party</th>\n",
" <td>280.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Independent</th>\n",
" <td>159.000</td>\n",
" <td>19.600</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Labour</th>\n",
" <td>90.263</td>\n",
" <td>86.265</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"6\" valign=\"top\">2014-2015</th>\n",
" <th>Alliance</th>\n",
" <td>63.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Conservative</th>\n",
" <td>105.000</td>\n",
" <td>97.794</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Green Party</th>\n",
" <td>167.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Independent</th>\n",
" <td>103.000</td>\n",
" <td>14.000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Labour</th>\n",
" <td>64.351</td>\n",
" <td>61.986</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Social Democratic &amp; Labour Party</th>\n",
" <td>88.000</td>\n",
" <td>72.000</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"4\" valign=\"top\">2015-2016</th>\n",
" <th>Green Party</th>\n",
" <td>176.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Independent</th>\n",
" <td>54.000</td>\n",
" <td>19.000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SNP</th>\n",
" <td>19.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Social Democratic &amp; Labour Party</th>\n",
" <td>151.000</td>\n",
" <td>117.500</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"5\" valign=\"top\">2016-2017</th>\n",
" <th>Conservative</th>\n",
" <td>126.075</td>\n",
" <td>111.386</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Green Party</th>\n",
" <td>142.000</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Independent</th>\n",
" <td>32.000</td>\n",
" <td>19.000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Scottish National Party</th>\n",
" <td>111.556</td>\n",
" <td>95.583</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Social Democratic &amp; Labour Party</th>\n",
" <td>108.000</td>\n",
" <td>79.000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"gender Female Male\n",
"session party \n",
"2005-2006 Conservative 134.312 132.520\n",
" Independent 95.667 45.750\n",
"2007-2008 Independent 85.000 79.800\n",
"2010-2012 Alliance 158.000 NaN\n",
" Green Party 320.000 NaN\n",
"2012-2013 Alliance 62.000 NaN\n",
" Green Party 205.000 NaN\n",
" Scottish National Party 139.000 110.200\n",
"2013-2014 Alliance 115.000 NaN\n",
" Green Party 280.000 NaN\n",
" Independent 159.000 19.600\n",
" Labour 90.263 86.265\n",
"2014-2015 Alliance 63.000 NaN\n",
" Conservative 105.000 97.794\n",
" Green Party 167.000 NaN\n",
" Independent 103.000 14.000\n",
" Labour 64.351 61.986\n",
" Social Democratic & Labour Party 88.000 72.000\n",
"2015-2016 Green Party 176.000 NaN\n",
" Independent 54.000 19.000\n",
" SNP 19.000 NaN\n",
" Social Democratic & Labour Party 151.000 117.500\n",
"2016-2017 Conservative 126.075 111.386\n",
" Green Party 142.000 NaN\n",
" Independent 32.000 19.000\n",
" Scottish National Party 111.556 95.583\n",
" Social Democratic & Labour Party 108.000 79.000"
]
},
"execution_count": 235,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Sessions when F spoke more, on average, then M\n",
"#Recall, this data has been previously filtered to limit data to Con and Lab\n",
"\n",
"#Tweak the precision of the display\n",
"pd.set_option('precision',3)\n",
"\n",
"sp_wide[sp_wide['Female'].fillna(0) > sp_wide['Male'].fillna(0) ]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"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": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment