s444463/sportowe_wizualizacja
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
cdb14194a7
sportowe_wizualizacja/xGStatsbomb.ipynb
Koushik R Kirugulige 7bb8465f3f using Statsbomb Freeze frame when there is a shot
2020-05-13 17:47:39 +05:30

2856 lines
391 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "xGStatsbomb.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyNsyQ1grvKucvpzQ+6OWDaR",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/koushikkirugulige/Football-Analytics/blob/master/xGStatsbomb.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "g37QpaaPZHA5",
"colab_type": "code",
"outputId": "e4d0b0c8-f58b-4e46-a41e-65d2743d1e50",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 187
}
},
"source": [
"%%time\n",
"!git clone https://github.com/statsbomb/open-data.git"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"text": [
"Cloning into 'open-data'...\n",
"remote: Enumerating objects: 1133, done.\u001b[K\n",
"remote: Counting objects: 100% (1133/1133), done.\u001b[K\n",
"remote: Compressing objects: 100% (632/632), done.\u001b[K\n",
"remote: Total 9855 (delta 925), reused 690 (delta 482), pack-reused 8722\u001b[K\n",
"Receiving objects: 100% (9855/9855), 996.16 MiB | 25.43 MiB/s, done.\n",
"Resolving deltas: 100% (8672/8672), done.\n",
"Checking out files: 100% (1648/1648), done.\n",
"CPU times: user 478 ms, sys: 94.4 ms, total: 572 ms\n",
"Wall time: 2min 17s\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "nd6vcG3uZNJb",
"colab_type": "code",
"colab": {}
},
"source": [
"#import all modules\n",
"import json\n",
"import os\n",
"import codecs\n",
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"from matplotlib.patches import Arc, Rectangle, ConnectionPatch\n",
"from matplotlib.offsetbox import OffsetImage\n",
"from matplotlib.patches import Ellipse\n",
"from functools import reduce\n",
"import math"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "5NMxa9NNZR5m",
"colab_type": "code",
"outputId": "163c47f0-dae4-4337-af58-3d2696232bf7",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 68
}
},
"source": [
"%%time\n",
"comp = ['FIFA World Cup','La Liga']\n",
"main_df = pd.DataFrame(data=None)\n",
"path_match = \"/content/open-data/data/events/\" #location for play by play events\n",
"for root, dirs, files in os.walk('/content/open-data/data/matches/'):\n",
" for file in files:\n",
" with open(os.path.join(root, file), \"r\") as auto:\n",
" with codecs.open(root + str('/') + file,encoding='utf-8') as data_file:\n",
" data = json.load(data_file)\n",
" df = pd.DataFrame(data=None)\n",
" df = pd.json_normalize(data, sep = \"_\")\n",
" #for x in df.competition_country_name:\n",
" # if x == 'Spain':\n",
" # print(df.match_id)\n",
" #print(df['competition_competition_name'])\n",
" for i in range(len(df)):\n",
" if df.iloc[i]['competition_competition_name'] in comp :\n",
" match_no = df.iloc[i]['match_id'] #gets match with Spain as country\n",
" match_no = str(match_no) # from int to str \n",
" #print('match list \\n',match_no)\n",
" with codecs.open(path_match + match_no + str(r'.json'),encoding=\"utf8\") as event_file: #open the respective file\n",
" df_match = json.load(event_file)\n",
" df_match2 = pd.DataFrame(data=None)\n",
" df_match2 = pd.json_normalize(df_match,sep=\"_\") \n",
" df_match2 = df_match2[(df_match2['type_name'] == \"Shot\")]\n",
" main_df = main_df.append(df_match2,ignore_index=True,sort=False) \n",
"#print('total matches ',len(match_no)) \n",
"print('Done')"
],
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"text": [
"Done\n",
"CPU times: user 6min 28s, sys: 1.27 s, total: 6min 29s\n",
"Wall time: 6min 30s\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "waQI6t6OVM33",
"colab_type": "code",
"outputId": "16372efd-c12f-48ec-f02c-95279925490b",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 508
}
},
"source": [
"main_df.head()"
],
"execution_count": 0,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>id</th>\n",
" <th>index</th>\n",
" <th>period</th>\n",
" <th>timestamp</th>\n",
" <th>minute</th>\n",
" <th>second</th>\n",
" <th>possession</th>\n",
" <th>duration</th>\n",
" <th>type_id</th>\n",
" <th>type_name</th>\n",
" <th>possession_team_id</th>\n",
" <th>possession_team_name</th>\n",
" <th>play_pattern_id</th>\n",
" <th>play_pattern_name</th>\n",
" <th>team_id</th>\n",
" <th>team_name</th>\n",
" <th>tactics_formation</th>\n",
" <th>tactics_lineup</th>\n",
" <th>related_events</th>\n",
" <th>location</th>\n",
" <th>player_id</th>\n",
" <th>player_name</th>\n",
" <th>position_id</th>\n",
" <th>position_name</th>\n",
" <th>pass_recipient_id</th>\n",
" <th>pass_recipient_name</th>\n",
" <th>pass_length</th>\n",
" <th>pass_angle</th>\n",
" <th>pass_height_id</th>\n",
" <th>pass_height_name</th>\n",
" <th>pass_end_location</th>\n",
" <th>pass_type_id</th>\n",
" <th>pass_type_name</th>\n",
" <th>pass_body_part_id</th>\n",
" <th>pass_body_part_name</th>\n",
" <th>carry_end_location</th>\n",
" <th>under_pressure</th>\n",
" <th>pass_outcome_id</th>\n",
" <th>pass_outcome_name</th>\n",
" <th>ball_receipt_outcome_id</th>\n",
" <th>...</th>\n",
" <th>pass_deflected</th>\n",
" <th>block_deflection</th>\n",
" <th>substitution_outcome_id</th>\n",
" <th>substitution_outcome_name</th>\n",
" <th>substitution_replacement_id</th>\n",
" <th>substitution_replacement_name</th>\n",
" <th>ball_recovery_recovery_failure</th>\n",
" <th>dribble_overrun</th>\n",
" <th>50_50_outcome_id</th>\n",
" <th>50_50_outcome_name</th>\n",
" <th>shot_aerial_won</th>\n",
" <th>shot_open_goal</th>\n",
" <th>bad_behaviour_card_id</th>\n",
" <th>bad_behaviour_card_name</th>\n",
" <th>pass_no_touch</th>\n",
" <th>block_offensive</th>\n",
" <th>foul_committed_offensive</th>\n",
" <th>shot_saved_off_target</th>\n",
" <th>goalkeeper_shot_saved_off_target</th>\n",
" <th>miscontrol_aerial_won</th>\n",
" <th>goalkeeper_punched_out</th>\n",
" <th>clearance_other</th>\n",
" <th>ball_recovery_offensive</th>\n",
" <th>shot_deflected</th>\n",
" <th>dribble_no_touch</th>\n",
" <th>shot_redirect</th>\n",
" <th>block_save_block</th>\n",
" <th>injury_stoppage_in_chain</th>\n",
" <th>half_start_late_video_start</th>\n",
" <th>player_off_permanent</th>\n",
" <th>goalkeeper_lost_out</th>\n",
" <th>goalkeeper_saved_to_post</th>\n",
" <th>shot_follows_dribble</th>\n",
" <th>shot_saved_to_post</th>\n",
" <th>goalkeeper_shot_saved_to_post</th>\n",
" <th>pass_backheel</th>\n",
" <th>goalkeeper_lost_in_play</th>\n",
" <th>goalkeeper_success_out</th>\n",
" <th>goalkeeper_success_in_play</th>\n",
" <th>half_end_early_video_end</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>fb785612-71d3-44df-aae4-da6e005756de</td>\n",
" <td>117</td>\n",
" <td>1</td>\n",
" <td>00:02:06.532</td>\n",
" <td>2</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>1.015179</td>\n",
" <td>16</td>\n",
" <td>Shot</td>\n",
" <td>222</td>\n",
" <td>Villarreal</td>\n",
" <td>1</td>\n",
" <td>Regular Play</td>\n",
" <td>222</td>\n",
" <td>Villarreal</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>[1febb4f7-0e2c-43f7-96fe-51fbffaaf664]</td>\n",
" <td>[107.5, 27.2]</td>\n",
" <td>11386.0</td>\n",
" <td>Santiago Cazorla González</td>\n",
" <td>16.0</td>\n",
" <td>Left Midfield</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2dfa84fe-3579-4705-8d27-44b8917907e1</td>\n",
" <td>499</td>\n",
" <td>1</td>\n",
" <td>00:09:49.110</td>\n",
" <td>9</td>\n",
" <td>49</td>\n",
" <td>17</td>\n",
" <td>1.302674</td>\n",
" <td>16</td>\n",
" <td>Shot</td>\n",
" <td>222</td>\n",
" <td>Villarreal</td>\n",
" <td>4</td>\n",
" <td>From Throw In</td>\n",
" <td>222</td>\n",
" <td>Villarreal</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>[1af68944-ff3d-49a1-92a0-fe6198e73e78]</td>\n",
" <td>[88.3, 50.2]</td>\n",
" <td>25921.0</td>\n",
" <td>Rubén Gracia Calmache</td>\n",
" <td>12.0</td>\n",
" <td>Right Midfield</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>c9d92f30-2159-4a5a-a5bf-9d1163e4b33f</td>\n",
" <td>587</td>\n",
" <td>1</td>\n",
" <td>00:12:58.407</td>\n",
" <td>12</td>\n",
" <td>58</td>\n",
" <td>24</td>\n",
" <td>0.521000</td>\n",
" <td>16</td>\n",
" <td>Shot</td>\n",
" <td>222</td>\n",
" <td>Villarreal</td>\n",
" <td>5</td>\n",
" <td>Other</td>\n",
" <td>222</td>\n",
" <td>Villarreal</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>[61239f9b-052f-42ab-8a73-3c3c3841d419]</td>\n",
" <td>[108.0, 40.0]</td>\n",
" <td>20135.0</td>\n",
" <td>Marcos Antonio Senna da Silva</td>\n",
" <td>15.0</td>\n",
" <td>Left Center Midfield</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>26b5d67b-5fce-4a5a-8b31-b879adbb61d3</td>\n",
" <td>1113</td>\n",
" <td>1</td>\n",
" <td>00:24:01.266</td>\n",
" <td>24</td>\n",
" <td>1</td>\n",
" <td>42</td>\n",
" <td>0.647279</td>\n",
" <td>16</td>\n",
" <td>Shot</td>\n",
" <td>217</td>\n",
" <td>Barcelona</td>\n",
" <td>7</td>\n",
" <td>From Goal Kick</td>\n",
" <td>217</td>\n",
" <td>Barcelona</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>[1d8506ef-3a55-45c7-aba9-e31204db051e, 354b60e...</td>\n",
" <td>[107.3, 36.1]</td>\n",
" <td>4913.0</td>\n",
" <td>Bojan Krkíc Pérez</td>\n",
" <td>23.0</td>\n",
" <td>Center Forward</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20528610-c092-482c-8238-6b9679328680</td>\n",
" <td>1343</td>\n",
" <td>1</td>\n",
" <td>00:28:38.374</td>\n",
" <td>28</td>\n",
" <td>38</td>\n",
" <td>49</td>\n",
" <td>1.023005</td>\n",
" <td>16</td>\n",
" <td>Shot</td>\n",
" <td>217</td>\n",
" <td>Barcelona</td>\n",
" <td>1</td>\n",
" <td>Regular Play</td>\n",
" <td>217</td>\n",
" <td>Barcelona</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>[06385378-493b-4bd8-8731-f983c4ac28d8]</td>\n",
" <td>[105.3, 29.4]</td>\n",
" <td>5503.0</td>\n",
" <td>Lionel Andrés Messi Cuccittini</td>\n",
" <td>17.0</td>\n",
" <td>Right Wing</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 147 columns</p>\n",
"</div>"
],
"text/plain": [
" id ... half_end_early_video_end\n",
"0 fb785612-71d3-44df-aae4-da6e005756de ... NaN\n",
"1 2dfa84fe-3579-4705-8d27-44b8917907e1 ... NaN\n",
"2 c9d92f30-2159-4a5a-a5bf-9d1163e4b33f ... NaN\n",
"3 26b5d67b-5fce-4a5a-8b31-b879adbb61d3 ... NaN\n",
"4 20528610-c092-482c-8238-6b9679328680 ... NaN\n",
"\n",
"[5 rows x 147 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 4
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "WPZPi5M7ZI5o",
"colab_type": "code",
"colab": {}
},
"source": [
"\"\"\"Distance of shot location to centre of goal\"\"\"\n",
"def distFormula(coordinate):\n",
" a =(math.sqrt(((coordinate.location[0] - 120)**2) + ((coordinate.location[1] - 36)**2))) \n",
" b =(math.sqrt(((coordinate.location[0] - 120)**2) + ((coordinate.location[1] - 44)**2))) \n",
" return ((a+b)/2)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "ZRX43XViZshf",
"colab_type": "code",
"colab": {}
},
"source": [
"\"\"\" near x y (nx,ny) (120,44)and far x y (fx,fy) (120,36)\"\"\" \n",
"nx = 120\n",
"ny = 44\n",
"fx = 120\n",
"fy = 36\n",
"\n",
"goalpostLength = 8\n",
"def shot_angle(points):\n",
" len1 = (math.sqrt(((points.location[0] - nx)**2) + ((points.location[1] - ny)**2))) \n",
" len2 = (math.sqrt(((points.location[0] - fx)**2) + ((points.location[1] - fy)**2)))\n",
" ang = (len1**2 + len2**2 - goalpostLength**2)/(2 * len1 * len2)\n",
" if ang > 1:\n",
" ang = 1\n",
" elif ang < -1:\n",
" ang = -1 \n",
" angRad = math.acos(ang)\n",
" return( (angRad * 180)/math.pi) "
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "Skzv7m2GcOek",
"colab_type": "code",
"colab": {}
},
"source": [
"\"\"\"If shot was taken under Pressure?\"\"\"\n",
"def under_pressure(coordinate):\n",
" if coordinate['under_pressure'] == True:\n",
" return 1\n",
" return 0"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "VRBmlZBtdbCf",
"colab_type": "code",
"colab": {}
},
"source": [
"\"\"\"The Shot type Id\"\"\"\n",
"def shot_type(coordinate):\n",
" if coordinate['shot_type_id'] == 61:\n",
" return 1\n",
" if coordinate['shot_type_id'] == 62:\n",
" return 2\n",
" if coordinate['shot_type_id'] == 87:\n",
" return 3\n",
" if coordinate['shot_type_id'] == 88:\n",
" return 4\n",
" return 5"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "SfSB2laheYY4",
"colab_type": "code",
"colab": {}
},
"source": [
"\"\"\"The Shot Body part\"\"\"\n",
"def shot_body_part(coordinate):\n",
" if coordinate['shot_body_part_id'] == 37:\n",
" return 1\n",
" if coordinate['shot_body_part_id'] == 38:\n",
" return 2\n",
" if coordinate['shot_body_part_id'] == 70:\n",
" return 3\n",
" return 4"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "XshqSKelezC2",
"colab_type": "code",
"colab": {}
},
"source": [
"\"\"\"The Shot Technique Id\"\"\"\n",
"def shot_technique(coordinate):\n",
" if coordinate['shot_technique_id'] == 89:\n",
" return 1\n",
" if coordinate['shot_technique_id'] == 90:\n",
" return 2\n",
" if coordinate['shot_technique_id'] == 91:\n",
" return 3\n",
" if coordinate['shot_technique_id'] == 92:\n",
" return 4\n",
" if coordinate['shot_technique_id'] == 93:\n",
" return 5\n",
" if coordinate['shot_technique_id'] == 94:\n",
" return 6\n",
" return 7"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "7DLY4vXtffsL",
"colab_type": "code",
"colab": {}
},
"source": [
"\"\"\"If shot was taken first time?\"\"\"\n",
"def shot_first_time(coordinate):\n",
" if coordinate['shot_first_time'] == True:\n",
" return 1\n",
" return 0"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "7PkUfTrOwjmd",
"colab_type": "code",
"colab": {}
},
"source": [
"\"\"\" To Find if a point is inside the triangle\n",
"https://www.geeksforgeeks.org/check-whether-a-given-point-lies-inside-a-triangle-or-not/\"\"\"\n",
"def Triarea(a,b,c):\n",
"#return abs((x1*(y2-y3) + x2*(y3-y1)+ x3*(y1-y2))/2.0); \n",
" return abs((a[0] * (b[1] - c[1]) + b[0] * (c[1] - a[1]) + c[0] * (a[1] - b[1]))/2.0)\n",
"\n",
"def isInside(a,b,c,p):\n",
" A = Triarea(a,b,c)\n",
"\n",
" A1 = Triarea(a,b,p)\n",
"\n",
" A2 = Triarea(p,b,c)\n",
"\n",
" A3 = Triarea(a,p,c) \n",
" \n",
" if (round(A,2) == round((A1 + A2 + A3),2)):\n",
" return 1\n",
" return 0 "
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "U0pQQZPDf4oV",
"colab_type": "code",
"colab": {}
},
"source": [
"\"\"\"If shot was taken first time?\"\"\"\n",
"def shot_one_on_one(coordinate):\n",
" if coordinate['shot_one_on_one'] == True:\n",
" return 1\n",
" return 0"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "C30AcDZJ9DY1",
"colab_type": "code",
"colab": {}
},
"source": [
"def infronofShot(frame):\n",
" if str(type(frame['shot_freeze_frame'])) == '<class \\'float\\'>':\n",
" return 0\n",
" if not len(frame['shot_freeze_frame']):\n",
" return 0\n",
" #print(type(frame['shot_freeze_frame']),'\\n')\n",
" loc = pd.DataFrame(frame['shot_freeze_frame'])\n",
" \n",
" #loc = loc[['location']]\n",
" X = frame['location'][0]\n",
" Y = frame['location'][1]\n",
" countgoal = 0\n",
" \n",
" for i in range(len(loc)):\n",
" \n",
" if isInside((X,Y),(120,36),(120,44),(loc['location'].iloc[i][0],loc['location'].iloc[i][1])) == 1:\n",
" countgoal +=1\n",
" return countgoal "
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "J2Qd_aEHZaja",
"colab_type": "code",
"colab": {}
},
"source": [
"main_df['Distance'] = main_df.apply(distFormula,axis = 1)\n",
"main_df['Angle'] = main_df.apply(shot_angle,axis = 1)\n",
"main_df['UnderPressure'] = main_df.apply(under_pressure,axis = 1)\n",
"main_df['ShotType'] = main_df.apply(shot_type,axis = 1)\n",
"main_df['ShotBodyPart'] = main_df.apply(shot_body_part,axis = 1)\n",
"main_df['ShotTechnique'] = main_df.apply(shot_technique,axis = 1)\n",
"main_df['ShotFirstTime'] = main_df.apply(shot_first_time,axis = 1)\n",
"main_df['ShotOneonOne']= main_df.apply(shot_one_on_one,axis = 1)\n",
"main_df['InFrontofGoal'] = main_df.apply(infronofShot,axis = 1)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "VbP_YO_tg694",
"colab_type": "code",
"colab": {}
},
"source": [
"goals_lst = main_df[main_df['shot_outcome_id'] == 97].index.tolist()"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "e4X-RpdOguqH",
"colab_type": "code",
"colab": {}
},
"source": [
"#if shot is a goal \n",
"main_df['isGoal'] = False\n",
"goals_lst\n",
"main_df.loc[main_df.index.isin(goals_lst),'isGoal'] = True"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "5Y8BHzgGp2iS",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 401
},
"outputId": "2b549b10-f7a9-49d0-a290-361596e56c41"
},
"source": [
"import statsbombpitch as sb\n",
"sb.sb_pitch(\"#195905\",\"#faf0e6\",\"horizontal\",\"full\")\n",
"ilocv = 3477\n",
"plt.scatter(main_df.iloc[ilocv]['location'][0],main_df.iloc[ilocv]['location'][1],color=\"#ee3e32\",edgecolors=\"none\",zorder=10,alpha=1,s = 40 )\n",
"#plt.plt.plot((main_df.iloc[0]['location'][0],120),(main_df.iloc[0]['location'][1],44),color = 'black',zorder = 10)\n",
"#(main_df.iloc[1]['location'][1],main_df.iloc[1]['location'][0],120,zorder = 10)\n",
"#plt.plot((main_df.iloc[0]['location'][0],120),(main_df.iloc[0]['location'][1],44),color = 'black',zorder = 10)\n",
"tri = np.array([[main_df.iloc[ilocv]['location'][0],main_df.iloc[ilocv]['location'][1]],[120,36],[120,44]])\n",
"t1 = plt.Polygon(tri, color = 'blue',zorder = 8)\n",
"plt.gca().add_patch(t1)\n",
"loc = pd.DataFrame(main_df.iloc[ilocv]['shot_freeze_frame'])\n",
"for i in range(len(loc)):\n",
" plt.scatter(loc['location'].iloc[i][0],loc['location'].iloc[i][1],color=\"#ee3e32\",edgecolors=\"black\",zorder=10,alpha=1,s = 20 ) \n",
"plt.show()"
],
"execution_count": 233,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 748.8x489.6 with 1 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "w-w3CxaPylta",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"outputId": "0d4f68b2-291b-44e4-82a9-cec63d91df92"
},
"source": [
"sortxg[50:100]"
],
"execution_count": 237,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>location</th>\n",
" <th>Distance</th>\n",
" <th>Angle</th>\n",
" <th>UnderPressure</th>\n",
" <th>ShotType</th>\n",
" <th>ShotBodyPart</th>\n",
" <th>ShotTechnique</th>\n",
" <th>ShotFirstTime</th>\n",
" <th>InFrontofGoal</th>\n",
" <th>ShotOneonOne</th>\n",
" <th>xG</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>10082</th>\n",
" <td>[115.2, 43.6]</td>\n",
" <td>6.902760</td>\n",
" <td>62.487997</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.593055</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11940</th>\n",
" <td>[118.0, 45.0]</td>\n",
" <td>5.727806</td>\n",
" <td>50.906141</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.588634</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5946</th>\n",
" <td>[115.1, 37.6]</td>\n",
" <td>6.607503</td>\n",
" <td>70.644874</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0.588151</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4032</th>\n",
" <td>[114.3, 42.8]</td>\n",
" <td>7.348970</td>\n",
" <td>61.917732</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.582283</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10411</th>\n",
" <td>[116.3, 40.1]</td>\n",
" <td>5.449276</td>\n",
" <td>94.443109</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0.578671</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10059</th>\n",
" <td>[117.9, 44.7]</td>\n",
" <td>5.581727</td>\n",
" <td>57.994617</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.577080</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5721</th>\n",
" <td>[115.0, 40.0]</td>\n",
" <td>6.403124</td>\n",
" <td>77.319617</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.573219</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10216</th>\n",
" <td>[114.8, 38.0]</td>\n",
" <td>6.755564</td>\n",
" <td>70.123128</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0.563681</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4014</th>\n",
" <td>[112.3, 38.2]</td>\n",
" <td>8.824071</td>\n",
" <td>52.934164</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.561885</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8422</th>\n",
" <td>[113.1, 43.4]</td>\n",
" <td>8.521922</td>\n",
" <td>51.972274</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.557730</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6056</th>\n",
" <td>[114.0, 37.0]</td>\n",
" <td>7.651153</td>\n",
" <td>58.861028</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.552528</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1551</th>\n",
" <td>[114.4, 39.4]</td>\n",
" <td>6.899202</td>\n",
" <td>70.664392</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.549695</td>\n",
" </tr>\n",
" <tr>\n",
" <th>250</th>\n",
" <td>[113.1, 42.1]</td>\n",
" <td>8.183296</td>\n",
" <td>56.874096</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.548621</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3272</th>\n",
" <td>[113.6, 40.1]</td>\n",
" <td>7.547661</td>\n",
" <td>64.001725</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.542347</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9799</th>\n",
" <td>[113.2, 42.0]</td>\n",
" <td>8.078323</td>\n",
" <td>57.813206</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.538975</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10820</th>\n",
" <td>[113.6, 41.8]</td>\n",
" <td>7.702349</td>\n",
" <td>61.154851</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.533676</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5077</th>\n",
" <td>[114.1, 43.6]</td>\n",
" <td>7.767437</td>\n",
" <td>56.055770</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.528097</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12541</th>\n",
" <td>[113.0, 44.0]</td>\n",
" <td>8.815073</td>\n",
" <td>48.814075</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>7</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0.527048</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11843</th>\n",
" <td>[113.0, 38.0]</td>\n",
" <td>8.249827</td>\n",
" <td>56.546691</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.524932</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3227</th>\n",
" <td>[115.6, 41.8]</td>\n",
" <td>6.099730</td>\n",
" <td>79.380345</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.522069</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1710</th>\n",
" <td>[113.3, 39.1]</td>\n",
" <td>7.841507</td>\n",
" <td>61.008967</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.514230</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1796</th>\n",
" <td>[112.4, 39.7]</td>\n",
" <td>8.592467</td>\n",
" <td>55.459494</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.512211</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12751</th>\n",
" <td>[115.0, 42.0]</td>\n",
" <td>6.597707</td>\n",
" <td>71.995838</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.510614</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12635</th>\n",
" <td>[118.0, 36.0]</td>\n",
" <td>5.123106</td>\n",
" <td>75.963757</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.509163</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5094</th>\n",
" <td>[115.6, 43.6]</td>\n",
" <td>6.599972</td>\n",
" <td>65.125846</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.509059</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12870</th>\n",
" <td>[109.0, 41.0]</td>\n",
" <td>11.742400</td>\n",
" <td>39.699073</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.509021</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12363</th>\n",
" <td>[109.0, 41.0]</td>\n",
" <td>11.742400</td>\n",
" <td>39.699073</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.509021</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12622</th>\n",
" <td>[109.0, 41.0]</td>\n",
" <td>11.742400</td>\n",
" <td>39.699073</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.509021</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11356</th>\n",
" <td>[109.0, 41.0]</td>\n",
" <td>11.742400</td>\n",
" <td>39.699073</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.509021</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11390</th>\n",
" <td>[109.0, 41.0]</td>\n",
" <td>11.742400</td>\n",
" <td>39.699073</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.509021</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12918</th>\n",
" <td>[109.0, 41.0]</td>\n",
" <td>11.742400</td>\n",
" <td>39.699073</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.509021</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11495</th>\n",
" <td>[109.0, 41.0]</td>\n",
" <td>11.742400</td>\n",
" <td>39.699073</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.509021</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9319</th>\n",
" <td>[114.0, 42.8]</td>\n",
" <td>7.593725</td>\n",
" <td>59.886267</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.508912</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5479</th>\n",
" <td>[114.3, 42.5]</td>\n",
" <td>7.269647</td>\n",
" <td>63.495292</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0.503553</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9820</th>\n",
" <td>[116.5, 37.5]</td>\n",
" <td>5.595149</td>\n",
" <td>84.897835</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0.502442</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5385</th>\n",
" <td>[112.6, 42.2]</td>\n",
" <td>8.634894</td>\n",
" <td>53.628856</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.496973</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9100</th>\n",
" <td>[115.8, 44.3]</td>\n",
" <td>6.756425</td>\n",
" <td>59.073874</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0.495486</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1360</th>\n",
" <td>[113.7, 36.1]</td>\n",
" <td>8.202624</td>\n",
" <td>52.338128</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.493024</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3664</th>\n",
" <td>[116.4, 43.2]</td>\n",
" <td>5.868831</td>\n",
" <td>75.963757</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.491836</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8527</th>\n",
" <td>[115.0, 43.3]</td>\n",
" <td>6.948463</td>\n",
" <td>63.561138</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.491444</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10394</th>\n",
" <td>[112.4, 38.0]</td>\n",
" <td>8.770864</td>\n",
" <td>53.033726</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.490224</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3910</th>\n",
" <td>[112.6, 39.5]</td>\n",
" <td>8.423397</td>\n",
" <td>56.617007</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.486898</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4346</th>\n",
" <td>[108.3, 40.3]</td>\n",
" <td>12.368128</td>\n",
" <td>37.728461</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.484093</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11026</th>\n",
" <td>[108.2, 40.1]</td>\n",
" <td>12.459894</td>\n",
" <td>37.449331</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.480520</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3793</th>\n",
" <td>[112.3, 44.5]</td>\n",
" <td>9.592653</td>\n",
" <td>44.111835</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0.479089</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6938</th>\n",
" <td>[112.2, 42.0]</td>\n",
" <td>8.946530</td>\n",
" <td>51.949987</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.478999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7928</th>\n",
" <td>[113.3, 38.2]</td>\n",
" <td>7.956833</td>\n",
" <td>59.059829</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0.477739</td>\n",
" </tr>\n",
" <tr>\n",
" <th>554</th>\n",
" <td>[114.8, 36.7]</td>\n",
" <td>7.104802</td>\n",
" <td>62.203440</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.477342</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1305</th>\n",
" <td>[108.1, 40.0]</td>\n",
" <td>12.554282</td>\n",
" <td>37.158541</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.476817</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3704</th>\n",
" <td>[108.1, 40.1]</td>\n",
" <td>12.554640</td>\n",
" <td>37.156345</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.476794</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" location Distance ... ShotOneonOne xG\n",
"10082 [115.2, 43.6] 6.902760 ... 0 0.593055\n",
"11940 [118.0, 45.0] 5.727806 ... 0 0.588634\n",
"5946 [115.1, 37.6] 6.607503 ... 0 0.588151\n",
"4032 [114.3, 42.8] 7.348970 ... 0 0.582283\n",
"10411 [116.3, 40.1] 5.449276 ... 0 0.578671\n",
"10059 [117.9, 44.7] 5.581727 ... 0 0.577080\n",
"5721 [115.0, 40.0] 6.403124 ... 0 0.573219\n",
"10216 [114.8, 38.0] 6.755564 ... 1 0.563681\n",
"4014 [112.3, 38.2] 8.824071 ... 0 0.561885\n",
"8422 [113.1, 43.4] 8.521922 ... 0 0.557730\n",
"6056 [114.0, 37.0] 7.651153 ... 0 0.552528\n",
"1551 [114.4, 39.4] 6.899202 ... 0 0.549695\n",
"250 [113.1, 42.1] 8.183296 ... 0 0.548621\n",
"3272 [113.6, 40.1] 7.547661 ... 0 0.542347\n",
"9799 [113.2, 42.0] 8.078323 ... 0 0.538975\n",
"10820 [113.6, 41.8] 7.702349 ... 0 0.533676\n",
"5077 [114.1, 43.6] 7.767437 ... 0 0.528097\n",
"12541 [113.0, 44.0] 8.815073 ... 1 0.527048\n",
"11843 [113.0, 38.0] 8.249827 ... 0 0.524932\n",
"3227 [115.6, 41.8] 6.099730 ... 0 0.522069\n",
"1710 [113.3, 39.1] 7.841507 ... 0 0.514230\n",
"1796 [112.4, 39.7] 8.592467 ... 0 0.512211\n",
"12751 [115.0, 42.0] 6.597707 ... 0 0.510614\n",
"12635 [118.0, 36.0] 5.123106 ... 0 0.509163\n",
"5094 [115.6, 43.6] 6.599972 ... 0 0.509059\n",
"12870 [109.0, 41.0] 11.742400 ... 0 0.509021\n",
"12363 [109.0, 41.0] 11.742400 ... 0 0.509021\n",
"12622 [109.0, 41.0] 11.742400 ... 0 0.509021\n",
"11356 [109.0, 41.0] 11.742400 ... 0 0.509021\n",
"11390 [109.0, 41.0] 11.742400 ... 0 0.509021\n",
"12918 [109.0, 41.0] 11.742400 ... 0 0.509021\n",
"11495 [109.0, 41.0] 11.742400 ... 0 0.509021\n",
"9319 [114.0, 42.8] 7.593725 ... 0 0.508912\n",
"5479 [114.3, 42.5] 7.269647 ... 1 0.503553\n",
"9820 [116.5, 37.5] 5.595149 ... 0 0.502442\n",
"5385 [112.6, 42.2] 8.634894 ... 0 0.496973\n",
"9100 [115.8, 44.3] 6.756425 ... 0 0.495486\n",
"1360 [113.7, 36.1] 8.202624 ... 0 0.493024\n",
"3664 [116.4, 43.2] 5.868831 ... 0 0.491836\n",
"8527 [115.0, 43.3] 6.948463 ... 0 0.491444\n",
"10394 [112.4, 38.0] 8.770864 ... 0 0.490224\n",
"3910 [112.6, 39.5] 8.423397 ... 0 0.486898\n",
"4346 [108.3, 40.3] 12.368128 ... 0 0.484093\n",
"11026 [108.2, 40.1] 12.459894 ... 0 0.480520\n",
"3793 [112.3, 44.5] 9.592653 ... 1 0.479089\n",
"6938 [112.2, 42.0] 8.946530 ... 0 0.478999\n",
"7928 [113.3, 38.2] 7.956833 ... 0 0.477739\n",
"554 [114.8, 36.7] 7.104802 ... 0 0.477342\n",
"1305 [108.1, 40.0] 12.554282 ... 0 0.476817\n",
"3704 [108.1, 40.1] 12.554640 ... 0 0.476794\n",
"\n",
"[50 rows x 11 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 237
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "Ybc3gad1S2Nm",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"outputId": "afd2ff80-63d6-4f19-8063-c4e63998d027"
},
"source": [
"countgoal = 0\n",
"#isInside((X,Y),(120,36),(120,44),(loc['location'].iloc[i][0],loc['location'].iloc[i][1])) == 1:\n",
"for i in range(len(loc)):\n",
" if isInside((100.7,25.6),(120,36),(120,44),(loc['location'].iloc[i][0],loc['location'].iloc[i][1])) == 1:\n",
" countgoal +=1\n",
"countgoal "
],
"execution_count": 205,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"9"
]
},
"metadata": {
"tags": []
},
"execution_count": 205
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "Mp8Ut4YUBZUQ",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
},
"outputId": "cdcaa1bd-7e6c-47a2-f8eb-2142672d80bd"
},
"source": [
"%%time\n",
"main_df['InFrontofGoal'] = main_df.apply(infronofShot,axis = 1)"
],
"execution_count": 182,
"outputs": [
{
"output_type": "stream",
"text": [
"CPU times: user 16.9 s, sys: 39.6 ms, total: 17 s\n",
"Wall time: 16.9 s\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "ddhlIVCHbZ-_",
"colab_type": "code",
"outputId": "439c3763-a163-4885-c410-03a900095f0f",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 609
}
},
"source": [
"main_df[['location','Distance','Angle','UnderPressure','ShotType','ShotBodyPart','ShotTechnique','ShotFirstTime','ShotOneonOne','InFrontofGoal','isGoal']]"
],
"execution_count": 207,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>location</th>\n",
" <th>Distance</th>\n",
" <th>Angle</th>\n",
" <th>UnderPressure</th>\n",
" <th>ShotType</th>\n",
" <th>ShotBodyPart</th>\n",
" <th>ShotTechnique</th>\n",
" <th>ShotFirstTime</th>\n",
" <th>ShotOneonOne</th>\n",
" <th>InFrontofGoal</th>\n",
" <th>isGoal</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>[110.5, 36.2]</td>\n",
" <td>10.896986</td>\n",
" <td>40.593846</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>[114.2, 48.0]</td>\n",
" <td>10.186866</td>\n",
" <td>29.611685</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>[95.3, 48.3]</td>\n",
" <td>26.332306</td>\n",
" <td>16.596593</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>[103.3, 61.6]</td>\n",
" <td>27.413807</td>\n",
" <td>10.378789</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>[94.9, 55.2]</td>\n",
" <td>29.543437</td>\n",
" <td>13.366677</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12952</th>\n",
" <td>[111.0, 27.0]</td>\n",
" <td>15.981653</td>\n",
" <td>17.102729</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12953</th>\n",
" <td>[114.0, 33.0]</td>\n",
" <td>9.619084</td>\n",
" <td>34.824489</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12954</th>\n",
" <td>[107.0, 32.0]</td>\n",
" <td>15.646638</td>\n",
" <td>25.606661</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12955</th>\n",
" <td>[97.0, 22.0]</td>\n",
" <td>29.376742</td>\n",
" <td>12.398277</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12956</th>\n",
" <td>[109.0, 52.0]</td>\n",
" <td>16.508979</td>\n",
" <td>19.464104</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>12957 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
" location Distance Angle ... ShotOneonOne InFrontofGoal isGoal\n",
"0 [110.5, 36.2] 10.896986 40.593846 ... 0 1 False\n",
"1 [114.2, 48.0] 10.186866 29.611685 ... 0 2 False\n",
"2 [95.3, 48.3] 26.332306 16.596593 ... 0 4 False\n",
"3 [103.3, 61.6] 27.413807 10.378789 ... 0 1 False\n",
"4 [94.9, 55.2] 29.543437 13.366677 ... 0 4 False\n",
"... ... ... ... ... ... ... ...\n",
"12952 [111.0, 27.0] 15.981653 17.102729 ... 0 3 False\n",
"12953 [114.0, 33.0] 9.619084 34.824489 ... 0 1 True\n",
"12954 [107.0, 32.0] 15.646638 25.606661 ... 0 1 False\n",
"12955 [97.0, 22.0] 29.376742 12.398277 ... 0 1 False\n",
"12956 [109.0, 52.0] 16.508979 19.464104 ... 0 1 False\n",
"\n",
"[12957 rows x 11 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 207
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "54NSbs9R1HQD",
"colab_type": "text"
},
"source": [
"#xG Model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "KCl0-Opqhxx-",
"colab_type": "code",
"colab": {}
},
"source": [
"from sklearn.model_selection import train_test_split\n",
"from sklearn.linear_model import LogisticRegression\n",
"import xgboost as xgb\n",
"from sklearn import svm\n",
"from sklearn import linear_model"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "Q5_VKZrBhyRi",
"colab_type": "code",
"colab": {}
},
"source": [
"xgModel = main_df[['location','Distance','Angle','UnderPressure','ShotType','ShotBodyPart','ShotTechnique','ShotFirstTime','ShotOneonOne','InFrontofGoal','isGoal']]"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "WOLF5IqBh1Nx",
"colab_type": "code",
"colab": {}
},
"source": [
"X_train,X_test,y_train,y_test = train_test_split(xgModel[['location','Distance','Angle','UnderPressure','ShotType','ShotBodyPart','ShotTechnique','ShotFirstTime','InFrontofGoal','ShotOneonOne']],xgModel[['isGoal']],test_size = 0.2,shuffle = True)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "mJrKwMAy1Pdl",
"colab_type": "text"
},
"source": [
"**Logistic Regression** Model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "fwxMcSWQiCbw",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 71
},
"outputId": "e1df75a6-e814-4037-a0e3-6775e7761e8b"
},
"source": [
"clf = LogisticRegression(random_state=0,max_iter = 5000).fit(X_train[['Distance','Angle','UnderPressure','ShotType','ShotBodyPart','ShotTechnique','ShotFirstTime','ShotOneonOne','InFrontofGoal']], y_train)"
],
"execution_count": 214,
"outputs": [
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n"
],
"name": "stderr"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "v2sAXpKaiS7d",
"colab_type": "code",
"outputId": "f16daadf-0f9a-4b34-a5ca-f6e8b4eb7f94",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"#model weights\n",
"clf.coef_[0]"
],
"execution_count": 215,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([-0.05881247, 0.03193658, -0.45802499, 0.59881635, 0.21925344,\n",
" -0.00195693, 0.21331492, 0.50199851, -0.29032136])"
]
},
"metadata": {
"tags": []
},
"execution_count": 215
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "DBQ7Hrsm1WNv",
"colab_type": "text"
},
"source": [
"**SGD** Model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "02YCl85sicPO",
"colab_type": "code",
"colab": {}
},
"source": [
"xG = clf.predict_proba(X_test[['Distance','Angle','UnderPressure','ShotType','ShotBodyPart','ShotTechnique','ShotFirstTime','ShotOneonOne']])[:,1]"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "WmD0Au5iv0Lh",
"colab_type": "code",
"outputId": "d451e487-f5d5-4384-d0e7-c793da528d98",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 173
}
},
"source": [
"#SGD\n",
"sgdclf = linear_model.SGDClassifier(loss='log', alpha = 0.17)\n",
"sgdclf.fit(X_train[['Distance','Angle','UnderPressure','ShotType','ShotBodyPart','ShotTechnique','ShotFirstTime','ShotOneonOne','InFrontofGoal']], y_train)"
],
"execution_count": 239,
"outputs": [
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n"
],
"name": "stderr"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"SGDClassifier(alpha=0.17, average=False, class_weight=None,\n",
" early_stopping=False, epsilon=0.1, eta0=0.0, fit_intercept=True,\n",
" l1_ratio=0.15, learning_rate='optimal', loss='log', max_iter=1000,\n",
" n_iter_no_change=5, n_jobs=None, penalty='l2', power_t=0.5,\n",
" random_state=None, shuffle=True, tol=0.001,\n",
" validation_fraction=0.1, verbose=0, warm_start=False)"
]
},
"metadata": {
"tags": []
},
"execution_count": 239
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "xgnm32tEWJsS",
"colab_type": "text"
},
"source": [
"Xg Boost Model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "gXzsHLvQWLvm",
"colab_type": "code",
"outputId": "6c27f43d-ca87-4596-e349-2e934d3f7e33",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 224
}
},
"source": [
"xgb_model = xgb.XGBClassifier(objective='binary:logistic', max_depth=4, n_estimators=100)\n",
"xgb_model.fit(X_train[['Distance','Angle','UnderPressure','ShotType','ShotBodyPart','ShotTechnique','ShotFirstTime','ShotOneonOne','InFrontofGoal']], y_train)"
],
"execution_count": 245,
"outputs": [
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.6/dist-packages/sklearn/preprocessing/_label.py:235: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n",
"/usr/local/lib/python3.6/dist-packages/sklearn/preprocessing/_label.py:268: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n"
],
"name": "stderr"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n",
" colsample_bynode=1, colsample_bytree=1, gamma=0,\n",
" learning_rate=0.1, max_delta_step=0, max_depth=4,\n",
" min_child_weight=1, missing=None, n_estimators=100, n_jobs=1,\n",
" nthread=None, objective='binary:logistic', random_state=0,\n",
" reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n",
" silent=None, subsample=1, verbosity=1)"
]
},
"metadata": {
"tags": []
},
"execution_count": 245
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "LVID9Zsn1atX",
"colab_type": "text"
},
"source": [
"**Predict** Shot Probability"
]
},
{
"cell_type": "code",
"metadata": {
"id": "P8yo8gQev-q8",
"colab_type": "code",
"colab": {}
},
"source": [
"# change model here sgcclf(SGD) or clf(LR)\n",
"xG = xgb_model.predict_proba(X_test[['Distance','Angle','UnderPressure','ShotType','ShotBodyPart','ShotTechnique','ShotFirstTime','ShotOneonOne','InFrontofGoal']])[:,1]"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "xL2vLcVfihcb",
"colab_type": "code",
"colab": {}
},
"source": [
"X_test['xG'] = xG\n",
"#X_test.head()"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "q2BO-NLSijd5",
"colab_type": "code",
"outputId": "94151586-c063-449a-e5f6-46d7ea262272",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 609
}
},
"source": [
"sortxg = X_test.sort_values(by = ['xG'],ascending=False)\n",
"sortxg"
],
"execution_count": 248,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>location</th>\n",
" <th>Distance</th>\n",
" <th>Angle</th>\n",
" <th>UnderPressure</th>\n",
" <th>ShotType</th>\n",
" <th>ShotBodyPart</th>\n",
" <th>ShotTechnique</th>\n",
" <th>ShotFirstTime</th>\n",
" <th>InFrontofGoal</th>\n",
" <th>ShotOneonOne</th>\n",
" <th>xG</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>646</th>\n",
" <td>[118.8, 37.0]</td>\n",
" <td>4.332081</td>\n",
" <td>120.077993</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.979459</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10495</th>\n",
" <td>[119.3, 41.4]</td>\n",
" <td>4.068882</td>\n",
" <td>157.545469</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.979459</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2681</th>\n",
" <td>[119.1, 39.6]</td>\n",
" <td>4.100949</td>\n",
" <td>154.403626</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.979459</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5237</th>\n",
" <td>[118.7, 39.4]</td>\n",
" <td>4.210111</td>\n",
" <td>143.294745</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.969388</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7452</th>\n",
" <td>[117.7, 37.8]</td>\n",
" <td>4.766741</td>\n",
" <td>107.693813</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.967390</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>505</th>\n",
" <td>[58.1, 28.1]</td>\n",
" <td>63.155775</td>\n",
" <td>7.132821</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.004881</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11160</th>\n",
" <td>[61.8, 39.8]</td>\n",
" <td>58.337636</td>\n",
" <td>7.863251</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.004881</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3568</th>\n",
" <td>[63.0, 30.5]</td>\n",
" <td>57.920804</td>\n",
" <td>7.813054</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.004881</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5084</th>\n",
" <td>[87.5, 67.5]</td>\n",
" <td>42.683234</td>\n",
" <td>8.235003</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.004615</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6085</th>\n",
" <td>[58.9, 43.2]</td>\n",
" <td>61.313999</td>\n",
" <td>7.470866</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0.004594</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2592 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
" location Distance ... ShotOneonOne xG\n",
"646 [118.8, 37.0] 4.332081 ... 0 0.979459\n",
"10495 [119.3, 41.4] 4.068882 ... 0 0.979459\n",
"2681 [119.1, 39.6] 4.100949 ... 0 0.979459\n",
"5237 [118.7, 39.4] 4.210111 ... 0 0.969388\n",
"7452 [117.7, 37.8] 4.766741 ... 0 0.967390\n",
"... ... ... ... ... ...\n",
"505 [58.1, 28.1] 63.155775 ... 0 0.004881\n",
"11160 [61.8, 39.8] 58.337636 ... 0 0.004881\n",
"3568 [63.0, 30.5] 57.920804 ... 0 0.004881\n",
"5084 [87.5, 67.5] 42.683234 ... 0 0.004615\n",
"6085 [58.9, 43.2] 61.313999 ... 0 0.004594\n",
"\n",
"[2592 rows x 11 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 248
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "lrUnxsmxpvPM",
"colab_type": "code",
"outputId": "eb22ddf4-3d3e-48de-ecdc-e3a196669746",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 401
}
},
"source": [
"import statsbombpitch as sb\n",
"sb.sb_pitch(\"#195905\",\"#faf0e6\",\"horizontal\",\"full\")\n",
"plt.gca().invert_yaxis()\n",
"for i in range(len(sortxg)):\n",
" xe = sortxg.iloc[i]['location'][0]\n",
" ye = sortxg.iloc[i]['location'][1]\n",
" \n",
" if sortxg.iloc[i]['xG'] >= 0.75:\n",
" g = plt.scatter(xe,ye,color=\"#ee3e32\",edgecolors=\"none\",zorder=10,alpha=1,s = 40 )\n",
" elif sortxg.iloc[i]['xG'] < 0.75 and sortxg.iloc[i]['xG'] >=0.5:\n",
" o = plt.scatter(xe,ye,color=\"#f68838\",edgecolors=\"none\",zorder=8,alpha=0.75,s = 30 )\n",
" elif sortxg.iloc[i]['xG'] < 0.5 and sortxg.iloc[i]['xG'] >=0.25:\n",
" a = plt.scatter(xe,ye,color=\"#fbb021\",edgecolors=\"none\",zorder=6,alpha=0.5,s = 20 ) \n",
" else:\n",
" b = plt.scatter(xe,ye,color=\"#1b8a5a\",edgecolors=\"none\",zorder=4,alpha=0.25,s = 10 ) \n",
"plt.axis('off')\n",
"plt.legend((g,o,a,b),('>=0.75','>=0.5','>=0.25','<0.25'),scatterpoints=1,loc=2,title = 'xG Value',fontsize='small', fancybox=True)\n",
"#plt.title('xG SGD model')\n",
"plt.savefig('xgXGBmodelFreezeFrame.png')\n",
"plt.show()"
],
"execution_count": 249,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 748.8x489.6 with 1 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "DzQLtbmByqBa",
"colab_type": "code",
"outputId": "acf7c28d-56f8-4aa6-9862-04a340160cd3",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 401
}
},
"source": [
"import StatsbombPitch as sb\n",
"sb.sb_pitch(\"#195905\",\"#faf0e6\",\"vertical\",\"half\")\n",
"#plt.gca().invert_xaxis()\n",
"for i in range(len(sortxg)):\n",
" xe = sortxg.iloc[i]['location'][0]\n",
" ye = sortxg.iloc[i]['location'][1]\n",
" \n",
" if sortxg.iloc[i]['xG'] >= 0.75:\n",
" g = plt.scatter(ye,xe,color=\"#ee3e32\",edgecolors=\"none\",zorder=10,alpha=1,s = 40 )\n",
" elif sortxg.iloc[i]['xG'] < 0.75 and sortxg.iloc[i]['xG'] >=0.5:\n",
" o = plt.scatter(ye,xe,color=\"#f68838\",edgecolors=\"none\",zorder=8,alpha=0.75,s = 30 )\n",
" elif sortxg.iloc[i]['xG'] < 0.5 and sortxg.iloc[i]['xG'] >=0.25:\n",
" a = plt.scatter(ye,xe,color=\"#fbb021\",edgecolors=\"none\",zorder=6,alpha=0.5,s = 20 ) \n",
" else:\n",
" b = plt.scatter(ye,xe,color=\"#1b8a5a\",edgecolors=\"none\",zorder=4,alpha=0.25,s = 10 ) \n",
"plt.axis('off')\n",
"plt.legend((g,o,a,b),('>=0.75','>=0.5','>=0.25','<0.25'),scatterpoints=1,loc=3,title = 'xG Value',fontsize='small', fancybox=True,edgecolor = 'black',framealpha = 2\n",
" )\n",
"\n",
"\n",
"#ax = plt.subplot()\n",
"\n",
"#plt.savefig('MessiValverdeEraScatter.png')\n",
"plt.show()"
],
"execution_count": 0,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAlIAAAGACAYAAABmwYzKAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nOy9d5Rk2V3n+bn3PhM+0ldmZZbprrbVRralRg4kQUsIpJaEk8QuA4cdZs/ODCBgZoA9LKDh7O4wy8HszGjRMHip1SCMDsIISS1kaSPbkrpV1d3lMysrfYaP9969d/+4LyJ9VVZ1dRn1+5zTp7PCPBPxIu43fub7E9ZaMjIyMjIyMjIyLh55tQ8gIyMjIyMjI+N6JRNSGRkZGRkZGRmXSCakMjIyMjIyMjIukUxIZWRkZGRkZGRcIpmQysjIyMjIyMi4RDIhlZGRkZGRkZFxiXjnu3Pvu4JZYM8VOpaMjIyMjIyMjGuSmQ9EYrvbLxSRykRURkZGRkZGRsYOZKm9jIyMjIyMjIxL5LypvYyMjIz1vPNV7+T+e+6/2ofxnPPhxz7MA5994GofRkZGxnVAFpHKyMjYNfffcz+Hpw5f7cN4Tjk8dfh5IRYzMjIuD+J8s/b2vivY9s73/9T7uWv/Xc/ZQWVc2+T8HACduHOVj+Rbh+vlNS2GRQCa3eZVPpLnjuvlHK+Xa+Z6IntNn9987dTX+OHf/uEd79+p2PySUnuH9hyiGBav+S+ajOcGJdXVPoTrn/U/UcT185pqo6/2ITznXC/neL1cM9cT2Wv6/KUYFjm059AlPfeShNSJ+ROcmD/BO37zHZe004zrmw+++4MA2fv/LIiXLCZ2asofEPzZzz8IZK9pxu7JPoeXn+w1ff7Se+8vhazYPCPjKqBKYOsgPIEIrsw+TWRJ6hbhCbwKCLFtlPqSeGGhyJsHBslLyWfqNf5+deWCz/GtILCCpjSX7Th2S8VIGsJgLt9LkJGR8TwlE1IZGVcBGQiC4Su7iusG2ARsYrE5gQgvz3ZvDEN+bnxvX5gdCHMIBH+3urzt430r+PerE7ytNUjeSh4NGvzy4DSnvGjX+wyF4LuqAxwIQo502nyytspuEnKv6pT4D6sT3JjkmJcx7y3P8WBpadf7vVpYa8GCkJnyy8i41siEVEbGNYzVFtMB4Tvx9WwQPhCDECAuYynIK0sVRs4qhmcVKoGVEcN3jFd2FFI/WdvDu5rD/X+/LCrx3oWDfO/YUe5M8hSs5EtBi1js3AjzHyamuDWfB+AV5Qo35/K8d272vMe5Lwn4fxcPEKTNyqPG5/9YneSsF/PpXP1iT/uyYCKLjUHmdxZJVlviZYs14JVB5Z/ddXC+ffbvy4FQmWjLyNgNmZDKyLiGSVbhQEFx38E8QUnw8EKXx5fiS9qWVxZugZTPfpEsSck7hke5PZ/n1pmQfSf9/n17zkheXM9Dafvnvr05uOW2gzrk7+ZuYb92YbIFEfMzw6f4Ytja8tgbw7Avonq8slTmA4vzrOqd41Lf2xroi6jNx3M1hJSJLfGKizTJWOAP7PC4CGx6WqYDKr/943a1z2TdPiOBv+6tsHrdfV2BP3Tp+8nIeD6R+UhlZFzDeMLylpsLlANJQQleN5FjOLz4j621rj7KtIHLEGj4yfG9vLZSZdwPmJrxt9w/sepzKN6YOwyt4C2tAQp2++PviSiAEevzuwsHyW1TxBQI93wVw8iMZOyUIt+SeBeo+Qrt9vcHO9z+nGNZ6948T5mYDNIIonBRpMu2z80Bv3X3WbNzNDAjI2MjmZDKyLiGKQ1KwlAgQ5eGEQhK3sUv/KYNumXRbYvexrXEGotuWnTnwgvooFLckS+kTwQ/3v54xvSawBrRHn917mb+r+V920aF7JZVHfIofmVlcsvtRzptmksJtz8WMPW0z94THrd9MeCNK9XzHvdH86u7uj0vJa8tV3lDdYBB9dy1w8tA4JUFKu+K/3dCKEEwIglGBSr37ESf9Hfep2tCSO+rZmm9jIzdkqX2MjKuAiZOUygXqHtqAtOJZl/oPqorkeFs+xJ8juQOf6foBui2EzNCgAwFoYI3TRXYW1DMtjV/e7pNR1sia0msdREgAfWqoby6caMNoflqsJaW+1f1MQ7onavbxQ5hsld3yltus0DpKYGXbHzOz66O85H8Cqtq+9fnyaDDr1Wn+enaOCWriDF8sLjEhwtrHYYDSvGeqf0Me04E/uDQCP9x+jQnou6Ox/5sUIULCxZrXN2S8NkxmmitxUYgvAunbc+3T5UX8GyjXhkZzzMyIZXxvMFaC+bqFtFaY9FdQ7ICCHcsMhAutbNDfPivT7Y4POjjCcGTKzHRJbgFqJxACLDGFRJvOS679e9XjOU4WHJfEfuLHq/eE/KxmQ5NY/hEbYU3VF2BzfRNCQce98jH7gRiDO8ZmKa1ztbgxVHh4g+aHQSWhbu6W1f7EMndcYHPqJ3rnR4oOeF0UxJyRkUsbRJd31Ud6IsogJyUvG1omN+cnUEAA4GkrS0dfWVSX9Za4iWL1U4k+UNsew0nq2C6FiHdY7JC8YyMK0cmpDKeF/QXpMQV63qVK7/QmK7rvooW08iPL5C+JY40umURvsBau8XfKbFccoH5emS48zl7ZdBSICT99NHmFGLRX/v3Hy/Mc6Td5vZ8gTNRl0dH67yyXaZgJZ/K1VlQyYbnTquI2+KLD3X8Q36rH9Wru2XkDqGZaXVhC4WWNDwetLfcPqAU31YqM6g8ajrp2ykMKQ9PwPcdLLC34JFYyz+cafNULdmyje2w1mJagLyEjju7VmhuY4gWDWiBKm56WOKuKWvcf5ezK/PZYhOL7rhar2fbeZqRcS2SCamM5wVWOw8lcILmslRcXySm6zqj+rsWIEPoTKfHZy2ma1C5K78KCinwNmXRnlyJOVTxEAgslidWNoq5R5oNHmk2yAnBrcU8jwdtpuPthczvlxZ4TaeMvy7s1sGQO0+Z5j/lavxGdaulwf2t7dvbjqsOx/xLS8HtCwJ+eXI/Y57PuO8z6nsc73aJreWxZoPDgz57C+7r0hOC75jI8VStsatt64arT+txMWKq976YDqAspuOe665hh00sMgATO6Ei/WtLrMQrLqKmWxCMZF5YGd96ZEIq43mBUC4iYyKL3EVdynOBzIHouGJembP4FYnwoTtnXJpPcE21fzxdT/iz4y0m8q5Garq1tfbotlyen5uYJC/dgX+qtsr75s9tedxXwhY/MnqMH6uPslf7PBo2OSsj/vfaxmLyORHzU8MnWVAJM972UTi1Q5fdp3O7Ezbb8ZaBIfJSUjeac3HMsO9Rkor3L87zkZUl7h7aaD9/Jd8mVRCogku5JtpZGKi86HfZRUuu3k7lXSH5NU3WDJjxLUgmpDKeFwjR8+m5eguNDATh2Nb9F29RyFyaVguuoZwMMNPSzGwjoHr82OhYX0QBfHulymcbNZ5ob02dPR60effwqQ23WQE/1hhlj/b557DBr1fPXjCq9PeFFe7rbOzQM1j+tnDhsTQ7MeCtfRUu6YQlnfDFRoOzccT9g0M83myw0NWMhAqL5XNzu498uTSce3+3q0/bLUL0vJ0EJnFpamvAdCwyFP2I67WGVxWYTs/G4RoXehkZl0AmpDIyrjJeQSIvMG+v15WF5JpK3UwFWzvx9gXhtkJqOx4oLfHARY5o+cd8jf9WPsePNUbJW8mq0PxmdZZvpHVPgRC8bXCIV5UrCASPNes8sLhAZHcOhzzWbHA4X8DvuqCJCeHuYoGXlJyr6NsHh/kvZ8/yCdukmRhWI4sA3jiV55aKRy22fOR0i/nOWoG9idLOzHBr2vTZYiPcgQpnWyB9gdrBAPVqI32B3Go1lpHxLUMmpDIyrgP6dTYC/MHLI6assSRpg5tXurRowdFOm1tyG4vIj5xHRAVCUFaKxcSFT0Y9j+8dGGLE9/lys8HHa9t7PW3mv1bm+KPSAnt1wCnVpSOdSDoYhPzK5D7uLrhq7IbRDHquzusPF+bwheC7q4Pcns9zOuryN8vL1I3ma4tNBk/AgZYThjOVmKXDkKQCVwrBWweH+YUzJ/vHcNegz21VpxAGAsF9k3ne/4wz6TLd1CWcdKzLZU4nyxAnooBgRFzWIm4TW3TDdQmq0vmHW1trQTsxl5HxfCUTUhkZVxmTpO3t51mL+mkby7Yu2ErAS0YCKr7k6GrMqaZLx1lr0S234MrCxkVRt1xaCFzH3m6iJt/WKfFva3u4OQl5wu/wp3qB4kHJZBASGcNfLC/u6Ln0nZUq7xgeJS8l01GX9507x89M7KWaptVeWCgy6vk8sLSw5bkFKXlVuUJFKR5t1DkVRTSk4ajsbHjcu0ZGmQjWwnslqagoxb2lMn+4MMf/OjbOvSV3oncXirygUOTnT5/kd1cOcqC7Fl3bW/MpHtUcv3MtXzbgbUy75teJBxNbQu3EqZAb02zPRcpNKJcqtDjBsxnddteUKlx8cbdupNG0yKWjdxpuvb4TVubAz0w8M56nZEIqI+MqkdQspmPRXUCntcPpQrwZVQIawhkubpMGvG8y34+O3DHg8+DxFrNtjW6CbqaREeGKlnusb5HfTbv8bVGO9y4e6HfevTQqcse5PG+3T9HOGepa09khfTbu+/zoyFhfyE0GIb8wOUUura8aDiV5JfjR/DCfaC0xty5FVpCSX5vazx7fnfj9A0P89rmzfKG5tbh8XxCQbDqGUAjqWlMViu9ZrTJwTGGUZXHcMDUc8p7BKQ5Nby1eqixJVAw9g/ZHGhv3d3Q14SXDFt+6eXhfOROhmy4CJfMgE1cQvtmq4GKx2mKijTVGumP7tgi6wQaXchNZklpqh6AF/vkN37fQvxYEcL7rYl0nrI2uTidsRsa1QCakMjKuArpr6M5ZhHILnzUWrOsq3G4MiPQFcuus3z4HSmsrnhSC/SXXabcd1jhjUpUXbtG05/eY6vEDraEN9gUAeSt5W3OQ3/a2duqt57ZcfkuKaNz3CYSg4ik8BS2r8YRLkf3pM2tzbF5VrvRFVO/83j44tK2QeqLdpqo8hj1LkO6vaQx/ubzILy7tZV9rrVinuqg4c3NMZWB7pWOB6bhLQSoeaTT4wOL8hvuXI8P7n2kw5SuWlgwnVpN+Ck/Iixcw2x6Ddd5jPUPOYHgXTujWolvuOb4HFyNwrLGYdM6eVwF5vpSdApkT2K697KnLjIzriUxIZWRcBXrz7kyXNEokQLrb1SV0di10DPuKcsO/IY2GCOcPLvPOcyhetljj6qJUcfcL4IDZPjyx/vacELymUmVUKOIYlBI8kbRokDAYSAyWemwxFhSCAc8jlAKFwBeSR80iuU21WnuNz+A5SeJb6oOuTqystv/q+pOFOYY8DwEUleTJdpv3npslahne1NqqbEZOKr45EdMpW3L1jfv9dFjnZ8+e3PKc9azGltU4QRuLKm6M+O1EqOBlIyE5JXh8KeJc5zxW9dZ15sGa15gQbuaeUE7sbSkytwKh7CUFiEwbbJqZtZGA81yLQvTEYiaiMp7fZEIqI+M5whqL6boZaZt/2UtPoEoWYQXeIIhUA11q0e7fn2nz2okcZV/yzdWYY3WXcxFC4K0LuOjYYiLbL17P75e7LjL/VK7OG9tbzTA/lXMV64EQvGdqP5NByH4voKgU052IhtAshU3mZYuDokhOWc62NB1rON7tMuZ5VAJFbA2ztsPjS2umnj/QHOLd03vw0sW6XTA8c1fMw+3tx8CsaM2vTp/m9XGZt9WGmDSK+3IVnvTa27qh5yJJzgrECyXmaxaZOih8LqzzS4NndvW6wMUVk79tX4Ex6VTQzfs83n+iyWq8fUp0vSGnzG8q/FZOwmxOBYs0UrSbWY5b9udt/3dGRsbOZB+VjIzniGQ1LdoVEAxv7IpTZRCBRHggPWfMid1Y69LfTsNZH6jizim4ZmL5yOkLWw7I0NXNWGGRvouIjQ9JXjuRI5CCLy1GWxzMe3wkv8K9nRL3t12O0WD5YHGJf8rX+c5ylXdP7GUqCKnrhEJaaDMa+HS15nZV5m/NWZ6xDUp4vO/sCr8ycQAhBLNJzJJJkAI+Ntfm0WUnpIbbil9cmeiLKIB8S2KOGh4szG89wJTXtsv81tKBvnB6UVTksaBBWxjydmNq8smgTSIk9cBQeJmk2zLMJzG/OjvDUnwJw6E3oVu2L4JUXhBI2BMoTKoVPSMYLyhWVzdWpJuuRTddPZwqpsOIL/Btvf468QeFc9GXLvq424JzGQr8Qc6b7tVti2m7a+liIpoZGd+qZEIqI+M5wqa1JliIGwbTctEFryTT9Iy7O1rVmE66WG6qI7KJ7ReL2xoEo2v3W5125HkQFgTaXtg4WkhBMAZJzXUJCh/u31+g7DuBcd9kjoWO3lDs3cMI+MWhM/yPeJ6b4hxPBm1OeREvKxb5v/cfJBCCUAhynk8CdI3BSzvYinjcJaqcti2eTloc70Q80mzwuoEKQ4FENqG9oBELAuE7o857akWCbTzEb1wJeJEq8ljY3HIfwE/Ux7ZEn+6JSszKiLxdq7VqYXjf0Bz/gnHORBGBEFQDj2Kg2BeEO4676dUfqeL5BYqzl3DviEk72yIjqGlDWUisBatgcZvXOqm7fdjIYloCm0aX/B3q5LZeJ5I47coUnsUfvAgxdYEoVlJ3F5qJU7f+zGQz43lOJqQyrjtM5BYZmTu/x83VxisLdBOsZ4hmQDcMHaB4u8UvrNUVtY9bTGIhAd3RG2ftSZf2s2Zr2i+pudfidQdy3HNDSAL843SboxcYpqtyqUGigNATfREFIBAMhLIvpPb6ATflcjzT6fSFxTN+l2f8rusma8M7p0aRgLYWm9Zj+UKghaBmEvYHOYy27BUFJmyBz83NoC2899xZDg5B9ekyw08HDOHxX7mBo0GbHx0+zpLSsM2plKziDxdu5Ei+za+Mz/B41Npw/z69vbvpuAmok/CAXGKZhL+RKyyR8B3dAW7NFTgYhn3Z9lPjE5w61WVmk5jSnTVxZM32BeXDoeRAyWO5qzmyFLtCcbV2rf7V6TbfvickkIKvzEYsdNeEVK9Dz+I8vmwCIjR4Bemue7vDNb/pOjGRJZozrmuw5I4V4aJjQj274cHSE5jYNUpcSyONMjKuFtnHIOO6wsTO6DCpWfT2ZTJXFN2xtE8bOtNmwyBZ6EUQBF5RuOhCul6a1qaNCPBsk5xZItj000ZIgT8k8AcE3uZFW8D+iuLF487ox5eCN0zl2U3gwfkQCSIDZ1praqWrLTOpB9WbBwb5z/sP8q/Gxvn1/Qd5++DQhm303oc4WjtvnRZDi/TvklR4QnCy22W+Y1joGl5XcmGVBJitddjzdIhYF0G6Jcrzc+09PDrU4KjaOV15azvPb3CAnx3f27+t4gu+md/5OWU8pmXEf5fzzIoYBPzG7Awda5BAICVCwK25PO+Z3Lf1dVv/2hpXuO+66txrsCcnedehIt8+nuOtB4q88tYQf8BdBz1WIsOHT7f585MtnlonensdeknNYmOLCKzrnFMSrPNrSmrrIp3rj2vTdWI6aRoXd93pGkTnLPGqIV62W67Vi8EboH9O1/IPmYyMK0UmpDKuLwz9/JW9hBIWq11EQbc2LiT2PONDwKVzktragtkjXnYplaTuFqntkFKS2+8WoHDEjYRZz8vuCZjUn2fcfoEfub1KflOqRCiBDMWW1IxXhnxJonJraRtPCC62Xv3DJ1t8fq7DFxa6fPB4k0ZiKUnJ9w+NbHjcWweHGVDromXp6f7+iXMk1hJKiZeKqMgaOtZwLomd+/a6eXxFubaN+MT2QfFXdEogBf9y9AR/WViiJbZ/s8tLkhcXS7yoUORgyeNf3Fxi+gU1Wv7OF8dATqGKTnQIKVhMEr7eahFbS2IMHgJPCG7O5bklt7FtTYYCryJQJQGpdYWJLDrVbrdUfbx14uKOoWDb926n660ntpECL+8aAbwBkHlXT2c6LqrUe7BY5/a5/jqRoSs4DwYFKnARJN2y/QifPU+j4IVw2xfXVUqv9xndToRmZDxbMiGVcVXofbFf7BebDAWqKC55fllST0VRfe1XuW5bonlLtGi2PR4TpeKrbUlqm47HT6MUEsR50iV+SVG8SZGbUls6vF51sIBUFiFhIJDcObi7wWRCCaatZjFZWxW/vhwR7bBIWuPOwUQbzzEy8Mh8xGfOdVlK00yjvk9RSg4GIbfn8hwMQopSMuqtHZtXEQwUPN6wb5C52BWod4yhawxdYwmFJDIWC31PJ4DPN9ZCiUd2qENa9pwQWlAJvzQ4ze9UtvepSgJ3LuO+z71jAZ4QrJQSPvSqGR6vbvWZAvhkoY5X2jhW5bFmnbyU5KTET2u9Ckqy19+aJlR5F2VcP6anVwjeSDa+to1tuvHiVUs0tz5FmH4WEveaylDgVyX+iEAVXXQpqRsnvoTb161Vj6nGQ0zVP8HrJrZ6FMjQDTiWBcDvHbfrLlQF8ayGJ19v6I4ladj0c3+1jybjW5GsRirjimO1JVl29R6y05tov3u80rP4JbzuqVa7WivdcsWzNgEbs3Ukhtjhb3DWBX6abtGCpGZdR942KQ8hxLZO0XpTdEJfQFuaxLpCcSWIDTx4rMnBkkfXWE42do7EJPV0JMwF5vVNFRSahAk/IC/dHJK8kEz4AafXjX+RoeB/OzDOi4slmtbQMU6EtbQmTCNQkTWc6nb4ZqdDIAWPNhp8aN0ImE/ka8zUI/YmGwXLe8M5AKqBYCCQfIxV/mV9jGGz9pVlhWV+UmOt5evtFvfadfeFhr8+PMvyV8b49rZrhexi+M3qLM/4W0fYfLK2StsYvDTiFluLuoA/ksqLvoDqvZZfXYrYk5McqvisRIaPzWxMM1pt18bytC1eWZCsOoNWjGsE8AfWft/aCGxsEAon3nICP53rJ9KQ7AuGAp6qxZzujQUy7rqO5tPOP98S7pFIX26ps7M6/Rx+C8/KW/9RzDKRGc8FmZDKuPJY6GkHFwG6ct9uXhlMWiyb1IGGRQZpUa9yoqgXHVAFV7grfYE/kAot4aJSMu8WT10XmC4kDVDF3twxse0Yl5345NkOPy48pE0420742nLUN17cjIuKOTGkCoakJohCOGp2MdCtb+yYnkOYdp6t28+b9+W5qeJTxadjE5TxCIQkMoaz3Yh9QchT3bX5di/MFbGRJZGWmtJUlKL3jsbWci6J+dOF+Q1RqPXcMuTxyQPnuOfYIBPLOY4T8XuleT6Rq3NzxeNNU3mkEDQSw7+2x/ixpT28OC5gClA/aDlXTHhwfoHTUUQ8q3nbAcVwKDlY9rDAN165xB8fmSdoKR73W6wozd2DPgdKHgtdwyPzXWcOKgTHux2mgpC8lCTpsccXSPluFqPGwj9Md2DavUY5JVBinTiWrnbORBYZCqyxxHVDsgrCM4hAEq7LqJrEXafO1dztTwmQac1d760L1qUOkxUX8e3OWWQIQgsnvDeJJRO7mizsczNY+VpBhml9oXaf24yMy00mpDKuOMJLTQYjduUEfVn3LV26xNbAKTq3OHkVQDix1E+5JGvRMhkKrLJEi+55JnbjOmyauhESMKmFwS7m1q3nZEMzU3oNysY8eOwPSDqWZMViE0swCjJcF6HoWTxZ6MzgVm5A5gxecedMvYldG7wAbNdZEujEIpRApYvLnpzkporLA3XQKAVz9YjhriQpQSGEJZ1s2GZBCCbLPpE1rHRjKkqBgZZIMNLQLrQ4pjdX169x73BIPdE8dNMCQsLna12+sODSfS8fDZGpUih5koFx+Blxqv/c/Iqku2T6M5xn25rfO1rnrfvztLRlNCfZkxcsHTQ8cMwJucMDPq/f6074JiCQ8KnZLpG1fLZR596Sq3cwQFNrvtza3mLhQgjge1NRGhnL351uc7yROIPUAQvG1RglDYsgFe4hiHW6zZdw12SIGLN8bSFCW/dadGPLl093+YHU7mK+oznVdO+LNRYTu2uHxGKAYFBsm3a2Mf16QxOff6ze9c52Y5cyMi4XmZDKuCq4Wo2rt3+Zd4uHEK5epFcMbEU6WmO7QJmgf18viqOKAt2y+MNrYzsupQjXCp9E+FhAdmGfUnS0ZW5eE+5dG2S84biDdYXH56l2tHot8iB953QeLxvnuu65FBXA+vKeLobOUzE3Hs8hjMBKizikGS0K5hdcPdcvTU2yN+9TVk58FaWmFWsW4piBgksJ3qEqvH5vnQeONdlXUMQWZlqaw/k8bxkY4sVByCxtnkoaICAxcCjM8dbBIe4J8qyIDkdtHZseX8V3nYlVX/JULeZTsxvTdLGBWmy5sewxmtpI+AL+7nSL1dgyWVD9OjghBZMFD3Db+O9zs6zqhLvzRc4lMX++uEDLGHTb1dfIQOCVd/fe3lr1OVTysMYSSMF9kzl+94ir2Vqf4hXCCWV/wLpoU2pwKYDvO1hgPFCYLrxgMuSBmYZ7jwR8/ESHn869FEnCg8f/gDhVk70fCvEiqAH3fvtDW4vdwdmHyK6Lil3KZ9EkTphfqhv/ZnTTojtu1mRm9JlxPZEJqYznJdIX2w6AlV6axou3pgGEWndfWqzbK969WHpdW5vTd76E77uzyHDslNGjC10ejdYKstcft1cRvKwYMl5VzGjDFxe3L9x2PfDpn8bilQTxikDmLKEVBBa6Aha7hi8sdHnpSMjUQo59z6y9AMIIhp8KeeOBCl9dmucFhQJ354oIz9IWMRhBYi1n2hH51JdKCPCRBBLevj/PpO+BgLMty/eEE3hCIBO4KzeA0oJ/aq0wUzP8p337CaREJXCrV8FH8lB7iVZT8H8emiTvCY7bBuVhyULH8I1NTuwPz3V5541uLk5XW861DQfKHo8vxUwvJ9wWOOGn8paz6wY7d6zljxfmgTXX9Im84oVVn0hbPnemQzuxuxIOnl7r5JOhxd/Bk0IW0k7Litjgi3bvWMh3jOdoa8uZhmakoBhf9jjT0m5szCBEwTBI+iKqv++ScAad56Trztsh1CRkz+Dz4q9f3bEkq2m9XXV3Q6/PhzWuIBycQ7vM785A1Bq7a6PRjIznikxIZWRsQgYCdqhxOt99u8XELnWHdZYI67vHbih7TFQ8TOLSPd9WzfHFozHbNTe+ekxv9cMAACAASURBVDLPPSOuMv4mXB3OV5a2iinhudTloJTcPuHTtpYvrUTcMxLyqv0hKi94dCHi83NdPnOuyxcXI35xYfuWyNsWi8A8Y55PJZAoCUoCnqXW0jSNxVrn3K0EnLRNTjUS7iwGFKVgICd5eb6MaAmMha6Gs21NkgT8+ckWb6oO9q0SIgNnWxpsQKOu+O0b91PxJdpaDiZFPmnOUQ22huJWY8unZjvckAu4k0HeQMgNA13e2znHI2cbqA4cqHosrxgeXt1BfAIlT/D2gwVU5Kw2JisefzLduKB7PMCRhYQXlTQDOQUaHl3aWuAOTjhtjgbdUvV45VhINZAMCmfF8HQtpr6uO1P62zcu9LcrBV41Fev2/O7rfZPOixBD61PMJnb1ds8GIQXCc9e88HYnopKa60KVofO1ysi4WmRCKiPjCjMkJOWqYKau6XZArhNmvbVSegI8iI3tiygT2Q2pw/H8xpV0b0HxlSX3ty9hX9Gj5LnRMcUR+PbxPImFG0WRoT05ckpwLKpTLmpeOhIwVVT85YkWrcTSZHsPhQWjER58PWkRBoJIW2ILxlgeb7T4nbOzfP/oCKOxzwnT5kOLC0gpeMVQyO0DAQLYJxRSKpqxRSeCcT/Akuc/7zvIQ6vLG/ZngQHp8Yvj+wmFJDEaTwnyUnJYlZB7NS8e9vn8XMSX1kXkPnK6zf+4eZy9fkhXw6Dn8ZPje/k3jWc4UU8YDUJO2mRLh6S11nVuKhgpeQRSYHMWNIwVJe/IFan4kjNNzUen2yQ7qKrIt7z/aJOpkkc3tJzbHDY6DxN5hbZwdDXhhrKHD/zj6Tar0YUlXM+qo5fGFVJsiKya2HV8opwY0k3bn/vnD7rztto1XZzPbFPlwcbCpeOEuy57KeJLxR8UfSF1Iax1IgrcXMKLmSeYkXG5yYRUxjWLNalvzrdAz7LpWnQH7prwuW9/DtMQtCLDn802WO92dKyecGQ15taqj7aWj8+4Iqik4Yw/hQB/yEWZZtuafcW1j/BMy6WpAgk/dLDInWWfQwMeucD5OWkDzZWAG5IKInBdX1OFHGfVMh1ibqn43DMa8s9zXf66sMw7msMbBgZrLA8WlyiFChVYzhZWuYUqnpacTjr8f8fP8lTc5ddmz2CtS3v2aopq1iIV5D1BQ3QYbOfJa8lYLgQriKzh9ZUqg57HYhIznPpV7fF8ImvJCYmHxDeSJjGehJtKPvkgpJ1YBgLFTEszm6bqQiRDMsBa93qM5RRRU/M/T4zw9tFBAiHRxvKH03P80dJifxFOaul8OgkLQUKU1jihYCyvMMLNvbu5JFgsBnxuvovKuwHBcd0JCq/kCsl1wfJMPUG0nXXB+agGgleO5fAkLKdGYCuR4Ytnuzw+E/HV45GrdfIEJnG2Bmi2RKV00zVMAHhVsaHIWjdd+sx0nRDpDa3u1QjaxPlbmQhUWRCObjxm3XHPVXkXRfUqrukCC7phn7WQEnJjt6tNLEkTpLd1OHKvttF07LaGpxkZV5JMSGVck+iOa/PvC4fryEV5M9Za4lUXJXhxOXDt6MpSzAvurIY8XHchgcNTh/nguz8IgDRdrFC8Iv15bhP69gXCwxWXW0MlOkaga3S9IV7uHwAhKMQzDDW/RiU6jmcaeHSIZQlhDRKFiX0sCisUvq5TKVdp76myz5/gNf5elvJ3ATD9+DcZ/7uHCBeW6Q4PMH/fK3lvdZVibRYpu8RDIaIYY03CoDfBL7/2DW7eW6/sSLjIBkApOsFQ+wkCs0qYLJOM5SmfbiAbHawUhEIRIHl1rsDxF76OoB4h44Tq4jEQAr+7gh+5DjrfC7CeQIwqBsIisSxw576QV3/ba1jO3wlAvnuG0a/9OUK7F62CoFId4y4RofSafcO/H5zkzXe+C513NVXrO9mED4FZoRydwCIJTB1fO9lrDbxJTbAY3u18xGI3mBhcmkuoHd6zDRdGer8wTLQ+i2dcUZURipp/kNDUiG2Rb/Nu4ieE6m+jd4yH9x/mG6eeIJo3yBJ4eQnKpoOKBXLTt7tJ0uHGrdQ/KnSF6dIXyLwAZUlSVW9XLeHoukM1qe2Gdd5WwahwJrT9CNbl/3wm9dQ5HvdebJ4P6FcFtpxFojKuPpmQyrgmMR36flMmot+ify1gbeqKblLPqF18kQvhziVJ3al7BkA9n6IPP/Zht20NGDAy3LDwCpl6b/U6B427sRbetO7ADLlkgSBZdbPZXDgPrMCIgETkCEUDaWKMACMCIlkh8TzacpR8cg5pI5Tt0PAmKd4wT+Nf385ZO4Xvtdlz6nH85RaxKiGThMJsndaeUbrlQaJgxC30vY5HC5XaSUbnHkeahMXhW6kPHKAYzSBtTCcYxi91sK3eCYFAA5Zqchw8xfTgqynU58l35hBCoz0fDOhcgB5VBGGEMh0CUyeWlnJ0iliWiFWJwNaIB32CuVQ0SUmzPEZl9RQqihFagxDEgSLfXqaRCqmeMOi9zpEaYDH/QgCK0RmG9Dewxg0Bbgbj/TrtDXZTO2XgzLr3Dye0CvEMg9ETVJNjdLxhEllCWk3sVah7N4FZdzy960FAmCyx9MTvsnDkq7wwH/DYmS7yBgPW1RohLdaIDWXkqgA2EojAOpFlnEN7z0C2NwjcxtaNwNnhGu5tVEiB8F1USgTPgR/cuvPdadOZiMq4FsiEVMY1icw5ASXkxhqiZ4NuuS/9XmqiRy9VIryNKRg3TmXr45O6JTrnhJQ/CMHY+b/MhXDdUfGK5aHTHb5voEguFMw0NY83I0DwwGcf4AOf+gDRQi8cAuHY9p4G8bJ1I0OMIJwAFUoE8NYDBQ6W3Ee67AuEhlsGfJSC5fY0XzzT5dZCgZeHIwgJxsDJWsz/c+IUL7nBZ9+gRz12vkZTvsfxlQShYHJQUYstrzcTKAQdbYliwcFcgGgsI6Xm0eYyv3XqN6jFlteMh9wS5nlbYQ/tVDDK6a/y0HKNrrV4vsardgkk3G/3E6CQApSAmtcl+PpXaCcWXXuYT7c7vGF0CJNuZ9XGvL9+isqK5PCgz/6iYjUynGvPYnmGrv4bjtU1JSl5QzBGoH08BKfjDu98+A/4m5sPszcIUL3jilb4tQ/9Mg83t/pFVX1Bx1i668ziD/iKYSs5vRpzpm7wRwTSEyRtg1mASlESD1i0FGuF3J5LufVq3Hp2BLlVy4/fXUYKwUv2BYRK8KXFiFZi+KOjf0DPpF6n8/VUPo3QxJZ/+5Iq+VAQr1peeyjHmVrCCsZZc/S6CjcJOukLglFXhG4TJ36EWkudCyXITbrap83F471OQRutFZbbJD0/CaYJnMdC4VLS9F4ZjO/c43dy4c/IuBbIhFTGNYnKuS/zy1UfZZN1s81iCEbWCaaaK8IFNztPBiJ1/04f30tl9LYVraWvTETfhdzEqfAKt3rrWO3+m17R/LdH6+SLgnactnmnDx0vKm4oedTahseXY1dEm7ClFTxpGeIVi1CWZFWgxmA0J/siCqAeWz54vMH8qkYkILqWN04VePNN4Ic1dCNgtaP5L8/M8thSh4kpyUDsCm48BMXe8RsIlSDQ0DQJFXyUhPHAJzEQWUtk4BXhIAsHO8xEEeN5j5fKMoOBopUYEgN7/IB3jo5QI0YJwYKOeCiZ4y84zc3JAPvDHEmuw5AuIBH4EpCCVw4N0LAJARKDxUqD7Xos2JgHnolQWN58oEg1UOS0x6gXojptikkIiaKuNZEGnSh+YWIKhTO9tLjRKNpafn58in935mTfsV0KuH+/E6XaWj463ebIqsvbHW8nHF1yKS5VcteCjixDFcn33+2Oo5EY/uJEi6Wu6XfkJelA617EEQnVYYWXCoUnV2L2FT1O1WI+/s0OizWDV3Z1QL2UWrTgRFQhLwmMSy+qoosyDU9JagZE2Ym483XhyUCQRJZk0aX4vIpFFYWrO/JFfzbfluelDRBrN+wutdfvrvMF3uD2jv3bIeTV9ZrLyNgtmZDKuGa50Beu1RaXxbJ4VXH+eWFplssJpk2PU0DMlvSJkG6x6t2m267gG0CVnfO5N5imRcza/EDTXhNqSc0NCRYB/bRXElnq6cBkZQReybmK/9CNRbcrC+OLir//mquZkbHzr1o7cdsvKO7Vjq0fVGy6FqMtK0ua5qpzub694nNgxCf0BCbQ2IEWK8sJDV8jFBypJbxkJOCWqk+gBLO1BCFdbUonthwqKmLTImhXibsCJQQtbYiVi4KEUvIGfwwdWE6YFt107p4UAk9CaCUaGMR17hkBY4R0rOFIPaEonev3kHT31SKD1IKKVFgp6WKIhcGXgheUCnzT1kl0zNPnNN81ZhjXefZGFQIpeKkoYKWkYzRLXUNgJQfDHMPKZ1C50TGRMfhC4EvBoXye9918A1/urvDrz8xStILJWJLULaoIr5/Ic2S1jrWWqZziDffmyXmCL5yN+OzTTny94mCeG8oeUdviacG/O1zmTMdwrJ7w0ek2sugEu8yviexFbVjCMKIUkYHPzXX54NEWUSrgTYe+0LYWSJy4aLUNT52NuXlvABZageFsaokuVOrSz8brIam7uinhW0w7nS8p0uJ0A1iBDN1tu43+COmc/63evtPOGvf5jBacoDQAWjxnq8768/QqWdov48qRCamMK4bpOpNCGT77VmkA3V6LJJkWyMrOjxVKIIsWvQgo51TdM9LckEJIF7ntUhm6afuRqHBMbllw7KY/bLLWoq1raSrFc6lK3VwTiqZrmcp7CJ0usgIOFTxnTBhsLbItFhXf/YqQgVBygoSvrCYs1TWfeqbNq/aFmBg+fbrD8pJL3aDAS7exHBmSVK19bSGmGzkfoKfPxdT2Gebammbbsto1HI9jGg2LjH1W6oZ7JgW6vExt2UO0Ssy2NONFRU5KKsKnE2ushtuDCk/FdepSIxAoCQIBxkUjlIAqPrlEcrcaYjkwJB3BmPQxUrJiEhabhkP5HCAwxpKXCh/Bqo7JFzT3FgJeORTwUNLBxpZyXOy/H6EUWCOodaHTsUwVfbBu5Iu0sCcMUEgkAotzPlcaXqCqvHmwxseeamGGgK5F+KKfWtZ1+O5b8uQ7Er8Mr5/KMbMQM13XfMfeHAeLHiaAwIP5rmFOWm6r+sy1NQ8vdV0oLIIBT9Cx0NGWPzvW5PCg6y78xkoEvhMlVvdElEsLm/Q61E0LQvDhU00Oz8X4VvK0jomqOwsg3QTPQkUKVmqWpGsxbYtII6fCc8IqrlmSVYNQgmBY4g+KCzZ5CCnceKRtMN00nem7z2owcn7vq2eLbvYivxYTCVTuudtXRsZ6MiGVcUVY37nWWxSe7S9GGYBu4epCdlFHJRDr6jvW3b5DCmFzKkP4LuXnvJw2bVsK/OpaO7nbgHuciddcoG0MqgrSk6iKKwCOFy1LUruRLco9brFukL6LeqnSxijad9+R56aCDwpu8AJatsXXn4n455Uuj57qIKQg0c5+wA1kFpwIEpaV5kxHs1/BiYZmWmuebsYI6drXkwSmV7VraQfOLGnmI82dhQBfWkZzrnPMlrrUA03SKjDXEkwVFfNRxNm6Rhuo5iUhAe8+cpzvnByg4kneWBohp5RLUSXOL6uzoljJG6yGGMt0PaEcWs7FMROejwBmul325N3oHN9KZKHLaMkwXvQxGl4wbvjGdMTLJiWJtrRiiwZMYni61qWIwhOC1UizrBOMbxi0ikDItCbeYrDkhcKgGQg8np6PmB3LsafqzDQ/P+fMNGViySHwBdxdDSgUBOpFZR4606ZmDHFiUVYwGEq+uhT137Ki76wFfAk/eHuRqVEPLeDvT7d5up7w5XX+V0I65/r1Q6uFJ1BeaidRdbfHK4avnHH7kHlBrih3TMmNVSRvP1CgGEhW2pr3P9yk5hlU2eIVZFrQ7sYIxSsghMUmGpOo/qDk9djEpb2tAL+ys9iSvoumqbzrDvS2KWC/nIgAiNO6yh1ei4yM54JMSGVcEYQQCOkiOuI8XTjnox+6V26auwwEwTAbC2zPg8y7NBkWROg8cUSw+zosrwK2kM7T2252WeiE2oAvGDOKuWbCQtFim6mBYCOtr7IQ7rGovHTbkZZvLsWMzHQ4vC8g7wueXo3JFQTxNuc2XvI2LG6jOdWftGuEwBsA37pIQ+/cYuCDx1r809kuOeUKxs+2NYl0+Uar4evzES8Zc0qzmzgPpJYyrCSGSqgIUnNPgK6f8J+OnyBIPF41UuUV1SpJrzgaSy6A/+VlRRaSDgsNy1JSRUWGnJK0E8NcO+ax2Q77biy67swEEDBDxE+fPs6PTAzxPw2NUQigQYzREBtDO1en4DlfrCSBqSGPp5djjjZb7A8K7r1V0LWGn/3GCbyO5Ucm93DPnjLSA6Ncp+Sq7TKQ+kwJAb6QrNLhy6sd7LjkwZN1JioecUGwqtJauSIcWYx50615coEgMhBJeMFESFvDV+Yj8lJwsiGoC4vAjc05shqjyoK7SgGTgx4DOcmhkscLSz7v/XKdx7rR2qzHNB1mEoMKBaWK5IYBn2ZsONXUazMe8wJ/UJC0LCQQ1zU2lq7WSbkasxvLHomBOwd9SgWJjaCsBN82FfDRUx2Ur/rNFVZDvCxQgTNXNR3hPm8r4I9s/Ix0F1Jn/rR7dLtRS+CuW3/YXe/nTbtfJrxSWlcpua7tUjKuPzIhlXHF8AeFi0ZdhHhZj/O/2Ri6v5gvTCFdrZHupMXa9Ewjd/l8Ifq+SJDWaDXSX91pC/lEIHnbeAGpwU7C355o8VSk8QecGWK/SyoVOuDGW5gIHm1FDHYUd+QCXndLnrv3hjx4okG86bU63Uy4Y2AtBHemlfS3If2dRWVi4UxLb7jNK0OCSxl94kiHmYamkpccqyXUpAUr+LOzTe7fV2ClYyj5krGc5NGFLsVAcO+BgJztMpgXrKRRlMGi5AumzlROMoDki1GXZ6I6Q1GRjnHdjk8st/irpUW+/6YRJgsB7ciw0I350JlFir6gNBixLCJGCSh4gro1HInqzM9F3Dzq40eC4VASCctyaHj3o6f51dsnOTxYZDWO+Z3pWep5Tdwx/M7Rs/wEhnvHyxytRczqNrcViyzbCKUVoZQ8E7V5f/MsA2OKHxot85nTbWZbBimdIALXHfnxdofJuiIOYTEyJBYWuobVesIdAz5LkeH9x9sgBUOh5GQjYaFrUDlBUHXXz80VHxmDNvDyoZDTZxPOpflgE6Xu5A3I+fDO24tUqxIhBI/Md9eiY6EgGJWotksf67pA1yx+FfLD8IOHSoylQ5sHAsFSy7haqMQVlDuTy7VIp1CC/AGJP2IxXYNpC5dS3s7KwW76/3kQSlzKb6ZLJuvuy7gaZEIq44ohlHhWflAyWGeJcJFXrk2HyPa693QbvLLFJpf+xaubzlkZerUmltsLPtLSj7y9aG/I8ekWykhe/iKfgpI8sZiwMmg2tJ2rPISSvkASQjBSlkwqxZG5BK8MKueKUT4x06EeW6q+4Jl6wsmG3vVr60t48XBAXkm+PtdltifuUkF6ZDHBr4oNEcOuhpwUfOyZFlN5DynhozMt7hoLEcrSaid8fGWWqBUQBYKJomGlHbEnCfCkmxX3pF/jsadWOBjkObHc5bP1Vf7Nob1gLE00nhAsdRP+YWGZG6d8BILPmgUO2AKj+DzSaPDFZpMvLHT5cVvm9gGfJ1ZiHpnv8pHTbUpj8IGVczBveWy5S1wRqLzARJJOovmtozOESwIRCG6rBPzH26fYa/O0ifmrxRrvW5jlh28qOhdzYOyWIr9/tLGhiB8AT/Dhsx3CnKSYRsYenutypqX55NkO2q7pi+ONjU/9xlzEnb6HHHRRmpPLCQgo+BK0E7jSp29qeuuUT8mXboMCXjQc9IUUuIisUGnnoLZ9t/q9edUXUeBmMJJus9kxPHKy456bCm4Tu+isDMEvSyhLZ7PQYcMg5R7BSBrtlJc240633UgXtcvBxBkZ1zqZkMq4blDFtMZJXvwXcLLqFgxdB5F3E+OTmkVIg9VyS2TLpHPNNhd6b2B9ka1w9SWtwGArrmBY5SHuOJHyljsLHPQ9MJaX3BzywZkWCy1XjyQDdz5JatjppQuXjWD1nCFecp1Wub1pV6CBz5/rnDeql1OCG8seHW05Vl8rCHvzvgI3VzwOFBXfO5bjVz6zwlJikTkBaTv9dnS0JdKCFWEQwOx0wuCEolBR2Mh18C3GTfbsUewpB8QtwdenI4bKijOthEcWI55YivlkXEe3LFWleHmlTE5IqoGHj+AOr8BLGkWebLeZ72hGc4rjtsmnVxM+dKLVP5YPn2rx1SXFmeWEYy1NGAh+6FCJii+xxnJLFPCnx5poCzJ0rf1vvDXPnaMBbWEpFyUPR4uEqd3Dx2pNir4gkIJQQjWQdLSg5EuWultn5C01NL/3cJ3RoqIeGlqpctpu7p7Vtv8et9rwh19rEGvL/kGfjrE0PcuMXRclTDtHZR4iYd3zOwKZs3S0i6LeN5nj1qpPI7Z85HSLc0Iji2A7bsRKtOmyWIkMf/REHb8JZ2cTIkCFLipqcWk6a1zDhj+SplkteJWdap+2jo/ZLb2JBe4fWzsMMzKuR3bot8jIuLzYxBKvuGiQtbvICeyA8C5trlZvnyIHUop0Vpgr1jKdjY/V7bTwdnmt665HNG9onzQkDYMqOi8hr7rm2fPwfJfp1QQkzK9oPvrlJp1pw4FQOUsFX+AXBFMF5Yw1Vy3t05r2SUN7wfAPZ9pExmKxfGGuy5nVtUXWxL2CYFdvtZ5AwlgoCHEi6ocPFblvb4637Mvz+glX/S6AGyuK1+/N8YLBkHv35njPawZcZ1jV1dzsVMvy0GyHG8d9bhsPGC0rbioG/O2jLWo1g/BhJdKMDSiUEhw5F4OFB7/U5Gc/tcifHGvy5HSMxaIKOBPRQBB6ggO5HHkh8RAMBh5vHxkhsfDnx5vMthOkgHZiCaUzQn1h6PN9+wu8qBzy2nwOHjcUFw0V332VCSkYyimKLWg8pemcMdyS97l7KEDEUEJyx4DLz7atpm01aJg9p9Edyx1lnwPK46DvcUNJYROLJyx7cpJ8KrZ1G9qR5dRyQj21w6gGgpFw49eptbb/HsfLFuFZEuBPnmjy4ekW/7Ta4cGzLdZrNRM5IaMCwTfmE55cjjHG0mpbPnqmzR2DPrdXfSRO8N03mXcdpgWJPyTwSoJzHcPD812MtcTG8o/THZa6hjM1TUe7K8G0nJmnNRuvb902REsu9a1ThWiNTUfLpJ+JztbPb+8zs/nzsh0mMcQ1Q9K48HeBtW7fz+Y7IyPjuSaLSGVcEZKGKxYHJyaudGuyXxUunee7FJluW5IaTtxs6vhb39G3PligO4ZoMa1lmYXcpHA2BoAYdGmOQSlZMIbZ2S6feaJDJ3JFuefOacZHPbc9C4sd3d92tAgqb9BtwZFyxFM1JyC0tgRjwg2KLbPOUGjjMVZ9wQ8cLFBIJJ3Y8o16RAmBbrmn3Dng89DZDhao+pKikngCPCG4YyRgbESybM6/UMXWcqqtOd3RJG3L+LCHCuC9X6mRH5bcnPf5nj15bAIGy3Lb8uRijNoj/n/23izIkvQ8z3v+/8/Ms9de3dXT093TPT07MNgJEMAAIAFSBC0bIE1DFHWhcFjeIhTWha4cvnAowhF22L5Q2BEOBRXhkAQuIClCoAjCAgmIBAhgsM9gBjPTPT3TM93Ta1V1bWfN5f8/X3x5llp6mV2EzhvR0dXVVZl5MvOc/8vvfb/3xWaMF2VjcE1DOwlcz3LupzbiwgZF4FRVb4x7Z2JWahFB4P7ZGArhi1d7vGshUR1RHohSw0OLCT85m5J/WIjLAnvgAzde8eRbASNQP6Xn3JS2D5fbBRLpU+SNfuCptYxeT/jptYwTziECl7YKHjIRP9nJ+HuPNlmYdWRB+LcXe7zcL9TR2wBOeF+zwkePVrCR4cV2zp9e7OtLEqXaRIR8VbB1iJqWaMFwtltAd3iPaf6dTSaovQBRHb5yvs9XX+pjWhpAvJJYnVQFXFWoRzrh53tlM6uuVNzjqynfW0spBoJPBUn1nonqprRXECQzhL4OJ4SBdmHz9TKSqaS9JYh2RPPSXb1udPJ0IgxZpDS7FbXSuNVEronAt1XIHpJAGLibUtIiQrGpDxC2ssdL7RbwfR2ecPUpdTjFW4NpITXFW4KRXYDZbx3wRkFEp4yk0KywSa8qE+0Wlbva2B9oL63n6iBedUKTtghDcXjIA9YaLQ5KTYzkMD9r+a3TTaKg/76rEfGvvtvBAP/m+R6/EtdoWMtTL6e8tO2xdaFYL/ftwZS0JUCQoaXC7gXL1TQTzTXHx/W+pQp1r8Vh4uChVsyCtdgabA4CJ5oR/+iRFtuZ8J3rAz5xuEolsmReqCeGdy/H/OX18Qj+QRgUQt4XrABO/a2yGlRnLbZquZh7tjqBmYrFJoYz/Qx3yBDPDB3fBZwgXatu7Q34g501HpytURPLwAfW84K21epycU93Z6muHb1+HpizVrU7DlIv9Izwpxd7fPhwFUH4q4t9ukMn8WB4oZfzkViooYL8vzg74KlBRqvhWB94hqqj1XbBCzdy1bdZQy8EPrSScLoZYRK4kQkfXqhwYbtQTyQDdgd+fjHRCVAr3NuKOd7MVLdmDa4uDF6BfEe9qowVvaYTn7wj2rkPyYIhXlSa1URqtzF5j55ZLXhvU6hEeh88vZ3ju4yMYiMztvLwuVqOiNcOpknAt0XtN9xQn1eGFsfqnG4q5b0YqWWBFIyy/kYPFXutPyYnci23nMgd+7IZjak54LNAgiYEGCMjK46QSTlheevCKKQTiQReLUmmmOLNxrSQmuINhYjqkMTrRNhQ0Oqa2okafnC/XoS0fApPxvl4ko+1Tb4ntzX9vNnEn3H7n341Mga031Iew0B9n0ysQvMjFadiZQtEcLwa0TpmyAOkUeBLV3r49nhSyjYMtg7Vii4qlRWDjV4d2y5S6mi8dr5CAUdnFIECTAAAIABJREFUHK3EsFKPiJbgTCfHYJhLDN3c8a3LKR+9q4L38MSVjEMSAbsLKSlklxatnwr/7lyPT91ThR5853rKlgtUSlFzrx/4F493uG8pxtfg5cSTzNvR/WAshMJAHJBgCT34fr3DD3sdTsQVJICJ4YvrNwC42C5470KCLfd/se+J5w1fWx/w2fk6LWt5mZRnipTWuwwXup4L57tl1zCMHMHjeUPWsPz+pS7HTcTOjud822MTQ9d6pBBsXSAIP76WcfdMxKlWRC8JfPNcyn/3wAyn52NMBIuDwM5WoNaBQXN4/xzQySsnS41TKwJbFVwO5CUFfFDx4KUsokvqurwN9t6jOzbwr55tc3I2plcVLvT9vm1NblOC6gFNpN0dDJCb0YPGZIyMqxvogFtQexFj1JrDJtqFilb0ePbm8MGdT+TaCkQtg08gnqOMmJFdr7PYKo12BUws4A22bvZtV0TAA+72BdYUU7yZmBZSU7yhCANGOomiMy5IjHlj6byiXbqMT2TbmWj4wXwbkfgE/ECUqpiI7jjw53qQbwhFu1w8E+1QxXMWjAYSX8sKwlHBRoZQCNv9QKgYzEC7DhrArAuOicAlIH0AQzxnbnvMIR3SFoLvGeJFIfQM39kacOK046HDCZVEu0cv7XhebntOHoqA8YJfwfD5pzpc2SgoekolbWwVPHa4QtUZntrIuLzm8b1hwK4WU8bBs5s5P/1+RnZDX6OJIVmUUUZbGgee3syIPNjEYgyYqgqZTWRwpcs6QQuKAvgnl1/hI80ZluOIJ7pdzqUDxAvnLuT88WaX+1Zi2k740XqGjQ0bCP/vuS7FhuBzwc26UbGFaH6cbxtcBVzT8vDJmNOLMZtp4AfXUmbF8Msna/gEvnc1pbOjtJWIID3Dl8709HosGe5pOfpWGAShjuH++Zi1jucfvKvF19cHnOkW+Lrw7VdSHjtVxVjDCxs55y7kaiA6p4WFawDGELXUMXwfbDk1V9UCSoKMaFlbh3ctJqxUHBc3Cp7p5QxmDM9JAZogNNq+QUXqAJIK+XZJAVuNusFB6CkViDGEYXDx0JuqbkZu/0MMndXFo4a6oYya2fMy7nRq1Dgzik8KqYyocj1XQ08r1UUVHbA1IWocXLwVW/rgNJnhZysqYB9Se1NM8VZgWkhN8YbCOEbr9kH5W2/cfkqXccv46b3M/hrSIreDFKXjOCB5+bs33Z9u18aqIRm6qZsy7gWB1W7gz17s876jCb2dwNdf6JMVMl4gQunyXB/GcRjcjG7bt8F3Aq5lbtpJG55b39En9XwLEGFzAJe3ClbmI4ogvHshYSfP6RlhfRDwpa4qFMKPzqf84HxK3cKJasyNbc+RJcfKkgqwH5yL+U7os2WFn17OIIJkTrsk1UV4oBFTLMCzVzKKCE62IuYSx0vtnBu5vkaM7KKaohbjUXoH+abaRoQqZDFcoMsGhtWgwq9sIzC4JDxrM17YLKiuWA2+HWiXMWoZpMxHDF4IqfCueoXHjlSZudfw7PWcr7044PApx2dOjscQlyoa7DxfscwmjnfOxfzT7+2oBq1qCAnkO4KrC9m6YTs1pCvwk/WMexYcUQSV2HBoxvHxapUzZzv4juG7mylnNnLqS4brG2EoYyPkGs2TLNnSKPTg6yoFowJGCi2Y860ABj5yuMrHj9QIqfBAJYYBPNPPd9PWxmCMUlq1LfiNd9c5XHdcXff84RMdBrGMBywaeg10wEI9sm42qTmJfEvI1kvReddQPW5fdxdo+D4afj2k2qMZQ7YONgmEnqHw6j22KzhcZNR91u7V2LLjjYifmmKKV4NpITXFGwqb6BMsYb+I+41ENFt2v8puTzRTUikTtMitMJwi9F0pn+Jv/eHr6obkkCHfABGlSnwHXFX/hBQQeH6Q8/wLOenVoF2FCJJlkLwU7zYFEdXACCCpISBKR8WA04Ug2wwUm4JPAwRLvAjVFVd2B5TGM7aMgEnh+GJMt1CX63MbBTVnaAfha1f6nNnOOdaIWFv1XNwocDWl5r4tKdWK4R89qEISA7xnIWH5Acv1Nc87DsX80Uvd0Tn4zEqdY/UIDsN/8lCdVs1wYj7m5XbBRprw+XaXjf5+uwBTEfwmFDtgagHfKfU5MTx2f5WfW65gjWbe/c6LHc4N/Ei4nG94QtnhdHXVpbmmuswXBqQDrdTyscNV7mo5TrZiHj1U4dRKxEttj+/LSPz88HxCIzI8PBdjjOFEw/H4KwO+d7WMWjHl9NkG4AKrFp5cS3ns3ippqc853tSPzLi3+zVuZYHuwGBrZYFgGHVgbyZ4VlpWu06hW1LfMfgtNW+VAHcZu2tK7sRsxDNpvm9bvqcF5UeO1zhcc4iHwy3Hx+6t8ucX+9oRbuhUn+/KaPDjTlB0tEgLA9UuYfXev1Mj25vBlu8bKSm8oQbKVgyVw5BtKeVtD/gcEV/qt3KIFqai8ineXkwLqSnecLwV7sLGGkTKAgWlul7NB/vQJd0mpRD9DkSp8ZzFNXSKKd9UZ+iirU/KeykbW9eJp5HvVVIukh2I5gU6gh+oZsTmwmPHq8wkhvMUvBwKslUNls3WwbYC4g3RTCCqWyrLVn+3DDSOZoQNG2hWLJLDxiDwxbNdXrF+dC22sxw/4Y0lZb0zGMDOIDBbdTQiQz0yZFYDnY9XY5Y2I3YQZozh7mqEBGgkhnffleAMBAwPzsX88GrgvmbE49up6mCapRi7pgXUSADcZUQLidf4ksjo39XIslC1/LNum6f7GcEHJINgSwqnBgSjAdV1vc+Cg0pFaa3DdTfqUCZYWkbdvEOmRc3FTsFHDlfGsTkCD51IeNJrJ6xoK3Wrujd47+GE96wk9EUwaWCz46kZ1X11OwERIZoF31exto1MWbip4Ns4o8aWpdnlXup2SE2ZCOKlsQbIVlRHFwaBa6uekwvj8OQbEnZNzI3ut4pOwtUSfZCwiRYhzXmLWRteC92urUM01Ondhv4KefmwUQX6grWqSZT99fKrho21C5xv6pCIrTISh5vIUFlyxDMyyuYUEe3+lsdlIn1QmbqZT/F2Y1pITfE3EhJEi6iRqPfV/f7w501sbhm8uhc2NsRLZc6YmHHkyx4kC4ai/ICPGpBnMppSsrEaJ1p0kf30vXUenI+RHN5RTfjilR4vxLlqqeLh8ZqRm7uJDFFTvYtOtTSH7avrAz4RVWlawzNXcy7kfl9IrGsYXRDNWNBrLHzxQo9PHK1yvBGRWHjnQoUbdc+ZrZyiDhSQihBEsMZQi7VwGXhIHMTWEEWGTj8QMjXAdI0J6ikZni8tsEysU2a+a2h3A/cd0SIKNMz44/dXeaHICd6QvqLTadGsjv/7gWpnIquvxRWG1Xbgcq/gYWKaTicV+0HodR22HyGtnOuDnG9cHXB6JuLRhYQg8MSNTLt4w/NTL4OeYz1Xv/BQDRdpgVOPLdf6nq2tnNwLa6F0pncQlROUIZuYGCsM0VxpdikQ+hAv775XQj62srACD8/HRBbOkJNveKwzfPPigMqs4ehyzJW84PurKeaAGKCoZXB1y5ko58FagrMGHwtPb2X4HfCixVgyX+oV74DOAy16jdWukavY0nVdKcI3AkVHyNa0KIqMsFeJb5PxdG3RHVPGwwayeCGU528qOJ/i7cK0kJribyS0EADQbtJBT+m3gmuUuXnm4CfakOrTr4l1kZqEdZZksSyM4nKir03pBs2IYpwcvY7nlYYw8XBcXAXBPhNOLETYyCBWOwZHk4hLxwtCzxBOekgtUctgk3HXq5kZfvNEg1pNi8Af30j5yqX+6P/3FlFDDAvGaE6QXAX6W4XwpQt9/sv7mpzdLjjRjJhNLOc7Bb2y0EiBv7gx4BdWqmxK4Mx2TubhvtmILAhPrWc8vZqNxuTzTS2eohmIapbaCe0u2aaOwKuODb58pse9ixFHxbE+CKwNdCrSxlb/nAiqr6rDA7WEDywk5F74xo2UVQlELUj7wh+d7dFILJ+6r4Zx8L7KIh9ajgmFBhj/H2uXWao6sgDPb+fMJpb5xPLNa4Nd52b+hOGXDtdYqFtOzkZc7gUEYb3v2egVNMTRCYE/3+gfcHIP+Hqo8z/gcjRnLIsYthA+fbLOPSVt+N7FCp9P2/R2dJLvm+0Ul+VkN4Lecxbixf10lnGGi/3A753vcrjmuN73XLnhlUYWjS/6yL01MhH+8sqA64Pbt5WMU6o+5PqekBxsomL1NwLD4PDRROOtjmXia1fXQ8i3tUNZBKZWB1O8bZgWUlP8jcTQkdm43cnyIahAFXSa6Zaj2LeYkis6WiiRH0zLTHbBis5Yc3IzitFYox49qIHm+x+o4DeE719MubruOX23OqyLF651cghlwRNH2D1FUciFk5WIxKhZp60Lj8wlfONaune3+1B1hg8tV6hFhp9uZrzSHY/PVxysDgKrA7VCuLon4Pj5TsHzL6il+nxieedCzL+/Bj9eT+l1BSKDRacbQekgE1uiRpkTWGqGpKLUYciEG17435/e4TdONjhUddQjw0YKv3CkyuOrKYPEYhOYTwyfPl3DFICBX19y/PZZPZZKzXBvPWKh4XhyM+OYqXPKVVkNevwVY/l7c8t8vn+VIHBmOx8FEff9bq3QLx2tcXpG24BZgEM1y9Utz4UbBX/w4w5JE4pgiObMvoXfxlrUq3gcFUjHkOVQnTd86miN9y0lXO15vvHygF96qEa9ZjAGZmLLTklTzyWWY4sxL1WKXdunrHskMBJpi8i+e3w9DayXduluFmwfliTiV+6t49Bhhs+cqPPPz3ZG5g2+p/e7a5SDHBPbNZHBGrCRUJQdwfyGEM2/flrNldFEJtr/wLIXts4oPsnWyoLcBsCMzs0UU7wdmBZSU/yNRDRjRm7QQ5qj6JSTRb4c9zb2NVMQJjJIodTX7WjDyenEsWmn0jqALrrlguMM/MbJBq3Y4KtwshXzuz9p0x1UaWI4s5pxtlNgK9q18gNIlnZ3H4yFrh9O4qnuaKe4s5XkPzte455mxFLV8djhCv/0mR1Wy87Ej1ZTPrxUxTjoBuHs9n5R8xCbWeCbE4XbkGYLqYDRfDjxkBwwCWmM0l4E7aalAX7/fJd7mhGfOV5joeJYqDgO1yy//3yXfEtozEbYoFQsQA3DO+ZjPr5SJTKGrAjYCAyGJpEuuOUpa8aWD8/W2Qw1GgVspypu/unVjKW+ZeWQ43IauNb3zE50/dYGgWe3Mr59ZsBmP/CZB+vcfzgmFfjKao9LB+TwDTujBvjl+Sr33xsjIszOWD5wqEIW4F3zws/NJpzbKPAZxFXD4Zpjq5+PjD072X5/qGhG3fmHVFe2HiDsjiiCku4qdVkusVSPBJbEatfTgyA0IkviNJA6ZKUzOUrb2ar+2zghnh8PcNjSysM4Sn0iEN/0FtmHoWh+snuslCSqI7xNl8tMmI0C+FTd1k2kHboppni7MC2kpnhTMDLmLNSM8059ne4Uk9qJIUJPMKak/MKYChibaY6pt4MQSjuEMFBdz9BX53b6KVctu1Myfp1hwEiQG9Iy+gP49N01Pr5SpV8I50KGBEOrZfmzZ/sjp/RkyY4O/qC1xTjDi77gibUBD0Q6rfeVqz2YCJkdBjTjytdc+gwdb0S8Yz6hUr6m3zzZ4P96rg3At59PeflSQatquRp5hgN4SxVL1cC1vqe4yWJnSpuDVt3wqfvqNGPLM1s5P85yvPf0zgn1zPDZj9ZZOhTxQrvgr6+PC7EglFl22g0JAziEI1sNFF24XBR0+kKr7M5d6xd8pFlBtgRfg4WWwwLbWeBqNuAuaaqXkIOFhuUKfYKHdib89fk+V9YL5mccv/5gQ6clY/jShR4vbOQszFvVviVwZitn2wmPHIq5/64YgqEaw6eO1PjtH7XVt+gAGvX+2YgHFmOsh3cdrnDvYoSzhtQLaz3PbMVSiw3dICO9VtETogDfvZpyrRf2jfHbythPyfd04k9EyNva+dIBDM28Ew+mpwWGjS3XB4F+EahXDJIaLm4X9PulNcceSjL09V6WYizUH/pJ2apmDdqo1NvdAiLl+84DkQZv68Uuo2a8Tia+lq6WiOb6Dc/RXl+rKaZ4KzEtpKY4EAdRBq/q9/OxMae0IVl884WgtmoIQYhKimU4keR7E47nfTMSB8PEJJCoJ5Hvl7YGdf1wvh3dMNp3bHYFq9qKLjgGRovfuxYS7m9GGK/03un5mKeKjHuORnzgRIXrG57vXk2JlsoJsMHNc8tCBv/fD/p8ud+HAJWjhtrMuHXmO6WYOYeQqFmiAHmQURElIswklnpkVAsV4FLbQ8dTWTLUYstDczGPLVUIKaz3Pf/6cpf8AI+ukOoC/rlHGqw0HHHFsLjk2H5FePZFT3FD+NX3NThqIyrW8v6lCptZ4Keb467X2sATRAg9CH1htetJtwPWWjpt4Q9e7vCulQq5F35yfcB/ddcMQdQuYMcFfrA5wOSGG5s9vtHN+dypJWarjlUZ8BPZUv8k4OXVgiu9gg+fqJX+Tloo3D8b82dP9dhY8CzUHJcouJQGXN3QWHQYY5BSAxaX4cK+EDVz3VNsV5wW+nPOUq8aMg8Vo993zvDcZs5q7mnElk438Edn21x62SMFxLOWypEDznGuxYhJyk6s1YlIm+gUabxQ+it59YeanKzrR8LvP9vl4bmYNBee3MgorL4vbazGuaFQY9ow0IcRHYwYb8M4LRon3z83w7AYDmUXSvrjbq0EfbjJN0qzVqcFna3duqiSUL5Xjb4/bdUQBvq7U/uDKd5OTAupKfahaGvSu00gmntt0zDGMQpffavGk6MZg2vYfTTBJPVm91ARoceuSaDh+PyrjbLxPfX+GdIhNjEkS+Vmyw/52cRQDOCZ6xnHZyP6JvBsO+dj99QRhAePQuuoG1FmN1uwfBbI1mSUw+ZqOkW1S9cSo6kvZvfr/7cXezwwGxNZw/W+ZzMLpOV2ojLY+dCs5TcebNCMLA/NRZxdzcmABxdifs01+KuNwYgOhHJR3BaKrnCiHvGuuxKiyLAVAt9aTUsrAJit213dj9l4dxthdRD48is9HrYx3bbw9We7qoOpC9GCoW3gr14c6PWKhCdcyqPzCQS4etXz+GqKd4Z8S/jR5iZ/dnGDWtXxqx+q8eBygjGGq1KwngScsfTisCvYtlPoZNvTaznG5sQL427k2e2cdzdimtZigB+uqo7MOA70LXt+u+D9i0IjBqzh6a2MRqQU3reuD/jC+R7X2wW1rmFn4OnfKHV0TrDN/YUZoBOAARhoARQtMsqElAIk0w6Q5KrHi1pjS4UwEFavBa5dLnQQYs7gJujAyW6XFinlvfMq3/u7g4aVRpRUH2pcSZu6uj5oDQsq3za4ltocDF3PD4LvjcOvMZpDKc2Dz/8UU7yVmBZSU+zD0AAxZJpz9VruEuPUI0YKbmnMOWz/SyFEM+Z1F13GaTyLICMRuquZUTEx7BwN9zlZZEQNo3YIi/pE/2oMRX1fRnSI5GAO6CSdbxe8sxbTLeC5tZzvXhvQqlukdJjGwNF6BKT4nnbHbNUQNcxIx2Ii1SH5PhBBVFXfoTCweDs2SYyaZtS1mByVf6nj+e2zHT64nFAIfO1yn6HeeriYfvKeGs3SjqARWe6ac4QMjrUiXA1W5hx/+FKPa8Oct5IdclWYr1kshrmKZSVyfOpIlbPbOebRgpeLnMOtKpKBt4HnL+fkbcG1yusShDOvFDzTzdX0MTFUZlRIPOwMVnI43HRs5oG/Hgw4+3xOLHBhy2MPaYEQL6AmoG1D6gJ/8myPpxdyHHBRCtycwebwrXbKTN9xbyvier/gh1cGuKYoVRvtLmZ6hfDFqz3+zokGzQQOHXLUegYfHVxsDLzwu+c7HG9EfH8t5VQr0vN9pc+Fjp63ILCZqhP6KEDbmlF25D5YxpS1AWstUWt8n0hBGfirxqxMxr0Y/f2ZiuXIYUc7EbbyoBTgAUVb6FM6ybMvNmb0M6k+PNjY4Fp6HqTYbevgKgZflHl5lQktV6LHHFIZxdrcxhN3F809/PpObUummOLNxLSQmmIfbLU0FkzMgQGrd4o78XcK6bj97ztg51/7/kKmnZFhuz+eG39wTxZok/s0VrO5EMqgW9Xp3NH+fNAuglGPo6JTmgTu6XoNg2Nf6Xq+eKXHPdWI1Q3PM+s57zqU8OgKo/N8re+10OtoYeY7upj5blmkFap/iZpQtNVbSvoGiQUJezQ1Q71WLiNhvqsZntzIeHJjd0jxJJKJAvB8u6ARGQ7NWrYL4UY/YHI4lbhRIWWsIZoHyQwXfMF8bpkTy42+Z77i+OWjNf447/Gt9YwthPmq5Xyac+GyOpiLKBWbb5TXrmKwVUvUojSDVG+nmcLwn9/XoGY1RPfvP3OMhli2XcF/cdfzbLWEvigtGjct5KJFtQgvrimF6Gqq7fEDaIuwOvAca0Qs4vj1I3V+72wXO39wcfRzyxUaFYsAD88ntAvhO6u3mJQUeKXrObdTHPjfNlaLDCkM8XxpLVDdPYU6iXjOlPq9cZE+6dkVCsGvK2XmamCSgK1ZjNX788gRy995oEG9YSkK+DfPdHl5o9DCc6IgkVDef2h3evy+2I1h3qUvBFszpb9VaZSa63UbTuSJ7L4/jRnagzjNOsy4rebK1tU/DG7/s1NM8VZiWkhNsQ/RjME1D9bmvNEwE5m6ewuQV4tiW8r4CzCRELKDw07tnn2+lmyubCOQrwsmFiorVs0ua+yiQ0TUsbnoBGxVw1qvpIErqQqLAZ5ay6jPG443Ita6nsc3U43JiMbuzSN6LtMn8WjOEHJTuhAKwejiezMqsNjR0fYwKEXvt8kh/OF6yqfvrmGN4UrP86WXu/zi0RqHqg6fqUZoa1vNN4fFmo0NxPCj7ZwH5hJ28kCKsNYvmMHwzmZMbc7w7LWc59KCUEiZ9wYPz8XMNRxn2ylXN5QetbEpxf76+kNPeKQVUXeGI9tVPvviysjCYN4n/MX2I/zOoxc508/502t9vFO6SDYNkg8jdfR6F9tKkUU5vHch4fSMY8E63neowvWu5y876YG19ORE30H/nsR7FhM+vlLBoB5fN7OmsBUDFXAeHq7HRMZwNsvpHbBp43YbaYqUmilXdhMjzSEMqU5EYsbaIeMMHzhdoTGjGXkuFz54V4WXnivKrtTkjsrip9C/b0bvmXicdzkUexujAcKI7lu86prCAHxSWmLs2d7w3rkdjLmzYOQppnirMS2kpjgQb5V400aGZKHUUiVKyyGvUVdlS4qkXABCKmTZfsrQRIZkcRgRs3s/u6jG5n6vIChFr2UWmqSMpod8T/c5okO8FlG+qyG0YWCJF5RCdM1ynNzBj9YzHn8+HU39xfOqTZPCjBayqFWOtWeAqD6k0TAcNpZuEG5E4eYLnjEIpbt4+SMh1wnHyaJqSCc+28m5kQbmE8vVvqdbCH96scen767RCpYX1nKeuJxCBDax6p0UhPQKfPN8n17P87kHmnRyIUuhJYaPzVSwieF9ywm/93KX9VUPRvil+6u8/0SNkAnvbcb8zqDNVj2MCuDhJFq2JWROz/lnXjw8KqJGrxHDb377bn770Yucajues7mG8Rl1vldPK70/fEmRBdFiaKmi1KUR+Pm7K/zF4wM1Yp3ZvY+z6zl3WacaugTOTdhD3F13xNZwsVuQWDMqokANNs9s51zreMQDTvA7SmUO783PHmvwc4sJKw1H1wf+12e3OX+50CiiqgrJMWbX/erb44GOeF7vnahpCIV2MI2TXcWul4kYmgRyKQv1aLdj6HBCb1hIDTH0S9Pgbe3kSs2UQdRCvhOIWobK8sTUqTNIoUaixbYQz4ylAuLlwPfgnSDk6iJvnB7HVGw+xduJaSE1xdsOE+mSE1INEgYOdCsfUmQ3g1IfBrOsOqWhN47vgd3jenwz2lHyMe1XdISkLKQm922swTV1YmjY0dIn7/Hv2apGWoQcQhF0gs8Fktjw8ZM15muO8zsFT23mZXr98AAY7cMkJSUi+v+hbGoUHaHRNPzWQ81RV+Qb1wb8+MbBdJ0GPOv2jNPg36KthVU8N17IhnRiBeimgY008NHDFT6xUqUfAn/ycp/nt3PCACp1Q1TA9mbQEGYZC4F/9HzOhnQ42YpYX/f80l1VjAe8EDvDsZpjNfNEDcMvn65zqOXodAMXtzz3LiR8fz1FUtHioNROhR58t5Py2MnaviJq9DqDRQo43nDcNxuR1wx/eaZPryhjWtoQOlKaZmpH73sXUx6oxxgDa31Puy8woqt2F/Q/vpiRtwNzFcul4LlUenf94pEqH1+pcrhmWRt4/p/n2vuOMRJGU2raDRUM0MgNcd3wjuWYE60IEahWHL95osk/eXZzREP7VLsxrjF2rZ8YEh1N6NnEEM84THnPFG0ZTcx+fz3lWNOxWLF0isA3Lw108nDb7KPUh/ff8N5H2HV/u7oWZSZRE9xsXYssvyNELcFVXXmMGuEiXl+3SDlRODG1Z2vlkIRwx51w3xlT3SGddqqmeHsxLaSmeEsRUqWZbG3/B2aY8H+UnLET9sQkkKvf3JJgkvoIww6MjCf1JrUYNxOpGodSSQPB2rEwXbU7WqwBJAuWaDaUcS+lE7Qru1xx2Z0alBNKYiBo8fKJk3XemSREdcPJZkzfC+d2CqKWvv5J6iZkpalnSedN0i0PLSS7qKUPLldGhVRs1WohtoZnNjN22L1dnwm+FzSjrGLH9Fxk+OhKhQ/eXcFUYSsLPLZSpVVO163UHP/n023mFyyfWq4SdoTnrmZ85VIPN29G59vVVOu1kXoenYtZnrG0u0Je0ms7PmAiePehCncvRDSsZT52WGv48nmlihBoZY5fymZAhK9Ut9nKPRvFfqPK0T2DECw8ciSGusXVDEvvs/zei12KzXKCTABUV5RvwFfO9pjHcGQmIgd+sJ4ShH1GrM7AZx+qc6zqyPrCxQs9PEK9afj5QxWJIqv7AAAgAElEQVQemI0wxjBfcXzuZINntjIemdNK5JVuwaW2H9sRBGhWDJ97sMHSrKNvhHpcaoxEiyJnBRebCS1f+Ron3iNRE7wxpVnm+Ps2Ugq46JaUplEX8l4Bn3++Q9KBTjfgM9VDSn5who2I5uCFVAsnHOD3d4uttRjn8al2ObMNqN1VTnNulsVSHaIJTzYVxpf3Y0e7Z4pSs7jnOEIfsBOGp5NTqa9TEjDFFK8X00JqircMIR93nGxh9mVjuZqObiPscjDGjyeBwkDgDrydbFxShiVNOPxQR8AMbu5rZZzB1bSTJF5GBRGURWAYF4DWjQsZYyamFGO1VRh9v2XwccCnwl2zTs06a0oPrdQc53YK1QPtPV8DPX7fFfxAiBdVB2Mi9YOaRDbx78+eqHN3Xd/a75yP+fwL3V1RKCELDK5oh80mSscYa1heNHzonsqITvzQoQpziR1N9bUidRt/7HBV19RCeGAp5sxmzKWap34PBK+TWiETfu2BBnfVI5Kq5ZNHY1Z7gW+uDrjYDcTzhrtXIl7sFZyqRSTOsCGBYiFwfz3mc+kif3/zMLZc4P8XK7xUSfl6WGNtrs/y1u7OlCD8Xn2V76Z9PrFUH1FSh2sOawyNWfiVQzVWWhFXfcFXLw/ILeQ5/M7zXU6uRKQWrqVe3bzd7kL/4bmYk0sxPhUS4JfvrfPPn+0QGmokOkmrziWWr10Z8OxmjjPwSs9DpJ3LkCtl/NFjVZYXHMYaGhheaucsVCyxN1zaKfjxpYz4METzpXfVwKpjf6mDkyAjs9t9mXuRIV7Ua2Fs+QDh9b4JBdp1s6XGrvRPyze1Uze5Ld9l9J4BoXJYueGDCpfKMS2Mgtfu58hDzpexM9aoncSwq5uURVzpw+WHZp0HaMN8Z9ztNIaRCap6rL3Bk3uablQWgFJmXE5pwylujWkhdRuMJp4idiXaT/EaMLn2H5BoMgxI3QdX6qcynQ66Uwwpw337lwN+eNcvltNwJT3iamY0Yn4r2mGSDrF1wQYdI3d1mJ9z7GSBS9uexVk3OoYrvZt3WJQe1CgM6yFfheoxHTH/yYWMU9WIexdisiB87bKuRDVnRkUUlPYFdccL2zmjQOF1pcuMESS3SgF1BcSqk3XZlevkQs0FaqUVwnbmudbzOKOGoCbSqay4UtI8FYMphPyG0IwNK05Lw2ONiE4BF3oFc4njnmbEy52Ca5knBZ7t5NqdiITP3d/icD/mb//1bh2UwXCKKvc8dTcvfHKD5vcdtfbYn+Kv2OZ/Tq9xtO/AMfrda32PAB8/VuXeef350yRsZcI3i4FSnhFcLGm6IV21F25CWxS8IbJK3+YBvnKpxz+cmcEZ9eZ6fjtnNjK8ZzHBWSjWMi73fNlp0e1E0e57aW0Q+Mff3eC0ielmgafXc+IlM77fq+PfFSlpsbI7FB8Uw+PMeOoxGdPYJhoLyZNFq9Rhpt3PfRRZKF9vqsJyE5ub6vCiqiNZNviO6PmT0kzWAcEQzex+veOpvWFhVWojD5rGO4DChDfen24YyiwCRTtgKwbfHVtTTDHFzTAtpG4D3y4dhRmKVafF1GuFTUrRdLGbarodRuJXufkE0W23UYpSJWfsW1NCQjn9FOnTrqvr03jog4+EZMHgWvsXET9QPc2Qpgy5isFdRYsMyQQLfPbuOqePxPhH4N+d6fKjbViOLefXPS+2Dx6N1wMD1xDdbs8SbHlcmS6if/Rkl9lDltwy6hqlQRh4oTqkUBBubHqyGwK2nLCKZZRBmBwqBcG5cD31vLiZc18cI0b4+it9doLw8ZUK/UL4k4t9rg8C31vL+OB8gq3Ate3ABVMgwTArhncsxnQS4em1jEEuLNUty1WLF2EYH9cqx+OfuJRhAxyfidjKAx9YrCDAfWv1m+qgLIaZHzX4gw9eI/eqUfudJ7pcuJIRtuCVouCP8i6fvr9GI7H8dCMnZEI9jIN4ZxPDB5crrPU9z1zNb19Yo0HH716MmU8c9RZsdVWY/sRGxndWM9Jim08erbHV9/ybJ7r81iNNZppqPXC0HvEvz3XoFOMdPXEj4/RMTNUZiiB854WUtY3AepSW4ce3KNpDqTlCNUIHjhhSeonV1RAz9EstktXCa9gxMrGMpkGHnaahJ5ptCIlRn7Ooqff/3nt+EvEwU9KMrUSSJUPIgxZrudy0+LGJHqNkjMK9h9DPipLCfJW2B3vf27dCmHgrDq0a9hbVUgg+1eN9q4yGp/gPH9NC6nYYtprNWKcwxWvHQeZ+owkco35CN9UvvY7IGihtDg4QpRY7+jQKOh1lY4OJZDR553uidgSotYLkJX1XUn7OG1xTKDZLUXNfHZqNNdw/E3FyLsb3tMj6xeM1/tmFDubKHiG9l5F5qTGGdM2Tr5ceSjWLdahGxTIaKzcG+iIYGW8rCPzJxR6fWK7gcvjB9YzrmwVgNE6kIlhncCtGC8Rq6TbdAILhTy70uXstJRRwqeOJ5+Ebzw90irGlU4zfXUt5qa1GmFf7HqkZqlvC5x6oU4kNbtFwYj7iG+t9/vHdc6hW2XCs4fjJZsZLOzlzqWGp6jh3KecnrZzIwHsWEpwxzK0e4FkxgaWthLQvSC6sDzyrgxwKECMU65bqAjSCxRnDp+6qkm8GnrmccaIesTRrua/ueO5azicbVaozhu9dTfW638QWQkTo9YTPP93mniTmb99XZ6Fq+Ui1yolWxFcv9fngoSp5gBqW//R0nUZsR9czBlp9w2Y7jO7v9TTwL1/osFy1bHQ9a+te40+A2gkzoqOLbd1/NKu0bkgD+Sb4VCfhXM1CIZyejwnAS+2CIvf0X9BOZnJYNUwATtQBP/SULgO9pvHCmCLzfX0vArhQ2ocYLaKyG4HshmoFk3m7T8tkrBkZwkLpR7UN2YbgqlpExUv7CzCAoj0e8hhOII626/brpu4UxfY4Hmr43r4ZXA19fwlUjwB2v0FwvqUPMcFqjuF0WnAKmBZSt0U0U0483YH/zhSvDb5Xik8p6YUJfZSIqKnfm+lgLPu/djU12JRMx7aLDriaak1c3Si1VdIlwQuyozScrY0Lm2gWkprBVlUsD0Bhxk7mw11OTjBVDdhAtqqRKy5AdcYSzRuCF2xVMDVDvqXHKn5/gX+l5/mXT3ZHC4iJzCiqZ2iYOIyxGcLGBltSRK/c0Mw3gFowfOxYlUas3Z0X0P+4PoyIsQa8cLQWUbFK9WHh9ErCpaueZ7dynt3KWa5anIHff7HLctXxq6VPVRGEL631udr3fO3KgE8dqbK8eeu2Q0Hg6y/1kC78dDMjd2WWYK67v/9QvIvGvW8+5o/P9uiGLr/2zjr9jcDOIBByOD0T8b0r6b6uVMOqwHzHQ7Gli/GgI+THRHVgHnBwdz3iVCui4rRQbM4YjjccT6/lzNX0wvT7wmrba2dx4v7uFcKFji8zGlUvZKvjKVM/mNAG9sA0hPSautoLBlcBF8GvH21wfEEtHM7XC/746c7IUDO/DpUju+/toowzclUdhHCTxcLEefC9cbZd1NLYKEq6WuZueYn0mNNx99T3y47Xzbp/B7wH3xC8im0ZO5GAULnJU3O5PXkjj3GKv/GYFlK3gbG7F/Yp3njYpOzu7JnAkTDWgkTNN0+jFrXA98oiIxmHD7sGFKWhoAQpNbem/L9SRxVK+mCgNImIvoaht9T5vGA9F+YjixTCdy4P9r3rxI+1H1KoN454wAMFuBlBcqM0cw9cU0aFTr4huMZ+R2yblDomA/FsOXEVwHfHr/NmiGd16tDE8GsPNDhkHCJwfDHiX1/u7dN1GWfoVDS+xjilD52Be2ciDtcs13qeaxueGz3PxnbgUw/XiMtIk0pkeHQh5uplLbpkzfHfyq2v8+/WbvDjtQy/I9gGRFWrlGxTO4c7RkYUkLGGbRs43HCcWozYygIuGAQwkbDV86OImiHePxfz83MVwHC2l/PltR71yPDukxUWZyyJE3zZiegVgbVB4GjdcVfFIQGSuuGqGXB5W/VkP7ic0huagh4g1FYKbFwQDzU5NtaEJkQ7W1IWbwAGzQVcaTiOzTrtlAY4WYtYnDVcdvq+cXPl+6Yc4NDCRsAIvq9xSJPUoK1pJ0qLdO3AMpwkrOn0qbmF+eskbKz3X9QoBfCz5qYPRFELfFnI3I6CezWIZibe228AFRfNqrv8zcLEfxbg+1owH0TfTnEwpoXUFG87XE0jQDC7O0+Sl0WGCPmOYKv2TelMmWhMHSgdoVNympsno8m/qKH2CsYZsvVA1tEP1qhlqHk4sRTTTgOvtD0h1YIirxi+cL7LoQS628JmFHB2v4GVTShNSYEoqIdRrTTutJaipBHFT3jyBCGUdFDoQ7I8PjeuocG1ZvKcOu6IIpk8H4frTl0NCu3ALVctFvhbd9eoOsMTqyl/9fyAy8A3Zvq851CFuoW6NRxrxFgMi4nliesZXz3foxgIaR4wjWjU0VupOf77B5UT+un5W2jG0IbA/51cx+R6blytNGQ0Boch3wx8/3zK/QsRi62In25kPHst4+8+1CRyBusgqcO1jcBqu+DrL6eYUtB9rOFYqFg+vlwlKz27HpqJ+emRiF9YrrHUtJgIqrHhat/T9/Dvr6hu7Hw7Z8FaiiC8uFnQcIYvXuyPjjtZNPvu713XPy5DrmXc+baJGsdOfi+etbiKaHFkoLfjlaZzZQGO4KuW5sM6eRq39txrtvRDKwv39BK4lufe4zHNquNCp6DfLCfuCkj7Mioc4oVSu3ULt/Pd+yr/RPs7oHvxeui7W2HyXn4jYBPzMy0+D+kEtevfnGvys4hpITXF2wp9Oj6YNjWxLjDZlnYa8g3Zlws22k5pGvh6C61iC/IdpfRMFXCGuHyiN27Y+h9rV7J1YeGI47fe0aIeaSfpr18a8N0rqfo19cHHcKEszIwz2EXVg4mIUngd9cca+k8ZY6gsl/ShVQ0XpS+WcWXhmYDJ4aP3VFhpRLzSKfhBmu9iMm6m+Xk1uNTz3J0obeSDcHmr4Dfub1ArrR8+sFDhfD3nwo7nias5T3cKPnq4wgeWVOd0te/ZSj1feL5LsaXTWV97ps/iey0LtYidPLBcdfiyA/LoEcf3LrT5YGgdeDzfPNVisKFfG6MdjuGiHrKA24DffG+DdzQrzM1Z+t3AFeuwOWA1NqhbCF8416XqDVlQmvVDyxV+/lCFyMKjczFPXknJvN6Xiy3H8rxFMvX66hrh310e7OrMfXs1JfaGkKuw+dLerl15LSQMfaEOuN8PuHf3fi9qmZH9R7YZWNsUvvFCn4/dV8FU4BurKX0BV3W4CYZ0SJHjIJ7X+zRkQugLHztS5cPHqriKoZ0Hfv98l26hnScbCaZemsGGV9fVCWlJPcObMv02ek329esnp9iPKX1555gWUj/jkKCLubGvLVPuzYTvahFhnApM9y4awwkjCabUWQimzb5ICCnGxn9R6+Zp9TeD+PIcRYx0KgF0PNuUWXVDl0YxuFldFLIbAsZw2sY0S9G2OOH9xyr8cCcru1ra3RrqvMSjbRWjC03R1ZFr3wOq5TGImhfGc9r5GotllQ7zPaVpPnGsxnvmEqSAY4ciZM3wg/WbhxHfCUKqnQxX0+P98sUe728kVMXwzFrGmoTRRCBoYdeoWDB+tFBupru9LTbzgKsbfDcgCOvXA7/97Q6NJS1S/u69De0+Fir0/R/tBf4nOcYvyOwo1SZUq/zuO2f43658HVtX4TTs8RszcHo54h0rCUdnHDY2PHZXlcubxchoFRGMh//6HS3iyHC95/nilS7vXUyouLHv1Eoj4uKO58XtgnPbOR9ZqBD7soDJhc0tj0Rjt/ufbOSIwNFGxLW254kDXOZDNvZRi2dfP4XlKjoU8fjFAT+8kRIvGkxt/3TppKGtrSrFVlmGfAe8Fd53tDLqDrZiy30zMU9uZMwllkdOVcgGgR+tZfhXGWBu4/ItE15fEXWzz7BiW+9XmxiiOZkWU28AbGUYR/XqJqv/Y8e0kPoZh+9MjDrbN1Z/8HoxjDwJqZCugk2EeG6/jiJqGbJSKxVSfbqdnA4K+VhjNAwshpvrgMRrsWATLciKnfFkj6kKpq9mntGMJd8WjA2qLbKqe7LWEh0qyLd1W+01IZwSNcs0hiwKuIah6GkhZWKlBCUvM99GUTOao+ZL/Um8AKFndtlsSK4dMhuDawm+XX7fG5ac+gBRhsYuV8crXUiF9LpOtsVLhnh2t3g2pKLj5BMdhknDVMnVciIN8K2tVLtiVs/7c1s5D5eu3Z0gXHGeZHF83Z7ZyplLLPfOqCbpL17uazHqdRTd1nVbgwGsJYFr257lyIEIlzc8L3cK/pvaSyRLdvf9eqX82+vx+45QdPSDP2oYbGzxVWg1LTilZQsRxBm+tZnyzkMJ2zuBQ4mlGuvPHJmLeDStUAThkbkKidNpuXYa+MIzHS6nnpZxnBM4MStsdQq++eKAjaQgqtpRhymeNTy1mfPU5oT1+B5oTuL466Ebue/razFxObV6BwWBeKXcXBOleQXytn6g79N0hgnRelrq+CKd2pRZoagINhrfHwMv1CPDb56qa9Ec4L67Y37vpd5tj2sSQ2NQwusb1Jn8DMOou7lPA9l1AaeawUg032/ve3uKV49X+yA6xbSQ+o8K/6G1am0dZEcNDo0TpDCEdP9CYCuGeE4pLpFS/F26Otu4dDiOUHG2FfJyQi6a2d+FEym7V2Xifby4e1+SmlG3aLhIYsqMs5bBlQWctRYTBfDw9LWMB7diHlhK6BWBP788wPdlFMoazULU3D8FZBNDsmTVWLFa6nz2Dqw5LZJCMbZbADhSd5yqx5xuRVzYLOimwsXuWF9U9GTkBp1vBfUT6tvSi0tGTtJ7R80Pwl6j1K9eHvByp6DqDC/sFPQPoFS/vZry7VWtlEPZlQupFolJDT55qspdSxGXBp4/PNfl/mqMiPDseo5t3vp4/EALX98H4wUjMDtrqUeGV9LAk+2MX6yqHcHzGwWXpODJXs6TL6un1N8/2qTmhFAY9VHywvcupDy2XEEs3Mg8W5nQD8IHZ5r8wxN3kVilWr90ZZ0XVjskS+rdZdyQ4tVrGLVuoYOqltdwj/Gk7w4DsHWo4CBD0ElIEA3DzvSeUc8jGU3/HXT9XE19z9yejpVxhq9eGfC3j6vm7cxWzpntnFOtaETfihGWnCPpQVq9dd7lvn1bc6Bb+etF6BlMomJ4Y8cxTZPv7WRpWhBM8dZgWkj9jEOfWNXZeG8I8NsNVzX6dNnXPLtJU8C9sFWIgsGXIa75juAHhsqKfpAOI1907HscT7EPMtG9yoWiXU7glNErvq3TeRIodVH65E8QaJqRzsQlhsohg++r8eGfXevz1dXByBhTR93LXQ5HpocUhRkbFt6uiLHx2OJACi3mYoHfeKRO6gOrW56FiuXLZzv8VMaF1JD2kVTwfaF3XnRcvmZGCw3oNhlNiZWmpcUBXY09OLt9a1H4rteQ6HUmKG36yYfqvPeItmNWmhEDH3j85QwM2EVwPb1fb9Y9tQm6OBsh9A2nlyI+c7KOM4bVnudfnGvznRcHHK46rg0Cz/p817F8+0bKr9SqRA428sCTr+SYXHj8lZSkZjCRoahAmIV/cHSFZOi+HcOvnVriL1e3WZ3NcVX1P5LUIFYghcLsjz4a7Tsy+xZ3ES2i/EB1cpOdmxHNWh1/P2TC4GrQAGFjiOfLgOztsmBxBxdT0Yy6ix+ESz3PPzvTwZmxsetmGggiWGOQHLr9QLcTMH63V9RbAdcErCk7uKUQv6Kdk6ipmi9g13tbAiMD1immeLMxLaR+xrHXJO8/FIgvaSTRybfhAmOcodgRDQmum1HSvTHlxFwCgzJEGC+Ewe5YC1cDKczo6337zSGkQRceUwYoV3Q6yriyG9Ubdwx8B4iF0DHlNIt2xygNDF1VixtjzGgRGu1LfTAZfpb7nnYfACJzZ4n10axROgawkcXVDXMVS9UZfCpc7RdIAReu5ISFcfHh6obaCVMaIiqVVKRqyBk1DeLNgU7Rr1VHN7pmDZ1u3ItkyVDs6D6X6pobN+zcLFUjouaw2DHY29yvNjFUliyuHvBt+NQDVUxmCAaWIsdDtYSfdDOe3s41M29iMQ2Z8NxWyqUbGfOHHDcKYSCCz4QvPd/jY/dXEQd/fT0lMY65JBrZYVhjkFi4/8EaW6WPlk001LdoD+9f3Y8UoqHQt6GYfA+GwdquNnYzl0LIt/X9EdJxNmRI0UEIq920eNYiueZDglKy3NrP9ObHMnH/bmaBr1zq84GlCmkqfP1snyAQvUqd1BsBY/fbLbi6GRXUY6pcfy4Mxg8qbyREdAhlLyU+xRTTQmqKtwV+wMgLKfQZPS2r8Fs/0X1PRoXUEBqfIXh3cPfKuLLQudl+uwDafZKgVKKdWHi0S1Z6WN1QjVPoaTEUMijaoiat6diGwPd2b0PKFWlUBNrxE/NBCKnmOWIEROmvyd9NlqzqPsp9bPU9NzY9M8YChm4R2CTg+3bXcdjYEs0KxXYoQ2IhnjG4xmvnWiIDv3CkyuGa41LX883rA3wxcc26cmAhNaQH/UB48WrBXccibKJu19e6nuUoYq248y6XcYaobpFMqSbjxt0IKCf6Dvh0831ADO0M+tsqgndNMLHhkvN84eJuHdDVLONIMubagoFz+ZhjNU4NWk1UxqpUNMdwOPxgk5vkRw4h4+3cycJva9ot9D2IZq0G/0al/gpYnrXEsWF1EG69oTvAuZ2Cczt6TUIixLG5I42lBO30IremOl8vJrt3EnSgw9XfPN+/UXiygXju9pT4FP/xYFpITfG2wCal2SDs1oSUT3shl5t+UMWzGt1gXkP2lq2AGWjnIGqCSfYbBYqUQuaulLoXi+SCTwUTQeiPk+dDrvSLFmQG3xOK9tB8UTUvGO1kuQZKs+45bp0K1L9dUzCZPm0PX7+JDG7inVp4+MJzXd5/OMHk8OO1jNwaogO0NTY21E5YfF/P+UELoQbWlqaescEqC3cgPnq4yjvK8N/lqmPghcdXB+NrdsD23zkfs1JzXOt7nriU8b0rKWkhHFlwnK61+B/mDpEsWC5lKf/02hWu5mMqTkQLWRGIGyB79D3JouHbnZS/NVv7/9l703Bb0qpM8F3fFxF7PNOdyekmCWSmZAJOSDIKCMqoPPA4ttVllW1rOZStJfbTf9ouLbG7q6sB+2nnKkuhWilKwYJUKRRFTdJkkgTMJOeb83CHM+2zh4j4vtU/1voiYo9nn5v3JkPG+8CT556zd+zYEbH3t2K973pfmBw43Xe4fZBiFr0FyDG4uh3jyvUIm5HH57az2do0xf/zwCP4l5dcguOtGH3v8d6zp3Euy8WmwpTCXJOQUsUsdLDTjLuRaOTmdaWKawIqwg/vLRKK0KfjnVUTEZqXjreFKJaO30uPNfAtR6WSvnsnw4ceHOBCIVyLri/Xqm3Pf09+UMa9OHvxO+JF4ZrLsZpHYT7p1wlSAZ4jG6jxtEVdSNV4SlAYvRnRNJhYnKjdDsP3CSbRzgIRog2WKsuqjmlbJ6PWRb8yq9W/LGyHQAkhi+QONlqdvst2fRTj1uKDU2qu8j0GO49kwyA+TEhPSyci22Ykh8vOgFAyVPhAmZjRTAjXXB4jyxlfOJXCe0a0LrovtycTdi5nEBsx5Ey0MOtJ5yZaV11VTOgbj796YCR3xocICY8Xg5PHO1qRwNn0CS8mheuyELIvKdYTkcVbr++gHRHu3M5x4719eD+urTvcHO9mHW6YqXNWxTccTvDKE1KlXL8hMp5Pn0rx+Z0M/djghw8dKh57WdLA/3D0OH7hjgfFGb4pXaXGCHjbNR2cWLd4wnl88P4+BhUe6o7tHA/v9dCJJMPOTTijc16+x+tOJnjjlVKZEBE6DVOI4ifhU8adm0P8xOP34KhJsE05uCOd1GKKTHU7bugxfFA7kavSIXMZYJoMtzeRQRdobb3+ZnXwACl6zZI0XctSUUQxM54ZRzg+JDwCf2BtpE/L7loV/fsk/DrqAs1L7Hyzxso1QFZ0i64vRXYwT72QYFfpbo8k0zLf1mt/xhTw+SLqAjmrfu+AN3A1vrZRx/DWeErg+ioAzUvbAx6KgMhn4qUUILSMFFV+iMLN2w1nb/ugYEcA62vPuGknyF0uxdr9SqTYsm0qujauHyil8S9puVPXzk5cbjA2wPdc1cG3XdLCt59o4S3PaoM1t8xEIjTmmIEUAErHctdXnUxaxsKwdjuIpDs2az9mHe98R0T62baH05Bmn0oXxfUZr7+qhU5kQCBc3Y1wdRRJzuBeWbSc2h2n30715N/Vc1bFFZ3xyurKlQjxGuHEMYt/fuUGjjdl2i7gmmareM9uIJNor7i8iWO6nRMti5cen64uejnj8aGf0qkBSiNrDM/liZV91f082Z2+l/Q5lxObAOCAx3opMo0syre5CLmeOt5Oi+nqYQjMrhato9Ms59OjmJ58sqjuTXivXq+vg8ANpbuTbXGh5wPE7NTtyXnJdxdvwzbFyTxe11zKcA0PWSZrLzAoAkxTxegdGQAprv0L9J0hryPvK1pdjoat8fRB3ZGq8ZTANFA4dRdZYg3xgCKDmXoWQCnAQfnzBdmXqlHgrDt+y+A00GpAY4OQDYFoHXA9McWEEb2U7UhhZhLVuViJanEDHc2OZWG5ZCXCkYYttnnVeoyVBmHYAJglct5mBDYAHBX6r0AXUlQRMnuhuthpt6op0SV+WNJ3s44353rn7pRthIyR26bQk62K0Jw9CuNN1wv6E+AzZ1MMHeNEy+Khfr7v9N6ZocdVlW7MOTXrfMvJNqLYIzaEQwkh8w6OgdQ6vP7qFj7z0AhncoZpMTorBiYBOi3CM1oREgP8/RMj9B3PpSDHzndDBggYwFk3rh06PRxf2fMd0XuR1UiUVXUrTyoeRS2AR4BdAZ5zNMZzViNsrXrcNBogS4Go65FuhepJKDDllwkAACAASURBVF1LwDetNdBdIdx5JsVdTzhQc871dx4QinWEFx8Tc807zqV4aNeJE/pBoIfDZ4xsB6WnWSQWHsweVqOLFqFKy1ODwEPpqk52LC8EqJiU1Ncc6mcP2NdK4ssJzrkIc/5Km6iucTDUhVSNpwQShipfGqF7YjvS4QHN11uYhmaQYfH000FAVo0CZ/gfAVDjTFmhX/OMFl5wSYLMA3/64AD3Jhk4F6do6UoB8ZGJybCszKsK3ax+Xq74ZAjcYuSGkW3LtFZyhBBtGLieitU9kJ71xV19NQZDaFEgOwNQxIXGiowUnckRnWqS3N3iuEVd0WsRCb0JQHyqIoKNgVu3MrykJSvdAIy7+7l6WIkYnp0I+f9xK8M/blV0TF4XrhnBsDefHiEywOWdCFd2LV54tIFr12IcbVqccSM8wH1cQWL8uNogfMH08PzLElx7Isbv39NDLyd8oZfi6vUI160lsAYgsvjVGw7h1nMpbnpihE/v4+ZuYoJdESPKW3czdE4bXN6yePxMjr+8awDeIEQtac4HY9bQBbUtEssIFn+ifAtFiPaVR2J85xUtEAhYB9Y7Bn/+8ADpWS/TXVCHeCK85pImru3G8CPguUdi/HFnDw9n/oLQTj6TbuXNTwxx+1YKawhnBw7Jkdm0ls8YuRqvRuvS9Q1Uqu0CJtegX8vIt4D4qPimNa7waOQGiA72WYzXCNwFGDJlSxFf1Kk325RusHcqC2Ch0L/SJu2ybS4me02EJ2VaWuPLi7qQqvGUQCZelN5ALvEvh2nMUXkeLoZD8aJt2pZM9z2zFeF5hxIQCIkBXn9ZC7/2pVw+NcRzp/CqCDTV422Hjz82xIuPNeCY8RcPDbC3KXoOP2TYroG1BrQinlqcA8iD2HiGL1CHJPstBY40CDaV6TdqA+HO3KdKHTZZpplWANMQR++QwxetAtyUTtot51I8OnLoxkbCa1tAZKkwOJ2j3xZn+JEI7JNDE15IDHz8sRFuOFo6r3djg9WEMBgwPsubuA+76MQRrtgAjhEj24vw4J7D8VaE3m6Oux/J8dH+AOvGIIsY1x1KACI0LOHlx5u4eyfHViqdJvZS8MCKZQXnAFsP34MUjcz4xBMj5LuM0RMenAEmBexlki1nOyQu48n41F+gLuON0jn7sk4kRZTiitUI9CjBWAPbccj35BJhx7i8E6nzvQweXHkkwSNztFmTYJZrAk66YGNu9BqPBAZMStheEx+1YFDpM+muVa93PywnHN2AC/rPDRi2K104TlmMPivn3BgDJLo/u0LH2+5y02tkCfnW7Otkch8512GN6gDIjN/t93o8KCdo/RAl1f4VAiIJmZZ/fHn3pcaTQ11I1XhKEKZc3A6Q7aoGpg+0TnKhg7LtxV+U7KQzQnZ+jAGz5veRdJVEQyTdr2VBkXj0tLqEFUt4RtfCgfBAL5PvOxKxdrBOmNRLmFg6N24o2iOfAbwLfPZsik8/NpKFy3r5vVPvH6DQKnEGwErkzKIv/2gVeOFaEy852gA7xkNbDn/00F6xiOZ6nH2GIpqGJqgkovHfPbDnUBWymERiS4TOlAXdtDEeiBzYMjVEnHWkG1aLnAyABW7bynDHdoaGJTRtiuvWExz1CRqWcLRpcaqX4+zIF8XA7Q9neOSEw/qGAYiQOkZo8jUKylM0TOwg6k/PRc4cSIof1vww05D9BckgAHspiWyLCpf5maiYQk7SguHf0Rrgc4OYRICfnmE8vuXQrXSIJp87D+wY6TkJFzYNgj8rn5PCvFONYwFM6Y/yHcANpFiM1sSTjYx0KgNdLkapUuBQjOLaidZp7vUt2ZD6oj2COYTlMOM6GadSNX9yZ9xioDoJG2+UheR+hpsmKSndC0WhXkhEa4AblLKAGl+9qAupGk8Joi6QQ2IdAkIQsevpv/18V2hARK5B5DvL+Zo9Y/SoFFK2pV0FFQNRNN8pexYoImwNPK7aiNBtyeJ9duSKNWtMTD4DpiE6J0510dDCI9/WhR5CN8GrZosIXrsqFJfThD6FxKAkcldNtuwA2IjwspMNCfxlwmWHIlydxbh74KRAskIdFIG9FRxvGlzRjXBm6HFfb7HOyTZl30aPsdAyWekkD0iXBHvjGYGT+MfNDNcmMRJD4JzxqbMj3K7C9edtxLhuXTL8TnYtehnjQw8McHbTId9jZJsegz7wXz7dw8tf2EK7QRg40Yk9uJfjiUGwqq+MpTsGDAE5QA0GcoJ3pWO7SQjNywluTzVlut/pOQ/f10ggnZJkH4p90bSYSP52z26Ojz06wNVrMXZSj48/Jh0msnIdZ1uAGwrN96Ev7OE117ZxaN3gzu3Sn2k/5DsAaxwOs9chCYBzyWY0ieY45tMhs6y2Fn4AkOVi2tUkhKhbUs8Mh7wHIGcMH0Nx4zHp4RZANkzKsRYoy32uZl0nk1RqMXTC+nMiNwLV37HRLpyXYmS+Az4hvsCygAsJsuc/fVzjKwt1IVXjKQFF0qWxXSNanlTcmueJzGdvRFv8BsCMO1ERU5du0NGTuAuNVoFjXYvbeznWc4PcM3YzXuixNLW7RhY7zlGah1L532SDAF8KywtaKZKuiO+HyBt9nnZQqnflngEbS6AyCOBKpyjekHgPise7Cpe1Ld56pUSqAMBfPzbEP5ydrTNilmIs29RuII1TJFd2I7z8hBzov3tsNLcoO9K0cJ5hDeEjpwa4zeXFXfgXNzOcaFlcvRbjpsdyfOj+Prac5MmFKTiTAPftODzypT184OEBnrUSgUiKmerpMEnobopA3eeAe1QmD+M1KUZDwWEbBrZyjbg9RnZGc++80K0Uiy7KZ1LwU8sj7xF8Kjq7W89luPXcdFCxaYglhH9MCrjeNuNP7+sjWT/goDTJZydaYdgOwY+ouA4Coi4VdhcmQSEwl8cz0EDh2s/MSE+Ldsi0gAQsBV8PEi4cswjs+wzM6+IyhNo2OFB+p4kJZsIs13YIbk8CmykSLaXPoB1lfUxbCigyVOQVFh3u4eJu01diAVXjaw91IVXjvHE+WVYmIrROWtV9MPJzABJG1BTvpEWv5QZeJuXUYmDs714oAjYQTypLMB2GIQOnd+Zk+UCCzjO5Q8aMs+oSfXroli6iyjc8fsccr1NpjhnT2DE0De1k6b/HRvBzyMQTA/DSycsz4C8fGuA1l7VgLOHunQz3VuwJZlF5AHD1WlwUUQDwdWvx3EIq39QiYo9gOh5wVPgHtSPCmy5vIdbF6k1XtPDv7+yNCesBYCMx+I5Lm1ILZsArn9PCXXf3CmqOAXz0kSE+cv+g0PtIASNj+NRV/y8PwImI+O4JGwY3VGExSfeTcykyKRE6S6KD1NpgV86LbZcFZsi8owTgIQq39Op5kOxCORcSnk2gNf3bjM+BicIwBQN8fsaU0arQP5KVacQFP2NEE5+VfFc6nS7nwqLDtgmmZQoNlGmVtBw7Nc50UhCR0RhJ3a5ZMEXGHlKUZTLRmUUepIazhc6J5x+XKoKYP4BijHU7AXkv1YxC8ZyTIu4rkbKr8fRDXUjVOD94ID0tLs7xBh34zs8P5PmSdQfEK4vvHv1Q75ohobs+x5jbt+tVBKVGhMF+D6Cu5GM5sEydLYrrCK+lU00Pw+FDpo9vON7AIGf87eMHM6Vxe8FME4g2VI9Uaedn25JPZ1uyyJWTVLoQdiBUDtTYURdUWHnsoaZBMiT8zeND3LuTYztbrsrr5eMWALvZdJyIz8TryI3UL6vBsC0jE1FaGHYjKoooQPIDVyJCr+/lvKouay0xMLqgUgI0QWhaQm+i4OIMhd7HD4B8oExWDiTr0n3wI6kpJ2OAqpRQtiVFMyCFiG1Buy2k2jxd5LXAcsNyyjJekwk8W7keo1WSSJYVAqwWd5AiODuj7319emKRjBSdIQ/SzNHBuIEUgLNG4EmpULm+PeDFjsHTOJVHMUl+oRm/ySCaiEyxLIULq0Fmh2ATQt6Qf9uWaKYWaXaMFqfMDGRyM2SakGJxVYrVXAvi6CJEqTBUp5dMH/MaNb4cqAupGucFdhDNQpgsO4DTrxsysi1f+ByJ4cu81xGxLacM02B4rwaZk/4w+nwiAlvJyMPEtNKykzF+KIUEANx5Osc9exIMTPuMfbPngsYjopKaggjKq542weCQrHhOMcpJqlAQhoU47HzhB+UYh1oGP3hdF41YFr+NJMXHHl2u0PvMmRRHGhZXdiOcGTn8VeV5BODSlkE2YDzQc2AvWrC4Y6Y0M+dGHmdHDodV7X1u5HB6zxUu4rwFmAbj4SzH7iUeK7Gs8I8O8rEiip12gxoMMxJNkl0Fsk1Z1E2C0qB1JGaYFJX7w6yu8HtCf5lYpiEpoiJGhtekiJNifHxSyg/LX5kmTU1JVq+3fA8gz0DCMJF0OwEdPJihmSuyG7UD6zPJjwzFaCGk1t2afG3RZ8nf3R4DVjqYbshjAxTRKuATGeDIt4FodXb3lazYiXAu12MYNkgaZRdUxPqLu81RR4pSn5bHrno8x67lBV5Ocu72/2xVj0euOYY+ApLD+z6lRo2LjrqQqnFeCHe9ZA8+Vux6rGGvHqZFRXae62uHqjIVlm5KeDBIOgPNywyoycWXdqAQbFfvoo12LbZ0XDoWOo1zLKQOx8Fw6t4crTLyLXFfp0gmi2YtMMwigPUZwzYMTEsEwn4IRGuyqLk9WaQollBXCTtmRKsGJmGw1jNVuuK56zGevRJhK/O4+YkRMu0WXH15jGZLw5eZce1aPFVIzaNXHAN/+tBsy+s3X9HCVZ0I7hjjS+cy3HjfAMmRssVR3WbOwH++r48XHIpBIHzu7AiZatTKCUvC3pbH++7bw/M2EuSe8blzJY3ITiftvBQR8UZZVXeu9si3CaYNRB0DEzNGT8h0mdtjKd6NFvMZiqw677Vj2fQAWeQ97VCNCDCMaEXGzkMHqDAvpdmLfnjP8EC26eD2pIig476kZZPFdFY1VibfZcRhQs6Xr5HvSmfNdMq4JDJSxPlULCyCY7dp0tjrEUnRyTmDwXB9mhvhIp+T6e5lmHp0Iw/AIFmfP+1q2tKBhI7wE1Px+TIN6ShWqTf2PLNQynfE/oMMxNutckM0E1wWaZhupF4wsNchGCOdv4vpZD7v2NT46kFdSNU4EPKeUGUgNaI0B49LoEhoiKgjeXVkysBXP2JQj9B4hi4Q4UmsnYEmkJ2TLx/TVM0Ki7FgsEQQ8ap0H0bMiFcXUxUz9hBWtS/MZXeKc0wJfYvdc2Vwqm8wkoh0lF46B5yVwnHuSQEaraiGhhnp4yL+jQ9TQQE9ayXCa4824TPgyhhoPYPwkYelWNpjMTV0QynOtifoOTfQAF0j4vTJ98+udF4P9MjxpsFV7Ug0NR74uiMJPtlLsa0LdmHkWKFsho5xy+m0fP/aQWKUGiOKCbuZ+DdNH7dK9yIbP7gmMUiOlo81DULUNTLpZcR5W8T0WoTkgG0LReV6HtkmkCYOyWGj2jop4CVMGuARI1pXy4NgXjpxLfsRI9tmEEnHLN8moWNXASKL6IhSWT2hQk1EM493oNy8E1NKPi2Uru0C8CQxNp6R9xm8KUV/tFIWl2K4qsWTWEUhOyvHO14rp0TDUMK8IY4Q8Jv3WOweulRQ814zCfNd0YOJSeTsqbhxynBa0xQf0f0wVNh6mKSchCz2J3y2vGrxduXn8N6nXtcqfTgR5nyh4Xpl4UuWLsprBWsOn0lCwrwpyRpf+agLqRoHQqAZRPR8foGg0ZpSXRXqjUg6Sa4vX+J+IF/U8ToVnjPxutgBhImdfBdib8CiQwndhKhLSAeyHTAjPU2wHRnbX2SvEGBbAGfShYnagDfypSp5XrK/+Z7qm5pi4iiGjaz6EtGhiD8UwUS6QPXkC1M6Iaq/6QD9+3yRJRivo4jRuKRty3w9D1zSKPM17tzJcezxIa6OY/Qyjz+7bwBUxMyBrgpTb5MLQbalNKQWxPBAmkpRFmhGzhlZxsW3hB/Np2z8qDwvMIRkTYpl6cDNP9YUa3dFKa9JsBPvKp8y4nUpmDmTCbTsnL52X85v6PZ5ZqG+muLa7XMPGAmHRi66PtvRgszRTKfuIoNwqN0sIvhdMeTMd+X1bEcWwewcihw6mrPIk5UJTjdiZOc8WIunaNVIkG8ilJxPxYEdLF2dsJ3ycyLv3fXlpsP15dg3L9Vx/0Py3HnaoRATxKlqjfTfBc1nVWelxqHnm8Ya9hMAvBYk1eMdYLsyqWoSKmlF6HTlnOJFBOrnt19Lo6oIuEiJtNJJ1WMzYKAupL5qURdSNQ6EYpqHUHQcDgoiAmJtnTMLLRcR7KosIiYpF2yKCI1jlS4FxLyPvQiws7MQbUm37GaYBiFaZ6SnId5Bif5tHyog3O1TpAuS/s60ANup0FteF8NMCqyG3jnHa7I42xaNbUOcwRm2AdgGIVobF+ebRHRSJhpfuB7tO3zjqnZdDPDohInjX907xEdOD8A50DhGiCtPNk0UOYYzNSrVejiVYuUxdrilNcQLjzThc+ATjw+xtemRHDV6XGVxB6MYTS/fA6YmqUL2ICCFJ+dSOFa1O1M5aRX4jJGeDTEfYgfRvFw0cuE6cSMP2yWwk64mMiPi/q48Jz4MJOsGbDyyJwC0AM4NmIWCnZf95vZCB5JVT8QwXYCHojGKNwx8KrYQ+bYUhOyV6q4cb/ZcdLrIShHodfIvOVY+LtCM7Eo3/MljPHm8fUrq3M3wIxW07zOVStplokSOONmye0WRXMOmJdE18eqFiVUxLdKOFE0db9GQVd67+r4teu9PBapSgYP4zx0EIVLJZwwzo/tW46sHdSFV40CIuiWFcD68PrNEUvghl0Z7JKPh8WpJa41NGlVQzclzAwKvqolllS5QfY5pAUQiSva6iM/drwo1Fa3KFzxr/AZzSZ8U70G9bMgB2Tm507ZdIFkrJ5pC8jzFAFI1Qlyh4k7UNOX9NJ6hxpBNGlsI797N8ZfREM/qRtga+mlqLJcJQGaecnpfRFcBOommNgzSgpIF7G8fTvHZvRTZOcYwG19ECsoG09ukaJzOqcKPWIKPAeRMMI1ysVxEC+c7MjTg9uRYwcrE5iRtRUbd1zMUcTbJIUK0gSKCiNnAd7UL19BjveD1wzmzCcGuM9wugYeqDepKB5Iz0bbYDmt8zLh9hesrhVahVzmX5zPzlP4odCptm2cex4CQbWjXGCZVen3Jb/LgbRatlx0wtyefPyL9mzcXTLPDLDc+dgWI5qQRBOS9QNlPC/73g89EchA+U08WU9OOFwHheAfatsZXL+pCqsbB8SQ+825PaJDgUG4aZReGzHyvnSpNFGgD22RwaqQjVf3SEw0sQLLA2A7B6HSQT0UgHO4EJTB0nDL0Q5lCTM+JJsg0AdegstOi03Scl9opImnPR9q5Cmaari/2B3ZVRs0BFFNtZlS6U0uXRXQ2ZMvF4IubGb64mcGriNvE0r1ye9rpiKRYmJVyP1XQVLZRnURjL7oidkJXpSDwOhBXjUTDNhcUPlU6ZwyVLptM3cnPkacpN+7J7ZkYiDfEUT1atYBO5IHEmsH1ALfr0WoZmMQA7MV885DkOFbPcbwh5yrbVkpswIXObxJRN0R3AOypPNcjgILhZVsoahNLITe5gI/RqxlgrWw378nE3zzKc+5xVOTb4pju+kJ/zbJeWAQiEctzJpN5fsDASqVLeIEW9bwnnVvprhGM5bndnTCdSETg0cEE2OEmqPqZ+mpCXUR99aMupGo8pWDNPzMNGb+2TZpq44vZoSxAUReih9mUQsokpRcU2dm+UGQkCy8fOpgIAIzkjvU88j0gWlFNhiavS6YXCsqQGlLQBJd0NwAaxyvbJ0JyWKgVihiuJ0VZ9S6auRR0wwBmBNAqwWdeFgkKU1flc9yuUIVkZDowdP2ybY/srEz4xRtGpv+Upow3MOVcXj3WoSMVRNNgEfLCMPIBwyYkov91jO0LGZpZnBXmlBNf/m7AhTZo0jcoZA+KsFzObThG4XzP6sBEa6KDY2eK6VC3Taoj8ipiBuJVA6eeYWLISci3vXQKiRF1TZHbJpQWB712QXHOey9hwq1KwTSthFjvAAsXbdOS6UGQdjA15Dc5/CRFNyzb4gxAE0LrHZQK06ghn47TSvPOxYF30UuxH+xRqKEhyHMQXMuzTV9mCC57mIqTGa7PujCp8dSiLqRqPGVgJ3edfiAFUrw+e+LPD1W8C8nnizplt0g6A9PPcUMGnNJ5hsAjj8FdUhi1rnBqbAj5gvZQp3MUi5JJhDL0qUd6mgB4EAyoxbAxpooKikgNQSW0lXm8mLFt6UKgx4ABKDZazACcC21gVyY6GJUJpnRT3g9ZRtbz4FRpoRWI+eJIrBbSc4AJtgyVxS/blELDtIDkkCknDiGUU3o2UGaM5qWijdkPYWpviup0ZUAyp0BydPr8lLSo/kK7iGGKTCivctyemQsBe+EwHiKAEAosLaoyViNWeazLPPItAiD0sWl5cGaBMIywJiJ0mgiLDR5VeV8L3QxIjsg1Gm2IncX1axFec7KFKCbc08vxoQfHbSS6EeH5hxI4FpuHYRNwu+oVxh4+k6JHaOfpYhQ8/jf28nmpTs9FqwDrZ0B0NvueuvKYDrQTFUkXDVR+BsemyNpl1ExBU/Ps/Z6J0C1tSSEddadvmCZhm4BrSnc338VS5rmAfBYj1RIub3FSo8aFQ11I1XjKIIu5FBFk59smjDkzG/miNC01XFyZUXilKkgGYDXCJN0ui69sE2hfqQuP1amftnjtwJRfvkQkE1g9WUhNx4tmi2QcehbtKKP40yJfMiTvtQmhITsyiSjUmiyKk3RMoH0oAvK+h++LDse0GIhFP2bbAKxQSvkOxsJeQxyMG0qhxLnSSl1d0FIq2zBcPjfQrPthbGpvVPG7UiqVGXO7CD4TQ0qicRpMOn/ymPSsh+kJDURWfbdYPYoa8t59jsKFnKAhvC0qCrD4EGAyguvpwqpGptUFdpahq89kslIKl/G4E0BE9m6H8corW8BAhhievRrjqpUylqdhgO+9qoNVNR59zmqM/3TPHpx6NnEq9CpnQMTjtGbVXd26kuLOd4TGQw7ERwm2YUARITlE4DU1MiU5dpPHdhKuB+S7HvkuYBoetmPQOFoZoqhOkQ1Lus8PUJiGTu73PBAFKpXmdkynYMrHHXSQxbYIqIuoGl8m1IVUjacMFMtdKrvFd46moVSQF/Eoe/GLkk4TAZMi0EodEDoe8ZpM7XEu7semQYV7s+7NzDtk0SfJa9umTINNvkZAiIAp6cHxxSLflUWIqHwvfgjR7MzICKvuI2eAyxiUEGzLqBt2uUhSIh2dvKeaqmpXQifnnEMxtUempEH9SIxGwQTbLXVd+4EaDOxxQcMAJRUUbZBaY0hBYhpAQkAbBrvWSyckBxjioxQW4zC55EYePpfilogRBfqWCNFq6REGJzYJ3jPIS2cmXq3sPwM2MWifFJuCqAuYxhLvT89v0OnZDo2fI5bzOMl4Vevno01bFFHFvxPCVkf8q/xQncBR6cxNvP7kz+wZbkcL2IhhT5R/C1OR+S4Xxzbv62SkoWkaVikwn0ouZb7DMNYjPiT7TNFsum/W52spkH6elvSZM3GpY9uvs8Q5i8u80Qm7A3rZub7St+3pz22NGgdFXUjVeMpARuM69gk79plQMlanqkKECDCb2hOjRi1+tLhwewatywGz6hHFy9/exhtGXjdRY8c+AI+Zd+E+5Oaydtsmuhy2qfSc+hSZmBAfXe5LP5gwhtiQyak8ABpKO7090wTiQwbRmhQdk3oX0yA0nmHQvGT/cxEQFnRAIkWC70+g5UxTzSs3Adv2uCyyeOu1HTQjg3NDh/c/2MeuZspVi74wRWY9YfQo4FIASldRJN3A6qIaaE0bG8SHqNCAAeG8qwP9Bk2F3y6CTFRCTT0xFa9i2gCzwSe3RnjJ5U2YSKJu7qmEJ+9mHo65CIROPWOQy/G1LTlGbg8FrTm2/aZ0osDj11q0IuJyo55rs85XOJ7sALcr9J1tqgcWVbIbuwDIwHsxK6VITE3timjAii7SBE1t2oBlmrnfsxAoxGxbNGq2ZSTDcAmYhKY+R7OQ98pOKsUH04gVVDTkhmUWFV2jxkFQF1I1nnIsWriLLC2W7k1yRDyZbEfuIuelvRfampyR76qDZ04wfDCOwMSkmhPVoyygMaIOkDulBytf5OyVvlEfnqp7+LJ3zkUmmps9kcVOOj+AiLLNhDeT7PcCcS8dbH/YoTQHDV2VvPyd60Hz8KQIftWVLTTVeuBw2+KFlzbwdzSUXTKyCN7wjAZeeLyBkWN89OEB7vMZ8ob8XQKChdrKzqiRaVttDvJxM9eAYBbrM7W/aO7vq1RFKFbL2BpGpPFFRARKPP7+zAj3jjI0I4PHnYerdGi2M8afPTTAK080sJZY/P0TQ6QV7zKiMrB6EvP+ZmKDxjHRi82za7BNgonk8+GUPs7VPZ9Vt4aQ3bgC2LYBMZcWHBObnHqNCv1rW7SvCNwPgWzHSwHYBIgYvDq+XWbx3+JcInvmTvO5Sn5l5XxXqb8DG2aSPIf3CWeuUWNZ1IVUja8IBBoCqDAJlUXKJGqdMIA6U9PY88hQuQBmssDH68v768zdr5yLRWmSQqiablaRb8liTlYMIc83p4sMjS0SzFxMMzmlynzugYiQrB2sYAzHbb1hAAK208WcTUH7qJ1Atikh0iaWaJFoNVCGonGKu9KFEY8cwPTKEN18h3HcGrxotQELIIkN3nRFG792+y7MkfI1fSbDCdcdifGC4wlGLeCvHx1iF37KXFUmQfW4ZIRs14N6hPgQwSbTK204lrMW0mpotR/otOCQMXpU7CxOsRefqtXxIGd2jDMDh9gYOAZecaKFzAOf38ymXmPWuRjTZKVaDCZyk7CfLoki1ZClXHS1/AAzaWSyhOZlMu0nBp2Lr0831KKZ5bMQr+9zPWtHixItGxyv4wAAIABJREFUvtrTekhOy+LM7c2muplV6+flOqt2GIOJL9mDU3OB5vbZ7NetUeOgqAupGueF5172XPzhz/zhhdmYBrGGSZ8QTEoWZVPFleJxmMrjdI0KBVPokExSSOeLYtIvvMYycpsyk7fMP7sA4FyPCwOwUO8rNTxs7t8pkI2U29nI78CqOwUA6CWXY7P53OWeX6kLJDRZuwKV99nMT+PI4FaQd8jRxEua34KfSFoAyfNb2WM4Mrp17Hmv+I5Xg6snjYFkdA7Hhp8GILYQP2vX8HhygxTZqmcrqFX9XWEPwKEAnH0MxrYx5z2Gc85Ozit7tQeIacwVPFyfa9mdWHP3FZv6LtvBY52XzT+evrxmq9cXZyh1W8tcQ+GzEd6/nz4ncx8/D6z7F/7rUExG7neDEj6rc/dhv3Og2/AjeXpwY7/YeO5lz8VtD9128V+oxtcU6kKqxoHxJ5/6kwu6vSLNXb+wYWe06w3KhcVOPE9/pkieCy3CisXQYnlPmknQnJ9nYDLUeOFCBqCRn8Xh4RdgOMdufAW2m1cv2DhK6wYf6BjW40TlwrkPAh1nXR8r2Sk5LgR00wfRiy9HZuc4ogaQ/j/49gS6j8cX12F0FI92XgqbDZBiBUwxQnwbWcDnESxGAAgeCfrx8fEiSl8roV2QKbtlidstO5V6rVR9hIpzj8rxmJTVTTx+qpioFuHVcxlBsuKUGqou/kGE7RGPvZ7Hgmo+TE7qw5nL3ZSJShH2j9WW4Rozeg3oIENRGIX3FIqpWS9fuSkhzHj/4bWq29XPHxH2jVoCZhdG4w+oXC/zPiPhml4wDXqhcdtDt13w77caX/uoC6kaB8Yf/N0f4A/+7g8u2PYK+wISkfA83YLPxck60GxwpUt4tD5uJ+D6paDUNGlpseskgofOfhSCG3oMH9buUJvQOLb/N/+PXdtFy5aP++NTe7h/z819fL7DSM8xoJEwQWdiG4TGZSjiUKp438+8DzdcfQMe33ocr/3F1+L0/ZvwGWOVDX705SuSC6i0y3+65/fwxHD2KslOheJKoQZ38Xxb/h6m79ir15WeQzdkuB0GrJ5bQ3jOaoQ3Xt5CTIT1hsFHHx7g44+N4CuvEXC0afD9V3VkWs4Dp/YyvP/W34HXkGPbFtF7viXXR7Qi8SLZjhhymoiQHB+/Npi5oF/DNp4s/Eiu4SgG3vaCDq5ciXHk0JX4nu/6bTyDVvHvbvx3+J2P/c7Yc9KzHn4o/lTRGiHekIgg12cMHvTwqVCmzUusUKhpiCxiteNQ/VZS+q7ZLuD3tCgjsUyYpNXyvTKyJ+rSVFRN8bhdoTIB0ft5peNsm2YGTF9ouIF8hk0kBru1A3iNr1TUhVSNLztMQktNzrhd1YAAOqlDSI7Mfp5416AIt10WPpeJI6OTaWHiat9924N0i7Jy6oodF5oudlR4WAEyRt+cKBjbscF4a2Ec0apMXolFAGDahOaJxcfte9/5vfj1//HX8fqvfz1ufsfNePMvfRfuuP9ODBvA7aMcz2vLwbl9K51bRAWPIwIkvy4Ox0RaU5wBIC5NVIsg4vFQ2oAXHEpAIOQMnBl6NC0h00Wb7Li56OPbDu+/bQ9ftxJjb+TxydMp4o3QFhOEyb/q72yD4PW8uR5gKuaOYTrtgnGuUOsKDdf+wAMD/NC3vg3/8nt/Cbd+/h/xf/7Rz+Pjd/617ncJyQ0UAXhyqLyB4FyvWabCjgNQeks7raVJKSNa1+NBgGlqkZvLdej2ABOPR7PYtmwbJBN582A7gBh26lRha/y4X2zY1njmnhuK8LxwnK9R4ysEdSFV46sGBV1A+1MHZAA0GNYCtmVkommPQSEXbY4APN+SKBo3kIy3fAeAl46BSaiclmMUE12Ain1XxJtJ4lY0FDYrHcSD749JCJ6BLz6S4bnrMSgCesQ4tZuX29fXpEi0UEZFwWTmT34BZaFZ7Z792G/+GP77b/xneN31b8Dv/uh/xP/9l/8WH/zkB/EXjwxx67kUBMwtogDVfLEyYjoBFmCbJDElKTS6pjQCHXMNzzTipwEM8nFh+8Bxsd9hOpASKUSzbcZ9LsPdd2WIVmV7yeQEmJfiwcSV1wy0KmvxoU7pEjUzp+OZVTqja7SvCLt4/Ylz9q4feSfe+qK3YjAa4F/9+58rNDeTtgLRKsH3AWqIiJtTD9sWYXnsDJilIxWKyqJg9AQ/UlPUdklrmwaQ7xBYj2W+AylwSbzUCg+yBdODVcy61kL3mOxi888Ljbzn5XUjAmezo6Fq1PhyoS6kahwYnLNoNJZotUu6vHSI9qMD2Osk1cQC5nWG3K4QKKGFi6Es5Iz0jBRBFAE4IdNf7AEeceG2PHN/R0IpmCQsVtJVciNG47iaKo7UYHFQxnNEq4BJTEFxFfvjGN4z4BnckwKqcdiCLHDjl/q4+1CMhgVOuQwDC/CISkuBAQAPuIEHWSA5YhYuXMFkMexPuJvnHPidP/8P+Md7b8e/+q6fxbt+6F14ydUvwc+/9+dxeqKACuaOtlsKuU1LjgsIc2M+QgZielZdwjelO8KZTG+V/kmEv3l8iI2GwdGmxcP9HLecTmHbBLcrhW44Nz5lZDtepv4a2hlpTVNVwcuKDCSEWMOqoxXVMjfLHEMQkBySa2zy2vSDUjvkhphZbMy69v1IjnE7buPdP/hOvPmGN+Dc7jm8+f94M06dfRBEKpSe0GpJt06emyrV5voM2zFzO2ZkZKjARoBpSTxOdk6PbYtK7deThBsIpV12opQS3WV4J2aofkSFrxSzeKbhAAacyyLvSfGW7wK2yxfVQJPVz6LueNU4COpCqsaBkO+IK/IkBTP38bowI1W6bEEBlJ2TrkU15yvf8Rg+Kl9uzUuBqDtfexS24bOgj6JCWGsSKvZ7UTeLiFWcLne/oXDKd4G8zzAxg0cGZOVxPkPhMzRFAZJ0QWyTkG2KLsUODKJGaZJ4x7ms6HCZBEguC4HG8u/0CS/0oAGidYZd8AXPbvbPYcrq5jtvxtv/8Ofw5y+4EW/6+jfjZOeZePsfvh0PbJ8CEEbudex/s9SUm1gKmP0oFYpD8SVFis9kv7lfWh9wDuxmjPfes1fVrBc0Tgg1JiNdGqQElzLiS4FE40yYGb6vRVK7fK+sYnwmsSpgJ4HF1KIioy8IvCmauDYTdYMfysNm0cGF4aeGShcdnhj4lpMvwiuv+ja4HvDBj30YP/37PwVuOkSrBBfL5yY7w7CrWlzGKClPPT/SiVtuAfc5Y/SI6KhkW5KnGK0BLtgCxFKMm+RghQH7MjvRZ2XxnG9K19FnQLw6fozyLbl+TDzbEuTJIFCgtiMUZbR6Ybcf4NOKN9sqpijpGjXmoS6kahwIYxSMw76TYmRlESNa/NhABwHqLxMKKe1kAIDrz+4STG6DjPrusGSqRR0UPjv7ddKoQbA6NRiCjPm0F5oEABtCfERjOxwh3+KiCzIJ74TOcbtCPYUuCMODyCLaYMARsk0PQMS8hgm0qsVfUxZWyrhwR18E20IRaVN1oC4oIQc8kj6Ib3z7N+JnXv7zuP7S6/FLb3wHPnPuFvzqn7+7nDLUiS+QdGCynuhlOC9py5nHjmSR8wPpwPi+bMe0hAINna7ifM3YRr5bMdbU7o9p0diEpu9LUSMbkQiZoGsjS0i3fDFoAOMRrRvYFQA9Ghujp0gLLKWKyRKSw/o3SyK2HjBsixCtUGlEqpYFZIEoTfD21/7P2LCHsba+it/76Hvwl7f9hTilc/B20uex5D6GKUQ/1JiSpvhdhY7OMngGG6ytR3hoO8fpkYdR/RzZcTpuVj7kvtDPavh8h3QBn7FmRALx4dIxn7mkZn2m+X8XUBgedYCcpdC2K8t1vPI9pdS18FrmOV4pbEAp7AO4pdd4eqMupGocCLZNhdZoGbPLaE0oABPt380wDQnpLcw2mWFXlBYyche8CBRrdEnOSA6bMaEqME4ZzqMR4w0q9TZGA5C3UGQE2lWdjmvP51AC/WMbQJapXkn+B9smxOuabUYEREB82CB9zIMSgs9UuA4ALFodE2Gp4022FHlP/U1fCwByn+P/+uC/wbdd8834J6/6cfzU638Sb7nhu/D97/x+PIrHlFr00hHyJBl7SyLQVQCBG4x8wIXGKlovFzRmhtvVY7oy24E8VmE7PCNaqSZZY+zn8jXL92oa8rq2RYWxqZnQ1USrgG+MX5uF4NuX3Tmh21SPtKtatRh45XWvxA9/04+Cc+Ceh+/FL77nF3F688zUebItqCBf69RA3falGHMDueaX1WRdtx7jNceaUug54AMP7eHxpCxkisnWJYuOSQQxvnRbURwX25KbHNMZjx0i0oJxyBI4bajcj+j8svDG9idaXMDPgu9rR23IQIeWWulsUylsxr5ZfzVqVFEXUjUOBNteblxcXKnVmXmJFjlR+LIsH5tvSxGWHCJEG5VF2IvrM+nUUTXuZJlpLM4Z6VmhzKIOIT5S6m7YyaLHFUF71LLAugfnQOtSgm0YeX8j7YJUFolgu0AE2A2JuJFJI1OIpScRrxHgpVDId8rXZYelxvNdXynRznKdgNWY8D0vXEGH7sLnvvDzOHzJ/47rn/PtuPkdN+ODn/wgfub//Tmke0JdJscJfkQF5XoQUERALsfb5dIdIHWS9kPVLAFAj2DWgXVr8YorVpHkBp/Y3cEjJkM08Zo+Y/ichYpLaObUmdgvmLEpyZn7R/Mz2shIN9OnoskhI4+1TcJlhy/Db/zIb+D6K67HPadO4Tf/5Lfx3pveg/gQodmmcqqyFY6DWHAQAdSQ0GaKZNH2Q6HDDuKTdP1GDBPLtF/EwPNtgo8+OgIgE4rFZGuyOIOuoEhZ8wXHIlgIhsLnjGHa0Ot39vGMVqjoIgM6YZux0qbleX+qYBpK5QdvuSVA0cHyGWvUCKgLqRoXBfmWtPjdAEiOnF+rv0oXwFPxhej2QvHAMCMpwEKg6zL+QD6XboAfAVnOsN1S3zS532JAqQLsNsH3DWzQerFOqEVlkGyVxkEepqz26cZZKQp9yqBE9S5+MY0Z4IZcUFA4LVTkfp5Z33A4wUojrC453vPB/wnu+Bvwr7/nX+NtN7wNx/hSvOev34P/+qn/qtN3gOtJYRyvT3fxFkEm6nT8vpqPFkGoQ8fwObCBCO+4/CRWrXwlfefxQ/i3jz6MLwz6xXN8yhjc70VYvSIL+6xOx36TjcsiWocYcOp+N6Mm3vnP34nXff3rQCDc+8S9+In3/jhuf/B2obp0XybzGcP1CgCRKT2YTIOBLqm55vLHtK96r6A37Fe1ceF461BGQLbN4gGlNCUgxWxBkfpp7dHkfi9jAxJAEYDQhTtYetEFQbSq9P4Bj22NGueDp8gvtsbXEvKeirpHCyifOd9d7KWjsAxsRygZ25ow6aQgiJUFPtuSMfnBQ17F2Vx2O2YgdDOIMH3HPrHfrqd6CdBYZI1MpsmUnNutbLtRLnKhW0VWijyfiZni9EEBqClBzWGUPV4v37PoTma/n7BG+CEA0ulEt/j4hr8yM9yQke0B77/p/bjuZ6/Db330t/DMk1fgh171T/Ff/pf/jO/4pm+HH6ouyGkBu+T58yN5z0QAxePPCZ5Iridmpt+KVayYcsW1RHjzxrhq2Q10vz3GYmqWhc/nH8dZ50em/6RAevt3vh1feOcX8IZveAN2+jv48d/+cbz6f3s1vvTIl1RLBuR9MQENxcd+CNfGwhBvN328P/bAAI+cyZENGfecy3DTnUMRgevxBkRfFwotduV14XpcaJryrcq+LlFrsF9wDU/Arsg1HB+SQnTRNXwhUT3H+x3bGjUuFOqOVI0DgfPSeJF3MNdIM1qXiTcyqpWIhY7JzknHx3b2t0OIOiT6hvDaLJ0f21EtAwCQipsjht9juBFgmUAzNBXh+WQIjUsA3xfRSpX+idcJTinJ4OJdTAw1y7v2sQk5FUL7rCyqTHO8C5dvyt8np5oCFeiGBKOdraqwOjvnkW1LIG/jhCn0J0HQbXWfZG1bjib6zJkUz1qJsQrCcMT4m/sGcOpI/st//Mt495++G+/+Z+/Gtz3v2/CyF74Yt732dvzCb7wDf/WFv5Ju3nC5qSZ2KlQ2DLct/ka2K+fVaxCuTz3y04TGIQtOMUYBdc34GzENtSlItct5gEm0WRN34XooOpmpUEHxIdnvbrOLn3rVT+PlV78Cz37mMwEA7/zwO/GuG99VvkeWgtpnQoNFnXLSLZz/gnI1i6nGSRRTZCxaw3C8N895/N7ju8UxNhEBI30dEqfzsQLCALBAvikTftFAaK+Qm2camBmKXN1v09TPbl5aXSwCUUnnZVtS5FWP7cXAvKnKGjUuNupCqsbBYHSiZ4ZQe+xhEcF0geycUnMDnfzSIqEa7LsfQhSKT1msEbqi1TBNGcVOjjL8QLoHUYMRdUr7hAC3x8j3GCYuRc+zFg+KJqaeukAOERebJoo7d7JcHIvw+BCUC6iJZlPoMLYq3A6BtJWpJq+dFdNg1eHQmBZJFmkpHOMNoWbybdFEoQ9wV2iz5gkjnaglqIy9nPH7d/ewwoStMw4jhzH9Vm/Yww//+g/j5NGT+JUf+BUci07gx974I3jjN74Bnz31GXzwHz4Al2b7TjWZJmBzQr7HYKiPV0pAp6T2KAFgGTed3cYb/MZYDfiJ3u7Y9myTYI7r8T8gVVyduPMZw28DLvMgdfgO03mcA1ccPolf+cF34NpjX4fbbrsTjzz6GD786RvxH275LQxz8UdgFww+1cOKRBQPYDxsGzpNqo6mPp8trJ8FXwkurk6R+VzsBkwEmBWx+SCrmiwv1hnVa5uIwLmX647KCVLOWQrxFZp5PIvpV4TOWNivCUOsBQjeUxSCFh1mrjp+JNeHaZ5/oTV+jgH7ZaAUazw9URdSNQ6EMErPOeaaWo4/ofyvaQCcSZdnsohxw8q48mSnyqGgEf1AdSXQO3QCojaBWyoyNmamVYAb6EKWLjbknNp97UZlZyATaBkhWmVkW+JDRNAuVc6giDVvTgq+UPy5PoHZAxnBHhvfN9uWAswYMzNPzLQJvMvFpFj1mLqBdtn6cgc+b4H2I0Z6WqjD5KgUa46BLTD8GiFmTJkcsmfcfdcpfPcvfD+6nQ7+yYv+Kb7pmd+ENx1/E37gNd+HYXMPv/e3/xEf++LH5h87I27vbgTwHuByKQYBKjpzdsXANgl3jIb41YcfxluOHUHTGPzdYBsf3tmcuU120gUCpDO2TOfBdsqJO5BSYE7G5KNVgjUW/91LXoe3vex1ePEL3wiyCe596D6892/fiw99+kNTeY3ZVmkCapqyiDdOaPZdXBYDVQqYIim648PLFYK2CTFoZR4T1RurxbsB4jVTGJCSJZgZk62B6jWJiP9NSw1nQ/dvCYEH2XIy7yDZhBKdxMhHpRHq1GOG6igPwHqa0pgti+IcWxkUYM+FZ1hN8dW4mKgLqRoHRog6WQbRKpS2Ut3QnKk6t6si75xhmxNfuOpkHnxsAKXgKmaDBACLOmQNCYMN2pxl4IYyQs8QH6lAn0Ur4nouf2OkZ7lYGIXy0gm8XWm/sZc7f+oQoolFyMRlXuAs7UlyFHBdgm1QUSiF945glc26WGqXwfWlyA00UralHTEAWQzYSj7f3LiUYVm89oY9/OYnfg3mFoOfeetP44de9ENY76zjlc//VgzSAW6+42b86p/+Kv7h1D/MPpAsE2ZSTFf2MQKitkV0uTzsk/09fOKLuqMxw8ZGqNfO+ELoBuUgguvTUl5JpkFI9NqRbqoUlq/4hpfhO1/8ZrziOYdx1cojAJ/FmTt/F//r33wSN37uL5AP/NgwQnmAUGwr7s4P2i7MQlme4x3LSGh4L/0wyDBdZEgMC8PtqYeVflubJorsxjBRuPjNA7ZhZPquKdcSs9iKcC43OMvYC0xO5i0FLxOLpom54cioUNmzoiYDBbsfxs8xIzurMoLWxTPxrFEDqAupGhcZZJe7w6RINDTiKj7xNyIxr/TlglU1HuRcs9Ya87sT0UrFkHPGl/LkNthp3ArrotVgIFd6yolfU/CbgkPhMM0ZFRRMtEpwe0CjBXAIoJ3hmM1eNTo5I+qiuOOXXDN9UGUhD+/dNOWOn708zhmZaGMPYIAiroZi6cIQZjt2z0Kg3sCyDdknxrtufBfedeO7cO0l1+Kn3/TT+Nav+1a8+nmvxquf92rsDnbx+fs/jxs/eyM+cMsH0E/7pUnnsKRtst3SwJGishsWXtP11J0+9ojUs2jMYDSa/fMyuHTjUnzfy78Pr3zuK/Gso89Cu9VGmqZIT/0uPnvv5/HJuz6FYTbEw48OZdIt7PdEsRKtaiG/4JoDgv5IdGJeBxf8UIrD0oEfYnaq2jnpmsrr5jtl0QjL8HsEr4HEtjNbTF1cywkKsXy0Pv75gWYaCvUmhdzFiF6xHb32DebHC7UA66jQTlYh54BhW5hrHzILnFe0i+nyVGSNGueDupCqcdERgmxd5mFjgknGKyWfM3wqGo740LhjcvCjiVZo5hd9EPuyB6iPorsDqK7Dl12XwmyRJYePc9kuRZjeBhV1BCgB4rZBetaBHZCdZSRHCe0rSINuhTokD9ij5b6ZmOAjjYlpzxca+0ynDK10W4pCalguBm6PgfZ4B8lEBLMGZFvyntgF/RUQXMnZiMloMZ0YlceFaL7OzSSldcOs4/6lR76Ef/Fb/wIA8KLnvAg/+bqfxHOOXIOr1p+Nd/zAO/DL3//L2Oxt4tb7b8WHP/Nh/LfP/zfs9NUevro5qpynRApmzgAYEUT7hMFsxp5km1KUspeJwEUdi8sOX4a3vPAteM3zX4NrLrkGraRVCMw39zbx4U98GO++8d14w7FtdCMjWiYHZLkrHdaHDF4ZL6ZMQ6Yy90MICDaJQaYaqmDAWRwLRnHz4LNSYG4ymtJahak8P5o9rDH2eahmDxJN2E9IcZqdA0CSjRhvLC6mwue4Sl3uB2ZI0cYoGqjTD9KCdGK7YdoQ0GM2YTDqMxGWzypkGXJjAw/YfYZaatR4sqgLqRoXFSH/Lj0ro9ZRG2ie9AX9BQDpWUauchjbBoy6c3Namja6HmBmZXhxKfBmXy6qQZsCFu1UVdcRjBAB6ehEa+Mi8TAlF6nLuW3Kl3W2beAHDE5ZNEmJgWhoy4JszD29MuHoejy3kHI98bUCA9El5e9NUybkZDsEP+SxMOLq43wqhVG8Lt0Nn2poMzHsBmDbRqaaNhmceenMqWP0vMVzWVH0LXfdgptuvRnDBxkbnQ18x0teize+9Dvwkq+/Aa+6/lV41fWvkgXeZdjsbeLex+7FJz5/C774yOdx+6O34/57HoJ3cnziNQPfZXDfweQkdNgA4FZ5HcAApq0xPTkjbkR4zrVX4Vue/S345md9M6659BpcunEpVtursGqpwMzYHe7ilrtuwZ997s/wRzf/EXaHpZj9Y3mE11/WgsmAB87l+Py9mXYYpWiaRZ8touUmIdeGUmk6fWdi6WxyXnHS9igE5vCaDDDQayvWoq6yjVkoPg/7uA1EK2K0GiZgq9Oi09vkIhx6v6k9N5Bi2LTUry0Uf0OaMnWtZmwGHaVtyjGHxjT5VB3TK0VUvidWDkRANKEPlElY2V68PvsGLMCPGG5Yec0aNc4DdSFV44LBDfVOujp5o/5DPpX/MsvCOBbpUf2h8uUvovGgaZn9miHGRcKBy9flysSTz8bNjau0FcXj23B7XvVBQHKYxIJBYRq6kMRAMHAKDtM+K52/w0QXIqEqQ+jqvGMFjUkBy765vhRyJiEkR2QxCrExnGGM5gN0mi2R90REQEOPN4u2y42A5DAXU00ytaUF2uDCUDp+IPt/bvsc/r8b34c/+tT7YRLCdc+9Bt/94u/G808+HyePnsThlcO44Zob8OJrXwwA2Nzaws1//yncfeoU4jjCm974Wtx9/7049cCDOH3mDI4ePQxmxnXPuwbnzmzh7JlNtJIWrn7Ws/D4o2dgjYU1Fq942YuLfWFmDNIBHjzzIO55/B7cctcteN9N78NWf2vu/t+zm+O379gFbTG2tXiP15SOnVFEzaPl5qHIO+TpzhYqnS3TkMw8zjUjUifnmMXywnYW66KIpDgLxcF+naNoBciJChuEudB8wfDe51FlnCslDv1MNEkkUDT7Mxz8yZgZbjtESok2MCQVzMru44rxLWcYW8nCJCxY93kOnS3TwKKV86PzNw5+uoK9UN9Vev7pirqQqnFB4AblF2jky7HpQCHEG4y8J7oOOyEOjg8F6m1cB0FWJwQdFk7ZscaQhMBeQA0JR+UEXRUmIiSHUNBJY9vwsh8ETK0V8ZqBiWTiqUqx2TaNFWrZJheBr9EGRJtS2f+pY9UlQAXi+TYj1zvt5uVG9Ema1caeZ0aiANMLgO1ABeaSi5idVQ2Xlym1sIDkOwyfOpjELB3uOgvRGuB6mlOYBCE444tf/BJuv/ffjHXRus0uXnrtS/Hiq1+MSzYuwX2nH8DOYBsnD1+O7a0d8JBw5YmTWG+s49jRIzh8+BCefdUz8RcPfBy9MwOsXLKKTruDlUMDPPDwg2iuJPjwZz6Mux+9GzfdcRM+fe+n4XInNNQSYc8BIw+4BKAQazJj2ivvqSeSFq5z6aoZIKJ9H+v2VBPUHM/ek66lFnjrWBi5UqUdResn+xmtqhbRCR3Nnoviuxq1NHPfrfq37Te1RyhvUohEH0YMY2Yvtka/H9yQYXS7nDLSs5JVOc+aIVipkJ2mWG0bOlFJc3VZY/vLel/09K4FDoxqwHh8aP7gytMBdSFV48KgQgtMUgrRCiFamT8qZ2JC43hl0RiqrqilX75mPkfBvqTP8h7DtFCYbi7K3aOIir+wK7dhrNgvUDKjOGnRcoaKFWqFzIww2sqx8k6MSiWUWETCIeDW9YXmJDv/vVQXw7GXSEMHQIKgw8ImU4IGgAc7FGP53jO4RYUY3g1kX4rAIkFgAAAgAElEQVRzsA9MZNA6GV6b4QcaWJzTFK3ZG/bwkc99BB/53EeKx+db8j6ij5DQQUOZ0IzX5XluyMi2PFiLnMaJxTP7ISrooCaQtikLs+tJXpztlhOZ1euEnRSPyOmCBdwycxHZUlzL4RqsfAQWUXCTGJtwHEj31PUBl3qZymSdSOxTQanPQ9SlwnpkHsgKXcxqSur6onN0BMSWCyqxel1FKwTbNXIjk5LQcuqib1qzKWaTzM/FM/FymXlFOPNICtP9rhH2XHesqvBzfn4aoi6kalwQmJZ4wIAPHm5bBfvKtFwqi1WxyK5P3/Uwa+QMA1HbnF9HxVT0Kw2aP6a9JKK1ykTXjC9e05ZjFcS0o8cA29TR9BWAM4JpMMw+n84iIDkSoXD1tThD4eNkuwQeih6GwuKlU2cRRCNiYi7F+K7smHE2LuAPflyhYJ2F0M3xWegm7rP4xoDRCUyKhFKbFHeHzhI1FozRh/fOZVQK5zhQ1wgQmrKMeamMzlevk0hsBHAeYbw+E5rVNMYpXyl0SxF1QfHGocOruqEFXRY3ZBkQaJXbc6HrotcTQztSlSBqs6Sv2jIwCRV0WjgPYNUjqRaQ0zIVweeMfFM6pPGa6L/8KNDi4kM2eawuFCgi2H0+Z1Xn+4NOD34tI1oB8j21tnma68vqQqrGgcAsQlKy49MyZJbz81kGMokFgFQYXkwq0dQXvuuRuIw7wHR0ck2pwGWLqkKLkc/XYh0EJqG5NgM+06JwRQoZP0LhNm2bQLxqEHcBZtq3Ve7FZFtoyWyc7rFdgHcAYw2iNoBAd1RMPaMOkHmCyUNUSklpVs9BQJWStLzY1iJoglxf8vzSsxIPYxsGfqQFYKzatL6KyPXlbHu6ADURITmMsSnMua+tk3JuqCLlA3QRmFkpXi7iUQDVveUM0xYT1mUm9qoImYMwZTA2DcaLVEBuFjgniQ3S0ODksHzWolXZD84AxNOTiuH8uAEXtHjUKbVZAJCe9aK16ir11pYbh0XHNFCBgNCDPtUirznDPHcCgWaTIp5BA7nOqhYnPCq7bH6kwx+ZdKLzTe0EzThWM/fV60Sumz/pW+QRTt6UBcqTWfRxoXDzla7ekOtCSkGR6PFq1IVUjQMi3xHahcz+Ds3MPCWu3Q9kCNEGijt2mc6Rv0VrM1oLXgumSH4usvwOaMJHhsY8norg0wvYyg8dJJkmUp8fK0JzigGQWCsgwpjIfR5MU7o+YaJr7G8z6I2CttP9YEj3olgwdLEtzkE2IUA+YCufDIm2K/XIdgHbF60ch8EDx+AmjVHBiybNDmIEazvn11mU6xsyNr+qhYBOluU97Zp0l/fjAsbPu2kz8l0p/mdpjYrrkMtOTkEVO158fbN244YyGOF6SqHp+U23fFHIw5cmmfOKKKEydQpPp2FdyOlj0XPZlpyXeRRzcWPCgNsh2ECHjgnsAerLWy6CvhMUU7gAlqaOfFoaybq96fNUvRmI18c7KW5YFlmuj7FOZJgePEhWYo2nD+pCqsaBwIEy0WkbmiNVYV+OS0fd/emYKkxExZVJBNi1kmaZhGg+QkQGxI8qD/t1fl96hWYHIha/UCLKMPUEnTQyCSE+LPvp9sQJPd9W6iafHwgdYNu0kGKbB58y3NDLQtumgq6Ypk3Hn2fa0onyqWbn5fvTLRQDHLpNVjtnMYBMzhFFgI2B4PY95SB+AAhVqlTheU4RheubIulmEBF8MGJVmpA5dFnKMf9FBXd1isztECgunzcP0RpJMHVcHuPgEybbnL6pMC0g8gacsYSExzSu79oVas22Cclxua4XXTuhiPIZy8CEej0ZtdegSDR++Tm5lkyD0DiOMYo42xSHcdNSEbylgl4OoIgQH9GfK/tDpjKBuOR1YaKymzprQKX4DELOy1hBV6VBK88tOtZ88M9ajacH6kKqxoEQrZAIYZN96IC8/NJyQz5v3ZFQA1Ktzfoypai8M/eZF11OtlhHsh/8qCwi/OjC6UfkvZB0JvS9hC9mCoJ60iJwifyz6vNdn1VTQ1OBzVWwZ9WqMHwqmiyKxn22iiw7lu5M6GzJFJaM4fsMyIa8b7Enwn2SriKX4/viFl4uuheCFs63S+p0Xq7b1HN25XjYttBcs65vExMo8vC5l0mwmODJIzst78GmZqGvku1AVmgjx58z0VbZBV5QJp6msUPsj894JqUWKM1wnVVpap9KIWua+l4rprghFDwY1JpKzIrPpCCLugBpTJFp6HtQI8/0CR0O6QhlGCv1FSxPTAvqWj4/Smeu3m4f49Ni0lapfIrk5mQeBVx8BjH9fWISnebFbIF7XUTVmIe6kKpxIFTzrBYhxJP4/Mm1w8uJtaUeLV+OrfEvUXaMedEwxWNYaS6rcTB9WSSrX+JPlu6jSO0cfKArRTckESgEGINoRbQ5B9Xg5D2lW/pi9zDT7VlNFV1fNTcrMrm48PxMUm1c6VQplbTfAmMTAzvhs/Rku3yzzgVX6LD99OUSqyMu4qYlXTPbppnXt1BcBCINxI4JbkvyIYX2WfxqJqLCTJY9Cu+dg4qnQ9zOMp3WKY0gyTXHTEB3/LFuVzRsRidVTUMKUj+CfCZiwHbKwqug3hwACBXNI/nZD4GcWAvmULxJwW4PQIcuA86V6mRoEaz7t4AC3u/7pDrNW6PGsqgLqRoXBUFs/FS2w42Kl7lijhmyukwieWMzs8kqUzkm4cIg0LRIom1SBhuP7LR0kxonnlwh4AelYzuoXACkQ3F+2zVxSbfM7WYpJWVaAMggPqwdoonCsBA2p9P0U6Bb/AjjxqvV9zdiyYPbh/I6XwTq9f9n792DZMvqOt/vb629M7Pe59GHbuACircBeQgifcG+jggNtKM20LSPFrxemQjiQowi0oqoEKPXkYmYiLkK3BmQCZQgAkIQaGnHwEHl1UN3XA4PH4gBtCBM82i6+7yqKisz917rd//4rbX3zvfOrKyqrHN+nwiii1NZO/crc/327/H9MtCnzJ5sEXzQ45qmyu7agOtKedJ3ZFJwHCIIGXqL4iDDXshuOBSej3UY9A1cNMUkpw2TnDGgZgoK/uV0pu8x8j2P/AEJgDijog8xmi2b5vjyX7xP4AluneWcczAHt/Jw0LiK4J1HfgFwlyTAmtagXpco8AvIZ15RjgoNpJQDpc8bq8uAnb7I7Qe7QoXytzTehom/nvSl5Dvy73atfLLum8ppoxBidJcYPjzZ5rsA98I0VyI6RiODiJ40s5IhJCfGBBKVQIeKck94X0vlNqwsfnWCkTjtRVb23fcYvQc9TEJIT1PR+O0z0XZqXCWBW3aeAfj+KSWEoG6cyeyEckvhFQdZmNMTU3d9LD6e73Cd4vkW1fbwmq5kPjiXDBMApGtUntN09PmLvX3UYiRrcq3GYVJCsmVgmpLtsy0qMnWuJ0KzqeUDGc+flcLuxQVl8XD/mqZkhuCCUrqX6+R2gCz05dk1CQ7zSx55x4N7BnZFynUTIYIJ/W9I+qcdAQCOwHmcvOWpWlQR5jCY4KXpffAzRQ35vHM+vI++F5r7r2CRSOXw0EBKORTynSBmSMEcteYXXL4T/MzWZv9SlPFuyf6YZiWQCGrPdhVFX4xpyZe8XQfgpCRpWlQ86ZoUyHvBl6sjgo/VEkEsNbl2OZGW70A0fdL+Znu7QhJAcQhmzkkvClkEyYByG75LExtt+0qSlZ6a3v3BbwwMakrfitsN5zCV/4qPn7xerGK40L+qW44dKptWS4Ex2OiESbLW+L6gwVKdazOySx7uoshaJGtlH5JpBksalL1wbq//WHzINpEN06UDQa9dJeQ7oYwTPP0wYSIw2SBgo/8acl42nrvObJmpecl3JUAc93kwK2GS0/ZPrMVMYoRdeaHi5yA9CWQPikgrTOi3Wp8iwxGv8Q7kIYlkurbqpTlvmd9thym7XQ5+l/1+fWWpc+DvdoOwKWGil6SiLAoNpJRDgSuTS+wA1Gjg9r1SSRqeRpsWT0FUk8ssDShMG0ZxwrD42lUARhZIk5Qj+b4tpZ30NJDskPTUtOJCVJZIYhYmLl5EgN+LT+Hy9FxdkKpj13FRYweAJfASfanRk0fF31VLkq3+8lSMG4gq2ZcG+qblDMKUUtjvqu9YVUyUmeHbcrjVpvSoWWRSQnJSMkemIaXKKPbIXAqs+ihCOaTCXp6/uPBxDvF3q0zIxfNtUhpqcjcNCaAAgBIGt+O5xdiGKQk25FqzQ21phVHvOctAgu+JbphpzZad9ZkY9QKyv6PUu6My+7RyOlkJrExD+qZsU0Qws/NSljVp6NWbclymBVgnqulkJHNkEvn7eL/PW+aPn00TpE1GyXyM/DsXf8BErz1FWRQaSCmHgl0HsC2TRHUbqckAhZ/ZjItc33aiwXCjFHX0e2VJgH2prMwdllFnF0oHRSaJwA3Rz+IeYCulIN9D8WROVt4DBOSXyuBtnEwEANiN0NvTROFpZpqyjXFTTvLGZUlStHPK16ZnQuYpKY8hWS+n5XxHntxNGvzMEgIsA/nwvrpdlAEtldmqomyasURk4dukbwKQwzmbIJXhu+X5E6++4KXmDABpgh6cRIxlH7LSIGyaMnFVnDNfZsGGDG/DlJrvsvSorY8WbpyGaYZrDTm+3gN+ckkX4V67EALWzrDIZL4j9jqmNTx9Wf08TLov6gYrvhv7CaWfSUQ2AcqB9CpCujldzJTC+SMT/PFW5Jz63nBwOWuvpF0HsCO2TGZFAruJn4f4d6sQ380pKvCKsig0kFIOBZPOnlGipFQcHxd8seepC0vx2lCGMtb0fcmz56IiJaKH8vRsWv3lkGjZAfS/n2kFEUcOC3cSm5+lNBd7n8ZhWwQ78IVf7bcZN3VItlKSHCiZmJTQHCFNEDMgbteLNlIvCC6G5nAEW5G+BXREuQ4ATFx8mzQ20C38zEKA5NrSaxZlEIDK+UO58MXpqvTk6PMWhWGrUgd9PV6rZQkoTkkyS/lN/N6kB42S4SBtFOxjqVS2Ea8nWZLA7DzXL8d6iA5XT3rUTFP2l7nMwLp26OMzIoDpO1K2S0/SxM9DXTjnYuDB7Yo8iV2hQjYg2Zot8LGrhGYiEhQgMRzeL6ZR/c6ovy/xe0NRDgsNpJSlJvb0jMJnQe8IwaNrgixDvi3aSaN86chIU7TvAjClXYk0yFYCpgYF+43+MpBJaLR9RSwZ1dSEmnW/gVjOmz2bQg0CdxgwjHxXSoCciZq3CCCW0112DQARiPqn+JL16RYhQMiyrQyUpnxZmhpVqptKtXzjJ58Bvwfkuz7YDREapyj4uNXvn3F7ZQbOVeyQJIgK12mPkY4QNu3bTlu85eBQmFQXJU8r1kK+V4ppSgAXSqOZiLQObt91ykC4zgMFAMCi8A2kZrzOpRq8zxiuW3r91cE05riOinIZoIGUcmzpKwmFvh7OQ49HM0gM5ECyaQrbiML3qxLc+J4sVJKZIBH2HNE8nGwSYIPop58+Tdf7DiO7xKAUaD0MACQTVnuxA5DvOVGNbgDJpq0dlMXSF8zohTDZBDgsmuJnJtmU7rcZoFDyWim92Oo0UvueTM6RHV3eIoNSdXoGWYR81wMeSDbKg49ln1oq5jZkwjKIr+EGYFYlGLaDmlE+9C8N6DzF8y5CpgyQkSDSBc2lLGQOEyp68Hy3nL5kePiOiGmaJsTI2Ve2Hd4qOSFlqRiox+EIMhTOX7lPovUk78FOAmAiknt5a3JAV6h1++HesCLDxhKEplfNXpary7jzDUiA6LZlGrLu9GodYjlcm9CPN8W9M+N36kGggZSyUDgPZagD0A8axFZLaiuxLBd6nXxptJp2PJJ1gtthUKNf8dl1yrH5ZCM03/ZCs3iHihIFO0bvvEf3GwA1GG6VsPKoyfvn9mTfuCceepTw2CkyIDbXS0NtzPS4iyTBSUJoXO3BzkiJiWR/x51ntyOL/uCUJLNkQ0oZCkJ6Sr6Qug84dO8L53aVYZs2lJhqZm12Q0DmgxXJQIYkGukOWnNMIr/k0fmmXJ/GVR6NqySiMQ0CbfJ4zawKNvQbxUxPfiHsjwHMae47h/mlUPajcJ1iVm5FmpN8Jucyu+Dhe6Gx28q5JkNFiTKeD+8Y+UWH7Lz8nQhTSk+X3RCF8CiECSCoc4e/75T3MKX9wwS+x+g94JFd9Mh35H6xXdk+EKYaw3Uwfb1+JTE4O0rGnW+gHPTgnpwnmqRwHkuvHD4XYxbWwvcQ8jCh3nnHl/yifA7q+L4eNBpIKQsjShwMiQEeEDRQUvM9Lqft9lD597KhdpCq91bhZRZF/iqlPdeWKTzfkxHvaG46ifQkkF0Ik3zRfyxuf8SpybelRIPQT2Qa0jBrQ1DFTiQLYnbNp+PFHfsmlypTkvl52XfTKPtIitLbnjRpA2WgM+iLNojrcCGAappyrn3GcN+RrEzjaoZtVkfhCXaGbx3fG/45Br/syuOYdq81TlPhyeh2gnde5VpHot4Rx5JhtYTbIiSrklXiHoFTwIVjb14jQZRdKS1WqAm4c0B+jgAnfXiGCI1Cg4wmfwOHaxhtaWI/lm8DeUdKvvAEQ/KZk+nUcHs1ZKqSfaV0WGNCMG6f0pCxW5nsx7cfmBn5tvTqmSbAvl+RfHDKdBJ+sPQ6xrA8fi58JhIodcRbleWk+Kx6SHb3CB8KNJBSFkZRPnMoNHzGvo7C6LmXEX52LMa5I/qc4nYn9UABsj27Fnp9thj5OWnMbZ7pf88qxYQPo7BWKbaxVr5ORuUNkk0PGELz6ulfvulJsXyBkdLjuCmycmcAH/qhYmDQvJqQPQggYRhD4OpCE35mFjsPMuXx2XUAHHuBGL3vMJCEJ7ggBTE4jm5XxfAWBLQeAdh0fBM5IL0+MZvHGSE9JRma7n0M1wPQY7ht2lfjcXICcF0pgzWuKt8zvxSmIUOv0zTpArHECT8bFJmawQDMbgC9+0Jjeg99/XlEIvMAR8iSEPQawOUM3pNAqypJYFeCrAYB+UVZ3BvX1C+TmRXA5OW9CUiWJt9hySxaOd+2RbAbhPRkCETC8IVkdLiWd6PPZJrQd0NGOSiTL1rQMrvI4C7DrIpIZ74tGdtoolwlWQ9DGDUy3NVAa9K9YFclI8q7BE7ku2dkf6Oy9CSbVH6OjzgY1kBKWRh2jYqehnF6L4VYHoBkC6GJNk4qDZd8Zk3Fl83PFsnDRmxjq18UclCosH8blWNbpZBps7V6K9hxXwnOrkye5KpCoCJTkqwbmJSRXQCyC2JWm56gvqCwKk+QngzTTgnBhIxT74GQqcvC3zhZ9AcX9PSEBD2mKf1RY4+NSxudoX0PC7BkfViyCpVzEl8ziO/JZB01+s+/SQxWHl7ZRi4BFBLA7wC8glraQlUmKbOTJVDDg7yo2ds1Ko6X4oIeGv99T3qusgskPVc02FdFSDbk+qUnpAeveu+4jmR/TAsjs6Wj7k1Agkm/J0Ff44QJgUb5N25PJBSoyUhWSfqPpgQifg9Flo5zgIz0GlISHox6Epzvp6+IXek04Nph2tYA1Bq/ENZdIE0zZFh58gNX1M/inAHWAOo4M83Q+jDRQEpZGDLGP/nLiX3l/zgUukYxvT/0+pCK532k4osy18DPszItI1bFtQHXlkkxzmmkeOLwH5ULVXUSbXD/KSp7c1Bsn3J8xbRhIsHSuEU1Waep9h1xSq0oD54IViTVab4tkgxcF/BdyTr6Loos0ihl+6KsmVXKmoOnp82Ftx33CPY0gzNGdl6EPBfSI0ES3PieBCquHcRCqVJGNHIObUsyVyaV80Ej7o9BRfS+Y45CpVk5tQdU5ChGmE+bVYAuEEzKZYnYA73z8UGh7BVCDjTO1MuAmaY0q5um3F/5RYKxcm5hJIvJ26NFQGsTBh+k4Z5gmgzXDXHxmFLcTJuvGeSRDfdtD0OyI4oyDxpIKYeC+N4BlHLIhkjpggwhPY2iHDGIXZUyW9YGjJ0vFW9Xpf8CQK2skPjRoU/de+SxJGVA4PbKMXW7AZkU25XAxrUZfovHBoA+98i3AdNksDFDk2imBdhcNH7sGpAFzaLeeXk/05AMkwm6Un37aEOWJwFM6HcZVQqsTSWD6HuM5AQhaVKhSxTLZWSDvpSXc1D0OoXm+0FJC0pkG0T9pRmfc1DFL3WcTItADUb3OyEzs+vhdgwaV0kfkQSXXGhXzdSrxwSzyuE8ynu6bSmLghh5WzSSCtXuUO5jJ/epGF/XXdArJfCQUYo+i4CUnO0KF1ZC8f3supSJ47lybRQZTN+T6xoFWpmHjboH7+8o3SCToUYim5yl5J1IhpRrarVNPN5KaRQ2PGCcCiVMe7gNLqZBfRY6irIfNJBSDoViigziJ1fNSEzKJETjXp9jbJP2NGI6vw6cB22qEYKckegBVs2uxLF4tyMLarJlRGIglKLyILxo1mUhIVsed+frsuiTBVa+m2GS/kWFBptnKZRHLgKwDN8hrGz2T2bF8+07oecqISRGnsBjKdC1RcgzPVVf2ZuMNLj7DpeBmZdzxsHGo3FaJBOqU5KmKROVMHL9By9ksgn4ZihDxcZ8x8jjFCZEykJ6tggwYiDsuwz2cv57D0hwYDckqxR7p8ZNSY48PgvYFQPuSVkyCmFK358ck2+XIqCAbNvtVe7vk/0BauwFgumftExPlgrg46Y4owkxXEWhfhPgVqUfKpVmcxCQrBB8QzwhyTL8joGp3Dt993eTkGxxsd/xvQoR1ZAdhJfPH6UytRhNvWch35aA2KyFKck8ZLtYAkZT8/OpKMuIBlLKoTBUfpqhr+UwU/F9k1xjyoDVibioBWSaJBOLBkAi22lcRXB78u/sJfhyHQBcGhSTKUtz7MrtTSLdkuk9sy6mvki5mAoc3Mc40ULV4/GyoPquLLb5jCWboXIVV0q24b/SE1YJJnqAaUjA6LYxrHIfMzqMcqqPw/QcM3ybJGCANI3nOyGr2WCQkbJa4Z/oyv3xmZTQYlP2NIhi8BwyjU0G5xI85hdke6NEQPvu74Fr6NqldlF10jKWB6uYhjw4cA6ARb5gcJtEIgUQe/+IgOQUFRlPciiU+4sptW4IyhIu728v2zJN+b1pUHFQZAk2ZgaNZIOzcyjkTaSXrl652/ckWGOWXj+7Jtv0Ha4MCmi/knJ80UBKORSSdSCHPEXP0yB4WKn4YvIv75/aq2I3IGKQSbmQiI8dhTILFTYiyToALjWdYtNyXOzJyOh8dh7BNmV6iYMS2W5+keAaXjJDA1m9eL5NU9ZNY6hQJbdrgM8JNpOsy7SG3ii0CQo9VgOvjxNxvouxcgyUlDpTrg3YNS+ZiNAblF8qS4axZCo9VpLpY3iYOB5PJOUh44tzYdcJZAyIwvGl0kfm9oIQZpdBxH3vCUjWKzvPIvi5NTw1Wg2+7AYDu+G6N0af71H3d1GqJBTBnu9JECEWP3JI8b3je8agnnn0eY3lUmaRdMCKbIMawXIm9pN5RnaxbO62a9R3fydbADxhlA1R+WbymeCM0b2PkWwQkk1C4yHTe9PIyvGxK2M47pXN7YMSFIpy3NBASjkUKJGs0nFgmu2JSQhmxLGYpL+MEimmnawsIG43lPsuSjbFrAErj5ytRyRmt4wxMBVl7Eh5vkdMg1mxSeEt6ZWhKQGq74RFjxnd+wFKWCx5QtDne7H/bfy27KosvOyk1JhdCEFTO/S8xd0kWXTjMYIkC+S7gLchkCMCwDCW4Cn0elkjyvPx/VryP/YSNEg2RP6ueE/IdmPWJjZbj8Oko687MPn+tmthipVCgNgrrY0QG8MhJTvTKvumhkq6Q+dUXuuzMAHYLSdbo9RDvi2SBpxx6QE5cH8T0VRTcJnGFGkL74OtUAuok0mKQqyigyaK+2YdoE7IoI2QWIilQDHw1myVstxoIKXMBbugwp2MHt2e+vcsfw9GYc562IxqxD2Iv42lGABAOF/ZOYbrSJN5sgbgZH0FcQBF47nvSjZmHr0faQqf/ro40cVdsc/hjOB3gdYjxP6kb+IuZERGkZ4GfNeAEkZ+iYrSKDMj2QTcXjBMDgu+aUrvk2R5ZCLUNMvXU8PAbkgTvxkzRJCekP4lSkRFO5bliuvHQSqgMXrBdm0usje1jLHH3Bd9PVODU5ghhmYPUebPJeBKTk6+x0xDBGnFj1HeG758vc/Kkproo5XDCPOQbIioqesBlAfz5jGf28HzIKbS/efYt0RiYXAAJO43AJkU1EBKWXI0kFLmIt8uhTLjQjeJ6hSZaZCUXXZjTr98gj4MiuZoV2o8AbFxOUgyTFjA4oQeWRYRxDmCwMIwFpB+kd74UuIo7Io0P8dS1iwU18LUe9o3TRIxzB6jc294valkTsLEHeehaX5E83S+45GfZ1CL0ThpylLgSpkRGfI23IjlUinzxaC9eP0aMC0jUpRXEYKmynuyKzMr0q80MN3WLfXH2E/PqOaXwvRbq9/OpdheJlkWarKU3rxY8fi9uC8O7ryUlj0AME08vOJ+XeWgvA+4lIOmFQEkww8+E1PvOgbTk4iTkGQIyUnq8z4sXsMyWet7DLsOJBMeDsbpAFHQxWI/OlulKMuGBlLKfFD/z+y5MGsdFYQUk26QqabBvz9MfC+URHqMblsUs02jLDeZXrA8GfMl7qOHXo6wMM7w3jmDIH1WlJJk5TB7MFQGb0FfKxkvrzBInNpjL70udq0U52QXFueBYycjPWrpaQkWklVbZJ6STcAZIN9BkWVMNkJZKUy/9e4PJZ0M8KtS7pomReE6krU0DULzIfu/SYZEUWOcQmM852a4R5m5uL99h8EDPohFLxYDpisq5HHDJg2+fD0DajJ8TmhM0PsCJIiK96uIxYbgLA8BbgqIlIMHOUiT+T7xXfmcpEYC3FGfj/i5AgC/x8AMWdZIUQqsUXZWlGVAAyllLpINwId0PSViyss+9GeM6Osopqi6YsSanpSemWg4fJiY4CMmxrpcBDOyn4zsHMF3ZLw+qUynxdkVNlQAACAASURBVHKFaclTPlkAtr4mg9srrU2iMKZoQM2pGD1ierAWHvDOw21LIMguTALuefTuY8AC6QkjRr9h2otSDrpYhGTN9GVcotFutUTFeWWsvsOwDSDPwutrBp5uR4Jzl0uWZ9F2JZJZCdnAEfsUBUc5n36PFvdFR6bfBoOgPg9HP3zPUFP6xewqIR3R9D5IdYpPsqgyHQrLRQkyZn85r2/O6/aCTMHK8PkWc2UA6WjfyuI9o+hmyPAVPXSNepOTsp16Zef9lOcVZVFoIKXMBRkqsig+4zJQ6o0OLJINIMvlS987Rr5dfSofj++FnpFJHnWz7rsNIqAmZJRsXCiDrEAQrIrHMlQKXJVR/OwikJ0Dkg2utVBxFn+QgNKFzJbvAOmZ8udRU2GjsJsAdkV7aZZAjFKG3w0ZhpTFWy73pTwDANPysOummPbiHZQK19nwNa6Khibr8utYnrFrRspya1LuqZs5oyQ0pxvUWlTnwaRUSAWM/H2TgJqBX7pFQ5mo6vskG0EFfsQEnkkI6VUIk3UTMlHh81AtDybrQOHnmMkDQuxfSk9N32aE81IM1PeGhW+pxj5KcCr2K2QkEO/d70XYsxN64BZkZj6tlKooh4UGUsq+oUSeeKUvYtyTatDHiVmUgVIKM8NtS1CWrMsTuc9D+YIB01vs1F8UHYyBFFmCWZcSW35JgoXYU8JZ0PWBlPVifxJczLgApsV92xqFCYapRASzUnoOUiqltexCGPV3UqajhmT3xi1aJqknZMgc9i14rvleaM4mIN8LI/LBgJcaAFyZiQv92LIANihMUtHI7Q72ucmkVrVnarbFjpoMxGnAMefAZ7L4k+0/Vz6LAdjhLrCTAha7ShOH46Svafzvufp56PY/iPg8BFhEUlJbj9dv8jb7dyD8b1KgVNme78o9bFKSUjX1v6fvyf7mbdl30+jvSdwP00qpinKYaCCl7BuiWM6b/EVm0vGlEs7KHqp8h2VSp6oxM6Z0Je729b5AmaX5FiySBGRkwkxKLeWxVAUZgbCQWxS6P4D0JMHIk7dplT1gFJS7Ry3gJik998QPTcQekyhOGXbD7QFoMYgB361vdjyO/JIsNmRkco69R74DkCOYhocP03LNqwicyTmJZZ30pPQqUROwaX/0G5uKyQLJCQlm5DqiEMDcTybJ70IW5K4ERqNKe2439KrlXJyrfIdFHJWA5FT9DFgd2EtptlpOcnvShG1X6mUGo1RB3dcX783hfica0l4aVVKbFbLh4aKHWtN9+Xal9LoybFQes9S2Jf1zdiWW0+favf59rZZSm/MNfCjKotBASjlUxpVKRDcnTOrE8feGTFz5PE5olVTNc+1avYkkX7HxABHsWpgwGtiG75V9ItGgtvADNDKSn+8AMLLwmITQa8uqwcFbDkb6QoDRT+CSvYqBhvw+lurSELRVBRz3A2dx8gzI9zx635HmZySMpGEkSFoNulCDzb0UdKTaANa5rzcmbjff5cJOhDMGiIrG5CJD1C0FKAcXvcHzXbx1Orm0J55xHLSpKsrmWZgwywDTAcw+p9UihZJ4gsK8mF3pscg9oHFmWm8TF2bFdV5fxXfkb5gg5bNqsE9SxvO5NPXn216yrDOcbyAE0AMBUa3rM6JZ3zQleykm1ABoPpmOcUwqpSrKYaKB1BIxWCq5kihF+9D3ZGvX+ssh7LkQWPSh58h3pJThs2B6W8lA+F74ok+ov5xI8l6FAW/cxmA58WR4ebWk0YFkBIL/GhIJwvKdsKCngG9LZoS9CEGKIWy5kNh10cihpNRdKkt1o49lXux6sK9JgPw8gZ0H90Rg0a5JoDgYqBbnLyvLsb7T399jN4LOk5GpN7kuUg6s9v/GEg8AmKzfv5BHnG9mLpTO7ZoEosPN24zsnGTW2AErjyizaGaV0XtA+r18j0GPBGxzdlPcfFc0pswKIVmjIjDum9akoho2VK72eTiuweCBJRAnSCavbnDh97hoQjdjvh/cLiHfkUGCZINh183Q+e6d89KA3hVh1kmMuj6RZBPgFSpMl7MLDNf2wY9Rhkmi9AQ7HvpsL4Ir7XtSWU40kFoiqqWS6MN2JVFnUic7H8QfLQf9onJiKd+JE3GSzYolnmguXEwMcShdcKUcslL+rvSxGL0PZkWyZGRQ2NaYJvUJBzKXTbsEBhuxj4k9TaZBE/3t5nlyd7tB4HCtv5xlW6KRxD4EBomc5+bVhGR1coBhGqGs6YfLsdFPz7U4BJFAulmWB4v7t3oeB84pjzjf3AuBLQDuEWhMRsn3QkBD/SVQ0yCYFSpseNxOOZXHHK1SpmeOXOhhczssZbg4rZmUAUGc/OOsXxXdd0tbljigEF9vVgmmy6AgezBOLX1wX82KBK5RJX/0H6H/fA6cb5/L1Gzxu0HPw6F9KLcxOG1IVD4EyHRnCBCNfObMankf1p3CU5TjiAZSSwTnYfGI5rWzP0Rf1jBz0fQNR0jPUNGvkl2M3/ahcbpRNogX/5YOjF9TaIjmsuclTldxPt43zq7QVNFOuwqZXEpRTOtNmg7bLz4rm9fhaNgUGLIgpyeD3EILsK0avn5G1LMnjZnbNSpFIIGh0pBpSmaC3bBe1uD5Zh8a7vMyuzduv5KTIZBucN+5JZJMSzeTqcSYxYlaTuynNz2TIVBSqoxLliWUtwbOw6hymJgOV36unq8WwReB/Oj3H1W6Fs2vyUFgsgGQMbBNOe7B802GYFckOzRK8mEQk0r/I2cSGI0j+unJsEVZqleUKwENpJYIu14+cS6ipLMMMEvPBiX7n6AikkXX7bHYluwEBeW1sEA7Kd/FRlm7BrHMmGKUPLgw1rK84ZA9HDNRVk6xBdXvUSWeBeEzCRDyHdG+woSFVtSkZ9+PaVo9034/yf6mer5lpB2AwVRl7HTdIFlhsB/uvbGrBiuPLH/nMxaft2qZckrTcxoCtWqfWl3NIrMipTDwcEBuUkLjNEYKn0bEQ6+/7AyU9xp7ySyx576ScZxeHDf4QalohPnKVOokXJuL76RJTfuUSB+hPQEQ6IpsT1CuXDSQWiJiqeRyom9ibMw02yzYVem/8BkjOxdKL7uM9DQhOdH/5W3S0ZmZcbCLpQlZxAEAXvaZHYs8AEl2JpYYKcHEEh0Q+qCmvXeljFPshw0eb1MWb9eGLNhB2HOS0e3g8cZj2g9x6nERCyfHWQDTv3CPmpYDJpeM4u+iCjh7BrxkueqIwMapznmI2b+xvx/Y78FrQcmIsnMF3ykVxKsl46n7VXPCNiIK+PLwYlfLnj0pfcpriglYS7CHLDehKMuABlLKgVKUK8M026L6JGL5QCbkgOwByfrsR6cm3wmaNJmMp0uTLEKZSYKU9CTKUiHk/ferrlwIfob+JnZljxAlBDtlFN2kQcgzlQbfOgFNIWaYEsx6aD5vTW9uZy8ZIxMMaH2PkV9gMMretFnx3dDb1RJNK0dU+Df6Hod99QAIjYdQ0Tjuw3Watt8+XCsRke3XPFoGCrmGyjRgnMLL22IpNGQCnKLocp+1ZFw93/HBhpnh94L+VrjnyJJM5nW5aCiPuHYpVwI7flhhPwzea4qyrGggpRwoybr4yVE63yI7jqjaHCfv3Lb8e52Szfhtllkp42SC0q5LCTE5IYs6+1C2Wxc9INOSrBtnPvjHzX6M0R8NkEWuep7q9JnY1dDcTfUzftFw2nU9fJcKuYZBNetB8ktBlR2SYfTdMosUJQ/qwC5MX1LZ/Mw9CtZB8hq356VkuSvX164CvQeA1sMke5efl+B52n7bFYCzUGarkeEb2tcwRcgZz32NJ1E01kefvHAO3V68rxnWU5+pc1Ee5Nl0snwuTfCSURIzarLyGc23PfKLwUh5TYYhKGVw0AXrkz6o3Jf77YWK98JgmXzwXjuo0rii7BcNpJQDZZzD+yKIY/dkZDScXb2SzTjsOsDBEoYSAkO2b+OkXavM9tg1yW74HiMLTd75Nk9tQh95HLGMk4vVjFkJ5cDolVajBDer6GQxAdakPuuacfgeF1mIYuEM04++sJWp995FadTFN5U+sjz4sSVrsm/ZBRbh0uBnSFayE8V2hn4YDZn9qeJzXgY7bre0Axq8Lq4jwahpzpYVtasyYWoGm+snTjvK9WAP0DrXL5mHKTzXBuDLkvuoCT9AZDwo2M/EAYC4zwifO98FyPJcD0oiYxGMshsD5dAJx68oy4QGUspSw8zwbcg49YiJKUCeqBunJ0+W1YGIkG4QTBKyUVcBsGVf1Mj3TqTEmO8y4IHMzC5dUWTXKtODMauWb0uzb7XsswiSdSqyM9GYeFIQml8KgQ+HxuMmFQvnLKKSACT7FK2CiGDXgewBAojRu190qTgPPTerDJNaNB/KIGfKQJWAdAtT93sRVMvI8Ziziyyq2mnwlgMKoU3fG87gTMKu0uhpwBXA+jKTVsV3SnHZjAEbSn3jPiPFNsMUnu/KPRVL7rJ9A9Pk4IsYerUaBO7Ivw1OEZsUkk2EfF5mvg8AwKNQQJc2gHIbyaboYg16T/peUJKvUYpWlMNAAyllqXFtFHo+CWisJAGwuL4Xu0LAwOI8bttliTFkVhxKscYZGfUesQTHeegxW+BIeSH5UCNrGJvgTRL6sPbRVBxLozEIsisEv+7Rux9SsrvEIrngJGATD73hAzdNKUmOsw8ah+9KJskEZe6oyj7JiDeWkWN5KV4Xn4UGdksgE0QnCXV7ucv3GBWkU385jzlM6mXcd39xD8i79T4jgJzv5jUGbqcsuUu/mTT0J+vl9U02AV6lIGcwsI+E0o1gzvuBEgnouTcsr1BOIFaO1ZcCoXVK0YpyGGggpSw3xyC9T4aQbBop7U3QPqrCPkzpTVmAirJPSpjVLoZdmHRbQBYrOSGil+I7uP/tSWm0sv0NEaeMRsPR920cUW8qv4QiY1NnnD/fLYU2kxMMd6mUIUgnTHjGMnKx/6tlaTRmatKTJNmoxsE0s3NWBnDIgjyDD0337dm2ZRr9E61+r8wSuk5pyUQ0WcsrPSkipfsp39e5bgVL+h2gXNloIKUcOXE6h2hYw0kWWynlTBIEPGpmka7wGUujNKQ8NWkiKco9zErhC2dCSXBASmDc+R6HCDnOvBv19rUj5s2N05As1JReq2g547vBRielslSIcHxtKccNXpOiqb8nPotxeGCwrDSNZJ2GAgCyB3eOgLKMHEuMsdxlGiKhFkt7c227ASD2us0wBUgJwR7iKkJWLIZ8TWNlRTkMNJBSjhy3WzUT7l/8BssblwNDk24H0Iwv8g0IGQv0LXaTzvdh4zNGHlTpTUP6peCD+W4eeo0Gsju+B8nmpQBYAorq+H2+XZGPsP39Ncka0Av2LXGsPt2ipQ7SI0WJ0fcPF8RS6X6wLSoCqEVkHA+SgxxgUZR50EBKuaxxHdHHMc362ZeDxsZJNz64Rmm7GrIvZvZATfq9Dn9B9RnDn5P39znBhum3wT6ZOClIICRbw6rmfQyUgigh2HWCORd/T0inGPcuE4MlxoVue8kDKEVZVjSQUo4cuwaAZIFYZLpe9H8qk1StxU297QdK6MCbZE2Txk5RTTrfhdku5hfYnGk/U0KyJf0/IIbbDZNkOQNNGvKpAyQbM+n8JRuAs6Wo5yC2VU6uTeqLWnZcW2QD7Gr/fe2zIMPQUu0lRTkMNJBSjpxFlCZGbpcIZIPYn8XMk1THCfZcCGJOyyxMOt+xbBZ/riuwuR9si4BWGIP3UrJL1gEwlVY9MzDtfiJDaF4DmbZbkvF5dmEazUOybFMCWNeRHjgAgC+zdmJ2XAqVpleFl3RDmXOOwIrzsG/A9AygolyBaCClXNYUk1Tp+Ekqn4lvGCXBN2yJ7EPqUnj/GSA9PX/mzbTK/qpp1jSz4ruScaLmsBlxLCcmm3NoB9R578FrbMppu2UgOy/Bim0Bbo/2F8AS+kqa0e8SBDROza695DrlRJ/vzG5JoyiXOxpIKQuDXZiWSo62gTkyrvQx9LrtoAfUk1LQvEa1i8btBf+91Rr9K2GhY4+xI+Lx+sAwwAQKk5DVwNGk08uOvheyXzOWjvJLcj2QAbZZLuh95cQpU4zz7kffNW5QbZ2vYgJwxLlaFJzLBCI70U2LWaRJ2BYVYpZV3SgiMe+OpT0iAkKQCg5TijPun2kEJXQcToZSUY4bGkgpCyO/VDrSR9uTReDaXGgpJSemL2bMopCdnWeYJtA4ZYYalqtQAiBDITC4DESzXgDgfLKmEiAlF9cOU25jgq58O2SF2gzTELuPpKasQSwdkmVkF1AIIqZX1Q8uKCFwL1jMVM5zXzmxpibRkDDjFFXtvms8g3F2doGR3S/ZnObDhiUPFoKR4C7ZlHvctuoroo/cXEp9WSO7AWAnaIAlCGbV9TNTpiGefHV0z2Ylioz6nvgYDmYqFeU4oIGUsvS4dmwYZ3BWI2Pkg3Ahl2WqSdiNkImyS2Q5EXaDs+BBl04WLjRNAiXiTed7jGRjsYtefiFkdIDoZSO7OUOGJtkCfE8W+WqG0KyE60Sjy4nRlJoSuVbxPQmA9/UUGuM1xozX2O0xvBPbGt8FcBC9fEHWwGf7LOmNwaQEEwLx3oN+rhLwQQ1psKuoxLcZ0EBKOYZoIKUsjGRT+jsWmY0CZAGMfnO11L0NkKyJdwU1pjcsE9Uv9RwWcZqtdz+DGtJbZJqTz6trl4uSS4YbrpNNILsAmDXApmK/UrcEy5WAJdmK9i31j8e1pXQ1qkw5bQrP7YQgLgsBY/Cxs+uM/H6CSSXLNkneYp5rzDkXXnQmZSSbB5euJEuwM2TK5ib62k0oAR8m8vCCoBmmQZRyPNFASqkFe1GC9jkj2Ri9AJM9mOm7ZCP4h5l6GRAiMZJNtsy+sjKcV3zY5tiO6wTl7UbQPRoQh5yGbRGSDSMK3kayCMyhxEbDC081yBwXcHIOEBM4A8yJ+seSbFIRzNVWcM/FzBaQTBkgyuXpDO8LhGPpQVJQfcEGwbZEkdy1pfwWzYLZcSF2Gq9dnIxjBxHhnLJw+xywDYI5E8tl891LzCJHQObog4Vkc3oJuNjfGe/XeSAK1jz78OtTlKNGA6krDPbBWDWZrSzDWVna8Xs4UCuMUcz6JUtEA4vubLCXHivRNJLjNS3pS2EXfPImlIiiRYvsS6lknp6aLVuXbAHco2APIr57brei81RZmO0KFf0/IxdAquzLjGuWWJLUfz17Rn6Oi+Ou7sOs2PXQID5QljMtwHTEcNf15L42Lek1ys6H+3y37OPyvdIiJgYTkzANeV92M/rBDeB2gXzHAw5ITxHsyvjMlmuXGlAHISBbRxXcbUtJEyT2QgctdzDps+ozHm2YrChLhAZSlzG+G57KV4LTvWdk58oFJ92qvy0xqw1ljiUpgzFLySua1i70yzZMODEz8l0JPH0GwJRGucnm+OxM1fvNu0oTu59tN4ZKUpW/r75HZFIGoZjoipmaGSfQZjrfvgweyQJ2XQKSWQNw12FwT+7hwcC16C3qAdn5+AdhX2MJi2V/QSGzaILFSg1ph2jKu285Bi/BFGeyQ+ZhPPLcMctQBTg03c8pIMvM+5ouLO4rxsz36yLJt6VkS0YeQKoPU8WEsBEDbEU5SjSQukxhH0bKQ8N140wYl44LTW+2tAQZQnoaS5WC93sosjMAIdlY3LbJRvVrQlxNyIaMRuy5zgCMCQzsGgCW82RWGK4dMir7bCa2awBzUCWfIys4ONE1C7Ocb0rk974nfVHzlIg4L334fAY0TlcWUh/KT2np0cdZCPAoXLtOfzBClkRagA8nw+G7ktE0q6E024R843qM1LDqE5BNMHP8VghneiDZhyp9sgHku+OV4Q8LKQujyApXpy3znYqfYnL0JVPlykYDqcuYQpcvfMdQIqPuvje5MXfs9vZZLls4VAo5osYTOPuQTfKSTZo2vWVX5Hwl3oAzBJNcgHvy1D/J6JZM1SOOYGbI/k2C7GyZxP1SlIIHleFr3D52lfo0jsa+hwsBx2AJiVDcxIMZlvxSaKwnID3JUvpbKQMk26KRE4BEtO8EUx1cpwwC7TqheTUF2YnJaurpSSruteoxjz1HFXx3QDhzzqCdknr3GOcxkDmYE2rXAN6W7Q8+gNCM96KiHCQaSF2mkCEkJ0NGoFIaOijl6KMglhrBEJHJKcfl9ypTbe1hM9yx72P6y2viz3b053C/JZw6RNkDSqS/JwHVNlt2e9JsHkvLo2AXys0eMC1Gsi5N7WSlZJOekGzUUFAUS04cynoc93H2kuWB4Pt/thtU6+Fl8F4DpGk/9pvZ9WFV+OJvmwC1pZy5iPL7pPurCBRpvIjqfu9P0yQ0xmSa7HrIjB9CQ7yiTEMDqcuY/ZRxloE4eUUNGZEfxPcqX6J5jUUqRZnhOAZ3vu9JmWewV0b81CTAmbSw7hfX8ch3WLIBuQRQteUSXCko6nsYK2/ATko3viPZwvwiQA1ZgGPJZlRmxW4C2CWYBMh3o3ApJIBZgqypWQFMHqY103pl9KIU2BrIRmVlvxn3AKyNec9kfOnS56HXbMK0XpXsIsN3GKYlE46DxLJb0c81ELi5PRm2IMtIT9LCS6lkSMrnirIEHIPlRLlSKSavxogH2hWZaGPmWiUk0wij1nzwk0j7xWelcrfJ+kstnFcnKA9GxFAyDqFpOyMk8yyGsbY84c8olcGHfEcWbQ5TWpjSI0RWrj9ZIKFQNmvR+JH+XDI6h3XdiSTwRFDuJsuTNcCqpUDXLyNimgCMNF9Tm8E5IdkcLd8wqnTJPhgZe8lYTbMAkv6zcH91GLw5nOWzKwBnVPw8iN+DlMFzCbqWTadNURaJBlLK8lIR0h6JCb0kTLUNaEdltg4L9qOntUa/GKVg4sDkVJ+IYU07kZkJ7yl9Yv3WKL7LcB0pt41r8iUrE2/cmzwhRyRBIiUGboeBFYZtiWbTpJJNHNGXiS6CXR1/AxReflMmLReOH/PzjK8lI1k505QsH1kABmPLXqPgMffSIG6PxbLHyGtNi4ogyrV9GB6g8qFkDKYlmSqyIROsKJcxGkgpS0uyRXB7pcjiIL4d7GMAgGaf2mMXJr8aB5+pmFYqGcQ0JCvhcyAZKGHEsf+DnD4zK5IZiVIHkeo0KHeB9Mz4niSTElBzEU3WgucfUa2+mpiRi8rjk/zzfM1Jy0VTTL/VmCozK4D1Mlk7qmRlUskOxZH/ZBbpEhMnUEdb8EQ4L8uxZIH0TJmFzHc8OvdKEJdsAs2rpwxqrJIE0CT3RxT5BIZLl4py3NFASllapopAmjE/1yS7ID1IIKBx+uBkHWQRqZRKNuoFQHaNxrb7HPT0GY0LTAmlqGdNpfna7zlDUJisSzmQEpqa8bAtKQGDUasEvCjqTr8B4XxPcAWwqyLkaZo+/P/Z9mXcFGP/TqDsITT9pVzXYTAYXJkMnEb17/0eCoHahOtNcyrKcUEDKeXYYleo+OKvI7A4BA/8d58UgpUhqxADMyJ5OpeM1P4bb32PJVPX2F+ZyrXFAseu1s/Iif2OZKPqToax577MRJ1MWnxddWGvMmmia2ifbRTWnL6fh62gzZ7hdgDQdJHTZIPg2iZIKCx+X4py7IjmcbtCIDA8zTeoUS3P8xGKfCrKQaCBlHKssfvoEUq2gu/YnF56g/hOKVjJ3J+NSLeodiZqGvklacKPWkHz7LvPSgsbzvvFLqdhEqr9zeHaotYt5SiZzONcgoZxtitRgd/nDHgRhrSrEkjMAjNL0zNNDzizi4x824MMoXE1YOzBGRT7rJygc51gxwIAhobKuFWSDVq8gv8A1XJs3/lrEZITo8uubo8LSYxxGUq7AsCH5nTNRimXGRpIKVcsJl2cUCaA0gZm4Ofy3xazAEZTXtqHJFg0QOYcsAfYH+a7kH6qEPhFrzvfYWBcIJVJ1s33WCQeVgjZtz3SPYP09Pggh1kClOhLGD3ufFsyWOJzN1rvyO14yQxBsoaNU+O3C0iA6NoM06SZArxigo4B2uv30xt1zwxS9x7yWWhMJ0KyNV+wnV9g9B6QbGLzYYRkXQy0q+fQdcq+KuvG9ymS6f+d22W4PTnX8EEkeG309VGUZUcDKeXYw8wLta5xuwyfz1byAsJifQK1vdzmJdkS6xpK9xmcMQGe64jCz011esusysi8z6TpPt/hYAg8cO1Imqpjk3jvQQ9iIHMMOELzoaPfK78kAVr0ZgMDcKJjRYmUXeNCzY7hHcPviRaVaRGwzUOK4kAQJe1xnwxH9MRzbZHemOXe48oPdpWK3qTB7GpR9kMQoJzhWvu9ID0Ahu+M1lyqllwjrs2FrY9r9yuli9yEZAiL0mu1LF6zRC7+lfL3+SUv+2AIboc1kFKOJRpIKceeuNDVnYibhO8F41gAcAQzYcR7FIfh+UV2/8267BH83+hAe1bsCvVNaZlT0i/jOygyGTkGmrJZshecA25PNIjceRQB3zjFbK5O8oU+NfZilkwNBoWgOL8k2RC/B1DLw5Nkq0wLgBs+t9EKhT0KnzyTkgRXCWYadCAjx+q7ZbA9Lnjwe5Wy34xTqZQCCGW5Uc34+Q7D7QY1+JMhy5n3l3uTEwhSCASzWpp1+440+bOTc2zXhqc7J+4biVCw7wWxV5asFKlCuXJM0UBKOdawlxIQMF48cBbIoBSSPLg2mSPHpBIw+B6P7VWahM8ZcPUCx8HrEc15i/8/cJ4pNNH7LgBikDUwCSNZIdi18fIIyUYQ9mxQkUlMtwjJBoNd2aBdTFA6hvUAEgnSkrXRF9xuENyulPGir1xyAuA8GFGP2R/fjereobwWMkqmSTBNCQhlcpRh12m4329KqXgSdoXAWQgYO8PTr9EqiXP5HzXQN5FJhpCsEcwjYgmZ4ElKkgwAMVPVna2/LlKev5ghnK+JXVGWAb11lWMNmXIizq7U0yCauL2knFyiZjTsHb9N3+OiYX0eI+jDhH3QCAoLuvT2zNeonp3nIgsxKRAbHuoesgAAIABJREFUfM+IaYTz7IbLoETRB1HKgJwBjTPTpx3HTfLJKH/ldasSGKUnJaCZZiQs0gEjgsEpsgtuV46PHcP3huUHuFfxftzlofewKxR62ebzzvNdACDpRVrtF6O1KyHoTMoAk2yYyMzKa1L9mzR4d1IKuG2Cz+cvxQ2ev1kDRUVZJjSQUo496RbtOxNVxaQEThj5eQrNztHseZj8olhv+G59H7OjwGehyRnjTWbrwhWBS59JIAkMT235jJFfkCxGsin9TaAy4KxjNjtJ1NNnXJTIZlGsT9bD9NsBi0JSA0AmQcIoz0tKQtO/H38u9nOdqEHgjohoDgYqdpVGTtlNOt+UEGwCAFSUaFVYU1E0kFIuExb+he4qfnYdBjb7AwRwyGRYCvpDmHuC7jDwvVLLx8+gATUK0wJMj6S8Y7hfaLGqgt5DUXbNzxNgYr/P/m1aqtNvvjPdP26QwwgAkvXQH2ZGN4qTJaSnQ1buACYnk02AV0P5cdT77zd7S4T8Essk3xotfUZWUQ4KDaSUA4eZ4bblyTvZWN6sTR9WsgG+xzCVBSI779E7xzBNoHHKSENuV5pn552g891QHmweXHnQNksjWUoZ2UXph7Ebsy+o0R8PkPKVD+mpoaEtkkk5ZiBZnyx26TOZUKO0v1TodsMU2dpw1oaHfqhH3fMt/UUSOM4b+E3LlA2WHRdJnfLjfuCci2Z4t8saSClXLBpIKQdOdfrImdj/stwQiZRBNc0Uvcg4A7yDlBNN8IjbB/mlUB7sHVx5kBIqsjb5pdKyhpL9TQCaVcDyGKFFpsITzjTlvYhGS0Pkl4JdTzgHJg1TZGGCkl1/1qmYfptiijyKOuebWTJtvsvgS0Drf6EDFek8llTMs3XiTrmS0UBKOXD6DGWP81pEojfkHcPY0do8c232sMuD1WmwCWa/dZjkEWdWAJPLaPu0TCRZKmUGMoZHLIkFqYYRfxun32be55rnm51k1MgA+TbQODH8GrfHcDsirZBsXVk9Q0RhYMCX95HvijZVnf43Rblc0EBKOXBMs/zC3U9vzlFDltA4LY3npjl/KW+QRZQHZ8GuheyQOdgFL2aNRsEs8gmw5ZSe7xJ8h5FvAyCZqktPEvwI77dJ+FxKyZQEIcuB4KbO+ZaMpEgIUArQmIjLtSW7xV0GZyQN5lcQ1dKka5f9cumJw9FUU5RlQAMp5VC4XJ5Qy8mlBW5zAeXBmd6PhkfxDxNmRn5e+qKiGnw8BzKyz4WtjGnNfr7ddmhy7wGUEohCn9VKDCDrnW+7YtA4E2x0xpQ/TYPg8jAZd4V/m0b7n+LnY/zQpCizcIV/9BVFOXQ8kF304l/XRF9JzK4DYJk0mzd7SQmAHkLZThrrwdITNat45LQm82QjBGVjJvMWhe8x8osMGCA9QUs5sBGV5EFS1lWUKwUNpJQrGvbBp28GHaK53oejuOeV1UczlqCQTcSoNiqZhGBO9r+0mOgbU6qr4na58PKzqxRsZWYc65uR/dw77GIpM/SRjQnG3F5pUeO74zNkRwnZOKChKFcWGkgpVyzsGdk5CXAmiW4ugsIPMCUx1L2SMUB6whSlPUC830SsczhQcjtlqc40CDQmU1Wd8oMDzFa0iUFR2ls2XLuibm4nNO43JICiMd55iqIcHRpIKVcsYt8hP4tw5MEEUsziB+hz8VbzjtA4OdmW5HKGiJCcDErnVoIJtxvkGDA8DVlMFhKASVOGY6b85p3uOwyqfVWTeqzsSvDLo8MZSFAUpT4aSClXLJTIIsuZKDMf2PuQBAf+AZbFMJZnjumnj1kasCmZv0xJRMW3D00pvdmNMAFmJwtckpFsn88wZNK7rNgVKgLFaQMZR9UXxV4mE2ex4VGUK4lj+lWuKPtnlOjmQZGsE0xqkF1kEHDkY/I+Y/i9IH45w5h638RdMB7eL2YVSDC+SZlofDlv6LWWYPepjXXYLPNE62GWvxXluKKBlHIouA7DXWLALn7qiJ2UzOCAZIuWVr/GNAmNq+TnWJ7xPQ5j/ofbhJ5flPd1HaBxeoZsB1c8CHu8EOPamLEb+5YsVi2UHIwn3VFQHJM9uEAq32W4XQl45xUL5fxwyt+Kcpw5zjrTyjHC74nnGufS+LvQbffCFz5Lv80yIwKGZRCVnRfbGbdz2Dsy558ZMaclA9g1OpTgz22LrUt2nosgbhlgP//+uJ3KMfUO5ph8W0YjfZeLYGhWKBUtr3i9FUUZRjNSyqFgmhLwiJr2grfdKJuMZ/VdOwiYuVaAwb7y85wL3bykWwTXCeeuZjbK7YnPoFkFko3DewYrMiIdRn5JVLOPWkeJXSh5eZk0TDZm25/DuPamSXB7Mik6rxVQaVCtQZSijEMDKeVQsKskQQ4tvoRFlpCeDj8f8UST77L0QRmxOJm04JumnBf2QLIg3766UDJ+1H4U0bAZkGbuusKWiyhh2Q2Az0nwwTmQ72Cs9cxhwa4MhuYpeSXrQI5g03NAwX+yGUqmRrXLFOUg0UBKOTQOMsg56gAq4vZQ2JtM0y4iIiQbh7ZrAMIElptj4o7C/2bsiXLbkskCgPTUfD1OJiEkJ6R0uyzEkte8E59kx/sQLpKjztwpypWABlKKskCKEiYBZsmEE5mlJ4dzzCwMGlWrfYaZfPr6ylZ+7MumEhum4ZbDfkRLXoqiRDSQUpQFYleC+OMBlDD3DZfGsj6bfeLONGjm/rZkA8h3o3fe/s6HbS3Z+VQURYFO7SnKwiFzONNss0KGYNdE/pJzsa1hf/A+dOkWIVlfvvOhDJNvM3oPerjOEtVRFWXJ0UBKUa4gknWCbREokSZp3znqPVKWBZ8zXFtKv25bAylFqYsGUopyhVH0btFkfzflyoKCVyEA0GUifKooh4F+jSrKFYZdJVAqDfFXqnGyMkz0KmQnU4mKotRDAylFuQK5XKxWjhOuzTL1uHo0559ZlM4nSYWQnV+8U1GuVDSQUhRFOWB8xshD3xHn9QVN3Z4EP2Zlf1Og7IL0hZdJSruigbSiLAoNpBRlBvJL4o1m10gXI6U2ZFAKmtYUj3V7pZq8ZdqX+r3vVax2upOFYhVFmQ0NpBSlJj7jQqXb7bAGUkptyBLSkxCvwrqCptXBuX2ImQLRU3F5/CgV5XJCAylFqQnZsBg5gOb0jVOuXExKwAxN3GYFsJ4Ahnjm7QOyhMZVVNtQW1GU+mggpSg16Ztq0k+OcsAQzWYsXXebiqIsFl0OFGUGyFChtVMHZgb88TSPjarnsafnOB+LcuWi961y0GggpSgHBDMjPy+9VXYFSDaPzxe5zxn5efHjSzalxyYaHttVINk4Psey7LBjuD0RSt2vH6HST/UzaFpAuqXnV1k8qmyuKAeFky9wAPDd42W5wV1pTAbLlBe7iuHxMTuWZSe/CLhdRnaRwbme24Xij+9nUDk+aCClKAeFDRkGAswxm/AzrdBcb2RUnhLANORYRk0rMsuofnaBwW7xC5bbEx2ky9pMl/sH9ZT9Q5ZgWuPvW0VZBFraU5QDgoiQngBEQOh4Eae8qqQngXHH4jsopCFyIqRbi9sX9kHMkuV9/DrDNkkCu8uAZBNwe2LbY9SyZ+FIOU/Pq3JwaEZKUZR9U7UVWbjFCJVmuvkuw7dxYJmvo4ASQrJBsC1d7BXlOKIZKUWZE/bBu0yngWAaQXDSA6a52G0TybZ9DwBp/UtRlOVCAylFmQPOB7zLVjWYGiy1MTP8ngRXdrW+NcooyJL0aqUGfi8qdes53y/sGa4tWUTtIVKU+dBASlHmwGdhqg3Bu2z1aPdnGfEdFEa9YEKysf9tmoRgamwn32b4PYZZIZVqmEC+DfhO1AtT+QVFmQftkVKUOTBNsfwgo0HUssHMcG3RwHJtLoRFFUVRDgLNSCnKHES7GJ0GGo9pAQlTUdo7LIgIpgH4HsM0aF8lxcudZANwlkBWs1GKMi8aSCmKciAQ0ZFl65ITABwBi54gvMwgs3g/P0W50tBASlGUyw4i0m83RVEOBe2RUhRFURRFmRMNpBRFURRFUeZEAylFURRFUZQ50UBKOTYw6xi7oiiKslxoO6ay9DAz8gsyzm7XgGRdx7QVRVGU5UAzUsry4ySIAgC/p1kpRVEUZXnQQEpZfqyoiAMqGqgoiqIsF1raU5YeIkJykgFWlWpFURRludBASjkWEJG6sSiKohwxrsNwu2K/pIbggpb2FEVRFEWphdthcC6G4D7TnlVAAylFUZRDxefyRM9OFyHl+EGhX5UMQOplCUBLe4qiKIcGe0Z+nsEeoD2gcZWWRpTjRbIJ8AqBLLRnNaCBlKIoyiFS6MpqQko5hhARqHHUe7FcaCClKIpySJAhJJuA7wJ25aj3RlGURaCBlKIoyiFiWwTbOuq9UBRlUWizuaIoiqIoypxoIKUoiqIoijInGkgpiqIoiqLMiQZSiqIoiqIoc6KBlKIoiqIoypxoIKUoiqIoijInGkgpiqIoiqLMiQZSinIMYM/IdxhuT+WwFUVRlgkV5FSUY0C+DfiOBFFkAdNQjytlucm3Gb7DMCuEZF3vV+XyRTNSinIc0ESUcoxgz3BtMWd2uwxmvYGVyxfNSCnKMSDZAJwlUKLZKOUYQIBJCT5jmAaBSO9Z5fJl6QIpt8twuwxqirmnfgAVBSBLSDaOei8UpR5EhOQkgx2B7FHvjaIcLEtX2nNtBrP0g7A76r1RFEVR5oGIYBLNRimXP0sXSJmmfOgoAWjp9k5RFEVRFKVk6Up7ySbBrgKwWtZTFEVRFGW5WbpACgAo0QBKUZTJMEv5n/ShS1FmwmcMtyOfHbuhn5/9spSBlKIoyiSYGdk5BufSDpCeOOo9UpTjg9sBfC/o0jUItnXEO3TM0S4kRVGOHx7gPPzYO1iNIvaiKM+5aiEplwcUUygEnapcAJqRUhTl2EGWYFcA32WY1YMtS+QXpBRCBkhPA2S0DKIcb+x60KOzgNFWmn2jgZSiKMeSZJMAHPwiwJ7DfwF4aB5fOfYQEah51Htx+aCBlKIoygSSTYJrA6ahgzCKogyjgZSiKMoETINgGke9F4qiLCuapFYURVEURZkTDaQURVEURVHmRAMpRVEURVGUOdFASlEURVEUZU40kFIURVEURZkTDaQURVEURVHmRAMpRVEURVGUOdFASlEURVEUZU40kFIURVEURZkTDaQURVEURVHmRAMpRVEURVGUOZnJa8+1Gd2zLTz7vT8N7/1B7dNSQQRsXLOG5nUd2FU1LFUURVEUpWSmjFT3bAuvfsWvYXd3F8455Hl+2f9vd7eNX3n5r6J7tnVQ10BRFEVRlGPKTIHU9rd38ZpffQ0ajSvHCr3RaODXf+3Xsf3t3aPeFUVRFEVRloyZAilmXFFBVKTRaID5qPdCURRFUZRl41Cbzb/85S/jpptuwrXXXovrrrsON9xwAz7xiU/0vabdbuPMmTO4dOlS37/ffPPNeM973jN225ubmweyz4qiKIqiKOM4tECq0+ngpptuwste9jJ8+ctfxtmzZ/HGN74RX/nKV/pet7q6iuc973m4/fbbi3+7ePEiPvnJT+Kmm246rN1VFEVRFEWZysIDqbNnz+IpT3kKOp0Odnd38aQnPQmf//zn8a53vQvPeMYz8PznP7947ROf+ET8wi/8wtA2br311r7s0+23347nPe958N7juc99Lp72tKfhyU9+Mj74wQ8O/e3HPvaxvoDrl37pl/COd7wDAPCZz3wGz3rWs3DdddfhR3/0R/Gtb31rcQeuKIqiKMoVx8IDqeuuuw433XQTXv/61+PXf/3X8ZKXvARPfOIT8YUvfAFPfepTa23jxhtvxOc+9zk8+OCDAID3vOc9uPXWW9FqtfD+978fn/70p/E3f/M3+LVf+zVwzealLMvwy7/8y3jve9+Ls2fP4qUvfSle97rXzX2ciqIoiqIoM+lI1eX1r389nv70p6PVauGNb3zjyNe86EUvwj333INrr70W73//+/t+12g0cNNNN+F973sfbrnlFvzt3/4tbrzxRjAzfuu3fgt33nknjDH4xje+gfvuuw/XXHPN1H364he/iM9//vO48cYbAQDOuVp/pyiKoiiKMo4DCaQefPBB7OzsIMsydDodrK2t4fGPfzzuvPPO4jUf+MAH8OlPfxqvec1rRm7j1ltvxe/93u+BmfH85z8faZriHe94B+6//36cPXsWaZri0Y9+NDqdTv8BJUmfWGj8PTPjCU94Aj75yU8ewBEriqIoinIlciDN5i9/+cvxO7/zO3jxi1+M1772tQCAF7/4xbjrrrtwxx13FK9rt9tjt/EjP/Ij+PKXv4y3vOUtuPXWWwEAly5dwkMe8hCkaYqPfvSj+NrXvjb0d4961KPwT//0T+h2u7hw4QI+8pGPAAAe+9jH4v7778fdd98NQEp9//iP/7iwY1YURVEU5cpj4Rmpd77znUjTFC9+8YvhnMMP/dAP4SMf+Qie/exn44477sBtt92GV7/61bj66quxvr6O3/zN3xy5HWMMbrnlFvzpn/4pnvnMZwKQYOwFL3gBnvzkJ+MHfuAH8LjHPW7o7x7xiEfgp37qp/B93/d9+K7v+i485SlPASDlwve+97141atehYsXLyLPc7zyla/EE57whEWfAkVRFEVRrhBoUrP2w17c6Pvlt/9EbFOIxHOubqP35UCSJLjm1gOphCrKFU0zbeKqjatwav0UTm+cxumN09hobcAaC2ssjDFwzsGxQ+5yXNi9gAe3H8SDOw/i3PY5nNs5h9znR30YiqIcY/7kV/4EAHDr79869jXffHdvpOGuRgaKohw4jaSBR1/9aDzmoY/BYx72GFz70Gtx7UOvxTVb12Cttbbv7V/YvYB7H7wXX/rWl/Clb35J/vutL+HeB++9oh74FEU5fDSQUhRl4ZzeOI1nXPsMXP/Y6/H0a5+O737IdyOx8nWTuxz/8p1/wRe/8UV89B8+ige2H8C5nXN9/93Z20Hucjh28N4X2ak0SXFi9USRuTq9cRqn1k/hzOYZPPKqR+IZ1z4DL3r6i4r9aHfb+Kd7/wl3f+lu3PWlu/CZf/4MOlln3G4riqLMjAZSiqLsm2baxA9/7w/j+sdej+sfez0e93DpX9ze28bZe87iQ5/7UJEt+up3vope3pv7vR7cfhD/fN8/j/39RmsD1z70WjzmYZL9esqjnoKXP+/l+MV//YvoZl189qufxd1fuht3fuFOfO5fPqcZK0VR9oUGUoqizEViEvzQ9/4QXnDdC/C8Jz8P66117PX2cPaes/izT/0Z7v7S3fiHr/8DnHeHul/bnW189qufxWe/+tni39aaa7juf70O1z/2evzgY34Qr/qxV+HVP/Fq3PvgvfjzT/857vj0HfjCvV841P1UFOXyQAMpRVFm4mmPfhpe+PQX4sef+uM4tX4KF9sX8d8+899wx6fvwNl7zu4r23RQ7HZ38bF//Bg+9o8fAwBsrm7ihifegOc/7fl42XNehlfc+Arc86178MFPfxC3/3+3438++D+PdocPCGYuhoUURVkMl2Ug9drXvhZ33303HvWoR+Htb3870jQtfnf77bfjzW9+MwDgK1/5Cl796lfjla98JR772Mfi4Q9/OADgN37jN/Dc5z73SPZdUZaRxCT48R/4cbzsOS/Dkx75JOz19vBXf/9XuOPsHfj4Fz6+lMHTJC61L+H2T92O2z91O06uncSPPfXH8PynPR+33XQbXvXjr8J//9v/jv/61/+1L6t13PFdRn6RAcNITxLIakClKIvgQAIp/8170fvIXwHeIf2R58A+8rvm2k6WZWBmNBqN2n/zd3/3d/jGN76Bj3/843jDG96A973vffjZn/3Z4vc333wzbr75ZgDADTfcgBe84AUAgK2trUK8U1EUYaO1gVv/91vx0me/FA8/9XDc8+178Bvv+g382dk/Q7s7XlD3OHF+9zzedee78K4734WHnXwYfu6Hfw4/98M/hx976o/hM//8Gbztr9+GD//dh+HZT9/YEuM6ADMAB/guYFePeo8U5fJg4crm2f/4OLb/z59C9+3/Bd0//kPsvPRW9P76L+fa1sWLF/Gc5zwHt912W20V8rvuuqvIJt1444246667Rr7u29/+NrrdLh71qEcBAHZ2dvCsZz0LL3nJS3Du3Lm59ldRLhfWmmv41ef/Ku5+w9143U++Dl+//+t46X9+KZ7zfz8H7/4f775sgqhBvnn+m/iPH/yPeMZvPgP/7j3/Dme2zuAP/68/xEd/+6O4+X+7+ViXxUwTAAFkAFP/2VRRlCksNCPF3mPv//1PQF4Rx/MOnf/8/yB95g2gSomtDldddRU+8YlP4K677sKb3vQmfO1rX8Mtt9yCF77whfiZn/mZode/+93vxoULF/DQhz4UgGSZxgVFt99+O170onJM+s4778Tp06fxzne+E7/927+NN73pTTPtq6JcDlhj8dPX/zRuu+k2nNk8gz//9J/jrX/1Vnz+658/6l07VNrdNt7xsXfgnR9/J258yo34tz/6b/EHL/0DvPRZL8Xvvv93cfaes0e9izNjWyQBFOFYB4SKsmwsNpC6/zvg+741/O8XzsPf+3XY7/6eubZ7/fXXY2VlBW95y1vwtre9DbfccsvYMtyJEydw6dIlAJLROnXq1MjXvf/978fb3/724v+fPn0aAPCTP/mT+KM/+qO59lNRjjP/6nv/FV53y+vwuIc/Dp+651P4N//l3+Dvv/b3R71bR4pnjw997kP4y7/9S7zwuhfiNS94Dd532/vwoc99CP/h9v+Ar90/7Pe5zJDRAEpRFs1CAyk6cQJYWwN2d/t/0WjCnHnIzNvrdrt461vfijvuuAOPf/zj8YpXvALf//3fj/vvvx/Pfvazh17/7ne/Gz/4gz+I3//938fP//zP48Mf/jCuv/76odfdd999fWW9Xq8HZkaz2cSdd96J7/me+QI+RTmOXL11Nd7w4jfgOd/3HHzt/q/h5W97OT70uQ8d9W4tFcyM2z91Oz70uQ/JlN/zXoEbnnQD3vZXb8Mf/MUfIHPZUe+ioihHxGIDqWYLzZ/5P9D9o7f2/Xvj5p8GrW/MvL3d3V2cOXMGf/EXf4FWq1X8+5kzZ8ZmpK655hpcffXVeOYzn4lHPOIRuO222wAAL3/5y/HWt8p+feADH+gr650/fx4/8RM/gbW1NTQajb5MlaJcztz0tJvw72/992imTbzhA2/AH3/0j4/dBN5h0sk6ePOH3oz3fPI9eM0LX4Nf/Ne/iGc98Vn4lXf8Cr74zS8e9e4pinIEHIhpce+v/xLZh/8C8B7pDTci/dGbjn1NXk2LlcuJrdUt/O6tv4sXXPcCfParn8Wr3/Hq/7+9ew+KstzjAP5992UBV+SyGCHoWpOIXZyOKDJoaQcZxzoRcOxqpZV6NBvvoxMO5Tg2KXicDkhKamRjakcblGjSQ0cyyTnVmsV4lDNeohQUUZHAdNnbe/7YoIuZ7eXdZ3ff72eGUdB9/aKo3333eZ4fGlsbRccKOuOGjkPRU0WI7hWN1dWrseHfG4J+dx+RFgXc0OLw7AkIz56gxqWJyEv3DLkHq6esRnyfeKyqWoV1Nev8fvp4qNh7eC/GLx+PFZNWYMlfl2Dc0HFYsGkBmtqaREcjIj/x+fEHRBS4Zo6fic2zN6PjSgfyivJQtqeMJcpLbZfbMGP9DMzfNB+3978d1QXVyBycKToWEfkJixSRBkToI1DybAkK8gvwwaEPkLMyB/89ra0jDdRW+Xklclbk4GLnRbwz5x08PeZp0ZGIyA9YpIhCXFzvOGyduxUPjXgIRbuKMPvN2bDYLKJjhaRvz3+LvOI87DuyD6888QpemvhS0K8PJaLfxyJFFMIG9B2AnYt34q4Bd2HWxllY+6+1oiOFvMuWy5hePh0VtRWYlj0N66avQ3gYjxInClUhWaRefPFFjB07FpMnT4bN9svzXfbt24eBAwciKyuLg4kppCUbk/HuvHcRa4jFE/94gmdD+ZFTcWLZjmVYtmMZ7h92P16f9jr0snuTHYgoOAR0kbLZbLBa3TvT5udDi4cMGYL33nvvmp/z6KOPora2Fh999JGvohIFlMTYRGybtw19evXBU6VP4VDjIdGRNKmitgKF2wox/u7xKH2uFLJOFh2JiHxMlSLl+N9e2Kpfhu39l+A4sue6503diFpDiysrKzF27FjO06OQlBCdgK3ztsIYZcTTpU9zUblgm/dvxrIdy/BA2gN47ZnXoJMC+vkrEbnJ5+dIOb87CMfXO3vedxz+AIiIgjzoHrevpcbQ4hEjRqChoQEAkJeXh9GjR2P48OFuZ6PgpygK7B2AYlUgR0mQewX/omBjlBFb5m5BYkwiJq+ZjPrv6kVHIrjuTIWHhaMgvwBWuxWLNi/y+AkmEQUW3xep019d8zHl9NeAB0Wqmy+HFkdFRfV8PycnB/X19SxSGqXYAafF9Z+Z4wcl6ItUmC4M5X8rh6mvCVPKpuDgNwdFR6KfKa8pR3hYOBbmLMSp86dQupt3xIlCge9PNo+MvvZjvdyfsweoM7S4o6MD0dGujJ9++ilmzJjhUTYKfpLselMcgC48uEsUACyZuAQZKRmYWzEXnx3/THQc+g2lH5bi1oRbMf/B+Th86jA+PvKx6EhE5CWfFyk59c9QTn0JxXoFACDpIyEPyfboWmoMLd6+fTs2btyIsLAwjBo1CmPGjPEoGwU/SSdBb/yxSOmDu0jlj8zH1KypeLP2Tewy7xIdh35HwZYCpCalouS5EuSszMF3578THYmIvKDK0GLlagecpw4CTid0A4dDMsT5MLIYHFpMgeqO/negclEl6r+tx5MlT8LutIuORDcwIH4Aql+sRkt7C/JX5eOq9aroSESa5s3QYlW2j0i9oiGnZkG+PTskShRRoDJEGPDGjDfQ/kM7Xtj4AktUkDh98TRmV8zG4KTBWP74ctFxiMgL3IftKRrHAAAIn0lEQVRLFMQWPrgQpr4mzK6YjQudF0THITfUNdTh9T2v45HMR3Dv7feKjkNEHmKRIgpSQ01D8WzWs9i8fzPMJ8yi45AHynaX4UTLCbw66VVE6iNv/AAiCjgsUkRBSNbJKHqqCBc6LqB4V7HoOOShLnsXlmxdAlNfE+b9ZZ7oOETkARYpoiA0NWsq7hxwJ5ZuX4qOqx2i45AXPj/+ObZ9ug3Ts6fjzv53io5DRG4KySL1e0OLq6urkZmZiTFjxmDevJ+eAcbExCArKwtZWVk4fPiwvyMT/WHGKCPmPzgfNfU1HEQcIl7d+Sou/XAJSx9dKjoKEbkpoIuUGkOL7777btTV1WH//v1obW3FwYOu059TU1NRW1uL2tpaDB061GefA5GvTRs3DZH6SKzYuUJ0FPKRjisdKNtdhoyUDGSkZIiOQ0RuUK1IKVdboFw969U8KTWGFptMJoSFuc6DCg8Ph07n+i04efIk7rvvPsyaNQsWi8XjzERqiu0diyn3TUH1l9X45tw3ouOQD207sA2t37di7gNzRUchIjeoUqSUlo+gnPonlFPbgbO7PS5T3UOLJ06ciNLSUkyYMAEbNmzoGRHz67eWlha0t7f3jID5raHF3cxmM1pbW5GWlgYAOHbsGPbt24d+/fph7dq1nn3iRCqbmjUVhnAD1uxeIzoK+ViXrQvlNeUYPWQ0Rtw2QnQcIvqDfF6kFOslKN8f/en9zuNA13mvrjlq1CjMnDkTJpMJ69evhyzLPS/D/fwtMTHxhkOLAaCpqQkLFizApk2bej4WHx8PAJg4cSLq6+u9ykukhmhDNJ758zP48KsPcfzscdFxSAVb6rbgfMd5zHlgjugoRPQH+X7miST/xsc862tqDC3u7OzEpEmTsG7dOiQkJABwzfSLjIyELMuoq6vDoEGDPMpLpKbHMh9DdK9olO0uEx2FVGKxWbBx70YU5BcgpV8KCzNREPB5kZL00YAxHUqb64BAKfZPkCL6enQtNYYWl5SUoLGxEXPmuJ7xLV26FDExMZg2bRqioqIQGxuLt99+26O8RGrKz8jHV41foaG5QXQUUtGO/+zAoocWIX9kPoqreEYYUaBTZWgxACi2TgCKq1iFAA4tJpFSk1JR81INXn73Zbz9CYt+qHtr1ltITU7F6MLRXm3YIaI/JuCGFgOApO8TMiWKSLT8kfmwO+yo/rJadBTyg51f7ESyMRkZg3gUAvmW06bAcUWB4mBB95WAPkeKiABJkpA3Mg+fHP0EbZd/excqhZaa+hpctlxGfka+6CgUQhSnAvslBfZOBfbvRacJHSxSRAEu7dY09Ivrh11f7BIdhfzEYrNgz9d7cP+w+6HzcLMO0TWcQPcrxYqTd6R8hX9DiQLcyEEjAQB1DXWCk5A/1R2tQ4whBkOSh4iOQiFCCpMQFi1BF+n6lnyDRYoowI0cNBLHzx7HpR8uiY5CfmQ+6dr5nH5buuAkFErkXhL0MRJ04SxSvhK0RYqDiUkLdJIOw28bDvMJs+go5GfNbc1obmtG+iB1i5TiVLzaGago3j2eKNgFXZGyWq0cTEyaMThpMGIMMfjixBeio5AA5hPmnpd21eC4qsB6QYHtome7uBS7AtsFBdbzCpxdLFOkTUFTpI4cOYKFCxciOzsb1dXVHExMmtA9c413pLTJfNKMm2NvxoD4Aapc32kBoACKA3BaPXh8F6A4Xddw8J9U0ijVilRrayvOnTvn1S1fm82GDRs2YMKECSgtLcXDDz+M/fv3Q5ZlDiYmTbjlpltwpesKmtqaREchAY6dOQYAGHjTQFWur+sFQHJN9tKFe/D4iB8ngEmAHHnDn04UklQpUmfPnsXRo0fR0NCApibP/wPo7OzE+vXrYTKZMHPmTGRmZgIABxOTZiQbk3Gm7YzoGCRI9599//j+qlxfjpQQfpMEfbwESXZ/8bEUJkHf13UNXQQXL5M2qVKkrNaf7hH/eiG4O4xGI8xmM55//nlUVFRg3LhxKCkpQVpaGvbu3QsAbg0mdjgcAMDBxBQ0koxJvBulYS3tLXA4HUiKS1Lt15AkqWfsl4jHEwU7VYbH9e/fH1arFYqiwGQyeX29YcOGYc2aNbBYLKisrERKSgoHE5MmJMUl4ejpo6JjkCB2px3n2s8hyahekSIi76hSpGRZRkpKis+vGxkZiUmTJgEAiouvnYpeXl4OACgsLERhYeE1P969e48oGESERSAhJgFnLvGlPS07c+kMko3JomMQ0XUEza49Iq2J6R0DALjYeVFwEjFy03Nx4JUDaFzbiAOvHEBueq7oSEJc6LyAuN5xomMQ0XWockeKiLynl/UAAJvD83WGwSo3PRcrn1wJQ4QBgGux9conVwIAqsxVIqP5nd1h7/laIKLAwztSRAEqTHY9z7E77IKT+N/i3MU9JaqbIcKAxbmLBSUSx+F09HwtEFHgcatISdIvd+RphdVqBTelkL91n8GmxR1R11tcrdVF1wp4ajhRoHKrSPVJ7I2iVUWaKlNWqxVFq4rQJ7G36CikMd13orT4ss71zs7S4plaelmvybuSRMHCrfvFEekWvFb+dyxfthxOp1OtTAFFklwFMiLdAkB7dwZInC57FwAgUq+9I6OLq4p/sUYKAK50XUFx1bW7dUNdhD4CVrt2nrwSBRu3ipRskGAY24X3528HADz+2uOqhAo8XWCJIn9ru9wGq92KhNgE0VH8rntB+eLcxUgyJuFM2xkUVxVrbqE5ACTGJqKlvUV0DCK6Dq5gJApQiqKgpb0FyXHaPEOoylylanFSHD+uQfNgNIo/JcUl4dA3h0THIKLrYJEiCmDNbc1IjtdmkVKT06rA1u4qUvoYBOycOEOEAXFRcWhuaxYdhYiuQ+reGURERERE7uE5UkREREQeYpEiIiIi8hCLFBEREZGHWKSIiIiIPMQiRUREROQhFikiIiIiD/0f2JPx/csWcDwAAAAASUVORK5CYII=\n",
"text/plain": [
"<Figure size 748.8x489.6 with 1 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "YGtDnKSjdfPU",
"colab_type": "code",
"outputId": "d2ad66b4-dbbb-4223-9295-bf9e704666ca",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 401
}
},
"source": [
"import StatsbombPitch as sb\n",
"sb.sb_pitch(\"#195905\",\"#faf0e6\",\"vertical\",\"half\")\n",
"#plt.gca().invert_xaxis()\n",
"for i in range(len(sortxg)):\n",
" xe = sortxg.iloc[i]['location'][0]\n",
" ye = sortxg.iloc[i]['location'][1]\n",
" \n",
" if sortxg.iloc[i]['xG'] >= 0.75:\n",
" g = plt.scatter(ye,xe,color=\"#ee3e32\",edgecolors=\"none\",zorder=10,alpha=1,s = 40 )\n",
" elif sortxg.iloc[i]['xG'] < 0.75 and sortxg.iloc[i]['xG'] >=0.5:\n",
" o = plt.scatter(ye,xe,color=\"#f68838\",edgecolors=\"none\",zorder=8,alpha=0.75,s = 30 )\n",
" elif sortxg.iloc[i]['xG'] < 0.5 and sortxg.iloc[i]['xG'] >=0.25:\n",
" a = plt.scatter(ye,xe,color=\"#fbb021\",edgecolors=\"none\",zorder=6,alpha=0.5,s = 20 ) \n",
" else:\n",
" b = plt.scatter(ye,xe,color=\"black\",edgecolors=\"none\",zorder=4,alpha=0.25,s = 10 ) \n",
"plt.axis('off')\n",
"plt.legend((g,o,a,b),('>=0.75','>=0.5','>=0.25','<0.25'),scatterpoints=1,loc=3,title = 'xG Value',fontsize='small', fancybox=True,edgecolor = 'black',framealpha = 2\n",
" )\n",
"\n",
"\n",
"#ax = plt.subplot()\n",
"\n",
"#plt.savefig('MessiValverdeEraScatter.png')\n",
"plt.show()"
],
"execution_count": 0,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAlIAAAGACAYAAABmwYzKAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nOy9d7Rk113n+9l7n1C5br6duxVaoWUFK1mOQsYBe9kYjAHbzADG8HjrvSHNzGOxFgwMDDOwYHi8mfeI85Z5wDgDXgLb2MY2DnKQZFuWZFmh1epWd997+/aNleuEvff7Y1fVzbeDWupudD5rael2hROqTtX+1i98f8JaS0ZGRkZGRkZGxrkjL/YBZGRkZGRkZGRcrmRCKiMjIyMjIyPjPMmEVEZGRkZGRkbGeZIJqYyMjIyMjIyM8yQTUhkZGRkZGRkZ50kmpDIyMjIyMjIyzhNvuzt3vTs4BUy+QMeSkZGRkZGRkXFJMv2BWGx2+5kiUpmIysjIyMjIyMjYgiy1l5GRkZGRkZFxnmyb2svIyMhYzbte9S7edsfbLvZhPO/c++C9fPC+D17sw8jIyLgMyCJSGRkZZ83b7ngbh/YcutiH8bxyaM+hF4VYzMjIuDCI7Wbt7Xp3sOmd7/+F93Pjvhuft4PKuLTJ+TkAukn3Ih/Jvxwul9e0GBYBaEWti3wkzx+XyzleLtfM5UT2mr64efT4o/zYf/uxLe/fqtj8vFJ7V01eRTEsXvJfNBnPD0qqi30Ilz+rf6KIy+c11UZf7EN43rlczvFyuWYuJ7LX9MVLMSxy1eRV5/Xc8xJSx+aOcWzuGO/8w3ee104zLm8+9EsfAsje/+dAsmgxiVNT/pDgI7/yYeDyfk2vi3MUreThoE266e+2jAtJ9jm88GSv6YuX/nt/PmTF5hkZFwFVAtsA4QlE8MLs08SWtGERnsCrgBAXRu2MaY//Z2E/NyYFAOZkwr8dOc63wva2z/OtILCCljTntV9poWQldWHgHE+lYiRNYTCZ4MvIyHiOZMXmGRkXARkIglGJXxXbChoBVHyBfwE+qboJNgXTtdj4uW+vz68u7xqIKIBx4/OHi/vw7ebn5VvBry7v4mszh3hg5gb+Yu4K9qXnpiZ/qDXMZ09dx9dmbuCTs9dwT6d8Vs97VbfEP8we5GszN/D5U9fxo82Rc9rvxcJaizVb17NmZGRcPDIhlZFxiRJKeOeVRd57TZmfuabM7sJzq98Qfu//AsQFKgWRFu7pVjbcPmZ8bokLmzwDfr4+ybtbo+St+/q5My7xJ/MHEAZujPO8LCpuKcIA7uoW+a3lPUwad0L7dcgfLu7jiiTc9lj3pgH/98J+rkxdQfG48fn12m5e0z07EfZ8YGKLbm0vkqy2JAuWeN6iO89dTG23z8F9OhNtGRlnSyakMjIuUW4eDdiRd4onEHD3+PZC4Ux4ZYE/IvBHBcJ7bjmtkpT89Pgkv7/vAEJsvui2xeYpu7e3hjfcdkCHfPL0NXxo7mreN38ln525ltuizYXY29sbo0g+ku9vD217zG9pDxFs8pW32fG8EJjEkixb0qYlrW/zuBisBiyY59hMZtJV+6ytvc/qre/LyMjYmkxIZWRconi9lJ/VFt0B0QXdPr9IgbWuPsp0OOd6os34+R27uKdSZUcQbJma7K4TUqEVfH97iKLdPBy2T68IxTHr82fzB8htUsQUbBGtCs5wYuFWz9sm+vW8Ylnp3tymTEwGvQiiAJm/gPtcfymtui9LI2ZknD2ZkMrIuER5dCmmkRisAWMtX5uKsOn5bct0nAjTHYvexLXEGpfS0d0zL6DDSnFDvhctsqC2qNie0P7g7zHt8bHZg/zO0l78TQSP3bCqQx7Ff1zeveH2T+e3CJec4dC3et762/NSck+5yhurQwyr568dXgYCryxQeVf8vxVCCYIxSTAuULnnJvqkv/U+XRNC775qVoWfkXG2ZF17GRkXAZNYsG4x3YpGYvnrI00mQ8nigmWpY7ZdcLdFbvF3D91kUH8jBMhQECp4854CuwqKUx3NJ0506GpLbC2ptS5iJqBRNZRrazfaFJqHg5WuvZ9tTLBfb52aFFtEk169Sf3SPxZq/Ptawg7jr7n9Xa1R/rw8R01t7gP1eNDlt6tT/GJ9ByWrSDB8qLjIvYXlwWOGlOK39uxj1HPb/pGRMf7T1AmOxdGWx/5cUIUzCxZrLDbp1bht8XBrXQOB8JzwOt99qryA5xr1ysh4kZFFpDJeNFh78YtorbGkHU08b4gXDdGcwdQtXtpEbBJuijQcbxuaeYs/cv61TSon8Id6EYdNSo9WDzjo//2KiRwHSh6BFOwrerx60gmhljF8rr4iPqauTun4K7mpBMNvDU3RXmVrcOsWhednYlOBZWHCbPwNGCK5Kdl+Px8sLXLPjid41/jTvHbHE/zu0MwacfL66tBARAHkpOQHR0Z7xwLDgSR3BqFyIbHWkiy62qVkyW55Dac13GMWL/41npHxYiOLSGW8KOgvSDYFlQev8sKnLkzkFsN4oRf58aFSFLzrYJHJ2lewymcyJ5ntnp+v0pmQ4dbn7JVBS4GQDNJHpXWireiv/Puv5ud4stPh+nyBk3HEA+MNXtkpU7CSL+YazKu1onBKxVyXnHuo41P55Q23vToqI7cIzUypM/s6tKXhkaCz4fYhpXh5qcyw8qjrlH5ca0R5eAJ+6ECBXQWP1Fo+dbLD4frZ5VmttZg2IHsRn3PB9grNAZtAvGBAC1Rx3cNSd01Z4/67UF2ZFwKbWnTX1XptF4HNyLhcyYRUxosCqxnUF5nIckEqrs8RE7nC8f6uhYC7rgypSAkWhE545VjI353cuMg/3wgp8NZl0R5fTriq4iEQWCzfXU7W3H9/q8n9rSY5Ibi2mOeRoMNUsrmQeV9pntd0y/irguBdDLltguJfyNX5g+qpDbe/bYvuvKOqyzP++aXg9gYBv7F7HxOezw7fZ9z3OBpFJNbyYKvJoWGfXQX3dekJwffszHG43jyrbevm2iaBcxFT/ffFdAFlMV33XHcNg69rvOdgicI18J2ZhM9Nd5H+pSVWkmWL1aDbEIy5c8rI+JdEJqQyXhQI5SIyJrbIs6hLeT6QORBdV8wrcxa/IgkqEukBolebdAkl259upHzkaJudeVcjNdXeWHt0XS7Pv9+5m3zvwL9Yr/Hnc7MbHvftsM2Pjz/Dexrj7NI+D4QtZmTMr9bXFpOflgm/MPIs8ypl2ks2bAdAbdFl96Xc2Qmbzfj+oRHyUtIwmtkkYdT3KEnF+xfm+PjyIjeNrDUMfSHfJlVw6VhrIdXOwmBsSDHW/hbD0eNcUfZYigy37gs5JTVP1s6zI+GFIMs6ZvwLJBNSGS8KhBD4Q3AxIlF9ZCAIJ9bu/6FazMF9PsIDKxQPLFxAy/ELwHRbM72JgOrznvGJgYgCuLtS5b5mne92NkbVHgk6/NLo8TW3WQHvaY4zqX2+Fjb5verMGaNK/1hY5g3d6prbDJZPrCoax8JtcYFR43F/0NqyAL3PkLfyVbioUxZ1yv3NBu9fmAPg8eWYG0d8xkKFxfKV02cf+XJpOJc2lbmzftoGhBD4I25bP3xNkXw6h68bXFPxeGQpoZNait4lpMR7eFWB6fZtHLJoVMa/PDIhlZFxEanFlr862uRNb7qTVOY53vp/N31cvysLyQVL3UgBB3upu6frCel5RAv2BBs78fYG4aZCajM+WFrk44VlhozHSRVzNpZOn8nX+ePyLO9pjpO3kprQ/GH1FI8FHXwreE9jjPc2xyn1/Kq6GH5zeIq/L2yst+rzYKvJofzaQvWjaZufubZEXgkeXUr44JEWE3lFKzXUYosAvm9PnmsqHvXE8vETbeZW1beZuNeZGW5Mmz4XQgWV3sygRJYRQlBQgqXIcKS+eRTvYiJ9gfTP/LiMjMuVTEhlZFxkIg2xt7279qDORoA/fG5iajSUaAvL8coiL4C37y+wt+i+AqbbPh891uZcfRif6na4Jre2iPzJLURU2Uje2h5ml/Z5MGhxX9jgV+q7eEdrmADJcRXxH4emuD+3idHVOv6ocpq/LM2zSwccVxFd6Q78vy7u5XXrolU5JL+5tJsvhw2anuFN1WGuz+c5EUf8w9ISDaP5TG2ZQ7k8bx4aRlvL3y0tsmNMU+pFeG4ZCTjeTDnSWEmb3Tjsc13VKYShQPCG3Xnef8Qdu4lcpx24Qv6zsTk4WyINp7suwtb1xnhsKeaz0x2+s5RQTy7ACJnEopvOSkGVth9uba0FzXN2ys/IuJzJhFRGxkXGpK4Yd5v1asWI07KpC7YScNtYQMWXPFVLON5yC+2b9uQHi/035iO+POtSUiOhHIgogF0Fj/GcZLazfcegAO4slrgizPFUt8Ofnz7FL+3Yxe4gJDaGv11a2NRzaWfq89fzV7JTu1qj9zDOk16Ha9MVEbZPh/zJ4gHesPNJ5sXaOp+faIzxrtYoQ0bxxVyD36/OMK9SnpIrM1Oui3MbRFSfAMkrohJX7ipwV8mFh24qFLm5UORXTjzLj46M8eahYSJrqWvNa8oVjqiUGisRnsI6sZBf9W+TWELt7C2EFGuMU8/XRHU7/vZYm3/tHUDYlD/5bp25eK2A0h13TanCuRd362Yvmha7dLTYwv5rdSeszIGfmXhmvEjJhFRGxkUirVtM16IjQPcmdPQW4vWoEtAUznAx2HA3b9i9IphuGPL58FFnhtm/DeD2sZCHFmKaqaWrLcZaZH8MDe62M/G/TezgFeUVV9B/qi3zyyeeZdzzaGhN126+jZ9pjA9EVJ/VIqpPaCV/EO7np+IjA/uBH2+O8sv1nYPHvKUzxMEk5O0TT68pedufbj+LMFaWu4olSlJigLYx7AlC/o+du3jL0Agl6VKBZamZSmKKUZ5azgmpZmp4prFWET1VS7lt1OJbNw/v2ydjdMtFoGQeZCqc83tx/ZGcG1ZbTLy2xqjVMix51wIwM2/W2HmY2JLWe3YIWuBvri23ZGCdIIDtbBRWdcLa+OJ0wmZkXApkQioj4yKgI0N02iKUW/issWBdV+FmY0CkL5DbZP/2l1ZWPCkE+0qK483NC6ytsTS7ls/PdLl7Rw4h4MunImrx9kJqp++vEVEA31up8rGlBebSFZGhgDcNDXNjvshsEvP3y4vccg6GnBO+z0v9Et9ouS68dzfHNjzm2jTPHXGRB8OVNOCjQRuNRW2yoD/jdTlejjmYyw9mGHaM4WQccVdp7TlVlGIuFRypp3z2dJuCJzjSSGmtKyJbig3vP9Jkj69YXDQcq6WDFJ6Q5y5gNsPanhGndqm2YPQsnNCtRbfdc3wPzkXgWGMxvfyuVwG5XcpOgcwJbGQvaOoyI+NyIxNSGRkXgf68OxPRcxoXIN3t6jw6u+a7hr1FuebfpzqaJ2rJmtReo2vcwmzg21HMo0tnX5xc3mTunBSCklTUtBNtOSH4zT37uK1QGnS6v65aJVeXsHTmfWhhqY0ayksr+xrWm4dFqmbt7dNewvtKc/xMc2Jwm8XylbDJrw+f5J3D47SNodI7j7x0tp4dY1hKU0rBKjEKfK62zNPR9nm5WmKpJSnaWFRxc9f49YQK7hwLySnBI4vx9gas1hlsQs8LzVqEcDP3hHJRTFVa/xyBUPa8AkSmA7aXmbWxgG2uRSH6YjETURkvbjIhlZHxPGGNxUTOwXz9L3vpCVTJIqzAGwbR00DnW7T7jyc73LMzR9mXPFFLBmmofzzZ4YG5aFBsbhIXAesXr+f3ybNuST/S7bKQJmtGqJyMo4EJZyAE/2nPPl5bGSIvJQqIrGVn4FM7mGK+YZFbDDju0ylbOsrwULvJSCj5ye4ohU1cmzrCcH+40Tfq/6rO8qVcg+/pVvADwUNDbb6SNGgZw+4gYDqJ6VqPopR0jeULjToHciEvLeeJZEqAZD7W/NrJ4xyOuhu2vxXnEpH5wb0FJqRTQQf3erz/WIvaFkXiqw05ZX5d4bdyEqafCt5fVAyHimeXE07lzjzLcdP9eZv/nZGRsTXZRyUj43kirfWKdgUEo2s9dFQZRCARHkhPuoG0lk2HEqdNZ32giluPeWmllo+f2LxbbiFaiXjI0NXNWGGRvouI7RiR3LMzRyAF31qINziY99HA705P8a/GxrkiDDnc7fLX86cBeF25yi/t3MWeIMQXYlBa4/cW/uKQ4vAtXcamFEEkqCcpu1sbi72WVMrvzUwR+Jaf3FXhX903uWEcTIrl14ZO0pCbR3IeDtu8/sAwNxWK3ESZHzHj/P7MFN/tdNgdhCymKQ0JqYWH2i2mvAb75DiWkBoxf99Z4PHu1vYNI6EklILZrj5jl6Nu24EIUnlBIGEyUJieXZhnBDsKito6E00TWXQLghy8+WCeybxiuq3555kum5Wy3TIScM9OFz5Kd4R8RLWYbqQgXfTxbAvOZSjwhxnYNmx6Th2L6bhrSRWzaFRGRiakMjKeJ2x/lbWQNA2m7aILXkn20jPu7rimMV0XAVjfam5Ti271CofrEIyv3G+1Rbd7bepnOXZESEEwAWnddQkKH962r0C550v0ht055rua01ukm6aTmN+bmRr825dwZ7HI7+47QCgEgeiNGRbCpaGAxFqUEFSHPebLmo41fG5qiV84Mom3TiT9n2qax7sdXj0Zsn8pv6mLeV1qPlWobXmOdxRL3FRwFd4C2OX7/ObuvfzhqSn2hD6vHa4ghOWwaTJl21SFz/1mkRIe+0SBQ2GRca+9pu6rz51jAa+cdG/cVDvlb4+1NxU20BtQ3XB3ml5nW2wEdW0oC4m1YBUsrHutfQmthqtxeuWuHNdXfIQUjIaKdmr56iZmoC8ZXokSekJw146QRtEniSz3z0ZEpc2bGDbjTFGstOGiXSbpufVnJpsZL3IyIZVx2WFit8jI3PYeNxcbryxcLZRniKZBNw1doHi9xS+s1ON0jlpMaiEF3dWo3KraH+nSftZsTPul9d5rYS0mcXUzZ5PKUbmeQaKA0BMDEQUgEAyFcksh1SeU8AP73RDfe5hECdBYbE8YCZxLQ0drNJCTkmHlMaw87m81eH80z6nhmN9o7aIUe2jPwlWC/3zgCr6vXufjndN0gs2L5XM5ye/v3c+3Wk0eard5Yl30aFewEunaH4TkpWTCh5/fsZvvmBqftjMYa0mx3DUR8pXZiDurRe5R43hIOgr++/4y/+74MaZXzQ6UAl4+sdIZuLvgcVXZ46l1w4tHQ8n+ksdSpHlyMXGF4mrlWv3YiQ53T4YEUvDtUzHzvYhh0RP84P4C4znF6cmUDz7QZAiJTVc6NUfCzZ3L26sK4X0JL5sIOeVprIV9FY//OdXCChcdE+q5DQ+WnsAkrlHiBZ2Vk5FxiZIJqYzLCpP0jA4tqERsmgp7IdFdSzxnERKCMbEmHSIDgQzAGIHVLsWCBNMGVhclC/BsC89GBB6slg9CurEgNnXRozX0dmW6gHbpFn/47BbJfhQhNnCynbKnN5A30pbpngeVJ+C1u3LsLnjMtFM+N9Ml6emrO8bDwRBfJcFDkBhLhCVc1RUnpcBaeKzTJpQSCzS0JrKWTxZq7LpJ8xY7wdW5MkIJAmO5u1zFWvhnM8udpWFGm2tTgI29htdWhrinMsThbodvtJr8walpRj2Ptw+PckM+z7jn0TVmML6mZdw53RFWuY9Tg0J4Y2GqrYlqIUlZMuT5FBWMKZ/f2r2Xnz52ZLBfa9eOirPWEtXc9ehV3Gs6mZP8yJXFQWfgfWGH+6fjNe/dcmy4d5M07CsmQsZ7InqsqrjnYI5nOglXpj7WcxYIT04nm1pkfG66w1v2FRgJJbWuIbW96yWB0YIi3xXUmsZJ3d64pK1Sd2fCGwKbiE0jqBkZL0YyIZVxeWEYrGZ2+/FpmzJIh6m1BcL9bqit0G1nPKiKa1MZydJK6k34lnBik842Kcnt00QzoALwCmt/xt95R8Bu/VWEsPz49VU+9EyLzqp8kVBixdtnFV4ZtOe6/VjV2bUdoYTEsqa2595n27x0NCCQgseWE5q96MbLJ0JuGHIiZigI6Gr4wqlubzsrr8HDZpk9soAU4EmQCBo24Zk4oiI9xj2fQEraphd5kSsn84XZLj91II8QTnCZXrPZ9fk8/+WZhLeXjvALZpK7uxUKecncbs3wvsAVWfe2dWuxxG2FIv96bIJx3ykWA4Oi+LYxnIpdZClKoKEtpUDQ1Zb7egal0kiGpIe0oITAAAdzea7J5Xiq687ZAl+Y6XLPzhxSCI7Mpxw+nWAB3RF4Jbim6g9EFMANIwEPLqzUnAng9rGAiZziRCvlkVVdk+Gq60pIyBUkDz3bJfbb7Cx4HF9IeGoxxSv3ugOtQfTe+FpiB67qFV/wEwdLeL4AH2p1Q7Nt0G2LDAB/pRPwfBBya5POSxXdcj9kVPHcDUozMs5EJqQyLgomsdh+jcU5fLHJUKCKLkLjrW/7PgvShivkhV6KIxTojqtlEcriD4sNx2PilVoXq3vFuP3j8V2tkRUgtokE+SWFd7UFs7Gm5FUHCkjltj8USF4y7PPg/JmHFwvlFm+Vh7TJtkNxBfDmPXmuqfrExs2Fe7bnMxUbuH9u4/6GAknFF+wpesTGcqqzksJ6dCnmuiGfQArqKuIvmyd4fX6MglUU8WiRUvEl9Vgz5vmEQtCPwXy12Rhs5+lGyuFWxE0Fj9Venm1jaGpNpCz/YXiKQEzzpweuIpSSyVVCJekpgjtKpYGIAlhIU5ZsQmwt3qqhyg+2mrxvtkE1kDQTQ39qzoOtBu8eHSNYte2Ckuzyg4GQAnhkKeHpRkogBQs1PYhQ9Tvcmuu8pprruvFeMRFy57hTIddUfSzwyEKM6cJDsxFXlD28npD7TpSgivDYdMKjcewiQNJFgq6teuxpfh5hNa/dmePzMyvHWE8s9z7b5vbRgCSGLx7toK27TmQoEL54TsOTLzd015I2e59fc2H8vTIyVpMJqYwXHKst6ZLFWpDd/kT7s8crPYdflKuearWrtdJtl7OxKdiEjb+2xRZ/g7Mu8HuF5VqQ1q3ryNskuiWE2NQpWq9zAz+TwbhJLUJA6At25hXN1LKgtg8xXFv1uabnJxVIwRt35/nzJzfaBwDsKSgMkBjLKydDir0aKm0tnzjRoZ5YTncN//PpJtcN+bxlb56gojlZXMBimagPM0yABWJrOR5HPNFpE0jJA80mf7M4P9jX3iCgblIUzpMqtpa2Mfz1/ByRtVQDwVDgRtf83dIC7xodp2k0JaloGOekbq3lcLfLq8srK6QUoKTgv81M8YbyMDv8gEc7LT64MI9EULE+XRLiXkTnn+s1Osbg9TymEru5sSe4eqQ2FpUXAwHVn3348GLMZE5yVcVnOTb80/TaFN7u4toLYHdBUV/0ePUVIUoKnq2nHG6kzHY1i5HBxgKbGIQCryiQOYHfm+sneuHHm0cCDtcTTvRSstZYji2nPHk4xrQAH3KTAunLDXV2Vvc+h/+CZ+Wt/ihmmciM54NMSGW88FgG0QfX2fbCfbt5ZTC9Ytm0ATRdusOmvYJgf1Uar+AKvKXvakpsClZY0npvBIgv0A2BiVxESBX7c8fEpmNctuKfZ7q8V3hImzLTSXl0Kd4y1ag7bvxH3he886UFhn2FlfCF+S6PLG5trrnKaxJrLV7qbBVUca3oe+vePFdXnOAqeoKOtlgMiXGppwNlb7CfWmK5cyjk2pJPNSfxlUACTb+FrkuSRFLTKX80O7cmCtWnLBW/d2A/u0KPBgkhiu+2O/z21EmeirocrHi8eU8eKQTN1PDhZ5Z5vNPhZaUSdxXLjPo+Da358MI8X2jU+N7KEPvDEF/CRE5x3LZ4+V7FXx47xUzHiYwb8wX+98mdlJUiNob3L8zx2XoNJQRHoy57esXpqbXMpgnJFiNv+qwfHm0sfGqqC1Obe1DNdjS7Cytfu9dUfd66o8BITjLX1jzTTZnqOBEFTjSnjb6rudufEiB1rwGht/tgVRQ1XXYR3/i0RYYgtEDIjc0KJnGu6dgLP1j5UkKGAq8KaPe5zci40GRCKuMFR3g9k8GYs3KCvqD7lr3UYB2conOLk1cBhBNLgzReuhItk6HAKku84J5nEjeuw/ZSN6JXpyQ8Nq1n2o5nm5rp0mtQNuHDz/wFadeSLltsagnGQa7q1LI9rXRo1KdqFaaXbXv5SLitkHpiPuHWSsBQQWJjuP/ZCN2yCCVQvcVlMicHIgpgPKcwBoqhRAiItKK1KlU1LAUvqfrsLnpUQklkLM1EM1ISmGIDm1iOzbR5Zra96THdXiwxGbivoBRLSkrRlzzVM8J82Xg4mAVY8iQ3jwR8ebbLkajLBxbmyUtJZMxghvN/nj7BG6pDvHasSGoVkyLHD3t7OLS3xS8/fZKOMfzsxI6BQ3sgJT8+NsE3W02WtOa+ZoO7SislZy2teajdYkdesb+kWIwMh+tnP4HYGjuwteg3ANw3G2EsTOYVjcRwaCggl3NCZ6KsmNGGocC9376EG3eHiAnLo/MxumcFESWWh05E/HCv+H2uqzneSlf2mbj/rHaGsMEwCH9je51NGNQbmmT7sXqXO5uNXcrIuFBkQirjoqAKZzdO4/lC5t3iIYRYU6dlRa/aebNAWb/C2a5EcVRRoNsWf3RlbMf5+OpY4ZMKVzNjOm6gcb8gONy10qXVP24j3QLdf0zK1pETqy2NBctfLjY5MOrRtpZjJxPnur7Kg2pdeQ8nWinjoaDoeRhr6WrD7WMB37MzRzu1PDPX5ephn0CCEq7LL0AQSIG2FhEIDlZ8vndXjlNzHm8erhJZy0fnF4ms4e0jI4wInxhDp9ermFjLVWGOHxge4Y4gz7Lo8pRtYHvHV/EFb9yTp+pLDtcTvnhqxVOpZQwfW1qkWEr5mdzuwe1XegV+fGyCv1mcZ9jzXBRUuPdQCcGVYY5vtlv8j9OnqOmUm/JFZtOEjy7MM5wTvONAYSDo7pvtnlX92r6i4tVDOZSGr0x1OZykLoJp4cu9AvfRUHJoKGApNpRK7qvYWMvTjQQB/NCBAjsChYng5t0hH5xuuvdIwGePdfnF3O1IUj589C8G3ZT9HwpmweINCZQH/rDctA5R5kBGAmvseX0WTerMLs7XjYrKKGwAACAASURBVH89umXRXTdrMjP6zLicyIRUxosS6YtNB8BKr5fGSzamAYRadV+vWNcJwvMQTr2U0aadgr7BdCxWgl0XSOgf95Mm5ZBOuWs0R94XfGp6aydurPuvqy1PLiT4o8KN9stBaAWBhUg4B/RvzEfcPuaKxB5bTnjz3jztXh3NSKh4zY4cT9dTSlhec00FX4KnXAfcUlc7/yhh3MJtITJwyCvyE3tHBp1+t5dK1GJDYi2pgaLywMKySfnkwjK/tmsPgZSoFK71KvhIPt9Z5NHFiHdcUWAs9NAWbh0Nme8aHlvnxG46PrrqxJ22UI8NLy0U+fPTp1iOUir9kKHnBNWx2AmbrrX81fwcMDfY1g/tLHDdkI+xTlheWz1zI0Ag4a37CqjYdVF+35V55p5tUV8ndvuvN2MhkbYcbaZ8eqrDiZbmFRMB37MjR0dbTrY0YwXFjiWPk23txsYMQxyMgmQgovp4JYFNBXoWjGbLb3kh+40T53796q4lrbnXz6+ev5VCH2tWCsLTpnXjcM6iCWUzK4iMjBeaTEhlZKxDBgK2qHHa7r6zxSQudYd1njwbfJ+0xBvR6Bi84ubRBG3hVNcwl7jHXV3xuWVE8+3FjYu88Fzqsp9KFULglSR3jgW8al+IygsemI/56umIL89GfHMhxlp47c4c3dQSKoEQkFeCdupWbWuc0WNsoJO6BfWrJyI+c6zNu24qcfWQTyOxHGukXGcqhFI4vykhqEpFBZhNUp7udhn1PGIsv3XyJKM9qwRw3YQzbQ024BvzEb992zC3joZE2vDN+Zi5ruHlpTI7jOYbreZgcPLxbsxMR5OTgkkv4GAYsOyl3Fwo8qfHT/Fze3aSV5LUwEeW51nYxMEcoOQJbhsLGAmd8HJzDFtnfH/zykXlbOBSwJ4UDBUl9dZGb4rVr3ff8uKaqscrJnJUA8mwEHhC8HQ9oZGuGvXjb964MHjPpcCr9sT6Ju7wfQbpR3VuYqifYh44nD9HOwTXjehqDPvdiWcirVt0x9WB+UOZmMq4eGRCKiPjBWZESMpVwXRDE3Vx3j6rEAJkIJHB2tEvJrZrUoc78mrQvg+wq6D49uLG/RU8wc4Jj8WWZnZO4/lwywGPt+zLU2s6I887hgIeX4pZSuzAJTuxLkqyyyiUEJxqJ5zqaMA5o9diQxHoGohT+PJ0ly/UIp56SDPiS/BhrmP4xYkq1xeg4EmUFeS0R6AgEM5bqmFS5k3E43GTO9Ta3nQLdLThp64psb/k0dGGku9SYv5claQkaecsP6bH+Z3pkxyOutzfavL6boc3DQ1TVM4ENEoNP79jF//m6SP8u6eOcMdokadsxMl4rYiy1tlyCAVjJY/5rqHia4ZCSWIsQ77gZ68tcbKl+fRUZ5AO9SXsLXp0Usupjmamk7Iz76FCqCeG2c7WBl/tdTnVnXmFtvBULeWKsocv4DMnOtTiM7RzstaqQ3gglVwTWTWJ6/hEOTGk266OCpyZq1Auiib87c02Vd6ZcuqWRQt3XZ7tmKKt8IfFQEidCWudiAJnZ3Iu8wQzMi40mZDKuGRZXctyuWMii+7CjTt93rAvh2kK2rHhI6earDchUGUXRVo9yiNtOuNPIcAfcfef6mj2Flc+wtPtlcXaxIZoDoZ8wbtuL1IuSnQEn07b3DQRcPWkzw3DAaeU5vCpBBGDaACr/IW+fjpiT8GjUXWRp/c91aCRWA5WfHwJV1Z9Kp5AaDi8GPPobAIWTpxMOW5d2tMrCz66sMCrhpzpl288NBaNRQETvs+E8NitFH91615+/pEZFtJkYKbpC2jl21xb9RnPK2qxoREbxtI8oefTEZaKD6e78I6RUX5nZorEWt63MMObxiokwpIKQzGEIBW8arTEq24TjOcVjY7PHz/c4EiaDhbhtA6m65zq54OUyFiONFJoOIEzknN+VwdLgoViwFfmIvJFwY9eWWQ0kCDgwbmYvzvW5iUVHxEJHl2Oic8iYmN71un9DsPl2PDNmYhHpmMePhrjjwiEJzCpG2iMZkNUSrdcwwSAV5Vriqx1y6XPTOT25YZWC2TOpcds6jr9TAyqLAjH137udNc9V+XddelVXMQNC7ppn7OQEnJtt6tNLWkLpLdxOHK/ttF0rfPGykRUxkUkE1IZlyS669r8B8LhMh6Maq0lqblF8tZy4NrRlaWYF7ykGvL1hkvHHdpziA/90oc230bKwL1ceLjWMmuoxM8Q6DqRN8LL/P2DfngTuYWoGj/FkD02mIn2I6/uDSuWlnx6mhvSJrffeICOv4NX5l6KWJ/esQZlY7QI+N27Jb5uUEhPUUim8XSLnF5CmITKvp3su/uNbi5gX8+JlbE28dLDiLmHEfNLWOUh8Qg7HaRNsJ4kF3gcIs9H3vFylnPXEiy3qHSeRea7XJdrkYocxfQU4ybFSB8WfWRiKSPQwmeiqrhq/wQ3v/MdAOSjk1Qf/ShCuxetjKAyNMmv3fVKqhwZNBO86qZdHK3+wKDTcnUnm/AhMMuU42NYJIFp4Otm/2XhzWonC+FNFJlmtPOoK/wX8A4pOFl+HVbLje/Zmte2957KVe+xdY8tpifJp6dJbJGXe1fzvwg12Eb/GA/tO8Rjx79LPGeQJfDyEpR1QtATyHXf7ibtDcFu9/yjQoEqWjfKKCdAWdKeqrc1Szi++jJwn0cs2Lg3PFuujmBd+M9n2nARNoN7L9anwP2qwJazSFTGxScTUhmXJKbLwG/KxAxa9C8FrLXOHd30PKPO4otcCHcuqe11BfYET9+n6N4H73Xb1jgbBcmaaIOQPe+tfuegcTfWw6tXHZghlzqzy7YdBQS2/xHviwNSSuk0UhhiUabp7eJ0cBuRN8xY+jC5eJFYlWl6uxmKjiCEpu4fIDANiskUheQUHW+MQNeRaDreBACxGnMLfb/j0YIQhmr3CMKmLFauxeY9Jsy38ZttNDk8GWGtwPa6voRNKbWmsFLhyxbJSBmlBPloloA6kaySegViVSFfmidfrwMGZSMMPjIfUYqOkagSgamTDAcE830/J0FjaDciiCHSSKMxQqFstNZvtScM+q9zrIZYyN8CQDE+yYh+DGucQ3Yr2OEsM1jlym7pxdo2uSbMqvcPJ5wKyTRDyVMgBEvetXS8HVgDrWAPrWAPmFXH0xdiAsJ0kcXv/hnzTz7MLfmAB09GyCsMWFdrhLRYI9YchSqAjQUisE5kGYFXFAMD2f4gcJtY1Camt/1ruL9RIQXCd1EpETwPfnCrznerTWciKuNSIBNSGZckMucElJAba4jOF912X/r91ESffqpEeM49evD4jh2IuNWPTxuWeNYJKX8Ygontv8yFcN1R8ZLlcye6vGOoSC4UTLc0j7RiQPDB+z7IB774AeL5geIhnNjo/QNuvl/aMFgjCHeCCiUC+IH9BQ702uiP1GP+5tttygG8+yVlbh4LkAZaiSEfSnZWPExq+dNv1vnM0Q9w99U5Xr4v19u1ZY/vcXQ5RSjYPayoJ5ZKIDlQ8liODE/XE+4cD0m0QQrBJ092+PSUcz1/zY6Qki+5azxE9I7nZDPh5x6tUVUe7x2f5NZiiVER0DApVQSeBF/B9OwCo88uYQxoY3lc1ji4y5BXgoXoJF861eV01zAWKl5VrLJHF0m14LToMLVwmM7cfTzT0PgSbhoJKHqKXBrwzeUOv/61+3nNaMB/uGmIobzCWMu9Rx/htx//2Kavc9UXdI0lWlXetN9XjFrJiVrCibohGBdIT/DGiRzXFHy0tfzTQofDzf+xxkdKt1Zq3PwRJ75zNct7byojhUDlIO5Y/uyhBnHBRYn6IkF33XZUvjdaKbb8m9uq5ENBUrPcc1WOk/WUZUwvotVXamvPR/qCYNwVodvUiR+hVlLnQglyu13t0/ri8X6noI1XCstt2js/iXNQ38ZC4XzS9F4ZjO/c49cbn2ZkXEpkQirjkkTl3Jf5haqPsumqeXkJBGOrBFPdLVDgZufJQLgxNvXe4/upjP624pX0lYkZuJCbpCe8wo3eOv1I0/Sy5o8faJAvCjpJr827/9C+N1TqFg4T9ZzS17WCp21DsuxmA6Y1gZqA8ZwciCiAqyoBr7zWcNdEyHVVn5wUfOd0zJ0TIYdrMSemU9LYcnLeFdRUyyuizUNQ7B9/z9E80BD1usoC5cw7hwNBznPeV6/akaPoS5YjzY6CR8GDV0yGzHU1kYZbRkP+7JVjbiiwjLlvboZCGvAShpmpwVhekpbbTEYlJAKDRRs4JIcwZpFTkaatLddXfb610AILf7Q4h+I0b91XpBpKqgj2hwELUZdOaskpQS1JmTIJsyS9wIZgpqkxFqIU9hV99oeKZ1epJSngbfucKNXW8umpDk/W3Ot0tJPy1OKKG7iNQceWT812+AIdri+5gcS11I3R6fszpTWz5jpAQnVU4fWEglCCoASVccHsrCXVFq/sflD0U2rxnMWklkJeElgGQ3htLBjdI6kbEGWLlmLbLjwZCNLYki64FJ9XsaiicHVHvUHHmz7PE2tXjLNM7Q2663yBN7z9cPDVCHlxveYyMs6WTEhlXLKc6QvXakta6408qYrt54UJJ1icYFr3OAUkbEifCNkzvOzdpjuu4BtAlcBq9ytdCGdq2J8faDorQi2tWxeJCBikvdLI0ugNTlZGDIYvm8idE0ogCoZk2W1DJs6/auXE7aCguF87FirBaCjpaEuzZTDa8rLhEE84UZT3JKM5yXxLU9CS062UVmSZ04brx32WE0NeuZElgRScaqRurIgP3cRyVVFhpSAxhlpkGAolbQ15353WnqKikSgKyqeRGPaVPEqeoOu5fNBwKImNIZSSgie4ouzx6FLEZ+wMD8xrXr5Lsb+bY1KUMLiOwFrbsr8QIE4PU/IjbKFFNS+4rupClAWZ0qiDjg2RhGrohizfPhZyeDkmlIIn2inzLYMSkOta2ssGoQStxGKw7CwrfuPWKkN5RT023DfT5evHu+xOJGnDjdD53p15nqw1sNZyY9XnrTfniQzcdzLivqdd6lBZeM3OPNeNBOQ8+MnrSjxVT/nOUsKnpzrIohPsMr8ishe0YRHDWM9pfbZjWGzbFZHeZSC0rQW0EyHtjuHwdMLBXQFYaAeGGWEH14NXWXt5m6g3lNvrpeI6oNuAcJFYawArkKGLGp1t9EdI5/xv9eaddta4z2c87wSlAdDieVt1Vp+nV8nSfhkvHJmQynjBMJFFd1xq4Ll2+ADozkokybRBVrZ+rFACWbToBUBZdNsOjDTXpBD69TqbpDJ0a2WRCyflhgXHrvvDpist2roOMrCurdxzC5kYFIa710W33SKPdqmStGkHEbLVFIuKN70iZCiUHCNlJjZ8/74COSW4quzxRBTzsWc63LU7hx8IGokl74FE8NRCwqMnYua1Zqqu+aGXFKkU3blUfMlcR9PsWGqx4Vic0mgaZOKz3DDcsStgrOjRTVMMlki7qJGSMBJK7hgNMRbKgeSZRspcV1PwJO1U000MO3IKYyFQgrJwqS4vgLsmFaERVHKGWkujtWChZbgqn0NaQZzCEHnyHcl34yWuKnvsKynG9+U5uqQZKwq6BvaWPLCWiZxkZDLHcmy4Mu8TNROOziUszGpOllIqgWCsqCj5glZiqOQknhTkENw9niOaN84SILIIXwxSywekxy/fWCVUAuvBqK+Ynk94ZlljE8sVoYduW67c41PxJWM5xXVVON3RfH0xAmEhhiFP0O0ZpH7kmRaHhgOshceWY+hdH1b3RZRLC5vYjQrSLYsVgnuPtzh0OsG3kqd1QlzdWgDplvMerUjBct2SRhbTtohe5FR47kdCUncmm0JBMCrxh8UZmzyEdONtNsNEvXSm7z6rwdj23lfPFd1yr5vVFhO7dGlGxgtBJqQyXhBWd66Znjh5rr8YZdD7ZW05qyHBArGqvmPV7VukENanMoTvUn7Oy2ndtqXAr7rFo+963k99mKTf8eRazFXFIj2JqroC4GTB+eC457rt21ggfXe7Kq2Nor3phjxXF3xQcIUXsBhpAimYamum2ynHF1MenInRSvD6So6jzZT5ruahxYjHZ1Mem4+RoeBlVwZUhyT9kuQdBcVDp2LX0g6cWEqZizUvKQT40jKeVygpGA4l2lpONBKW2ppyKNhRUCy0LEo640qwfH0uoegJ4sRwqBKwr+rhCVhsaaYWNPc/0+XmfQGBlbSxPDwb86Vollf4o+z0AgQwG8VUPIiNxesGTFYVIgf7Kx4S6CTu2tpfVeSUwCKwqaEZWb46G3FFTrEjL7n3eMyNOwL+11srdI3rBOsYi1SCkhREqTt2TwmaXUNLw2RVYQ189bQzWrptLCBQzlh0oqAYy0k6Ly3zp99pML2cstQyjOcVQU8gd3v+UEXfve++hB+5vsiecY/AExxvphxtpnxrIV4z4iUYFWuGVgvPjXpRBVffJIQgWTZ8+2TsIkh5Qa4ot0zJTVQkb99foBhIljua93+9Rd03qIrFK7jOQmssyWLPrRywicZqhT+yUaDZ1IkuIcErby22pO+iaSrvxtZ4mxSwX0hEACS9usotXouMjOeDTEhlvCAIIRDSRXTENl042zEI3Ss3zV0GgmCUtQW22yDzLk2GBRE6TxwRnH0dllcBW+jN09tsdlnohJq1lmTZYhOLLIFtuYVKt/oePhBOugVGSAHSFa57JYGquIUrWbRI4X7trz+3HSVvzeKWX7WQWQRx6AqavxPHzDytKSjnOdX3fQzGes7hOHFZDQRXVXzKnmBv2ePZxZQodf5JbWVYTg2VUBF4blZcfz9/+e0GGCcsfvkVVawRpBYiYyl4grt3hMx1NLFWWOBkPSX0BE+eTnh8LuHp+ZSDe3325CX7y+6r6G+mWvzcs8/wEztHePfIBJWSO8ZOYkmNxWIpeM4cUyGo5CSpsZhBM6Sg5EnqscaTbuBys6159dU59g154AtU4Fr3a7FBSUFOuWuyrS0LXc130oTvHk/YVVHEBUFNuZPueu7+gyO+E1ypJZZw9xV5PvKdFvc+2eaNV+cZqkuGpWQ5NqTW8mQtQZUFN5YCdg97jOclr9uVJ1SCE62UT5zs8KdP9G0VXDrMpAYVuplzq4XKYMZjXuAPC9K2hRSShsEmGx8P8Jorc5R6w6orSnLXnoDPHO+gfDVorrAaktCJd2NAx86jKV0Gf2ztZySeNyTLvZSjgWBk88+P8AT+qLvet027XyC8Uq+uUnJZ26VkXH5kQirjBcMfFi4adQ7iZTXO/2Zt6P5cvjCFdLVGutsr1qZvGnmWzxdi4IsEvRqtZu9Xd7+FPLVEs4Z4yRULe1IifYk3ZNBNkP3OeCsGdSX+UO918QEFuglIUDlXdL/+tTrRSrlhaCUE97mZDreP5diRVyzHhi/NRgOhtRgZNjE7B9wsvStKHu+8sogFvrUQE0jBE62Y+0/H1KWLon1kpsXb9hZY7jpX8Ymc5IH5mEAJ7tqTB2M5UdPsKXsoBdPtlJwnyCnJZF4w3UrR0lINFb4U3LAjoKUtPzZc4lSiuXrUQxjBQldzoOAzkU8oDscsi5hxAgqeIDWWw2mDudMxB3s1XftLztxzPtaEWiDzCl+6zsST7ZShQNI1lhPtFBkKxiqSx1spw5FkPKdop5bHazHaWB5ZjKkECiHgxj05lq3lVNsgpR1E7L4yHzFZUpQLkmJq+NZCTGpdcboqQVtY/u50m79vd7iy6jMSSp5tpsxHBpUTBFV3/bx0JKDgO8f1kZzidbvy/MVTTSLjorUmdtdVal2NlgxdF9/qiI4MBcG4RHVc+lg3QNcs/pDzXQMG16YAsM7cVAiB8l09oSquRDqFEuT3S/wxgYkMuiNcSnkTM3U7ENNsev9qhBLn85vpvMm6+zIuBpmQynjBEEo8Jz8oGayyRDjHK9dqV4fU797THfDKFpue/xevbrlf7dCvNbHEC5Zk2WAiF53xh8Ergk0VdqzXdu67epHVbef910V3XP0WgJFA23lWqTKonIskfW66SyOxVH3BkUbK4brmcL2Fv8kA2/X4Em4dDcgryXdOR/zDk22urnjYwXJneTbS1MXKChlpyEnBPx1psyfvIQR8eqbNjRMhQjlLiWOzKR94qMFizvILt1TZU/ToaosUkAKxhrl6ijaWkZziigmPcldydz5Hkrpo01RTIxUMBy7deJ+ZZ78tMC587m82+Wa7xTfmI95ry1w/5PPoUsI35iM+ebLDf7ltiFdO5oi04Ylawj9NdTnWTLh7Rx7jARq+PRej8oKTbY0U0Ogaktjy35+s09bwkwdLBFJQLEkmrinyvqeaa0bw1BLLXxxucd+piJ++tsRYTnGsmfL101FvfuHKtXS0mXJ0nWX9Y6djXuJ7sMMJlMj0rh0Gvp0uHdYzNZWBq8vDuk5T6a/txJOB6KWBQWvX0OA8rlzDQ//a/NqJiFtvCThY8Eliy4nlFBWIQaTTJC5SKkPwyxLK0hlhdl2aer2QD8YkUllQ5zfjTnd6KeuzHEyckXGpkwmpjMsGVezVOMlz/wJOa27B0A0QeTcSI61bhDRYLTdEtkxvrtmGgcKrWV1kKyzJslu8dFcgA9dJ6JVc+k6VLOmywFrjUhA9iwWT9CJ0si+qVjZpY4hqLh2qOoLcrl5XoIGvznY3LHCrRVROCa4sOzHzTGOlIOytewvsL3lYY7ku8PirR5s8NpVwaLeLcNUTw/FNhut2tSXWgmXh3OZPnUwZ3qUoVJSzgEjhYClgco9iV17hazjd0ORDwemO5onlhL0lDyUE+8uCUEmqviJUgrbUBDlJquCTJzs8WU+4eTRgPKc4alt8aTnlb461B8dy7/E2Dy8qCgbCQHJVyeOJWkrBixkOJO3U8NnpDgcrPrsKiqoS1NuGKLV0rCXShm/PumHPAHs8j9PKEEhBxRfsLCgaiaXkSxajtcq05AlevzvPXGQoKEEtNpxsb3y9Bu/hqve43YH/79EmWMs7DpWo5iWxttx7vL3y3vU6R53IgDRyEUpV6nVzAm/YnePaqk8zsXz8RJtZoV1XXORGrEhfDK5fgNlIU0ssjzcTGnXDxIjiqhHFcWuwuAHa1riGDX9sxWHdq2xV+yTO6J22Ff2JBe4fGzsMMzIuRzIhlfGCYNNeGky5NMj5+kOdTS3Upvvv5SNEDqQUEPTTdMKZHRZXHqs7K1/2XmVth2E8Z9Bt8Ed7878EKzPxGs4XSuYtXs7VN0Uzzs5a+M4DyHXtuWLiZMmJJBO5FJoq9bulelGFxEJt5bhMYkkbgN2Ykgykm6tXi1wN2b99SZmryj6psXziRIe/P9FBAPtKCpMakiUQKewuSD7xTIdnrSZQcLiW0tUb8zWfP9XlV2+ssCNww4+vLgd84oE2b7+zSDkvWWprJoYUSgnuPx5x84jPs8ua41HKvDBcXfUZzznh1NWWTmLI+5IiMJn3SI1lf0lw/+kusYGPHm3x9gMFdhXcIOBQQqtmuX0s4Hv25biy4HHzSMBsQ///7L15rGzZdd73W3ufc2q6831TzzPVpDiJFEVRIi1aoibLsRXHJhwYEOA/DMRAgARJ/hACBAgCGAjyR5ABUYwYtqLIFkBTkjXalmRRkilRtjiJ7JFs9vRe9xvvfOvWcM7Ze+WPtU9V3ekN3a+7RaoWRPXt27eqTp2zq/Z31vet70Ny83f61t4UMK6Xwsc6LS5t1YRFz/ff0+LaQUAdZB4+//p45oLD1RuB4kH44QfaeIRalR+/t80vvXBAnsN6y0xJ7+3aewgR9qOy1vK0PIdMO2fXXHONP/5Qi8cfzbm2Gfjnzx7w9WHN42sZL+7VfG2rml7jBEpdIcQaM88szUHfZcJ3r+a8e9n45eXC8WP3dfjnLx7ge3JoDWe9RstnXawqKntBCclZX0dCFfQYkAmDmChBW1++a9YeNLTj2LSGsxl+zWem6WDdaiI31jHR9G5CiZ9WqjrJFPxOyNyc13dmzYHUvN6WqvsJMGDTb2/3aHK+LEbn5UaRGVjCgNCRib/ZiT6d2SDDKFJuJtrtKrTvE3NEB2Q1aZ3GYhEvXqi2Y3J0TnEyWUq3b2F0TXruckNxHSUMhWwx4gprdbkCOGd+QtkSM4ZCh49xORf+zsNdurVjVCmXy5oPrBYTp8+/9XCX37w0RLEg3F5fWCscK0uOp7c931wKPL873cxPqkqVi8PIpWFJPVIurGX4Av7vP9+ju+54vJPz18530BoCyp+9VvK//fEuckb4b39wmajw7I6ZYm6XgdXCU3j49MM9QjRzzO1h5BMXOrzy4gGPLeVc6GRENW8rauVXrwz4wFpBLOHRCxkOoZs5DqrIQ4sZV4bWYhqFyOiGEs+YQer6eSH3gvMQk05IM2sobg4jX79RMhgoB4PIYGT5NnujyMdXW3x274C/9/4F1pY9ZVQ+f3WEMtVN9cvIwa4NFkhu05+TbqnaIN1//t4eH73QZiMGLvQy8iXhd14f8bW9Kq0xy79zxQy1FyHrQqwEaTOx6mhrmlQFfNtE/ar2eAFcd0aQ3jZT1/Fu5I++MeQT97cRJ1zaq3lxv4JMiEMhW7E1Fkul2kyRTIn2bqb5YpXc1buCVoeBlGoyu1Ws+3aTiVzJIOzbccUiEkf+VLpfVam37QbCtY54qd2kwjB1cbunH8e85nU3aw6k5vW21ISykuPWAXerVG3KSGvLCpu9M5bscAfHd6b+QEdpPd81s02EQ7YIjTg8VhHnxLRM9n+2uXQFUHRPiAPrvMUDsXzcPJl4jo1CqQO4nlJv2GMIYgBrhi40SwWB5en78x3LRPML07/78JkW3WDgcKklfPKJnmmUorI5itzb9fzX373ITqn80ZURnz7X4b3rBdf2an783V06247fvTLToTmhRrVSDZW2wPvP5fTOO/Zi5DNXD6hy4WIV2O1HlloOVwjPD0tYF7JlYVQpHWcAIZTw718Y8si5ggvLnhf3KrwKdVCiQD9xd7YKlwAAIABJREFUXOutw+ZEZ7oeBIZVZMU5KoxijJiVwVObJVeHAUX5w4tDvnWp5Nq9bc4te7bGkYMQiWIA9Nntkn/69D6LPc/GKNC886v7NdvDKZV3UEa+/0LB4wsZUsBKK+N71gte2q/YGUeujyK/99yQass6LNmSgrrJOhMn/Kfv6/LRs20u9DznxPPUTsmZ9uEPwIR2HtoEXL6ewHhm9O/sGn3+es2HFpRWZuvgqd2KcMDEKDaTqZWH1mY5okH5wvUxz1+uyMfCDVdPRODijapzuQF6aQEhWS707Hw1WX+Tm4qj1h+zE7mOm07kTn3Z0k3FCd8FGjVpIXVixRFLo7Vv1ZWK45lEgmCWJPOa11tdcyA1r7taqqZD0mBGlw0V5xesE9V8cb/ZiuN0F15M8/G0mmqbwkBvSTGcNvEn/vjdr0XGAESiGt4JY9NauRwks40kDJIQPgO/6GAFs1vILUQ2JGoujswQ1HWgOC8QhNYFwWWnuBueUqq2UcZglM0jywag9saRxdxxpiVcGRq9uFIIP/NEj7WWZ7Er3LPa4togcGbB88XNiu0ZZbXWekiLNhwr//aFAf/lh5boOselcc2ZC56PFx3+4MqIwTDy//5pnyfO5IQOvFIEijWHqvIbTx/wU4+aYejXb5Q8e6Pmua2a4ozjz7fG/FfvXmIhczy9U/LrF4cAXNyv+dBaYTQscHEYyFeFf7cx4qdXu3z5xpgPrkId4WJV838+u8d+3XQNI7EFv/T0Hu99vI2rhHffKPnIWsHOfuTnv95np1Tefc7zqXvb7JaB3/3GgM88e8B7zhY8uZ6zr8o/eWafTz+8wOOrOb220Gs5XunXDGsYBvjlVwboWLlnwbNbR4YojyxlfPyRNkGVz18d89Baxp5GLjiPw8xKL24eB60a0qKiscQ4eY3uucj/9+w+jyznDNrKq8Ob67M0ajLNVK5fCYiY9ilLNxqz4nXfFeiDXzN7ERGz5nCFdaGy8/Z5PprDB7c/keta5j0VCshXSBEzeuh91juJ1lYsDLkWXPf49Oqc9pvXX5SaA6l53dWKIyZu3nV/CkhE7i6dV+8nl/GZbDvLLGsmnm7vizWM1LpJM9EdJ/7dADMs3BcUhRY4Lza1JFDtGCXUdLm0UrQUskXTYNW7TAKYY2ndLddOMSCZI1uVWx5zHDe0hRIGQr6uxIHwhZ0RDzzmWeo6fEt4eb/mhY2a8z1Pqcr1MAVIDy1kXBsGFto5XoV2JoSh8ulHury0X/P1rZLXbwTCoAnYNTAlHp7drvj9V4c8tJhPTEkbDyuXC+M88tR2SRbAFc5G79vKq7uBn/vKPqKg3kbumw386e2af/CFLRzTybVMlXO14/pmoPbKy1XgyxslLhe2UP7ZCwfUW0qoFAf45typ5ceFfcG3QBccYQEeWcx4fRD49Zd2GG+bsPrJ+3M+cd4W5Lp3/MQ9XX7p0gH//ee2EYTsjPDwomfklFFUFkVoeeHybk2slY4X2l749Id6rHpHqK3b98lHOmQJ/P30Q57dMkIO39yrWGk5/vD6iM9fOwKkXJqaaxuA0phuEsSoug+sF1xoeS5u1TwzqBgtCc9pDYY5TRsl1mFyiSbTsVLtJgrYqXUwPcShWCSMQGyCixsqsCsTCrGpxlldg61xHSl5dtzN/HYncsXLJD4pjnVClecr08+sBp1oKl1HyXong7d6x26cZjP8XMsE7A21N695vR01B1LzuqslE58kTszfunuvk1zGHdO795T91dAityqtZ52cZeK/c/Lr2fO6vAkqNrpOCrNBaPx0zCzUJvhCP22QzQYRk8tzV6n2bCPwS/bcYR9CP+IX5dROWnNuQ986XNUOoMr2CP7Jf9jl7GLG3/twj7/yaIeyhqdvlPzGpQGfeqxL4YRYK69cr9iulK3lyErm2BhFui3hEcnoZo53Lef80xt7bB4YwCSDYkUm5/aZUcmDyxmCUFfKzrjmg2sFL+9XbFakTVoPUU3ZIjzeyVjoOV7sl2xfV+JIiW34nuUef3ftLGfyjK8eHPALG9f55ErBw0Vm77cQ/mh7TLWnhJF1GbNFQVM+Yh0UGSsf6Lb4xD1tlh4Tnr1W8e9eHPF972/xEw922B5Hygi9zPH79YB6R1lzbuIergHOLHikgGpP8V0lbgi7Y2F8Ab62UbI6Et61kJOrsCKO370x5H2rOesd46ZcIfzo4x1Up9eu7YXfujTkw2daXPOOr18qeWbnuBZN66kGSmsDzNVOxDv49BMLfO89LW7sBb6rlcMInhlWh2lrEUSUajfS3XH87Q92Od91XNkIfParBwyziOsKruXIFhJlNgKS1mtWpH5aVTtKeWMK4jsPujfdBYolk89N080C65iVG+CKSBwY7Us8EhyuOuk+W/eqMcy6O/FT85rXndQcSM3rrpYr7A6WeFzEfTcrW07dr9TtyZaMHpilRW5WWpv7eDjQdBd/8y9f37WR72oLVM0zKhxYJ8u3bfNDU0dABS1TVyFTirNGO2oN2jOpMlFNWzUWVJRyM9oUobeNoNyO1NtKGEeIjnwd2hd86g4YjSfOdF46htoLF3oZ3jue3qjodYVtIt8oA1df7PNAL+PG9QC18lOPdfnT10YsZo7NKvKu9ZzrI+sH5QIXCs+1vUC2YJqWpup95ZlLNRuX+nzs0RafeKTNhx5c4pX9mq1xwS/uH7A1ozFq6scebfPenuXJfaQs+PnX9umXyrluxn9z4T6y1E35q8tLdL1wkO1D0uZIrazvCK9sBnzXGWW7YOL7WkD7sDh2/JXzbe5d9DyymPP+cy1+5Ls6tDvCSuG5v6c8tVXaxOJYiJXyrYsVH7unRd4zavaV62baGYZKtQX4yHUHn399xCceb7NTK89vVrhSqGqFUtHW4TWzXyltDyuF46BWNkaB1weRS68OT16Dal1V17VsRcltkjTsKHVf+dvv7/Gj93dY7XnOF56vXS15aDnjmfFxMBYGpiv6wQdbnO84NMD5Rc8nHmvxOxeH1hHuGaUXDvSQPcKtqu6b7iiOI7E00Bb63LaR7Wnl0udGG+o7aaBcS2idh3JH0gTj8cdqSJ+nCrK1uah8Xu9szYHUvO56vR3uwuIE1UShYXfJd/LF3rikuyIJ0W9DlJqvOHzPppiqbfA9syMozgrF+mH01oyNT3yvCutghQPIVhRUCSPTjLgKPvFgm6VCeImaV2JNeV2JQ7U788WIBiFbimRdR+uss8cWBlyzJaU+cPSWLB6kH5TBGDTRbrulsltWhNI26H/8tX3rHKX6hz+wyHISQIcSNsfBxuezqQlorGyUPw6hcsq7zhc8tJJTeOHJlZwvXYk8sZDxp7tj08EsWIfAdeA9izZpB9BV4dGlnK9dKfnQwgKZCA4413FkIvxUe5lfHfRN0JzO0bWdSL1vOYREE/K7bvJL8tBqGRA73/WTDuU9Pc8wtTvylA/41HZlm/IIrgwCn3m6z3sfa9EPypf7JdmiUO8L4s2mAoX/eHHMl7bGfN8jLT6+3DLXeYH3Lhb8wpU+TyZbh1qV1/s171vLWW85vET+2TcGFhCczC6PUrcNNSUZ5DMGra6lrHYcD63kHAwjq11HryUsdoXNjXjMesAeI7ix0mkJiODaBjQWVh3ZDTGasJNo1S5k6cbB3YL+ilW62WiDDME5G+TQ43j5jsvl1uWstm1IxLWZiMMlE1pnPPmSTrI5Ve3mpTkuyRJFPnczn9c7XHMgNa9vy9JoI+eNUPVOJwGbv5dcyJdunXLflMuF/EwKdtPk1XMCxZGvCZK+4LMeVKVOppRckYwTsU32Jx/r8ORqjlbw3nbBr14e8K28msbGYJRh4+YumZDNTO2JE/JF4aUs8H2F0s0N/Hxtq5w9JDM0bQMyFfSKg199dcAn72tTOOGLr464vhNxC0q+5CZCfnOTFyLK2oLDOaiiUnghd0KWCf1hJJaaPI2m52QYlU4TRZILo1ZEMmVjv0ZrpZdAFMCYSJUpl0Y1XS985VslF3dqsmWjPMPItDOZs/fia+H6fuT1Qc17yFnwsD2KdHJhO0aWFRZy4fmdit+/POSTD7f54Htyqlr53VdGfO7KaNLN8F0DwC5n4stU95U4FvZ2FVm3TiQKg6iUKvzSSwespQ7U339igTIKr/ZNAP5Az3P99WAmqkPIzx5eK7GaWlk4hfes5mQOnqditK9oBq/u12QdoVcIX94Z82fXxxMvstnKFgXfdTzvK57sFngnhFx5aqek2sPaPrlQrCa94m3Qec11F2cPdy2XXNeF7DYff6sKfbVpQQ/2lg6/L1dMp2vrgyll3PyZBiWm8zcXnM/rnao5kJrXt2UZEACwbtJJd+k3K99Lhpxy8h1tHNvdr+S2Sc2W845ifRr3omFqlJktMaEYZ0ev81WjISRvxsUx+q9UHlrLzGPKWcfgviLjtQdr4kCIDwcoHdmiTPylwGi2xn7BdwW/CLsV/IuXDnhwIWPvFMftBjBmK4pW1nXaqZVfe3WI1kq5pWmy0pH13KHHtS4YpbrZiYyd8uJezRPLGWVUvr5R8tT1EgRWM0e3dlwdBFiAf315yI/f06brhad2Ky4S8B3hK4M+39wf8eH2tC3ynO4xispvvz6y69CKtO+1LkocJkpU7Dw1ppHjofLZbwzoFY5PPdGBDL62O+ZT93XoZo7XDgL9WjnT9nzvmZbZSEThp767y899Y38SxCxeWH1I+NHzHda6jpd3a37vmSGqyrM3Sh5cdTzZKejXkd/dMrouKmwk9/PINLvO/p2JXvAk5tj3hDhQXFv46Ud6PLxgX8cfWm/xi+N9fue1IT/yWIdv7FV84XrJn70wsjXnzBD2KJ0lXrg4jPzSSwec73iuDQOXNwPEaTcnLsQ0PHB7nxfxRtXHyj4TWoErFO4SaAljNd1hZR2pmx7LzM++a4dQ7VqHso7MrQ7m9Y7VHEjN69uytMkp84eT5WM0gSrYNNNNR7FvMiVX9w0oUZ1My8x2waxr0dgunEwxiks+Uan8QhKLo1zZCDx+v033aVCu9itzjgSyIsMdAXKxMhBV75sIV1HrFrSgXyvPniBoPn5Ah3PbIAnFNU1AnqA5EW8amxHwmZcGvG8t53NX4SsbYwYHCpnwPecKPvWQGT9uDgOfefWAy4PAz794MHke17LpsFAq/9Mrl/ir9SI/ec8Cg6xkI5b84ZXR9G8LZzowVUi5fuKmgwxOoNURHutmrPU8f75dIghPrhT0a+jXkcIL71vNeTEZYJqXmZABmYMwgzd/9L4Ojy9ZG3Ct7dkZRf7shTFaKb/9xSG/vzikjkK2IsfO3+eujPiJ+zp4EV4f1Dy/VU08l7IVA36NwL3RKUkOC12ZgChFWSkcD6znvNSveemVmcC+ePg6AZPnm62NcZyAO78MbphMMEfK8FUD+/nq4RuIMLD17ntpkGPmeSUTnIDLlDp1BKtNJVt987SabzuISpZxKKvwpHJdJp1L10n6PdeMIL6pw5jXvN5UzYHUvL4tK1uSiRt0Q3PUiSbQoGkk3L1hCkIyQWujvm5FG85OJ05NOy3DDGwTnd1wtE5u0Sm89TefPuCHRx0WVHh+o+Qb+zW+BTghjKA4c7j70NAt4qEeKuwKoaXHNvaTSoOJ7DWk+JuZTp54kicP+FvozbbLyL+/Oh3jb2i2TzzSxudCrGC943nv2YKn9iv+2gMdlnLhj66OeH0QTScWBTz8wd4+f7S/z3Lu6B9E+tvRrBdWBDRZS6TBrOZ4tYJ3ncn48fs6ZCKUdcRlTBzHF3NJKmahlwnfs17QLyNFgL2RiZufvlJyZui4cM7z+jhydRhYLg5r3dYXvT2vCn/z3R3edT5nrPCvrw947UgO3zd3ay71+7S9sFNGxrtK6FuHTyOU15VyR3GZgXObvoSDOlKGSKZCHNtUXb883k3Mlsydv6G6yo0I0bqEs9dew1SX5QtH+55IWZiOUMuGFhezXcd0WvX+1MTSte3fxSv56nSAw7UEGdk60RSk3DzH7VRIIcqza84oSUxHeIsul8yYjYJ1s+LIPnP5+u0fx7zmdbdrDqTm9ZbUxJizNjPO2/V1ut2a1U40FQfJ7brCpgabY5mYaU6pt5MqJjuEODJ/ncZX51Y0iG+n7pRO32ccMRHkxnGK/gB+6EKbh1uejTOB337ugP19ZZwrv/3scELVFWccSOq4nfDS4k2kGwnELftdGB/e05qAZnx6z+mJLC/NJgrjCNr3T0FatZ0MDk8Aj7G2c3uqiakIH34o5yP3FXjgxe2agZrO57973xIfWi7QAJ862+Znv7TFtfrwc0U1cFb1lRgicQfC2IBUHCSg1mQbipC14UeW2+iOEjqwtugRYK+MxDF8+WLJWtfxyFrGYjvjP9yoKGvTqn3+5SGXbwRWlxx/68me6dBy+LVXB3xrq2Jt1Zn2rYCX9ip8T3h3N+Nd9+YQhXYOn7qnw//z5X3zLZrppAyDMkxcYThIQw3RDFPDPmZfUacLK+nfI/zWxSE/vNomU/gPV8ZcHcRjY/yuNfVTCgMDwxbPAnneDGBM8/0kZUIaTatojESJUHnzCcvSep19GTE9F5qsGEqbSm38pFwbA3OZ3JKKU02fuwBkNqhgFzsNYwS7kXgjXS1VJQynprtHfa3mNa+3s+ZAal4n1kmUwR09vpoac+o+FOtvvRDUtYUYlSw33VQzkRQGM47nw8NC7ckkkGKb3dBGuy2n67g+6tTXzmUSjAyp4zC0ParZ/D6wVvDB1Zw4hsVF4Sef7PEbFwfgoG5Fm4zyQnHWTDqbqb6TaLZYQnXdui5xxDFqI/STmLmCWEzNEhtDUK2BQomjmbv8hjpKWvqOF4ZBKbci9a7i22Ib8wmg+Lx3fHKtzZX9wBOLFqz7ay8PeXan4mfft2z2DxG66vjeVovf2B4dC8wF26jr6xD3wQWbyHTOEUfQOmd0mqoiteLGBsDCbmTPwxe3x0gFm9uB516q+PsfXWBvHLm0Erg6tC5XBF6+VnNlUPMDDy0alZkGBt61nPPbXx+wtRZY63heo+a1ccR3hd66N2pObNozT+cw1GpmricATN+xv40j65SJT+avS85cvQXqsYKHFy6XPPPVEq2VfFlo3XMcGcTKwIgUqRPrIOwJWihsm3lqY6kAHJqscx3wQ4HoiEGRINT7SrFu3dJ8xQw6fSfl7lWJNp9B5w21O/v5Oa00rcuYulA6nHZrNabO6JYBKbziC3P5vxmo0pg+q2KfT9c2utIVJ1PR85rX21VzIDWvY9UImV0B2cobm4Zpkuff6B3nG6lsSfA9d4wmmKXe3BEqIg44NAnUjM/faZRNGJi1QEOHuEIozqSnTV/yy0XSQam9xvqqI9t1SetkRpP52nQM/rQNK4yjmSOmjdK3bVLukK4lB8r0nmapRy8UZ20TFSeH/luWgp3PLTv+9pM9FjLH1X7Nv7jYpxzDd61lnF/LuFjXE98psE1xIQixhnoI2oO2E6oqEjGd0rI4zix4Wl742INt/mRjzO4J7821IV8QarX3KQr0lGzNQFTdT5NbmfKVq2M+uGadritXav70+ojghWpH+Tvv7bLQdgwjLOSOXqUc1HBFazaLiBfHII+Hgm37tQUPP3WjQlxl1yIBpG/sVnywl7PgHAJ86XqZzien+pbly4JkYiA+Jm3YkuJbtvHHSpGhdfuq7en18Asnd0HrnXTNR3Zjkq0b+BcxvyUtrQOkKeTXL07XUhwZpRuDvY5vH17fs90uAylMun93UoeDhk3zpWO7qfGJNvVdJsBaY+rULRrAb1zPT6owsM+ZnXjLodSF08//vOb1dtUcSM3rWMXUSYqlhem+kVXS0E9ac1Njzqb9r7WSLcmbBl3izcFb0YkI3XemgKHpHDWveQhI9MyyIF83x+c7MRQNQ53QIVqBnNBJemm/5n2d3HQ8Kjx/paLaVeIoTjZDo0FswwhDm+jKejLRsUgm05zBTPFtyFpCHAnBTU0SswWZdC2Ojcr3HC63bLdZoX6zmf7Iwx0WUubf+a7no4+0qIbKxx/tkC1BpMW/fHnA1SbnTeDSbs2ojjx2vsApXN8PPLSQ8WSd8X88t8f/8P4VfA4v7lbcGEd+5PEOn3l2YDTPYrousaFgzR3eDZ1t6HHaGTRRtJ3rPx6PeOGbFZnCqzsBd84ie/I1eOiBDJ+0PS/sVjxzueKbWxUXtcavCK6CP94fszT0XGh7VlqO96/mnHmv8DsvjxjL4fy3Qa38yuUD/u7DPRYKx7lzns5ACNnpYEOyZnIzgSnH8SzFRO9NArTdYeuIQ5VydCQ9zjlHvjhdJ1onGnFslgCH4l7EHu/EJjyzZUASBXgCaItDkpM8x2JjJn8ztpsHl9tzNmt41tbBt4RQ2/eIa81ouQo75jhu/K04cbLx0KmS4z/f7vThvOb1VtYcSM3rWLm2OTy7Qo4lvd9J3Y6/UxxP2/+hD271jb9eLDUBEzv2fGX6xT0L0GZfU5xlczWu5LYp3t6XcwxplFwE37ZuiWSpGzRTTXDspYPAr14e8HA74/pW4JkNmyKzuBsm51vVNijUfHZ8x/Q2Whv402C6s9A3uigOZRKKPFsTvValE2F+oym5mWatOCRsF7orjofuy6xDpiAVPFr4CZASJ4wWlM+8MuDRMxnUwuXtmhjB7cNTdcXPfWOfD61by8N3haIWqp1o4FONiq02DQS4luDajmyRZAZp3k71gTnAx6F14Nbu8Xz8/hbDA0G6Y4YrylBhjHC9itzbzVBsOu7Lr4+50jfbBdc2R/x9VT778gEfW2rx0fMtOoXw+FLB6EH4vcujY+flo+fa9FoeBd6zWrBfK1+4fjyA+KQ66Xy73ICW1kK+mqwF2ofB7WzlK5L0e1OQPuvZFWslbCjlFhZDVERcx6UOVKLvxgau630MlDm1PMUZQKIxrT+sOz39XByuJu8y1IrrSPK3SkaplV03i2tKlOPM+hSZAZmVouWt7Q9cl0mO4a3+dl7zejtrDqTmdayyJcEvnKzNudslGUyy+e5gAuikqneN9olj69bE8uSwU3fkNd9INle5HaluGHBq3ZPMLjscokNUzbG57kdc28JaL48jl8cl9WAqJs9XrItGYz/gzHyzcW+e0HOl/X22IsRKcN48lSz4+HTtSr1no+1xlETvt8gh/NLGmJ+8v4MTYRSUp/oVZxY96yKEsW2eO7tmvtkABJcLeyi/8tqQH1xroQj7MfDs9ZI6hz+/WvKelYK2F6IqV/ZrfuBCi0s7gdUVx0rP8839MZd3jB51uSSxv73/OLCJzNA3TdE///gTfOreKerefN8+ry3ssDEK/PwLfX7z0pAfXG/RGsPXr5Zc3gvWncttnWg0UOF7sLBoRp8u2Osdndxr6ujvT/u7psLIwLBrn961ci2BloHkas8Ab7588gSm+MNGmqpJM+VTNzFLIdnjNBEpU+2QeNO3lTciqJjmbQFAUldq9oUS+Kntn6d23PJp3mUj9haxAGHUXltD8q8aQSj0xHPhcrmt6T+R2wtGnte83u6aA6l5nVhvl3jTZUKxlrRURQIU+gZ1VS5RJMlBPJaWLn+UMpRMKNaZdoFm6hDVuHDcKwiSrqNvm7GWShgaGAsDozsmdEgwEBUOoN6JxJEjXzMK0S+kcfI07Vcn92k3tumobMU6Fc1Gli2msfZSQR35shDbUPfttWcn846WiKDohEaCBNLkMKhq6MRn+xWb48hq4bgyDBzUyu+9PuQn7++wGB3fulHx1dfHkJnPU7Zs52R8Gf79S0NeeaxiIXdcvFZzMAYtA5cuRv7xq7s89GjGA2dyPnyhRVhSHlnO2C2Vjd3AhxZy/sWoz3YvTABwM4lW7qRzrvBD93X41D2HW5fr40WutXZZUsdfX+/wtctj/s0Lw8nAg++mbkkBYYYiEwfPXyp5vMgMYHvl2Usl9Z6tm9n6xkbFvc7TRP68sHu6X1cYWj4dgA8GcjUkIbhXE4nH6doMQ+umam2ap+Ksp9qJFkXUNiE5IofWa9ifDnTkq7aWswXTqoWD5mZiCnZFGnBjovKJtUd22DG0mdBrgFRTjV+aBW/bmtOOreFqW6n2Itmi0DrrJk8nXtA6orUB2HxpKhVozscbmeiNlZ1f8Wntz8Xm83oHaw6k5vWOl2Tm/hPHJogFTnQrbyiy08qoD0FSSHDjjRMG4I64Hp9GO2o1pf3qvlIkIDX72uJsI4lD0yz5TnPnPX2caxsVFUsIdSQOBfXRXrdl+pZZ6q0xWGz+Kc40Wqpq04CagpExCtF1kqA/s+7VzUTBFvBszydepmaegtGf6TgmdGKtbHQCm41jd4jsRuEzLw9MgzMCWjYxFQ6sw6E6FQJfuhTo3K+waqaX5bZRUnsSee6lmu99oG3dlS48diYnVMoLES7uBB5dy/mzjYiOdGIaqVGJAxPpf/jxFv/7Jx4/kX1dGS7Q93ss546/fqHDTgZ/8PyQQW0ALPYhHqgBv1rAWdfyuasVg8EBD65nXB8HXh4ZZXl0iuwrF0uq/chKy/FaDLxW2/lpJj8b/zKXuen1TNf00JSaAKoI0KuEssDE9UPr3OAVtxiNph5bZyuMHL5rz9/YLcwMiU4GD1wh5EseUetwNpN5TeWrBtrIIPYNVIVdOUapN+vPnjuti5n17btGaUthJrjlhoE2A6CKb/nJuYkpgBpJ08DIofPhOmlIQrntTnjoT6nuOJ53qub1ztYcSM3rba04NprJdY5/YcaZG3ytgKSDmJ0E8t3TLQlmqY/YdGB0Oqk3q8U41Q/JY1TSSHFuKkyPI5tCylfsccW6I1uJ07t8TcaLwTbfxqfJjkcIyUdo1FeqHSFfiWRLzrpeuXWcYsUh6iaWydQz0XmH6BZn02mxUiJGWTWAKHdmtZA74Zntkj0OP28olTCMpslpTQGdy4RQRohG4WVdodqyTZJMaV9wE7otjpXxloEoySBbZXK+m02tcPC9jxWpZAqpAAAgAElEQVTQV770dEk/GgDcq2zXv7DgWWo5BlF5YCXHO+G3XjKqqBHukyJ1XNu6Dz/4XW1eZ8ADHE/b3fSjtFHDPcs593eEMx92/NKLB9TbaYJM7Xr4nlBtpTXVFi4Nal6rI75n3ZmjRqxe4Kff3eWBtqccKhdfHRCw7kwcQbUVCQPrDrbvt/fpQwIHPVsXEzuCCAst4dNP9jiz7BmI8ssvHPDadQuNEwQtjd6Mo8a/y45LZz4j2QIEkWSWOf29AWsD8kY1mwu5JO+qODZ7iVjae9fqcEeqKVWlvJG6UD0Bn0TjR7rFzjnEB0I61nITOvcm8LidwFIXshlPNhPGp/XYb96fXZujthgNhYmb3lwdmkp9k5KAec3rzdYcSM3rbatYTTtOrpZj2Vi+gzkuK4ccjAnTSaA4UrgNbyeXJ8ow0YTNlzoKMjrd10q84DsWRaJhalwJCQTGKQB0fiaLTmamFHOzVWh+ny0KkkfiNSUG0B3baN1IIXUXfFeO6fobq4RwoISRkq+bDmZCtzQvLzM/Az/9UJf7u/ZH71vN+cVvHUxMIgFiGRm9nrQtebDjc4LrJe1QpYR9AY3UB6mLUlrHyXdtAs26WrZJuza07nV0H4a13PHXn+ixkAtn255+um4fuK/g57/eJy46/ujqiI4X7uu1eWG3QirInbClkXot8q5uziOrGT/0SJv7XZeVYY+NB5VfvrxJbFe83Nrj+8I6bpJcCztVxf/84g1WOsKTay3TqwHnO94m1RYUbfwWGiornTPfk5RlKOAMrJh9x3SNvGcl55EzOWGsFMCPPdblnzzbn1BkzU2AqnW5fOdIVJAk0FUZZfzxB9qcXfOIExYQ/sr9bX6l32f0moC3zmpx3jpI6kCHzjpeSQenUSdmt8cy9zLTQ8XQHJuiYQrELa9vSivH9NnIlg8/Vzhg8pkBpXXeuOGTgEvrftAgtn5GMvWQCyl2xiVrj6arW5AmDdMwRWPWeYLsLPSn3U4RJiao5rF2+k3RGyq1/xkA1Om6mNe8blJzIHWLmkw8ZZw+ljyv26tZuuOEbKwmIPVY+aSfKm066HaroQyPvb6e8MeHHmh0WUOp+Y5MRsxvRjvM0iGuq7hoY+S+C77riINo01LJuNzdImjZ6EEDcBLMgLP9gG2E9VCRXMkK2yCbSa+OlwmIAuhljnu7nm/tVkatBKg2xJwsJVFcat2L0DfD0sYaQUidspF125r13wi1LQPPNhoRQVrCf/J4jzMtT+HgvasFL+xWbAwDXfWczzMu7QdYFH794pCX9ms+dW9n4nCNVz79rkUeWcj44HpOrypY3liDtkNb8InVRf6vzdd5ZEH5qn+N+3dW6VVtfu3yJv/jNy/R8sLKWeGDF9pUNhDI1WGwzODczrvWicpaM8f3OJKpw3dzHU+wvfBNxlsBMQiZ08nkmGsJrTNCtZe6ndkshcdkstM6LfY82ZE8wywBhGJFJpSdiEzXe2v6WNVEi6XuZ752wlr0Mp16LKY0tmRTIXmxZvYDsbTu1DGKLKb3OzZhueRyKoWcdTzFuWiROIW9b9dKXb0oZEuH3+/s1J6d86kw/1idQGHC3fena0KZVaHej7iWEA6m1hTzmtdpNQdSt6iwz4n0ybzuvFyRRNP1YarpVjURv+rNtUA3fY4kStWKSbeiKY1p+ilLpolduxuPQwiZUqwdNjdsKowUwpSmjJVponzLQJyWtjnUfetGtO5xZCumB8lWzGPnpqXge/accShEUcKBAcrGvbpYPywYH0dlFJR2Q6GgbG4Hyk012siB5DqhHPNzRrdo6hy5tk79ejIl7zmy5aYbkLpnbdsYNTjEQX7GOhFhpCym160jhKgUPnUpVNkbx2lsTqV89bUSF+HBpYydMvKRsy1U4f6ep+sdKztLEA0BCNB1np9ZO8dnNy/hInwhXEFy+PxgxH/xgUVWMs/9657NEOm2hc9dHvGHV8cJJKSQYCc80PU8cT7jxjDyzJXq1sAaeH634oPrOauFx3WVL14uD2fGLTv8klHHFtGiCAreAMPRoYWvbpY8vpTT9kIdlS98a0y1ZWvQ53Kqo72dPKbu5fXJtBwkL7GuGWLGYdIiOQNeTceIXCfToE2nqfFEcz2lEIdiXTQRObbmZytvMiVlaiVSnBFiFW0NV3oq+HGFHaOWHAr3hik9jrtz24Ojn+2bVaxnHzftnB16vloJ6Sbi7TIantdf/JoDqVvVDH0yz3N683WSud9kAkfMT+hmeW5v6rU7AieIUus9uxsFm45yuZjZZZq8CwPF5QYG4tjAmORTys8Ho47q7SRqHppDsziblotDodoOxKG5nbfudccsCDToxLxURBhvBKoNu6t3HUkTZVinKI2VyxFKD6zR9OsXB3zybAtfwRevlVzbrgGh3gPXUpwX/D1CsSr4dnKb7mEj8+m5bcoKZDUSDoyCyRanm1FxxgCWOECgvG7i6K/4MR95dxvfgae2SzYOIqNB5E9eHrNdRwNgUScu3V98cczXzlRkAt+zXuBFGASlUxRQHv96OpO3uHIjcDbzaKVsjiIfvFBQOMvVW2o59vrKazuB7c3I3lYwkb7a+3v8XMbfeLgLNdCD9pLwH6+M7bqfYguhqgwGyi8+tc85l3FQRW4MAi5zEzqsEVqHoQHVWDLRi9UHCv3D63tjHPmFb/U523ZsHQRubASLPwE6D8mEjq537fWzZaN14zhSbithrFCD77hjACVUgeG3LNS3OG8aJgCvQtZLbv59AKOu/NqUIjs0bRiTfYgYiCo3I9Vm0gquumNaJnGH6UyNdvzlluLbdoz5mZMBYr0/HfJoJhAnz+uP66Zut+pdJvFQzWf7tPIdJt3i9j2AO64HawK/o7Mcw/m04LxgDqRuWZP2/23478zrjVUYJO0GiV6Y0Udpmj56Sx2M9fjPvmPTcVpCtRsJ/eQTFQwMxrFO1kMMiu4ZDec6imiib9K0XJRA2Eidmj3Qe01QPHnJ2QmmtoCLlNeU+sBEvu0lR7Zq1hCuo0hHqHZI02DHAf7lQeAX/vxgsoFIJpOonsYwsYmxacrlRncB1r1K5yKWEFIcTDg47MvVbDJmy2DX8d8+M+RqFVi71/PSOHDjWrAOmtroezOFF0ZTsTPY1Nq/uzziU/e2eXG/4mP3LBqwO1KuED77wgHf1c7QA3h6u+QffP8SbgmcSxoan4T7pEkz1wjW4ckHCqjSe6vg8aWM/3h5fKwrpTGdOyfUO3aso75y0Ksm5qbEaVZhPIAfvKfFfV3Plf3AH18ZEzWB3dRBOrq+B7Xyaj+kjEYDq649nTINoxlt4ACkp4yvTvVEjX1G3dd0LLbmwoCJoWZ1zXzOZtd2neKMfNuoWT8LFmbOQziYZttli6aLs85jkpndoow2TKadw9TxOu1xJ3wG70rdwXPNRia51il3zc1H424e47y+7WsOpG5RNur+Th/Fd3a5InV3jkzgaJxqQbKFt06jli1CGEy1Mk34sO9BHZR40GysMgVaC850VCkvLI5I7uIgbSbJ9L4L7Zan3ozW1UlZgLM1O9GltU6czglY12FJ0UosiHiICacTDVFuRYt8OeKI3YQTi1jmGx6IBoaOaoKOVr5sU4eS2zRV2E/TiOsn00gWB2SP0aA8t13R6gQTxuegI9NfEU3J69oYzSiA6CQj8Nmdim/sVjzQ8/zMY2eJ2abd+s9sWvLuH6L60y/xlRslYc+u0Z9eHfPjKx0uV4EHWsJmGRkE5StXS+u4tSOxb+9naxyQbm40X6bsDMIkoqapWCnltUiMFpTcnOsmosXl5ig/u14/+kDB9y21IMIDaxnFWcfnr40n4b31nh5b35P3JNapbABxo8lxuSU0odapNOPMmWnUdA21SiajwW5IstXpBKlfSZ+bNMBhwEZBlDC0OKTZa+o61olCzSldU2fNbArSP/3tBRe73NZf1ksC+OWTMwQhfQYTkLkVBXcnlS3NfLbvAhWXLduU5k2p12/zCkO7eT2Jvp3XyTUHUvN6x8t3LAIEOdx50iqBDFWqPcW13VvSmZJsSh00tFNINg1a6WTyL+uZvYJ4odyIlH37Ys0WUwp90ofEcRKIu6ZrIHSfsEgXv6A4d9zAqrlbdwWQRZvq6yTjTueoE42ogaknT1TigRAwHUhxdnpufM/8qmT2nHpuiyKZPR9hZMDNukozYKM2rYx4qHYN6XQfEROf50Iszf1dCplMmiHma5QX4AtBM3u8iEy6Z1HMb2qUr9Lym2hRm4OmAkXG1Qd/Ah39r4jacfmO8GxdcfWFyEIu7G7UtGvHVhYoe4J3NoEYR+Yy/4X9MYsfEh7wGdf3a37/lTFyZICh3lPqfvp5x6wnwn6K//EkesodOrcXVjwu0ZyocDZ1NBo37pPW92y5PIVc67Tz7Qozjp39XbbscK1kRyAwuqboEGIdcbkDJ2Q9x8J7IrGCfPHIWnPJDy0B9/Fr4BcD+ZozgChTkKQ1jG+kyKWWUKw5dJmbup0ffq30v+x4B/RovRn67mY1u5bvRrlCvqPF53F8xEj2Lbgm34k1B1LzekfL7o5Ppk0ltw2m3FFcBtXW8VywyfMk08A3C7TqHYvqiKXpifBCnu7oxTet/6l2pdxQ8jMO30t5eDNUW0iu5y6HMLLORqitsyOSHLuvJ5qly8R/SkRonTUwgkuu58kXS3wCnqnjVNNMiJ1Ag90FKtoVTEbaRUy0jZsdi59WLGUaLnxgwnIdKdmKoIXpS1yhVJtCtqIQnTmNJ12OJuPMK7nyT1/c5B8urSIHfYsP8V2qd/9N/pd/83OT1xUxkCoibJeRzX5kcEmREPihhzs88mDO5f2az70+pNoEWhHdE37nqRG+ZSARwKeOTN1PnT437fpIYeL6WCnahzrl4eXLh8/ta4PA4+s5sTKg8dpOOPTfm/U9SxkerZPW7tHfZYsysf8otyOaOrmuY6ArW7Bz4r3HzwizG4ocnywVQprUGyquhnIjOfL3pp0bM3tVpGvTfU037nYrjtPnAd6S6bfJe3JvXj85r+M1py9vv+ZA6ju8NCYBrHtjmXJvZYUDAxHiTWB6dNNoJow0JgfmoSL7HIuE0Hpq/Jctnp5Wf1ppSOcoY6JTAes2iUtZdakLhAp+2TaFcktBhHq7+SI36kpysdT7kYGDMFKIMqFbSGxKHJsQWSvTtdBOx6BmXpivWOdrKpZNYGzQWCqIxYSMFL940ju784pj89DynQQcnZAvOlwSxRjQYAqiZk717EbpChMui0+bb5qEhKnQvEigOFaRODLwqi6iteMf/eYf8Mpf+5v87If+M9YcbLRX+Ud/8sv8+hd/Hdc14TRwjHYXge+/p81H7m+RtYQLuad6TPnccGgUVbre9SjpplpTyqtx7gaSfmg6JaZ14yxvQdKSafKQsuP42laFKtzXy7i6H/jqZnn83JZTH7WTJvnutHzLhiK0TpN+xYzH2EzNGtq6tlFsrbNQ7UFwdlK0UqID4lQrByCFoKOU+XiHAeYut+8djW8ORJ32HVbv2np1hUymYef15sq1mjiqO5us/stecyD1HV7mDdTcBd9d/cGbrWZjimNlfB1coeQrx3UU2aJQJq1UHNuGPDsdFKupxqgJLIbTdUAaDCy4IomJ96aTPa6tMDQzz2zJUe0q4iKhD86b0Ns5R3aupto1iqu8EcnXEpXjhXxJkEyoByk7LTd6S0sTPE+jZmzDDtE2iHwN4kAO2WxoZR0yl4NfTEaZgAbrFlR7jR7m8O1jHCvjaxGtbFIqX3bH/jvuuDao2ei1mnp6mTO32N+nYGZfpcy2hWkHbva6ZUsyibHR2sBorKMFBXckTbolrYmk0XMxwKlqgPZf/slv8Mtf+s3jFzDY8Ye+Uvftiz/rCa5wtC5E7j3ncXkKc27DhaWM9n0ecZZnF4dG3WUL4DJn3UFn2qHQN7CVLZgWKI6gHMQJyKu303CEU7R0kw5Tvix8fbvi69un5+81k3zNz41wPwztvUiepvpuAxBosPfnF3QC8EPfzuUxTWecEa2PresnmVCsCbqsxNo6rCiHwJLZecTJ9bxToNIYgxLf3KDO7HcYYh3CMLaBDLydg0wt3+/oZ3ted153eiM6rzmQ+ktVf9Fata4LumcGh+IVrY1COLoRuJaQr6SJtybXLLk6u8ZzJ8PE2U6ptu1x2dLxLpxq6l4lfU++fvi14lhsYx9PaRgk6XEW3aTz45xDMkWC3dE37s1meGjdmCaUNVuGbOH4FJArhOKMMyF3O+lpjvrkeAMqsZ7aLdgbsUkore18HP3yqw/MSBbs/bqOoiOXvLh0Mvl1dNT8pDrJKPV2tBOTqT6sK6el2TjYSL2aEF0xXc8CgKTju/nzNhN/YQgSFFEDUgDZouNqO/BElieAJ7ymdcqnsw7O6HKcWBQ0Vg+hn2iotgFmDc50TRE+dqHFoysZ164Ffu+5IcOhgZigCSiqUm7YNcwWb6KDaqdrONPpAuvMagQd21DBSYags6VRLQy7BBGXbiJ0Mv13tMytP3UuO4cBkdGAgqym6KbZ4xpgwDYq1aZNpGaLdwZQxMmx4Yq7UXEgSGF2JOKmMU2zn+3izBwQzOvtqTmQ+g4vvwCI0UpHQ4Df6fJtsbvLoeXZzZoCHi3XhiwKYWx+M9WeEkZC64J9kTaRLzb2nboq4YQn0pkJuRRs7JKBpmQQ9tXon0jSRdmmqVFggYnOxBdC65yBmWxBJiGuTcVKJx23BsBOKAphYlh4KxDj8qnuSmvrzmkAyZXh64F6l2Ov3ZxbyZIR5RAGLytZK+A6brLRQKLqJlNiybS0PqGr8SbKFXadiUabZkuCjoV61859tgyoiaddW22T9Kd3T12Bbc5iHl21KmwHqAww/LlWlHtwT9tzdRR5NlSHjiVfdYg36/FsBer+1EdMxMTy+Ypdm+/uZvzAOUMXF7oenwm/+cyAfMW6ifU+6Ng6WoyhluPRR5PXzuTY5q7aWAqYTm62czOhWdvT38dSGV2JRkOKkK+mgOzdBFj8yWAqWzIT1VOvUS6mRTtynuMIm9zLEng84hX1dpRfAJykDm4S4rds3WcLpvkCDn+2I5Np0HnN662uOZD6Dq+jJnl/UUpDopHUtEjNBiNejAYaKa4rk6R7kTQxV8AohQgTko/PjMmm72CxJ8BJifBa2WPrfUAiWe1sImk9dRLEPHuaO/PQB3JF+5KmWaw7Rgq19e2UpXfCF7aaD+akwxIGTHQ4mdxeYn22bJ5VitFQTeep2kmj6c4MQ+vdaJNRrUY7JHQestiSatPcrasxFC1zqZ5QdUc6YG9URze5Zj2ZdIdmqzgj1Htps5dIPUihvKWd0+Y6g+BusV5dIbTOOHw3mjVDVMorBjbrDNpeeLZT8cxuNZkKbMpcziOusG6kyxzRT6ngbIkUqWKPObecTUCliOPeBz3dSnCZS48xsFrvN+vX/lZrJda3ppjCAJpg7YbybB5f7drnI46n2ZBxbMBGnCC5ki87tLJ8SDBKltZpr3Zn1Qw1hFFj4Dl9f29niTtut+C7MgHUU6rc/i6Opjcqd7NUp5+5uav5vGZrDqTm9Y5UGDHx54lDJnfLJvy2TSEMdGaDtXK5kC0rwZ/cvRKfgM5pr5sMBk1XZFTirMmkdclIdIZpnOIAcEYF1ftqJq3jqQ1BGBx+jmYScQICm430FGo1jhMNJwpqGqnZxxZnnOk+WtPnj0PrhIhTpGU0aRhyxDDTkS8p9U602Jq2mWL63pvjWlTN+oAEUg5dswM9EUg19GAYKfWuRdLEqORr7g1teOKFrOvQ0kKCpYjmVg7WSZSThddhiHW/MM0aWdJ55TIVxs/Uq/2aD65NubZL4zABUc1x+K51/yxfLlFhafjBOmA3eSM6fZ7bOQ+uY93CMEhWCG2zkYhJ236MGn6TJd6Ascun7+9WpTHdqOjNqc43fWwz3TuNNsHnu2+d798kPFkgX7k1JT6vvzw1B1LzekfKFclsEA5rQtLdXqz01C+qfNnoF3kD2VuuBTJO3aSFtNEdMQpUtWnCepCop8W0YVcmZI/DafJ8rOz3BsjEukP7Znjocoi1oGJdF9/DaNYjx13v2aZb7yl+QZHS7rab9y+Z4Gc+qZpGvovzQhyZB5fkJ/vbuFzoPuQMZBUnb4TWpbFjutWd9qEJsAYkzF6zW2y0Dd1qG57QWhQ+cqbFYi58c7fi1YPDfKyqAVlNhpKHgm/9DKU7xAw6OwYqT6uGrpqlkU/UpqV64XrFvxoc8PjZjK1K+epmaRTtIA0LpA6hK+z91/tqdHBIGXdjJjEyJ9VkTXD4uM3A0gDSbOfSZUL7vsNtIcmt4zc5Vw1NeBfF1s1abNzNb/b8cTiNewn+re+IT4BrbefqZhTmm3qdZmnqKbKBef2lrTmQmtfbUhOjN2eaBpebOWXYM02MK8woUETIVtVQlrcNu06Gj/mKTcOd1Oq/3fI9QQqh8uZjlC3Jsc0/DGwzELDOS6O5qi00WEOkWHXk60J5w+7Uq12lWJ92BtDkvePSBp9bpEy2kGibTQU1j6Uwtk5OrJWwYxEzruPMQiDFebjc9DyNhse1jNZs3ZvAzxEPraPnO1s0O4byerTjWLGNUOOUYo0jyFaYiI41TUMe0tbpzARYqZMg6dlrdrTqfZ06vfdmqNcu/Nh9HZ5cNkTznpWcz74y4OK12v6+bV2luq8pfFZO9RHLOo7sFKpU6xkaecWmCePArrMsna6jafLznt8tee6VykD1QrKgaKbIkm4njCKjS4m2XbLuVqhM8xUOjmTQNbR2TNqlUxz7XetwJM+tKo6m56raFnxb8Ytyx9rIWJ7cfRq8bOHX2QK07/WnDxzMrIEmwiYMDGRnS28B5RZmutvj1DneTWv/hCngN1rZAtSaOpd3ufM3r2/vmgOpeb0tFQapkxJJI/Cgo6RJqtK0Uto0RGSyMsNIJ3d/YcQbBlCzpcGAB5IiV458KQp2lyuFibvjEDQZceIVlzvCQPE9N41zSeW7BkDEG0iZ+E9hG2i9Z+8JDDjGIebR1AU9sMk2yYR4ACwlKkETaKlT5EpIWg2x6SW/enyjOOl813spHDrZOGQd0yiFPcBbSPPEaLPPxP1aw3QqrolMiiPFzUyAzV6zQ+c62iZqx2SO3I2ZpUblwe5013Ui3N/1vDwwcXgYqtlGqFFFrjBa5U6nscJo2kGIQyYmlnGk0Dt+3LHWw/mFYdqBq7aS75Ie7r5NzremaJ60pmTy/xLl1Vx/tet/lI69G6W1gUeNcuL6vlkZ9ZoA4UwsUyyTwF1NYH+z8m3rujZgrLweE1A/+Xy/2ZIMozhLW19hOLP2R3fPD0myW9C08/pLW3MgNa+3pVwrbTBuas7nWuYBJY4T9SyQKMDh9Oe7ciyzRoEnbWLeAA3YcWUr1l3KVp2Jm5MpZb2vE48lVySdi7eoljBMo9l5M0GXRPSlQgJY0rbXV7XIeVc51Jv+qKGdGrqwiSeBZiIpAbN+is7Jksi2mHYyjp5v22Cx52/8jAaCtKN1oVoWqgsNGLS/Cf1Gf5I0MzPu2rcqcY0LuwGRhg6KtVJvKVdvBB4+KxNKcWMccS2ZGC26jpLRaNn0DU1juZZ1oJTmfJvJpMuPd9DqPZ0YieZrNukWK1LWXfIo6oCOwS/CE2dznljK2FmK/Ml4SFVCthgpt9I5V5ls5GGQpgNjunFo310Q5dqQqUytMvQNPH8CnFor1R5TT7PMLDxUo3UWb3FDM0vLS+v08303SiaTkuk1R+mzB7e0kngnS2udhDn/RZuonted1RxIzettKdexyWzxU2rG98ygEjldb+FaKYOMu6f5EJ+MAo/QYU1pJWbMiQE9pwmgFA63ZgJ0M2a0zkV+hmPWB01elSum1GEDFiVL5psjowR9x6YWs1XL4yMYcCk3I/mKaYlmYzBcMvisNkyzZRqraYejOJOmmlocOrfZgoAYCJFmo2sE1oX995AZiHI9RUcGaGKtKZD4ZCG/xrRxnRIMm61gfkRMI3O0MjD4Wy8O+JR0WF1xPLdV8fzLpkHKlpJ5qTikq2RLSWAfzNPIdy3c+XbEzy4X/GLKTEwgM7SUajcSXheydSXrWAuqMWZtMg19R/Ad0x9psAihJkT74TM5f+PBDoLACqz0HP/29SHlZkST40Lj26Rqppt2vW3N+PbdoZ1iNfWA8l3BI+iCnrq+Y2Xu8nZtzHS0oVL9AriaiW9UvQP5WXDO0Xow0qodZHf2WcyXBV0AxehoyfQtnXrzbdMNxpC6a4lC/4s2aVft6mSy12WHxfPz+vaqOZCa19tSNvGSNkKpDcysyaEJqNPqrXAovtlz+o4ZWsahdXBi+pTkawkoZKQJu1u/TkPNuRTpIhmTqcHyujlmx5HiFxzeO2TR6B+tgboRG58ATnqClkxMJRtQZ92Pho4xKsu1jbbzi+BazsBTE4K7BNq2Tlqj4UpnCFKeX2NweoI9EWBGqXGcaLe14xuCiHUi6i3bxMVBtmrnchiVf3N1CFct7y2O7VhjKZP3HfZt5D+OTBsWBjqZlDwaCTShU70S+6ZnwpszPR5Ejf7RSgh9tenBGvz9pmHzPfu9HIlbsSlA821qnLPv72UGolI9uJQhVwTnHX4hmMln6hw2FG/jBJ/dweSkqq0JgnXBDrnRp3gkFFw59bBqDCpjZd212fVuvmj2cxjaOm9+9gvWhdMy/c3MpXTOQdFQrRZt1Axs3KrEC/XOyevk6DFqrRwLMD/hd7d6PU3Au3nP7hSPuneqROzmwv7lnT2Web25mgOpeb0t1WhU6n6KNVETWHcesjtiDVPq6PTnSNNS/vQYg2biTsS6SnGYjPxOEfSeVJKlqUCx43WtiMvNyJI8iatXmFgnHKWZzNDR9CZh8P+z96bRlmRXeeC3z4mIO7w5s7KqqCqpLAZJFoKmBWhglARqQEgG45YZlhfGzcLGNFgLG9Grf7nBRrTby5ZEr6wCynsAACAASURBVG7GdtugbpBpWsKWmGzLZtmiuhgMElgSIIlSSaikysp80313iIhzdv/Y+5yIuDfulPUypVLFXqqll+/dG8OJE3F27O/b3ycLL59r+V55WbBefu+kAgYoKXssCxQswyS08uGf7ANuQkJcJxLoql+pPJfnyq9So10yFQ8tnist/q5xLpnYlgQz3/JMksKGIbIuykEQcdlIOzXJpQRIYZBeIYRP5zeEYMQ54HuMRCtNIRkoL7xWtcI10l36avvsGYVaCQl0K5W68jScC8AKs5keQCwLGSXVcdsBRZX59gGpYJjr02brVvh3cgD40oB2GfCE/IZ0f8LINd1mLrKTRCmQtf2N4LOoiYjysmSAm98tzwA3kepYciBaXWS0IqfJkwilSoJDaZWABTi7bX6LN6TudNT05lsZLfOkCaXKPVWeNSUGqk5YVeJPq7mxCuI1WRPS/VSL5EDu30AL6OKpG10i1cUdiWQXKEGwGaHUJ78vg8+YfIb9clVoQEiuUYG6RfmaPWP2mCRSdqBVBSUDUbKZBk4ISkgMjFOphIhfmDLUIQ/zVUmO6SkxXN/sw9t3eRrI8wI3wStniyj6mlGK2E3oc4gNSmjbtzVZBKumtaxwXFZVcYiC7Y5ynZ7Ec9r25dhmHxezXlNUsgOAVElw0fQIbA1V8aZqGGNQQqBSYMBQ+XMXjPKCURwHAU+gd58ojvsxRUmEGL5K2NkBMPI76kEqT67SGDIZofcM6agzvUphPr/p4cdS2QtdkuxV3V7NrU0if/vgeYl3PjbBsw9SnOUev/lxkbInK/O4OAH8VKqOdodghoR0bzs4L1T73FgSh9AkwaXAwyYLnZCLpGpWWQs/gTQYaLeryQjJbgU9M5wQyEvG9OOILx7zGm7xWqm3Y2Ups9n5tM2TeSg1QKLQOY1MXgTqv2OjVTgvychyBXzxmQRuT1X7yQbZW+8+7uJTK7pEqos7EpRIlcbuGrABeMZIr5qlJPP2jWiJ3wBthmyhWymoQSdP4i00QF7lefU2y8V2HUdkZLHjsiKPxzWHgOyIAE/xbxFWSqQq4sfB8kZON1ip1d/KiZSHkzCSYTORSY9ISOPpYlXBTRnuQlvSlyyYgCzeXIqSuhvL/uYTSCJJlFdxPJ57kOKLPmOIogTe+egEj8M3/h7GG8Tx2pYjL0bVuVjykJXxMomBWdJ6b7JQ3VSSewm4x7wYXe83u7hsz8DW5oi7YBRPKKHdC9xKqfCifCEJPw083Eigx/Qq8O6bBd59c9Go2PREEiL/uHR1liMgW1NxbQ1SyHVfGhv8jGIyFcdul6LchdFOU0Dmk58x0ENU7Wdm5Nfls6JPxShOVKjWA5QKP82PtcOuLVTyAoYbFcF1YVKCmePY2R1JmCkVKNUMtAGFKEoMxE5YQ9GvsN7Ju6ra9KmYQHXx6RddItXFLceteFmZhDB8plXeB6O8CSBjJH0Ds8IyhZnhJh7FuSQMNEcxER87BhsGZQxjDcwOw5ARSGmmb+VbEDopkwd9ecaN7rftTrj5xpweUiWOmVJjDE1PK1n672iaDEkIyEIWUS+VPC4EZksOCHC0MH5tUF4Id64ebyU3vNzmI4hvugshoMNRQz/Iz9TKBEC6pDpwlBl8zf19kZUogP/2cAc//YERyhrHjIi00gCAGSYVraXyhGF2ALNjhJZWSjVkPiGJbfua1HEJeIZUJY3a8TjhFPG5XBc7rBLM4HlHGcBTHbvYJRmqmgI9cinEaXdBoAOOxz8fJgnNFAzwrQlTBvhW7IiMVKcKXtDMKs+l0ulKjsKqdih6ZIEDZQYVLMelcBbtvryYkBHkLYh/mhVdZOwBJoWsLxhF4kEqOBt5Trx8XOoRyPwhKEWj2gnIudQlL0RzDto8sHLzXXRxR6JLpLq4tfBAfl00idIj2vrNz0/k+9J2D6RrXOW9+n0R5A3fl2iofbtRIJQSYCotJtqVxc+BpetsAx2Y+a6m7Jq8zW+bNLqLIKYp5GqB26pyfnEq/nR2IItctU9dCHeAYGdiBgynZr6w1Wd9AWRXt7d8oUR0d8hCKnwtY+Bzhptx5NWYgZGOqFqy5AtEjo7PVWogr2AfMoSDzMAEvakM6IPQt4RRPZOCQjn6KzdRfgtJ9SE7FJNqPxMnmPnuwTokVJxI0gxIImIH0GqLVHMCvyckWG5adVmmBwQcCgwVux33SSxZ9giw0skWdlY8IT+Fa9YYY0NaBZP9mCXVKDeRBLCtBZ6MQMxuBPiZB5zIMXhqQnmUilUPmeZLBtGcZYrlOB6mL2KgNiOUPalO2oHC2CsqZ0HGgj0DhbwMmT4kWdxXaQslwCe3wUqFoTy9rL1LtIsu7nR0iVQXtxTsIJyF0Fm2pehfceKjzhEqznHLfkQF3JUsOkde+CwL1SH9PhGBrUgUYK5baVOekJ+iUu+eUYQWkPDKZI89RxiPiCpoCgIL1jVtgsAhWdGcYlTE6dBhFBbicPDmoBoTkPB+3BgwKcvCv0WilxzoMbW0srOXhVA6zuRY7I5phQBtH1Fzyw60i0xVxPkEMD3Gnxclzu/z2EtlhX9sUjaSKHZaDeoxzIxU/gAojkmkJ3rKoSKKdjaUVH6EAj8KVGnVF87n+h21keEDSeKEj9fslAqaS4AkF/NdkvX5Vl4A7J1685nI2fOz9q6w6N2oFVhfiH9kSEYjkVoPa37fws+Sv5fnwlEjEpX6Omk92Qd8JlWm8hRI9turr2TFu5EPZTxCs0EWyP2h69GsrjYnO5KU+rwau/p4Nubyikous1RW2+Zh6+fD3PTSTZtdXfuVLrq47dElUl3cUoS3XjF63e67bsRq9uphBhS98wLkUO8KK44Z+c1QXSD0HzCgPseHdoAQ7K6+RRvt/DnRdulU4DQusRI6bAbDqXpzss8oT8RHjRIhQrctMMxCgPUFw/aMVJAmspAkB7KouQvtKEtFqVs0lVjMZzMWxW0swhXee2k91wjGzPl1kTYoxx6mZxZgvFXwyjLYj73oKxUXkhjZviy8y7YZNLHC31jtRaoOS8LFicdb/uwCn3eUofSMP7iZV9tz2mnnJYlIj6qseufZHuUpCXy5Y2BSxuwTAGUCNdo+AFMl82ZYQXS+BGzfA2RRjrRCNRNeT7In3XqhAhTFS6l90Q/nDA8Ux060vgigu30Fy2arx7tuK1OeM9LQIeerfZTniBpewS6pLmhqd6RaJNU+auyPKPyNBXYc01ILF7lPFrU7QtejWMQop3GZfc0QSIgAbeEXWyNU4zlpQm9B52w+yjOR/yAD0XarvRC1BldJGrbgZ20b7LUJRiVFLtvWZn5fHZfrqR1dItXFVlGOKnuS9C7EB/42QYnAEMmO+NWRqQxf/YxBI0LvM7S6VHve275wToqb8vAxfTGGDR5qQRJByKtSfZgxI93fluRLsMp9Ya6qU1xigegbIrSpcynt+1lC2kofdIsq4jiPJAGVyoTsJH+cQX3hh9QhoNnjHsVNhu179J6JmFCZTDg3s+sMlCIw2bAsmaiBrhFy+vz5s6uU1+vwSHHKyB+XczYpIblSh/EU8myBbOL5axciZxXHiFLCecH4rcdnLeNWq14UzcE1mUF2rfqs6ck5+xyAAYpzmYuUSuLr1bTW9ElkNo6BPHPIrhpRoVcRT0qlCsIzRnKokgdBvHRuLgcOGJEkcOWpLPzJHoHIILlLqnBuVI1n23gHyM07keTg6wKx2V0AXvwW2YlRNh9L0p/sVckle0RpAilfAsUNGe/ATaNUh4+xtIkjGPyWIxa5h12K0HyoJpZnDEoZlJil3a5NyHCR05TepcdhKMp6mKzqhIzHE+4tr1y8c/k5nPvCfq3Ch3NmzpcdblQlvmTptuyrbgBud7Cy6aOLT+3oEqkutooAMwjp+daUmSOsVIPeiKSS5MZC6vUTeVBnRxShg+SAVIBS/l2eQ+QNWMUatZqQ7BLyiWwHzMivE+yOtO2vklcIYQcAF5KwJEPAG3moBo0mQAU7p6oGvaPVg4SVXyJq5aIPRTAJIz8RUUi7E7gwyr/ZBcaPiEULTQAcomGjEbg7biqq0KbGd6GBjwaqfq5xLMBVsettbiEoThSG1IQYwXYmQDWu2R0FyPVZBtn4We2zlpAdUBSipBUVS0q1uqKQ13wEf0KfM9JDSZi5IIAYhdqwuAmEkO4BJCzaU3pt/BTwpQeMwGFwkmSI6KeQ59uUun0uiaibajWLCH5ESK6IN6HdlWvpC7G6Kccyhsk+tY63CNACbsYobnqwJ/GO3Ddi5DsVSC4YQYOlqhO2U90nUg1zY46yCH4G9O/Xdv8r8t1l3KFgE8S5co303xHmsyyrQihCbk+/axwnAHhNSOrjHcLuSqeqyWrelNDuyiXJixDUb+24No46I+AWx2BdcFmjEEwY6BKpp2x0iVQXW0Xs5iHEisO2QURAqqVzFmNaSgh2X208smrBpoTQu7tWpYAQpNkLrFXcgHBLdqtqhukRkkNGfh3wDrCZ/m0NFBDe9ufhKjMQjlD8nGeUxx4ulwcg6ZtzemAEghlQYxvFsRyZ0apRctAk55sUcCWaC5hGsi9Guba3yAvzE0lW3AzI7m7+LSRXS7sN6/lwrsrZLFUX0wd8qUTsEcfKQIBswIit6XF/GRY6qYL3ICCJJ5dAsoMGd2fBJ61+foXw44pTDzDBTQiDB1T7SOeJm3pReVdjYRQiWZCoRUp6FcgODdh4FNeFp+ZLua5WVd7bwl2ECqSaRWeA3WH4mYG9S6QlRPVdxo5SgcNE56s2zJ5jpYusJIEhQe3VrlmAGdnV1PBX8A4F7iNV7haPRDtAUyi1JSjR/zIdcVNxqSiROWwGHsaKwvllkLnNgLQiRQvjLRyy2rmTyKmvOvc7EXWqwDb6c9tEsFTyhRiAd/HUjS6R6mKrSHYrCOFWcH1msaTwU66qKCSQTbpfwVqNTqNa1H3y3ITA+ypiWYcLlJ9jBhD4ZVeMXJMVLvB1aCrZlwc8q/0Gc7O1n1kqFVwCzgHFTXnTtrtAdlApi3vlPFEKQLWQ0j2Kb6KmL+fT+wyDcqzJ0txC2LvbIL3i2610SukAZOYFpfdVcBWgnWgqwyBQUeDbGPSfodWe0OmmESEbLG6TkiacUw8/E+gLAEoWmxcAqxXEIdW4eC172vLumtYtYR5KlbOys8muiHdhGDdmA7+jyVxP9r1q//VrZg8Z7pzgZ8rX2lX/vIK1849BqYkCmWGbbqwQWg1e5VK6/5h5gX8UKpV2yK3jGCJ4G9oDhskVXt/wSR60zZLDmj7WhUBpRPo3by6Ns8MsLz52H0jWJAvlCNFIvA3WWxW+EJg33FNPNha6HW9DhPEOsG0XT93oEqkuto8ncc+7C+EwhW4n06NYhSGzXGunDhMF2MD2GZwbqUjVH3rCgQVIFhi7QzDaHeRzIQiHN0ExDG1Chn4qROb8puoY9QGnZrfVcWoiqGRnIqlOBQ+1IKbpVJHb7kurOYDY1WZmlTp1lmnypZIE9cXAJAZehUZNKl1+7kIrHYn8vc3lfiGhqW2j3onGXipl7ISrYaxBdrXqQGxsc0XiU4dzGlHLAUPXHQAknhbUuOe3RwmQHMmYJPsG0I48EKuoKOBGHoOBgckM2Hu4MUcfx/o1To/kWhWnColNOPL85iPZDdYdAHtJqgGAZwAFwcuhQNQmlURufgFvwKsFYJUXV45YrtkSyHPpOGqUp4CbefgLghlwq/TCqiASuJxL6czzEwb2alXCS1rUy5HAmFJdIxjDS6s7oTuRKPj8bU7ADi9B9XvqqRRdEvXUjy6R6uKOBnvhsJiewiX9xTI+syyQ7IRDBBIIhZ3yQFQLimy7LhQZ8cIrpw4mAQAjvmMjj/ICSPaUk6HO6+LphQgZUo9VC0lkCfwEsPfUtk+E7KrRFnsWpeuCG2/RwazWzyDwwAygfYIvvCwSFLquagTxc+FikZHuwFBtKU49ihtSlUmPjHT/KUyZHqFVuTyMdahIReFMluoDDKOcMGxGQvo/RONYyFBrchbFKece/m7CkRs0rxsUvAeFWC7XNoxRuN5tFZjkQLq6rBNYzKSAOyXlEXlNVIF038CpZhgZSVbcKePipgOIkeya6NsmkBYHvnaEOJedS+hwa4NgAu9pWZiBwIiAVGCDye+t6H41QrlsoarpZ7SV/AgAMa7OZCxNY96uroZtfIhekv3QUUk9BvsVSbiqlhfHvvIQ3HSY4sUM87NLTLq4s9ElUl3csWAnb51+IglSetje8eenUrUCxJ8v2amqRVIZWPxOIBKbgTyUeeYx+VNJjAbPdCpsCHlAe6jSORD8u0wmkKHPPfLrBMCDYGD68mCfTyooIRUEFdNW5mYyY4dKAB8xYABKjSYzAJcCG9i9uQpGrYMpP1ZitGWUIy98mFIhmJTAM5FayG8CJsgy1Ba/4tijPBd+V3bFVB2HEMgpvyG2KabP6D8gyci6CF17C1CnqwySOYcImM5FBYvqL7SKGLrIuJQ5EeAuZo7k9lDpiRZAkEYDdlq9KKTqByPX1JeM/ES60nwJmIEHFxYIzQgHwlOiObNYP5NKaXkh1RAugOwumaPJkchZcMmY3fCwKcHurhaiDQbIIUFm9vCFJD0COy8mo+Dm39jL/VLvnkv2AWYh3NMaY+t6RFi9ZOFAHUCqtjV199hFNqysZiJMze3H3RqhWjqQRDrZXc97sn3A9aW6W55jI/FcAGqho/fx7Sahd9FFS3SJVBd3LGQxlySC7HLZhIYys5EHpRmo4OJeS+KVqz0IpHqR7AP5aZV8FcfA8C8oodZq189QtHZgqocvEaG4qTpXRDBDId3CSDt0G+zoc0mU5rlNZAjwctxE0jXoJ6TQmiyK83BMgH0oAcqxF2PegmUbqfDH7BCAFUipPEPD7DXoQrkpI7/BaqcC+F1d0HKKZRgOBr8OEWpbF42uvVlFKg9QKjOWVhF8oW311ITBggo6AOQ3PMxIYCCyqrvFqlHUk3P3pXCnxIuaYHelohISsPQK4IqaJhN0rGsLbJugqy+k9T8kLnW7E0CqkuWZal6Vsuj37l3UavKlzMXGeapmE+dybFwACTdhzbq6unUVxF2eCaEeJZBeI9ieASUqMnqoQqYkYzc/tvPhRkB57lGeIcpy9K7VmijqXWTTCu7zE0TR0PnjXhZEAUqlpRXThTDV57ZtZLEDArokqotPUnSJVBd3LCiVt1R2q98cTU+hIC/kUfaiFyWVJgLmSaA1eCZUPNJDxuxxIYFnV2WbWYOf0f6GLPwkRIFIdrSwjxDBAqaCB5uLRTnS5EmTjGC4CqolIXPnHRWmC1l0KSPYgYmaU2GRpEwqOuVIOVX1qoR2zjmH2LVHpoJB/UysUAjS7ZgMN1jkIPAMLnSbOnYBCkqOSKUxJCERfSyVXhiqlIJ61PlptRiHziU386LHNCYQMZIA35J0j0UyvROZBO8Z5AEGNatpDNjMYPigJFPJLmB6G2BEen3JEOyeKHc3rlGEjhChJG6ZE35cnaebSjXV7sh181PVwELLd7n9Z/Yit8Aq7WDvrf4WuiLLc477LMfaGRksXFBLCIOsQiGV4fJMvp9dkfGhpB3ua7u/NgrS+2lDnTmTVjy2dZUlLhmlzkW7u/k+Qrgxx7l52RY2XTz9okukurhjQUbfpNeYHftCiNxWu6qChQjQDu2Znnav+Sq5cBcGw2cCZt8jSTd/vU2PjOw3Ex6XU32gtrfwwH8JVjmYq3LYPgGe42JiUkJ6bbOHfhBhDLYh8115ANSUdnF7pg+kVwySA0k65uEn05NOwf59669FiLCgA1L5Cro/AZYLHnvFMWCHHjRBVRGbSTKECRDU5kOELjLrCbPHAJdDdJ1SrfJRc1ENsKZNDdIrFDlgQLjuqkB/RAvmt6siCJxyqWbGcxVGMwQSFnX1KFa6u7gdShHPM0BuRCpN0Jdmi4XmCMjfrJOKYX2uJXtCLjequdZ2vcJ4shMzaj+RRgw3lWpV9G7cBUBCyC+OtfJ5xsIZTKmqIs3B1GYIWKbW426LACEWpwwQww6MeBhuECajhfuoLcoRYsMKpdtxxCIUDXlhaYOiu+him+gSqS7ueKxauOs+b36qHJVEKhhuzK22JkCNW1MyynMvuVZJMLwdRmDSwDlRPsoKGCPZAUqn8GDtQc5e4Zt9wKSmoR6+6ZuzeKJp9a6lI4udetpBSNlmTptJjnsFuZe2Ox52iBAch6pKWf2uvGCYRKpJvhBD6XIssByY0bvHyLgSIDY+lR6YJB0GvXs8yp78Pd0jMWc+A4onpJvQDlXmoGyKuYYIYrE+eBD21+sq1SMkq5VtDSNR+yIiAmUehkVEktAuRmsHFM9zQd2c2pOvVX8zqUHvbuGLLZNrsH2CSeT+cAofl6qeH0VWg3fjHmCHBmCpPNk+YX6TC/twVdJiB7SWBO6nQHHqJQHsA0QM3m9ul1lU4rkUlfil3Xyu5l9Zu9516G9rwUyS79T5d1108WSiS6S6+JSIAEMANSShBiOYTN7m/QRwttLgqcMXcQEsZIFPDzfX11l6XCXHRWkeQqiLbtYj6POQFUHIW/XpIkONRYKZYzeT04qPLz2QELKD7RLGZd13S48lwD4qJ1Aci4m0ScVaJN0n+Jkmj/1KeZoLgSHZV8KP5RmLhMMMMIn8XqBRg+yuap8BggIEvjJ9PV5VkG+cDwuc6CbCHyvOPWhESK8QbLa40oaxbFtIG6bVE6ksuSlj9jGOhPD0CokqeU2NOppJe1Rm0ku86hrH0nItfK7JYCYvCet4SZQoh0y9Du2Oiqe2wMhkCf0HpFIoAp2rjzFopjHLvZAerjkn7fozKoRrh4t8SM6r5MxdtEPdzMr18zLP6hXGIOJLdntoLsDcvmjfbxddbBtdItXFLcXzHngefuH7f+FyNqZGrKHTJxiTkkVVVHEVeRym9jkV9QwJU6iQzENItxqx0y/sYxO6TeXJW/mfXUJwWXF0yCpR28nCGAx812+k2g5pdYgISxW+W79fs6OhRKEgg8Xz9GEBhjYNyGe40O24av9kW44hHKvTc1ZV7tiBqHy2CK3q78IxMocEsH27jW0sOcdwzdkh6huBBU4iW827OD8JjReAtdc/zH0051cYo422ofsHaufvl1yTts8vC0a0DoKvXa/6eS/7qm5/6TGsuwYIsLB8Paix3+543gPPw3s/+t7bv6MuPq2iS6S62Dp++Xd++VK3F93c9YEN21KuN6gWFjv3Pf2ZEvkuNAmLi6HF5po080FLfm6JeVPjlQtZ/JL+t+74wtj4Cg6L+0Bt4Vy3meC1xpBuMl9BNRt1ShEayUKE+7hlcTXyH9UI2oGAHD34wni1HXs9sQZighATFZ0rdR2heO1RG495Wh23bGN+v2n1M8K2EohXnEJD9fGqyzossviWhCaT4fPM1fekG1NkGOovBHGOhQRYK2AxMQrnFJKptpeJ2ksJoeX8w77q29X7jwhrrZaADeYS1ebLssEKc3qT++OS4r0ffe+lP9+6+PSPLpHqYuv4+f/08/j5//Tzl7a9KF9AQhJexlvwpfjzBZgNrlIJTw6bcgJuXBFKTZ82JrvOR9DQWQchuKnH9M/VDmNI6N29mS5TUGS2Q4q6PcuiPGPkqhRthxR5JrZH6D2AVhuZt3z/W/DiZ78Ynzj5BF7xw6/A9Q8fRw4R9ZXXZEQ+YJX7fICtAoQa1MXLU/l76L5jr1pXeg3dlOHOGLB6bRW+chMZVzOo+8xV+2iOLaM89XKcRwx/Lorlya7ARuxZ4FTl29gBoTjzKG7K+WX3NOcGM0f4NWzjyYaf6Ry2lSn3lz3/S/Gzr/0XKIsS/+Qd/wQ/886faXwnv+Hhp3ItkkNpdDCJ+NJNPuLgc7FN6t1nBELNg2URqxyH8reySnfN7gL+QpMyEsmEeVitvKgse5JdWgo/lueizA9UZsx+JnZEq+bKZYWbyD1sEhHY7RTAu/hUjS6R6uKTHiajjTpn3LlyQADt1CFkd7V/T7RrEM1tNw1fSseR0c600HG19tguIEKfRdV1xU5EHMmyeMTZpodYXSST3cImFyLZJ9hdI0kQAWZI6N+7ety++Q3fjB//mz+Or/uCr8NDr38Ir/4H34A//vCfILsmY+TGcgyrODhB44gA8a9Lw5hIaYoLAMSViGo0Im6a0sbz9pVmUuCpuJE2E9imuKifKdnYqjHxuUF6FMpiEqHzr/472yN4vW5uBJiauGPoTrs0zBUqXVEz1/72r/p2/NA3/xDe/Z7/gv/ll/4xfvNP/oMed20cHKKYZHaleoHgUhsMGA3jZ0qqSmusypaM5FDHg0QfinMATjrs3IVwtepkbjsEwPr5FV14dgcQwU7tKhw0x/12hx1Q435xU9XwGmDpy1YXXXwyokukunjKRIQLCGuhAzIA9RjGAHZgpKPpQoQtkwMsJYCXJ8I7chMgPWKUZwC8qGGbjKpuOUbs6AJkQbR7DDCp3Yq0rQdTWNP3cVEMlS2fq2p1Ctir8p24fd0nJaI9ZJQUTGZ551fYJtCsnn33T343vv0FfwNf+/xX4v/8W/8c//Tf/WO87bffBmB1V2IIzhEhq9ABFsL2CejLMYp1TSUE2lANL9TiJxgpx64puRY+93r+kkhQpmNxKtt056Eqwgvt+eylQmbS2j4DrKp8sqCUTra9CzIcY6yMHtBaEnbc/9w1e+N3vQHf9KJvwmQ2wd/7P34gcm7mjzvZJ/ixzNNyBHDuYYdCLE+d0a7BKqmMCaMXYr+fSSIUYG3TA8ozinOgPIMkuARkV6uxWdU9WI+2uRaqx2RXi39edpQjL/tNCFy0W0N10cUnK7pEqoutg0sWjsYGpXafSyJBKdbCAey1k2puAQuLrN0jUEYrF0P2DHaM/AlJZISwLt1f7AGecVRbbj3emVSRTCZdTeHfbsbo3UNws9C6T7GjC9ButcxEiCsej5OF3zkPHgHMhOyqfX8hsgAAIABJREFUFbK4Qlvee3BB8Co4GnhHbgLAA27ioxzCqoXLTapKT7JfVb+4BH7m1/4Z/suH3oe/9w1/F2/8jjfiS579JfjBN//gwjaCuKPdRSRym4GqnxOW2nwED8T8RoAstTpSECjjmn6SQJjpFU0QtVpohwR3LoluuDY+1/MxUvEhAsxgEaoKWlZkICbEwex4T7nMNZsWEJBdkTk2Pzf9pKoMuilak422ue9nMsbDdIg3/bU34NUvfiVunt/Eq//Rq/HIjY8ImT7DAnlKqnXy3VyhNjdm2B2ztGJGRjhtNgHMgMEFo7ipYzugBtH9yUSEXvu1ecQCtXknYqh+RlFXipmFT7WFAOemUY4keSvPRUD2dgpostOKd1fx6mKL6BKpLraK0Lo+D8Es/bwuzMgVLluRABU3pWpR9/kqzzymj8nDrX8/kOwu5x6FbYgdSfgdotlxOO6V1SwikOXYmeSnyn85F10kkwKcE8h4wBqYAlFnaAECNBytVIoThSYnBNurRBJ9wXCnhMkpYDJG9kAwNJYkI39c4UHDSA4Bu+IBX4cH6z+Hc3noTx7C637hB/Br/9U78KoveDUe3HkWXvcLr8Ojp48ACC33Crkdx4KO6GANaC2kQmlIviRJ8aXCq+NK+iB2qNnmeAUYJ5gakxHPO18IVJXcD2R3yYVjZlEQh/r1BR/GQMYnxuwxSaiTXQMaUPToCwRvSubmZqYQ41QvXQscHAU/1VQ6VnhS4IUPvggv/cyvghsBb3vn2/Han/0+cN8h2Se4VO1lnmDYfU0u04obBr0+UonbbAH3pZyjn/kIc3Mp/CwXZAFSxJeCbRID9pV3oi+q5Lk8lqqjL4B0vzlG5YnMH5OuNnK+lQgQqN0RiHLelueywuc1bbZ9LEDSXXSxLLpEqoutIsAGweNtXacYWVnEiFZ/Nra5Q/VlQiKllQxA+DyrIIkIKRl56BILETfZQdTZWVdJCzYsYq0iRsZ83VeJmSGk1xjujAAnUGCogsyH1+44d66wklZBGB5EFskRA45QnHhNPgDDBNqHGDCrwjoVyo9Zk7TaAaKlTV2BOkJCDvhY/hG84HUvwPd/+Q/i+fc/H//g61+P37v5MH7s195UdRmGdndSLaeRjCGXFWzZFmLngghX+okkN2YgEGiodK2K8rwS1mQn2zR9SLdcGNexJDXyIVFND7w2soT8xMdGAxiP5NDA7gEYUaONnhJNsBQqJit2QoD8XJ7LS4MdSBUtCpGqZAFZIMkzvO4V/wOO7FXsH+7hZ//Nm/Hv3vtvRSmdg7aTfo/F95HUe89P1aakL3pXoaKzSZTngZMm42L2SauITTiuzR9ybQToVe/v4C7gC1aPSCC9WjUOMHN8LvhC/f8ukRie7AAlS6Jt9zareJUXMj4h8drkO14hbEAh7C3U0rt4ekeXSHWxVdghRa7RJmKXyYFAACZZX80wPTHpjWKbzLC7rH5yhHTNmyilkvxwyciumgZRFWhChstgxPSIKr6NUQPkE60YOILdhxgZr+j0CvCP7QFFoXwl+R/skJAeqrcZEZCInUv+cQ/KCL5Q4joAy0B6YES0coPxJluRvBf+pvsCgNKX+JFf+od44We+CH/nlX8H3/d134tvfPE34Fvf8K14DB9X3zYPf64E+S1ECwNcBRC4zygnHDlWyWG1oDEL74kdYPfaFciTI70+Hs2OxvpHqb7P6lxNT/ZrBxSFTc0crybZB3yvOTcj4dtX1TmB25SPdK5ctRR46ee+FN/5hX8LXAIf/PMP4Yd/9odx/eSJhetkB1BCvuapAbodSzLmJjLnN+VkyZdZIOYEyK6ZSGT3Ra2zdcOkYz4CGd8XFXQdKoh+xjA7TdshIk0YpyyG04aq40huzQuvcTzJ6gS+LfxYK2pTBnZoo5XO9hXCVji7iy42jS6R6mKrsMPN2sVFlVqVmTcokROFh2X12fJUkrDeVSOLKtUXOWjnWvX7TbuxuGTkNzzcRMxp07sq3g07WfS4RmhPBhY48vAFMLiPYPtWzk9hu/oiEWQXiAB7JBY30mlkxG+uJdIDArwkV+UZV4u5w0bt+W6skOjO5pUAuwM8/CcP47uf+Jv4hWf8X3jBs16Ah17/EN7222/D9/9vP4D8QuDN3j1GOEBuM5+1elBCQCnj7UqpDgSLHz9VzhIAjAhGF8pkD3A2dDgaJHMLmi8YvmSB4jJq7ToT+QWz0CW5cHy03KNNlLkVrspUIqIvc/mBqw/gJ77rJ/D8Zz4fH3zkEfzkL/803vyun0N6hdDfITVerhZjSkSCgwignpg2UyKLtp8KHLaNThI76QJNjwAwGt2AblTrbM1We9BFiJTVX7BhwUIwFO4zFq/B/eVde8kexSoyoDB2wQqb0lJrp9sVpqdQftCW2yAo2c6fsYsuQnSJVBe3JcoTKfG7CYQkfQul/jpcAE/xgeguQvLAMDNJwIKh6yb6QL6UaoCfAUXJsLsVX2f+uEWAUr3zhgQ/EVNjaU/XDrWkMpKtwzgoQ5fVmmqclaTQzcRL0PZVj2mDzio35QhB4bpAkZtoZrkLObfzkwv85f/5L+M1X/oa/NBf/SH8lRf/FdzN9+Pn/sPP4V/9zr/S7jvAjSQxTg8Xq3irQjrqtP2+7o8WVM7VS43LALUhdqDNh88Zk0d9rFAtg2zWdTZuGskhBFLU4+4nfbzhv3sDvvYLvhYEwoce/xD++zd/D973kfcJ1KXHMt8JGeYrACSm0mAyPQZ2ScU1t7g/FHoTmK1ZHYrjnVWyCYAYCPtZBVMCksxGiNQvco/mj3sTGZB4iAmAUIXbzr3oUiLZV1udbce2iy5uIe6QXmwXn05RjpTUPVvRIrTk2cVeKgqbhN0RSMYO5kQ6CbEl3o2EIFqcMqYf9Zh9wql56/J9hGoGERbf2OeO242ULwFqWNYEMc3yTI4jbrsvstkmpVitIitJni9ETHFxUKRSEVSjKVGfQFvBNXUvwsbhhuOZArE70W0wvjqGpY7fL77rF/G5f/dz8VP/5qfwrAefie942V/H//M//kt8zRf+N/DTirTvxlwRt9eEn3H0rKO0+Z2giVSeM8qpw/QxDzf1MqanHOHNeriJjBWrXte24cvl49h2faT7TxKk1/2l1+EP3/CHeOV//Uqcjc/wPT/9PXj5//RyvP9j75exLIFyLCKgIflYF2FurDTxdovjHeyUYGXeFDeFD1QfbxOSfd1GmBduxJHTVJzWjnWDXIP9ijk8F3ZP5nB6RRLRVXP4MqN+jdeNbRddXFZ0FakutgouK+FFPsNSIc3kkFQRXLkSqcAxxU2p+Nid9XIIyQ4JvyHsm6XyY3ekmlSqZ4WfAJTIIuFzhfladGbC98kQevcBfiyklTr8kx4SnEKSQcU7dgz1q7f2RoecWmb4guHOAIAqg12N8lj+Pt/VFKBANyXhQhE1rG+Kmx7FqRjy9u41kX/iJ0KatnpMsrZtDhOlB4T8JmB7UhFyY4HEfuT//RG86VfehDf9jTfhqz7vq/BlX/wSvPcV78Pf/4nX49//4b+Xat50s66mQBaHlc5Ezhl2V66rD0a4BTB7VOaHLxjJjh58iw2J6QnfhguVOdiiE62t4y7Mh1jJzAUKSq/Ice/2d/F9L3stvvzZX4HPftazAABvePsb8MZ3vLE6R5aEOqjFJztVp1u4/hFyNauhxvmIXWQsXMMw3uV59TJSnIjGWBCCJZIGi0YCYQBYoDxmkXqYKOyl1SLTaxdkrR+36eu9W1ZSF6uCqILzipOKzxXG9nbEsq7KLrq43dElUl1sFwaVmOIKiMckBLMLFDcVmpvIgzkkCXVj33URrFB8ziKNsCtcDdOXBSS7xvAT0jZwgeDm7VbchbTTm7QiPbctHpTMdT3tAiWEXGz6iG/uZDmORfh8MMoFVCOpL3AYW49SCcAeaHQ1hcqK6bHycKjBRZJFWhLH9EigmfJUOFEYA7wrsFn/XiOVqA2hjKCoXbd4CTGajvCdP/6dePDag/jRb/tR3J3ci+/++u/C17/glfjPj/we3vb7b4XLi7VdTaYP2JJQXkinIjsC5wTsVNCeyQAkmnhwsHxZsrD3CeYeJepvCRXXO+58wfAqlsrMUsmbCHTFJfDMqw/iR//a6/Hcu/8i3vveP8HHHvs43v6778A/e/inMC1FH4FdEPhUDSsiIFZC0KjwiLehNDf4sp1Y3xa+Zlxc7yLzpcgNmAQwe9K5R1Y5WV6kM+rjR0Tg0qtRtXQKho5F25d7pW08pfsV8XwDSV6qXpudgzQVeDABBiSdiS2rjp/JC5bp33qi1bzGgP0kQIpdPD2jS6S62CpCKz2XWCpq2fxC9f+mB3AhVZ75hdJNa+3K85Uqhwgj+onySqBv6CSJEw8QOTNtUgFuol08+WpBzoXD12pU8QSkA60gJPuM4kQqAwStUpUMSlj95iThC8mfGxPYe/CUxJqldmx2KAmYMabVT8wMCXzOsVOsPqZuolW2sbyBL1ug/YyRXxdh0OxaZdli+1SJbs7pF7FnfOBPH8Fr/v63YmdnB9/+or+OL3zWF+JV97wK3/bV34Jp/wL/4j/+c7zzj965fOyMqL27qXCfXAmkV2QRDpU5u0cwfQM/YyRXtNJXNyZu2SY79SiEXvMNKg92p+q4A3GEmtxI+TTG4Bte+Cp888v/Kl72xV8BIsKHPvpnePN/fDP+9e/+6wW/xuKkEgE1fVnEe/cqZymtkoEIAZ8LeT/ZBdKrmyWCtg8RaGVukOqNbgdGujrjnLcE09LZGqBekwn53wyEQ+UDD22DCibZqjNvG29Cp75/fizq/W0vX+KlKMdoPW2ktt8W8RpbaRQQcV6FkTuIr4vbGF0i1cXWUff/WhfJPhS2Es6GWdJV586V5F0ybH/ugWsr8crgGZYeUkNskABgVYWsJ2awgZuzSbiptNAzi45UgM+SPbHo4BxgMPIbHBdGgby0A+9cbU+8vPlTQkjmFiGTVn6BbdyT7Brgdgm2RzFRCueOIJXNulhqlcGNJckNMFJxIhUxAChSwNb8+ZbapUyr5PViOsJP/tb/DvOwwfd/02vxHS/6DhzuHOKln/+VmOQTPPTHD+HHfuXH8PuP/P7SsUz2SJPp2jEmQDK0SJ6h410zms7PGDY1Ar3uNBdCN6kaEdyYNtJKMj1CpnNHqqnSQPAVL/gy/KUXvxovfN4X4WB/H+ejEd736Pvxhl/9p/iNd/8G3MQ3mhGqAULcVrq73Gg7QsBOdbkcyw/h12NVkh8uJhliw8JwF6phpU9r00f0bgwdhatPHrA9I913fZlLzMJD41JecDaRF5jvzNsovJLie1hqjtyAcVs8JwMEuy6a15hR3FAaweD2iXh20QXQJVJd3OYgu9kbJiXCoSGLhTdkIhLxSl8tWHXhQS7Va623vDqR7NUEOVseyvPbYKf2JKyLVk/sOESIVPSagt4UnPJrUqm4BQgm2Se4C6A3AJhl4aMWxWz2ytEpGcku4hu/+Jrph2oLeTh309c3fi+fc8ZHMjYmiHY1lEoVhtCu2N0WAXoDyzbkmBhvfMcb8cZ3vBHPve+5eO2rXouv/ItfiZd/3svx8s97Oc4n53jPh9+Dd/znd+CtD78V43xciXROK9imOK8EHCmpqmFhn24kcKZLvTYcNOHOOgy5iZZZPe4/uh/f8uXfgpc+76X4rGufheFgiDzP8eFPPIo3/sv/FW/97bdi7C+QHpF0uoXjnktWkn1N5FfMOQBVAmE4Ni74qSSHvqgSRy4r7pxUTWW/5VmVNMIy/AXBl/J9u9NOpo5zOUMkyyeHzfsHroIcy3NJ5G6H9Yrd0blvsNxeaABY1w7pyjVg2AGWyoe0BZc17mK+ORTZRRe3El0i1cVtj2Bk6woPmxJM1syUfMlwuQexGvXWFJODHk2yR60P+kD2ZQ/QGLG6Ayivw1dVl6jPxGIhw6VslxIsboNiHgHKgHRokN9wYA8UNxjZNcLwmaRGtwIdkgfsterYTErwiXBp7HA50dgXIlxJRqotMZGaVouBu2Bg2KwgmYRgDoRwzKxJnkdUKOeSwUZ0hmJ3YlKNC9FynpvJKumGtnF//8fej7/9U38bAPCiz3kRvvdrvxefc9dz8JmHn43Xf9vr8SPf+iM4Hh3j3R9+N97+e2/Hb7znN3A2Vnn4+uaodp0ySZi5AGB0TFMGs2l8KUCS7IUwvapi8cDVB/CNX/yN+OrP/2o8577nYJANIsH8+OIYb/+tt+NN73gTPvL4R4VMzeqjWEoSJdeBwXvNZCpUWdZFMAg2mYkcqiDAGceCEV8efFERzE1BC1yr0JXnZ+3NGo37oe49SDQnPyHJaXETAIk3Ynq0OpkK93EdulwXzJCkjRELqIsf0oR0bruh2xDQMZsTGPWF3DNtiSxD7Zw8YNc0tXTRxZONLpHq4rZG8L/Lb3jpahoC/Qd9hL8ASUzKYyCY4gZxRs4r0UY3AkybhxdXBG/21aIauClg6Uar8zqCECIgFZ3koE4S59gll6jKue3Lw7o4NfATBucsnKTMgBgAVQlZQz291uHoRrw0kXIXwiEBA/a+6vemLx1yXKrHWeiWm9uO6Ut1jEggGi5JDX+FXGyPADs00tV0LNUgshwVo5ctnpuSoh/+04fxrnc/hOlHGEc7R/iaL3kFvv5LvwZf8gUvxsue/zK87PkvkwXeFTgeHeNDH/8Qfus9D+OPPvYevO+x9+HDH/wovJPxSQ8M/C6Dxw7kBLb0E4AH1TyAAcxQOiS5ZKS9BJ/z3M/ECz/7hfiiz/oiPOf+5+D+o/uxP9yHNZU/3/n0HA//6cP41T/4VfzSQ7+E82mlW2FSGYviWBbw8pi0wihJUxt8tgqWmw+ZGwqlKUfNpFLZ5LKmpF3nh3l1Bpjo3Eo1qattoy3i/bBGbSDZI7BTNW9USXv7NjmaQ6/r2nMTSYbNQPXaQvI3pQVR17rHZuBR2r6MOdSmyeeqmF5LosoL6dIlApI5fqBAxLK99LD9BSyEnzHctLbPLrq4hegSqS4uLdxU36TrnTeqPxTUsVkXxrp+U3zgz72xCmk8cFra9xlsXPxME56gUF7rePJFU9y4DltR2tyGu5DFys+A7CqJBIOGUakAkwJBwMmkwtHxRaX8HTq6kApUGUxXl40VStHdAaQTy40lkTMZIbtL/u0uauc1x9exfSHXgvT8e5JYBW6XmwHZVY5dTb5gkBcPP9e/HEjHq8bTjZOb+L9/5S34pd/5RZiM8LnPew5e85LX4PMf/Hw8eO1BXN27ihc/58V4yXNfAgA4PjnBQ//f7+ADjzyCNE3wqq9/BT7w4Q/hkUc/guvXn8C1u6+CmfG5n/cc3HziBDeeOMYgG+DZn/XZ+MRj12GNhTUWX/FlL4nHwsyY5BN85ImP4IOf+CAe/tOH8ZZ3vQUn45OV52B6BEoYUJhJtLzaieHLYLllEf0OebGyhVply/TEM49L9YjUzjlmkbywO6t5UUSSnIXkYF3lKNkDSqIog7A01F8wnPsyqIxLhcSh90SfhAJF7fdw0CdjZrjTYCkl3MDgVNDm3cc14Vsu0FjJosYY6zEvgbOlG1iaMPzs1oWDn67BXl7u6vD80zW6RKqLSwk3qR6gia/apgOEkF4huHOBNOwcOTi7KhweY5uyBWS1Q9BhZZcdqw0J14xtTR8ws6qDrh4mIWRXEOGk+jbgIUKHwMJaEXzvTEYNiM0OqZGoFcccDV+TIwg3pXb8C2O1S4ASxMtTJakbYPAMI/wk9Wpjz62WKMDiAmB3IARzFp++4oZyuDwj3Rf+D7NY0vBMfP42NXdti+QAcCMC5Rx5WG7M+KM/ej/e96F/2Kii7fZ38aXP/VK85NkvwX1H9+HPrj+Ks8kpHrz6DJyenIGnhL9w74M47B3i7mt34erVK/jsz3wW/u2jv4nRExPs3bePneEQe1d28OiffwT9vQxv/7234wOPfQDv+uN34Xc/9LtwpYsq6dssjnaX4EaqDN7S7VWORBNJkmksh6tagojWflYqj1VzQvz9qFIZTw+x0nKlDjsK10+OM9lXLqITODo0NxBRw2qp9dit6ret69ojVC8pRLA7BCaGse2LrdHng5syjG6Xc0Z+Qzwel0kzBCkVsosQqx1COyppKS+rcbys70VP71xg66gbjKdXljeuPB2iS6S6uJyowQLzkEKyR0j2lrfKmZTQv6f6u9OKkB3ow9csxyjYV/BZOWKYAaLo5irfPUoo/oVdtQ1YRrJrRNRwPjkZ0GaCijVohUyLGW1trLyTxENMieW8g3K1GwPmQBPKJefCnqtKVH0XuSafUzGCDgubdAkaPW+VcLDC7+IBRTK8mwhhOV6DNWESg8GDAGDgc4afqGFxSQuw5mg6wq//wa/j1//g1/VYGeWJnEfy6yRw0FQ6NNND+Z6bMooTD1bvtt69q3v2g1XQtiKQti8LsxuJX5zdrToy6/PEOUkeUdKlGdwyc7RsiXM5zMHaLbAKgpuPRofjRKqnbgy43EeDXjsAMBa+3apIdilKjywLsgKRsoqSurE6EJDooIXqdH1eJXsEu2vkZSgngeVURd8M2iFmky33xTPpZp550Zx5JonpujnCnruKVT38kp+fhtElUl1cSpiBaMCAtze3rQf7WrdcLotVXGQPF996WP3uwAw7NLdWUTEVf8X2zPI27Q0jOah1dLU8eM1QxiqQaWcfB2xfldMPlNCbCcy3KqJBciJE4YbnWqEVgT3xEuSp8GEoLF7adWbB4CmAFFEWInYs6nbqBP6gxxUS1rYI1RxfhGrimsU3BYx2YFIiquvz5O5QWaJVbfTh3LmySpG5ga2qDX6Cms1LrXW+Nk9MIjIC2IBwvrD9QmBW02tCvpLoKnRmRCLC9LRrckeOBSu63wCFjH11fUwqSQy4Dq0JjOZdRXo3G+qqbRImowinhesAVj6ScgE5r1wRfMkoj6VCmh4I/8vPAizOcLPFsbqsoIRg19xndeX7bbsHP50j2QPKC5W2eZrzy7pEqoutglmIpGSb3TJkNtPz2SSkEwsAKTE8dirRwgPfjQgwHuwAsxvkCbbrLIpcjHI5F2ubMBktlRnwhSaFe5LI+Bmi2rTtA8meQbIj57+uVB66yoLVSh3usbsAnwHGGiRDAAHuqIl6JjsAe4IrZeFmpghp1q9BiDokaXm1rEXgBLkxw01Fa8vuSqLqZ5oApspNGyuJXHdnh4sJqEkI2VU0ujCX7ls75dxUScpbVBGYOfq1BXsUQHlvJcMMRYR1k469evhCvRRNZYxNk2aSCsjLApck3DY1Dc6uyr2W7MtxcAHh383N73B93IQjLJ7sVNwsAMhvePiJ3CuWRNbC7tDKMQ1QICDwoM+1WtRvEc+diwCzSRLPoIkor9clTnhWVdn8TJs/CqlEl8daCWoZq9Zj9dqR65Z3+kY/wvmXshrkmR7UKsm+VtWbcpdIaVAifLwuukSqiy2jPBPYhcx6hWZmXiDXrgsyhOQI8Y1dunPkb8lBS2lBiahkADjRnbkVET4y1NB4isanl1jKj4KTBO2Wk4TU7mmCQ9LBiAQNkvuyCBY5oaOr8bcWeINq3KXynMHQ6kVYMHSxjdegmCMgb1nKJ0PC7co9inPAjhXeyZVg7BjcpwYUvKrTbBshWLtDt1RZlPktCWayr4mAdpaVI62a7GJjPS6ged3tUDvKLBbEWYH6PKwqOfFHx5VXZdv8Zk0Ep9IY4UYKoen1zU98TOThjVj4rEiiBMrULjzthnXq0wcWPpcdyHVZBjHHFxMG3BnBBji0QbAHaKwvD8HoO0PswgWwMXTk80pI1l0sXqf6y0B62KykuGmVZLkxGpXI0D24jVdiF0+f6BKpLrYKDpCJdtvQEqoK+6pdOtldD8fUwyQUZyYRYA8qmGU+hPMRLDIAN5PqFAwjwa2ZbUXODoQsflkkytD1BO00MhkhvQoAItxZnnuUp1Un3zJD6BB2SCshtmXhc4abellohxThikXYtPk9M5RKlMwBhSDXtf2nAIdqk9XKWQqgkLlDCWBTIKh9LyiIbxEClSpUeItdRGF+G+1EIiKtUFUwIXOoslRt/qsS7noXWXlGatCMpY0DgMDDfqKV1SRwtGqVm5bOOTMAEm/AhehvmZSa/K5zgdbskJDdI/N61dwJSZQvWBomVOvJqLwGJQIPlsce7lw4bb17TKXXplY+xQ3lOvUIxlKEl0NQQkjv0p9rx0Om1oG44bwwSVVNbWtQifcg5Lo0Ero6DFr7bqxY8/b3WhdPj+gSqS62imSPhAibrYEDyuqh5aZ8y7wjgQYkW2t7mAbzXQDwhRcvv5KBFTo768LPqiTCzy6PPyLnQkJ10XMJD2YKhHrS5HQD/7P6992YVTZh0bC5HuxZuSoMn0sHJSVNna3oZcdSnQmVLenCEt9Bn0tlcl2yl+zKwulGEP6ctu+LWngFD18GLFyeVtBpdmUzTk15LuNhhwJztc1vkxIo8ZJkqV0Rw6N4nADLsLlZqatkdyArtJHx50ItU1bwSky6CGMH2x9fcCukFiDNMM/qMLXPJZE1fT3XmihuMAUPArWhSiP8Q0nIkl2A1KbI9OQcgpDn7BNSZRS1dY6ehF4rj2YAVS1fbqWzlG+3RviUNckNUD4l8nKyDAKO9yAWnycm025etBPcuySqi2XRJVJdbBV1P6tVEexJfPnkyuFVx9pGn4Ydypt6/SHKjrHMGiZ+hgXmIit2MBgLR6b+EH+ycB8lKufgA1wpvCGxQCHAGCR7i/vdJMqRwi1jkXtoVXtWUUU3Vs7NnnCiVl6feaiNa5UqhZLWLTA2M7BzOktPtsrXdi0iDMTr+eViqyPjYQZSNbNDap3fAeKCUUPilESmYiQQt8lW780kFMVk2SNq72xLng52O5sw5xc4gqQWNUzAbvOz7lw4bEY7VU1PElI35ZgI2Z0q8YrQmwOgCuJlLvvwU6A0rAlzSN6jygfYAAAgAElEQVQkYbdbwKGbBJcKdTI0CdbjWwEBr3ue1Lt5u+hi0+gSqS5uSwSy8Z0shxslL3NNHDN4dZlM/MZavclqXTmUcbS0sAOpqrmcwcajuC7VpN69Ty4R8JNKsR1ULQC2T9hkkWwLk1Zwy9JqlkJSZgCADNKrWiGaSwwjsTnHQmt/gFv8DE3h1fr5zVj84NZAXrcaAXploKHMnhwQvOpxrVNld2PAzap2/FBFaQv2qMY0WKRMKiJ1srv0qwsx7xt42RE7Oa12coaEmkkV/Dn+zueMcuJRPiEJEBcUeYjsAAKtlAWI88RLd6gkhmoObuXlILuL4J1HeQK4M0mw1hHUN40g8AvIPd9FF5+s6BKpLm5rNLyxZgqN3IY25hB2QFH5W4i32vGXC5+lHMnv7U71Zt3oyhkzjBq9lucV5OYudBteFozeve1SC2LNIlWl5HBJIlFLdCjCPVqlsFRtw8rit0kyErq9yMp5+VyqDJQC2RWqiN8F4EtRjrY9EggPvtmlBE3qlpnMroBbolccZGFOD9ce+tKI463XKYy3qLbrZ2ZS+eBSKkwAkO5QNaZp+/gFbh/1BSZLVhynWLkY2J5U+2yfYqXO5YxyBKSWb0t7/rYR7V6cKotrZcb0pDIEp0rpXq6TGwGF8vLsjiSH5ZlHORVNJzuUDtBVQaSwZQ4gaXY7AhCl+DJ03vJaLaoQzNqY4KUiOH9PUSb3O5eLx+hzgXifziKRXdy56BKpLu5IlCMVMyQ1R93wAVeO1M9sZ/uHIpGqJk+EO8SFavio2rMdIvJiTF8e8skeAaVAkqZXvelSCnCuvlxTEXysQwQBanLjqiOtHEG64tIm2d4OpMuQWRbl4qYQeslCJQOqbfgZrSTaNiDJGqcmf0K7k0gW0XRPCO2UQoyjE4o+foAIN5qMo/7VpnDsAmxahwJDsjHVTrJ+qLq1bGcOqnNjRnEqFjfJDsPuVDwk01NLGlSaSm7SPBc/UzK81e7SuaTXDgnlSGGcgqKi/bJI9gjYa15DLiviuZtuV5m61SgvJEFcdj+YgXZy2mbHWqgkhmBXXahwH6RH0jVanEnymuyt7uqTDcn/uRHkJYmku7bupXmrML871y67C1a/y6ZfXwV1zn3vQoVNCSu9JLvo4rKiS6S6uCPBdf8rB2ADArfPa4rjntpNi9eEqCZXVRqQdhvqzA+Lrx0CMLJAmqRqyfdjgXbSq0AyIhQnDNMPC1EFkYQqTFi8iAA/CW/h8vZcX5DqbddhUWMHgCXxEn2p9s6j+L0aJGn6y+Gp8FvK0OiWM9AuJT3uuu9YXUyUmcVUmZqk9KBZZFJCciSLr8lkAWan0BdXAqs+iFAuqLBX4xcWviikyYB3gKmNt0lpgeRuMkmgAIASBo/D2GIpYYrUtoR1Tm4qrdC2z20aEnwuumGmv1111hdi1AvI8bapdwdl9nVwOllJrEwmvCnbI7i86rRFqly9Nedl+oB1oppORipHJgGMdg0Ctw7zh3vTJJCXhRaZj9bvufADVnrtddHFZUWXSHVxR8LuAjiXTqJNidRkgOhndmtKBrKdYDCcVaKOflJBAuwrZWWesrQ6O4UOYiWJwBmDjEIeNSjI54hv5mRlHyBpdQ/J2zKZCACwe8rt6SF6mpmebGNZl5PsuIIkRTun+mx2TRSHKRP/OEC4KaFbzk/lzd2k6meWSAcaysVjdReoElqqqlURNi1YMjJ9mjQ6AFkI2aukMoJVSRhLk6mXmjMAhAQ934kYYB+yQhA2Pem4imPmqyrYguGtdqn5XEbM7rYLN64L09NrDTm//Am/GtKFzrUTTViniyKT5UjsdUx/sfuyfj+smhebJit+FviEwmcSkU2BiLO7RBJjHawsnYKSROU3ADtggEiu43zX4ZZcSbsLYCS2TGYgid3K+yF8bwjx3VyjAt9FF5cVXSLVxR0Jk25fUaKkUhxflnyx57ULS/yswlDGmsZDnj1HRIo9YieQ6TfhkCAvADT3Z/qqMs66cCeB/CzQXOA+LQvbJ9i5B36db7Os65BsBUnOQyYmJWR3t0A/ul134UUbSVWq2Wk7uNqKNBbQFrgOAExYfHu0NNGNfmaaILmxQKRBBgGojR+qhS90V6VH7eMWhGHrUgcNjtewgoBClySzwG9CMOdYmVslFxFP26uQJmQb4XqSJa0M8sZwrHdaGZ2JwbXpyfEy17z8xsrjMyKA6acC26VHtPJ+2DS45Njw4C7UTHxAUTYgOdgu8bFDQi8RCQqQGA4/2TBZ/Zmx+bGE50YXXdyp6BKpLj6lw6S0FAb0heodQT26VsgylOeindTmS0dGSNF+BsBUSupCkK0lTBmp/UYTBjIJtdtXBMhoQ02obY8bCHDe9tUUygisiUg5FvsSLgC7HwQQq+4uuwOACETNLr5kd71FCKBVtsEcNOUraKoNqlsbdfjGrx4BPwHKC692QyTkeyvXZtNKlJtUFThXs0NiFhuT4tzDj4G0Rdi0sZ2xHDt7AgxXMJ9WI02mUK2KaUoCp9BooZXGue27qfIIB5u9UAAALKJvIPXCda7U4H3BcDOOXn+bhMlu4Tp20cWnQXSJVBdP2WhAQsrr4VJa701PJQZKINk30TYi+n7Vkhufy0IllQmCLzx8C3k42SfAejHj9eu76fLHlbibAv37AEAqYRsvdgDKsYcbKby1bzdOygL0BdO+ECb7AO8ITlQeSyXCO4/y4wCDQcYgGVRebJsQqX0unXNk2+EtMqhUp7eQRSgvPODFhzBEgH02UjG3WgkrIL6Ge4AZSjI8L4rJXhObOZ2nMO4iZAqAtI3fKbSZAygZSChy8Pys6r5kaCKXC4fJUNV5GCE7aPelq3SQQnNEsEFqdMEWHPfBThJgIpK5fLA6oYtq3X6RGybJocKPEyC9a3tYbtNYNt6AJIjuXLohN+1e3SQCHN6R0J/aEefOls/U2xFdItXFpQaXCkPdBv2g+bB1SG2AyouMFYpRo9V06pHsEtyIQVlT8dlNq7b5ZE/Jt7mSxacUIQp2jOLEY/rnkhi5IWHw4OrjcxM5Ns6lG4oSXtpFBgRyvRBqQ6WnPBO4xCRAdo8HOyMQE8nxLhtnN5JFf75Lkll0sioZCkJ6RR5IsxuM2ePyfdNnISCPN1eldxeyMLNXK5K5Ckkw0p235lgV5ZnH9GNyfbK7PLK7JKMxGYH2eblmVi2s8o1Cpac80eMxgLnKjTEszxT2I71OoSo3IIAqSYXiRKpJpoeYqMFQhCjDeHjHcKcOxYmMt9nzsJmF6YlIJRcUhTABqDq3fn9azWFKm80EPmfkT3jpbBzJfLEz2SagXY16HUyD61dF9Kj8JMay8QaqRg/ORUmdVimcB+iV9b5YsrBG30PIy0TnnffUDeE5bub7erujS6S6uLQIEgcLYoC3KWgOUvM5V912E9R+XxFq56PuvRW9zILIXw3ac2P5z89k7Q7mpqsiPYIsoBmA4D8Wtt8yNOW5dkwpn8hkstCFpIqdSBaE6ppPl4s7NjqXal2S5bEcu8kqHkmA3nhsACdmbravcgRr3trdlKMAqumpdUzBcI9LVSa7h2F79VZ4gt3iqePzxZ9D8steEqNN5lp2laInoxupd17tWocIekccIMM6hNuTOeQLlsU9JTiVIsjulSTKDiqLFeoB7iaQ34RUrhiwRMjuDR53tPoJrNdQuuco8rH8GCinAvnCEwzJPSfdqTq9MumqZF/rltygQzBsn1Kt2A1W+/E9mWBWmQLHoJ7AnfXxnu8yXRV+HnpdYlge7gsuRAJlE/HWLj41I96rHiJf8kl8KegSqS4uLSJ85hA1fJZ+jrT13EsLPzsW49wWnlPY7ioOFCDbszvK9TlglDeFmNu71txnPWKHDyNaq8Rt7FSfC63yyb783Ltn/cM3PRLLFxhJwJZ1kVUHA3jlQ4XEoHcPobgBIGEYQ+D6QqM/M7PIJZjq/OwuAA5cIEb+OAOJvsGpFMR8O7oZAkku3U79ZxBsupxEDgC+JoLJBSG9IrDV7BMMlwPIGe6cnhTxODkE3IwAD2R3VfsMGlmkUgvrpAvEEkd/NoiVmvkEzO4B+eMAvHRn1vl5RCLzAEfIrVb2DOAKBk+kOaEuSWAHMqdSkrfndA/ofcbmiYkZAKas5iYgVZpyxFJZtOrZ1yfYPUJ6pImINl9IRYc38m70hRDm/UwryqpMftmClsUpg2cMMxRdqfLMg3Ogd+/ivpJdbcLYoMJdT7RWzQU7lIpoeQFYK8+eVn5jF5/ykexTdR9/kpPhLpHq4tLC7lDkNCzTe4lieQCSAyiJNnQqLUI+25biK/KzRXJfyzYOmqKQ80KFzW3Uzm1IWmnbrFWeHTcgODtY3clVDwLFSkmya2BSRnEicFKyS0gPqZEU1uUJ0iPtdkoIRitO+RNaqSs0GS1l0Z9f0NNDUe82PUKyYpyZtUMtmu7Vjl0XYKn6sFQVamMSPjMfPheSP2XN8TeJweD+2jZKSaCQMPw5gQfYSFuoHquU2UXYVDhZpXazhfOlsKAnQHbFiHwCMYoTEs4VzfOqCMmeETL9oXDw6nPHTaX6Y/porZa2zU1Akkk/kaQvOzSaaFTfcRORUKAeIxmqDMaaRMRPEKt0XAJkhGtIib4Y5ZKcPxleEbvKacCNOfIMqb+8orjpAml6WmHl1S9cQT8r6pR18ZSNdYbWdzK6RKqLSwtp41/94GNf+4dD1DVi386bCaV4XzCK01srxUeYa+7nbWNdRaweAgUKwZhLahVPXPxStVDVO9Hmj5+CsjerYvua84vdhonwbJYtqskurbXvCF1qER48VCuSejffAUkFbgb4mVQd/QyxitSmbB9hzaKCNReGR2Uakj3A5wb2mkBsxbEIeV4KR4IkufG5JCpurGKhVMGhwi2SagkHAdWCY/dbPeYV0RvnHIRKi6prD5AmCS6rCmk9zBCgE4JJuYKIPZAfhxeFiisEtQLapAJmekJWNz2ZX+UpwVgZWxipYvJ5uwjoxqGND75gXQQZPJOXArsEittq8xsmeWR13uZYkB3pootbiS6R6uKOhPjeAZSwVkMEuiBDSK8iwhHzEUrxfEGg5NZK8Xao7ebARlUhX3DU6mlbnKtzqRICN6na1O0ehIB8IYmNGzP8AS9NAH3pUZ4LwZtzs9CJZvqALaWzzu6I9hA7ID/2IFaycp9gVFeqcYxWqzwJYJTv0gYFbhy1CqLPGckhIelR1CUKcBlZ1ZfyMgaR66Tk+3lJC0pkG0RNaMaXrKr4lY6T6UsikV9Xy54LDzcyyO4SHpEklxy1q7bi6jHBDDmOY3muJsAJAGKUY9FIiqrdCvexEzjY57zFgl6DwLWiFHwWAYGc7YCjlVDYn90VmDiMlRuj6l7N5bpGmJ0XE6n5+V2eB4V6IDkwkpyVLJB3IhVS3lCrbeX51qBRWHnBSK+yQJj2zhJcTEYNC50uungy0SVSXdyRiF1kED+5ekViVSWhKsUzwNRK0l4XYRubBJeqTdUiyBkieIDVqyvSFq/Cj4UsSMl+BUWVKrxodmUhIVud9/RRWfTJAoNnMUzSXFRonjxLMo7lKUCWQRPCYL/ZmRXG20+Vc5UQEiNv4AEKdGMR8kyvbK7sTUYI7n7KVWLm1VpEbTyyqyKZUO+SND3pqISR6z9/IZN9wPcUhgrEfMcoQxcmRMpCOFuyTbtDkjB4Gf/8CUkO7J5UlQJ3almXZOv5WcAODDiX7kw/kzFjL3w7N5JtBxFQQLbtJrX5fdRMULnUJNA0Oy3To0oBfFkXZzAhhquub7IPcL/Gh8oYNJMhTQYEnzHcVF48/IhganOnMb97hOSA43GHZDeKqGp1EB4C86UsPn7J5uMZojyXhNgMVZ+s1GoXS8JoNrw/u+jiUzG6RKqLOxIL8NMWvJY7WYpvdHItgQHrHXFQqNL0SDoWDYBEtpPdRXAT+T17Sb7cFABXBsVkKmiOXbW9VZEeUDTJLU8hYzn3Qh+3qR0tVD8fLwuqn0kiVm4J2SzAVVyDbPX/hRNWSyZywGSSMJbnkog0IlR0GFVXH2v3HDP8mEApgyCk8VCdQqbk6BrhNHZfQknUZ4ik7HVBFJJnrTROGbwjyWN5IslFmwhoY37PXUM3rrSL6p2WAR6sh8lEM0k4PCJfML9NIpECCNw/IiC5QrHiSQ4C/aGaW36mSZnlan572Zbpyd9NVr2okCXYUBk0EJjvJqK8ie3JmG4Cd/tckjVm4frZHdmmn3KtUaAjfHfx1I0ukerijkSyC5SQt+hbIQjeqVJ87Pwrm1179bB7EDHIpFpIxMeOFGahaCOS7ALgStMJjgFNnoRsKx1LxTHUNmU9xEEJaRJFoMwLRDoHjYTxNj1ZN42hqEpudwBfEmzBjQRkWQShTRCQHtLC50NHnJ9hqRwDJZXOlJsw/MxLJUK5QeVZBRkGyDTyrHKGh4cN7fFEgCfAeJjk/2/vzeMlKcu77991V/Vy9lkYGAYZ3EZwISoyImhEAQGXAUZcEI1KlEc0UREiEYMxvhpU8uY14AJBJUQfUFEZgSQYjIiMwBMHQaLCI6AIsg+znbWXqvt6/7juqt737tPd51zfz2c+HM7prr67qrrrV9fyu8Rd3RuTfUDk3l9C6sjEkTzyKuKS1wQk6pXfxWL4OVXZNVosvrwJBubccS+L4NU7v+NUJSHuLrM5EREy4kfeUvTa0WtGop65+n6NIkjMEinDiGyDkm7kTOhG4lhGfo8IKDIS2So+v/0puP1ZJ9LkitBtnpF7gmUY+CSQ2ts07qjz5P0Vi0HOFYrbtehbGXZUSCmLAvkSVRoGGo09MT7BVHkvxjclaZSIuNvJAzgnESoQxAXcMMwYMLK+tRqRKLpFxsB4qLihL+zvKt1gnoxJ4SmplaEGAtVmooseI7dd6tz8qYLoszlXj5WovS1vVC68CAH44q8FMGje1bxFyyS56EbvESTpJJsF2HNCjkiea6TWjozse3+ySPSko5ScvEeJhlDpa8Jt10VtomLrWphE9eMO1D+/vTHXxUpOIOYKo40wiziK50/CDQ1GnPqt5Yck+zQSN64DMFvobI2sHoIZSTlzviDiys9vImo4FFy6MYHgCQsbMoI5ND0QODJiFR80cdw34wBlXAStisVClAqUAd4arVIGGxVSSltw6Fy4/eqt2w2fz/J8MOLhrIsNM7dtNtjKc6NUDADA7a/8TkaYkSJzfwzAyuYdxAERNt6oiwKNtef3I0XhjR8XdXRxHghzFhwQwjlCen+pdynpuHMRkWokV5Mb4izptig1yszwJ4FwwQ1MdhEv45zVJcojHaEmVXg8JQ38SSniNzWaCBIrpH6JfMSvybbo+LFYCVCyuogK5zmO3jQ1GLvGeVFSM1WcBgwQWxfEA7MDEVz+yvrnmEmKIa3MY5TXhi083uYLKTXyAG/MNC1+quFPEMJ5A5uTaKI3WftzW74fZKh0qSiyabFYKG8AidYNQDoFVUgpA44KKaUtgplCZ1B0oatHcReZSZKkXeaimH7hDnoxiIujw4LHEyDvh62zZKhzAYs69MhjMUFsQwTGA2MBqRfJ1U4lVsMbka4nSdW09trxsTDN3e2bFIkZZhbIPBL9kuX1PcQddxw4w88qxdPBrEV+l3QmJlcWpQJHChGRitmGE1G6VNJ8kWiPHz8GNKqtidOrcKKp6DXZRVYoLXVGXro0KmizBf8xto0jqsG0635Ll45zibeXd5GhFEvqzQLeKMMuuLXMWgS7i45ng+aK+HwdlZsSuwCECXaeVgSQND/YvKynmQHT9ZBOyEKThT9WGUVlls5am2N444Bf5+aglg8QOV8sttWjVYoyaKiQUtqDSn9my/Gw1moiJO50g3wJlz9/MbE5xBf97BwjucbAJMXwEgBM1qUUanyJ22iGXgB3YWzhtQMGQeqsKEESlUPrYqgg3tyoC7+2vUI5UdceW1frMlYw5+TQXZzL3jsZuegl9nJmkCMmjjz5k0BoJB0TzhGieWdRWskkgdx2Lux3Nwi5kRVFmBGBYJKE1N6dnyQVpqiRTqEakbkWzlFmjs9vm2Fw2RzEuBaLAZMVF/Jowybh5vLlnAVGAHgr6gt0m+X4fPVGJcrnjUrtEweSZhUrBwsKAfidFyLZrCuGn5A6rmqfj+hzBQB2gYEWoqwRcSqwibSzogwCKqSUtvAnAOvC9eTLUF62rj6jSl1H3EWVlUGsiZUkNS2MmmmZXmHcHDE7L69diIxF0apC4bRf1J0WpStMWu7yyYN0QTWpBMOFwmiThLtQmqREwNpyjK7SPdgUFrChRTgjQpBD1wm4YJF7IqqBMjLo13V7UYKdL5Y4lxdHXKJBu/HIGtcVGKVngqy7IOYAcP3hsyVvb1bEeRhIlKfb40rIEPyVLhpYZU2R4SgHjc/R+LzIsJuRWLrWkhmOtvKcoRRA8/L5SVQpei+npHDbilVHOMclxyGK/nLQ/HDecMHZFIxU7m8Zrhw1ZFTfHnlFppuuaD6uoUs21zkp22ku7dxJel5RuoUKKaUtyFAcRbF5LgilXHVh4U8A+UC+9G3ICGaK78prY3OuZqTejLpW1+45E1AqFPbKhVIGz0aTj6P3UpEKHJVW/PxuRn4nwZ/gpi5UYiwJgEVQhi6yZTNAYk3h52pdYdXwJgHMifdSK0KMEgw75yIMCUbuCYADi3DBIsxImMakGTyOuNuLZ1FwuM5XHuNi01B/XP4cpWckYkLwxhj+OJqOnJEvKS8yaOqi2g4mIRGhmn9PEdCk8EtMUUUkqvh1/AnnAl+lA8/4hMRecJ11dSJR7vNQnB70x4F4nmOeEc67rlEjkZ1G24zgoGAGanOVxrfUxBpFnIrnGxkR4rntVow9M64GrkvDzBulUhVlsVAhpXQM+XLHK3URte5UnT9OFEUp9z1iRjgjFwJ/XO7IbeDSFwyYXHe7/ohc+sBFlsgjmHGAx4BgWsRCVFPCeefrA7i0ltQnRVEgGUbMJduqhnEu7UQEM1KYOUgJSa3ld3PcFk++hUmKqWeti5bxmzMyZC50bZEh2JwrzibxOPLGpd4JRqIOkYO67CfEY1AoSa6Tiqput7zOTTq1UFQz1drFjlIMrhHhiRCfKCl6L95XNh8JsMW9wNYTLN4o1W2Ok7qm2n/n4s9DtvRGxLoaNSKSlJo7dxtts3QB7l89oVS0PZuVc9gkSFLVVPqaNifrDaKC/SRgJ5qPjtWjUSpVURYTFVJKxxBF6bz6X2QmUTtVwvlCDVUwy9KpU+wxUyN1JdPtm/sCZZbiW7BYEpCRDjNJtRTeS7EhI+CEgIfY9weQ9BeM3HmbdKEGjJxzd7ULuPELM/dkHpoIGD8yp3TLCBcYXhqwzLDZ5ocd1yKYlosNGXH5ZmsRzEJm+6UAmyGYJCO1lwHnZZ9EaZ3ESqlVoiTglXlcRUXF5AH+ChEzchwLBpidRJLsnBMGGcCOctXUXjjnatWCwr4KZlnSXAT4q5qPgDUDW0nNFqeTwgWp//JGmosMRlYFzT4+fm125zsRyr2XqqXUWoU8cTTnXHPWBsFMUep1pHJQeRSl9kaAcEbEezjf3JimhmstTqWm2mv4UJRuoUJKWVRqpUrEN8d16kTt70lJUdgg6tAqUDw81xtr7P0EuK4mV7cDklSTuFWXbiPy3YlmAZbMAzTSkh/MAjBy4TE+ITcvVw12s+VgpC4EqH4HLtGrSGjI36NUne9B6p8IsfdPJ3A+6jyTQcq57QyEhRQipSRaYpIGKC/uJecjNQ9gnEusLqLthnNurl2qKHKXjWpq3D7NFgwoyy965fs7fulE/dSezIxjeYyr15N1SXF3mAdMBjAddqtFxE7iPuLhxRwWZixyDkiuaVTbxPGw4mYeX4zNyHOYIOmzYrHvIqw2EJ+mYMZKlLWF/Q04AV0miJo6PlVs0EzKWXOkTGym2806t3qpVEVZTFRIDRDlqZLlRMG0DyV3tt5YaTqk2GDRupojm5FUhs27obdFEQibc1/0PpWmE0leKx7AG22jPJ240j28OKWRgUQEQpfi80WEBbPugp6QQvZglmMjSJME/MlCp5M3Lh455Bd8lwqpuurvpV288UIhcn63pC1tDvBHnVmkoQqhGu+/fCEdazOl9T3ehIhKuBQauxo4MkBx/W+U4gEAky+dX8hV9jczx07n3pgI0cribUZ+p0TWOARG9i9cpM0oI7fDuZrnLUb2B7xU60NxgzmGXZBoiz9GsTAu6dakOBtWka62gXtf5eKBRYgTJJLXrLiwCxwXoZsa3w/hHCGcFX8yb4Lhj5vK/b1DOjZNjpBsUKdY7fhE+JMAj1A8dDm/mxHOWzePUZpJIusJDrnis90Nltv3pDKYqJAaIIpTJdEctuVEM506+V1ccH52XkxRx1IwG3XESaQlSvFEvjdxxxC71AUXpUNGCn+L0yY1OsbNiETJyNUUAc5rqajTil3BOmcBdi7c4TzimiaTpLrz7dq5cw/nnMHhWGk6y0uLmSVbJwwSEr1J7UPwR+sLDJN0aU1bmY6N5umFaXYiEkhMiLikomhUyX4s26dcZX9zzglbAJwjUI2Iks05QUMoSYGaJDmHcAYCQjhb6MpjjkalNI4cha6GLZxlScNF3Zp+QRBEnX+cLzX0tNnCWJaoQSF6vBklmKz4bYVzqOmWXr5WMyLCNXLJr/4klO7Psv1tXUE5M+BZACtRl+LjU95tSFS4CZDuTicQjXzmzGjhPGy2C09RhhEVUgMEB+7iEQ2vbf0meknDzHHqiEOXFnH1Kvk90be9Sy8lC2mm+HeJsvZrcgXRXKh5ibqrOKg9N84boYamnd4opHMpUYh61esO6xSbLxSvIySY8qHAkAtyYqWzW0hXGlBWg4y4Z9drM/fGqGACCVSkB01KIhMcVvplle9vtnJBtnlX4F5jn4mAkSiYSXLJviUiJFcxsnl5fhTFibyc2JYasdbaPvkFl3GJsrj0ViwyJdIAACAASURBVNl+qJYOk6HDRT8X7680wcZCvvrrV0tdi+dXfRHoT0DGBqUkelW+v8lIowMHgEk19pYyCal/5LwIo1pE8/Sk2aKQqleU5YAKqQHCGy/ccXYjpTMIMEvNhvjbdPaeiOSiGy6wjC2ZdQ7KY+4CHbrOM1co641BRmY0GJRcfmFsauQNF7l4V7mwFbrYnOt3tRRPl7B5Rn6XRThLMGMM1LnQipt06+to5NXT6O/1xt8U729paQfIkw7Qes7YiXEDf4TBttIc0hs1GFlfMBe1eenyKklTNih6TjihVlyn1qxnkRmRVBi4UpCbBCG5GlWNTyOiAcGy1qIuPHds2YofG1suSRlH3Yu1Gj8oASRWmLg7thHhPMffSfWK9smXOkJvBUCgZVmeoCxfVEgNEFGqZClR0jFWo5utFbxRqb+weUZ+Z6HYObGa4K8o/fI2ieqRmVrImA65k/aicSXW1f+ErhaIJDoTpxh91E3RAa4OqtFrF6Vx4nV4bsZbg4t3OA+JfqU5jiA0+36j99QJUddjNy6cHPUCmNILd7VuOaB+yij6W+QCzpbleCZqz+Yreb6pPTewmecm6qTNytddfizIr5J2LsJmCg7ixSnjhutqssM2QhzwXSfpaKFmT1Kf8pi4A9YjeItsN6Eog4AKKaWnxOlK183WrTqJKH0QbTP/lER9GqVs6hHMiuizeUaYlTtrDqWuJDK9TKxEIVUIef1O3ZVjw09X38RhoUaIfILXoBXdJJyXVUIKfJsRNLGZYYJgxi04J6/TKBLKViJGxg2gtTlGsJvBKNSmtYrNutqutJhLhm5kS7z9aUa4ILnu5D4c2zDYvLMRaLBu646VmMiWeh4NArFdQ1E3YNSFF8zLSKGKIcAJxFXuraaMi/d3dGPDbnizzXN8zpFH0pmX5bigPCKcL9iVwKvdrNAJ5eeaogwqKqSUnuKPyzw5SrR3ka1F5Nocdd7ZnPy+mZRN7W26tvlZAKHU6XjjkkI0K+SiLl1pUvMTZsRVOZgGOG/d/LjW32M0Hw2Qi1zxfmqmzsQbdcXd1HzELxo4HeYs7A6IM3am0s26nGDaubJDIow2W4giRZYHzcCh674kSVGJHQC50UHymHBBBh2H84xwWrrx8tsBs06id8EuEc+N1u2NAJx3abYmInwVa3VdhJznto9xPeLC+mhOntuH4YKY1AIMz1LJUOc4Pcit+WTZQIrgJaIkw6jJk89oMGMRTAPeCMOOSTMEJRjsfMFKrA+KzstOa6Gic6E8TV5+rvUqNa4onaJCSukptSa8dwPxeJIvcuvqXzqZ2+eNA8wkVyePYCDbj9rHTboQ7fHGJLphc4y8K/IOZixM2rR8oY7TOIGMmjEjLh0YzUprIgXXqulk3AHm0kcE1OxSBCSNFEUh4gun636MbAGaMXEEUEiNhkW/CxiBm8fmj8na8rvdQOaERLyiKGT8nIofqkOmM1d8DgpiJ5wrjAMqPy5hRrzDTKq1qKg3Kh2mxi8ztazb7SjHgy1A49x8ytx14YXzAGwh5V6rW9XOu89XVo5RFPnzRsmJbzeL0eO2bpTExsLVsiXL0qF13r+iDBIqpJSBhplh5yHt1FU6pgC5o06urt9Z1gxEhMQkwSTEz8vbC4BXqIuq+tpuSGwwK1GSvOGWrSvi6FpR92AUVQtmpNi3OO3TDfxxiqMz0WDieiI0mI6Ej3SDmSTFF85WTCUhmyiIKBIBm38KYFjktotY5cDV3IwxKGmQWstAaArdkiQCt9G6u0FxGjl6z/k9LK7aCTdbDoiNNiNz0maPlTdK1bsBRwDPFiJpxdhMwVw2iNJ7dT4j8TZdDZ3NyjkVpdxl+9LtR36hOYCSBM7I78q7iE0CEk2EfF5aPg8AwCJ2QJcygMI2/EnxxSqfPWlzzkm+iVS0oiwGKqSUgSacR+zn44NqWhIA3at78UYIKLs419p2cYoRcDVTkVlji1R7jSgFx4GrB+tiS3ls+dBE1DAqgjeetOF30jQQpUYjEeSNEOy4Re5JACTjc5KrAQ6lw1Bm6FW+cZMiwHDN8UG1sFmJJBnnzG3zKHFhr7be6BhH6aXouNg8A1b2BxlnOklotpa78BrVRDqVpvOYXadenkvOL5strKfRZwSQ/Z1aaxDOFlLuUm8mBf3+eOH4+pMAj5KzMyhbI6EwjaDN80GGWUPG0pStu9CBWIBtwSC0mVS0oiwGKqSUwWYIwvtk5As/mKmSnqkBW9el1+ACFKd9EoRWx8Vw6DrduhDF8leI6aXMHex8e5IaLdr+hIs+mMKw4Xpdb2zZFaIjjtg0084fzBWMNv0pqUGKbAgSdTo8ozRyvP5RlxpNURypSawkiUYle1PMzvmCYELe2TNYVyM439q2TLK0o9UuFG4GwkxhJBNR7fM56ky0ZWakrdLMcYsZ0O8AZXmjQkrpO1F3DlGlh5NcbCWVU88QsN+0Yl1h8yyF0pD0VL2OpMjuoVXiuXDGpQTLrARq7e9akOl8eHLNtWZkeHNyNYNd+q4e0cgZm3VjdBJUWm9lpX6IvMpapbioPydzFjmynChLKzXCH6cKAUBe7/YRUEgjRynGKN1lkmKhFqX22tp2EkBU69ZCFyD5BG8RryLkyYgh2+RgZUVZDFRIKX0nnCseJlx68StPbywFKjrdelCMb7PyX4lYoORiV29/LzY2zwicK71Jkvh3WTd8N3C1RmXRHZuDRPMSAFgERXH7fTBTZB/hldbX+GNALsvI7wFMQgqkE1M00CI9Ik4x2tLmgihV2glemmIB1Y2IYy/pZQOLorSDCillSRNmxB/HpJqPvvQaL+p0494VSnujLvpiWhdqHEYiZHH3l80z7E55fRsQPNf9Vl4nE3UKEgj+VKWreQllqSDyJZKU38kAy/MSqwbjvGiG8hRjV7c94AJKUQYVFVJK3/HGAJBcILoZrhf/n6JOqnT3ut46gXzqeZGsSVHNLqp6+zsetov2DTZbWmeC4E9J/Q9QaOnngIEUVcypAyQaU2//+RNA6BVMPSuenyb4k9KpmFjZ//OhXcJ5sQ3wRkvPa5t3Ngxp9V5SlMVAhZTSd7qRmqi6XSKQ58z+PLTcSTVMyLBfV+jcILJQb39HabPo52YNNjvBSxOQdm3wLmXnjwNgKozqaYFG5xMZ6VqDHZz2eQ5dN5qFRNkaCNgwIzVwAABbiNrJsOOCUWliL/eQrEtztiGsOHBrAxpHABVlGaJCSlnSxJ1UidqdVDYvbubku7lhAzQ+pFni2X8GSKxuP/Jm0oX6qkajaVrFZllc7lOoGEYcpRP9yTa8A5p57fJjbArddoNAfpeIFS8NhAvUmYAllKQ0o3mXICC5qnXxGGYKHX0yiqiDtSnKEkSFlNI1OHTdUn5/C5gjaqU+Kh434/yAcpIKandQbbcJF9z8vdEm6lciHysX1alGdHxgpD6IXCdksXA0icZpR5tz0a8WU0fBtBwP5AEvVbigl6QTG3QxtruOkmOcpKZ9vuIOwCr7qltwIB2IHIpvWhRFqoeXptjMstg3ikiGd0epPSICnEgFO8+nFtdnks4JHYsToVSUYUOFlNI1gunCRPpo7Ek3COc59lLyVzS+mDEzcttlDIlJAclVpqJguRjyAeQRGwwOAtGwXgDgoL6nEiApl3DedbnVEF3BjIsKzTMo4fZnk7YGUeqQfEZ+N2JDxMRezYsL8gmccyNmivZzSTqxSU+iCmPGBq7aJce4hcHZ+d1yLhEBqXWVlgddwYi48yflmHjp5h3Rq24uQSVRI28CwKzzAPPhhlU3H5kySZnJ14zvWatEJqM2J3MMyyOVijIMqJBSBp5wPioYZ3C+iYiRdcaFXEhT1cObcJEob3BqZqKwAefdDLpEfeNCkyKQzyKWcgx/osFFr8W3Gex2ER24bjf3/FYiNP4UYHNykS+OEJoRd5yoejrR5sU4k3w5VtFrEgBrm/N/io4xWjzG4QK7mXoka+xFLZ+zNbD5DlN6NTAJgnFCPLfDtpUC7lWTBodFLvHzDKiQUoYQFVJK1/Anpb6jm9EoQC6A0by5pty9DeCPyewKSjYuWCZqPtWzWETdbLntDEpKbZFJ1d+v4XzhohT6lQXX/qSbjUaQ/ZJs3kSUbZQvdF12YWtePuG8pK6qpSkbdeGFs07E5Z1gdHPszAQjfBJAQqJs9ewt2jnGHIgYRwDQSFS/1RvII3gtRMraJpprVycFvJjIzQucZ5iKKGU4USGlNAVbcYK2AcOfqH4BJq833Xf+hJsfZpqLgBDJIFl/ynSUiuCgaA5bG9sJM855O+l8j8rMIRvhpQn+hBEHbyNRBGaXYqPKC0+xyKwlOG0eElHKAWaq+ffiT1Is5pp2cA84tjUIZuR3HBISK5p/XcC9lxwk8FQkNogptm8I5qSYOhoWzCHHZqfRsYs64ziEmHA2uHDbwI2OWeOcxNu8OWAWOwIy/RcL/mTjFHC83hbP13YgcqN5OpjXpyj9RoXUMoOtG6zqt5aW4XyU2pG5XL0chVGNVr9kiajkotsqbKXGKvI08kZkdIk3KhdpcP0UUTSiRdZScDJPrGotWudPAZwjNx5E5u6Fc0U+T0UXZm+E4vqfqhdAKlpLi9csGUnS/OPZMoKdHL/v4jW0ijfuCsTL0nImDZgMweYtOEcIpjn2iMrvcuf5XKGOy+YKI2IiMVEPk5TX5bDFeXBlhHNAMGuBUMw/vZHahXjhfMEDqhcGss24goczktIEyXihXtsd1Pus2jxXH5isKAOECqkljM26u/IRN+neMvI75QJj0jKzqllkWK2b8zUgaTBmSXlFQ2u7+mXrOpyi1yBfolMwhUG5/mTt6Ezx7DcbFhWx29aWUZGSKnp+8WtE1IsgxB1dUaSmxQ60lva3LYhH8gBvXARJqwI8zDA4J+dwuXCNa4tyBvld7sWKuxfh1uCEo0m6qJ5tzvg1GsrbsR2DFTHFeVmQWcdV9x2zNFWAXdF9mwayzNxRd2F8XjFaPl+7STDjGiOM3IAU30zFHcJGBmArSj9RIbVEYetayl3BdXKNa5eOLjS51sISZAiJ1RioELxdQBydAQj+RPe2TZ6YHNosgagwt40DxLUlnAdQQxh4Y4hHkJgRRjjvIiodFhN7YwCzcyVvIypY3tHVCq3sb/Ll7zYndVHtpIg4KMzhs3kgubroQmpd+ilRmNHHeSfwyB27TKkYIY/EWoAXJ8JhsxLRNKMuNZuCfONaVPWwKjGQ9dGyfouNMy3gd+BK708AwVxtZ/jFQtLCkdN9abdlMFs0T9Hvf8pUWd6okFrCxL58UYeVL63uNle/MLfm9jpMl3UdKhg5ook7cLYummQlmtSoe8sbkf3FVr7UZUguwDm566836JZM8Yw4aqkeqR7ktRZJ7JQ4FVzuDN/E6eONUonHUc3XCJ3gKE8hEeKTuDzCEky7wnoCEitl+DCNFASSl6aqHYBE1LJAaYcwUxCB3jghtY80TJgk1T3vEispPteK33PNfVSEzZYZZ7Yp2slv7hzjIBIyvdmh3hjAM7L98hsQavFcVJReokJqiUKG4K90EYGi1FCvnKP7QZRqBENMJhu8L7tQ1NU2XzkMt+brmNL0WmIVGr7WYtBpCqcZItsD8qW+xweh2WHL4YIUm0ep5Wpw6NLNFjBphj8uRe3kScomsUKiURWiKEo5MZDfBYCjNbaesuwJtvRnb4KaunkpP9cAKdqP6s288UpX+Pi5KYDmJZ3ZjfR7vfMrFopU20S10/PTpAjJGpEmb9xFxhehIF5RGqFCagnTSRpnEIg6rygpLfLl2FzRl2jQxEUqgUKEYwjOfJuTNE95rYzMUxOBU+/C2ilhxiKYZYkGBCKgmrZLCAuGojaHmvYGHErEL8xItDDYA1BSLsBRyqZaZMWbBDBHML7r2INLu1oMRNTUjAAmcN2aiebS6HEqMF0WjcoX6s04B2Csxmv6tVOXNnC1ZnW69YrJ72HYDMOkpcOxnCjtFtdzlQm3cEGaLchjJFZS11OpZEjS54oyAAzB5URZrsSdVzXMA70R6Whj5qZSSCbpWq25951InWLzBeduky9NtXBQ3EHZGxNDiTi4ou08wW/nYhjllus8jRLS+BDMsqSd8yy+TYkGz/Pk+JMH+OTSZmmq3dIfSERnsY47kQhPOOdu8ri+B1hxKjAstRExKQBGiq9pnsEBwZ+sbt9QLXXJ1g0ythKxajQCSOrP3PmVYfBkZZTPGwE4T/HP5dgFSBo8cGnxAWlQUZReoEJKGVyiu/BaxoHG1ZIwNT2Atlpka7FgW71bq/qDUTBMLOucKjExbHKcSMu415Q6sdLRKDbLCDOSbqtV5EuedLxxrn6HHJGIRPINwlmGn5KZdsanuimbqEVfOroI3mjtEyCe5deg07Lr2Bo/t/hYMhKVMymJ8pEHwKBm2qsaXONcKidcYNhcUYdummIRFSxY2Czgj1LhpqQGJi2RKvKcKFaUJYwKKWVg8acI4ULBZLEcO+/GxwAAtd61x6Hr/Er2PlLRKFVSjklKVMIGgF+Wwoja/nvZfWZGJDISWR1EFHeDchZIrKldk2QSBDR5EfXH3Mw/aq7GKYrIsetErTc/zzbZadlt4u63JrrKzAjgWemsrZayMgmJDknLP8Nv4hyKiBofbLb6CJ4IDgrpWPKk0zc6v4JZi8wjIlx5kpHap37+1Bt1ZqnueEYmn0Bl6lJRhh0VUsrA0tAE0tT4uUnyu6UGCQQkV/fO1kEuIkWpkonmBJA3RjXLfXrdfUa1hCmhYOrZpNN806/Zgij0xyUdSD41jHh4aUkBg9FUCrhbNNv9Brj9XWcqgDcqRp5e2qX/WnwftboYSxeBQg2hKU3l2gwAZoRZwFTxL6u6ueLnLyA2qPW5uW5ORRkWVEgpQ4s3QvEXfzMGixVw2X87JDasdFGFSJgRyd25RKQ6L7y1OZZIXbKzNFU4Lyaj3mjzETkZvyPRqGY7w9hySWSimUha9LjiC3sx9Tq6KtbsRcaajde52A7abBnhLABqbHLqT7jxLknqSbNEnI6tUjwuXZoEAreVHi9Oz3MfTT4VpReokFKGGq+DGiF/KrowdScaZTMFw0rm0mhEYoqajkQ1IpiWIvzIK6idtdt8YYQNB6Vml40wPjX9zRHOi1s3GcCfks48DkQ01Bq7Ejnw24ABK8aQ3qgIiVZgZil6psaCM7+HEc5YSZvuAxivjRBnk9h8oYMuzLhxLABgqCKNW4w/Qd138C+jOB1bsv/SBH8Fg6hyv4QLHFti1IpQeiMArCtO12iUssRQIaUsW0yie0aZAFB8jalyvenaBTAayksdWIKRgeuqYlAP68Ns1r2OE37RrDubYaCWkMpL1C0WHCNA8DgjXBB3/Voih1keH80ljGbcWRe9S6wyVQUVMyOctQhmAYBBaUJyVe3tAiIQw3mGSVFLAi/uoGOAFkrn6VU7Z8pp9hyyeVeYTgR/qj2xnd/NyD8l0cTUOoI/LgO0i/eh2FYUdRvWqFMkU/q3cI4RLkiEFtaZBI9VH4auKIOOCill6GHmro6uCecYNmgt5QVIuimxAk3PcmsXf8qNrkl0Js6YpSW+l7VWxd1bZlRa5m1eiu6DWXYDgcuOHUlRtRSJM8Idbq2hAYdAet/qrxVMi0CLZrOBAYQi5siT4xpdqDlk2JBhF8SLyqQJmOEKR3HAmZLmuMSGI5qJF86L9UYr5x4X/eCNUlybVB5djdN+cAaULRxru+CsB8CwmeqeS8Up14hwnuOxPna+1Cld7CYkQhinXovT4k2myJlZvL8YCKatrMEQwllWIaUMJSqklKEnutA12xFXD5tzg2MBICSYOi3e1ViMmV/kdV6syxYFF+0e1qx4I1TSpWVWSb2MzSCOZAQoK8pmiV5wAIQLAKcswl2F4vpajtlc3Mnn6tTYyrBuSiCOvAXTEg2x8wCNWFgiJFa5LrOwct9Go1DYIp6TZxIk4spHS40OZOS92mxBbNcSD3ahKO3XYlcqJQC4tFy1YvxglhHOOTf4lS7KGZSme/0pMVOFkXmB0bBum5Eifw5lH3tjld2ddddGYhRsc+KtxXA3QupQrgwpKqSUoYYtw+bqmwe2AhkUjCR7VybTd0xCBIPNcc1apXrYgIGwOeFYfjyi4bzx/5ftZ3JF9DYLgBjkefB8hhkB/DFT8/j6ExIpMkmKI4mJKYI/4Yxd3bdd3EFpGZ4F4Esnoj9W/YB7E4RwTtJ40Vw5fwXAgRtEXWM9Nhu5e7v0mosomRTBpEQQSucowxunynq/BqniengjBBuIWKw2dy8alcSB/KMkSjoyyYh3mEkXUsiWJCXJABBFqrKt1ddFFO8/gEqOj6IMG3rqKkMNmUJHnDdCHbfjk1/oXKJUNLC39jZtjuOC9XYGQS8mbJ1HkLugS21Pe4Xq+V0cRyHqCbHy14wwSbefw8o0KFE0B1HSgJwHzJrG3Y61Ovmklb/ocaMijBKrRNCYRP1BwmIdUEUMNrBdCOfk/XHIsLlK+wHOFc1+nOOK1/BGZN3tzs5j59sULnBsclq87WBWOvAiAUOe68jMF45J8XMSbnYnJYBwRoRau6m48v3XqlBUlEFChZQy9CSmqONIVDEmQWCfEeySC7k3Eg17riTYI3VGNtv8HLN+YPOuyBm1h8w2CxcZXNq8CEmgsmvL5hnBboli+JMMhJKeiwRnM8Nm65l62jzHKbJWWvL9cdf91mNTSEoCyItIqDbzknz5G9va+6KT40RJAmfECb1cqHijVLXLrt7+Jp/g+QBAcYpWjTUVRYWUskTo+hd6WDTPLsPAZKlAADs/H8/V4EQpwQHF5gpePrYFD6hqmDRgciTpHcOlRovFLug5xGnXYBcBJqr36XxMS3H3m800nh9XzmIIAEmNiYipFk0jT7oQOeyNs74/CfCoSz9We/1Oo7dECKZZOvnGaOAjsorSK1RIKT2HmRHOyJ23PzG4UZsSPIkG2BzDFF0g8rsscjsZJgUkVxn4K6SDznTQQWezLj2Y6l160EsVBslSgpHfI/Uw3kTrF9RoPh4g6SvrwlMVTVskBqXMgD9e3+zS5qVDjRKlqcJwznWRjVVGbbjih+Zodn+HCzLWxKTbF36NImXlacdu0kz6sRM44LgYPpxjFVLKskWFlNJziruPQhPVvww2RGJlUBxmimaRcR6wISSdaNyMuA4Ipl16MNe79CD5FEdtgunCyBryO+sANKOAxzWMFlmKrAH3vnwCUXVriGDajetx+8AkXBeZ66DksDTqFHe/NRiKXI1m9jezRNpslsHTQPpp1FOTzqGkaHi2dtwpyxkVUkrPKRkoO8zXIhK/IRsyjFfdm6etzS52erC4G6z+7NmG1JsRZ0YAE4jhYqNIJHkinBhOqCJKiTmrhirPjbrfWl5zk/ubQ4mokQGCGSC5ovIx4QIjnBVTU39qedUMEbmGAVs4j2xWvKmaqX9TlKWCCiml55hU4Qu3k9qcfkMeIblaCs9Nqv1UXjndSA+2gjfmokOmtxe8KGpUDWaxT4BX6NKzWUKYFdECYiRWEhIrCbbK7Ld62EBSyeQ7I8sycdPM/paIJIHzzoOqhuIK5yW6xVkG50kKzJcRxanJcL5QL5dYsTieaooyCKiQUhaFpXKHWuhc6uI2u5AebOn1qLIVfzFhZgS7pC4qcoOP9oHNiht3NFbGpFvf3+GMK3LPiQknkauzGokEZHP72xsxSK6RlGOt9KdJEsLAdcYt82/TaPxP/PMQ3zQpSiss84++oiiLjgXyu61EmtIMf6pgsumNA2DpNGs3ekk+gBycsSojHzly51o3j2xUZO5POFFWozOvW9gcI9jDgAESK2ggGzYiJ3mQpHUVZbmgQkpZ1rB14yla8CFq63U4MvdcXnU0NYkmvnCZj5FPMCtLHxp39NVI1RUjXX7i/WVGpLi95ba+Funk3OGQXSrT1ZHVEGPhQmFEjc3WjpD1E/KiBg1FWV6okFKWLWwZ+Z0icOqZbnaDeB5ggmSg7nLGAIkpE6f2AJn9JmadlUIpnC2k6kzSzQesQnGXn7WF4xl19y1m+rRZwvkid3OvTuF+0g1frjE7T1GU/qFCSlm2yPgO+VmMI3sjpJglSmIDma1mQ0JyZf2xJEsZIoK/0jmdeyImwjlnx4DKbsi4s5AA1OsyrNHl125332JQXFdVr8bKGyGZl0eL05CgKErzqJBSli3ky0WW8+LM3LPXIREH9imWi2GUnhnSTx+zFGCT336akojibx9qkHrzJlwHmFff4JKMRPtsvnJI76DijVAsFBs1ZPSrLoqtdCa2MoZHUZYTQ/pVriidU810s1f44wSTMMjvYRDQ9zZ5m2fYBWd+2UKbeknHnRs83ClmFPBRu0iZqHY6r+KxHsHr0BtrsRnkjtbFTH8ryrCiQkpZFMIMI5xmwOt+1xGHkjJDCPhTNLD+NSZFSO4lP0fpGZtj1+a/uEXowR553TADJFe3EO3gohmEOe7K4NooYlfzJVlGtZDfm5l0/SB+T17vhFQwxwjnRPC2axbKweKkvxVlmBlmn2lliLALMnONAyn87eq2c+4Ln6XeZpARA8OCiMrvkrEz4exiL6TNpxkZTksG8MZoUcRfOCNjXfK7OBZxgwDb9tcTzha9p1xv3pOdFz8um+VYDLUKJcTLKzreiqJUohEpZVEwKRE84qbd5W0nC0XGrc5d6wXM3JTAYFv0c5sXunZJTBHCjNt3TUajwgUZ32JGAX9i8e7B4ohIhhFMi2t2v32UOHQpLyudhv5Ea+tZjGNvUoRwQTpF2x0FVBhQrSJKUWqhQkpZFLxREpFD3U9hkUdIrHY/97mjyWZZ6qCMjDipd8E3KdkvbAG/S3P7moX82q321YgGNgNSzN2ssWU3UljeBMA7RXxwAASzqDl6ZrHgsCCG2kl5+eNAADemp0fi3590KVOj3mWK0ktUSCmLRi9FTr8FVES4gHi8SSPvIiKC57aWIgAAIABJREFUP7FoSwPgOrDCNjruyP1rsSYqnJFIFgAkVrVX42R8gr9CUreDQpTyarfjk7zacwi7Sb8jd4qyHFAhpShdJE5hEmAGzDiRWWpyOEDLxqCRa7XNo6U5fSVpK1vzYQ2JCqYRDsb4EU15KYoSoUJKUbqIN+LMH3uQwuwYLgyWtfnWO+5Mklqub/MngGAump3X2f7w0gO2PxVFUaBde4rSdcgsTjdbq5AheGNif8mBjK1h2/s5dIkpgj8+ePtDqSSYYeR2WISZAcqjKsqAo0JKUZYR/jjBSxPIlyJpm+n3ipRBwQaMcF5Sv+GMCilFaRYVUoqyzIhrt6j+fDdleUFuViEA0BIxPlWUxUC/RhVlmeGNEighBfHLdXCyUkk0q5BD6UpUFKU5VEgpyjJkqYxaGSbCeZaux9H+7H9mcTqvZxVCXvvmnYqyXFEhpSiK0mNsnhG4uiMOmjc0DRdE/JiRzrpAOXTWF1Y6Kb0RFdKK0i1USClKCwTTMhvNGyO9GClNQwYFQ9MmzWPDhYKbvMfUkfu9zRWN2snWN4pVFKU1VEgpSpPYPMcu3eEsq5BSmoY8QmIlZFZhs4amxY1zHZiZAtFMxcGZR6koSwkVUorSJOS5i1EIUJtz45Tli0kQ0EIRtxkBPEsAQ2bmdQB5hORe1PRAbUVRmkeFlKI0SUlXk35ylB5D1Npg6Wa3qShKd9HLgaK0ABmKvXaagZkBO5zDYyPX86imZ5jfi7J80fNW6TUqpBSlRzAzgl1SW+WNAP7k8HyR24AR7JJ5fP6k1NhEA4+9UcCfGJ73MuhwyAgXxCi103mESinFn0GTBhJTun+V7qPO5orSK0L5AgcAmx2ukRuclcJksHR5cVg08HjI3sugE+wBwjlGfg+DA923XcUO72dQGR5USClKr/BchIEAM2QdfibtiuuNtMqTD5ikvJdq3YrM0qqf383gsPsXrHBBfJCW9DBdLm3UUzqHPIJJ1z5vFaUbaGpPUXoEESGxAhADoeEi6vIqJrESqPVebAaxNURAhMRU99bC1plZMhBmGHac4KVIhN0SwJ8EwgUZ22N0ZE/XkXSe7leld6iQUhSlY4rHinR9xAhJZIxDIJyXn+0CI7l6aRQQk0/wJ/q9CkVR2kWFlKK0CVs3u2wJXMw7xSSd4aQFTKq72yaSbdscYndwRVGUQUGFlKK0AQdls8tGVUyVp9qYGXZBxJU32vxolGqQR1KrlQDsQuTUrfu8U9iyRPk8rSFSlHZRIaUobWDzrqsNbnbZaH/XM4jYDOJBveDupK+MTzBNbCeYYdgFhhkhtWqoQzAD2EzkF6b2C4rSDtq1pyhtYFIy8oOMiqhBg5kRzosHVjjPsbGooihKL9CIlKK0QTQuRruBamPSgM8Up/YWCyKCSQI2xzBJ6iiluNTxJ4DQI5Cn0ShFaRcVUoqi9AQi6lu0zl8BICSg2x2ESwwy3Z/npyjLDRVSiqIsOYhIv90URVkUtEZKURRFURSlTVRIKYqiKIqitIkKKUVRFEVRlDZRIaUMDczaxq4oiqIMFlqOqQw8zIxgt7Sze2OAP65t2oqiKMpgoBEpZfAJRUQBMqxWURRFUQYFFVLK4OOJizigpoGKoijKYKGpPWXgISL4KxlgdalWFEVRBgsVUspQQEQ6jUVRFKXPhBlGOCfjl3QguKCpPUVRFEVRmiKcZXAgA8FtXmtWARVSiqIoi4oN5I6eQ70IKcMHuXpVMgDpLEsAmtpTFEVZNNgygl0MtgAtAMm9NDWiDBf+JMAjBPKgNasOFVKKoiiLSOwrqwEpZQghIlCy36sYLFRIKYqiLBJkCP4kYLOAN9Lv1SiK0g1USCmKoiwiXprgpfu9CkVRuoUWmyuKoiiKorSJCilFURRFUZQ2USGlKIqiKIrSJiqkFEVRFEVR2kSFlKIoiqIoSpuokFIURVEURWkTFVKKoiiKoihtokJKUYYAtoxglhEuqB22oijKIKGGnIoyBAQzgM2IiCIPMEmdcaUMNsEMw2YYZoTgj+v5qixdNCKlKMOABqKUIYItI5yX4czhHINZT2Bl6aIRKUUZAvwJIPQI5Gs0ShkCCDAJgs0zTJJApOessnQZOCEVzjHCOQalZLinfgAVBSCP4E/0exWK0hxEBH8lg0MCef1ejaL0loFL7YXzDGapB+Gw36tRFEVR2oGIYHyNRilLn4ETUiYlHzryARq41SmKoiiKohQYuNSeP0nwRgF4mtZTFEVRFGWwGTghBQDkq4BSFKU+zJL+J73pUpSWsHlGOCufHW9CPz+dMpBCSlEUpR7MjPxOBgdSDpBY0e8VKcrwEM4CNud86ZIEL93nBQ05WoWkKMrwYQEO3I+53noUsRVHeQ7UC0lZGlAUQiFoV2UX0IiUoihDB3kEbwSwWYYZ7W1aItgtqRAyQGI1QEbTIMpw4407PzoPMFpK0zEqpBRFGUr8SQLQ+4sAW3b/BWChcXxl6CEiUKrfq1g6qJBSFEWpgz9JCOcBk9RGGEVRKlEhpSiKUgeTJJhkv1ehKMqgokFqRVEURVGUNlEhpSiKoiiK0iYqpBRFURRFUdpEhZSiKIqiKEqbqJBSFEVRFEVpExVSiqIoiqIobaJCSlEURVEUpU1USCmKoiiKorSJCilFURRFUZQ2USGlKIqiKIrSJiqkFEVRFEVR2qSlWXvhPCO7LY2jrnoLrLW9WtNAQQRMrB1DamMG3qgOLFUURVEUpUBLEanstjTOev9HMTc3hzAMEQTBkv83NzePj5zxV8huS/fqGCiKoiiKMqS0JKRmHp/DOX91DpLJ5TMKPZlM4q8/+teYeXyu30tRFEVRFGXAaElIMWNZiaiIZDIJ5n6vQlEURVGUQWNRi83vu+8+bNq0CRs2bMDGjRtx9NFH4+abby55zPz8PNasWYPp6emS32/evBnf+c53am57cnKyJ2tWFEVRFEWpxaIJqUwmg02bNuH000/Hfffdh23btuHCCy/E73//+5LHjY6O4thjj8WWLVvi3+3Zswe33HILNm3atFjLVRRFURRFaUjXhdS2bdvwohe9CJlMBnNzczj44IPx61//GldccQVe9rKX4YQTTogf+4IXvADvfve7K7ZxyimnlESftmzZgmOPPRbWWrzmNa/BoYceihe+8IW45pprKp570003lQiuD37wg7j88ssBAL/4xS/w6le/Ghs3bsTxxx+Pxx57rHtvXFEURVGUZUfXhdTGjRuxadMmfOITn8Bf//Vf4+1vfzte8IIX4O6778YhhxzS1DaOO+443HnnndixYwcA4Dvf+Q5OOeUUpNNpfP/738ftt9+OH//4x/joRz8KbrJ4KZ/P48Mf/jCuuuoqbNu2DaeddhrOO++8tt+noiiKoihKSz5SzfKJT3wChx12GNLpNC688MKqj3njG9+I+++/Hxs2bMD3v//9kr8lk0ls2rQJ3/ve93DyySfjl7/8JY477jgwM/7mb/4GW7duhTEGjzzyCJ544gmsXbu24Zp++9vf4te//jWOO+44AEAYhk09T1EURVEUpRY9EVI7duzA7Ows8vk8MpkMxsbG8LznPQ9bt26NH3P11Vfj9ttvxznnnFN1G6eccgr+/u//HsyME044AYlEApdffjm2b9+Obdu2IZFI4JnPfCYymUzpG/L9ErPQ6O/MjOc///m45ZZbevCOFUVRFEVZjvSk2PyMM87Apz71KZx66qn42Mc+BgA49dRTceutt+Laa6+NHzc/P19zG6961atw33334eKLL8Ypp5wCAJiensbee++NRCKBn/zkJ3jwwQcrnnfAAQfgnnvuQTabxe7du3HjjTcCAA488EBs374dt912GwBJ9f3mN7/p2ntWFEVRFGX50fWI1De+8Q0kEgmceuqpCMMQr3jFK3DjjTfiqKOOwrXXXouzzz4bZ511FvbZZx+Mj4/j4x//eNXtGGNw8skn47vf/S6OPPJIACLGTjzxRLzwhS/ES17yEhx00EEVz9t///3x5je/GX/yJ3+Cpz/96XjRi14EQNKFV111Fc4880zs2bMHQRDgQx/6EJ7//Od3excoiqIoirJMoHrF2utOTZb88fFvy9gUIpk512yh91LA932sPaUnmVBFWdakEinsNbEXVo2vwuqJ1Vg9sRoT6Ql4xoNnPBhjEIYhQg4RhAF2z+3Gjpkd2DG7AztndmLn7E4ENuj321AUZYj59ke+DQA45Qun1HzMo1fmqg7cVWWgKErPSfpJPHOfZ+I5+z4Hz1n3HGzYdwM27LsBa6fWYiw91vH2d8/txsM7Hsa9j92Lex+9V/772L14eMfDy+qGT1GUxUeFlKIoXWf1xGq8bMPLcMSBR+CwDYfhGXs/A74nXzdBGOAPT/4Bv33kt/jJr36Cp2aews7ZnSX/nV2YRRAGCDmEtTaOTiX8BFaMrogjV6snVmPV+CqsmVyD9Xutx8s2vAxvPOyN8Trms/O45+F7cNu9t+HWe2/FL373C2TymVrLVhRFaRkVUoqidEwqkcIrn/tKHHHgETjiwCNw0H5SvzizMINt92/D9XdeH0eLHnjyAeSCXNuvtWNmB373xO9q/n0iPYEN+27Ac9ZJ9OtFB7wIZxx7Bv7ytX+JbD6LOx64A7fdexu23r0Vd/7hTo1YKYrSESqkFEVpC9/4eMVzX4ETN56IY194LMbT41jILWDb/dvwg5//ALfdext+9dCvENpwUdc1k5nBHQ/cgTseuCP+3VhqDBufvRFHHHgEDn/O4TjzdWfirDechYd3PIzrbr8O195+Le5++O5FXaeiKEsDFVKKorTEoc88FCcddhJef8jrsWp8FfbM78G//eLfcO3t12Lb/ds6ijb1irnsHG76zU246Tc3AQAmRydx9AuOxgmHnoDTjzkd7z/u/bj/sftxze3XYMt/b8Efd/yxvwvuEcwcNwspitIdlqSQ+tjHPobbbrsNBxxwAL7+9a8jkUjEf9uyZQu++MUvAgB+//vf46yzzsKHPvQhHHjggdhvv/0AAOeeey5e85rX9GXtijKI+MbH61/yepx+zOk4eP3BWMgt4Ef/8yNcu+1a/PTunw6keKrH9Pw0tvx8C7b8fAtWjq3E6w55HU449AScvelsnPn6M/Gfv/xPfPW/vloS1Rp2bJYR7GHAMBIrCeSpoFKUbtATIWUffRi5G38E2BCJVx0Db/3T29pOPp8HMyOZTDb9nLvuuguPPPIIfvrTn+L888/H9773PbztbW+L/75582Zs3rwZAHD00UfjxBNPBABMTU3F5p2KoggT6Qmc8vJTcNpRp2G/Vfvh/sfvx7lXnIsfbPsB5rO1DXWHiV1zu3DF1itwxdYrsG7lOrzjle/AO175DrzukNfhF7/7BS79r0txw103wLJtvLEBJswAzABCwGYBb7TfK1KUpUHXnc3zP/spZt71ZmS//hVk/+WfMXvaKcj91w/b2taePXtwzDHH4Oyzz27ahfzWW2+No0nHHXccbr311qqPe/zxx5HNZnHAAQcAAGZnZ/HqV78ab3/727Fz58621qsoS4Wx1Bj+6oS/wm3n34bz3nQeHtr+EE778mk45v85Blf+7MolI6LKeXTXo7jgmgvwso+/DJ/8ziexZmoN/vl9/4yf/N1PsPmlm4c6LWZSAAggA5jm700VRWlAVyNSbC0WvvSPQFBkjmdDZL78/yFx5NGgohRbM+y11164+eabceutt+Kiiy7Cgw8+iJNPPhknnXQS3vrWt1Y8/sorr8Tu3bux7777ApAoUy1RtGXLFrzxjYU26a1bt2L16tX4xje+gb/7u7/DRRdd1NJaFWUp4BkPbzniLTh709lYM7kG191+HS750SX49UO/7vfSFpX57Dwuv+lyfOOn38BxLzoOf3H8X+CfTvsnnPbq0/Dp738a2+7f1u8ltoyXJhFQhKEWhIoyaHRXSG1/EvzEY5W/370L9uGH4D3jWW1t94gjjsDIyAguvvhiXHrppTj55JNrpuFWrFiB6elpABLRWrVqVdXHff/738fXv/71+P9Xr14NAHjTm96Eyy67rK11Ksow86fP/VOcd/J5OGi/g/Dz+3+OP//Kn+N/Hvyffi+rr1i2uP7O6/HDX/4QJ208CeeceA6+d/b3cP2d1+OzWz6LB7dXzvscZMiogFKUbtNVIUUrVgBjY8DcXOkfkimYNXu3vL1sNotLLrkE1157LZ73vOfh/e9/P1784hdj+/btOOqooyoef+WVV+Lwww/HF77wBbzzne/EDTfcgCOOOKLicU888URJWi+Xy4GZkUqlsHXrVjzrWe0JPkUZRvaZ2gfnn3o+jvmTY/Dg9gdxxqVn4Po7r+/3sgYKZsaWn2/B9XdeL11+x74fRx98NC790aX4p3//J+TDfL+XqChKn+iukEqlkXrrnyF72SUlv09ufgtofKLl7c3NzWHNmjX493//d6TT6fj3a9asqRmRWrt2LfbZZx8ceeSR2H///XH22WcDAM444wxccoms6+qrry5J6+3atQtveMMbMDY2hmQyWRKpUpSlzKZDN+Ezp3wGqUQK5199Pv7lJ/8ydB14i0kmn8EXr/8ivnPLd3DOSefgL1/7l3j1C16Nj1z+Efz20d/2e3mKovSBngwtzv3XD5G/4d8Ba5E4+jgkjt809Dl5HVqsLCWmRqfw6VM+jRM3nog7HrgDZ11+Fh548oF+L2voOPrgo/H5d3wekyOT+Mfr/hFf/a+vDn13n6IsRwZuaHHymOORPOb4XmxaUZQOecVBr8A/vusfsXpiNf7hmn/AxTdcvOju40uFH//qxzj208fis6d+Fh9/48dx9MFH46zLz8LDOx/u99IURVkkum5/oCjK4HLGsWfgmx/8Jqbnp3HS50/Cl374JRVRHbJzdifed+n78JHLP4LnPu25uO7c63D4cw7v97IURVkkVEgpyjIglUjhwtMuxLmbz8W/3fFv2PS5Tfj1H5eXpUGvufq/r8amz27Cjpkd+N8f+t/4s1f+Wb+XpCjKIqBCSlGWOCvHVuLKD1+JEw49AZ//wefxwa9/EJl8pt/LWpL8YfsfcNIFJ+Gm39yEz7ztM/jEyZ8Y+vpQRVHqo0JKUZYw+++1P7acswUv2P8F+MDXPoCv/OdX+r2kJc9sZhanX3I6LrvxMrz3mPfi4tMvRtJXK3FFWaosSSH1sY99DEceeSTe+c53Ip8v9Xe56aabcMABB+Coo47SwcTKkma/Vfvh22d+GytGV+Bt//Q29YZaRCxbfOq7n8KnvvspvPbFr8WX3/tlJLzWJjsoijIcDLSQyufzyOVa87QpHlp80EEH4Xvf+17FY97ylrfgxhtvxI9+9KNuLVVRBoq1K9biW2d+CxMjE3jHRe/AHQ/c0e8lLUsuu/EynPet83DsC4/FRX9+ETzj9XtJiqJ0mZ4IqfD//hj56/4W+Ws/gfA3P6zpN9WIXg0tvvrqq3HkkUfqPD1lSbL35N648swrsWp8Ff7soj/TovI+882bv4lPffdTeN0hr8MX3v0FGBro+1dFUVqk6z5S9sHbEf5yS/z/4a/+DUiNw3v2K1reVi+GFh966KG45557AAAnnXQSXv7yl+MlL3lJy2tThh9mRjANcI7hjRO8keEvCl41vgpXfPgKrJ1ai3d+8Z2468G7+r0kBRKZSvpJnLv5XOSCHD76zY+2fYOpKMpg0X0h9cc7K37Hf/wl0IaQiujm0OLx8fH4502bNuGuu+5SIbVM4QCwGbmYhXM89ELKNz4u+V+XYP1e6/GuL70Lt//+9n4vSSnikhsuQdJP4uxNZ+Oh7Q/hous1Iq4oS4HuO5unJyt/N9L6nD2gN0OLp6enMTkpa/zZz36G973vfW2tTRl+yJN/HAImOdwiCgA+fvLHcdiGw/Dhyz6M/3Pf/+n3cpQqXPQfF+EZez8DH3nDR/Crh36Fn/zmJ/1ekqIoHdJ1IeUd+GrwQ78A5+YBAJRIwzvomLa21YuhxVdddRW+9rWvwfd9HHHEEXjlK1/Z1tqU4YcMIbHKCanEcAupzS/djPcc9R58/cav4wfbftDv5Sh1OPeKc3HgugNx4Z9fiE2f24QHtz/Y7yUpitIBPRlazAvTsA/dDlgLc8BLQKMru7jk/qBDi5VB5XlPex6u/ujVuOsPd+HtF74dgQ36vSSlAfuv3h/Xfew6PL77cWz+h81YyC30e0mKsqzpZGhxT9pHaGQS3oFHwXvuMUtCRCnKoDKaGsU/v++fsXtuN/7ia3+hImpI+OOOP+KDl30Qz1n3HHz6lE/3ezmKonSA9uEqyhBz9hvOxvq91uODl30QT8081e/lKC2w9Z6t+PIPv4w3H/5m/Olz/7Tfy1EUpU1USCnKkHLw+oNx2lGn4Zs3fxPb7t/W7+UobfCl67+E+x+/H+efej7SiXTjJyiKMnCokFKUIcQzHj7/js/jqemncMEPLuj3cpQ2yQZZfPzKj2P9Xutx5uvP7PdyFEVpAxVSijKEvOeo9+D5+z8fn7zqk5hemO73cpQO+O/7/hvf+tm3cPoxp+P5T3t+v5ejKEqLLEkhVW9o8XXXXYfDDz8cr3zlK3HmmYU7wKmpKRx11FE46qij8Ktf/Wqxl6woTbNqfBU+8oaP4Ia7btBBxEuE87ecj11zu/DJt3yy30tRFKVFBlpI9WJo8Qtf+EJs3boVN998M5588kncfru4Px944IG48cYbceONN+Lggw/u2ntQlG7z3qPfi3Qijc9u+Wy/l6J0ien5aXzp+i/hsA2H4bANh/V7OYqitEDPhBQvPA5eeKyjeVK9GFq8fv16+L74QSWTSRgju+B3v/sdXvWqV+EDH/gAMplM22tWlF6yYmwF3vWqd+G6X1yH3z/x+34vR+ki37rlW3hyz5P48Os+3O+lKIrSAj0RUvz4j8APfQf80FXAY9e3LaaiocUnn3wyLrroIhx//PH46le/Go+IKf/3+OOPY/fu3fEImGpDiyO2bduGJ598EocccggA4N5778VNN92EfffdF1/5ylfae+OK0mPec9R7MJocxRev/2K/l6J0mWw+i0tuuAQvP+jlOPRZh/Z7OYqiNEnXhRTndoH33F34/5n7gOz2jrZ5xBFH4IwzzsD69etx6aWXwvO8OA1X/G/t2rUNhxYDwMMPP4yzzjoLl19+efy71atXAwBOPvlk3HXXXR2tV1F6weToJN796nfjP+78D9z32H39Xo7SA67YegW2T2/Hh173oX4vRVGUJun+zBPyqvyuPb3Wi6HFMzMzOPXUU3HxxRdj7733BiAz/dLpNDzPw9atW/HsZz+7rfUqSi956+FvxeTIJL50/Zf6vRSlR2TyGXztx1/DuZvPxYZ9N6hgVpQhoOtCihKTwKqN4J1iEEgrXgRK7dXWtnoxtPjCCy/EAw88gA99SO74PvnJT2Jqagrvfe97MT4+jhUrVuBf//Vf21qvovSSzYdtxp0P3Il7Hrmn30tResh3b/suPnrCR7H5pZtxwTXqEaYog05PhhYDAOdnALAIqyWADi1W+smB6w7EDZ+4AX/77b/Fv/5Uhf5S518+8C84cL8D8fLzXt5Rw46iKM0xcEOLAYASE0tGRClKv9n80s0IwgDX/eK6fi9FWQS2/HwL9lu1Hw57tlohKN3F5hnhPINDFejdYqB9pBRFAYgIJ730JPz07p9i52z1LlRlaXHDXTdgNjOLzYdt7vdSlCUEW0awixHMMII9/V7N0kGFlKIMOIc84xDsu3Jf/ODnP+j3UpRFIpPP4Ie//CFe++LXwrTZrKMoFVggyhSz1YhUt9BPqKIMOC999ksBAFvv2drnlSiLyda7t2JqdAoH7XdQv5eiLBHIJ/iTBJOW/yrdQYWUogw4L332S3HfY/dh19yufi9FWUS2/U46nzc+a2OfV6IsJbwRQmKKYJIqpLrF0AopHUysLAcMGbzkWS/Btvu39XspyiLzyM5H8MjOR7Dx2b0VUmy5o85A5s6eryjDztAJqVwup4OJlWXDc9Y9B1OjU/j5/T/v91KUPrDt/m1xarcXhAuM3FOM/I72urg4YOSfYuS2M2xWxZSyPBkaIfWb3/wGZ599No455hhcd911OphYWRZEM9c0IrU82fa7bdhnxT7Yf/X+Pdm+zQBggEPA5tp4fhZgK9sI9StVWab0TEg9+eSTeOKJJzoK+ebzeXz1q1/F8ccfj4suughvetObcPPNN8PzPB1MrCwLnr7m6ZjPzuPhnQ/3eylKH7j30XsBAAesOaAn2zcjAEgme5lkG89PuQlgBHjphg9XlCVJT4TUY489hrvvvhv33HMPHn64/QvAzMwMLr30Uqxfvx5nnHEGDj/8cADQwcTKsmG/Vfvh0Z2P9nsZSp+Ijv3TVj+tJ9v30oTkGkJiNYG81ouPySck9pJtmJQWLyvLk54IqVyuECMuLwRvhVWrVmHbtm14//vfj8suuwxHH300LrzwQhxyyCH48Y9/DAAtDSYOwxAAdDCxMjSsW7VOo1HLmMd3P47Qhli3cl3PXoOI4rFf/Xi+ogw7PRke97SnPQ25XA7MjPXr13e8vRe/+MX44he/iEwmg6uvvhobNmzQwcTKsmDdynW4+49393sZSp8IbIAndj+Bdat6J6QURemMnggpz/OwYcOGrm83nU7j1FNPBQBccEHlVPRLLrkEAHDeeefhvPPOq/h71L2nKMNAyk9h76m98eguTe0tZx7d9Sj2W7Vfv5ehKEoNhqZrT1GWG1NjUwCAHTM7+ryS/nDixhNxy2duwQNfeQC3fOYWnLjxxH4vqS88NfMUVo6t7PcyFEWpQU8iUoqidE7CSwAA8mH7dYbDyokbT8Tn3v45jKZGAUix9efe/jkAwDXbrunn0hadIAzic0FRlMFDI1KKMqD4ntznBGHQ55UsPueceE4soiJGU6M458Rz+rSi/hHaMD4XFEUZPFoSUkSlHXnLhVwuB21KURabyINtOXZE1SpaCRj5AAABhUlEQVSuXq5F1wx1DVeUQaUlITWxdgyf/4fPLysxlcvl8Pl/+Dwm1o71eynKMiOKRC3HtE4t76zl6KmV8BLLMiqpKMNCS/Hi1MYMvnDJ/4tPf+rTsNb2ak0DBZEIyNTGDIDlFxlQ+kc2yAIA0onlZxl9wTUXlNRIAcB8dh4XXFPZrbvUSSVSyAXL5+ZVUYaNloSUN0oYPTKLaz9yFQDglC+c0pNFDR5ZqIhSFpudszuRC3LYe8Xe/V7KohMVlJ9z4jlYt2odHt35KC645oJlV2gOAGtXrMXjux/v9zIURamBVjAqyoDCzHh89+PYb+Xy9BC6Zts1PRVOHLoatDZGoywm61auwx2/v6Pfy1AUpQYqpBRlgHlk5yPYb/XyFFK9xOYY+d0ipBJTGNg5caOpUawcX4lHdj7S76UoilIDijqDFEVRFEVRlNZQHylFURRFUZQ2USGlKIqiKIrSJiqkFEVRFEVR2kSFlKIoiqIoSpuokFIURVEURWkTFVKKoiiKoiht8v8DFWckd6oZIC8AAAAASUVORK5CYII=\n",
"text/plain": [
"<Figure size 748.8x489.6 with 1 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "EHBsENu7wRim",
"colab_type": "code",
"outputId": "50ba187e-e87c-4c03-f0b8-deb082050d95",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 340
}
},
"source": [
"#[['Distance','Angle','UnderPressure','ShotType','ShotBodyPart','ShotTechnique','ShotFirstTime','ShotOneonOne']]\n",
"xgb_model.predict_proba(pd.DataFrame([12.55,37.156,0,4,2,2,0,0]))[:,1]"
],
"execution_count": 0,
"outputs": [
{
"output_type": "error",
"ename": "ValueError",
"evalue": "ignored",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-43-9dff4c73a403>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mxgb_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict_proba\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m12.55\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m37.156\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m4\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/xgboost/sklearn.py\u001b[0m in \u001b[0;36mpredict_proba\u001b[0;34m(self, data, ntree_limit, validate_features)\u001b[0m\n\u001b[1;32m 832\u001b[0m class_probs = self.get_booster().predict(test_dmatrix,\n\u001b[1;32m 833\u001b[0m \u001b[0mntree_limit\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mntree_limit\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 834\u001b[0;31m validate_features=validate_features)\n\u001b[0m\u001b[1;32m 835\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mobjective\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m\"multi:softprob\"\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 836\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mclass_probs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/xgboost/core.py\u001b[0m in \u001b[0;36mpredict\u001b[0;34m(self, data, output_margin, ntree_limit, pred_leaf, pred_contribs, approx_contribs, pred_interactions, validate_features)\u001b[0m\n\u001b[1;32m 1282\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1283\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mvalidate_features\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1284\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_validate_features\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1285\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1286\u001b[0m \u001b[0mlength\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc_bst_ulong\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/xgboost/core.py\u001b[0m in \u001b[0;36m_validate_features\u001b[0;34m(self, data)\u001b[0m\n\u001b[1;32m 1688\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1689\u001b[0m raise ValueError(msg.format(self.feature_names,\n\u001b[0;32m-> 1690\u001b[0;31m data.feature_names))\n\u001b[0m\u001b[1;32m 1691\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1692\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mget_split_value_histogram\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfeature\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfmap\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m''\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbins\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mas_pandas\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mValueError\u001b[0m: feature_names mismatch: ['Distance', 'Angle', 'UnderPressure', 'ShotType', 'ShotBodyPart', 'ShotTechnique', 'ShotFirstTime', 'ShotOneonOne'] ['0']\nexpected ShotOneonOne, ShotBodyPart, ShotTechnique, ShotType, ShotFirstTime, Distance, UnderPressure, Angle in input data\ntraining data did not have the following fields: 0"
]
}
]
}
]
}
Reference in New Issue View Git Blame Copy Permalink