2120830
/
DAT
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
DAT/0_ExplorativeDatenanaylse_E...

955 lines
237 KiB
Plaintext
Raw Permalink Blame History

{
"cells": [
{
"cell_type": "markdown",
"id": "7d1106cf",
"metadata": {},
"source": [
"# Vorbereitung auf die DAT - Labore\n",
"\n",
"### Vorwissen:\n",
"Ich erwarte ein gewisses Vorwissen in Statistik (z.B. Basics aus MA3). Dies können Sie sich zum Beispiel aneignen durch:\n",
"- Kopp-Schneider, Werft \"Grundlagen der Statistik\" in Medizinische Physik: https://link.springer.com/book/10.1007%2F978-3-662-54801-1\n",
"(pdf des Kapitels auch auf moodle)\n",
"\n",
"### Literatur für die ersten Labore: \n",
"- Bruce et al. Praktische Statistik für Data Scientists, Kapitel 1 bis 3\n",
"- Sauer, Moderne Datenanalyse mit R:\n",
" - Wir machen ein Teil der Analyse aus Kapitel 10 mit Python\n",
" - später Kapitel 17 (und Teile aus 15-16)\n",
"- Python-Dokumentationen, z.B. VanderPlas: Data Science mit Python\n",
"\n",
"### Sie werden hier:\n",
"- Erste Schritte in python gehen $\\rightarrow$ Test Ihrer Python-Umgebung, evtl. Aneignen oder Auffrischen grundlegender Python Kenntnisse zum Daten laden und visualisieren\n",
"- Hinweise erhalten, auf welcher Theorie die ersten Labore aufbauen $\\rightarrow$ Möglichkeit zur Vorbereitung und/oder zur Auffrischung von Vorwissen\n",
"\n",
"### Lernziele:\n",
"- Sie können den NYCFlights Datensatz laden und den gekürzten Datensatz in einem DataFrame darstellen. Sie wissen zudem wie eine Tabelle mit Daten für eine Datenanalyse aussehen sollte. \n",
"- Sie können Daten mit seaborn als Balkendiagramm, Boxplot, Violinplot und kategorialen Barplot darstellen.\n",
"- Sie können deskriptive Statistiken berechnen und bewerten.\n"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "3548bf3f",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:18.427404Z",
"start_time": "2024-09-27T07:14:18.416601Z"
}
},
"outputs": [],
"source": [
"# Import nötiger Module\n",
"\n",
"# Daten einlesen und Daten verarbeiten\n",
"import pandas as pd\n",
"\n",
"# Plotten\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns # zum (einfacheren) Erstellen guter statistischer Plots\n",
"\n",
"sns.set_theme() # alle Plots (auch von matplotlib) im seaborn-Style\n",
"\n",
"# Numerische und statistisches Werkzeug\n",
"import numpy as np\n",
"from scipy import stats"
]
},
{
"cell_type": "markdown",
"id": "81da0a5a",
"metadata": {},
"source": [
"## 1. Vorbereitung der Daten: NYCFlights Datensatz\n",
"Ein in vielen Data Science Lehrbüchern und Anleitungen verwendeter Datensatz sind Flugdaten von New York City aus dem Jahr 2013. Diesen Datensatz werden wir in mehreren Laboren verwenden, um uns verschiedene Aspekte von Datenanalysen anzuschauen. \n",
"\n",
"Wir nutzen in den ersten Laboren eine gekürzte Version des Datensatzes, da wir alle Beobachtungen mit fehlenden Werten erst einmal löschen. Andere Varianten mit fehlenden Werten umzugehen (Feature Engineering) schauen wir uns später an.\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "e429ce79-f282-4000-b6d7-a72449e88f51",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: nycflights13 in ./lib/python3.12/site-packages (0.0.3)\n",
"Requirement already satisfied: pandas>=0.24.0 in ./lib/python3.12/site-packages (from nycflights13) (2.3.2)\n",
"Requirement already satisfied: numpy>=1.26.0 in ./lib/python3.12/site-packages (from pandas>=0.24.0->nycflights13) (2.3.3)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in ./lib/python3.12/site-packages (from pandas>=0.24.0->nycflights13) (2.9.0.post0)\n",
"Requirement already satisfied: pytz>=2020.1 in ./lib/python3.12/site-packages (from pandas>=0.24.0->nycflights13) (2025.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in ./lib/python3.12/site-packages (from pandas>=0.24.0->nycflights13) (2025.2)\n",
"Requirement already satisfied: six>=1.5 in ./lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas>=0.24.0->nycflights13) (1.17.0)\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"pip install nycflights13"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "7536dd73",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:20.002045Z",
"start_time": "2024-09-27T07:14:18.512263Z"
}
},
"outputs": [
{
"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>year</th>\n",
" <th>month</th>\n",
" <th>day</th>\n",
" <th>dep_time</th>\n",
" <th>sched_dep_time</th>\n",
" <th>dep_delay</th>\n",
" <th>arr_time</th>\n",
" <th>sched_arr_time</th>\n",
" <th>arr_delay</th>\n",
" <th>carrier</th>\n",
" <th>flight</th>\n",
" <th>tailnum</th>\n",
" <th>origin</th>\n",
" <th>dest</th>\n",
" <th>air_time</th>\n",
" <th>distance</th>\n",
" <th>hour</th>\n",
" <th>minute</th>\n",
" <th>time_hour</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2013</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>517.0</td>\n",
" <td>515</td>\n",
" <td>2.0</td>\n",
" <td>830.0</td>\n",
" <td>819</td>\n",
" <td>11.0</td>\n",
" <td>UA</td>\n",
" <td>1545</td>\n",
" <td>N14228</td>\n",
" <td>EWR</td>\n",
" <td>IAH</td>\n",
" <td>227.0</td>\n",
" <td>1400</td>\n",
" <td>5</td>\n",
" <td>15</td>\n",
" <td>2013-01-01T10:00:00Z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2013</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>533.0</td>\n",
" <td>529</td>\n",
" <td>4.0</td>\n",
" <td>850.0</td>\n",
" <td>830</td>\n",
" <td>20.0</td>\n",
" <td>UA</td>\n",
" <td>1714</td>\n",
" <td>N24211</td>\n",
" <td>LGA</td>\n",
" <td>IAH</td>\n",
" <td>227.0</td>\n",
" <td>1416</td>\n",
" <td>5</td>\n",
" <td>29</td>\n",
" <td>2013-01-01T10:00:00Z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2013</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>542.0</td>\n",
" <td>540</td>\n",
" <td>2.0</td>\n",
" <td>923.0</td>\n",
" <td>850</td>\n",
" <td>33.0</td>\n",
" <td>AA</td>\n",
" <td>1141</td>\n",
" <td>N619AA</td>\n",
" <td>JFK</td>\n",
" <td>MIA</td>\n",
" <td>160.0</td>\n",
" <td>1089</td>\n",
" <td>5</td>\n",
" <td>40</td>\n",
" <td>2013-01-01T10:00:00Z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2013</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>544.0</td>\n",
" <td>545</td>\n",
" <td>-1.0</td>\n",
" <td>1004.0</td>\n",
" <td>1022</td>\n",
" <td>-18.0</td>\n",
" <td>B6</td>\n",
" <td>725</td>\n",
" <td>N804JB</td>\n",
" <td>JFK</td>\n",
" <td>BQN</td>\n",
" <td>183.0</td>\n",
" <td>1576</td>\n",
" <td>5</td>\n",
" <td>45</td>\n",
" <td>2013-01-01T10:00:00Z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2013</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>554.0</td>\n",
" <td>600</td>\n",
" <td>-6.0</td>\n",
" <td>812.0</td>\n",
" <td>837</td>\n",
" <td>-25.0</td>\n",
" <td>DL</td>\n",
" <td>461</td>\n",
" <td>N668DN</td>\n",
" <td>LGA</td>\n",
" <td>ATL</td>\n",
" <td>116.0</td>\n",
" <td>762</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>2013-01-01T11:00:00Z</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" year month day dep_time sched_dep_time dep_delay arr_time \\\n",
"0 2013 1 1 517.0 515 2.0 830.0 \n",
"1 2013 1 1 533.0 529 4.0 850.0 \n",
"2 2013 1 1 542.0 540 2.0 923.0 \n",
"3 2013 1 1 544.0 545 -1.0 1004.0 \n",
"4 2013 1 1 554.0 600 -6.0 812.0 \n",
"\n",
" sched_arr_time arr_delay carrier flight tailnum origin dest air_time \\\n",
"0 819 11.0 UA 1545 N14228 EWR IAH 227.0 \n",
"1 830 20.0 UA 1714 N24211 LGA IAH 227.0 \n",
"2 850 33.0 AA 1141 N619AA JFK MIA 160.0 \n",
"3 1022 -18.0 B6 725 N804JB JFK BQN 183.0 \n",
"4 837 -25.0 DL 461 N668DN LGA ATL 116.0 \n",
"\n",
" distance hour minute time_hour \n",
"0 1400 5 15 2013-01-01T10:00:00Z \n",
"1 1416 5 29 2013-01-01T10:00:00Z \n",
"2 1089 5 40 2013-01-01T10:00:00Z \n",
"3 1576 5 45 2013-01-01T10:00:00Z \n",
"4 762 6 0 2013-01-01T11:00:00Z "
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"\n",
"Laden des Datensatzes. Er liegt als DataFrame vor: https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.html\n",
"DataFrames ermöglichen das (schnelle) Arbeiten auch mit größeren Datensätzen.\n",
"\n",
"Doku des R-Packages: https://nycflights13.tidyverse.org/reference/flights.html\n",
"\n",
"Zu diesem Datensatz gibt es dann noch weitere Infodatensätze, z.B. zu den Flughäfen: https://nycflights13.tidyverse.org/reference/airports.html\n",
">>> from nycflights13 import airports\n",
"\n",
"\"\"\"\n",
"from nycflights13 import flights\n",
"\n",
"# Vorschau von 5 Zeilen der Daten in einem DataFrame:\n",
"flights.head(5)"
]
},
{
"cell_type": "markdown",
"id": "d72baf05",
"metadata": {},
"source": [
"### Aussehen einer Datentabelle\n",
"Sie sehen nun eine Tabelle mit Daten. So sollte zunächst bei jeder Datenanalyse der vorbereitete Datensatz aussehen.\n",
"Es gelten folgende Konventionen:\n",
"- jede Zeile enthält eine Beobachtung (engl. observation), hier einen Flug\n",
"- jede Spalte enthält eine Variable (engl. variable, feature...). Diese können kategorial aber auch kontinuierlich sein. Ordnen Sie zu und wenn unbekannt, recherchieren Sie mögliche Datentypen! \n",
"- Bei jeder Datenanalyse sollten Sie ein sog. \"Code Book\" führen, in dem auch festgehalten ist, was die verschiedenen Variablen bedeuten. Infos zu den vorliegenden Daten (was bedeutet dep_time, welche Einheit...) finden Sie in der oben verlinkten Doku zum korrespondierenden R-Paket\n",
"\n",
"### Kürzen des Datensatzes\n",
"Da der Datensatz viele fehlende Werte enthält und wir uns zunächst auf die Visualisierung und deskriptive Statistik konzentrieren wollen, löschen wir zunächst alle Zeilen mit fehlenden Werten und verwenden einen gekürzten Datensatz.\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "0e26db8b",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:20.804624Z",
"start_time": "2024-09-27T07:14:20.226757Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"year 0\n",
"month 0\n",
"day 0\n",
"dep_time 8255\n",
"sched_dep_time 0\n",
"dep_delay 8255\n",
"arr_time 8713\n",
"sched_arr_time 0\n",
"arr_delay 9430\n",
"carrier 0\n",
"flight 0\n",
"tailnum 2512\n",
"origin 0\n",
"dest 0\n",
"air_time 9430\n",
"distance 0\n",
"hour 0\n",
"minute 0\n",
"time_hour 0\n",
"dtype: int64\n"
]
}
],
"source": [
"# Herausfinden welche Spalte wie viele fehlende Werte, die als nans (not a number) kodiert sind, enthält:\n",
"print(flights.isna().sum())"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "79e435de",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:22.090779Z",
"start_time": "2024-09-27T07:14:21.298237Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Anzahl gelöschter Zeilen: 9430 von 336776 (2.8%)\n"
]
},
{
"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>year</th>\n",
" <th>month</th>\n",
" <th>day</th>\n",
" <th>dep_time</th>\n",
" <th>sched_dep_time</th>\n",
" <th>dep_delay</th>\n",
" <th>arr_time</th>\n",
" <th>sched_arr_time</th>\n",
" <th>arr_delay</th>\n",
" <th>carrier</th>\n",
" <th>flight</th>\n",
" <th>tailnum</th>\n",
" <th>origin</th>\n",
" <th>dest</th>\n",
" <th>air_time</th>\n",
" <th>distance</th>\n",
" <th>hour</th>\n",
" <th>minute</th>\n",
" <th>time_hour</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2013</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>517.0</td>\n",
" <td>515</td>\n",
" <td>2.0</td>\n",
" <td>830.0</td>\n",
" <td>819</td>\n",
" <td>11.0</td>\n",
" <td>UA</td>\n",
" <td>1545</td>\n",
" <td>N14228</td>\n",
" <td>EWR</td>\n",
" <td>IAH</td>\n",
" <td>227.0</td>\n",
" <td>1400</td>\n",
" <td>5</td>\n",
" <td>15</td>\n",
" <td>2013-01-01T10:00:00Z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2013</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>533.0</td>\n",
" <td>529</td>\n",
" <td>4.0</td>\n",
" <td>850.0</td>\n",
" <td>830</td>\n",
" <td>20.0</td>\n",
" <td>UA</td>\n",
" <td>1714</td>\n",
" <td>N24211</td>\n",
" <td>LGA</td>\n",
" <td>IAH</td>\n",
" <td>227.0</td>\n",
" <td>1416</td>\n",
" <td>5</td>\n",
" <td>29</td>\n",
" <td>2013-01-01T10:00:00Z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2013</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>542.0</td>\n",
" <td>540</td>\n",
" <td>2.0</td>\n",
" <td>923.0</td>\n",
" <td>850</td>\n",
" <td>33.0</td>\n",
" <td>AA</td>\n",
" <td>1141</td>\n",
" <td>N619AA</td>\n",
" <td>JFK</td>\n",
" <td>MIA</td>\n",
" <td>160.0</td>\n",
" <td>1089</td>\n",
" <td>5</td>\n",
" <td>40</td>\n",
" <td>2013-01-01T10:00:00Z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2013</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>544.0</td>\n",
" <td>545</td>\n",
" <td>-1.0</td>\n",
" <td>1004.0</td>\n",
" <td>1022</td>\n",
" <td>-18.0</td>\n",
" <td>B6</td>\n",
" <td>725</td>\n",
" <td>N804JB</td>\n",
" <td>JFK</td>\n",
" <td>BQN</td>\n",
" <td>183.0</td>\n",
" <td>1576</td>\n",
" <td>5</td>\n",
" <td>45</td>\n",
" <td>2013-01-01T10:00:00Z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2013</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>554.0</td>\n",
" <td>600</td>\n",
" <td>-6.0</td>\n",
" <td>812.0</td>\n",
" <td>837</td>\n",
" <td>-25.0</td>\n",
" <td>DL</td>\n",
" <td>461</td>\n",
" <td>N668DN</td>\n",
" <td>LGA</td>\n",
" <td>ATL</td>\n",
" <td>116.0</td>\n",
" <td>762</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>2013-01-01T11:00:00Z</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" year month day dep_time sched_dep_time dep_delay arr_time \\\n",
"0 2013 1 1 517.0 515 2.0 830.0 \n",
"1 2013 1 1 533.0 529 4.0 850.0 \n",
"2 2013 1 1 542.0 540 2.0 923.0 \n",
"3 2013 1 1 544.0 545 -1.0 1004.0 \n",
"4 2013 1 1 554.0 600 -6.0 812.0 \n",
"\n",
" sched_arr_time arr_delay carrier flight tailnum origin dest air_time \\\n",
"0 819 11.0 UA 1545 N14228 EWR IAH 227.0 \n",
"1 830 20.0 UA 1714 N24211 LGA IAH 227.0 \n",
"2 850 33.0 AA 1141 N619AA JFK MIA 160.0 \n",
"3 1022 -18.0 B6 725 N804JB JFK BQN 183.0 \n",
"4 837 -25.0 DL 461 N668DN LGA ATL 116.0 \n",
"\n",
" distance hour minute time_hour \n",
"0 1400 5 15 2013-01-01T10:00:00Z \n",
"1 1416 5 29 2013-01-01T10:00:00Z \n",
"2 1089 5 40 2013-01-01T10:00:00Z \n",
"3 1576 5 45 2013-01-01T10:00:00Z \n",
"4 762 6 0 2013-01-01T11:00:00Z "
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Mit fehlenden Werten beschäftigen wir uns später. Hier nutzen wie zunächst den gekürzten Datensatz und werfen alle Zeilen mit fehlenden Werten raus.\n",
"\n",
"fls = flights.dropna() # fls = flights ohne NaNs, das ist unser Datensatz für die ersten Gehversuche mit Visualisierungen, Gruppierungen und deskriptiven Statistiken\n",
"\n",
"# Wie viele Zeilen wurden gelöscht?\n",
"number_deleted = len(flights) - len(fls)\n",
"number_deleted_percent = np.round(number_deleted / len(flights) * 100, 2)\n",
"print(f\"Anzahl gelöschter Zeilen: {number_deleted} von {len(flights)} ({number_deleted_percent}%)\")\n",
"fls.head()"
]
},
{
"cell_type": "markdown",
"id": "6418c67c",
"metadata": {},
"source": [
"## 2. Erste Python Schritte zur Datenvisualisierung\n",
"\n",
"Wir starten DAT mit der explorativen Datenanalyse, d.h. es geht darum einen Überblick über den vorliegenden Datensatz zu bekommen. Das geht besonders gut durch Visualisierungen. Daher hier zunächst der Test, ob bei Ihnen alle nötigen Pakete installiert sind und funktionieren. Zudem können Sie starten sich in die Syntax einzuarbeiten.\n",
"\n",
"Einige werden `matplotlib` kennen. Für statistische Datenvisualisierungen ist das Paket `seaborn` sehr nützlich. Es basiert auf `matplotlib`. Es vereinfacht sehr viele Vorgänge und liefert überaus nützliche und hochwertige Graphen: \n",
"https://seaborn.pydata.org/index.html\n",
"\n",
"Ändern von Darstellung und Beschriftung etc. basiert auf matplotlib. Die Dokumentation finden Sie unter: https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.html\n",
"\n"
]
},
{
"cell_type": "markdown",
"id": "c6af1355",
"metadata": {},
"source": [
"### Visualisierung kategorieller Daten\n",
"\n",
"Wir nutzen hierfür `seaborn`, da dort Graphentypen vorliegen, die die Kategorisierung vornehmen. Alternativ geht das auch, wenn man die Werte mit `pandas` kategorisiert und dann nur mit `matplotlib` darstellt. Die Visualisierung und damit das Gewinnen eines Überblicks über den vorliegenden Datensatz ist immer der erste Schritt einer Datenanalyse, die sog. explorative Datenanalyse. Hier geht es nicht darum, Schlüsse zu ziehen oder Vorhersagen zu treffen, sondern die vorliegenden Daten verstehen zu lernen.\n"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "d170440d",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:23.837640Z",
"start_time": "2024-09-27T07:14:22.203336Z"
}
},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Visualisierung von kategorialen Features mit seaborn:\n",
"# seaborn hat eine Funktion, die die Anzahl der Werte zählt und als Balkendiagramm darstellt. Hier ein Graph, der die Anzahl der Flüge zählt, die von den verschiedenen Abflughäfen starten:\n",
"sns.countplot(data=fls, x='origin')\n",
"plt.show() # zeigt die Grafik an, ohne die Objektinformationen auszugeben"
]
},
{
"cell_type": "markdown",
"id": "b391bc98d6e683fd",
"metadata": {},
"source": [
"Um mehrere Graphen nebeneinander/untereinander darzustellen eignen sich subplots. Hier ein Beispiel mit 3 Graphen nebeneinander. Die Position ergibt sich dann aus `ax=axs[0]` etc. \n",
"\n",
"#### Aufgabe: \n",
"- Wählen Sie zwei weitere Kategorien aus der Tabelle aus und fügen Sie einen Graphen mit anderer Kategorisierung zu `axs[1]` und `axs[2]` hinzu\n",
"- Erstellen Sie passende Titel für die Graphen\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "a0f2e100",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:26.286294Z",
"start_time": "2024-09-27T07:14:24.209824Z"
}
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABP4AAAHfCAYAAADAyBb0AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjYsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvq6yFwwAAAAlwSFlzAAAPYQAAD2EBqD+naQAAzQxJREFUeJzs3XtcVWXe///33uBGRTYHI8s8Ad0aFQbULTIQk6cMcqqZ0Vud710ahFgektFGc9RsxvE0WQ4egbCszEZzujtIjmX+ZHSYvndpOZV5Ao3MQzMGGwTlsPfvD7575RY8wea0fT0fjx7EWp/1Wddau7zcn3Wt6zI5HA6HAAAAAAAAAHgUc0s3AAAAAAAAAID7UfgDAAAAAAAAPBCFPwAAAAAAAMADUfgDAAAAAAAAPBCFPwAAAAAAAMADUfgDAAAAAAAAPBCFPwAAAAAAAMADUfgDAAAAAAAAPBCFPwAAAAAAAMADUfgDAAAAAAAAPBCFP+AakJubqz59+uiDDz6os++BBx5Qnz599I9//KPOvnvuuUejRo1ya1uys7PVp08fffXVVy7bHQ6H/vM//1N9+vRRUVGRy75z587p9ttv19SpU93aFgAAAAAAPBmFP+AacOedd0qSPv30U5ftZWVlOnjwoLy9vbV7926XfcePH9fx48cVHR3dLG05ePCgbDZbvW355z//qaqqKre3BQAAAAAAT0bhD7gGdOnSRd26datTbNuzZ48cDofuu+++OvucvzsLde5y++23y8fHp875du/erYCAAPXv37/Z2gIAAAAAgCej8AdcI+68807t27dPZ8+eNbbt3r1b//Ef/6G7775bn3/+uex2u8s+k8mk6Ohobdq0SY888ohiY2N1++23KykpSa+//nq959mxY4d+9atfKTIyUlFRURo3bpwOHjxo7LdYLIqIiKgzqm/37t2KiopSdHS09uzZU2ef1WpV79693XErAAAAAAC4JlD4A64Rd955p6qqqvT5558b284vtpWWlurAgQMu+0JDQxUYGKj169frpptuUlpammbMmKEbb7xRzz77rNatW+dyjv/5n/9RWlqaOnbsqGnTpumJJ57QoUOH9Ktf/UrffvutS1tOnjzpsu38tjhf+5Vq5/7bs2ePIiMjZTbzRxYAAAAAAFeKb9HANeLCufWqq6u1d+9eRUdHq0ePHrruuuuMfWVlZTpw4IBxzGuvvaYFCxZo7Nix+u///m/l5OQoPj5eL730kpH/zJkz+sMf/qARI0boxRdf1H//938rNTVVGzZskMPhUGZm5kXb8v3336uoqEjR0dHq27evzGazMerv0KFDKikp4TVfAAAAAACuEoU/4BoRFhamgIAAo9j29ddfq7y8XFFRUZKkqKgo4/Xbzz77TDU1NUaxrX379kae0tJSnT59Wv369VNRUZFKS0slSX//+99ls9l0//336/Tp08Y/ZrNZd9xxhz7++GMjR1RUlMxms9GW3bt3q127doqIiJCvr6/69OljtMX5k8IfAAAAAABXx7ulGwCgeZhMJkVFRemTTz6R3W7X7t271blzZ/Xs2VNSbTHO+eruhcW2Tz/9VMuWLdNnn32miooKl7ylpaXy8/PTkSNHJEljxoyp9/ydOnUy/t1qtermm282RvXt3r1b4eHhRoHx/CKksyjYt29fd9wGAAAAAACuGRT+gGvInXfeqe3bt+vAgQPGnHpOUVFRWrx4sU6ePKlPP/1U119/vbp3765vvvlGY8eOVWhoqDG/X7t27bRjxw69/PLLxoIgDodDkrR48WIFBwfXObeXl1edtrzxxhuy2Wz1tmXTpk2qqqrSp59+aqwEDAAAAAAArhyFP+Aacv4Ivt27d7uMzrv99ttlsVj08ccfa+/evUpISJAkffTRR6qsrNSqVavUtWtXI/78V3clqXv37pKkzp076yc/+ckVtWX9+vX6+9//rn379iklJcXYFxUVpbNnz2rHjh0qKirSvffe2/CLBgAAAADgGsUcf8A1xDly7t1339XJkyddRtlZLBbddtttev3111VeXm4UCZ0j9Zwj+qTa13s3bdrkkvvuu+9Wp06dlJmZqaqqqjrnPn36tMvvzvwvv/yyqqqqXNrSrVs3BQcH68UXX3SJBQAAAAAAV44Rf8A1xGKxKCIiQp988oksFotuv/12l/1RUVFas2aNpB+LbXFxcWrXrp3Gjx+vUaNG6cyZM9q4caM6d+6s77//3ji2U6dOmjt3rn7zm9/oF7/4hZKSkhQUFKTvvvtOO3bsUHR0tObMmWPEd+3aVTfeeKP27Nmjm266SV26dHFpS3R0tP7617/KZDIpOjq6qW4JAAAAAAAeixF/wDXGWdC77bbbZLFYXPY5C2y+vr665ZZbJEmhoaHKyMiQyWTSokWL9MYbb+i//uu/9Mgjj9TJ/bOf/Uwvv/yyrr/+euXk5OgPf/iDcnNzFR4erl/84hcXbcv5o/0ubEtoaKgCAwMbccUAAAAAAFybTI7z398DAAAAAAAA4BEY8QcAAAAAAAB4IAp/AAAAAAAAgAei8AcAAAAAAAB4IAp/AAAAAAAAgAei8AcAAAAAAAB4IAp/AAAAAAAAgAei8AcAAAAALeCtt97SQw89pIiICMXExOixxx7T2bNnjf0fffSRHnjgAUVERGjo0KHatGlTnRyVlZVatGiR4uLiFBkZqUcffVQFBQV14g4fPqxHH31UkZGRiouL0+LFi1VZWVknbuPGjRo6dKgiIiL0wAMPaPv27e69aABAs/Ju6Qbg8hwOh+x2R0s3AwDaPLPZJJPJ1NLNaHXoZwDAfa60r1m1apWys7M1fvx4RUZG6ocfflB+fr5qamokSZ988okmTpyo4cOHa+bMmfrHP/6h3/72t/L19dV9991n5Jk3b55yc3M1Y8YMdenSRatXr9bYsWO1efNm+fn5SZJKSko0ZswY9erVS8uWLdPJkye1cOFCnT17VnPmzDFybd68WbNnz9b48ePVv39/5ebmauLEiVq3bp0iIyMbfE/oZwDAfa72O43J4XDwJ3ArV1Nj1+nTZ1q6GQDQ5gUF+crLi8HuF6KfAQD3uZK+pqCgQD/72c+0cuVK/fSnP603JiUlRWfOnNEbb7xhbJs6dar27dun3NxcSdKJEyc0cOBAPfPMMxo5cqQkqbi4WAMGDNATTzyh1NRUSVJmZqZWr16t7du3KyAgQJL05z//Wc8++6y2b9+uLl26SJKGDh2q22+/XUuWLDHOOWrUKPn5+Sk7O7thN0T0MwDgTlf7nYZvPwAAAADQjP7yl7+oW7duFy36VVZW6uOPP3YZ2SdJSUlJOnz4sL799ltJ0s6dO2W3213iAgICFBcXp7y8PGNbXl6eYmNjjaKfJCUmJsput2vXrl2SpKKiIh05ckSJiYl1zpmfn1/va8EAgNaPwh8AAAAANKPPP/9cvXv31sqVKxUbG6vbb79do0aN0ueffy5J+uabb1RVVaXQ0FCX48LCwiTJmMOvoKBAnTt3lr+/f5248+f5KygoqJPLarUqODjYJZckhYSE1MlVVVWloqKixl42AKAFtKo5/o4ePaqcnBx9/vnnOnjwoEJDQ/Xee+8Z+8vKyvTSSy9px44dOnLkiCwWi/r27av09HT16dPHJVdpaakWLFigDz/8UFVVVbr77rs1a9YsXX/99S5xu3fv1qJFi7Rv3z517txZo0ePVmpqqsv70g6HQ9nZ2Xr99dd1+vRphYeH6+mnn64zz8XJkyc1b9487dy5U+3atdOQIUP09NNPq1OnTu6/WQAAAADapO+//15ffPGFDhw4oGeeeUYdOnTQ6tWrlZycrK1bt6qkpERSbXHufM7fnfttNpsxj9+Fcc4YZ9yFuSTJ39/fiLvSczaUtzdjTgCgJbSqwt/Bgwe1Y8cO3XHHHbLb7bpw+sHvvvtOf/7zn/XLX/5SU6ZM0blz57RmzRqNHDlSmzZtMp6ASdKUKVN06NAhzZ07Vz4+Plq6dKlSU1O1adMmeXvXXvbRo0eVkpKiuLg4TZkyRfv379dzzz0nLy8vpaSkGLmys7OVkZGhadOmqU+fPlq3bp2Sk5P19ttvq3v37pKkqqoqPfbYY5KkJUuW6OzZs1q0aJGmTp2qzMzMpr51AAAAANoIh8Oh8vJy/elPf9Itt9wiSbrjjjs0cOBAvfbaa4qPj2/hFrqX2WxSYKBvSzcDAK5JrarwN3DgQA0ePFiSNGPGDH3xxRcu+7t166YPPvhAHTp0MLb1799fAwcO1Ouvv67Zs2dLkvbs2aOdO3cqJyfH6DRDQkKUlJSkrVu3KikpSZKUk5OjwMBAPf/887JYLIqNjdXp06e1evVqPfzww7JYLDp37pwyMzOVnJyssWPHSpLuvPNO3XfffcrJydHcuXMlSX/961918OBB5ebmGsPorVarUlJStHfvXvXt27fJ7hsAAACAtsNqtSogIMAo+km1c/PdeuutOnTokO6//35JtW8xnc9ms0mS8Wqv1WpVWVlZnfw2m83l9V+r1Vonl1Q7is8Z5/xZWlqq4ODgi56zIex2h2y28gYfDwD4kdXa4aoW92hVhT+z+dIN79ixY51tvr6+6tGjh06dOmVsy8vLk9VqVVxcnLEtNDRU4eHhysvLMwp/eXl5GjJkiCwWixGXlJSkzMxM7dmzRzExMdq9e7fKyspcJrm1WCwaMmSIPvjgA5dz9unTx2XujLi4OAUEBGjHjh0U/gAAAABIkm6++WZ988039e47d+6cevTooXbt2qmgoEB33323sc85D5/zO0doaKj+9a9/uRTwnHHnfy8JDQ11mfNPqi3wff/99y656ju2oKBA7dq1M950aqjqanujjgcANEybn2jBZrMZ8wE6FRQUKCQkxGWePsm1wysvL9fx48frTHIbGhoqk8lUZ5Lb+ibW/e6773T27Fkj7sIYk8mkkJCQOp0sAAAAgGvXgAEDVFxcrH379hnbfvjhB3355Ze67bbbZLFYFBMTo7/+9a8ux+Xm5iosLEzdunWTJMXHx8tsNmvr1q1GTElJiXbu3KmEhARjW0JCgv7+978bo/ckacuWLTKbzcZgie7du6tXr17asmVLnXPGxsa6DJYAALQdrWrEX0P88Y9/lMlk0ujRo41tF5vk1t/f33h92DnU/cLJay0Wizp06OAyYa7FYpGPj49LnNVqlcPhUElJidq3b3/JczZ2IlyJyXABAAAATzF48GBFRERo8uTJSk9Pl4+Pj7KysmSxWPSrX/1KkvT444/rkUce0dy5c5WYmKiPP/5Y7733nl544QUjzw033KDhw4dr8eLFMpvN6tKlizIzM+Xn56dRo0YZcaNGjdKrr76qCRMmKC0tTSdPntTixYs1atQodenSxYibNGmSpk2bph49eigmJka5ubnau3evXnvttea7OQAAt2rThb9NmzZpw4YNWrhwoW644YaWbk6TYTJcAAAAwHOYzWZlZWVpwYIFmjNnjqqqqnTXXXdp3bp1xvx6d911l5YtW6alS5fqzTffVNeuXTVv3jyXKYgkadasWfL19dWSJUt05swZRUdH66WXXnIZlODv76+1a9fq97//vSZMmCBfX18NHz5c6enpLrmGDRumiooKZWdnKysrSyEhIVq+fLmioqKa/qYAAJpEmy387dixQ3PmzNETTzyhn//85y77rFarTpw4UeeY8+e+cHaEF05yW1lZqYqKCpcJcysrK3Xu3DmXUX82m00mk+myE+uWlJToxhtvbMSVMhkuALjL1U6ECwBAUwkKCtIf//jHS8YMGjRIgwYNumSMxWLR9OnTNX369EvGhYWF6eWXX75su0aMGKERI0ZcNg4A0Da0ycLfZ599pieffFIPPfSQnnzyyTr7Q0NDlZ+fL4fD4TLPX2FhoXr37i2pdqGQG2+8sc78e4WFhXI4HHUmuS0sLHRZdaugoEBdu3ZV+/btjbgDBw645HI4HCosLHRZZKShmAwXAAAAAAAAV6PNDXs4dOiQ0tLS1L9/fz377LP1xiQkJKikpET5+fnGtsLCQn311Vd1Jrndtm2bqqqqjG25ubmyWq3GcPbo6Gh16tRJ77//vhFTVVWlrVu31sn19ddf68iRI8a2/Px8FRcX66c//WmjrxsAAAAAAAC4Gq1qxF9FRYV27NghSTp27JjKysqMVaX69esnh8OhlJQU+fj4aMyYMcZCHZLUqVMn3XzzzZKkqKgoxcfHa+bMmZo+fbp8fHz0wgsvqE+fPrr33nuNY1JSUvTuu+9q6tSpGj16tA4cOKCcnBylp6cbq1b5+PgoLS1Ny5YtU1BQkHr37q3169eruLhYKSkpRq6hQ4cqMzNTkyZN0q9//WtVVFRo8eLFuueee9S3b98mv3cAAAAAAADA+UwOh8PR0o1w+vbbby86h8Urr7wiSXrkkUfq3d+vXz+9+uqrxu+lpaVasGCBPvjgA1VXVys+Pl6zZs1yWbVKknbv3q2FCxdq3759CgoK0v/5P/9HqampLq8IOxwOZWVl6fXXX9fp06cVHh6up59+us4ktydPntS8efO0c+dOeXt7a8iQIZo5c6Y6derUoPvhVFNj1+nTZxqVAwAgBQX5MsdfPehnAMB96Gvqop8BAPe52n6mVRX+UD86SgBwD76M1Y9+BgDch76mLvoZAHCfq+1n6JEAAAAAAAAAD9Sq5vhD45nNJpnNpssHotHsdofsdgbMArh2nN/H8GcgAOBqueO7Cv0PAFwdCn8exGw2KSCgI68WNJOaGruKi8v5iweAa8KFfQx/BgIAroa7vqvQ/wDA1aHw50HMZpO8vMxasX6Xjp0qaenmeLSbrvfXhNFxMptN/KUDwDXh/D5GEn8GAgCuiju+q/B3cAC4ehT+PNCxUyU6cuyHlm4GAMAD8WAJANAYfFcBgObFO6EAAAAAAACAB2LEHwAAaBDnPE1MtA4AAAC0ThT+AADAVfH3ay+73SGrtYMkJloHAAAAWisKfwAA4Kr4trfIbDax0AcAAADQylH4AwAADcJCHwAAAEDrxuIeAAAAAAAAgAei8AcAAAAAAAB4IAp/AAAAAAAAgAei8AcAAAAAAAB4IAp/AABc4OjRo5ozZ44efPBB3XrrrRo2bFi9cTabTfPmzVN8fLwiIiI0ePBgrVmzxiWmsrJSixYtUlxcnCIjI/Xoo4+qoKCgTq7Dhw/r0UcfVWRkpOLi4rR48WJVVlbWidu4caOGDh2qiIgIPfDAA9q+fbt7LhoAAACAx2FVXwAALnDw4EHt2LFDd9xxh+x2uxwOR52Y8vJyPfzww/Ly8tLMmTPVuXNnHTlyRGVlZS5x8+bNU25urmbMmKEuXbpo9erVGjt2rDZv3iw/Pz9JUklJicaMGaNevXpp2bJlOnnypBYuXKizZ89qzpw5Rq7Nmzdr9uzZGj9+vPr376/c3FxNnDhR69atU2RkZJPeEwAAAABtD4U/AAAuMHDgQA0ePFiSNGPGDH3xxRd1YrKysnTmzBm988476tixoyQpJibGJebEiRN688039cwzz2j48OGSpIiICA0YMEBvvPGGUlNTJUlvvPGGzpw5o+XLlysgIECSVFNTo2effVZpaWnq0qWLJCkjI0P333+/pkyZIknq37+/Dhw4oBUrVig7O9vt9wEAAABA28arvgAAXMBsvnz3+Oabb+qXv/ylUfSrz86dO2W323XfffcZ2wICAhQXF6e8vDxjW15enmJjY42inyQlJibKbrdr165dkqSioiIdOXJEiYmJLudISkpSfn5+va8FAwAAALi2UfgDAOAqffvtt/r+++8VGBio8ePH6/bbb1e/fv00a9YsnTlzxogrKChQ586d5e/v73J8WFiYyzx/BQUFCg0NdYmxWq0KDg424pw/Q0JC6uSqqqpSUVGRW6+xuZnNJnl7m+XtbZbZbGrp5gAAAAAegVd9AQC4Sv/6178kSYsWLdK9996r7OxsHTlyREuWLFF5ebmef/55SbWLfzjn8Tuf1WpVSUmJ8bvNZpPVaq0T5+/vb8Q5f14Y5/z9/HwN4e196WeBXl6N238pJpNJfn7tjRw1NXaVlp6td25FAAAAAFeOwh8AAFfJbrdLqh19t2jRIklSbGysvL29NWvWLKWnp6t79+4t2cSrYjabFBjo26gcVmuHRrdjxfra15onjI5TQMDFX6EGAAAAcGUo/AEAcJWcr+5euJhH//79JdWuCty9e3dZrdY6q/xKtSP8zn/912q1qrS0tE5cSUmJEef8WVpaquDgYJdc5+9vCLvdIZut/JIxXl7mSxb3bLYK1dTYG3R+Z+5jp84fBdnwfADQkqzWDo0aBQ0AgDtR+AMA4Cp1795dFovlovvPnTsnSQoNDdW//vUvlwKeVHdOv9DQUJc5/6TaAt/3339vxDl/XnhsQUGB2rVr1+gRhtXVjSuy1dTYG52jKfMBAAAA1yIeRQEAcJUsFovi4uKUn5/vsv3vf/+7JOm2226TJMXHx8tsNmvr1q1GTElJiXbu3KmEhARjW0JCgv7+978bo/ckacuWLTKbzYqLi5NUW2zs1auXtmzZ4nLO3NxcxcbGXrIQCQAAAODaxIg/AAAuUFFRoR07dkiSjh07prKyMqPg1q9fPwUFBWnixIkaNWqUpk6dqp///Oc6evSolixZop/97Gfq0aOHJOmGG27Q8OHDtXjxYpnNZnXp0kWZmZny8/PTqFGjjPONGjVKr776qiZMmKC0tDSdPHlSixcv1qhRo9SlSxcjbtKkSZo2bZp69OihmJgY5ebmau/evXrttdea8e4AAOD5zGZTo1eZt9sdsttZqApAy6LwBwDABf7973/rySefdNnm/P2VV15RTEyMbr/9dmVnZ+u5557T448/Ln9/f40cOVLp6ekux82aNUu+vr5asmSJzpw5o+joaL300ksuq/36+/tr7dq1+v3vf68JEybI19dXw4cPr5Nr2LBhqqioUHZ2trKyshQSEqLly5crKiqqie4EAADXHrPZpICAjo2eq7Gmxq7i4nKKfwBaFIU/AGgi7nhSjCvj7ifq3bp10/79+y8bFxsbq02bNl0yxmKxaPr06Zo+ffol48LCwvTyyy9f9pwjRozQiBEjLhsHAAAaxmw2ycvLrBXrd7ksPHU1brreXxNGx8lsNlH4A9CiKPwBQBNw15NiXBmeqAMAAHc7dqpER4790NLNAIBGofAHAE3AHU+KcWV4og4AAAAA9aPwBwBNiCfFAAAAAICWwjtoAAAAAAAAgAei8AcAAAAAAAB4IAp/AAAAAAAAgAei8AcAAAAAAAB4IAp/AAAAAAAAgAei8AcAAAAAAAB4IAp/AAAAAAAAgAei8AcAAAAAAAB4IAp/AAAAAAAAgAei8AcAAAAAAAB4IAp/AACgzTCbTfL2NstsNrV0UwAAAIBWz7ulGwAAAHAlzGaTAgI6ysvLrJoau4qLy2W3O1q6WQAAAECrxYg/AADQJpjNJnl5mfXWh/+Ulxej/gAAAIDLYcQfAABoU74vPtPSTQAAoNUwm02NfhhmtzsYRQ94KAp/AAAAAAC0QedPg9EYTKEBeC4KfwAAAADQjP7yl7/o6aefrrM9NTVV06ZNM37fuHGjXnzxRX333XcKCQlRenq6BgwY4HJMaWmpFixYoA8//FBVVVW6++67NWvWLF1//fUucbt379aiRYu0b98+de7cWaNHj1ZqaqpMph9HijkcDmVnZ+v111/X6dOnFR4erqefflqRkZHuvQFwG+c0GCvW79KxUyUNynHT9f6aMDpOZrOJwh/ggSj8AQAAAEALePHFF+Xn52f83qVLF+PfN2/erNmzZ2v8+PHq37+/cnNzNXHiRK1bt86lEDdlyhQdOnRIc+fOlY+Pj5YuXarU1FRt2rRJ3t61X/eOHj2qlJQUxcXFacqUKdq/f7+ee+45eXl5KSUlxciVnZ2tjIwMTZs2TX369NG6deuUnJyst99+W927d2/6G4IGO3aqREeO/dDSzQDQClH4AwAAAIAWcNtttykoKKjefRkZGbr//vs1ZcoUSVL//v114MABrVixQtnZ2ZKkPXv2aOfOncrJyVF8fLwkKSQkRElJSdq6dauSkpIkSTk5OQoMDNTzzz8vi8Wi2NhYnT59WqtXr9bDDz8si8Wic+fOKTMzU8nJyRo7dqwk6c4779R9992nnJwczZ07t0nvBQCgabCqLwAAAAC0IkVFRTpy5IgSExNdticlJSk/P1+VlZWSpLy8PFmtVsXFxRkxoaGhCg8PV15enrEtLy9PgwYNksVicclls9m0Z88eSbWvApeVlbmc02KxaMiQIS65AABtS6sq/B09elRz5szRgw8+qFtvvVXDhg2rN27jxo0aOnSoIiIi9MADD2j79u11YkpLSzVz5kz169dPUVFRmjx5sk6dOlUnbvfu3Ro5cqT69u2rAQMGKCsrSw6H67wGDodDWVlZuueee9S3b1+NHDlSn332WZ1cJ0+e1KRJkxQVFaV+/frpt7/9rcrKyhp2MwAAAAB4tGHDhik8PFyDBg1SZmamampqJEkFBQWSakfvnS8sLExVVVUqKioy4kJCQlzm6ZNqi3/OHOXl5Tp+/LhCQ0PrxJhMJiPO+fPCuLCwMH333Xc6e/asOy4ZANDMWtWrvgcPHtSOHTt0xx13yG631ynASa13rouqqio99thjkqQlS5bo7NmzWrRokaZOnarMzMwmvGsAAAAA2pLg4GBNmjRJd9xxh0wmkz766CMtXbpUJ0+e1Jw5c1RSUrtIg9VqdTnO+btzv81mc5kj0Mnf319ffPGFpNoBEfXlslgs6tChg0sui8UiHx+fOud0OBwqKSlR+/btG3zNjV11tqlyNXV+2gqgpbWqwt/AgQM1ePBgSdKMGTOMzup8rXWui7/+9a86ePCgcnNzjadkVqtVKSkp2rt3r/r27dtUtw0eyGw2yWw2XT4QjWa3O1i9DAAANKu7775bd999t/F7fHy8fHx8tHbtWo0fP74FW9Y0zGaTrNYObsvnzlxNjbYCaGmtqvBnNl/6CYNzrounnnrKZXtSUpIWL16syspKWSyWy8514Sz85eXlaciQIXXmusjMzNSePXsUExNzybkuPvjgA2NbXl6e+vTp4zI0Pi4uTgEBAdqxYweFP1wxs9mkgICOPHFrJjU1dhUXl1P8AwAALSoxMVFr1qzRvn375O/vL6l2tF5wcLARY7PZJMnYb7VadeLEiTq5SkpKjBjniEDnyD+nyspKVVRUuOSqrKzUuXPnXEb92Ww2mUwmI64h7HaHzpw567bCks1WoZoau1ty1cfLy0xbAbRaVmuHq6oXtKrC3+VcyVwXYWFhbpvrIiYm5pJzXaxdu1Znz55V+/btVVBQUCfGZDIpJCTEyAFcCbPZJC8vs1as36Vjp0paujke7abr/TVhdJzMZhOFPwAA0Go4v1dc+B2joKBA7dq1M6YbCg0NVX5+vhwOh8t3n8LCQvXu3VuS1LFjR9144411vpMUFhbK4XAY+Z0/CwsLdcstt7ics2vXro16zVeSWwtKNTV2VVe3jQIVbQXQ0tpU4a81z3VxqXM6czWGt/flq7mMEGt+TXHPnTmPnSrRkWM/uD0/6mrKzxHNh3sOAGjLcnNz5eXlpVtvvVXBwcHq1auXtmzZYkyF5IyJjY013lhKSEjQypUrlZ+fr5/85CeSagt3X331lTH/uDNu27Zteuqpp9SuXTsjl9VqVVRUlCQpOjpanTp10vvvv28U/qqqqrR161YlJCQ0yz0AALhfmyr8XavMZpMCA31buhmoB/NgeAY+R8/A5wgAaCtSUlIUExOjPn36SJK2bdumDRs26JFHHjFe7Z00aZKmTZumHj16KCYmRrm5udq7d69ee+01I09UVJTi4+M1c+ZMTZ8+XT4+PnrhhRfUp08f3XvvvS7ne/fddzV16lSNHj1aBw4cUE5OjtLT040ioo+Pj9LS0rRs2TIFBQWpd+/eWr9+vYqLi10WPgQAtC1tqvDXmue6sFqtKisrq/ecN954Y8Mu+P+x2x2y2covG+fO+R1wZZpiHgw+x+bH5+gZruRzvNr5MAAAaAohISHatGmTTpw4Ibvdrl69emnmzJl6+OGHjZhhw4apoqJC2dnZysrKUkhIiJYvX26M0HNaunSpFixYoDlz5qi6ulrx8fGaNWuWvL1//KrXs2dP5eTkaOHChRo3bpyCgoI0efJkJScnu+RKTU2Vw+HQmjVrdPr0aYWHhysnJ8d4tRgA0Pa0qcJfa57rIjQ0VAcOHHDJ5XA4VFhY6LLISEMx10LrxDwYnoHP0TO483M8evSocnJy9Pnnn+vgwYMKDQ3Ve++9d9H4Dz/8UBMmTNB//Md/1IkrLS3VggUL9OGHH6qqqkp33323Zs2apeuvv94lbvfu3Vq0aJH27dunzp07a/To0UpNTXXpxxwOh7Kzs/X6668bX8iefvppRUZGuuW6AQDNY9asWVcUN2LECI0YMeKSMX5+fpo/f77mz59/ybjo6Ght2LDhkjEmk0lpaWlKS0u7ovYBAFq/NjXsoXv37sZcF+erb66LkpIS5efnGzHOuS7On5/COddFVVWVS66LzXXhVN9cFwkJCfr666915MgRY1t+fr6Ki4v105/+1D03AADQLA4ePKgdO3aoZ8+eCgsLu2Ts2bNnNX/+fF133XX17p8yZYp27dqluXPn6rnnnlNhYaFSU1NVXV1txBw9elQpKSkKDg5WZmamxowZo4yMDK1Zs8YlV3Z2tjIyMjR27FhlZmYqODhYycnJKioqavxFAwAAAPA4rWrEX0VFhXbs2CFJOnbsmMrKyowiX79+/RQUFNRq57oYOnSoMjMzNWnSJP36179WRUWFFi9erHvuuUd9+/ZtjtsHAHCTgQMHGpOpz5gxw1gYqj6ZmZnq2rWrunXrViduz5492rlzp3JychQfHy+p9vWupKQkbd26VUlJSZKknJwcBQYG6vnnn5fFYlFsbKxOnz6t1atX6+GHH5bFYtG5c+eUmZmp5ORkjR07VpJ055136r777lNOTo7mzp3r/hsBAAAAoE1rVYW/f//733ryySddtjl/f+WVVxQTE9Nq57po166dXnzxRc2bN0+//vWv5e3trSFDhmjmzJnuvk0AgCZmNl/ZgPhvvvlGL730kt544w29/PLLdfbn5eXJarW6TPkQGhqq8PBw5eXlGYW/vLw8DRkyxHjoJElJSUnKzMzUnj17FBMTo927d6usrEyJiYlGjMVi0ZAhQ/TBBx808EoBAAAAeLJWVfjr1q2b9u/ff9m41jrXRZcuXbRs2bJLxgAAPMcf/vAHPfjggy5zwJ6voKBAISEhLvP0SbXFP+ccs+Xl5Tp+/LjL3LXOGJPJpIKCAsXExBjxF8aFhYVp7dq1Onv2rDHvLAAAAABIrazwBwBAW/HRRx9pz549deadPZ/NZjNWkT+fv7+/8Vqwc3V5q9XqEmOxWNShQweVlJQYuSwWi8sK887jHA6HSkpKGlX48/a+9CjHy62G3JjVkus79kq2sUIzAAAAcGkU/gAAuErnzp3T/PnzNWnSJAUFBbV0cxrNbDYpMNC3UTms1g5uas2V53P3OQEAAABPQ+EPAICrtHbtWpnNZt1///2y2WySald8t9vtstlsat++vSwWi6xWq06cOFHn+JKSEvn7+0uSMSLQOfLPqbKyUhUVFUac1WpVZWWlzp075zLqz2azyWQyGXENYbc7ZLOVXzLGy8t8yUKbzVahmhq7yzaTySQ/v/bGyLyaGrtKS8/K4XBcNnd9+S6Mqy8GAFqa1dqBEckAgFaDwh8AAFepoKBAR48eVWxsbJ19//mf/6m5c+dq9OjRCg0NVX5+vhwOh8s8f4WFherdu7ckqWPHjrrxxhuNOfzOj3E4HMacfs6fhYWFLnMKFhQUqGvXro2e36+6unEFtJoae50c3t5meXmZtWL9LknShNFxcjgcV3Su+vI1JAYAgNbCbDbJbDZdPvAS7HaH7HbH5QMB4P+h8AcAwFVKTU3Vz3/+c5dtWVlZKiws1IIFC9SrVy9JUkJCglauXKn8/Hz95Cc/kVRbuPvqq6/02GOPGccmJCRo27Zteuqpp9SuXTtJUm5urqxWq7FqfXR0tDp16qT333/fKPxVVVVp69atSkhIaOpLbpRjp0paugkAALQos9mkgICOjR4NWlNjV3FxOcU/AFeMwh8AABeoqKjQjh07JEnHjh1TWVmZsYhHv379FBYWprCwMJdj3nrrLZ08eVIxMTHGtqioKMXHx2vmzJmaPn26fHx89MILL6hPnz669957jbiUlBS9++67mjp1qkaPHq0DBw4oJydH6enpslgskiQfHx+lpaVp2bJlCgoKUu/evbV+/XoVFxcrJSWlqW8JAABoBLPZZIyCb+gDsZuu99eE0XEym00U/gBcMQp/AABc4N///reefPJJl23O31955RWX4t7lLF26VAsWLNCcOXNUXV2t+Ph4zZo1S97eP3bBPXv2VE5OjhYuXKhx48YpKChIkydPVnJyskuu1NRUORwOrVmzRqdPn1Z4eLhycnLUvXv3RlwtAABoLsdOlejIsR9auhkAriEU/gAAuEC3bt20f//+qzpm4cKF9W738/PT/PnzNX/+/EseHx0drQ0bNlwyxmQyKS0tTWlpaVfVNly98+dhYj4lAAAAtFUU/gAAAM5z4TxMzKcEAACAtorCHwAAwHnOn4dJEvMpAQAAoM2i8AcAAFAPViMGAABAW9e4tcQBAAAAAAAAtEoU/gAAAAAAAAAPROEPAAAAAAAA8EAU/gAAAAAAAAAPROEPAAAAAAAA8EAU/gAAAAAAAAAPROEPAAAAAAAA8EDeLd0AAACAC3l51T6btNsdstsdLdwaAAAAoG2i8AcAAFoNf7/2stsdslo7SJJqauwqLi6n+AcAAAA0AIU/AADQavi2t8hsNmnF+l2SpAmj42Q2myj8AQAAAA1A4Q8AALQ6x06VtHQTAAAAgDaPxT0AAAAAAAAAD0ThDwAAAAAAAPBAFP4AAAAAAAAAD0ThDwAAAAAAAPBAFP4AAAAAAAAAD0ThDwAAAAAAAPBAFP4AAAAAAAAAD0ThDwAAAAAAAPBAFP4AAAAAAAAAD0ThDwAAAAAAAPBAFP4AAAAAAAAAD0ThDwAAAAAAAPBAFP4AAAAAAAAAD0ThDwAAAAAAAPBAFP4AAAAAAAAAD0ThDwAAAAAAAPBAFP4AAAAAAAAAD0ThDwCACxw9elRz5szRgw8+qFtvvVXDhg1z2V9WVqZly5Zp+PDhuuuuu/STn/xE48eP1/79++vkKi0t1cyZM9WvXz9FRUVp8uTJOnXqVJ243bt3a+TIkerbt68GDBigrKwsORwOlxiHw6GsrCzdc8896tu3r0aOHKnPPvvMrdcOAAAAwHNQ+AMA4AIHDx7Ujh071LNnT4WFhdXZ/9133+nPf/6z4uLitHTpUv3+979XaWmpRo4cqcOHD7vETpkyRbt27dLcuXP13HPPqbCwUKmpqaqurjZijh49qpSUFAUHByszM1NjxoxRRkaG1qxZ45IrOztbGRkZGjt2rDIzMxUcHKzk5GQVFRU1zY0AAAAA0KZ5t3QDAABobQYOHKjBgwdLkmbMmKEvvvjCZX+3bt30wQcfqEOHDsa2/v37a+DAgXr99dc1e/ZsSdKePXu0c+dO5eTkKD4+XpIUEhKipKQkbd26VUlJSZKknJwcBQYG6vnnn5fFYlFsbKxOnz6t1atX6+GHH5bFYtG5c+eUmZmp5ORkjR07VpJ055136r777lNOTo7mzp3bxHcFAAAAQFvDiD8AAC5gNl+6e+zYsaNL0U+SfH191aNHD5fXePPy8mS1WhUXF2dsCw0NVXh4uPLy8lziBg0aJIvFYmxLSkqSzWbTnj17JNW+ClxWVqbExEQjxmKxaMiQIS65AAAAAMCJwh8AAG5gs9l08OBBhYaGGtsKCgoUEhIik8nkEhsaGqqCggJJUnl5uY4fP+5ynDPGZDIZcc6fF8aFhYXpu+++09mzZ91+TQAAAADaNl71BQDADf74xz/KZDJp9OjRxjabzSY/P786sf7+/sbrw6WlpZIkq9XqEmOxWNShQweVlJQYuSwWi3x8fFzirFarHA6HSkpK1L59+wa339v70s8Cvbyufn9jttW3/8K4yx3XUA1pIwAAANAaUfgDAKCRNm3apA0bNmjhwoW64YYbWro5V81sNikw0LdROazWDpcPuoq4KzmmIbkaqjnPBQAAALgLhT8AABphx44dmjNnjp544gn9/Oc/d9lntVp14sSJOseUlJTI399fkowRgc6Rf06VlZWqqKgw4qxWqyorK3Xu3DmXUX82m00mk8mIawi73SGbrfySMV5e5ksWv0pLz8rhcMhud8jhcFz0GJutQjU19qvK7Tzmwrj6crnDlbYbAOpjtXZglDAAoNWg8AcAQAN99tlnevLJJ/XQQw/pySefrLM/NDRU+fn5cjgcLvP8FRYWqnfv3pJqFwq58cYbjTn8zo9xOBzGnH7On4WFhbrllluMuIKCAnXt2rVRr/lKUnV144paHTta5OVlVk2NXcXF5bLbHfXG1dTYr/pcFzumIbkaqjnPBeDac+bMGSUmJurkyZN68803FRERYezbuHGjXnzxRX333XcKCQlRenq6BgwY4HJ8aWmpFixYoA8//FBVVVW6++67NWvWLF1//fUucbt379aiRYu0b98+de7cWaNHj1ZqaqpLH+VwOJSdna3XX39dp0+fVnh4uJ5++mlFRkY26T0AADQNHkUBANAAhw4dUlpamvr3769nn3223piEhASVlJQoPz/f2FZYWKivvvpKCQkJLnHbtm1TVVWVsS03N1dWq1VRUVGSpOjoaHXq1Envv/++EVNVVaWtW7e65GopXl5mvfXhP+XlZZbZbLr8AQAAw8qVK1VTU1Nn++bNmzV79mwlJiYqOztbkZGRmjhxoj777DOXuClTpmjXrl2aO3eunnvuORUWFio1NVXV1dVGzNGjR5WSkqLg4GBlZmZqzJgxysjI0Jo1a1xyZWdnKyMjQ2PHjlVmZqaCg4OVnJysoqKiJrl2AEDTYsQfAAAXqKio0I4dOyRJx44dU1lZmbZs2SJJ6tevnxwOh1JSUuTj46MxY8YYC3VIUqdOnXTzzTdLkqKiohQfH6+ZM2dq+vTp8vHx0QsvvKA+ffro3nvvNY5JSUnRu+++q6lTp2r06NE6cOCAcnJylJ6eLovFIkny8fFRWlqali1bpqCgIPXu3Vvr169XcXGxUlJSmuvWXNL3xWdaugkA0OYcPnxYr7/+uqZPn65nnnnGZV9GRobuv/9+TZkyRZLUv39/HThwQCtWrFB2drYkac+ePdq5c6dycnIUHx8vSQoJCVFSUpK2bt2qpKQkSVJOTo4CAwP1/PPPy2KxKDY2VqdPn9bq1av18MMPy2Kx6Ny5c8rMzFRycrLGjh0rSbrzzjt13333KScnR3Pnzm2WewIAcJ82Wfjbtm2bVq9erUOHDsnX11d33nmnpk2bpu7du7vEMSweANAQ//73v+u8uuv8/ZVXXpEkY+4+5xcjp379+unVV181fl+6dKkWLFigOXPmqLq6WvHx8Zo1a5a8vX/sgnv27KmcnBwtXLhQ48aNU1BQkCZPnqzk5GSX3KmpqXI4HFqzZo3Rz+Tk5NTp/wAAbce8efM0atQohYSEuGwvKirSkSNH9NRTT7lsT0pK0uLFi1VZWSmLxaK8vDxZrVbFxcUZMaGhoQoPD1deXp5R+MvLy9OQIUOMB0rOXJmZmdqzZ49iYmK0e/dulZWVKTEx0YixWCwaMmSIPvjgg6a4fABAE2tzhb+PP/5YEydO1EMPPaT09HQVFxfrT3/6k5KTk/Xuu+8acxw5h8WPHz9e/fv3V25uriZOnKh169a5FOKmTJmiQ4cOae7cufLx8dHSpUuVmpqqTZs2GV/KnMPi4+LiNGXKFO3fv1/PPfecvLy8XEZZOIfFT5s2TX369NG6deuUnJyst99+my9lANCGdOvWTfv3779kzOX2O/n5+Wn+/PmaP3/+JeOio6O1YcOGS8aYTCalpaUpLS3tis4NAGjdtmzZogMHDmjZsmX68ssvXfY55369sCAYFhamqqoqFRUVKSwsTAUFBQoJCXEZkCDVFv+cOcrLy3X8+HFjvtjzY0wmkwoKChQTE2PEXxgXFhamtWvX6uzZsw2eU9adC5409eIpTdHWprr+tnRfAbSMNlf427x5s7p27ar58+cbnVtQUJDxqtVdd90liWHxAAAAAFqviooKLVy4UOnp6erUqVOd/SUlJZJqV3U/n/N3536bzWasEH8+f39/YyoK58rxF+ayWCzq0KGDSy6LxeKyerzzOIfDoZKSkgYV/sxm0yVXb79a7szV1JqirU11/W3pvgK4cm2u8FddXS1fX1+XJ1rOjs7hqF1BkGHxAAA0jNlsMhbnsNsdF12dFwDQOKtWrVLnzp31y1/+sqWb0uTsdofOnDnrtsKSzVahmpqmW2ndy8vs9rY2RU6padoKoHWzWjtc1QjdNlf4+8UvfqG3335b69at0wMPPKDi4mI9//zzuvXWWxUdHS3J84bFAwDQHMxmkwICOhp/kaipsau4uJziHwC42bFjx7RmzRqtWLHCGI1XXl5u/Dxz5oz8/f0l1Y7WCw4ONo612WySZOy3Wq3GvLPnKykpMWKcAyWc53KqrKxURUWFS67KykqdO3fOZdSfzWaTyWQy4hrCnQWlmhq7qqvbRoGqKdraVNfflu4rgCvX5gp/d911l5YvX66pU6fqd7/7nSQpPDxcL774ory8vCR51rB4J2/vy1dzmZOh+TXFPedzbH58jp6Be954ZrNJXl5mrVi/S5I0YXSczGYThT8AcLNvv/1WVVVVGjduXJ19jzzyiO644w4tWbJEUu2ghvMHFxQUFKhdu3bGHOKhoaHKz8+Xw+FwGdBQWFio3r17S5I6duyoG2+80RiscH6Mw+Ew8jt/FhYW6pZbbnE5Z9euXRnIAABtUJsr/O3evVu/+c1v9F//9V+65557VFxcrJUrV2rcuHF6/fXXPbIzMptNCgz0belmoB7Mg+EZ+Bw9A5+j+xw7VdLSTQAAjxYeHm6sEu+0b98+LViwQM8++6wiIiLUvXt39erVS1u2bNHgwYONuNzcXMXGxhrTECUkJGjlypXKz8/XT37yE0m1hbuvvvpKjz32mHFcQkKCtm3bpqeeekrt2rUzclmtVkVFRUmqXWiqU6dOev/9943CX1VVlbZu3aqEhISmuyEAgCbT5gp/8+bNU//+/TVjxgxjW2RkpO655x69/fbbGjlypMcNi7fbHbLZyi8b5875HXBlmmIeDD7H5sfn6Bmu5HO82vkwAABoClarVTExMfXuu+2223TbbbdJkiZNmqRp06apR48eiomJUW5urvbu3avXXnvNiI+KilJ8fLxmzpyp6dOny8fHRy+88IL69Omje++914hLSUnRu+++q6lTp2r06NE6cOCAcnJylJ6ebhQRfXx8lJaWpmXLlikoKEi9e/fW+vXrVVxcrJSUlCa8IwCAptLmCn+HDx/WoEGDXLbdcMMNCgwM1DfffCPpxyHqnjQsnrkWWifmwfAMfI6egc8RAOBphg0bpoqKCmVnZysrK0shISFavny5MULPaenSpVqwYIHmzJmj6upqxcfHa9asWfL2/vHrXs+ePZWTk6OFCxdq3LhxCgoK0uTJk5WcnOySKzU1VQ6HQ2vWrNHp06cVHh6unJwc4zsUAKBtaXOFv65du+qrr75y2Xbs2DH98MMPuummmySJYfEAAAAA2pSYmBjt37+/zvYRI0ZoxIgRlzzWz89P8+fP1/z58y8ZFx0drQ0bNlwyxmQyKS0tTWlpaZdvNACg1Wtzhb9Ro0Zp/vz5mjdvngYOHKji4mKtWrVKnTt3VmJiohHHsHgAAAAAAABcy9pc4e+RRx6RxWLR+vXrtWnTJvn6+ioyMlJLly5VYGCgEceweAAAAAAAAFzL2lzhz2QyafTo0Ro9evRlYxkWDwAAAAAAgGsVSxsCAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAHCBo0ePas6cOXrwwQd16623atiwYfXGbdy4UUOHDlVERIQeeOABbd++vU5MaWmpZs6cqX79+ikqKkqTJ0/WqVOn6sTt3r1bI0eOVN++fTVgwABlZWXJ4XC4xDgcDmVlZemee+5R3759NXLkSH322WduuWYAAAAAnofCHwAAFzh48KB27Nihnj17KiwsrN6YzZs3a/bs2UpMTFR2drYiIyM1ceLEOoW4KVOmaNeuXZo7d66ee+45FRYWKjU1VdXV1UbM0aNHlZKSouDgYGVmZmrMmDHKyMjQmjVrXHJlZ2crIyNDY8eOVWZmpoKDg5WcnKyioiK33wMAAAAAbZ93SzcAAIDWZuDAgRo8eLAkacaMGfriiy/qxGRkZOj+++/XlClTJEn9+/fXgQMHtGLFCmVnZ0uS9uzZo507dyonJ0fx8fGSpJCQECUlJWnr1q1KSkqSJOXk5CgwMFDPP/+8LBaLYmNjdfr0aa1evVoPP/ywLBaLzp07p8zMTCUnJ2vs2LGSpDvvvFP33XefcnJyNHfu3Ka9KQAAAADaHEb8AQBwAbP50t1jUVGRjhw5osTERJftSUlJys/PV2VlpSQpLy9PVqtVcXFxRkxoaKjCw8OVl5dnbMvLy9OgQYNksVhcctlsNu3Zs0dS7avAZWVlLue0WCwaMmSISy4AAAAAcGLEHwAAV6mgoEBS7ei984WFhamqqkpFRUUKCwtTQUGBQkJCZDKZXOJCQ0ONHOXl5Tp+/LhCQ0PrxJhMJhUUFCgmJsaIvzAuLCxMa9eu1dmzZ9W+ffsGX5O3t1leXnULns5t9e27mEsdc6XbriTf1bTpajSkjQAAAEBrROEPAICrVFJSIkmyWq0u252/O/fbbDb5+fnVOd7f3994fbi0tLTeXBaLRR06dHDJZbFY5OPjU+ecDodDJSUlDS78mc0mBQb61rvPau1w1fkudYw78zUkV0M157kAAAAAd6HwBwDANc5ud8hmK5eXl7lOgctmq1BNjb3efRdzqWOc+853udwXy1dfLne40nYDQH2s1g6MEgYAtBoU/gAAuEr+/v6SakfrBQcHG9ttNpvLfqvVqhMnTtQ5vqSkxIhxjgh0jvxzqqysVEVFhUuuyspKnTt3zmXUn81mk8lkMuIaqrq6/qJWTY39ovsu5lLHuDNfQ3I1VHOeCwAAAHAXHkUBAHCVnPPsOefdcyooKFC7du3UvXt3I66wsFAOh8MlrrCw0MjRsWNH3XjjjXVyOY9zxjl/FhYW1jln165dGzW/HwAAAADP1ODC3//8z//o22+/vej+b7/9Vv/zP//T0PQAAFyRo1//7yX7o+PHv9P777/n1nN2795dvXr10pYtW1y25+bmKjY21lidNyEhQSUlJcrPzzdiCgsL9dVXXykhIcHYlpCQoG3btqmqqsoll9VqVVRUlCQpOjpanTp10vvvv2/EVFVVaevWrS65AADu9f777+n48e8uur8p+hkAANylwYW/p59+Wnv27Lno/r179+rpp59uaHoAAK7IJ9vXX7I/+uqrL7Rgwe+uKmdFRYW2bNmiLVu26NixYyorKzN+P336tCRp0qRJeu+995SRkaGPP/5YzzzzjPbu3asnnnjCyBMVFaX4+HjNnDlT77//vj766CNNnjxZffr00b333mvEpaSk6PTp05o6dary8/O1du1a5eTkaPz48UYR0cfHR2lpaVqzZo3Wrl2r/Px8TZ06VcXFxUpJSbmq6wMAXLkFC36nf/5z70X3N6SfAQCguTR4jr8LX1u6UHl5uby8vBqaHgCAK3Pp7kgVFRVX3R/9+9//1pNPPumyzfn7K6+8opiYGA0bNkwVFRXKzs5WVlaWQkJCtHz5cmOEntPSpUu1YMECzZkzR9XV1YqPj9esWbPk7f1jF9yzZ0/l5ORo4cKFGjdunIKCgjR58mQlJye75EpNTZXD4dCaNWt0+vRphYeHKycnx3i1GADgfpf73tOQfgYAgOZyVYW/r7/+Wl9//bXx+yeffKKampo6cTabTW+88YZCQkIa30IAAC5QXnJSFSU/LprxySefyGYrr7PqallZmd5+e5O6d+9xVfm7deum/fv3XzZuxIgRGjFixCVj/Pz8NH/+fM2fP/+ScdHR0dqwYcMlY0wmk9LS0pSWlnbZtgEAGu7QoYM6ePDHfmDv3j2qqamuE9fQfgYAgOZyVYW/Dz/8UMuXL5dU++Xjz3/+s/785z/XG2u1WrVo0aLGtxAAgAsUH/9ax/fvqP3l//VHF9Opk59mzXq2mVoGAPAEeXnb9dJL2ZJqv/e8/fZf9Pbbf6k3ln4GANCaXVXh77/+6790zz33yOFwaMSIEZo8eXKdCcVNJpM6dOigHj16uLzGBACAuwT3ipb/Df8hOaSv83I0+cnJior6T1VX//g6Vm1/1F5du3ajPwIAXJUHHviFfvKTuyU5lJo6RikpaerfP84lhn4GANAWXFUPdf311+v666+XVDvHUVhYmDp37twkDQMA4GLatfdTu/Z+kqSEB5/QyJEjZTa3V3W1/TJHAgBwedddd52uu+46SVJGxmr16hWiwMCgFm4VAABXr8GPpvr16+fOdgAA0CDBN92szp0764cfzrR0UwAAHigq6s6WbgIAAA3WqDHpf/vb3/Tmm2+qqKhINputzopXJpNJH374YaMaCADA5fztb3/T+vV/1rfffqvSUpsuXIDRZJI2bHi7ZRoHAGjzPv44X++997a+++4Y/QwAoE1pcOHvxRdf1JIlS9S5c2f17dtXffr0cWe7AAC4Ivv3fKS3Vm9WUFCQwsNvU1jYzS3dJACAB3n99Ve0evVyBQYG6dZb6WcAAG1Lgwt/r7zyivr376+srCy1a9fOnW0CAOCKHd6bp/79+2vx4hckebV0cwAAHmbjxjcUHX2Xnnsug0U8AABtToN7LpvNpqFDh1L0AwC0qMpzFRo6dKi8vduxuAcAwO1KS226555BFP1aMbPZJLPZ1KgcdrtDdrvj8oEA0MY0uPeKiIhQYWGhO9sCAMBVC7q+B/0RAKDJhIffpqKioy3dDFyE2WxSQEBHeXmZG5Wnpsau4uJyin8APE6DC39z585Vamqqbr/9dv3sZz9zZ5sAALhikQnD9cEHryok5D80aNDQlm4OAMDDTJ06Q9OmTVafPrfq3nvva+nm4AJms0leXmatWL9Lx06VNCjHTdf7a8LoOJnNJgp/ADxOgwt/U6ZMUXV1tX7zm99o7ty5uuGGG2Q2uz5lMZlMeueddxrdSAAALubjrWvVoZ1dzz47W4sXz1dwcJd6nvqbtHbt+hZpHwCgbXvmmadVU1OjefPmaMmSBfQzrdSxUyU6cuyHlm4GALQ6DS78BQQEKCAgQD179nRnewAAuCqW9h3Vs1tn3XRTdzkcPKUHGss5VxbzXQG1/Pysslr91a1b95ZuCgAAV63Bhb9XX33Vne0AAKBBfvrQRM1/Mkk//HCGxT2ARjp/rizmuwJqLV+e1dJNAACgwRo3AyoAAEArZDab5O1tbvQqj9ca51xZb334T3l5cf8AAADaugaP+Pvf//3fK4r7z//8z4aeAgCAy/r+u8P63//9X5WWVqim5uIjkyIjo5uxVWhJjFprvO+Lz7R0E4BW47PPdl9R3NX0Mzt27FB2drYOHTqksrIydenSRYMHD9bEiRPl5+dnxH300UdaunSpCgsL1bVrV40bN06//OUvXXJVVlbqhRde0DvvvKMzZ84oKipKs2fPVmhoqEvc4cOHNW/ePO3Zs0e+vr568MEHNWXKFFksFpe4jRs36sUXX9R3332nkJAQpaena8CAAVd8bQCA1qXBhb+HH35YJtPlnwLv27evoacAAOCy8v5nhXa+s/LycXn/txlag9bg/FFrPx8cwSqNABpl0qS0K/reczX9THFxsfr27auHH35YAQEBOnjwoJYtW6aDBw9qzZo1kqRPPvlEEydO1PDhwzVz5kz94x//0G9/+1v5+vrqvvt+XF143rx5ys3N1YwZM9SlSxetXr1aY8eO1ebNm40iYklJicaMGaNevXpp2bJlOnnypBYuXKizZ89qzpw5Rq7Nmzdr9uzZGj9+vPr376/c3FxNnDhR69atU2Rk5BVfHwCg9Whw4e+VV16ps62mpkbHjh3Thg0bZLfbNXXq1EY1DgCAy0l48AmlDu+v0tKzqqmpnePPbrfr+PHv9M47b8nhsGv8+Ekt3Eq0BEatAXCHjIzVdbY1tp958MEHXX6PiYmRxWLR7NmzdfLkSXXp0kWrVq1S37599bvf/U6S1L9/fxUVFSkjI8Mo/J04cUJvvvmmnnnmGQ0fPlySFBERoQEDBuiNN95QamqqJOmNN97QmTNntHz5cgUEBEiq/e727LPPKi0tTV26dPl/15qh+++/X1OmTDHOeeDAAa1YsULZ2dlXdY0AgNahwXP89evXr84/sbGxGj58uN544w15e3vr//7fphtd8dZbb+mhhx5SRESEYmJi9Nhjj+ns2bPG/o8++kgPPPCAIiIiNHToUG3atKlOjsrKSi1atEhxcXGKjIzUo48+qoKCgjpxhw8f1qOPPqrIyEjFxcVp8eLFqqysrBO3ceNGDR06VBEREXrggQe0fft29140AKCO4JtuVr9+/RQdfaeiomr/ufPO/9SwYQ9q9eo18vb21p49n7Z0MwEAbZSzbzn/n6boZ5wFuaqqKlVWVurjjz92GdknSUlJSTp8+LC+/fZbSdLOnTtlt9td4gICAhQXF6e8vDxjW15enmJjY41zSFJiYqLsdrt27dolSSoqKtKRI0eUmJhY55z5+fn1fv8BALR+TbK4h9ls1v3336+NGzc2RXqtWrVKv//975WUlKScnBz97ne/U7du3VRTUyPpx2HxkZGRys7OVmJion77299qy5YtLnnmzZunjRs3Kj09XcuWLVNlZaXGjh2r0tJSI8Y5LL6qqkrLli1Tenq6NmzYoIULF7rkcg6LT0xMVHZ2tiIjIzVx4kR99tlnTXIPAACXZzabNWjQvXr33f9p6aYAADxQY/uZmpoanTt3Tl9++aVWrFihgQMHqlu3bvrmm29UVVVVZ56+sLAwSTIGKxQUFKhz587y9/evE3f+gIaCgoI6uaxWq4KDg11ySVJISEidXFVVVSoqKmrQNQIAWlaDX/W9nJKSEpcCmrsUFBRo+fLlWrlypX76058a24cOHWr8O8PiAQBONptNZWXu748AAJAa188MGDBAJ0+elCTdfffdWrJkiaTa71JSbXHufM7fnfttNpvLYiDnxzljnHEX5pIkf39/I+5Kz9lQXl7uG3Nyfq6myNtWcjZlXgCeo8GFv++++67e7TabTZ988olycnJ01113NbhhF/OXv/xF3bp1cyn6nc85LH7atGku25OSkvTee+/p22+/Vbdu3S47LN5Z+LvYsPhnnnlGu3bt0i9+8QtjWPxTTz1V55zO14IvXC0LAOAe5aU/6LvvvlNJSbmqq39cwKGsrFSff75b69e/qjvuiGrBFgIA2rITJ07Uu90d/UxWVpYqKip06NAhrVq1SuPHj9dLL73UmOa2SmazSVZrB7flc2eups7bVnI2ZV4ALavBhb+BAwdedHUrh8OhyMhIPfvssw1u2MV8/vnn6t27t1auXKlXX31VpaWluv322/X000/rjjvuuKJh8d26dbvksPg333zT+L2goEC//OUvXWIaMizeef6G8va+/NMXntA0v6a453yOzY/PsW17/9Xf66/r5tW7z+Fw6PbbIzRjxqwr+nMUAIALjRjxs0t+77nttgg99dTMBuW+5ZZbJElRUVGKiIjQgw8+qA8++EA333yzJNV5g8pms0mS8R3GarWqrKysTl6bzebyPcdqtdb7NlZJSYkR5/xZWlqq4ODgi56zIex2h86cOeu2wpLNVmEs6OXlZXZ73raSU2qa6wfQulmtHa7q+2aDC3/z58+v0wGaTCZZrVb16NHD6Kzc7fvvv9cXX3yhAwcO6JlnnlGHDh20evVqJScna+vWrR45LN5sNikw0LdROdA0eCrmGfgc27Y7B47SiHvvcNnWHP0RAODa8PTTc+ot/Pn5WXXTTd0UEhJaz1FXr0+fPmrXrp2++eYbDRw4UO3atVNBQYHuvvtuI8Y54MA5yCE0NFT/+te/XAp4zrjzB0KEhobWWcSwtLRU33//vUuu+o4tKChQu3bt1L1790ZdnzsLSjU1dlVXu79A1RR520rOpswLoGU1uPD3i1/8wp3tuGIOh0Pl5eX605/+ZDwhu+OOOzRw4EC99tprio+Pb5F2NSW73SGbrfyyce582oMr0xRPxfgcmx+fY9vW65Z++vnPky76Of7wwxnj36/26RgAAElJP2uW83z++eeqqqpSt27dZLFYFBMTo7/+9a8aM2aMEZObm6uwsDB169ZNkhQfHy+z2aytW7dqxIgRkmoHHezcuVNPPPGEcVxCQoJWr17tMqhhy5YtMpvNiouLkyR1795dvXr10pYtWzR48GCXc8bGxjJ1EQC0UW5Z3OPQoUM6duyYJOmmm25q0tEVVqtVAQEBRtFPqp2b79Zbb9WhQ4d0//33S/KcYfFOPHlpnXgq5hn4HD1DTY1dBw8e0okTxyVJN9xwo9tGYQAAIEmFhQVu6WcmTpyo22+/XX369FH79u319ddfKycnR3369DGKbo8//rgeeeQRzZ07V4mJifr444/13nvv6YUXXjDy3HDDDRo+fLgWL14ss9msLl26KDMzU35+fho1apQRN2rUKL366quaMGGC0tLSdPLkSS1evFijRo0yFiuUpEmTJmnatGnq0aOHYmJilJubq7179+q1115r0HUCAFpeowp/H374oRYuXGgU/Zy6deumGTNmaNCgQY1qXH1uvvlmffPNN/XuO3funHr06OFxw+IBAJf24Ycfav78BTp+3HXhqRtv7KpJk9IVH1//glAAAFyJv/3t/9OyZS8YRT+nhvYzffv2VW5urrKysuRwOHTTTTdpxIgRSklJMUbW3XXXXVq2bJmWLl2qN998U127dtW8efOUmJjokmvWrFny9fXVkiVLdObMGUVHR+ull15ymdbI399fa9eu1e9//3tNmDBBvr6+Gj58uNLT011yDRs2TBUVFcrOzlZWVpZCQkK0fPlyRUWxSBYAtFUNLvzt2LFDkydPVteuXZWenm4sXnH48GFt2LBBkyZN0urVq5WQkOC2xkq1S97/5S9/0b59+xQeHi5J+uGHH/Tll19q7NixDIsHgGvM8aNfaXLmGt1ww40aN+4J9epVu9DSkSOFeuedt/Tb3/5Gixa9oP79f9LCLQUAtEX5+Ts1a9Z0delyg9v6mXHjxmncuHGXjRs0aNBlB1NYLBZNnz5d06dPv2RcWFiYXn755cuec8SIEcb3IwBA29fgwt/KlSvVp08frVu3Th07djS2Dxo0SP/93/+tX/3qV1qxYoXbC3+DBw9WRESEJk+erPT0dPn4+CgrK0sWi0W/+tWvJDEsHgCuJV9/slV9+vTRihXZatfOx9geH/9T/fKXI/XEEyl66aVsCn9tmMlkkre3+aKragJAU3r55RyFhd2sFSteVIcOP87fSz8DAGgLGjzD+f79+/XQQw+5FP2cOnbsqJ///Ofav39/oxpXH7PZrKysLEVGRmrOnDn69a9/rU6dOmndunXG/HrOYfGffvqpUlJS9N577110WPzw4cO1ZMkSTZgwQd7e3hcdFu/l5aUJEyZoyZIlGj58uGbMmOGSa9iwYfr973+v9957TykpKdq9ezfD4gGgGZT8+7geeughly9jTh06dFBi4s90+PDBFmgZ3MXPr70CA33l59e+pZsC4Bp0+PBB3XffMPoZAECb1OARfz4+PiopKbno/pKSEvn4+Fx0f2MEBQXpj3/84yVjGBYPANcGLy/vS/ZHpaU2WSxN0x+heXh5mfXWh//UzwdHtHRTAFyDLBYflZbaLrqffgYA0Jo1eMRfTEyMXnnlFe3Zs6fOvs8//1yvvvqqYmNjG9U4AAAuJ7jbf+iVV17RP//5eZ19X375hTZufEN33dWvSc69bds2jRgxQlFRUYqPj9eTTz6poqKiOnEbN27U0KFDFRERoQceeEDbt2+vE1NaWqqZM2eqX79+ioqK0uTJk3Xq1Kk6cbt379bIkSPVt29fDRgwwJgY3tN9X3ympZsA4BoVHX2XNm5cry++2FtnX1P3MwAANFaDR/w99dRTGjVqlH71q1+pb9++CgmpneS2sLBQe/fuVefOnTVt2jS3NRQAgPpExP5Mn2xZrbS0FIWH36YePXpKkr755qj27ftSgYGBevzxSW4/78cff6yJEyfqoYceUnp6uoqLi/WnP/1JycnJevfdd9W+fe1rqZs3b9bs2bM1fvx49e/fX7m5uZo4caLWrVunyMhII9+UKVN06NAhzZ07Vz4+Plq6dKlSU1O1adMmeXvXdtdHjx5VSkqK4uLiNGXKFO3fv1/PPfecvLy8lJKS4vZrBABITzwxWePHJ+uJJx5r1n4GAAB3aHDhr3v37nrnnXeUmZmpvLw85ebmSpK6du2qRx55ROPGjVPnzp3d1lAAAOrja+2sd955RxkZy/X3v+/Stm0fSKpdxGnEiFH67/8eq8DAILefd/Pmzeratavmz59vLDoRFBSkMWPG6IsvvtBdd90lScrIyND999+vKVOmSJL69++vAwcOaMWKFcrOzpYk7dmzRzt37lROTo7i4+MlSSEhIUpKStLWrVuVlJQkScrJyVFgYKCef/55WSwWxcbG6vTp01q9erUefvhhVpEHgCbQtetNWrt2vV599SX94x9/b7Z+BgAAd2hw4a+6ulo+Pj6aOXOmZs6cWWd/WVmZqqurjVEKAAA0Bbu9Rj4+PpoyZZomTvx1nf1nzjRNf1RdXS1fX1+XlWadi0M5X70tKirSkSNH9NRTT7kcm5SUpMWLF6uyslIWi0V5eXmyWq2Ki4szYkJDQxUeHq68vDyj8JeXl6chQ4a4FPiSkpKUmZmpPXv2KCYmxq3XCACo/fPeYrFo8uSpmjx5ap39TdXPAADgDg2e42/evHkaNWrURfePHj1aCxcubGh6AACuyOd/e+uS/dHjj6do+fKlbj/vL37xCx0+fFjr1q1TaWmpioqK9Pzzz+vWW29VdHS0JKmgoECSjOkwnMLCwlRVVWXMB1hQUKCQkBCXIqJUW/xz5igvL9fx48cVGhpaJ8ZkMhlxAAD3Wrr0OY0fn3zR/U3VzwAA4A4Nfiz1t7/9TQ899NBF9w8dOlTvvPNOQ9MDAHBFThTtU/Ijv7ro/nvuGaStW9+X5N55Z++66y4tX75cU6dO1e9+9ztJUnh4uF588UV5eXlJkrHasNVqdTnW+btzv81mM0YLns/f319ffPGFpNrFP+rLZbFY1KFDh0uubHwlvL3N8vKq+zzQua2+fRdzqWOudNvVnOdy2682vzvb2NY09t4Bnuj//t98JSbeL2/v+v9/GDhwsLZsyZW392+auWUAAFxegwt/p06dUpcuXS66//rrr9fJkycbmh4AgCty9oztkv3RddcF6/vv666O21i7d+/Wb37zG/3Xf/2X7rnnHhUXF2vlypUaN26cXn/9dWNxj7bAbDYpMNC33n1Wa4erznepYxqSr7G53HFOd7a7LblWrxs437/+9b169ep+0T8ne/bspn/96/uL7gcAoCU1uPAXEBCgwsLCi+4/fPiwOnXq1ND0AABcEUt730v2R0ePFsrX1/390bx589S/f3/NmDHD2BYZGal77rlHb7/9tkaOHCl/f39JtaP1goODjTibzSZJxn6r1aoTJ07UOUdJSYkR4xwR6Bz551RZWamKigojriHsdodstnJ5eZnrFHpstgrV1Njr3XcxlzrGue98V5P7crnqy3exuIu50nZ7osbeO8AT+fv7a9++A/rhhzP17v/yy6/VsaOvsd9q7cBoWQBAq9Hgwt/dd9+tN954Qz/72c906623uuz78ssvtWHDBt13332NbiAAAJdyQ/db9MYbb+inPx2ssLDeLvv27/9a77zzlgYMGOz28x4+fFiDBg1ybcsNNygwMFDffPONJBnz8RUUFLjMzVdQUKB27dqpe/fuRlx+fr4cDofLPH+FhYXq3bv2mjp27Kgbb7yxzlx+hYWFcjgcdeb+u1rV1fUXd2pq7BfddzGXOqYh+RpyHnef053tbkuu1esGztevX6zeemuTBg8eqt69b3HZt3//13r77b9owIDB/L8CAGiVGlz4e/LJJ/W3v/1NI0aM0MCBA3XzzTdLkg4ePKjt27crKChITz75pNsaCgBAfW6NSVT56UIlJz+i+Pi7FRISJkkqKDisXbvyFBgYpMceG+/283bt2lVfffWVy7Zjx47phx9+0E033SRJ6t69u3r16qUtW7Zo8OAfi4+5ubmKjY01VudNSEjQypUrlZ+fr5/85CeSagt6X331lR577DHjuISEBG3btk1PPfWU2rVrZ+SyWq2Kiopy+zUCAKTU1Mf18cf5Sk0do/j4hGbrZwAAcIcGF/66dOmiTZs2acmSJdq2bZs++OADSVKnTp30s5/9TOnp6ZeccwkAAHfo4OuvTZs2acGCRcrL+/+Ul/f/SZJ8fX11772JSkuboOuuC750kgYYNWqU5s+fr3nz5mngwIEqLi7WqlWr1LlzZyUmJhpxkyZN0rRp09SjRw/FxMQoNzdXe/fu1WuvvWbEREVFKT4+XjNnztT06dPl4+OjF154QX369NG9995rxKWkpOjdd9/V1KlTNXr0aB04cEA5OTlKT083ioi4NpjNJpnNJtntDtntjpZuDuDRrrsuWC+++KpWr16mnTt3NFs/AwCAOzS48CfVLuCxaNEiORwOnT59WpIUFBTk8poSAABN7frrr9ecOb9TVVWNiot/kCQFBAQ2aX/0yCOPyGKxaP369dq0aZN8fX0VGRmppUuXKjAw0IgbNmyYKioqlJ2draysLIWEhGj58uV1RugtXbpUCxYs0Jw5c1RdXa34+HjNmjVL3t4/dtU9e/ZUTk6OFi5cqHHjxikoKEiTJ09WcnJyk10nWh+z2aSAgI7y8jKrpsau4uJyin9AE7vuuus0a9azcjgczdbPAADgDo0q/DmZTCZ17tzZHakAAGgwk8mkwMCgZjvX6NGjNXr06MvGjhgxQiNGjLhkjJ+fn+bPn6/58+dfMi46OlobNmy4qrbCs5jNJnl5mfXWh//UzwdHGCP/ADS95uxnAABwB5abAgAAaIO+L65/hVEAAADAicIfAAAAAAAA4IEo/AEAAAAAAAAeiMIfAAAAAAAA4IEo/AEAAAAAAAAeyC2r+gIAAFwts9kks9kkk8nU0k0BAAAAPBKFPwAA0OzMZpMCAjrKy8usmhp7SzcHAAAA8Ei86gsAAJqd2WySl5dZb334T3l58dcRAABaE7PZJG9vc6P+MZsZ0Q+0Boz4AwAALeb74jMt3QQAAHCe80flN0ZNjV3FxeWy2x1uahmAhqDwBwAAAAAAJP04Kn/F+l06dqqkQTluut5fE0bHyWw2UfgDWhiFPwAAgKvgXJTEbnfwZQYA4LGOnSrRkWM/tHQzADQShT8AAIArdOGiJLzCBAAAgNaM2bQBAIC8vc0ssnEFLlyUhInLAQAA0Jox4g8AgGuc2WxSYKBvSzejTWFREgAAALQFPNoHAOAaZzKZtGL9Lv15y2ct3RQAAAAAbsSIPwAAoGOnSuRwtN256pwLbki1hUwAAAAAFP4AAEAbd/6CG5JUU2Nv4RYBAAAArQOFPwAA0KY5F9xYsX6XJGnC6LgWbhEAAADQOlD4AwAAHuHYqZKWbgIAAADQqrC4BwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHojCHwAAAAAAAOCBKPwBAAAAAAAAHsi7pRsAAACuHV5etc8cTSZTC7cEAAAA8HwU/gAAQJPz92svu90hq7WDJKmmxt7CLQIAAAA8H4U/AADQ5HzbW2Q2m7Ri/S5J0oTRcS3cIgAAAMDzUfgDAADN5tipkpZuAgAAAHDNYHEPAAAAAAAAwANR+AMAAAAAAAA8EIU/AAAa4a233tJDDz2kiIgIxcTE6LHHHtPZs2eN/R999JEeeOABRUREaOjQodq0aVOdHJWVlVq0aJHi4uIUGRmpRx99VAUFBXXiDh8+rEcffVSRkZGKi4vT4sWLVVlZ2aTXBwAAAKDtYo4/AAAaaNWqVcrOztb48eMVGRmpH374Qfn5+aqpqZEkffLJJ5o4caKGDx+umTNn6h//+Id++9vfytfXV/fdd5+RZ968ecrNzdWMGTPUpUsXrV69WmPHjtXmzZvl5+cnSSopKdGYMWPUq1cvLVu2TCdPntTChQt19uxZzZkzp0WuHwAAAEDrRuEPAIAGKCgo0PLly7Vy5Ur99Kc/NbYPHTrU+PdVq1apb9+++t3vfidJ6t+/v4qKipSRkWEU/k6cOKE333xTzzzzjIYPHy5JioiI0IABA/TGG28oNTVVkvTGG2/ozJkzWr58uQICAiRJNTU1evbZZ5WWlqYuXbo0x2UDAAAAaEN41RcAgAb4y1/+om7durkU/c5XWVmpjz/+2GVknyQlJSXp8OHD+vbbbyVJO3fulN1ud4kLCAhQXFyc8vLyjG15eXmKjY01in6SlJiYKLvdrl27drnxyoCmYzab5O1tltlsaummAC3q/fff1+OPP66EhARFRkbqwQcf1JtvvimHw+ESt3HjRg0dOlQRERF64IEHtH379jq5SktLNXPmTPXr109RUVGaPHmyTp06VSdu9+7dGjlypPr27asBAwYoKyurzvkcDoeysrJ0zz33qG/fvho5cqQ+++wzt147AKB5UfgDAKABPv/8c/Xu3VsrV65UbGysbr/9do0aNUqff/65JOmbb75RVVWVQkNDXY4LCwuTJGMOv4KCAnXu3Fn+/v514s6f56+goKBOLqvVquDg4HrnAwRaG7PZpICAjgoM9FVAQEeKf7imvfzyy+rQoYNmzJihVatWKSEhQbNnz9aKFSuMmM2bN2v27NlKTExUdna2IiMjNXHixDqFuClTpmjXrl2aO3eunnvuORUWFio1NVXV1dVGzNGjR5WSkqLg4GBlZmZqzJgxysjI0Jo1a1xyZWdnKyMjQ2PHjlVmZqaCg4OVnJysoqKiJr0fAICm0+Zf9T1z5owSExN18uRJvfnmm4qIiDD2bdy4US+++KK+++47hYSEKD09XQMGDHA5vrS0VAsWLNCHH36oqqoq3X333Zo1a5auv/56l7jdu3dr0aJF2rdvnzp37qzRo0crNTVVJtOPf2l1OBzKzs7W66+/rtOnTys8PFxPP/20IiMjm/QeAACa3/fff68vvvhCBw4c0DPPPKMOHTpo9erVSk5O1tatW1VSUiKptjh3Pufvzv02m82Yx+/COGeMM+7CXJLk7+/vEuduXl5ml59NdUxDXOl5rrYd9cVf7FxNfY31aco2NHVuLy+z3vrwn/r54Ai1a+elmhq72/IDbcmqVasUFBRk/B4bG6vi4mK99NJLeuKJJ2Q2m5WRkaH7779fU6ZMkVQ7XcSBAwe0YsUKZWdnS5L27NmjnTt3KicnR/Hx8ZKkkJAQJSUlaevWrUpKSpIk5eTkKDAwUM8//7wsFotiY2N1+vRprV69Wg8//LAsFovOnTunzMxMJScna+zYsZKkO++8U/fdd59ycnI0d+7cZrs/AAD3afOFv5UrVxqTqJ/P+YRs/Pjx6t+/v3JzczVx4kStW7fOpRA3ZcoUHTp0SHPnzpWPj4+WLl2q1NRUbdq0Sd7etbfH+YQsLi5OU6ZM0f79+/Xcc8/Jy8tLKSkpRi7nE7Jp06apT58+WrdunZKTk/X222+re/fuTX4vAADNx+FwqLy8XH/60590yy23SJLuuOMODRw4UK+99prxBayts1o7NMsxDXGl53FHey6Wo7mu9VKasg1Nkfv74jNNlhtoK84v+jmFh4drw4YNKi8v1w8//KAjR47oqaeecolJSkoyVnS3WCzKy8uT1WpVXFycERMaGqrw8HDl5eUZhb+8vDwNGTJEFovFJVdmZqb27NmjmJgY7d69W2VlZUpMTDRiLBaLhgwZog8++MDdtwAA0EzadOHv8OHDev311zV9+nQ988wzLvt4QgYAaEpWq1UBAQFG0U+qnZvv1ltv1aFDh3T//fdLqh1Zfj6bzSZJxqu9VqtVZWVldfLbbDaX13+tVmudXFLtyMELXxN2J5utQjU1dnl5ma+4UNOQYxqixm6Xl/nyI9Kc7blS9bX7Ytd0tbndoSnb0FZzA62J1dqhQaNlP/30U3Xp0kWdOnXSp59+Kqn2u8n5wsLCVFVVpaKiImNKiJCQEJe3kKTa4p9zGojy8nIdP368znQRoaGhMplMKigoUExMjBFf3xQVa9eu1dmzZ9W+ffurvi4AQMtq04W/efPmadSoUXU6xKKiIp6QAQCa1M0336xvvvmm3n3nzp1Tjx491K5dOxUUFOjuu+829l34xSo0NFT/+te/6hTwLpzT7/wvcU6lpaX6/vvv63xJc6eaGruqq6+uONOQYxrCy2zWivW7dF2gr0beF9mk7blYjua61ktpyja01dxAW/PJJ58oNzdX06dPl6RGTxfh7++vL774QtKPD6AuzGWxWNShQweXXBaLRT4+PnXO6XA4VFJS0qjCX1NNS9AUedtKzqbK25RTSABofm228LdlyxYdOHBAy5Yt05dffumyz/nFiCdkAICmMmDAAP3lL3/Rvn37FB4eLkn64Ycf9OWXX2rs2LGyWCyKiYnRX//6V40ZM8Y4Ljc3V2FhYerWrZskKT4+XmazWVu3btWIESMk1X6h27lzp5544gnjuISEBK1evdplrr8tW7bIbDa7PMC61hw7VVJnVUoAaEtOnDih9PR0xcTE6JFHHmnp5jQJs9nk1hHgTTWavCnytpWcTZWXaR2AltcmC38VFRVauHCh0tPT1alTpzr7PfEJmbf35Z+U8DSl+TXFPedzbH58jp6hue/54MGDFRERocmTJys9PV0+Pj7KysqSxWLRr371K0nS448/rkceeURz585VYmKiPv74Y7333nt64YUXjDw33HCDhg8frsWLF8tsNqtLly7KzMyUn5+fRo0aZcSNGjVKr776qiZMmKC0tDSdPHlSixcv1qhRo9SlS5dmvfa2zGw2GavJ2u0O2e0UDQG0HJvNptTUVAUEBGjZsmUy/7/pC5wjwEtLSxUcHOwSf/5+q9WqEydO1Ml7/ihy5/edC6eLqKysVEVFhUuuyspKnTt3zuU7jc1mk8lkatS0Ena7Q2fOnHVbEej8qQLcOa1EU0xV0ZQ5pbZz/SaTSX5+7d3y97WaGrtKS8/y4A/XrKudUqJNFv5WrVqlzp0765e//GVLN6VZmM0mBQb6tnQzUA+eYHkGPkfP0Nyfo9lsVlZWlhYsWKA5c+aoqqpKd911l9atW2d8Sbvrrru0bNkyLV26VG+++aa6du2qefPmuUwLIUmzZs2Sr6+vlixZojNnzig6OlovvfSSy8Mpf39/rV27Vr///e81YcIE+fr6avjw4UpPT2/W627LzGaTAgI6Gn9Rqqmxq7i4nOIfgBZx9uxZpaWlqbS0VH/+859d/sx3vkV04bQPBQUFateunbFwYGhoqPLz8+VwOFzeYiosLFTv3r0lSR07dtSNN95YZ7qIwsJCORwOl6knnNvPn7+2oKBAXbt2bfTbS+6c07OppgpoirxtJWdT5XXm9PauXdl9xfpdOnaqpMH5brreXxNGx8nhcDBdBHCF2lzh79ixY1qzZo1WrFhhPLUqLy83fp45c8Yjn5DZbOWXjWvqSdRRV1NMTM7n2Pz4HD3DlXyODZ1w/WKCgoL0xz/+8ZIxgwYN0qBBgy4ZY7FYNH36dGNup4sJCwvTyy+/fLXNxP9jNpuMLx2SNGF0nMxmE4U/AM2uurpaU6ZMUUFBgdatW1dn5Hb37t3Vq1cvbdmyRYMHDza25+bmKjY21ph7PCEhQStXrlR+fr5+8pOfSKot3H311Vd67LHHjOMSEhK0bds2PfXUU2rXrp2Ry2q1KioqSpIUHR2tTp066f333zcKf1VVVdq6dasSEhKa7mbgmnLsVImOHPuhpZsBXFPaXOHv22+/VVVVlcaNG1dn3yOPPKI77rhDS5YskeRZT8h4mtE6MTG5Z+Bz9Ax8jrhSjRlpAADu8Oyzz2r79u2aMWOGysrK9Nlnnxn7br31VlksFk2aNEnTpk1Tjx49FBMTo9zcXO3du1evvfaaERsVFaX4+HjNnDlT06dPl4+Pj1544QX16dNH9957rxGXkpKid999V1OnTtXo0aN14MAB5eTkKD093Sgi+vj4KC0tTcuWLVNQUJB69+6t9evXq7i4WCkpKc12bwAA7tXmCn/h4eF65ZVXXLbt27dPCxYs0LPPPquIiAiekAEAAABotXbtqh15vHDhwjr7tm3bpm7dumnYsGGqqKhQdna2srKyFBISouXLlxvfP5yWLl1qTDtRXV2t+Ph4zZo1S97eP37V69mzp3JycrRw4UKNGzdOQUFBmjx5spKTk11ypaamyuFwaM2aNTp9+rTCw8OVk5NjDJwAALQ9ba7wZ7VaFRMTU+++2267Tbfddpsk8YQMAAAAQKv00UcfXVHciBEjjBXfL8bPz0/z58/X/PnzLxkXHR2tDRs2XDLGZDIpLS1NaWlpV9Q+AEDr1+YKf1eKJ2QAAAAAAAC4lnlE4S8mJkb79++vs50nZAAAAAAAALhWuW9pQwAAANU+CPP2NrssnAUAAACg+XnEiD8AANB6+Pm1l5eXWTU1rLIMAAAAtCRG/AEAALfy8jLrrQ//KS8v/poBAAAAtCT+Rg4AANzu++IzLd0EAAAA4JpH4Q8AAAAAAADwQBT+AAAAAAAAAA9E4Q8AAAAAAADwQBT+AAAAAAAAAA/k3dINAAAAAAAAQOtgNptkNpsalcNud8hud7ipRWgMCn8AAAAAAACQ2WxSQEBHeXk17gXRmhq7iovLKf61AhT+AAAAAAAAILPZJC8vs1as36Vjp0oalOOm6/01YXSczGYThb9WgMIfAAAAAAAADMdOlejIsR9auhlwAxb3AAAAAAAAADwQhT8AAAAAAADAA1H4AwAAAAAAADwQhT8AAAAAAADAA1H4AwAAAAAAADwQhT8AAHDNMplM8vY2y2w2tXRTAAAAALfzbukGAAAAtBQ/v/by8jKrpsau4uJy2e2OeuO8vGqflZpMFAgBAADQdjDiDwAAXLO8vMx668N/ysur/lF//n7tZbc7ZLV2UGCgr/z82rdAKwEAAICGYcQfAAC4pn1ffOai+3zbW2Q2m7Ri/S5J0oTRcc3VLAAAAKDRKPwBAABcxrFTJS3dBAAAAOCqUfgDAABAvZyLn0iS3e646ByIAAAAaJ0o/AEAAKBezsVPJF12ARQAAAC0PhT+AAAAUC8vL7PL/IZms4nCHwAAQBvCqr4AALjBmTNnlJCQoD59+uif//yny76NGzdq6NChioiI0AMPPKDt27fXOb60tFQzZ85Uv379FBUVpcmTJ+vUqVN14nbv3q2RI0eqb9++GjBggLKysuRwUIhB0zl2qoQ5DgEAANooCn8AALjBypUrVVNTU2f75s2bNXv2bCUmJio7O1uRkZGaOHGiPvvsM5e4KVOmaNeuXZo7d66ee+45FRYWKjU1VdXV1UbM0aNHlZKSouDgYGVmZmrMmDHKyMjQmjVrmvryAAAAALRBvOoLAEAjHT58WK+//rqmT5+uZ555xmVfRkaG7r//fk2ZMkWS1L9/fx04cEArVqxQdna2JGnPnj3auXOncnJyFB8fL0kKCQlRUlKStm7dqqSkJElSTk6OAgMD9fzzz8tisSg2NlanT5/W6tWr9fDDD8tisTTfReOa5Jzvj4U+AAAA2gZG/AEA0Ejz5s3TqFGjFBIS4rK9qKhIR44cUWJiosv2pKQk5efnq7KyUpKUl5cnq9WquLg4IyY0NFTh4eHKy8sztuXl5WnQoEEuBb6kpCTZbDbt2bOnKS4NkCT5+7WX3e6Q1dpBgYG+CgjoKLPZ1NLNAgAAwGVQ+AMAoBG2bNmiAwcOaMKECXX2FRQUSFKdgmBYWJiqqqpUVFRkxIWEhMhkci2khIaGGjnKy8t1/PhxhYaG1okxmUxGHNAUfNtbZDabtGL9Lq1Yv0teXmYKfwAAAG0Ar/oCANBAFRUVWrhwodLT09WpU6c6+0tKahdEsFqtLtudvzv322w2+fn51Tne399fX3zxhaTaxT/qy2WxWNShQwcjl7s5X+10/myLrvQaGnKtLXFfLjynO9twuVznL/JxsViTyWQUBe12h7H4TFO2GwAAAPWj8AcAQAOtWrVKnTt31i9/+cuWbkqTsVo7tHQTGu1Kr6Eh19oa7k9LteFi57XbHS6Fv4uNDGwN9w4AAMDTUfgDAKABjh07pjVr1mjFihXGaLzy8nLj55kzZ+Tv7y+pdrRecHCwcazNZpMkY7/VatWJEyfqnKOkpMSIcY4IdJ7LqbKyUhUVFUacu9lsFaqpscvLy9xmCzVXeg0NuVbnMc3pwva5sw2NvXbn8SvW75IkTRgdd9H72hL3DmgOVmsHRrQCAFoNCn8AADTAt99+q6qqKo0bN67OvkceeUR33HGHlixZIql2Dr/z5+YrKChQu3bt1L17d0m18/Tl5+fL4XC4zPNXWFio3r17S5I6duyoG2+8sc5cfoWFhXI4HHXm/nOXmhq7qqvbdnHmSq+hIdfa2PtjNru+FtuQlXJb6jO61HnPfyX4YnGe8N8WAABAa8ejKAAAGiA8PFyvvPKKyz9PP/20JOnZZ5/VM888o+7du6tXr17asmWLy7G5ubmKjY01VudNSEhQSUmJ8vPzjZjCwkJ99dVXSkhIMLYlJCRo27ZtqqqqcslltVoVFRXVlJeLJmA2mxQQ0FGBgb6slAsAAIAmwYg/AAAawGq1KiYmpt59t912m2677TZJ0qRJkzRt2jT16NFDMTExys3N1d69e/Xaa68Z8VFRUYqPj9fMmTM1ffp0+fj46IUXXlCfPn107733GnEpKSl69913NXXqVI0ePVoHDhxQTk6O0tPTjSIi2g6z2SQvL7PLa7Fms6lBo/4AAACA+lD4AwCgCQ0bNkwVFRXKzs5WVlaWQkJCtHz58joj9JYuXaoFCxZozpw5qq6uVnx8vGbNmiVv7x+76p49eyonJ0cLFy7UuHHjFBQUpMmTJys5Obm5Lwv1aOhru+e/FgvP5I5XugEAABqCwh8AAG4SExOj/fv319k+YsQIjRgx4pLH+vn5af78+Zo/f/4l46Kjo7Vhw4ZGtRPu53xt1zmhf02NXcXF5RR4wH8bAACgRVH4AwAAaCRe28XF8N8GAABoSRT+AAAA3ITXdnEx/LcBAABaAqv6AgAAAAAAAB6IEX8AAMCjmUwmeXubjTnWAACA5zh/AaWGYuEleDIKfwAAwKP5+bWn6AcAgAe6cAGlhmLhJXgyCn8AAMCjORdWuC7QVyPvi2zp5gAAADc5fwGlhs6letP1/iy8BI9G4Q8AAHi8Y6dK5HDwl3kAADzRsVMlOnLsh5ZuBtAqUfgDAABow5xzGErMUQQAAABXFP4AAADasPPnMGSOIgAAAJyPwh8AAEAb5pzbSBJzFAEAAMAFhT8AAIA2rqETmgMAAMCzNW7NawAAAADAVTl69KjmzJmjBx98ULfeequGDRtWb9zGjRs1dOhQRURE6IEHHtD27dvrxJSWlmrmzJnq16+foqKiNHnyZJ06dapO3O7duzVy5Ej17dtXAwYMUFZWVp1FjxwOh7KysnTPPfeob9++GjlypD777DO3XDMAoGW0ucLf+++/r8cff1wJCQmKjIzUgw8+qDfffLNOp0UnCQAAAKA1OnjwoHbs2KGePXsqLCys3pjNmzdr9uzZSkxMVHZ2tiIjIzVx4sQ63zGmTJmiXbt2ae7cuXruuedUWFio1NRUVVdXGzFHjx5VSkqKgoODlZmZqTFjxigjI0Nr1qxxyZWdna2MjAyNHTtWmZmZCg4OVnJysoqKitx+DwAAzaPNFf5efvlldejQQTNmzNCqVauUkJCg2bNna8WKFUYMnSQAAACA1mrgwIHasWOHMjIydNttt9Ubk5GRofvvv19TpkxR//799bvf/U4REREu33v27NmjnTt36g9/+IOSkpI0aNAg/elPf9L+/fu1detWIy4nJ0eBgYF6/vnnFRsbq7Fjxyo5OVmrV69WZWWlJOncuXPKzMxUcnKyxo4dq9jYWD3//PMKCAhQTk5O094QAECTaXNz/K1atUpBQUHG77GxsSouLtZLL72kJ554Qmaz2aWTlKT+/fvrwIEDWrFihbKzsyX92Enm5OQoPj5ekhQSEqKkpCRt3bpVSUlJklw7SYvFotjYWJ0+fVqrV6/Www8/LIvFUqeTlKQ777xT9913n3JycjR37txmuz8AAAAAWjez+dLjL4qKinTkyBE99dRTLtuTkpK0ePFiVVZWymKxKC8vT1arVXFxcUZMaGiowsPDlZeXZ3ynycvL05AhQ2SxWFxyZWZmas+ePYqJidHu3btVVlamxMREI8ZisWjIkCH64IMP3HHZAIAW0OZG/J1f9HMKDw9XWVmZysvLjU7y/A5Lqu3Y8vPzjSdal+sknfLy8jRo0KA6naTNZtOePXsk6ZKd5Pm5AAAAAOByCgoKJNUOTDhfWFiYqqqqjLeKCgoKFBISIpPJ5BIXGhpq5CgvL9fx48cVGhpaJ8ZkMhlxzp8XxoWFhem7777T2bNn3XR1AIDm1OZG/NXn008/VZcuXdSpUyd9+umnki7dSYaFhbmtk4yJiblkJ7l27VqdPXtW7du3d+s1AwAAAPBMJSW1K3VbrVaX7c7fnfttNpv8/PzqHO/v768vvvhCUu285vXlslgs6tChg0sui8UiHx+fOud0OBwqKSlp1HcaLy/3jTk5P1dT5G0rOZsqb2vP2VR53d3Gtop76nnafOHvk08+UW5urqZPny7JMztJSfL2vvz/MPxP1fya4p7zOTY/PkfPwD0HAKB1MptNslo7uC2fO3M1dd62krOp8tLWaxv3tHVo04W/EydOKD09XTExMXrkkUdaujlNxmw2KTDQt6WbgXrwB5ln4HP0DHyOAABP4e/vL6l2IEJwcLCx3Wazuey3Wq06ceJEneNLSkqMGOdgB+egBqfKykpVVFS45KqsrNS5c+dcBjTYbDaZTCYjriHsdofOnDnrtr7aZqtQTY1dUu2DP3fnbSs5pWvz+psq7/n39VrGPW39rNYOVzXooc0W/mw2m1JTUxUQEKBly5YZE+R6Wicp1XaUNlv5ZePc/YcpLq8p/iDjc2x+fI6e4Uo+x6vtJIG2zGw2yWyundLEbnfIbndc0T4ALc85hVBBQYHLdEIFBQVq166dunfvbsTl5+fL4XC4TGFUWFio3r17S5I6duyoG2+80Zie6PwYh8Nh5Hf+LCws1C233OJyzq5duzb6DSZ3/l2rpsau6mr3FxOaIm9bydlUeWnrtY172jq0yW8/Z8+eVVpamkpLS/Xiiy+6vLJ7fid5vvo6SWdnd77CwkIjR0M6yQvP6Y5OUpKqq+2X/YdKevNz/kHmzn/4HJsfn6NnuJLPEWgNzGaTvL3NTVqENptNCgjoqMBAXwUG+iogoKNR6KtvX7t2XvL2NteZ+xhAy+jevbt69eqlLVu2uGzPzc1VbGyssfBgQkKCSkpKlJ+fb8QUFhbqq6++UkJCgrEtISFB27ZtU1VVlUsuq9WqqKgoSVJ0dLQ6deqk999/34ipqqrS1q1bXXIBANqWNlf4q66u1pQpU1RQUKAXX3xRXbp0cdlPJwkAAFqr84tuTTkq2Gw2ycvLrBXrd2nF+l3y8jK7FP6c+9a+/b8ymX5sk58fi5EBzaGiokJbtmzRli1bdOzYMZWVlRm/nz59WpI0adIkvffee8rIyNDHH3+sZ555Rnv37tUTTzxh5ImKilJ8fLxmzpyp999/Xx999JEmT56sPn366N577zXiUlJSdPr0aU2dOlX5+flau3atcnJyNH78eOP7kY+Pj9LS0rRmzRqtXbtW+fn5mjp1qoqLi5WSktK8NwgA4DZt7lXfZ599Vtu3b9eMGTNUVlamzz77zNh36623ymKxaNKkSZo2bZp69OihmJgY5ebmau/evXrttdeM2PM7yenTp8vHx0cvvPBCvZ3ku+++q6lTp2r06NE6cOCAcnJylJ6eXqeTXLZsmYKCgtS7d2+tX7+eThIAALg4v+h2XaCvRt4X6fZznD+S8NipkovGHTtVoq7BVpnNJq1Yv0uSNGF0nNvbA6Cuf//733ryySddtjl/f+WVVxQTE6Nhw4apoqJC2dnZysrKUkhIiJYvX24MPnBaunSpFixYoDlz5qi6ulrx8fGaNWuWvL1//KrXs2dP5eTkaOHChRo3bpyCgoI0efJkJScnu+RKTU2Vw+HQmjVrdPr0aYWHhysnJ8d4awoA0Pa0ucLfrl21fzFduHBhnX3btm1Tt27d6CQBAECrduxUSZ3pRhrL36+97HZHg0YSXqpACMD9unXrpv379182bsSIERoxYsQlY/z8/DR//nzNnz//knHR0dHasGHDJWNMJpPS0tKUlpZ22bYBANqGNlf4++ijj64ojk4SAABcS3zbW4zRe001mhAAAABtS5sr/AEAAODimmI0YVNjlWEAAICmQeEPAACgCZhMtav3Usi6NOeCJ865CWtq7CouLueeAQAAuAGFPwAAgCbg59deXl5mClkX4SyMenmZjQVPpNoFRsxmE/cLAADADcyXDwEAAMDV8vIy660P/ykvL7PxGuvlOIthVxrflvn5tVdgoK+xGMmxUyXX5CIjZvO185kDAIDmx4g/AACAJvJ98Zmrir+WRgk6R/m5ayES5zyBbenV6vNfc74WPnMAAND8GPEHAADQSjRklGBbduxUib4/XdboPM4CWmCgrwICOraZe2c2m665zxwAADQvCn8AADTA+++/r8cff1wJCQmKjIzUgw8+qDfffLPOaqobN27U0KFDFRERoQceeEDbt2+vk6u0tFQzZ87U/9/efYdHUbVtAL93N9lsOoQSkNBLQAiQhBYIKEVqEAFBKYEXQdAAAuL7ig1RRFGKVBEJiNKxgSkSqnRBSFCQ3iFKEgjpZZPd/f7IN+PM7myyCencv+vyMszOnj3TZ555zjkdOnSAr68vXnvtNcTHx1vMFx0djRdeeAGtW7dG9+7d8dVXX1W40VupYIXNEqSKH0DjNiciIqKSwsAfERFREaxfvx6Ojo6YNWsWVq1ahW7duuG9997DypUrxXkiIiLw3nvvoV+/flizZg3atm2LKVOm4MyZM7Kypk+fjqNHj2LOnDlYuHAhbty4gZdffhm5ubniPLdu3cL48eNRo0YNrF69GmPHjsWyZcuwbt260lpkonKPATQiIiIiOfbxR0REVASrVq2Ch4eH+O+AgAAkJSXh66+/RkhICNRqNZYtW4YBAwZg+vTpAIBOnTrh8uXLWLlyJdasWQMAiImJwZEjR7B27VoEBgYCABo2bIj+/ftj9+7d6N+/PwBg7dq1qFq1KhYvXgytVouAgAAkJibiyy+/RHBwMLRabemuACIiIiIiKveY8UdERFQE0qCfoEWLFkhLS0NGRgbu3LmDmzdvol+/frJ5+vfvj+PHj0Ov1wMADh06BDc3N3Tp0kWcp1GjRmjRogUOHTokTjt06BB69uwpC/D1798fKSkpiImJKe7FI3oscERdIiIiquwY+CMiIiomp0+fhqenJ1xcXHD9+nUAedl7Uo0bN0ZOTg7u3LkDALh+/ToaNmwIlUoeeGjUqJFYRkZGBv755x80atTIYh6VSiXOR0S2q6gDghAREREVBpv6EhERFYNTp04hMjISb775JgAgOTkZAODm5iabT/i38HlKSgpcXV0tynN3d8e5c+cA5A3+oVSWVquFo6OjWFZJ0GjUsv9XZkVZVlu/8yhl2zrd1vKKa1sqlZPftOJYdlvnt7PTiNOMRpPiIDgajVocEGRwLx/Y22tgMBgL9btFqZt0mvlnj8NxRkRERKWLgT8iIqJHdO/ePcyYMQMdO3bEmDFjyro6xcrNzbGsq1BqirKstn6nJMsu7+WVxbI7OzuIGXxGoynfbD5hQJDS3Net/dbjdLwRERFR6WDgj4iI6BGkpKTg5ZdfRpUqVbB8+XKo1XkZO+7u7gDysvVq1Kghm1/6uZubG+7du2dRbnJysjiPkBEoZP4J9Ho9MjMzxflKQkpKJgwGIzQadaUPShRlWW39zqOUba6o26K4t6VS/ZTKLs5lt8a8bLVahZVbjgIAJo/oYlNdC/ubRa2b9LcKUweVSgW1WmU1g5HKDzc3R2ZvEhFRucHAHxERURFlZWVh0qRJSE1NxbZt22RNdoX++K5fvy7rm+/69euwt7dH3bp1xfmOHz8Ok8kk6+fvxo0baNasGQDAyckJtWvXtujL78aNGzCZTBZ9/xUng8GI3NziD4aUR0VZVlu/U5Jll/fyymrZY+P/bQJvS3mlua9b+y1r0/P6I8wLJhkMRiQlZcBoZPCPiIiICsZXUUREREWQm5uL6dOn4/r16wgNDYWnp6fs87p166JBgwbYtWuXbHpkZCQCAgLE0Xm7deuG5ORkHD9+XJznxo0bOH/+PLp16yZO69atG/bt24ecnBxZWW5ubvD19S2JRSSickKtVon9EWo0HIWYiIiIbMeMPyIioiL44IMPcODAAcyaNQtpaWk4c+aM+NmTTz4JrVaLqVOn4o033kC9evXQsWNHREZG4s8//8TGjRvFeX19fREYGIi3334bb775JhwcHPD555/D29sbvXv3FucbP348wsLCMHPmTIwYMQKXL1/G2rVrMWPGDDGISESVm9AfIREREZGtGPgjIiIqgqNH8/oPmz9/vsVn+/btg5eXF4KCgpCZmYk1a9bgq6++QsOGDbFixQqLDL0lS5bgk08+wezZs5Gbm4vAwEC8++67sLP79zJdv359rF27FvPnz8fEiRPh4eGB1157DS+99FLJLiiVGZVKBTu7f0emZdNOIiIiIiosBv6IiIiKYP/+/TbNN2zYMAwbNizfeVxdXfHxxx/j448/znc+Pz8/bN++3eY6UuEIgbby0im/q6tOrEtx9OsmLJ+0L0kiIiIiqtwY+CMiIiKCPNBWHmg0atnItMKIrkUlLF9JjFxLREREROVT+bm7JSIiIipDQqBt264zZV0VUWx8smx02kchHRyCiIiIiB4PzPgjIiIi+n+x8ckwmSpvX3oVZXAIoVky+zYkIiIiejQM/BERERFRuSJtlvyofRuWFbVaBbVaxT4ViYgqIOEc/ij48orKCwb+iIiIiKhcEZolD+7l88h9G5YFtVqFKlWcSqxPRWZEEhGVHOk5/FFU5JdXVLkw8EdERERE5U5ZNkuWZnoUJbimVqtkwcviVhkyIomIyivhHL5yy9Ei97Nbp6Z7sQzMRVQcGPgjIiIiIvp/5pkejxJcK6ngpa0ZkUIAk5mBRESFFxufjJuxD8u6GkSPjIE/IiIiIqL/J830AFBuMzYKCiqaNzdmZiAREdHj6dEarRMRERERVUKx8clFbuJVHkibG2s06kfupJ6IiIgqJmb8EREREVUAQtNTjhJLhVGWfSUSERFR2WPgj4iIiKgcc3fVwWg0wc3NEQBKZJRYIiIiIqqcGPgjIiIiKsecdVqo1SpZn3NESqSjETMzlIiIiAAG/oiIiIgqhIrc3xyVPKXRiImIiIgY+CMiIiIiquCURiMmIiIiYuCPiIiIqISpVCrY2anFbCyiksLMUCIiIpJi4I+IiIiohLm66hj0q4SkfeoZjSYYjaYyrhEREZVn0utGUfF6Q4XFwB8RERFZJWSqcaCARyM0waxe1Rkv9G1b1tWhYqDUp15SUgYfxoiISJH5daOoeL2hwmLgj4iIiKwSMtU4UMCji41PhsnEm/SyJmRbPGowW6lPPbVaVSEexJipSERU+qTXjaJ2y1CnpnuFut5Q+cDAHxEREVml0ajx096zGNzLp6yrUi6x776KRZptUVzB7OLsU0/Yn4CSC8gxU5GIqGzFxifjZuzDsq4GPUYY+CMiIqJ8JSSll3UVyi323VcxCNtIpVKV62C2dH8yGIxITc2CyWQq1qb2FTlTkYiIiAqPgT8iIiKiImLffQWTBt1Km7urDkajCW5ujgAgZvmV12C2sD+5OGkRPLAdqlRxAoASaWrP0X+JiIgeDwz8ERERET0C9t2nzFrQrTQ567RQq1Wy7DZrykuz7dj4ZDxRw63C1ZuIiIjKJwb+iIiIiKjYFSboVtJsyW4rj822K2q9iYiIqPzgXQIRERERlZjY+OQK0axUaGa7bdeZIpchZN+VZrPm4qi3LdTqvGWzs1OLIwITERFR+ceMPyIiIiIqt4RgWkmNciv1qM22hey70m7WXNLNzQsaCVitVonBwNLYTkRERGQ7ZvwRERERUbnl6qpD1arOqFLFqdxnmgkjBle2prfSkYBXbjkKjebfrD8hKFi1qnOF2U5ERESPk8p1V0JERERElYo0mFZWASUh61DIbMtvMI3yOmJwcVBqtp1fUJCIiIjKHpv6EhEREVG5VtbBNPMmvI+a0Sd8vzT7Aixu5v0ZSgOCwvKVh2a/bIZMRESPOwb+iIiIiIjyIWQdDu7lAwBYueUoqld1xgt92xaqHHdXHYxGE9zcHAGgVPsCFAJ1xdUMWak/Q6Xlk/YFKFUaAbmC+iYkIiJ6HDDwR0RERERUAGnWYVEH03DWaaFWq7Byy1EAwOQRXYqtfgURAnUFEQJy0oE7lL5nHgwFlJcvr+mvSVYeALi5OZZ4QE7aDFmoj3TZiIiIHgcM/BWza9eu4aOPPkJMTAycnZ0xaNAgTJ8+HVqttqyrRkRElQCvM0R5pBljFa3JrHk/eaVBCIDll6kozZCzpVmztSbY0uVTaiZtMBhLNCAn7BtC3aX1Kc1RoisqXmeIiCoXBv6KUXJyMsaOHYsGDRpg+fLliIuLw/z585GVlYXZs2eXdfWIiKiC43WGHnfSfuWkGWyl2WS2IisoU1EIlhVHs2aBeXnSv0siAGrevNecNBApzTJkX4B5eJ0hqnik56+iKq3zXkWqa2XCwF8x2rp1K9LT07FixQpUqVIFAGAwGPDBBx9g0qRJ8PT0LNsKEhFRhcbrDD3uzJurlkWT2crIfKCO4mjWLCUtr6QHapE271UKWEoDkUKWIfsC/BevM0QVS0EvO2xVGue9ilbXyhSgZOCvGB06dAgBAQHiRRIA+vXrh/fffx9Hjx7FkCFDyq5yRERU4fE6Q48784BOWTSZrYyUBuoobcU9EnB+AUsh+Cgd8KQoTY8rY5YgrzNEFYv0ZUdRr4l1arqXSh+oJVXX4g7SVaQApa0Y+CtG169fx9ChQ2XT3NzcUKNGDVy/fr2MakVERJUFrzNUnhR3oMZWxZGBRnJKA3WUloJGAi7J4Jp5BqktD6JCfZSam5eXB7xHwesMUcUUG5+Mm7EPy7oaNinOupZEkK4iBVNtpTLxzqnYtGzZEtOmTcPEiRNl04OCguDr64u5c+cWqVyTybabHJUKUKvVSE7LYl83JUyjUcPdRQej0YjiPoK4HUsPt2PlUJjtKDysVVQldZ0BgOS0LGjUKrg4OSA5LQsA4O6iAwCkZ+jh7KQt1HxF+U55KNt8PpZtOZ9aBbg4OYjHkslkkgXihHNfRdnmLLt8lJ2eoQcAODtpYTT+e91UqVSK+5qwy6lU8r+Bwu2D6Rl6qNUqOOrsZfMJdTAvW1of4fvm9TafpyIpyecZk8n0yPdGStf84rjnMi+3opQJVJy6Fte9cUWp6+O+rUp7+dMz9DAYi1imWi2ew0ty+QWPenkwmQr/TMOMvwpApVJBo7F9owo3NVTy1OpHe7OQH27H0sPtWDmU5HZ8HEj3VfP9VnhALsx8RflOeSjb2nwsW3k+QDnIUZG2OcsuH2VLp1s7nxcmoPao9bH1mmJLvUm+7Yrj3khpXZdEuRWlzJIqt7yWWVLlcltV3OWXnouLq8ySWv6yUD5qUUm4ubkhNTXVYnpycjLc3d3LoEZERFSZ8DpDREQlidcZIqLKh4G/YtSoUSOLvi9SU1ORkJCARo0alVGtiIiosuB1hoiIShKvM0RElQ8Df8WoW7duOHbsGFJSUsRpu3btglqtRpcuXcqwZkREVBnwOkNERCWJ1xkiosqHg3sUo+TkZAwYMAANGzbEpEmTEBcXh/nz52PgwIGYPXt2WVePiIgqOF5niIioJPE6Q0RU+TDwV8yuXbuGuXPnIiYmBs7Ozhg0aBBmzJgBrfbRO5skIiLidYaIiEoSrzNERJULA39ERERERERERESVEPv4IyIiIiIiIiIiqoQY+CMiIiIiIiIiIqqEGPgjIiIiIiIiIiKqhBj4IyIiIiIiIiIiqoQY+CMiIiIiIiIiIqqEGPgjIiIiIiIiIiKqhBj4IyIiIiIiIiIiqoTsyroCVPEtX74cK1asUPxs5syZOHjwIAwGA7Zu3Sr7bMiQIfjrr7+wd+9e1K1bV5y+fv16fPLJJzh27BiqVauG4OBgnDx5EgCgUqlQs2ZNtG7dGtOnT0eTJk1KbsEeY8uXL8e6desQExNjdZ6HDx9i7dq12L9/P2JjYwEAdevWRWBgIEaPHg0vLy+L7wjbdujQofj4449LrP5kyXybent7K863dOlS9O3bFydOnMCYMWPw/fffw8fHR/x89+7dmDFjBp599lnMmzcPajXfH5VnwnZ/6aWXFM/TOp0OU6ZMwd69e3HmzBloNBoYDAaoVCqYTCbx348TlUoFR0dHZGRkiNNq1KiBlJQUZGdnP1K5JpOpOKpolb29PXJycmyeX61Ww8HBAZmZmSVYK2UVad+qUqUKkpKSSuW31Go1jEZjqfyWLapWrYqHDx8+cjnCtUKtViM3N/eRyysuTZo0gUajwaVLlwr9Xen58osvvsDUqVPRr18/hIWFice7o6MjjEYjqlSpApVKhaSkJOTk5MDOzg5GoxFqtRr169dH7969MXbsWLi5uZXAUpYfs2bNwrlz5xAeHm7x2bx587Bv3z7s379fNv2jjz7Chg0b8Nprr2Hy5MkF/sazzz6LS5cuYdOmTWjXrp3iPImJiejatSu0Wi2OHz8OnU6nOJ/5M45Wq4WXlxeGDBmC8ePHy+6B4uLisHjxYhw8eBAZGRmoU6cOXn31VTz77LNWy1SpVHB2dsYTTzyB9u3bY9SoUWjcuLE4b3BwMJycnLB69eoClzu/57GpU6fiiy++wJQpUxASEqI4z5AhQ+Do6IhNmzaJZdWsWRMHDx60uNd78cUXERMTg8GDB2P+/Pni9EOHDmHdunU4d+4ccnJy0KhRIzz//PN48cUXodFoABRuHzhz5gxWrFiBCxcuIDU1FdWrV0erVq0wfvx4XLlyBe+88w6ioqLQoEEDsYwNGzbgo48+wuTJk/Haa6+J05OSktCpUyfMnDkT1apVw1tvvQUvLy9ERUXBzu7fkIjwrFK/fn3s3r1bcV0JvzF9+nQsWbIE69evR0BAgPi5wWDAsGHDoFarsX37dsV7ZWvbq2nTpggPDy/UtjeX3zFw9epVLFu2DGfOnMHDhw9RtWpVtGjRAiNHjsRTTz1lUdaBAwewbNkyXLlyBdWqVcPQoUMxefJkcXsCkD2rm9u2bRvatm1bqGU3mUwIDQ3Fli1bEB8fjwYNGiAkJAT9+/dX/I38nlutfbZnzx5MmTIFnTp1wjfffKNYbnBwMO7fv4+dO3dCq9XKPnvttddw+PBhZGZm4sCBA6hdu7bF9y9duiQ+Lz3//PPi9J9//hmbN28WrzvNmjXDiBEj8Nxzz1mUUZh5C8LAHxULnU6neNDUrl0bqampWL9+PfR6vXjQpKen4+LFi3B0dERMTIws8BcdHY0GDRqgWrVq4jQ/Pz+8+eabMBgMuHbtGpYsWYL//Oc/iIiIgLu7e8kvIMncunULY8eORW5uLoKDg+Hj4wOVSoW//voLW7duRUxMDLZt22bxvZ9//hlA3sl2zpw5FidRKl3BwcEICgqSTZPePJnbt28fXn/9dQwYMIBBvwpICCjMnj0bUVFROHHiBLKysrBo0SIxICUEYqT/fuKJJ/DPP/8oBq1GjBiBLVu2yKbNnTsXAPDee+/Jput0OmRlZeVbR5VKBZVKVejAh5OTkyxQZ415UEWr1UKv1wPIC+4lJCTAZDJZBPgSEhLg6Ohoc7kA4OjoKAuoabVai3LVajXc3d3FwIpSMCwgIACxsbG4fft2gctnHvQzL0+lUsnqYTQa8w0U2tvbQ6fTITU1tcDfbtSoEa5fv271c/NtJK2XNGCpVqvRvXt37Nu3z6IMIZgi3W5KnnzySZw/f178jr29veL8tgZjpUE/V1dXq+vDxcUFaWlpsmkajQa1atVCbGys4vYw/31b932VSgUfHx/8+eefNs1fVElJSQWu78aNG+PatWuyupkvl/Bgbb5/KwWrW7dujebNm+PYsWO4e/dukeptZ2enGGBs0aIFLly4IP776tWr+ZZjft6qXr067t+/D0B+vnznnXfg7e0NJycncRoATJgwAbt378bVq1dhNBrh5OSE3NxctG7dGtevX4e/vz/8/PywYcMGpKam4u233y7S8lZWBoMBv/zyCwAgPDy8wMDflStXxAfksLAwq4G/yMhI5ObmIjc3F/v377caUADkzzhZWVk4ceKEeN2cOHEiACA+Ph4vvPACGjZsiLlz58LFxQVXrlyxetxIy0xPT8fly5exbds2bN++HfPmzcOgQYPyXU5b6ipVu3ZtxMTEICIiQjHwd+PGDfz111/44IMPxGn29vZ4+PAhfv/9d3Ts2FGcHhsbizNnzoj7umDdunX49NNP8cwzz+Czzz6Do6MjDh06hE8++QQnT57EkiVLoFKpbF6W06dPY8yYMejatSs++OADODs749atW9i7dy/+/PNPdOnSBQAQExMju3eNjo4Wny+lYmJiYDKZ4O/vj5s3bwIA7t69i59//hlDhgyx+P1bt27hzz//ROvWrS0+i4iIQNu2bfHqq6/i999/x5w5cxAWFiY+12zYsAEXL17E999/n++9stL2shaEtlV+x8Dt27cxbNgweHt7Y9asWfDw8EBsbCwOHjyIkydPWgT+zpw5g5CQEAwYMACvv/46rl69iiVLliAzMxNvvvmmbF7hWd1c06ZNFeuZ37KHhoZiyZIlePXVV9G2bVvs378fr7/+OnQ6HXr06FH4laIgLCwMAHDy5EnExcXB09PTYp4PPvgAgwYNQmhoqOy4OXToEKKiorBgwQK8+eabiIiIwIQJEyy+HxERAa1Wiz59+ojT5s6di02bNmHo0KEICQmBSqVCVFQUZs2ahbNnz8runQszry341EbFQq1Wo23bthb/eXp6wt/fH3q9HufOnRPn//PPP6HT6dC7d29ER0fLyoqOjoafn59smpubG9q2bQt/f38MHz4cb731FhISEnD48OFSWT6SmzlzJnJzc/HDDz9g0qRJ6Ny5MwICAjBhwgRERkZi2LBhFt8Rbio6d+6MlJQU/Prrr6VfcZKpXbu2xTFbpUoVxXkPHjyIadOmoU+fPvjkk08Y9KuA1Go1NBoNzp07hzNnzqBz584A8oIVAMTAlrOzs/idl156CX///TfUarXsjbhOp4ODg4NikGL48OGKN8rCg8Nbb70FIC9YULVqVdk8JpMJOp3O6sOBkI0nfC68cTavh1qtRr169RASEiLeSOp0Ori6usrm8/DwEP+WZtrY29tb/LZer4ezszPUarXF/u/g4CCrs0qlEoMFwnqtWbOmRZlNmjQRv1erVi0YDAbUqVNHVv7Vq1fxv//9T3F9KNVDqlevXuLfLi4uMJlMFvU0D44In7dv3x729vZimQUd8w8ePLC63Ro0aICMjAzZem3RooX4d05OjrgtNRoNHB0dZfuboEaNGuL81atXt1oX6XK7u7sr7qcqlUqWsWD+mdKyaLVa1KtXD0888YTFZ25ubsjKyoJarZa91FKr1WJWvMFgkG0jIRAr9corr4h/u7q6ius9MDBQNt+IESMUX7AB/77AkS6f9HeFY0L6QGj+0CNsK5PJJFufSqTBuSpVqshe3AJ5D356vR4TJ0602Bb9+vWzKO/mzZsYNWoU7t27p9h6wHwflhLWl1I2qb29PXbs2GGRmWG+DTp06GD1s2bNmon7Zps2bcTpiYmJmDx5shiwFrLqr127hitXriA0NBSBgYFIT0/H8OHDsXHjRhw4cAAjR47EuHHj8Msvv6B79+4WdX7cHT9+HPfv30fnzp1x/fp1/PXXX/nOHxYWBrVajY4dO2LXrl1WX2yEh4ejcePG8PT0FF9KWyN9xunUqROmTZuGnj17yrLBFixYgFq1aiE0NBTPPPMMAgICMGbMGFmWj7Uyu3TpgnHjxmHnzp3w9/fHO++8gzt37hSwZgquq/nz2MCBA3H16lVcvHhRcX3Y29ujb9++4jR7e3t069YNERERsnkjIiLQtGlT1KtXT5x2/vx5LFy4EIMHD8aKFSvQo0cPBAQE4M0338QHH3yAXbt2WT1fWbNlyxbUqVMHK1euRK9evRAQEIAXX3wRoaGhGDVqFBo1agQPDw/F58jBgwfjzJkzsvNAdHQ0HBwc0KpVK3Fax44dsXr1asXzhZOTk2JW4t27dxETEyO+OH///ffx999/i5l59+7dw9KlSxEcHIwnn3wy32VU2l7Nmze3fSUpyO8Y+OGHHwAAX3/9Nfr3749OnTph6NChWLZsGWbOnGlR1vLly9GiRQssXLgQXbt2xbhx4zBt2jRs2LBBfAEiEJ7Vzf+T3lPasux6vR6rVq1CcHAwpkyZgsDAQMyePRtPP/00lixZ8kjrRpCWloZff/0VnTt3htFoRGRkpOJ8jRo1wqRJk/Dll1+Kx2R2djbmzp2Lnj174tlnn0X79u0V9xMg71h5+umnxXvPffv2YePGjZg8eTLmzZuHbt26oWvXrvjoo48QEhKCjRs3itmuhZnXVnxyoxLn6+sLlUolOzGfPn0arVu3hr+/v2z6nTt3kJCQYBH4MyecSP/++++SqTRZderUKZw9exavvvqq4tsRrVareKMTHh4OlUqFDz/8ENWrVxfftFD5d/jwYUyZMkV8i2vtYZnKP41Gg19++QXZ2dmYMmUKWrZsidTUVKhUKuTk5KBKlSpIT08X5x81ahQcHBzE5mwCnU6Hp59+2urNzrfffmu1DkKG97Vr12TBH4G15p9CFpFOpxOzaYQbSqVMwmrVqkGtVovzuri4WGRqxcfHi8slXE/s7OwUyzMYDMjOzobRaLQIShmNRlmGk1arFQN+7du3h06nwz///GNR5sOHD5GYmAggb71Uq1YNiYmJ6N27tzhPQkIC3n33XcXlMxqNssCEeUahm5ubGAhJS0uDi4uL7CEgv2y3wMBAZGZmIjk5GQCsvhQQJCcni+cG82BJfHw8atSoIdu25kFYaVBw3759iucZIcPfZDLZnBnn6uoKg8Egy6IQ9iWDwaAYQLS2XhwcHHDnzh1oNBqLgFNKSgoaNGgAo9EoC7Ll5uaKgTB7e3tZK4XGjRtbLGedOnXEv9u3bw+TyQS1Wi1uB6H+KpXKajBW6AZFrVaL80n3DWHfFH7bwcHB4iFOGhwTsv6U2NnZyco2D+YDwIABA6BWqxEWFiYLtgOWx269evWQkpKCtWvXQqVSyTIlhGUXjj9HR0dxWwnbQ9gvlLahMM282bY0K8ve3l7W7Fc4Zwjr7OrVq+LxKd1WKpUKO3bsENfj2LFjAeTty7169YKfnx9Onz4NJycn8aW1g4OD2DxQ+jf9Kzw8HM7Ozpg/fz7s7e3zvXc0mUwIDw9Hp06dMG7cOCQlJSkmCNy5cwcxMTEYOHAgBgwYgCNHjhS6Kb+zs7P40iQtLQ2//PILRo4c+Uj3Rw4ODnjvvfeQk5OD7777rsjlWNOrVy/odDrF63Z4eDgCAwMtzvNBQUGIioqSXTfCw8MtWots2LABKpUKU6dOtSh78ODBaNCgAb7++utC1TclJQUeHh6K61Q49/n5+cmeI//++2/cu3cPY8aMgV6vlx3L0dHRaNWqlexcFhISglu3blkENwGgZ8+e+OWXXyyuNREREdBoNGKWaP369TFp0iR89dVXuHHjBj788EO4ubnJmhmXloKOgZSUFLi4uCi2YFC6nly4cEHMrBQEBgYiJycHR44cKf4FQN7xmZ6ervi7ly5dKpZn/927d8vug/M7r0ycOBFPPPGEmA375Zdf4v79+5g9ezYAYODAgbhw4YIs6x3IyzC9e/cuBg4cKE775ptv4O7ujpdeesnid8aPHw93d3cxC7Iw89qKgT8qNkLKvPQ/IO9GvUmTJrITc0xMDHx9feHr64srV66ITWNOnz4NAPD398/3t4S350pvgqlknThxAoBl9kFBwsPD0a5dO9StWxf9+vXDr7/+alPzMSo5RqNRdrwqBVyOHz+OyZMno3v37liwYAGDfhWcRqNBVlYWPDw80KxZM9SqVQtAXhApNzdXMSAgZDdJH6Rzc3MxYMAAWZBQEBkZid9//91iuhD4kt5EC01DzQMl5g/t0qaD0v7GrDUdNhqNiImJwf79+8X9umHDhhY38EajUQwYCM1yhXmUboJzc3Ph7u5u0XwrOztbFgjKzs4Wgz1eXl6oUqWKYrPDhIQEAHnr+48//kDdunWRmZmJwYMHy+ZLSkqyCDQJGUX5dXeRmZkpLoezszPS0tJkx7lSf2LCehayDqRNcAsirDvz4E5GRobF+j979qz4t1arFZfPYDAgMzNTsT9F6f4p3Q/Msyml61qv18NkMskCjUI5JpNJFryRUgocGQwGpKSk4N69e7JApVB3Ly8vWYDZ2dkZJpNJzIB1c3OTPUBnZWXJfsfOzg6rVq0S/52QkAAHBweYTCbFTCdrfeUJTVmF48Zac+Lr16+LgX3z83/t2rXFfTgpKUm2z0v3RfM6JCQkWDS7F/qxu3XrlkXzQPM+tISmk3v27EHLli1x79492edCwBbIy8gRgv/WmhZLGQwGHDt2zKJPS2mGjbOzs2xZhXKF7L4HDx5g6NChACDLtlCpVLJlEdZddnY2unbtinPnziEjIwNt27bFnTt3EBcXZ1E/ksvOzsbu3bvxzDPPwNPTE4GBgYiIiLAa9I+OjkZsbCyCgoLEIJa1IBeQF9QKCgpCTk4Odu3alW9dhPuktLQ07Nu3D7t37xaD0n/99ZfYb+Po0aPRsmVLdOnSBQsWLChUn6tAXtDe09Mz3z62C2LteczFxQVPP/00IiMjZcfLuXPncPPmTYu+CAGge/fu0Ov1OHr0KIC8wPelS5csmkb//vvv8Pb2VjyfCt033Lx5E/Hx8TYvR8uWLRETE4MlS5ZYBFUEfn5+uHbtmvhiJDo6GrVr10bDhg3h7e0tPnvm5OTg7NmzFs+XzZo1Q8+ePfHll19a7FcDBw5EfHy8+NwjCA8PR+fOnWWZzUJwaPz48di3bx/ee+89q5lu5sy31aP0BVzQMdCyZUvEx8dj9uzZuHDhQoEv0LKzsy1e+gj/Nt8mJpPJYlkK6sdXadmFa7+tv5tfebm5uYrLGBYWhjp16sDPzw8DBw7EX3/9ZbWrEq1Wiw8//BCHDx/GF198gdDQUEybNk28f+7Tpw/s7e0tzjXh4eFwdXXF008/LdYtJiYGHTt2VNw3nJ2d0bFjR8TExBR6Xlsx8EfFIiMjAy1btrT479SpUwDyTsxnzpwBkHfD+ccff8DX1xdNmzaFs7Oz+FlMTAw8PDzQqFEjWfnCyUSv14vp5E8++WSBzU+o+AkXbfOmMgaDweImQ/Dnn3/i5s2b4hvCoKAg6PV6REVFlU6lSdHChQtlx6u0iYdg0aJF8PLywuLFixUfpKhiyczMhMlkQmJiItq1ayc2SxMCYEIwQ3jrHxgYiBs3bgCQP+CnpaWJL2CAfzOLAGDx4sUWD+sAcPnyZQDAlClTxGnCfNIgj9KNovmNsNAcWK/X5xuQOn/+vFhvpWAkYNlMWFgH0unSQJY080rK/EWU0Cxk27ZtBWaTGAwG6PV68Vq4Y8cOi+UyXwdC4CsjI0MWTJHeLIeHh4vLrxSkTUlJsVqnnTt3ygL9BfXPCPy7zpS2v3nH39Ky9Xq9ReBVidBErX79+rL1Yb5+v/jiC/FvIcAiXVbpshQm00cIaOXk5CgGh3799VdZH3/COr9y5QqAvGWW1uPOnTuy5XVycpKVe/bsWTE4KJ3PZDLh4cOHVoMDsbGxssxY831H2IcTEhKQnZ1tcc0Wto2QJWnev2R+D6ZpaWkWgb/FixeL55GCmjAK2a2ZmZk4c+YMjh07ZjGPsC4ePHiguF8DyoFqk8mEcePGWUyXZtolJSUpDnbz22+/Acg7VsePHw9Avh/l1zyvdu3a4r2T0DxS6Rghuf379yM9PV28d7QWiBGEh4fDwcEBvXv3hr29Pfr06SOWISX0z1a3bl20bNkSjRo1yjfjR/qM4+/vj5CQEHTv3l0MUgtZnu+++y5atWqFtWvXYuzYsfjmm2+wbNmyQi937dq1LTJwbVXQ89jAgQMRGxsrS8aIiIiAk5OTYt9pjo6O6NGjh5gRFx4eDl9fX1nf7EDeeVZpcAPpMgGF2+/Hjx+PLl26YNWqVejfvz86duyImTNnissC5CWKmEwm2XOkr68vgLxnT+Ecef78eWRnZysmlrz66qu4du2aRfC3S5cu8PDwkGUDXr58GZcvX7bIeNRqtXj11VcRGxuLLl262Px8qrS9Cmp6np+CjoHBgwcjKCgI27Ztw3PPPYd27dohJCREsU9dIO9aa96PrLCuze+FDh48aLEs0sEBbV32evXqQaVS2fy7+ZXXsmVL2f0AkHfdO3HiBAYMGACVSoX+/fuLGenWdOjQAUOGDMHSpUvRtGlTBAcHi5+5ubnhqaeeku0nBoMBu3btQu/evcV7socPH0Kv1xd4nGRnZyMuLs7meQtzD8PAHxULnU6H77//3uI/oRmXv78/Hjx4gJs3b+Ly5ctIS0sTmwC3adNGvABFR0eLJ2wp4WTi4+ODwYMH4/79+1i5ciUHhyhHBg0aJDvRCs3XAMu+Q4QbLjb3LVvCqL3CfytXrrSYJzAwENeuXcPGjRvLoIZU3ITgrYODA9avXy9miyUmJor91wH/Bv4mTJggdsxsnnH26aefin/XqFFD/PzOnTuy4IXQL5vQr45SX3eAPHgora80Y00gzZTq2rUrAOV++R6FNHAgvbFydHRUbCaTmJgoPtRLm4IaDAZZgMCW69bu3bvF9WaNEEhJT0+XBVqUmk9bI/RXKGQuSOsmdH4vUAqGWMsALqhZMABZgMy8b0JrhP1K6JjdGmlH9EJTV6EvS+DfwFGVKlVw586dQnU4L/Sfp/QixM/PD/Xr17eYLvSBFx8fbxHYlh4rqampNl8XIyMjMXr0aKufZ2VlWc02UmqOK2UwGHDixAnxOi40E7dGuh9otVqLoJuTk5PYbMv82DGf9/vvvxfXYfv27QscUVj6fek5Ir/BSKRUKpVin43mmjRpIp5jzDNya9asKQ4mY+03qPDCw8NRrVo1sT/aHj16wMnJSfEYyc3Nxa5du/DUU0+J2b0DBw5EZmYm9uzZI8538eJFXLlyRRa4GTBgAE6fPm21CaH0GWfz5s145513cPjwYTFILZxPOnfujFmzZqFTp06YOHEixo8fj/Xr19v00kTKvC/Wwijoeaxbt25wd3cXgxQmkwmRkZF45plnrA4qERQUhH379iErKwuRkZEYMGBAkeoGFO5YcHFxwbp16/Ddd99h8uTJaN68OaKiojB69GixKXTLli2h0+kUnyPbtm0rm65SqRSfMVu1aoWnnnoKq1atssjA7tu3L3bv3i2eTyIiIuDo6IhnnnlGVobJZML27duhUqlw8eLFfF+qSSltL6WRdW1hyzGg0WiwaNEihIeHY+bMmWjXrh2OHj2KkJAQLF261KLMkSNH4tChQ/jmm2+QlJSEU6dOYcmSJYrXfn9/f4tl2b59e6GX3cXFBc8++yxCQ0Nx8OBBJCcnY8eOHeI+a20fsrbvDx8+XDZfZGQkDAaDeA7w9PTMt58+gRDoHzdunMXyBwUF4datW2JLht9++w3379+XNfMtDxj4o2KhVqvh4+Nj8Z9wEyb02RcdHY3o6Gg0adJEPCn5+voiOjoaqampuHr1quLbGOFksnXrVvzvf/9DSkoKXn/99UKP/EiPTnhoN2+m8vnnn+P777+XZfMAEDtN7dChA9RqNVJSUpCSkoKePXuKIylR2ahVq5bseG3WrJnFPNOnT8fQoUMxf/587Nixo/QrScXKaDSiQYMG0Ol02Lt3r9i/H5B3QygEfoSbmnPnzlltqiFtYhoXFye7YZYG4YQgkBBcmjNnjmJ50oxDgfTmShqEkj7sCxlB0qw3f39/tG/fXpzPvDmstFzz3xSa7UrnEa41KpUKmZmZiqNfp6eni3XIr0l8QQGJiRMnolq1amIzYCAvmGLetFTpYVJoMizo2bOnrC7mfcoJfQQK0+rWrWs1CGe+H5gHaqV/m7+B1mg0FoGjhg0byupp/rvVqlWzyCoRfsf82m/+wCoty2Qywc7OTha4FIJ2Wq0WRqOxUIMV1apVCw4ODorb+PXXX8fu3bvRsmVLizoDlvuFUncla9asEf9+8skn820uJmQDCH3+SbeBUlNkgRB8szaIiZOTE9q1a4dNmzaJ06RBRGnZarVa3DfUajX0er1FcDsjIwPp6emws7Oz6E/PfLvn5OSI/YQJD+3WlsvFxUXWXD89Pb3AwLr5fmsymSz6HjMP7Gm1Wty+fVtcX0JTM6HuwvJbeyD9559/xHsnIeNRaCb2uFEauVwg7T81JSUFBw8eRPfu3ZGeno6UlBTk5OSga9eu2LNnj8V59OjRo0hMTET37t3F+8xmzZqhRo0asgf6n3/+GWq1GoGBgeJ8Tz31lNg3mhLpM46/vz/GjBmDyZMn48cff8Tly5fFLhM6deok+15AQAD0ej1u3bpVqHV07969fAcvyk9Bz2NarRa9e/fGrl27kJubi99//x337t3LN0ARGBgIe3t7LF26FHfv3lUckKdWrVqK/dgKhM88PT1t3gcErVu3xmuvvYZvvvkGv/zyC2rVqoWFCxcCyDsf+Pj4IDo6Gunp6bh06ZIY3PP19RX7/BOePa11jRESEoLLly9j7969sulBQUFITk4W+8kLDw9Hjx49LM7L33//PaKjo7Fs2TLk5ORg0aJFVteFlNL2suXFmRJbjwEgb8CliRMn4quvvsKBAwfw5JNP4quvvrK4dg8ZMgRjx47FZ599ho4dO+I///kPXnzxRbi7u1u8xHV1dbVYFulAKoVZ9rfeegstW7bExIkT0aFDB8yfPx/Tpk0DAKsvRa3t++b1DAsLQ8OGDVG7dm1xPfXo0QO3b9+W3T+ZE649Si+ZhX1CWM/h4eGoWbOm7CVk1apVodVqCzxOHBwc4OnpafO8hdlfGPijUlG3bl14enqKgT/pG5e2bdvijz/+wOnTp2E0GhUDf8LJxNfXF+PHj8fMmTMRExNTYJ8cVPyEk5h5p65NmzaFj4+PRf8ev/32GxISEnD06FG0b99e/G/9+vX5jqRE5cfcuXPRq1cvvPPOO4UeQYrKD6G54M2bN5GcnIyNGzfKBqVITk4Wm+MK/z958qSYrWStuaC0fEFh+zUC/m3uKiUMpiH8LZAGfoTfkjbnateuHR48eCA20TXvV0z60KHUbNG8Tz4hMGQymaDRaCxeWAgP/EJAQK/Xi0EdpezA/Hz11VeIj4+XLaNer7dpUA7zhymhfzihjkaj0SIAl5WVJTZDvHbtmkXfekJwwzygIvQRWlCdhHqZX9ulN7TmoyIDec04lZqFKgVXUlJSZME784xAvV4vy4oU6i0sd0H9EEnFx8fDz8/PYl9Vq9ViwM/8RlxYN+a/Yz7AiVarxfr168VlHDZsmHhNlS6fSqWCh4eH2Jeg0I+ftWPQfJ0J/65Ro4b4HenDTEZGBk6dOoUhQ4aI06T7hbRsaVMka8sJ5PU72Lp1a4vPzJsZjxgxAm+88YZYjnlQVvrbQtaodLkLCqy3aNFCHDBFID2e1Wq1RV9Per1e/E/a36IQnHnw4AF0Oh3s7e3F411olu7g4IDDhw+jVatWcHJywpkzZ8R74seRh4eH1Was8fHx4jlbGFDi+++/l907RkVFISUlBb/++qvsu0IW4FtvvSXO26FDByQkJOD48eN48OCBmN1mNBrRt29fcT5hQLrCtEIRuiS6evWqOJiONUr9lVpz5coVxMXFKWamFZeBAwfiwYMHOH78uEVWpRJ7e3v07t0b69evR6dOnRSDku3bt8fly5cVAxUmkwkHDx5EgwYNULNmTZv3ASV169ZF3759kZSUJJbh7++Ps2fP4vTp09BqtWJ2Y506dVCjRg1ER0cjJiYm34EjhdGVzZuF+vn5oU6dOoiIiMCZM2dw9+5di2a+iYmJWLhwIYYMGYLevXvj9ddfx/bt2y2aqpY0W44BJR4eHhgyZAhyc3MtgtRqtRpvv/02fvvtN+zcuRPHjh3D8OHDkZiYKBvVvLhVrVoV69atw6FDhxAWFoZDhw6hdu3asLe3L3Ck5PwIWXk3btyQnVc++eQTAIU7B0gJzasjIyORlZWFPXv2iINaCezs7ODr64uTJ09adIcB5F13T548CV9f30LPaysG/qjUCH0tSPtfAPJOtllZWdiyZQt0Op1NB/To0aPh5eUlDp1Opaddu3bw8fHBqlWrbOqkNywsDE5OTli/fj2+/fZb2X/Nmzdnc98KQKPRYPHixfD398eMGTNk/atQxSE8HK9cuRLvv/8+/Pz8MHXqVNmNSZcuXdCgQQNxmtFohF6vtwgcCIE0887AVSoVAgMD8+38XwgkCvNLVa9eXZYVpVKpFDN4hGwx898RHrpr166N69evi2+vrWVNCRlf5po2bSoLJgi/4+LigmHDhsm6MhA+lw7cYGdnJ94UCw99QhlKzSClAgMDsWbNGossNmmzZ6EclUqFdu3aiZ9PmjRJtv4uXrwoG6ykRo0aFkFZLy8vWRBCGDREoNQMuCiEkaGFZRAyFoV/SwM2QgbNyJEj4e3tLVtuafalNdL+J7VarezGWDqgiVqtLjAwK/1cpVIhNjYWY8aMsQh01q9fH/b29khOTrboE09KqItKpZKNOAnk7cPdunUTy/7jjz/E66z0YdtkMlk08ZZmzpk/kBmNRsVmfNImv+ZByCeeeAJvvfWWxXY373MoOTkZDg4O0Gq1Yr2l2cOC7Oxsi35kjUajxf44efJkhIaGit8XRu4V6ifdlkKwUqVSifUqqMm/UnantB8qoR9qKelvtmjRQgxeCgEKrVaLrKws5ObmigF/YZCWnj17Ys+ePThz5gzat2+P9PR0sbP37OxsHD9+3OLvyqx9+/ZISUmx6HM1LS0NJ06cQPv27QH82/m++X3jt99+i+rVq8vuHTMzM8XRk83nXbx4MXJzcxEZGYlTp07hn3/+wdSpUy3me/nll3H58mWLY9Iaod/OqlWrok6dOmjWrJlFf5THjh2DTqcrMDAoyM7Oxty5c6HVajFs2DCbvlMU7du3h6enJ3bs2IGoqCj079+/wIHbhg0bhu7du2PMmDGKn48ePRpGo1GxT8OdO3fi+vXrYpNLW/cBa8HBmzdvQqvViudyPz8/ZGZmYtOmTfDx8ZEdr35+fti5cycSEhLyDfwBeVl/58+fx4EDB8RpKpUKQUFB2L9/P7Zv344qVaqI3YsIPvvsM6hUKvz3v/8FALzwwgto1aoV5syZU2ot02w9BvJbpwCsZpq6urqiefPmcHNzw4YNG+Dl5ZVvsLi4eHp6olmzZtBoNNiyZQv69++fb7cTBQkLC4NKpcLKlSst1lNgYKDYDLgogoKCEB8fjwULFiA1NVUxi3bs2LFISkrCunXrLD5bt24dkpKSxBHhCzOvrdhTOxULo9EodropJW2q4+fnh127dsFkMskCfy4uLmjSpAkOHjyIdu3a2fRwYW9vj1deeQXvvvsuDh06hG7duhXbslAeoWNSc61bt8aiRYswduxYDBkyBGPGjIGPj4/4QLR161axWVp2djb27NmD3r17yzrPFgwdOhTz5s3D9evXLQZ0ofJFq9Xiiy++wJgxY/DKK69gw4YNhepLjMqe0KSxevXqqF69Opo2bYrt27fDaDTCwcEB2dnZuHLlCl577TXMnj1b/J7wmVROTg7at2+PBQsWyDqiNplMsiwz4N++6ITO8T/++GPZ/FKZmZkW2XjNmze3eHN+48YN2NvbWwQNhODR3LlzAfwbdLQ2CpxarYbRaLRoeiQdcRb4N4MpNzdXsWN5jUYjC1wZjUacO3dO/Fu6rObLbP4298iRI3jw4IFs2dRqNXJzc8Vgn3Swh5iYGDg7OyM9PR2rV6+WBcSkmUsGg0EccVVYbiAvECsEQ+zs7GQPvg4ODmJWlXkmlbu7u9VOtnU6nUW/hkIfS+YPQiaTCfv375dNT0lJgUqlQlRUFAYMGIB79+7lm2EKyLNApdvSvN7Sewyj0Sg2AZaOHC3VpUsXsfmXMOLge++9ZzHf/fv3MXLkSIt9Va1WQ6PRiNtT2CeVRts1GAw4ePCg+G9p9wpCdp9Aekyq1WrZv80DV+ZNw4V1Kd3W0vI1Gg3+/vtvzJ8/X1ZHtVoNLy8vWVZPWloa6tatK5uWk5MDFxcX2bqvWrUq5s+fb7G8Tk5OsmNg48aNiIiIEL8rZPLWrl0bqampFtm+wnaLj49XPCeYE45toRydTie7f5UeG0DeuhO2mdC8LT09Hbdv3xZfAOj1eri6uqJ79+7i+VBY302aNEHTpk3x0ksvwWg0wtnZGVu3bsWlS5dw48YN+Pr64tKlS9i0aRO6d++ueK9UmQQGBqJdu3aYMmUKJk+ejKZNmyI+Ph6hoaFQq9UIDg5GXFwcfv/9d7z66quypnKCoKAgbN68GampqXB1dcW+ffuQkZGB4OBgxflDQ0MRHh6OK1euwMnJCePGjbN4GdS0aVOsX78e4eHhFi8/pM84OTk5+Ouvv7Bq1So0adJEfPEyY8YMhISEYN68eXj66adx9uxZrFu3DuPHj7d4uWNeZkZGBi5fvoxt27bhzp07mD9/vqwbgISEBMX78aefftoioG/L85harcaAAQPw9ddfw2Qy2dQPWevWrS2y4aSefPJJvPHGG/j000+RlpaGIUOGQKfT4ciRI/jmm28QEBCA//znPwBs2weAvMFSDAYDevfujQYNGiAtLQ1RUVE4cOAAxo4dK57LfX19oVarcfDgQbEfNkHbtm3x2WefAYBiizKpdu3aoUOHDuK9iiAoKAirV6/Gjz/+iBdeeEH2cuHkyZP46aef8PHHH4svUtRqNebMmYNhw4Zh8+bN+fbFWhBbt72tx8CNGzdw4cIFBAUFoUmTJsjOzsbRo0exefNm9OrVy6LV1p9//omTJ0+iRYsWyMrKwv79+7Fz506sWbPGIlickpKiuO/Vq1cv3yxOJT///DOys7NRr149xMfHY9u2bbh7967YxLuowsPD0a5dO8XBV9LS0hASEoJjx45ZBHdtERAQgOrVq2PTpk1o1KiRRZcfQN6LoNGjR2PFihW4d++e+DJs9+7d2L59O0aPHi0OslOYeW3FwB8Vi6ysLLzwwgsW059//nnMmzcPwL8jL1WtWlXWtw+Qd9K+fPlygSdlqeeeew5ffvkl1qxZw8BfCcjOzhb7U5D67LPPMGjQIPz4449Yu3YtfvrpJ6xYsQIqlQp169ZFYGAgFi9eDFdXV0RFRSE1NRXPPfec4m8EBQXhs88+Q1hYmOJvUfHJysp65IwdFxcXhIaGYuTIkZgwYQI2b96s2JE9lT9C1pDRaBTP1XZ2drCzs4OTkxMiIyPRvXt3JCUlyQJzWq1WFlAQHrJzcnIwaNAgxd+yNjqcLc2dlEbotNZcRvqALwTuhICP+Rtba81QhYdz8/mVBrIQ5hcCmebq1KmD27dvIycnR2xSrcTd3b3AUdguXbokCz4IfytlDxgMBmRkZMDNzQ01atSwGFxFSqi7tBxp0NM8OzM7O1vcbuZlurm5WQ38mfc/KDSTBCwDKyaTSbEck8mEBw8e4NChQ4XuHD8/1jIezPcRYb2Y9/lkrYzU1FTFfdVoNBZL1of5Pmlvb4/c3FyYTCbxb2uZCg4ODmjYsCEuXLgAQD6wStOmTTFq1Ch8+OGH4jRpOcIxLw2MarVa2f5g3iTbYDBYbFNhkA7zILt54Ds5OVlxfxC6H1AKHAv1LMqACOb7lrXyhbodPHgQgwcPxu3bt2WDQfTu3Rsvv/wyIiIixOxWk8mEr776CkajEdWqVYNarUZSUpKYVSgEem/evIlBgwYVOnujIlKr1Vi9ejWWLVuGr7/+GvHx8XBxcUGnTp2wfPly1KxZE+vWrYPRaLR67zh48GCsX78eUVFReP755xEeHo4nnnhCMeAB5D0vfPzxx7h+/Tp69eqlmAHu4eGBp556CuHh4Xj99ddl+5L0GcfOzg61atXCs88+iylTpohBoB49emDx4sX44osvsGXLFtSsWRNTp061CEQplenk5AQvLy8EBARgxYoVaNy4sWzev/76S/Ee+eDBgxZ9RdryPAbkNfddt24d6tWrV2xNNl966SU0btwY69atwxtvvCGeZ0aOHIm3335bDBTZsg8AwKhRo7Bjxw6sXr0aCQkJ0Ol0qFevHubNmyfrh9PNzQ1NmjTB5cuXLZpI+/r6wmQyoWbNmop9xpoLCQmxGIG+WbNm8Pb2xqVLl2RBUr1ejzlz5qBdu3aybhGAvEFHRo4ciSVLlqBPnz4FDtZlja3b3tZj4H//+x+ys7OxYcMGxMXFQaPRoE6dOvjf//6HkSNHWnzP3t4eu3fvFgf/a9OmDTZs2KDYFD06Olpx3xOeGwvDZDJh3bp1uHv3LpycnPDUU09h4cKFVgeHs8W5c+dw48YNcVR2c926dYOHhwfCwsKKFPjTaDTo168fNmzYYNEcXOq9995DmzZtsHnzZrE/22bNmmH+/PkW57zCzGsLlSm/TlmIiKhSmDJlCv7++2/8+OOPZV0VqoBWr16N5cuXY82aNRU6I8VgMCAwMBCDBg3CrFmzyro6hVLYY3j27NmIjIzE5s2bFQfuKanfpfKpIu/7RXXx4kUMGjQIq1atKnRmhODatWsYPnw4+vbtKwucEFH+MjMzMWLECJhMJmzatOmRmmgS0aNjH39ERJXYhQsX8M033+DXX39Fnz59yro6VEFNmjQJPXv2xNSpU8W+jSoSg8GAkydPYu7cuUhMTETv3r3Luko2K+ox/O6776JJkyaYOHGiTf2xFtfvUvlSkff9ohJG4Zw3bx6qVKliNQvGFo0bN8aCBQvwww8/5NvUkYjkHB0dsXLlSsTFxWH69OkWGeVEVLqY8UdEVIkNHjwYycnJGDBgAKZNm1ao0Z+IKouUlBR07twZ9evXx6RJkywGJSnPyuoY5rmjcqjI+35R7d27F//973/RvHlzvPvuu4p9LRERET1OGPgjIiIiIiIiIiKqhNjUl4iIiIiIiIiIqBJi4I+IiIiIiIiIiKgSYuCPiIiIiIiIiIioEmLgj4iIiIiIiIiIqBJi4I+ICu3HH3+Et7c37t69W+jvnjhxAt7e3jhx4kQJ1IyIiCqi5cuXw9vbu6yrQUREZNWsWbPQo0ePsq4GUaEx8EdEREREldaXX36JvXv3lnU1iIiIiMqEymQymcq6EkRUsRgMBuTm5kKr1UKlUhXqu0ajETk5ObC3t4dazXcPRESUl/G3YsUKXLp0qdjL9vX1RZ8+fTB//vxiL5uIiB4fOTk5MJlM0Gq1ZV0VokLhUzcR2SwjIwMAoNFo4ODgUOigHwCo1Wo4ODgw6EdEREREROVCdnY2jEaj4mfCM5C9vX2xBf1MJhOysrKKpSyigvDJm+gxdf78eUyYMAF+fn7w9fXF2LFjcebMGfFzoR+/kydPYs6cOQgICMBTTz0l+0zax5/RaMTy5csRGBiINm3aIDg4GFevXkWPHj0wa9YscT6lPv6Cg4MRFBSEq1evIjg4GG3atEHXrl2xZs2akl8RRERUqk6dOoWhQ4fCx8cHvXr1wtatWxXn27lzJ4YMGYLWrVujQ4cOmDFjBv755x/ZPDdv3sTUqVPRpUsX+Pj4oFu3bpgxYwZSU1MBAN7e3sjIyMBPP/0Eb29veHt7y65JRERUscTFxeHtt99GYGAgWrVqhR49euD999+HXq9HUlISPv30UwwcOBC+vr7w8/PDhAkTcPHiRVkZwvNIREQEPv/8c3Tt2hVt2rRBWloaZs2aBV9fX9y+fRsvv/wyfH198cYbbwBQ7uPPaDRi/fr1GDBgAHx8fNC5c2fMnj0bycnJsvl69OiBSZMm4fDhw+K1zdr1j6i42ZV1BYio9F25cgWjRo2Cs7MzJkyYADs7O2zbtg3BwcHYuHEj2rRpI877wQcfwMPDA5MnTxbfdilZtGgRQkND0b17d3Tt2hUXL17E+PHjkZ2dbVOdkpOTMWHCBDzzzDPo168foqKisHDhQjRr1kwMOBIRUcV26dIljB8/Hh4eHpg6dSpyc3OxfPlyVKtWTTbfqlWrsHTpUvTr1w/PP/88EhMTsXHjRowaNQo7duyAm5sb9Ho9xo8fD71ej9GjR6N69eqIi4vDr7/+ipSUFLi6uuKzzz7Du+++i9atW2P48OEAgHr16pXFohMR0SOKi4vD888/j9TUVAwfPhyNGjVCXFwcoqKikJWVhTt37mDv3r3o27cvvLy8cP/+fWzbtg2jR49GREQEPD09ZeV98cUXsLe3F68l9vb2AIDc3FyMHz8e/v7+ePPNN6HT6azWafbs2fjpp58wZMgQBAcH4+7du9i0aRPOnz+PLVu2iGUCwI0bNzBz5ky88MILGD58OBo2bFgyK4rIDAN/RI+hJUuWICcnB1u2bEHdunUBAM899xz69u2LBQsWYOPGjeK87u7uWL9+PTQajdXy7t+/j/Xr16NXr15YuXKlOH3FihVYvny5TXWKj4/Hp59+iueeew4A8Pzzz6NHjx744YcfGPgjIqokli1bBpPJhE2bNuGJJ54AAPTp0wcDBw4U54mNjcXy5csxffp0vPLKK+L03r17Y/Dgwdi8eTNeeeUVXLt2DXfv3sXSpUvRt29fcb4pU6aIfw8aNAhz5sxB3bp1MWjQoFJYQiIiKimLFy/G/fv3sX37dvj4+IjTp02bBpPJBG9vb0RFRcm6FBo0aBD69euH77//HpMnT5aVl52djR9++MEisKfX69G3b1/MnDkz3/qcOnUK3333HRYuXCi7jnXs2BETJkzArl27ZNNv3bqF0NBQdO3atUjLT1RUbOpL9JgxGAw4evQoevXqJQb9AKBmzZoICgrC6dOnkZaWJk4fPnx4vkE/ADh+/Dhyc3MxcuRI2fTRo0fbXC8nJyfZQ5lWq4WPjw/u3LljcxlERFR+GQwGHDlyBL169RKDfgDQuHFjBAYGiv/es2cPjEYj+vXrh8TERPG/6tWro379+mJXES4uLgCAI0eOIDMzs3QXhoiISpXRaMTevXvRvXt3WdBPoFKpoNVqxaCfwWDAw4cP4eTkhIYNG+L8+fMW33nuueesZvONGDGiwDrt2rULrq6u6NKli+x61bJlSzg5Ocm6NgIALy8vBv2oTDDjj+gxk5iYiMzMTMXU8saNG8NoNMr6UPLy8iqwzL///huAZfOpKlWqwN3d3aZ61apVy2KwEHd39xIZ4ZGIiEpfYmIisrKyUL9+fYvPGjZsiIMHDwLI67fPZDKhd+/eiuXY2eXdvtatWxfjxo3D119/jbCwMLRr1w49evTAs88+C1dX15JbECIiKnWJiYlIS0tD06ZNrc5jNBrx7bffYvPmzbh79y4MBoP4WZUqVSzmt/acY2dnh1q1ahVYp1u3biE1NRUBAQGKnz948MCm3yMqaQz8EVG+HBwcSuV3CsoqJCKix4PRaIRKpcKaNWsUrw1OTk7i37NmzcLgwYOxb98+HD16FB999BFWr16N7du32/TQRkRElceXX36JpUuXYujQoZg2bRrc3d2hVqvx8ccfw2QyWcxvLdtPmjmYH6PRiGrVqmHhwoWKn3t4eNj0e0QljYE/oseMh4cHHB0dcePGDYvPrl+/DrVajdq1a+Ps2bM2lyk02bp9+7as+fDDhw8tRrQiIqLHk4eHB3Q6HW7dumXxmfSaVK9ePZhMJnh5ednU8bkwWm9ISAiio6MxYsQIbNmyBTNmzCjW+hMRUdnx8PCAi4sLrly5YnWeqKgodOzYER9//LFsekpKCqpWrVrsdapXrx6OHz8OPz8/BvWoXGMff0SPGY1Ggy5dumDfvn24e/euOP3+/fsIDw+Hv7+/2G+SrQICAmBnZ4ctW7bIpm/atKlY6kxERBWfRqNBYGAg9u7dK3YRAQDXrl3DkSNHxH/37t0bGo0GK1assMjQMJlMePjwIQAgLS0Nubm5ss+bNWsGtVoNvV4vTnNyckJKSkpJLBIREZUStVqNXr164cCBA4oJCiaTCRqNxuK68csvvyAuLq5E6tSvXz8YDAZ88cUXFp/l5uby2kPlBjP+iB5D06dPx7FjxzBy5EiMHDkSGo0G27Ztg16vx3//+99Cl1e9enWMGTMG69atwyuvvIKuXbvi0qVLOHToEKpWrWrRdx8RET2epk6disOHD2PUqFEYMWIEDAYDNm7ciCZNmoh9utarVw/Tp0/HokWLEBsbi169esHZ2Rl3797F3r17MXz4cIwfPx6//fYbPvzwQ/Tt2xcNGjSAwWDAzp07odFo0KdPH/E3W7ZsiePHj+Prr79GzZo14eXlhTZt2pTVKiAioiJ6/fXXcfToUQQHB2P48OFo3LgxEhISsGvXLmzevBlPP/00Vq5cibfeegu+vr64fPkywsLCZC2SilOHDh3wwgsvYPXq1bhw4QK6dOkCe3t73Lx5E7t27cI777wjG3WeqKww8Ef0GGratCk2bdqERYsWYfXq1TCZTGjdujUWLFhQ5IehN954AzqdDt999x2OHz+Otm3bYu3atRg5ciS0Wm0xLwEREVVEzZs3x9q1a/HJJ59g2bJlqFWrFqZOnYqEhATZYE4TJ05EgwYNsH79eqxcuRJA3iBQXbp0QY8ePQDkNfENDAzEgQMHEBcXB0dHR3h7e2PNmjVo27atWNasWbMwe/ZsLFmyBFlZWRg8eDADf0REFZCnpye2b9+OpUuXIiwsDGlpafD09ES3bt2g0+nwyiuvIDMzE2FhYYiMjMSTTz6J1atXY9GiRSVWpw8//BCtWrXC1q1b8fnnn0Oj0aBOnTp49tln4efnV2K/S1QYKpNSL5dERMUgJSUF7du3x/Tp0/Hqq6+WdXWIiIiIiIiIHivs44+IikVWVpbFtG+++QZAXho8EREREREREZUuNvUlomIRGRmJn376Cd26dYOTkxOio6MRHh6OwMBA+Pv7l3X1iIiIiIiIiB47DPwRUbHw9vaGRqNBaGgo0tPTUa1aNYwZMwbTp08v66oRERERERERPZbYxx8REREREREREVElxD7+iIiIiIiIiIiIKiEG/oiIiIiIiIiIiCohBv6IiIiIiIiIiIgqIQb+iIiIiIiIiIiIKiEG/oiIiIiIiIiIiCohBv6IiIiIiIiIiIgqIQb+iIiIiIiIiIiIKiEG/oiIiIiIiIiIiCohBv6IiIiIiIiIiIgqof8D1IIFrESX6r4AAAAASUVORK5CYII=",
"text/plain": [
"<Figure size 1500x500 with 3 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#3 Balkendiagramme zu Abflughafen, 'Ihre Auswahl' und 'Ihre Auswahl':\n",
"\n",
"fig, axs = plt.subplots(1, 3, figsize=(15, 5))\n",
"sns.countplot(data=fls, x='origin', ax=axs[0]).set_title(\"Abfuhr\")\n",
"sns.countplot(data=fls, x='dest', ax=axs[1]).set_title(\"Ankunft\")\n",
"sns.countplot(data=fls, x='carrier', ax=axs[2]).set_title(\"Lufthansa\")\n",
"#TODO: Graphen für axs[1] und axs[2] hinzufügen\n",
"#TODO: Titel für die Graphen hinzufügen\n",
"plt.show()\n"
]
},
{
"cell_type": "markdown",
"id": "4656d434",
"metadata": {},
"source": [
"### Zusammenfassung kontinuierlicher Variablen\n",
"\n",
"Die Flugverspätung `arr_delay` ist eine kontinuierliche Variable, d.h. es gibt eine große Anzahl (prinzipiell unendlich viele) unterschiedliche Werte.\n",
"Die Darstellung erfolgt dann in einem Histogramm, die Werte werden in Klassen (engl. bins) zusammengefasst."
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "489fadc9",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:27.401876Z",
"start_time": "2024-09-27T07:14:26.408359Z"
}
},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"sns.histplot(data=fls, x='arr_delay', bins=100)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"id": "1da45283",
"metadata": {},
"source": [
"Hier schauen wir zunächst auf zusammenfassende Statistiken wie Mittelwert, Standardabweichung, Median, Quantile etc. Wenn Ihnen diese Begriffe nicht bekannt sind, lesen Sie bitte in einem Statistikbuch nach. Verständnis und Interpretation üben wir in der nächsten Vorlesung.\n",
"\n",
"Verschiedene Module bieten Zusammenfassungen von Statistikdaten.\n",
"Hier finden Sie einige Dokumentationen: \n",
"https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.describe.html\n",
"https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.describe.html\n",
"https://www.statsmodels.org/stable/generated/statsmodels.stats.descriptivestats.describe.html#statsmodels.stats.descriptivestats.describe\n",
"\n",
"\n",
"#### Wichtiger Hinweis zur Berechnung von Varianzen und Standardabweichungen\n",
"Verschiedene Bibliotheken verwenden verschiedene Vorfaktoren für die Berechnung von Streuparametern. Traditionell wird in der deskriptiven Statistik der Vorfaktor $\\frac{1}{n}$ verwendet. Damit sind die Metriken aber nicht erwartungstreu. Daher sollte, wie in der schließenden Statistik üblich, der Vorfaktor $\\frac{1}{n-1}$ verwendet werden. Gekennzeichnet wird das über den Parameter ddof (delta degrees of freedom): ddof=0 für $\\frac{1}{n}$ und ddof=1 für $\\frac{1}{n-1}$. \n",
"\n",
"Pandas: ddof=1\n",
"scipy: ddof=0\n",
"numpy: ddof=0\n"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "46a03abc",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:27.608456Z",
"start_time": "2024-09-27T07:14:27.583742Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"count 327346.000000\n",
"mean 6.895377\n",
"std 44.633292\n",
"min -86.000000\n",
"25% -17.000000\n",
"50% -5.000000\n",
"75% 14.000000\n",
"max 1272.000000\n",
"Name: arr_delay, dtype: float64\n"
]
}
],
"source": [
"#Calculate descriptive statistics using pandas for fls[\"arr_delay\"]. As fls is a pandas dataFrame this is a pandas method.\n",
"print(fls[\"arr_delay\"].describe())"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "04e7441a",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:27.760088Z",
"start_time": "2024-09-27T07:14:27.711610Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"DescribeResult(nobs=np.int64(327346), minmax=(np.float64(-86.0), np.float64(1272.0)), mean=np.float64(6.89537675731489), variance=np.float64(1992.1307271019398), skewness=np.float64(3.7168004488352424), kurtosis=np.float64(29.232579155522807))"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Calculate descriptive statistics using scipy for fls[\"arr_delay\"]. Be aware to correct for ddof=1!\n",
"stats.describe(fls[\"arr_delay\"], ddof=1)"
]
},
{
"cell_type": "markdown",
"id": "cb5308ef",
"metadata": {},
"source": [
"### Visualisierung zusammengefasster kontinuierlicher Daten nach Kategorie\n",
"\n",
"Es gibt verschiedene Möglichkeiten Zusammenfassungen von kontinuierlichen Daten nach Kategorien darzustellen. Hier drei schöne Beispiel aus seaborn im Vergleich:\n",
"- Boxplot: grafische Übersicht der wichtigsten Quantile. Praktischerweise dann auch für verschiedene Kategorien einer Variable getrennt möglich\n",
"- Violinplot: kombiniert Dichteschätzer und Boxlot (Box nimmt Form der geschätzten Dichtefunktion an)\n",
"- Kategoriale Barplots verschiedener Metriken (Mittelwert, Median, etc.)\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "6d5810fb",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:42.376578Z",
"start_time": "2024-09-27T07:14:27.799428Z"
}
},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1600x500 with 3 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig, axs = plt.subplots(1, 3, figsize=(16, 5))\n",
"\n",
"sns.boxplot(x=\"origin\", y=\"arr_delay\", data=fls, ax=axs[0])\n",
"sns.violinplot(x=\"origin\", y=\"arr_delay\", data=fls, ax=axs[1])\n",
"sns.barplot(data=fls, x=\"origin\", y=\"arr_delay\", estimator=\"median\", ax=axs[2])\n",
"\n",
"axs[0].set_ylabel('Arrival Delay in Minutes')\n",
"axs[1].set_ylabel('Arrival Delay in Minutes')\n",
"axs[2].set_ylabel('Median Arrival Delay in Minutes')\n",
"\n",
"plt.show()\n"
]
},
{
"cell_type": "markdown",
"id": "4b8cd2caf98fe15a",
"metadata": {},
"source": [
"##### Überlegen Sie:\n",
"- Was zeigen die verschiedenen Graphen? $\\rightarrow$ Lesen Sie ggf. nach, wie die verschiedenen Graphen definiert sind\n",
"- Welche Vor- und Nachteile haben die verschiedenen Graphen? \n",
"\n",
"\n",
"### Lageparameter im Vergleich\n",
"Im Balkendiagramm können verschiedene statistische Größen gezeigt werden. Unten zwei Graphen, die die Lageparameter Mittelwert und Median nebeneinander stellen. \n",
" \n",
"##### Überlegen Sie:\n",
"- Welche Unterschiede sehen Sie? \n",
"- Woran könnte das liegen?\n"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "5f3475ea",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:53.917392Z",
"start_time": "2024-09-27T07:14:42.415234Z"
}
},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1500x500 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig, axs = plt.subplots(1, 2, figsize=(15, 5), sharey=True)\n",
"sns.barplot(data=fls, x=\"origin\", y=\"arr_delay\", ax=axs[0]) # Mittelwert, Fehlerbalken werden defaultmäßig angezeigt \n",
"sns.barplot(data=fls, x=\"origin\", y=\"arr_delay\", estimator='median', ax=axs[1]) # Median\n",
"\n",
"axs[0].set_title('Mean Arrival Delay in Minutes')\n",
"axs[1].set_title('Median Arrival Delay in Minutes')\n",
"\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"id": "57782e6a47eb2008",
"metadata": {},
"source": [
"## 3. Weitere Untersuchung des Datensatzes\n",
"\n",
"Nutzen Sie die Ihnen bekannten Mehoden, um den Datensatz weiter zu untersuchen."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "651c0e725e27db74",
"metadata": {
"ExecuteTime": {
"end_time": "2024-09-27T07:14:53.957094Z",
"start_time": "2024-09-27T07:14:53.949728Z"
}
},
"outputs": [],
"source": [
"# TODO: Weitere Daten visualisieren und Statistiken berechnen"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue View Git Blame Copy Permalink