ajoubrel-ensae/BDC-team-1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
473f8100b0
BDC-team-1/Spectacle/2_bis_logit_baseline_statsmodels.ipynb

2867 lines
336 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

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

{
"cells": [
{
"cell_type": "markdown",
"id": "56949d8f-4eaf-4685-9989-ba0b4b1945b7",
"metadata": {},
"source": [
"# Baseline logit on spectacle companies with statmodels"
]
},
{
"cell_type": "markdown",
"id": "eae443dc-6c28-401a-a30e-e02f5f4da2df",
"metadata": {},
"source": [
"## Importation des packages et des données"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "72480e84-2ccc-481a-9353-1199e4358d62",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import os\n",
"import s3fs\n",
"import re\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.metrics import accuracy_score, confusion_matrix, classification_report, recall_score\n",
"from sklearn.utils import class_weight\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"from sklearn.pipeline import Pipeline\n",
"from sklearn.compose import ColumnTransformer\n",
"from sklearn.preprocessing import OneHotEncoder\n",
"from sklearn.impute import SimpleImputer\n",
"from sklearn.model_selection import GridSearchCV\n",
"from sklearn.preprocessing import StandardScaler, MaxAbsScaler, MinMaxScaler\n",
"from sklearn.metrics import make_scorer, f1_score, balanced_accuracy_score\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.metrics import roc_curve, auc, precision_recall_curve, average_precision_score\n",
"from sklearn.exceptions import ConvergenceWarning, DataConversionWarning\n",
"\n",
"import statsmodels.api as sm\n",
"\n",
"import pickle\n",
"import warnings"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "7090dc21-7889-4776-a0a4-f7c6a5416d53",
"metadata": {},
"outputs": [],
"source": [
"# Create filesystem object\n",
"S3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n",
"fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "2f0d08c9-5b26-4eff-9c89-4a46f427dbf7",
"metadata": {},
"outputs": [],
"source": [
"def load_train_test():\n",
" BUCKET = \"projet-bdc2324-team1/Generalization/musique\"\n",
" File_path_train = BUCKET + \"/Train_set.csv\"\n",
" File_path_test = BUCKET + \"/Test_set.csv\"\n",
" \n",
" with fs.open( File_path_train, mode=\"rb\") as file_in:\n",
" dataset_train = pd.read_csv(file_in, sep=\",\")\n",
" # dataset_train['y_has_purchased'] = dataset_train['y_has_purchased'].fillna(0)\n",
"\n",
" with fs.open(File_path_test, mode=\"rb\") as file_in:\n",
" dataset_test = pd.read_csv(file_in, sep=\",\")\n",
" # dataset_test['y_has_purchased'] = dataset_test['y_has_purchased'].fillna(0)\n",
" \n",
" return dataset_train, dataset_test"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "438d0138-a254-464c-9e94-f7436576c1d5",
"metadata": {},
"outputs": [],
"source": [
"def features_target_split(dataset_train, dataset_test):\n",
" features_l = ['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'purchase_date_min', 'purchase_date_max', \n",
" 'time_between_purchase', 'nb_tickets_internet', 'fidelity', 'is_email_true', 'opt_in', #'is_partner',\n",
" 'gender_female', 'gender_male', 'gender_other', 'nb_campaigns', 'nb_campaigns_opened']\n",
" X_train = dataset_train[features_l]\n",
" y_train = dataset_train[['y_has_purchased']]\n",
"\n",
" X_test = dataset_test[features_l]\n",
" y_test = dataset_test[['y_has_purchased']]\n",
" return X_train, X_test, y_train, y_test"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "ebe9a887-61a4-4a5e-ac64-231307dd7647",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_426/3642896088.py:7: DtypeWarning: Columns (38) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" dataset_train = pd.read_csv(file_in, sep=\",\")\n",
"/tmp/ipykernel_426/3642896088.py:11: DtypeWarning: Columns (38) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" dataset_test = pd.read_csv(file_in, sep=\",\")\n"
]
}
],
"source": [
"dataset_train, dataset_test = load_train_test()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "b21fdea2-02c4-4222-b4e0-635e423f91c2",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"customer_id 0\n",
"nb_tickets 0\n",
"nb_purchases 0\n",
"total_amount 0\n",
"nb_suppliers 0\n",
"vente_internet_max 0\n",
"purchase_date_min 0\n",
"purchase_date_max 0\n",
"time_between_purchase 0\n",
"nb_tickets_internet 0\n",
"street_id 0\n",
"structure_id 327067\n",
"mcp_contact_id 135224\n",
"fidelity 0\n",
"tenant_id 0\n",
"is_partner 0\n",
"deleted_at 354365\n",
"gender 0\n",
"is_email_true 0\n",
"opt_in 0\n",
"last_buying_date 119201\n",
"max_price 119201\n",
"ticket_sum 0\n",
"average_price 115193\n",
"average_purchase_delay 119203\n",
"average_price_basket 119203\n",
"average_ticket_basket 119203\n",
"total_price 4008\n",
"purchase_count 0\n",
"first_buying_date 119201\n",
"country 56856\n",
"gender_label 0\n",
"gender_female 0\n",
"gender_male 0\n",
"gender_other 0\n",
"country_fr 56856\n",
"nb_campaigns 0\n",
"nb_campaigns_opened 0\n",
"time_to_open 224310\n",
"y_has_purchased 0\n",
"dtype: int64"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dataset_train.isna().sum()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "42c4d034-8bc1-4ebb-a1ff-60c0a86f8f7c",
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = features_target_split(dataset_train, dataset_test)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "94b4498d-6ae8-4c96-adbc-7ba1b8348160",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Shape train : (354365, 17)\n",
"Shape test : (151874, 17)\n"
]
}
],
"source": [
"print(\"Shape train : \", X_train.shape)\n",
"print(\"Shape test : \", X_test.shape)"
]
},
{
"cell_type": "markdown",
"id": "29206597-bce8-41e0-9b68-9b9a2843787a",
"metadata": {},
"source": [
"## optionnel : calcul des poids\n",
"On pourrait utiliser les poids pour gérer le déséquilibre de classe, mais dans une optique exploratoire, c'est pas indispensable et ça a pas été utilisé ici !"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "6224fd31-c190-4168-b395-e0bf5806d79d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{0.0: 0.5481283836040216, 1.0: 5.694439980716696}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Compute Weights\n",
"weights = class_weight.compute_class_weight(class_weight = 'balanced', classes = np.unique(y_train['y_has_purchased']),\n",
" y = y_train['y_has_purchased'])\n",
"\n",
"weight_dict = {np.unique(y_train['y_has_purchased'])[i]: weights[i] for i in range(len(np.unique(y_train['y_has_purchased'])))}\n",
"weight_dict"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "4680f202-979e-483f-89b8-9df877203bcf",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([0.54812838, 0.54812838, 0.54812838, ..., 5.69443998, 0.54812838,\n",
" 0.54812838])"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Calcul des poids inverses à la fréquence des classes\n",
"class_counts = np.bincount(y_train['y_has_purchased'])\n",
"class_weights = len(y_train['y_has_purchased']) / (2 * class_counts)\n",
"\n",
"# Sélection des poids correspondants à chaque observation\n",
"weights = class_weights[y_train['y_has_purchased'].values.astype(int)]\n",
"weights"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "5f747be4-e70b-491c-8f0a-46cb278a2dee",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[354365. 354365. 354365. ... 354365. 354365. 354365.]\n",
"354365\n"
]
}
],
"source": [
"# verif\n",
"print(2 * weights * class_counts[y_train['y_has_purchased'].values.astype(int)])\n",
"print(len(y_train['y_has_purchased']))"
]
},
{
"cell_type": "markdown",
"id": "bd1f7d9d-1aff-49e4-81ca-038f732b1595",
"metadata": {},
"source": [
"## définition des variables X et y"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "ab25a901-28da-4504-a7d1-bf41fa5068bc",
"metadata": {},
"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>nb_tickets</th>\n",
" <th>nb_purchases</th>\n",
" <th>total_amount</th>\n",
" <th>nb_suppliers</th>\n",
" <th>vente_internet_max</th>\n",
" <th>purchase_date_min</th>\n",
" <th>purchase_date_max</th>\n",
" <th>time_between_purchase</th>\n",
" <th>nb_tickets_internet</th>\n",
" <th>fidelity</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>gender_other</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>13.0</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>10.0</td>\n",
" <td>9.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>14.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>9.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354360</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354361</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>11.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354362</th>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>50.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>91.030556</td>\n",
" <td>91.020139</td>\n",
" <td>0.010417</td>\n",
" <td>0.0</td>\n",
" <td>4</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>6.0</td>\n",
" <td>6.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354363</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>55.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>52.284028</td>\n",
" <td>52.284028</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354364</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>354365 rows × 17 columns</p>\n",
"</div>"
],
"text/plain": [
" nb_tickets nb_purchases total_amount nb_suppliers \\\n",
"0 0.0 0.0 0.0 0.0 \n",
"1 0.0 0.0 0.0 0.0 \n",
"2 0.0 0.0 0.0 0.0 \n",
"3 0.0 0.0 0.0 0.0 \n",
"4 0.0 0.0 0.0 0.0 \n",
"... ... ... ... ... \n",
"354360 0.0 0.0 0.0 0.0 \n",
"354361 0.0 0.0 0.0 0.0 \n",
"354362 2.0 2.0 50.0 1.0 \n",
"354363 1.0 1.0 55.0 1.0 \n",
"354364 0.0 0.0 0.0 0.0 \n",
"\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 0.0 550.000000 550.000000 \n",
"1 0.0 550.000000 550.000000 \n",
"2 0.0 550.000000 550.000000 \n",
"3 0.0 550.000000 550.000000 \n",
"4 0.0 550.000000 550.000000 \n",
"... ... ... ... \n",
"354360 0.0 550.000000 550.000000 \n",
"354361 0.0 550.000000 550.000000 \n",
"354362 0.0 91.030556 91.020139 \n",
"354363 0.0 52.284028 52.284028 \n",
"354364 0.0 550.000000 550.000000 \n",
"\n",
" time_between_purchase nb_tickets_internet fidelity is_email_true \\\n",
"0 -1.000000 0.0 1 True \n",
"1 -1.000000 0.0 0 True \n",
"2 -1.000000 0.0 1 True \n",
"3 -1.000000 0.0 0 True \n",
"4 -1.000000 0.0 0 True \n",
"... ... ... ... ... \n",
"354360 -1.000000 0.0 0 True \n",
"354361 -1.000000 0.0 0 True \n",
"354362 0.010417 0.0 4 True \n",
"354363 0.000000 0.0 1 True \n",
"354364 -1.000000 0.0 0 True \n",
"\n",
" opt_in gender_female gender_male gender_other nb_campaigns \\\n",
"0 True 1 0 0 13.0 \n",
"1 True 0 0 1 10.0 \n",
"2 True 0 1 0 14.0 \n",
"3 False 0 0 1 9.0 \n",
"4 False 0 0 1 4.0 \n",
"... ... ... ... ... ... \n",
"354360 False 0 0 1 7.0 \n",
"354361 True 0 1 0 11.0 \n",
"354362 False 1 0 0 6.0 \n",
"354363 True 0 1 0 3.0 \n",
"354364 False 0 1 0 7.0 \n",
"\n",
" nb_campaigns_opened \n",
"0 4.0 \n",
"1 9.0 \n",
"2 0.0 \n",
"3 0.0 \n",
"4 0.0 \n",
"... ... \n",
"354360 0.0 \n",
"354361 2.0 \n",
"354362 6.0 \n",
"354363 0.0 \n",
"354364 0.0 \n",
"\n",
"[354365 rows x 17 columns]"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# visu de X_train\n",
"X_train"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "648fb542-0186-493d-b274-be2c26a11967",
"metadata": {},
"outputs": [],
"source": [
"# model logit\n",
"X = X_train.astype(int)\n",
"# X = sm.add_constant(X.drop(\"gender_other\", axis=1))\n",
"y = y_train['y_has_purchased'].values\n",
"\n",
"# print(X,y)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "978b9ebc-aa97-41d7-a48f-d1f79c1ed482",
"metadata": {},
"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>nb_tickets</th>\n",
" <th>nb_purchases</th>\n",
" <th>total_amount</th>\n",
" <th>nb_suppliers</th>\n",
" <th>vente_internet_max</th>\n",
" <th>purchase_date_min</th>\n",
" <th>purchase_date_max</th>\n",
" <th>time_between_purchase</th>\n",
" <th>nb_tickets_internet</th>\n",
" <th>fidelity</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>gender_other</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>13</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>10</td>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>14</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354360</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>7</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354361</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>11</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354362</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>50</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>91</td>\n",
" <td>91</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354363</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>55</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>52</td>\n",
" <td>52</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354364</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>7</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>354365 rows × 17 columns</p>\n",
"</div>"
],
"text/plain": [
" nb_tickets nb_purchases total_amount nb_suppliers \\\n",
"0 0 0 0 0 \n",
"1 0 0 0 0 \n",
"2 0 0 0 0 \n",
"3 0 0 0 0 \n",
"4 0 0 0 0 \n",
"... ... ... ... ... \n",
"354360 0 0 0 0 \n",
"354361 0 0 0 0 \n",
"354362 2 2 50 1 \n",
"354363 1 1 55 1 \n",
"354364 0 0 0 0 \n",
"\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 0 550 550 \n",
"1 0 550 550 \n",
"2 0 550 550 \n",
"3 0 550 550 \n",
"4 0 550 550 \n",
"... ... ... ... \n",
"354360 0 550 550 \n",
"354361 0 550 550 \n",
"354362 0 91 91 \n",
"354363 0 52 52 \n",
"354364 0 550 550 \n",
"\n",
" time_between_purchase nb_tickets_internet fidelity is_email_true \\\n",
"0 -1 0 1 1 \n",
"1 -1 0 0 1 \n",
"2 -1 0 1 1 \n",
"3 -1 0 0 1 \n",
"4 -1 0 0 1 \n",
"... ... ... ... ... \n",
"354360 -1 0 0 1 \n",
"354361 -1 0 0 1 \n",
"354362 0 0 4 1 \n",
"354363 0 0 1 1 \n",
"354364 -1 0 0 1 \n",
"\n",
" opt_in gender_female gender_male gender_other nb_campaigns \\\n",
"0 1 1 0 0 13 \n",
"1 1 0 0 1 10 \n",
"2 1 0 1 0 14 \n",
"3 0 0 0 1 9 \n",
"4 0 0 0 1 4 \n",
"... ... ... ... ... ... \n",
"354360 0 0 0 1 7 \n",
"354361 1 0 1 0 11 \n",
"354362 0 1 0 0 6 \n",
"354363 1 0 1 0 3 \n",
"354364 0 0 1 0 7 \n",
"\n",
" nb_campaigns_opened \n",
"0 4 \n",
"1 9 \n",
"2 0 \n",
"3 0 \n",
"4 0 \n",
"... ... \n",
"354360 0 \n",
"354361 2 \n",
"354362 6 \n",
"354363 0 \n",
"354364 0 \n",
"\n",
"[354365 rows x 17 columns]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X"
]
},
{
"cell_type": "code",
"execution_count": 138,
"id": "81b38ceb-5005-417d-a9a6-b2dac181a8fb",
"metadata": {},
"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>purchase_date_min</th>\n",
" <th>purchase_date_max</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>354365.000000</td>\n",
" <td>354365.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>406.981861</td>\n",
" <td>396.551502</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>189.343612</td>\n",
" <td>195.881681</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>0.009640</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>188.475293</td>\n",
" <td>153.457966</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" purchase_date_min purchase_date_max\n",
"count 354365.000000 354365.000000\n",
"mean 406.981861 396.551502\n",
"std 189.343612 195.881681\n",
"min 0.009640 0.000000\n",
"25% 188.475293 153.457966\n",
"50% 550.000000 550.000000\n",
"75% 550.000000 550.000000\n",
"max 550.000000 550.000000"
]
},
"execution_count": 138,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train[[\"purchase_date_min\", \"purchase_date_max\"]].describe()"
]
},
{
"cell_type": "code",
"execution_count": 143,
"id": "60effd66-2914-4cf9-aa0c-4e2f9dd13895",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 354365.000000\n",
"mean 10.430360\n",
"std 56.442718\n",
"min 0.000000\n",
"25% 0.000000\n",
"50% 0.000000\n",
"75% 0.000000\n",
"max 547.443350\n",
"dtype: float64"
]
},
"execution_count": 143,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(X_train[\"purchase_date_min\"] - X_train[\"purchase_date_max\"]).describe()"
]
},
{
"cell_type": "code",
"execution_count": 145,
"id": "7a99e480-9e11-448d-806e-3b71925a19db",
"metadata": {},
"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>nb_tickets</th>\n",
" <th>nb_purchases</th>\n",
" <th>total_amount</th>\n",
" <th>nb_suppliers</th>\n",
" <th>vente_internet_max</th>\n",
" <th>purchase_date_min</th>\n",
" <th>purchase_date_max</th>\n",
" <th>time_between_purchase</th>\n",
" <th>nb_tickets_internet</th>\n",
" <th>fidelity</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>gender_other</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.0</td>\n",
" <td>550.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>13.0</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.0</td>\n",
" <td>550.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>10.0</td>\n",
" <td>9.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.0</td>\n",
" <td>550.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>14.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.0</td>\n",
" <td>550.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>9.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.0</td>\n",
" <td>550.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354358</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.0</td>\n",
" <td>550.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354359</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.0</td>\n",
" <td>550.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>12.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354360</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.0</td>\n",
" <td>550.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354361</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.0</td>\n",
" <td>550.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>11.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354364</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.0</td>\n",
" <td>550.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>179675 rows × 17 columns</p>\n",
"</div>"
],
"text/plain": [
" nb_tickets nb_purchases total_amount nb_suppliers \\\n",
"0 0.0 0.0 0.0 0.0 \n",
"1 0.0 0.0 0.0 0.0 \n",
"2 0.0 0.0 0.0 0.0 \n",
"3 0.0 0.0 0.0 0.0 \n",
"4 0.0 0.0 0.0 0.0 \n",
"... ... ... ... ... \n",
"354358 0.0 0.0 0.0 0.0 \n",
"354359 0.0 0.0 0.0 0.0 \n",
"354360 0.0 0.0 0.0 0.0 \n",
"354361 0.0 0.0 0.0 0.0 \n",
"354364 0.0 0.0 0.0 0.0 \n",
"\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 0.0 550.0 550.0 \n",
"1 0.0 550.0 550.0 \n",
"2 0.0 550.0 550.0 \n",
"3 0.0 550.0 550.0 \n",
"4 0.0 550.0 550.0 \n",
"... ... ... ... \n",
"354358 0.0 550.0 550.0 \n",
"354359 0.0 550.0 550.0 \n",
"354360 0.0 550.0 550.0 \n",
"354361 0.0 550.0 550.0 \n",
"354364 0.0 550.0 550.0 \n",
"\n",
" time_between_purchase nb_tickets_internet fidelity is_email_true \\\n",
"0 -1.0 0.0 1 True \n",
"1 -1.0 0.0 0 True \n",
"2 -1.0 0.0 1 True \n",
"3 -1.0 0.0 0 True \n",
"4 -1.0 0.0 0 True \n",
"... ... ... ... ... \n",
"354358 -1.0 0.0 0 True \n",
"354359 -1.0 0.0 0 True \n",
"354360 -1.0 0.0 0 True \n",
"354361 -1.0 0.0 0 True \n",
"354364 -1.0 0.0 0 True \n",
"\n",
" opt_in gender_female gender_male gender_other nb_campaigns \\\n",
"0 True 1 0 0 13.0 \n",
"1 True 0 0 1 10.0 \n",
"2 True 0 1 0 14.0 \n",
"3 False 0 0 1 9.0 \n",
"4 False 0 0 1 4.0 \n",
"... ... ... ... ... ... \n",
"354358 False 1 0 0 1.0 \n",
"354359 True 0 1 0 12.0 \n",
"354360 False 0 0 1 7.0 \n",
"354361 True 0 1 0 11.0 \n",
"354364 False 0 1 0 7.0 \n",
"\n",
" nb_campaigns_opened \n",
"0 4.0 \n",
"1 9.0 \n",
"2 0.0 \n",
"3 0.0 \n",
"4 0.0 \n",
"... ... \n",
"354358 0.0 \n",
"354359 2.0 \n",
"354360 0.0 \n",
"354361 2.0 \n",
"354364 0.0 \n",
"\n",
"[179675 rows x 17 columns]"
]
},
"execution_count": 145,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train[X_train[\"time_between_purchase\"]==-1]"
]
},
{
"cell_type": "markdown",
"id": "a022e8c3-93e7-4530-85a4-da8812d82737",
"metadata": {},
"source": [
"## Prétraitement des données + modèle\n",
"\n",
"- variables à retirer : fidelity (valeurs trop grandes dont l'exp -> +inf, autre problème : st basé sur des infos qu'on a pas sur la période étudiée mais slt sur période d'évaluation), time between purchase (revoir sa construction), gender_other (colinéarité avec les autres var de genre)\n",
"- ajouter un intercept\n",
"- pas besoin de standardiser pour le moment, mais à faire quand on passera au modèle LASSO\n",
"\n",
"#### A recopier dans la pipeline -> section 2 bis"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "e6c8ccc7-6ab8-4e3c-af28-e71d17c07bcb",
"metadata": {},
"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>const</th>\n",
" <th>nb_tickets</th>\n",
" <th>nb_purchases</th>\n",
" <th>total_amount</th>\n",
" <th>nb_suppliers</th>\n",
" <th>vente_internet_max</th>\n",
" <th>purchase_date_min</th>\n",
" <th>purchase_date_max</th>\n",
" <th>nb_tickets_internet</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>13</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>10</td>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>14</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354360</th>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>7</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354361</th>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>11</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354362</th>\n",
" <td>1.0</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>50</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>91</td>\n",
" <td>91</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354363</th>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>55</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>52</td>\n",
" <td>52</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354364</th>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>550</td>\n",
" <td>550</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>7</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>354365 rows × 15 columns</p>\n",
"</div>"
],
"text/plain": [
" const nb_tickets nb_purchases total_amount nb_suppliers \\\n",
"0 1.0 0 0 0 0 \n",
"1 1.0 0 0 0 0 \n",
"2 1.0 0 0 0 0 \n",
"3 1.0 0 0 0 0 \n",
"4 1.0 0 0 0 0 \n",
"... ... ... ... ... ... \n",
"354360 1.0 0 0 0 0 \n",
"354361 1.0 0 0 0 0 \n",
"354362 1.0 2 2 50 1 \n",
"354363 1.0 1 1 55 1 \n",
"354364 1.0 0 0 0 0 \n",
"\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 0 550 550 \n",
"1 0 550 550 \n",
"2 0 550 550 \n",
"3 0 550 550 \n",
"4 0 550 550 \n",
"... ... ... ... \n",
"354360 0 550 550 \n",
"354361 0 550 550 \n",
"354362 0 91 91 \n",
"354363 0 52 52 \n",
"354364 0 550 550 \n",
"\n",
" nb_tickets_internet is_email_true opt_in gender_female \\\n",
"0 0 1 1 1 \n",
"1 0 1 1 0 \n",
"2 0 1 1 0 \n",
"3 0 1 0 0 \n",
"4 0 1 0 0 \n",
"... ... ... ... ... \n",
"354360 0 1 0 0 \n",
"354361 0 1 1 0 \n",
"354362 0 1 0 1 \n",
"354363 0 1 1 0 \n",
"354364 0 1 0 0 \n",
"\n",
" gender_male nb_campaigns nb_campaigns_opened \n",
"0 0 13 4 \n",
"1 0 10 9 \n",
"2 1 14 0 \n",
"3 0 9 0 \n",
"4 0 4 0 \n",
"... ... ... ... \n",
"354360 0 7 0 \n",
"354361 1 11 2 \n",
"354362 0 6 6 \n",
"354363 1 3 0 \n",
"354364 1 7 0 \n",
"\n",
"[354365 rows x 15 columns]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 0. on retire les variables citées ci-dessus et on ajoute l'intercept\n",
"\n",
"X = sm.add_constant(X.drop([\"fidelity\", \"time_between_purchase\", \"gender_other\"], axis=1))\n",
"X"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "0e968aa1-fbec-47db-b570-4730ef7eebf2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Optimization terminated successfully.\n",
" Current function value: 0.234602\n",
" Iterations 8\n",
" Logit Regression Results \n",
"==============================================================================\n",
"Dep. Variable: y No. Observations: 354365\n",
"Model: Logit Df Residuals: 354350\n",
"Method: MLE Df Model: 14\n",
"Date: Thu, 21 Mar 2024 Pseudo R-squ.: 0.2112\n",
"Time: 07:57:46 Log-Likelihood: -83135.\n",
"converged: True LL-Null: -1.0540e+05\n",
"Covariance Type: nonrobust LLR p-value: 0.000\n",
"=======================================================================================\n",
" coef std err z P>|z| [0.025 0.975]\n",
"---------------------------------------------------------------------------------------\n",
"const -1.9633 0.093 -21.101 0.000 -2.146 -1.781\n",
"nb_tickets -0.0003 0.000 -2.191 0.028 -0.001 -2.85e-05\n",
"nb_purchases -0.0037 0.001 -3.609 0.000 -0.006 -0.002\n",
"total_amount 6.267e-05 1.63e-05 3.841 0.000 3.07e-05 9.46e-05\n",
"nb_suppliers 0.3368 0.019 17.662 0.000 0.299 0.374\n",
"vente_internet_max -1.9874 0.024 -82.965 0.000 -2.034 -1.940\n",
"purchase_date_min 0.0031 7.77e-05 39.936 0.000 0.003 0.003\n",
"purchase_date_max -0.0072 8.08e-05 -89.592 0.000 -0.007 -0.007\n",
"nb_tickets_internet 0.0938 0.004 22.652 0.000 0.086 0.102\n",
"is_email_true 0.8651 0.088 9.797 0.000 0.692 1.038\n",
"opt_in -1.9976 0.019 -107.305 0.000 -2.034 -1.961\n",
"gender_female 0.7032 0.024 29.395 0.000 0.656 0.750\n",
"gender_male 0.8071 0.024 33.201 0.000 0.759 0.855\n",
"nb_campaigns 0.0287 0.001 30.633 0.000 0.027 0.031\n",
"nb_campaigns_opened 0.0486 0.002 28.245 0.000 0.045 0.052\n",
"=======================================================================================\n"
]
}
],
"source": [
"# 1. Premier modèle de régression logistique sans standardisation (permet une interprétation des coeffs)\n",
"\n",
"model_logit = sm.Logit(y, X)\n",
"\n",
"# Ajustement du modèle aux données\n",
"result = model_logit.fit()\n",
"\n",
"# Affichage des résultats - toutes les var sont significatives avec des p-valeurs de 0, et de 0.28 pour nbre tickets\n",
"print(result.summary())"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "2475f2fe-3d1f-4845-9ede-0416dac83271",
"metadata": {},
"outputs": [],
"source": [
"# 2. Modèle logit avec données standardisées\n",
"\n",
"# Colonnes à standardiser\n",
"\n",
"\n",
"var_num = ['nb_tickets', 'nb_purchases', \"total_amount\", \"nb_suppliers\", \"vente_internet_max\",\n",
" \"purchase_date_min\", \"purchase_date_max\", \"nb_tickets_internet\",\n",
" \"nb_campaigns\", \"nb_campaigns_opened\"]\n",
"\n",
"# Standardisation des colonnes sélectionnées\n",
"scaler = StandardScaler()\n",
"X[var_num] = scaler.fit_transform(X[var_num])"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "696fcc04-e5df-45dc-a1b9-57c30d4d671d",
"metadata": {},
"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>const</th>\n",
" <th>nb_tickets</th>\n",
" <th>nb_purchases</th>\n",
" <th>total_amount</th>\n",
" <th>nb_suppliers</th>\n",
" <th>vente_internet_max</th>\n",
" <th>purchase_date_min</th>\n",
" <th>purchase_date_max</th>\n",
" <th>nb_tickets_internet</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>-0.024425</td>\n",
" <td>-0.050722</td>\n",
" <td>-0.048383</td>\n",
" <td>-0.768294</td>\n",
" <td>-0.599511</td>\n",
" <td>0.755994</td>\n",
" <td>0.783940</td>\n",
" <td>-0.264693</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.607945</td>\n",
" <td>0.522567</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.0</td>\n",
" <td>-0.024425</td>\n",
" <td>-0.050722</td>\n",
" <td>-0.048383</td>\n",
" <td>-0.768294</td>\n",
" <td>-0.599511</td>\n",
" <td>0.755994</td>\n",
" <td>0.783940</td>\n",
" <td>-0.264693</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.306155</td>\n",
" <td>1.701843</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.0</td>\n",
" <td>-0.024425</td>\n",
" <td>-0.050722</td>\n",
" <td>-0.048383</td>\n",
" <td>-0.768294</td>\n",
" <td>-0.599511</td>\n",
" <td>0.755994</td>\n",
" <td>0.783940</td>\n",
" <td>-0.264693</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.708542</td>\n",
" <td>-0.420854</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1.0</td>\n",
" <td>-0.024425</td>\n",
" <td>-0.050722</td>\n",
" <td>-0.048383</td>\n",
" <td>-0.768294</td>\n",
" <td>-0.599511</td>\n",
" <td>0.755994</td>\n",
" <td>0.783940</td>\n",
" <td>-0.264693</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.205558</td>\n",
" <td>-0.420854</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1.0</td>\n",
" <td>-0.024425</td>\n",
" <td>-0.050722</td>\n",
" <td>-0.048383</td>\n",
" <td>-0.768294</td>\n",
" <td>-0.599511</td>\n",
" <td>0.755994</td>\n",
" <td>0.783940</td>\n",
" <td>-0.264693</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>-0.297426</td>\n",
" <td>-0.420854</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354360</th>\n",
" <td>1.0</td>\n",
" <td>-0.024425</td>\n",
" <td>-0.050722</td>\n",
" <td>-0.048383</td>\n",
" <td>-0.768294</td>\n",
" <td>-0.599511</td>\n",
" <td>0.755994</td>\n",
" <td>0.783940</td>\n",
" <td>-0.264693</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.004365</td>\n",
" <td>-0.420854</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354361</th>\n",
" <td>1.0</td>\n",
" <td>-0.024425</td>\n",
" <td>-0.050722</td>\n",
" <td>-0.048383</td>\n",
" <td>-0.768294</td>\n",
" <td>-0.599511</td>\n",
" <td>0.755994</td>\n",
" <td>0.783940</td>\n",
" <td>-0.264693</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.406752</td>\n",
" <td>0.050856</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354362</th>\n",
" <td>1.0</td>\n",
" <td>-0.000838</td>\n",
" <td>0.092966</td>\n",
" <td>-0.009150</td>\n",
" <td>1.219633</td>\n",
" <td>-0.599511</td>\n",
" <td>-1.665887</td>\n",
" <td>-1.557073</td>\n",
" <td>-0.264693</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>-0.096232</td>\n",
" <td>0.994277</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354363</th>\n",
" <td>1.0</td>\n",
" <td>-0.012631</td>\n",
" <td>0.021122</td>\n",
" <td>-0.005227</td>\n",
" <td>1.219633</td>\n",
" <td>-0.599511</td>\n",
" <td>-1.871668</td>\n",
" <td>-1.755983</td>\n",
" <td>-0.264693</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>-0.398023</td>\n",
" <td>-0.420854</td>\n",
" </tr>\n",
" <tr>\n",
" <th>354364</th>\n",
" <td>1.0</td>\n",
" <td>-0.024425</td>\n",
" <td>-0.050722</td>\n",
" <td>-0.048383</td>\n",
" <td>-0.768294</td>\n",
" <td>-0.599511</td>\n",
" <td>0.755994</td>\n",
" <td>0.783940</td>\n",
" <td>-0.264693</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.004365</td>\n",
" <td>-0.420854</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>354365 rows × 15 columns</p>\n",
"</div>"
],
"text/plain": [
" const nb_tickets nb_purchases total_amount nb_suppliers \\\n",
"0 1.0 -0.024425 -0.050722 -0.048383 -0.768294 \n",
"1 1.0 -0.024425 -0.050722 -0.048383 -0.768294 \n",
"2 1.0 -0.024425 -0.050722 -0.048383 -0.768294 \n",
"3 1.0 -0.024425 -0.050722 -0.048383 -0.768294 \n",
"4 1.0 -0.024425 -0.050722 -0.048383 -0.768294 \n",
"... ... ... ... ... ... \n",
"354360 1.0 -0.024425 -0.050722 -0.048383 -0.768294 \n",
"354361 1.0 -0.024425 -0.050722 -0.048383 -0.768294 \n",
"354362 1.0 -0.000838 0.092966 -0.009150 1.219633 \n",
"354363 1.0 -0.012631 0.021122 -0.005227 1.219633 \n",
"354364 1.0 -0.024425 -0.050722 -0.048383 -0.768294 \n",
"\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 -0.599511 0.755994 0.783940 \n",
"1 -0.599511 0.755994 0.783940 \n",
"2 -0.599511 0.755994 0.783940 \n",
"3 -0.599511 0.755994 0.783940 \n",
"4 -0.599511 0.755994 0.783940 \n",
"... ... ... ... \n",
"354360 -0.599511 0.755994 0.783940 \n",
"354361 -0.599511 0.755994 0.783940 \n",
"354362 -0.599511 -1.665887 -1.557073 \n",
"354363 -0.599511 -1.871668 -1.755983 \n",
"354364 -0.599511 0.755994 0.783940 \n",
"\n",
" nb_tickets_internet is_email_true opt_in gender_female \\\n",
"0 -0.264693 1 1 1 \n",
"1 -0.264693 1 1 0 \n",
"2 -0.264693 1 1 0 \n",
"3 -0.264693 1 0 0 \n",
"4 -0.264693 1 0 0 \n",
"... ... ... ... ... \n",
"354360 -0.264693 1 0 0 \n",
"354361 -0.264693 1 1 0 \n",
"354362 -0.264693 1 0 1 \n",
"354363 -0.264693 1 1 0 \n",
"354364 -0.264693 1 0 0 \n",
"\n",
" gender_male nb_campaigns nb_campaigns_opened \n",
"0 0 0.607945 0.522567 \n",
"1 0 0.306155 1.701843 \n",
"2 1 0.708542 -0.420854 \n",
"3 0 0.205558 -0.420854 \n",
"4 0 -0.297426 -0.420854 \n",
"... ... ... ... \n",
"354360 0 0.004365 -0.420854 \n",
"354361 1 0.406752 0.050856 \n",
"354362 0 -0.096232 0.994277 \n",
"354363 1 -0.398023 -0.420854 \n",
"354364 1 0.004365 -0.420854 \n",
"\n",
"[354365 rows x 15 columns]"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "54421677-640f-4f37-9a0d-d9a2cc3572b0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Optimization terminated successfully.\n",
" Current function value: 0.234602\n",
" Iterations 8\n",
" Logit Regression Results \n",
"==============================================================================\n",
"Dep. Variable: y No. Observations: 354365\n",
"Model: Logit Df Residuals: 354350\n",
"Method: MLE Df Model: 14\n",
"Date: Thu, 21 Mar 2024 Pseudo R-squ.: 0.2112\n",
"Time: 07:58:13 Log-Likelihood: -83135.\n",
"converged: True LL-Null: -1.0540e+05\n",
"Covariance Type: nonrobust LLR p-value: 0.000\n",
"=======================================================================================\n",
" coef std err z P>|z| [0.025 0.975]\n",
"---------------------------------------------------------------------------------------\n",
"const -3.6025 0.091 -39.755 0.000 -3.780 -3.425\n",
"nb_tickets -0.0230 0.010 -2.191 0.028 -0.044 -0.002\n",
"nb_purchases -0.0519 0.014 -3.609 0.000 -0.080 -0.024\n",
"total_amount 0.0799 0.021 3.841 0.000 0.039 0.121\n",
"nb_suppliers 0.1694 0.010 17.662 0.000 0.151 0.188\n",
"vente_internet_max -0.8764 0.011 -82.965 0.000 -0.897 -0.856\n",
"purchase_date_min 0.5881 0.015 39.936 0.000 0.559 0.617\n",
"purchase_date_max -1.4197 0.016 -89.592 0.000 -1.451 -1.389\n",
"nb_tickets_internet 0.2895 0.013 22.652 0.000 0.264 0.315\n",
"is_email_true 0.8651 0.088 9.797 0.000 0.692 1.038\n",
"opt_in -1.9976 0.019 -107.305 0.000 -2.034 -1.961\n",
"gender_female 0.7032 0.024 29.395 0.000 0.656 0.750\n",
"gender_male 0.8071 0.024 33.201 0.000 0.759 0.855\n",
"nb_campaigns 0.2850 0.009 30.633 0.000 0.267 0.303\n",
"nb_campaigns_opened 0.2061 0.007 28.245 0.000 0.192 0.220\n",
"=======================================================================================\n"
]
}
],
"source": [
"# 2. modele avec var standardisées (permet de mieux jauger l'importance réelle de chaque variable)\n",
"\n",
"model_logit = sm.Logit(y, X)\n",
"# model_logit = sm.Logit(y, X)\n",
"\n",
"# Ajustement du modèle aux données\n",
"result = model_logit.fit()\n",
"\n",
"# Affichage des résultats\n",
"print(result.summary())"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "13cc3362-7bb2-46fa-8bd8-e5a8e53260b8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Optimization terminated successfully (Exit mode 0)\n",
" Current function value: 0.23562928627877766\n",
" Iterations: 240\n",
" Function evaluations: 243\n",
" Gradient evaluations: 240\n",
"const 0.000000e+00\n",
"nb_tickets 2.477006e-01\n",
"nb_purchases 1.636902e-03\n",
"total_amount 8.839088e-04\n",
"nb_suppliers 1.906550e-65\n",
"vente_internet_max 0.000000e+00\n",
"purchase_date_min 0.000000e+00\n",
"purchase_date_max 0.000000e+00\n",
"nb_tickets_internet 7.232680e-112\n",
"is_email_true 8.202187e-08\n",
"opt_in 0.000000e+00\n",
"gender_female 1.624424e-170\n",
"gender_male 4.961315e-220\n",
"nb_campaigns 6.276733e-205\n",
"nb_campaigns_opened 2.228531e-176\n",
"dtype: float64\n",
" Logit Regression Results \n",
"==============================================================================\n",
"Dep. Variable: y No. Observations: 354365\n",
"Model: Logit Df Residuals: 354350\n",
"Method: MLE Df Model: 14\n",
"Date: Thu, 21 Mar 2024 Pseudo R-squ.: 0.2111\n",
"Time: 10:45:37 Log-Likelihood: -83152.\n",
"converged: True LL-Null: -1.0540e+05\n",
"Covariance Type: nonrobust LLR p-value: 0.000\n",
"=======================================================================================\n",
" coef std err z P>|z| [0.025 0.975]\n",
"---------------------------------------------------------------------------------------\n",
"const -3.1162 0.081 -38.383 0.000 -3.275 -2.957\n",
"nb_tickets -0.0136 0.012 -1.156 0.248 -0.037 0.009\n",
"nb_purchases -0.0385 0.012 -3.149 0.002 -0.063 -0.015\n",
"total_amount 0.0588 0.018 3.325 0.001 0.024 0.094\n",
"nb_suppliers 0.1638 0.010 17.085 0.000 0.145 0.183\n",
"vente_internet_max -0.8651 0.011 -82.182 0.000 -0.886 -0.844\n",
"purchase_date_min 0.5790 0.015 39.391 0.000 0.550 0.608\n",
"purchase_date_max -1.4088 0.016 -89.101 0.000 -1.440 -1.378\n",
"nb_tickets_internet 0.2857 0.013 22.475 0.000 0.261 0.311\n",
"is_email_true 0.4224 0.079 5.363 0.000 0.268 0.577\n",
"opt_in -1.9818 0.019 -106.856 0.000 -2.018 -1.945\n",
"gender_female 0.6553 0.024 27.835 0.000 0.609 0.701\n",
"gender_male 0.7578 0.024 31.663 0.000 0.711 0.805\n",
"nb_campaigns 0.2835 0.009 30.547 0.000 0.265 0.302\n",
"nb_campaigns_opened 0.2061 0.007 28.315 0.000 0.192 0.220\n",
"=======================================================================================\n"
]
}
],
"source": [
"# 2.bis on fait de même pour un modèle logit avec pénalité \n",
"# pas besoin de redefinir le modèle, il faut faire un fit_regularized\n",
"\n",
"# sans spécification, le alpha optimal est déterminé par cross validation\n",
"# remplacer alpha=32 par la valeur optimale trouvée par cross validation dans la pipeline avec .best_params\n",
"# attention, dans scikit learn, l'hyperparamètre est C = 1/alpha, pas oublier de prendre l'inverse de ce C optimal\n",
"\n",
"result = model_logit.fit_regularized(method='l1', alpha = 32)\n",
"\n",
"print(result.pvalues)\n",
"print(result.summary())"
]
},
{
"cell_type": "markdown",
"id": "8c3dec50-7b9d-40f6-83b6-6cae26962cf8",
"metadata": {},
"source": [
"### Other method : take into account the weigths ! Pb : with this method, no penalty allowed"
]
},
{
"cell_type": "code",
"execution_count": 247,
"id": "2e3ca381-54e3-445b-bb37-d7ce953cb856",
"metadata": {},
"outputs": [],
"source": [
"# define a function to generate summaries of logit model\n",
"\n",
"def model_logit(X, y, weight_dict, add_constant=False) :\n",
" # Generate sample weights based on class weights computed earlier\n",
" sample_weights = np.array([weight_dict[class_] for class_ in y])\n",
"\n",
" if add_constant :\n",
" X_const = sm.add_constant(X)\n",
" else :\n",
" X_const = X\n",
" \n",
" # Use GLM from statsmodels with Binomial family for logistic regression\n",
" model = sm.GLM(y, X_const, family=sm.families.Binomial(), freq_weights=sample_weights)\n",
" \n",
" # fit without penalty\n",
" result = model.fit()\n",
"\n",
" result_summary = result.summary()\n",
" \n",
" return result_summary"
]
},
{
"cell_type": "code",
"execution_count": 248,
"id": "4cd424a0-7c55-47ff-840e-1354e8dcf863",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Generalized Linear Model Regression Results \n",
"==============================================================================\n",
"Dep. Variable: y No. Observations: 354365\n",
"Model: GLM Df Residuals: 354350\n",
"Model Family: Binomial Df Model: 14\n",
"Link Function: Logit Scale: 1.0000\n",
"Method: IRLS Log-Likelihood: -1.8693e+05\n",
"Date: Thu, 21 Mar 2024 Deviance: 3.7387e+05\n",
"Time: 13:19:33 Pearson chi2: 1.97e+16\n",
"No. Iterations: 100 Pseudo R-squ. (CS): 0.2820\n",
"Covariance Type: nonrobust \n",
"=======================================================================================\n",
" coef std err z P>|z| [0.025 0.975]\n",
"---------------------------------------------------------------------------------------\n",
"const -1.3943 0.062 -22.456 0.000 -1.516 -1.273\n",
"nb_tickets -0.3312 0.016 -20.967 0.000 -0.362 -0.300\n",
"nb_purchases 0.9258 0.098 9.491 0.000 0.735 1.117\n",
"total_amount 0.8922 0.042 21.393 0.000 0.810 0.974\n",
"nb_suppliers 0.2238 0.007 32.137 0.000 0.210 0.237\n",
"vente_internet_max -0.7453 0.007 -100.473 0.000 -0.760 -0.731\n",
"purchase_date_min 0.7123 0.015 46.063 0.000 0.682 0.743\n",
"purchase_date_max -1.3328 0.017 -79.297 0.000 -1.366 -1.300\n",
"nb_tickets_internet 0.1784 0.011 16.366 0.000 0.157 0.200\n",
"is_email_true 0.8635 0.061 14.086 0.000 0.743 0.984\n",
"opt_in -1.7487 0.010 -174.737 0.000 -1.768 -1.729\n",
"gender_female 0.8084 0.013 60.803 0.000 0.782 0.835\n",
"gender_male 0.8731 0.014 64.332 0.000 0.846 0.900\n",
"nb_campaigns 0.1751 0.006 31.101 0.000 0.164 0.186\n",
"nb_campaigns_opened 0.2962 0.005 54.145 0.000 0.285 0.307\n",
"=======================================================================================\n"
]
}
],
"source": [
"# with the function\n",
"\n",
"# 1. logit with weights\n",
"results_logit_weight = model_logit(X,y,weight_dict=weight_dict)\n",
"print(results_logit_weight)"
]
},
{
"cell_type": "code",
"execution_count": 252,
"id": "84dd6242-a9c3-4dee-a58b-abc5f1c6f8fa",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Generalized Linear Model Regression Results \n",
"==============================================================================\n",
"Dep. Variable: y No. Observations: 354365\n",
"Model: GLM Df Residuals: 354350\n",
"Model Family: Binomial Df Model: 14\n",
"Link Function: Logit Scale: 1.0000\n",
"Method: IRLS Log-Likelihood: -83141.\n",
"Date: Thu, 21 Mar 2024 Deviance: 1.6628e+05\n",
"Time: 13:20:06 Pearson chi2: 4.52e+15\n",
"No. Iterations: 8 Pseudo R-squ. (CS): 0.1180\n",
"Covariance Type: nonrobust \n",
"=======================================================================================\n",
" coef std err z P>|z| [0.025 0.975]\n",
"---------------------------------------------------------------------------------------\n",
"const -3.6025 0.091 -39.755 0.000 -3.780 -3.425\n",
"nb_tickets -0.0230 0.010 -2.191 0.028 -0.044 -0.002\n",
"nb_purchases -0.0519 0.014 -3.609 0.000 -0.080 -0.024\n",
"total_amount 0.0799 0.021 3.841 0.000 0.039 0.121\n",
"nb_suppliers 0.1694 0.010 17.662 0.000 0.151 0.188\n",
"vente_internet_max -0.8764 0.011 -82.965 0.000 -0.897 -0.856\n",
"purchase_date_min 0.5881 0.015 39.936 0.000 0.559 0.617\n",
"purchase_date_max -1.4197 0.016 -89.592 0.000 -1.451 -1.389\n",
"nb_tickets_internet 0.2895 0.013 22.652 0.000 0.264 0.315\n",
"is_email_true 0.8651 0.088 9.797 0.000 0.692 1.038\n",
"opt_in -1.9976 0.019 -107.305 0.000 -2.034 -1.961\n",
"gender_female 0.7032 0.024 29.395 0.000 0.656 0.750\n",
"gender_male 0.8071 0.024 33.201 0.000 0.759 0.855\n",
"nb_campaigns 0.2850 0.009 30.633 0.000 0.267 0.303\n",
"nb_campaigns_opened 0.2061 0.007 28.245 0.000 0.192 0.220\n",
"=======================================================================================\n"
]
}
],
"source": [
"# 2. logit without weights\n",
"\n",
"results_logit = model_logit(X.drop(\"const\", axis=1),y,weight_dict={0:1, 1:1}, add_constant=True)\n",
"print(results_logit)"
]
},
{
"cell_type": "markdown",
"id": "36c5e770-72b3-4482-ad61-45b511a11f06",
"metadata": {},
"source": [
"## graphique LASSO - quelles variables sont importantes dans le modèle ? "
]
},
{
"cell_type": "code",
"execution_count": 313,
"id": "af208fdf-b4c2-4acd-b29e-c5b67bec3a4d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"results for solver lbfgs\n",
"intercept : -3.617357317895187\n",
"coefficients : [[-0.03114285 -0.06607353 0.10099873 0.16977395 -0.87625108 0.58870838\n",
" -1.42022841 0.28837776 0.87461022 -2.00037064 0.70874574 0.8136523\n",
" 0.2850802 0.20640785]]\n",
"\n",
"\n",
"results for solver newton-cg\n",
"intercept : -3.5774790840156467\n",
"coefficients : [[-0.0224498 -0.05092757 0.07842438 0.16941048 -0.87645255 0.58801191\n",
" -1.41953483 0.28961165 0.84037075 -1.99757163 0.70302619 0.8068438\n",
" 0.2849652 0.20613618]]\n",
"\n",
"\n",
"results for solver newton-cholesky\n",
"intercept : -3.602198310216717\n",
"coefficients : [[-0.02297134 -0.05187501 0.07986323 0.1693883 -0.87639043 0.58815512\n",
" -1.41963236 0.28949836 0.86505556 -1.99695897 0.70307973 0.80688729\n",
" 0.2849131 0.20610117]]\n",
"\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/mamba/lib/python3.11/site-packages/sklearn/linear_model/_sag.py:350: ConvergenceWarning: The max_iter was reached which means the coef_ did not converge\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"results for solver sag\n",
"intercept : -1.251116606796448\n",
"coefficients : [[-0.02952178 -0.05691972 0.08940743 0.18616406 -0.85908081 0.46577384\n",
" -1.26014292 0.32512459 -1.00339802 -1.84528471 0.15832219 0.24753693\n",
" 0.26318328 0.21288782]]\n",
"\n",
"\n",
"results for solver saga\n",
"intercept : -1.112341737293756\n",
"coefficients : [[-0.03349226 -0.02298918 0.09611619 0.23784438 -0.80928967 0.28520739\n",
" -1.01029862 0.30172469 -0.99503611 -1.53140972 -0.04449765 0.02363137\n",
" 0.20352875 0.22580284]]\n",
"\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/mamba/lib/python3.11/site-packages/sklearn/linear_model/_sag.py:350: ConvergenceWarning: The max_iter was reached which means the coef_ did not converge\n",
" warnings.warn(\n"
]
}
],
"source": [
"# difference entre les solveurs (les resultats de statsmodel s'approchent de newtown cholesky)\n",
"\n",
"for solver in [\"lbfgs\", \"newton-cg\", \"newton-cholesky\", \"sag\", \"saga\"] :\n",
" modele_logit = LogisticRegression(penalty=None, solver=solver)\n",
" modele_logit.fit(X.drop(\"const\", axis=1), y)\n",
" print(f\"results for solver {solver}\")\n",
" print(f\"intercept : {modele_logit.intercept_[0]}\")\n",
" print(f\"coefficients : {modele_logit.coef_}\")\n",
" print(\"\\n\")"
]
},
{
"cell_type": "markdown",
"id": "e65ab8d9-54e5-4092-ad75-ac1909cb1f60",
"metadata": {},
"source": [
"on passe au graphique\n"
]
},
{
"cell_type": "code",
"execution_count": 449,
"id": "f0006351-9b43-449e-81a7-b4510dd55366",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.]])"
]
},
"execution_count": 449,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# il faut environ alpha = 25k pour annuler tous les coeffs\n",
"# on utilise pas de balance pour les classes pour le moment car les résultats de statsmodels n equilibrent \n",
"# pas les classes - on utilisera cette option pr la validation croisee\n",
"\n",
"modele_logit = LogisticRegression(penalty=\"l1\", C=1/25000, # class_weight=\"balanced\", \n",
" solver=\"liblinear\" )\n",
"modele_logit.fit(X.drop(\"const\", axis=1),y)\n",
"modele_logit.coef_"
]
},
{
"cell_type": "code",
"execution_count": 370,
"id": "24083a2f-e520-4229-a510-09e352b25cbd",
"metadata": {},
"outputs": [],
"source": [
"params = np.logspace(-5, 5, 11, 10)"
]
},
{
"cell_type": "code",
"execution_count": 371,
"id": "9c1c8efe-27e9-4307-82bd-ea356f219ebf",
"metadata": {},
"outputs": [],
"source": [
"results=[]\n",
"for param in params :\n",
" modele_logit = LogisticRegression(penalty=\"l1\", C=param, # class_weight=\"balanced\", \n",
" solver=\"liblinear\" )\n",
" modele_logit.fit(X.drop(\"const\", axis=1),y)\n",
" results.append(modele_logit.coef_)"
]
},
{
"cell_type": "code",
"execution_count": 383,
"id": "ceaec969-e72e-4520-afaf-7bcf5dad8365",
"metadata": {},
"outputs": [],
"source": [
"results.reverse()"
]
},
{
"cell_type": "code",
"execution_count": 384,
"id": "5b7c8d26-d1f8-441f-ab1d-89845e3e1ea3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[array([[-0.02299412, -0.05192013, 0.0799274 , 0.16931227, -0.87633381,\n",
" 0.58813399, -1.41967385, 0.28951886, 0.85509191, -1.99754475,\n",
" 0.70287087, 0.80669243, 0.28498239, 0.2061286 ]]),\n",
" array([[-0.02299201, -0.05191491, 0.07992075, 0.16931139, -0.87634243,\n",
" 0.58813708, -1.41968623, 0.28952223, 0.85577021, -1.99756453,\n",
" 0.70288563, 0.80669012, 0.28498258, 0.20612949]]),\n",
" array([[-0.02299764, -0.05192605, 0.07993569, 0.16930528, -0.87632586,\n",
" 0.58811345, -1.41964512, 0.28952983, 0.85374762, -1.99754811,\n",
" 0.70282334, 0.80664228, 0.28498228, 0.20613025]]),\n",
" array([[-0.02298949, -0.05191449, 0.07991828, 0.16931317, -0.87634417,\n",
" 0.58812319, -1.4196808 , 0.2895181 , 0.85546622, -1.99754003,\n",
" 0.70302758, 0.80684757, 0.28498265, 0.20613162]]),\n",
" array([[-0.02296458, -0.05187503, 0.07985942, 0.16928133, -0.87628414,\n",
" 0.5880753 , -1.41959837, 0.28951824, 0.85207105, -1.99743532,\n",
" 0.70275613, 0.80657079, 0.28497271, 0.20612744]]),\n",
" array([[-0.02266765, -0.05140588, 0.07913905, 0.16914597, -0.8759943 ,\n",
" 0.58782322, -1.41931263, 0.28941107, 0.84058764, -1.99706383,\n",
" 0.70135753, 0.805146 , 0.2849354 , 0.20613043]]),\n",
" array([[-0.01986108, -0.04710671, 0.07249967, 0.16755623, -0.8727931 ,\n",
" 0.58521605, -1.41621509, 0.28835319, 0.7063547 , -1.99262169,\n",
" 0.68764121, 0.79104559, 0.28452484, 0.20613349]]),\n",
" array([[ 0. , -0.02274081, 0.03249772, 0.15656967, -0.84560728,\n",
" 0.5601391 , -1.38630664, 0.27683263, 0. , -1.95240872,\n",
" 0.55820164, 0.65806397, 0.27970382, 0.20620792]]),\n",
" array([[ 0.00000000e+00, 0.00000000e+00, 1.55329481e-03,\n",
" 1.30027639e-01, -6.87367967e-01, 3.13022684e-01,\n",
" -1.08971896e+00, 1.74908692e-01, 0.00000000e+00,\n",
" -1.67160475e+00, 0.00000000e+00, 0.00000000e+00,\n",
" 2.21231437e-01, 2.08973175e-01]]),\n",
" array([[ 0. , 0. , 0. , 0. , 0. ,\n",
" 0. , -0.2624159 , 0. , -0.01813001, -0.22665172,\n",
" 0. , 0. , 0. , 0.01487092]]),\n",
" array([[0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.]])]"
]
},
"execution_count": 384,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"results"
]
},
{
"cell_type": "code",
"execution_count": 392,
"id": "9f6e6532-c593-4f3a-a718-5f4593749eb4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([1.e-05, 1.e-04, 1.e-03, 1.e-02, 1.e-01, 1.e+00, 1.e+01, 1.e+02,\n",
" 1.e+03, 1.e+04, 1.e+05])"
]
},
"execution_count": 392,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# le paramètre C est l'inverse de alpha. On préfère donc afficher les valeurs de alpha qui sont plus parlantes\n",
"# un alpha grand correspond à une plus grande pénalité \n",
"# et on utilise flip pour inverser le vecteur, et classer les alphas par ordre croissant\n",
"# par souci de coherence et de lisibilité, on inverse donc aussi l'ordre des resultats\n",
"\n",
"alphas_sorted = np.flip(1/params)\n",
"alphas_sorted"
]
},
{
"cell_type": "code",
"execution_count": 447,
"id": "1de056b5-e37c-4272-9acb-a197bdb5ea3b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers',\n",
" 'vente_internet_max', 'purchase_date_min', 'purchase_date_max',\n",
" 'nb_tickets_internet', 'is_email_true', 'opt_in', 'gender_female',\n",
" 'gender_male', 'nb_campaigns', 'nb_campaigns_opened'],\n",
" dtype='object')"
]
},
"execution_count": 447,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_colnames = X.drop(\"const\", axis=1).columns\n",
"X_colnames"
]
},
{
"cell_type": "code",
"execution_count": 448,
"id": "4436abe2-ac0f-480d-aa12-491c059f906a",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABFkAAAMCCAYAAACycxmEAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAABDrAAAQ6wFQlOh8AAEAAElEQVR4nOzdd3xT5f4H8M/JbtJJKbOlQBktgixZZQ9liQxRUVSGetWroKC4B4LizwVuVERBFPWiAipbQPaQvWXvXVq60rTJeX5/pEkz27RNm5Z83vfysn3OyTnf7OTTZ0hCCAEiIiIiIiIiIioVRaALICIiIiIiIiK6ETBkISIiIiIiIiLyA4YsRERERERERER+wJCFiIiIiIiIiMgPGLIQEREREREREfkBQxYiIiIiIiIiIj9gyEJERERERERE5AcMWYiIiIiIiIiI/IAhCxERERERERGRHzBkISIiIiKioGaxWDBt2jR88cUXgS7lhjRjxgy89957yMvLC3QppXbkyBFMnDgRGzduDHQpVEExZKEbzsiRIyFJUpkdv1u3bqhbt26ZHb+0Zs2aBUmS8Pfff/v1uH///TckScKsWbP8etyyVLduXXTr1i3QZZRYZa/fH1avXo327dsjLCzM6fF39epVPPjgg6hVqxYkSbLfTrzNCpTVa2F5vxZUxtce8uzzzz9HYmIitFotJEnCyZMnA11SkcrqPdWfJEnCyJEjA11GpadUKtGuXTtMmDAB77//fqDLKZGy/gxcUp999hnGjh2LVq1aQa1Wl9t5PX0mKO3n+NTUVNx+++3Ytm0bbrnlltIV6EVpn9OV4XXrRseQhfzG9kG4sH+V4QMVAEycOBELFiwIdBlEQS01NRVDhgxBVlYWPvjgA8yZMwddunQBADzzzDP4+eef8dhjj2HOnDl4+eWXA1xt4T788EOGBH6UlpaGiRMnFvsDpCRJ6NWrV7Eus2PHDvt72Lp167zuZzKZ8Pnnn6Ndu3aoVq0adDod4uLi0KNHD7z22mswmUxO+588eRKPP/44kpKSYDAYEBkZiUaNGmHYsGH47bffPJ5j69atGD58OOrUqQOtVosqVaqgS5cu+OKLLyr8X4dXr16NJ554AomJifjiiy8wZ84cxMTEBLosAMCCBQswceLEQJdBFUBycjIWLVqESZMmFfo5kK/pvluxYgWef/55zJ8/Hz179gx0OR75+hpgNptx1113oW7duvj111+h0WjKvjiqlFSBLoBuPEOHDsXAgQM9bqsoH6iK8sYbb2DEiBEYNGiQ27bly5dDCFH+RREFmX/++QdpaWmYOXMmhgwZ4rRtxYoV6N27N1577TWn9n///bdC/hXvww8/RN26dfnX5hLo0qULjEaj018/09LS8MYbbwBAmfdcmjFjBiIiIqBWqzFjxgx07tzZbR+LxYJevXph/fr16NixIyZMmICoqCicPn0aW7duxZQpUzB27FhotVoA1uCmS5cusFgsGD58OJ588kkAwNGjR7Fo0SJkZma6PeYnT56M1157DTVq1MCDDz6IRo0aIS0tDX/88Qcef/xxzJ49G3/88QeqVq1aprdHSa1YsQIA8M0336BKlSoBrsbZggULMHv2bI9fsh544AEMGzaMX6aCSJcuXbBkyRJs3LgRFosFSqXSbR++pvtGCIEDBw5g4cKFFSZg8fQ5vrDXAEd79+5Fz5498fTTT9tfz4k8YchCfte8eXPcf//9gS6jzPCDFhVHVlYWDAZDoMuolC5evAgAHr+QXbx40WM7P/TceBQKBXQ6XUDOnZ2djblz5+Lee++FTqfDV199hU8++QQRERFO+y1cuBDr16/HoEGDMH/+fLfjXLp0yekyEydORFZWFhYsWOD2R4lp06bh7NmzTm1z5szBa6+9ho4dO2LRokVOx3rmmWfw0Ucf4emnn8awYcPw119/+eOq+11hz+eKTKlUevySTf5Xkd4vO3bsiI4dO/rteCaTCUqlEipVcH31kiQJTz31VKDLcFKaz/EtW7ZEy5Yt/VgN3ag4XIgColOnToiIiIDRaHTbduLECSgUCowaNcqp/YcffkC7du0QGhoKg8GA9u3b46effvLpfIWNv3Qc92gb8gQAs2fPdhrqVNSxtmzZgttvvx1VqlSBTqdDUlISJk+ejNzcXKf9Jk6cCEmScPjwYbz22muIj4+HVqtFUlIS5s6d69P1AYC8vDy8/vrrqFu3rv1806dP97p/RkYGXn75ZTRu3NjezXzQoEHYs2ePz+d0JcsypkyZgm7duqFmzZrQaDSoXbs2Ro0a5fYlwZP09HQYDAbceuutHrfbxpTOnj3bL+ez2blzJ4YOHYpq1apBo9Ggfv36eOGFF5Cdne20n6+PG8Da9V+SJEycOBG//vor2rZtC71ej/79+xdZz/bt29GrVy8YDAZERUXhzjvvLHRo3erVq9G3b19ERUXZHzvvvPMOLBaL034HDx7Evffei7i4OGi1WlSrVg0dO3bEt99+W2RNgPUxNm3aNLRu3RoGgwFhYWG4+eab8frrrzvtl5OTgzfeeAOJiYnQ6XSoUqUKBgwYgG3btpW4fkmSMGLECABA9+7d7c9D23hzIYTTc9TWbdvbnCx79uzBvffei1q1atkfNwMHDsT27dud9jt27BhGjhxp3y82Nhb//e9/cfXqVaf9fH0e2x4Xp06dwpo1azwOnyzt/XTp0iWMGDEC0dHRMBgM6NixI1avXu1xX2+3j+Pjt6SK8zgQQmDatGlo2LAhtFotEhIS8Pbbb2PlypVu86+4zskya9Ys1KtXD4C116Ht9iyLubL+97//IT09HaNGjcLo0aNhNBrxww8/uO13+PBhAPD6l9rq1as79cQpav/Y2Fj7z3l5eXjxxRcREhKC//3vf24BDwA89dRTGDRoEFauXInFixf7dN0uXbqEMWPGoG7dutBoNKhevTruv/9+t9ce2+vw6tWr8eGHH6JRo0bQarWoX78+pk2bVuR5bPef7fFsu78cH4eHDh3CsGHDUL16dfuxn332WaSnp5e6lqKe+3Xr1rW/xzg+Px0fb57mNkhLS8P48eNRr149aLVaVK9eHffeey+OHDnitJ/jc2vJkiVo3749QkJCUK1aNTz22GNu7zuFWbFihf3yMTExGD16tNtrk+Nt7mk4i+21y5fh27b3wFOnTuHOO+9EVFSU/T17165dbvtPnz4dvXv3RmxsLDQaDapVq4ahQ4fiwIEDbvvaXov27NmD/v37IyoqCqGhoQCK/15ve29Yu3YtOnXqBIPBgOrVq+P555+HxWKByWTCCy+8gLi4OOh0OrRp0wZbtmxxO44QAjNmzEDbtm1hMBhgMBiQnJzsNHzPl9d0x9tt2LBhqFq1KnQ6nb12f3weK87rPuD7e5s3tvfelJQUjB49GjExMQgJCUFycjJWrVrl8TK+flax3V4XL17EAw88gOjoaISEhKBr165u79H++Bzo+tmuqNcAoPT3WUZGBl599VW0b98eMTEx0Gg0qFu3LsaOHYu0tDSfjmF7nK9evRodO3aEwWBA1apVMWrUKFy5csXjZYQQPr1WLl++HPfeey8SEhIQEhKC8PBwdO3aFYsWLfKpNnIXXHEqlYvs7GyPL9pKpRJRUVEArC/WjzzyCObPn4/77rvPab/Zs2dDCOH0Bfa1117D5MmTcfPNN+PVV18FAHz//fe49957cfz4cbz00kt+qT0pKQlz5szBAw88gM6dO+M///mPT5dbunQp7rjjDkREROCJJ55A9erVsXjxYrz22mvYuHEjFi1aBIXCOdMcMWIEJEnC2LFjoVAo8Pnnn2P48OGoX78+2rdvX+Q5H3zwQfz000/o0aMHxo8fj5SUFLz++uuoU6eO277p6eno1KkTjh49ihEjRqB58+ZITU3FjBkz0KFDB6xbtw6tWrXy7UZykJubi3feeQdDhgxB//79ERERgT179uCbb77BypUrsXv3bvt97kl4eDgGDx6MH3/8EWfPnnX6YgFYP9yGhoZi6NChfjkfYL2vBg0ahLi4OIwZMwbVq1fH7t27MXXqVGzYsAGrV68u1V+aFi5ciA8//BCPPfYYHnnkkSKHltmGDSiVSowdOxaxsbFYvnw5unXrhqysLLf9v/nmGzz88MNo2bIlXnjhBURGRmLDhg148cUXsXPnTnvwmJKSgu7du0OWZTz66KOoV68eUlNTsXfvXqxZs8YtxHSVl5eHvn37YuXKlejatStee+01hIWF4dChQ5g3b559qIbFYkG/fv2wevVq3H777XjyySdx8eJFTJ8+HZ06dcKSJUvQvXv3Ytc/Z84crFu3Dl999RVeeuklJCUlAQASEhLQq1cvt+docnKy1+uyZMkSDB48GBqNBg899BCSkpJw9epVrFmzBhs3bkTr1q0BALt27UK3bt2g1+sxevRoxMfH48iRI5g+fTpWrlyJrVu3un3BLep5HBMTgzlz5mDcuHGoWrWq09wxMTExpb6fMjIy0LlzZxw9ehQjR45EmzZtsH//ftx+++1ISEgo9LL+VNzHwXPPPYf3338fbdu2xeOPP46cnBx8++23HnuBuOrSpQumTZuGcePGYfDgwfZhNbYvaP40Y8YMJCUloV27dgCAVq1aYcaMGfjvf//rtJ/ttp43bx7uv/9+REZGFnrchIQE/Pvvv/j666/x1FNPFTrEbePGjTh37hyGDRuGWrVqed3v8ccfx4IFC/DLL7+gX79+hZ7/zJkzSE5ORmZmJh566CE0atQI586dw/Tp07F8+XJs27bN7b3kpZdesgdOoaGh+O677zB+/HjUrFkTw4YN83ou2/vqV199hXXr1mHOnDkArMETYH3e2YZOPf7446hfvz7Wr1+PDz74AH/99Rc2btwIvV5folp8ee5/+OGHmDp1qlNtQOGvKRkZGejYsSMOHDiA4cOHIzk5GceOHcPnn3+OpUuXYsOGDWjSpInTZZYsWYJPP/0Ujz76KEaOHImVK1fiyy+/BACfVrNZtGgRBg4ciJiYGDz//POIiorC/Pnz0adPnyIvWxpZWVno2rUrWrZsiTfffBNnzpzBZ599hs6dO2PTpk1o2rSpfd93330X7dq1wxNPPIGqVaviyJEj+Prrr7FixQrs3LkT9evXdzr2mTNn0K1bNwwaNAhvv/22vbdTSd7rd+7ciUGDBuHhhx/G/fffj8WLF+Pdd9+FUqnE3r17kZ6ejmeffdY+x1f//v1x8uRJp9eNUaNGYfbs2bjjjjswfPhwAMAvv/yCO++8E5988gmefPLJIl/TbTIzM9G5c2e0bdsWb7zxBjIyMhAaGuqXz2PFfd0vyXubN71790Z4eDheffVVXLt2DV988QV69+6NJUuWOM135et7vU1WVhY6d+6M1q1bY/Lkybh06RKmTZuGPn364Pjx4wgLCwPgn8+Brop6DfDHfXbu3Dl89dVXGDJkCO655x7odDps3boV06dPx/r167FlyxafJgTeuXMnfvnlF4waNQr3338/tmzZglmzZmHr1q34559/SvxaOWvWLFy6dAn3338/YmNjceXKFcyePRu333475s2bZ/8cTsUgiPxk9erVAoDXfwkJCfZ909PThV6vF7feeqvTMWRZFvXq1RP169cXsiwLIYQ4fPiwUCgUolWrViI7O9u+b2ZmpmjatKlQKpXixIkT9vYRI0YI14d2165dRXx8vMe6AYgRI0YU2ebtWGazWdStW1fo9Xpx/Phxp31HjRolAIg5c+bY215//XUBQPTt21dYLBZ7++nTp4VarRb33nuvx/M6WrlypQAgBg8ebL+dhBDi+PHjIiQkRAAQq1evtrc//fTTQq1Wi82bNzsdJzU1VcTGxopu3boVeU7b/fvtt9/a22RZFllZWW77rlixQgAQ7733XpHH/euvvwQA8dZbbzm1Hz9+XEiSJEaNGlXi88XHx4uuXbvafzcajaJGjRqibdu2Iicnx2nfefPmCQBi1qxZ9rbiPG5OnDghAAiVSiX2799f1NW269y5s1AoFGL79u1O7Y8++qgA4FT/hQsXhE6nE4MGDXK634UQ4r333hMAxN9//y2EEGLhwoUCgPjpp598rsXT8caOHet2LsfH7cyZMwUA8fjjjzvt8++//wqtVisaNmxo37849QshxLfffuv2WLbx9hx1vc+zsrJETEyMiIiIEMeOHXPb3/G6tGjRQtSrV0+kpKQ47bN582ahUCjExIkT7W3FfR671mVT2vvp1VdfFQDEtGnTnNp//PFH+2uvL3XYHr+vv/56kef09FpQnMfBv//+KyRJEh07dhS5ubn2fdPS0kRcXJzbsT2drzj1OgIgevbs6dO+Bw4cEADEu+++a2/75JNPBACxbds2p31zc3NFmzZtBABhMBhE7969xeuvvy6WLFkijEaj27E3b94sNBqNACDq1KkjHnzwQfHJJ5+IXbt2ue1rO+cHH3xQaL1Xr14VAETr1q2LvG6DBg0SUVFRbs+J48ePi9DQUDFy5Eh7m+15ePPNNzu9bmZmZoro6GjRoUOHIs8nhOf3ZiGsr4GSJIlNmzY5tb/xxhsCgJg8eXKJainOc99bbY7ndHwdsj3v3nnnHad9//77b7fHmO2xGhIS4lZH7969hVqtFpmZmR7P7Vhr3bp1RWhoqDh9+rS93Ww2i379+rm9Hnp6ztjYXrscPzd507VrVwFAPPHEE07tW7ZsEZIkuT2XPF2P/fv3C41G43aM+Ph4AUB89dVXbpcp7ns9ACFJktiwYYNTe4sWLYQkSaJ///5O7znz588XAMSXX35pb1uwYIHb891WS9++fUVoaKhIT093qt/Ta6kQBbfbSy+95LbNH5/Hivu6X5z3Nm9sz5EBAwY4PXdOnjwp9Hq9aNiwof02Lu57ve32mjJlisfr43g/lfZzoO18rp/tCnsN8Md9ZjKZnN7vbGbMmCEAiHnz5jm1e/tu4mnfd999t1SvlbZ2V1lZWaJRo0bipptuKvL6kTsOFyK/GzlyJFasWOH277vvvrPvExYWhiFDhmDlypVO3fvWrFmDEydO2P86DFgno5JlGc899xxCQkLs+xoMBkyYMAEWiwULFy4svyvoYseOHTh58iQefPBBexd2G1vX+19//dXtcuPGjXPq3RIXF4fGjRvbu5EXxna8F1980ekvoPXq1bP/9cVGCIHvv/8eHTp0QEJCAq5evWr/Zzabcdttt2HdunUeh24VRZIke2ouyzLS0tJw9epVtGjRApGRkdi8eXORx+jRowfq1Klj76pp46lHU2nP99dff+HixYsYOXIkMjIynG6Lrl27wmAwYNmyZcW8FZz179/f7S+Y3ly5cgXr1q1Dnz593P4KYuux5eiXX35BTk4OHn74YaSkpDjVP2DAAACw12/7S/rixYtx/fr1Yl+P77//HgaDAVOmTHH7K7vj49b2WHSdgLZRo0a47777cOTIEezdu7fY9fvL8uXLceXKFTz99NNuf0V1vC779u3Drl27MGzYMMiy7FRbQkICGjZs6LG20jyPgdLfT7/++isiIyPdelYMGzYMDRs2LPbxSqo4j4MFCxZACIFx48Y5/eUuIiICjz/+eLnVXJQZM2ZAqVTigQcesLcNHz4cWq0WX3/9tdO+arUaq1evxv/93/+hUaNGWLFiBd544w307dsXNWvWxEcffeS0f7t27bBjxw489NBDMJvN+O677zBmzBi0aNECrVq1chqKYXtcFPWXZtv2oh5H169fx++//45+/fohPDzc6bEeFhaG9u3be3ysP/nkk05zHhkMBnTo0MHnx7onttfA3r17u/XgfPbZZ2EwGDy+f/pSi6/P/ZL49ddfERER4TbXRNeuXdG9e3esWrUKqampTtsGDx7sVsett96KvLw8nDhxotDzbd++3f45Iy4uzt6uVCr91pO3MK7naNu2LXr16uV2PW3zqQghkJ6ejqtXr6JatWpo3Lixx/fnKlWqYPTo0W7tJXmv79Chg1vvoy5dukAI4dZbrGvXrgDg9HiZM2cOQkJC8J///Ac5OTn2fyaTCcOHD0dmZiY2btxY5G3laMKECU6/++vzWHFe90v63ubNiy++6PTciY+Px/Dhw3HkyBH70JmSvNcrFAqMGzfOqc02lNzxfvLH587i8Nd9ptFo7O93ZrPZXrdtyKivdTdq1MitV8nYsWMRFhZW4tdKW7tNVlYWUlJSkJ2djR49emD//v3IyMjwqT4qwOFC5He27vxFGTlyJL7//nt8//33eOGFFwAUjH22zcUAAMePHwcA3HTTTW7HaNasGQDrWNNAKay+OnXqICIiwmN9nj70RUdH49SpU0We03Y8T1/mXeuwvRmsXbu20NWdrl696vThzVcLFizAu+++i+3bt7vNP3Pt2rUiLy9JEh588EG8+eab2Lx5M9q3bw8hBL777jskJCS4reRRmvMdPHgQAPDf//7X7cOJzaVLl4qsuTCNGjXyed/C7sfatWu7famy1X/77bd7Paat/i5dumD06NH45ptv8OOPP6J169ZITk7G0KFD0aFDhyJrO3z4MBITE4uchPD48eOIjo5GjRo13LY5Pj+bN29erPr9xfZBoqiuvLba3n77bbz99tse9/H0nC3N8xgo/f107NgxNGvWzONEfk2aNHGbH6KsFOdxYHvNTExMdNvXNiws0HJzczFnzhwkJycjJyfHaf6Krl27Yu7cufjggw+cumYbDAY8//zzeP7555GVlYVt27Zh8eLF+Oyzz/D000+jRo0auOeee+z733TTTfaw5uzZs9iwYQO+++47LF68GP369cP+/fsRFRWF8PBwAL6FJ0DRYczhw4chyzJ++OEHj/PLAJ4DCG+P9ZSUlELPV5jC3j/1ej0SEhKK9f7pWIuvz/2SOH78OG666SaPE203a9YMq1evxokTJ5yGLXirGUCRt2Fx3vP9LTIy0uMwtSZNmmDFihU4fvy4fcjl2rVrMWnSJGzcuNHtS6frH6EA6+dFb5MKF/e93tPta7v9XbfZ2h1v94MHD8JoNBY61O/y5ctet7mKiYlxO5a/Po8V53W/pO9t3nh6DNrajh49WuL3+lq1arlNcO7t+VHaz53F4c/P0DNmzMDnn3+Offv2wWw2O23ztW5Pt79trpWjR4+6bfP1dfvkyZN49dVXsXjxYo+1pKam2odskW8YslDA9OjRA/Hx8Zg9ezZeeOEFZGVl4ddff0X37t0RHx9v30/kz2lRmmVZvV3W9UWuJEpan7cPFrbjlbYeG1mWAVi/zHnqHWFTkuW1FyxYgMGDB+OWW27B1KlTUadOHXtvI9tfTXwxcuRIvPXWW5g1axbat2+PtWvX4sSJE5g0aZLT7Vra89m2v/XWW2jbtq3HfRw/FJfkceM6HtafbPV//fXXTs8RR44fhmfOnIkJEyZgyZIlWL9+PWbOnImpU6di7Nixbn9ZLykhhM+P/eLW7w++Pp9stY0ZMwZ33HGHx30ce9LZ+ON5XFb3k6cayuq1sDiPg6JqqQjmz5+Pq1evYt26dR6/HALWSXG9Ld9qMBjQtWtXdO3aFT169ECfPn3w9ddfO4UsjmJjY3HPPffgnnvuwb333ouffvoJixcvxvDhw+0hlbeJpG1sE0TefPPNhe5ne6zffffdeOSRRwrd11FZrLDj7/dPT8cuK/6s2d+1FlabPz73eDrX9u3b0bNnT9SvXx9vvfUW6tevD71eb19dxtMcY97eL0vyXl/Y7evL67Qsy4iMjMSSJUu8Hqc481x5um5l+XnMxttnwOK+t5WE7bFQkvd6X58f/vrc6St/3We2FeB69uyJzz//HLVq1YJWq4XFYkGfPn38Uren570vr5W2+YPS09Px1FNP4eabb0Z4eDgUCoX9D0D+vl2DAUMWChhbD4bJkydjy5YtOHToEDIzM90+tNre1Pbt2+f2F5t9+/YBKDqFr1KlitsM5UDBX9FKw7E+V2fOnMH169eL9VeC4pzzwIEDaNOmjdM211n8bX9NSU1N9amHUXF899130Ol0WLNmjdMHiqysLLeu0oVJSEhAp06d8PPPP+Ojjz6y92h68MEH/Xo+Wy8TnU7n021Rlo8bwPl+dHXu3Dm3v1zb6o+KivL5vkxMTERiYiLGjRuH7Oxs9OnTBx9//DGeffbZQv/q0qhRIxw+fLjIJTVtE3heunTJPpGljevzsyT1l1bjxo0BWCeL8/YB07E2AGVSW1FfyEp6PyUkJODo0aPIzc11+6um7a+JjqpUqeLxr1SlfUwX53Fg++/Bgwfd/irnqWZPyjqgmTFjBqKiovDNN9943D5mzBh8/fXXXkMWR7YhDL6ufJGcnIyffvrJvn9ycjJq1qyJhQsX4uLFix57CwGwT6Ja1ASFDRo0gEKhgNFoLLfnoTeFvX8ajUYcP368xBM4+/rcB4r/eKpfvz6OHDkCk8nk1ptl3759kCTJazhXEoW9V+zfv9+tzbZMtj+e62lpaTh//rzbl+IDBw44Xc8ffvgBZrMZS5YscfvMk5KSUqxl2P312aI4GjVqhEOHDiEhIcGnkKMkr0H++jxWnNd9f7+3HThwwK2Xpe1xaXucluV7fVk9Nrzdn/66z2bPno26deti+fLlTj0FfX3Ps/H0GmAymUr1Wrlq1SqcPXsWM2fOdBu+N2PGjBIdk7iEMwWYbUm42bNnY9asWQgLC8Odd97ptM+gQYOgUCjw/vvvIycnx96enZ2N9957D0qlEoMGDSr0PI0bN0ZGRga2bt3q1P7ee+953D80NNTnrnutWrVC3bp1MWfOHLchApMmTQIAt+tUWrbVNN5++22nhP/EiRNu3b8VCgXuv/9+7N27123eE5uSDtFQqVSQJMkt4Z48eXKxU+9Ro0YhLS0Nc+fOxS+//GLv6eTP8/Xu3RvVq1fHe++9Z1/FwJHZbHa634v7uCmumJgYdOrUCUuXLsWOHTuctr355ptu+999993Q6XSYOHEiMjMz3bYbjUb7uNlr16653SZ6vd4+HKOox/f999+PrKwsj3+5cTyu7bE4efJkp32OHj2KuXPnokGDBva/rBenfn+57bbbEBMTgw8//NDjkqW269KiRQs0a9YMM2fO9PihRwjhdYlEX3h7TSnt/TRkyBCkpaXh888/d2r/6aefPA4Vaty4MQ4dOoRz587Z22RZxgcffODzdfFWB+Db42DgwIGQJAnTpk1DXl6efd/r168Xugy9I9uKIP7uGg5Yv4SuWrUKAwcOxKBBgzz+u/POO7Fhwwb7Y2X37t1Ot6kj2/KvjoHSihUrnK67jcViwe+//+60v0ajwVtvvYXs7GzcfffdbssaA8Cnn36K3377DT169ChyZaHo6Gj069cPixYt8rrkq7+H7Xljew1ctmyZ2+vsBx98gMzMzBK/f/r63AeK/3gaMmQIrl+/jk8++cSpff369Vi1ahW6d+9e7BVOCtOqVSvEx8fju+++w5kzZ+zttuVsXdWrVw9qtRp//fWXU/uRI0d8WsHLles5tm7dir/++svpetpW5XPtSfHFF18U+/Hkz88WvrL9UWfChAkez3H+/Hmn34vzOdHGX5/HivO67+/3trffftvp9jl16hR++OGHcnuvL6vHhrfXAH/dZ7bnh2ONQgj79wRfHT58GL/88otT28cff4yMjAz7+3BxeXvu7tmzBwsWLCjRMYk9WagM7N69G99//73Hbd27d0ft2rXtv9evXx+dO3fG999/j8zMTIwePdqti2XDhg3x8ssvY/LkyWjfvj2GDx9un4hq7969eOutt5zWu/fk0UcfxQcffIBBgwbhqaeegl6vx6JFi7yuTd++fXv89ddfeOedd1CnTh1IkuR1iUqlUonp06fjjjvuQJs2bfDYY4+hWrVqWLJkCRYvXozevXu7TUZbWj179sRdd92FefPm4dZbb8XAgQORkpKCzz//HE2aNHHrffHWW29h48aNGDlyJBYsWIDOnTtDr9fj9OnTWLlyJfR6vdcP24UZOnQo5s2bh65du2LkyJEQQmDZsmU4cOAAqlatWqxj3XXXXRgzZgyefvppjz2a/HE+vV6POXPmYODAgUhKSsKoUaOQmJiIjIwMHD16FL/99hveeecd+7mL+7gpiWnTpqFLly7o1q0bnnjiCfsSzrt27XK7TrVr18aXX36J0aNHo3HjxhgxYgTq16+Pa9eu4eDBg5g/fz4WLFiAbt264bvvvsPUqVMxaNAgNGjQACEhIdi2bRu+/vprtGrVyj4EwZunnnoKixYtwrRp07Bz507069cPYWFhOHz4MJYvX27/y/OIESPwww8/4LPPPsPp06fRu3dv+9K9Qgh89dVX9r/aFKd+f9Hr9fj2228xZMgQNG/eHA8//DAaN26M1NRUrFmzBn379sWYMWMgSRK+//579OjRA61atcLIkSPRrFkz+6SUCxYswMiRI+2TWRdX+/btMXPmTLz66qtISkqCQqHAgAEDSn0/Pfvss/jxxx8xfvx47NmzB23btsW+ffvw7bffolmzZvbJZm3Gjh2LH3/8ET169MBjjz0GIQTmzZtXouvkqDiPg8aNG+Ppp5/GtGnT0KlTJwwbNsy+hHPNmjVx5syZIv9KHB0djQYNGuCnn35CQkICqlevDoPBYJ9UsTAnT570GGICwAMPPICZM2dCCIG77rrL6zHuuusufPTRR/j666/xwQcfYPXq1ZgwYQJ69eqFTp06oVatWsjIyMDmzZvxyy+/IDw8HK+//rr98hMmTMCFCxdw++23o3nz5ggLC8OFCxfwyy+/YOfOnejZsyf69+9v33/UqFE4efIkJk2ahMTERIwYMQINGza0T2L7999/o127dvj555+LvP6A9Ytvp06dcOutt+K+++5DmzZtoFAocOrUKSxatAht2rTBrFmzfDpWaX3yySfo0qULevTo4bSE89y5c9G8eXM888wzJTqur899wPr8/PTTT/Hf//4X/fv3h1qtRrt27bz2Rnnuuefw22+/YcKECdi9e7fTEs4RERFu4UtpKZVKfPzxxxg8eDDatWuHRx99FFFRUfjtt988fokNDQ3F6NGj8eWXX+Kee+5Bjx49cPr0aXzxxRdo1qwZ/vnnH5/PXbVqVfz55584d+4cbr31Vpw+fRqfffYZ9Ho9pk6dat9v8ODBmDp1Kvr27Yv//Oc/0Ov1WL9+PZYtW4aEhIRiDVPy52cLX91555145JFHMGPGDOzduxeDBw9GjRo1cPbsWWzduhXLly93ug7eXtOLmsfMH5/HivO67+/3tvPnz6NXr14YPHgwrl27hunTp8NkMuHTTz+1v26X5Xt9WT02CnsN8Md9NnToUDz//PPo3bs3hg4diuzsbMyfPx8mk6lYdTZr1gwjR47E2rVrkZSUhK1bt2L27NlITEzE+PHjS3TdO3bsiJo1a+KZZ57B8ePHUbduXRw8eBAzZsxAs2bNPPboJh+U5dJFFFyKWsIZgPjjjz/cLmdbZgyAWLdundfjz5kzR7Rt21aEhISIkJAQ0a5dOzF37ly3/bwtw7Zs2TLRunVrodFoRExMjHjsscdEWlqax2XSDh8+LG699VYRFhbmthyet2V9N23aJPr16yciIyOFRqMRjRo1EpMmTRImk8lpv8KWTyxsyWBXJpNJvPLKKyIuLk5oNBrRuHFj8dlnn3ld9jY7O1tMmTJFNG/eXISEhAi9Xi8aNGgghg8fLpYtW1bk+bwtCTlz5kzRtGlTodPpRExMjLjvvvvEmTNnCl3e0BvbfRceHu5xib7ins9bDQcPHhQjRowQsbGxQq1Wi+joaNG6dWvx4osvOi2PKYTvj5uSLikrhBBbt24V3bt3F3q9XkRERIghQ4aIEydOeK1/8+bNYujQoaJ69epCrVaL6tWriw4dOojJkyfbl2jcuXOnGDlypGjYsKEwGAzCYDCIpKQk8corr4jU1FSf6jKZTOKdd94RzZo1EzqdToSFhYmbb77ZbblHo9EoXn/9ddGoUSOh0WhEZGSkuP3228XWrVs9HteX+oXwzxLONtu3bxd33nmniImJEWq1WtSqVUsMHjzYbensM2fOiCeeeELUr1/ffl2aNWsmnnrqKaeluYv7PL506ZIYMmSIiIqKEpIk2S/rj/vp/Pnz4v777xdRUVEiJCREJCcni1WrVnl9Lfzhhx9EUlKSUKvVonbt2uLFF18Uhw4dKtUSzkIU73Egy7J4//33RUJCgtBoNKJevXpiypQp9qVVf/755yLPt2XLFpGcnCz0er0A4NNrZ1HvUX/99ZeoVauWiIiIcHvtdq2/du3aomrVqsJkMomTJ0+KKVOmiJ49e4q4uDih1WqFTqcTjRo1Eo8//rjb0r0rVqwQTz75pGjRooWoWrWqUCqVIjIyUiQnJ4sPP/zQ67k3btwohg0bZn/tioyMFJ06dRKff/65x+VBC3Pt2jXxwgsviMTERKHVakVYWJhITEwUjzzyiNNSpYU9Dwtb9rQ4+x44cEDcfffdomrVqkKtVov4+Hgxfvx4kZaW5rRfSWrx5blvsVjEM888I2rXri0UCoXT483bOa9duyaefvppER8fL9RqtahataoYNmyY+Pfff532K+y9obDr48nSpUtF27ZthVarFVWrVhUjR44UV65c8fh6mJmZKR577DFRtWpVodPpxC233CL++OOPYi/hHB8fL06cOCGGDBkiIiIihF6vFz179nR77RRCiN9//13ccsstQq/Xi6ioKDFgwACxf/9+j6+JRX1GKM57vbf3g8Kuq7fL/Pjjj6Jbt24iIiJCaDQaERcXJ/r27SumT5/utJ+313TH282b0n4eE6L4r/u+vrd5Yzvu1atXxciRI0XVqlWFVqsV7dq1EytWrPB4GV/f6wu7vTzdT6X9HOjpfIW9BghR+vvMYrGId955RzRs2FBotVpRq1Yt8fjjj4tr1655Xa7ZW9uqVatEcnKyCAkJEVWqVBEjRowQly5dctq3uK+V+/btE/369RNRUVFCr9eL9u3bi4ULFxbr9YKcSUKU8cxgRERERD5477338Nxzz2Hz5s1o165doMshCmrdunXDyZMnPQ63ouAycuRIzJ49u8wnlCbvbKuvllcvQyodzslCRERE5So7O9utzTbHRUxMDFq2bBmAqoiIiIhKj3OyEBERUbmaO3cuvvjiCwwYMAC1atXC6dOn8e233+LcuXOYOXOm24oZRERERJUFQxYiIiIqVy1atEC1atXwxRdfICUlBSEhIWjZsiWmT5/u0+S1RERERBUV52QhIiIiIiIiIvIDzslCREREREREROQHDFmIiIiIiIiIiPyAIQsRERERERERkR8wZCEiIiIiIiIi8gOuLlQKOTk52Lt3L2JiYqBS8aYkIiIiIiIiutGYzWZcuXIFzZo1g06nK3RfJgOlsHfvXrRt2zbQZRARERERERFRGdu6dSvatGlT6D4MWUohJiYGgPWGrlmzZoCrISIiIiIiIiJ/u3DhAtq2bWvPAArDkKUUbEOEatasidjY2ABXQ0RERERERERlxZdpQjjxLRERERERERGRHzBkISIiIiIiIiLyA4YsRERERERERER+wJCFiIiIiIiIiMgPGLIQEREREREREfkBQxYiIiIiIiIiIj9gyEJERERERERE5AcMWYiIiIiIiIiI/IAhCxERERERERGRHzBkISIiIiIiIiLyA4YsRERERERERER+wJCFiIiIiIiIiMgPGLIQEREREREREfkBQxYiIiIiIiIiIj9gyEJERERERERE5AcMWYiIiIiIiIiI/IAhCxERERERERGRHzBkISIiIiIiIiLyA4YsRERERERERER+wJCFiIiIiIiIiMgPGLIQEREREREREfkBQxYiIiIiIiIiIj9gyEJERERERERE5AcMWYiIiIiIiIiI/IAhCxERERERERGRHzBkISIiIiIiIiLyA4YsQejs2e+xclUCUq6tD3QpRERERERERDcMhixB6N/DrwMAdu0aEeBKiIiIiIiIiG4cDFmIiIiIiIiIiPyAIUsQiq7SBQBQu/b9Aa6EiIiIiIiI6MbBkCUYSVL+DyKgZRARERERERHdSBiyBCWp6F2IiIiIiIiIqFgYsgQl9mQhIiIiIiIi8jeGLMFMMGQhIiIiIiIi8heGLEFIyu/JItiThYiIiIiIiMhvGLIEI4lzshARERERERH5G0OWIKTOzkZkWh6UOVmBLoWIiIiIiIjohqEKdAFU/pos/QMAIO+bDbT4MLDFEBEREREREd0g2JMliAklMzYiIiIiIiIif2HIEoSu14oFAGTE1g9wJUREREREREQ3DoYsQUhWKgEAksUS4EqIiIiIiIiIbhwMWYKQUOSHLDJDFiIiIiIiIiJ/YcgShITCerczZCEiIiIiIiLyH4YsQUjOn/BWspgDXAkRERERERHRjYMhSzBScE4WIiIiIiIiIn9jyBKE7BPfcrgQERERERERkd8wZAlCtolvFezJQkREREREROQ3DFmCkGBPFiIiIiIiIiK/Y8gShGTOyUJERERERETkdwxZgpC9JwtDFiIiIiIiIiK/YcgShOxzsnC4EBEREREREZHfMGQJQuzJQkREREREROR/DFmCkFCqAORPfCtEgKshIiIiIiIiujEwZAlCtuFCEgDI5oDWQkRERERERHSjYMgShGzDhQAA5pzAFUJERERERER0A2HIEoSEQlXwizk3cIUQERERERER3UAYsgQhWcWeLERERERERET+xpAlCNnmZAEAWEyBK4SIiIiIiIjoBsKQJQjZVhcCAJgZshARERERERH5A0OWIPTH4ToFvzBkISIiIiIiIvILhixBaPbeBgW/MGQhIiIiIiIi8guGLEEoF+qCXzgnCxEREREREZFfMGQJQu3i0wp+YU8WIiIiIiIiIr9gyBKEVCoJeSJ/hSGGLERERERERER+wZAlCKmVMnKRv8KQOSewxRARERERERHdIBiyBCGNUsBkm5fFkhvYYoiIiIiIiIhuEAxZgpBGKQomv+VwISIiIiIiIiK/YMgShNRKAZNgyEJERERERETkTwxZgpBTTxYu4UxERERERETkFwxZgpDTnCzsyUJERERERETkFwxZgpBaKWCExvpLblZgiyEiIiIiIiK6QTBkCUJaFZAh9NZfTOmBLYaIiIiIiIjoBsGQJQipFQIZyA9ZchiyEBEREREREfkDQ5YgpFEJZIgQ6y/syUJERERERETkFwxZgpBGWdCTRbAnCxEREREREZFfMGQJQmqlw5wsOWkBrYWIiIiIiIjoRsGQJQhplUA6e7IQERERERER+RVDliDEOVmIiIiIiIiI/I8hSxDSKGGfk0WRmwnIlgBXRERERERERFT5MWQJQhrHOVkAwJQRuGKIiIiIiIiIbhAMWYKQRlWwuhAADhkiIiIiIiIi8gOGLEFIo5SQ7tiThZPfEhEREREREZUaQ5Yg5DgnCwD2ZCEiIiIiIiLyA4YsQUijkpAJHWQhWRvYk4WIiIiIiIio1BiyBKHDG1ZCQIFM6KwN7MlCREREREREVGoMWYJQ+sULUEnmgiFDOdcDWxARERERERHRDYAhSxAKrVIVamVewTLO7MlCREREREREVGoMWYJQzQaN83uyhFgb2JOFiIiIiIiIqNQYsgShkPBI554snPiWiIiIiIiIqNQYsgQhfUQE1AqHOVk4XIiIiIiIiIio1BiyBCG1RgeVwowMYRsuxJCFiIiIiIiIqLQYsgQjSQG1Io89WYiIiIiIiIj8iCFLEJIgQa8yck4WIiIiIiIiIj9iyBKMJAUM6myksycLERERERERkd8wZAlSenU20vN7sggu4UxERERERERUagxZgpAEa08W25wsUm4mIFsCXBURERERERFR5caQJRhJkjVksa0uBACmjMDVQ0RERERERHQDYMgSlCSnniwAOC8LERERERERUSlV6pDl8OHD6NOnDwwGA6pVq4annnoKRqOxyMt169YNkiS5/Tt06FA5VB14EhQwqLILVhcCAM7LQkRERERERFQqqkAXUFJpaWno0aMH4uPj8euvv+Ly5csYP348UlJS8P333xd5+Y4dO+L99993aqtbt24ZVVvBSB56snAZZyIiIiIiIqJSqbQhy5dffonU1FTs2rULVatWBQCoVCoMHz4cL7/8MpKSkgq9fGRkJNq3b18epVY4EiQY1FnIhA6ykKCQBGRjWuXu1kREREREREQUYJX2e/XixYvRq1cve8ACAHfeeSe0Wi0WL14cwMoqA2tPFgEFMqEDABivng1wTURERERERESVW6UNWQ4ePOjWW0Wr1SIhIQEHDx4s8vJr1qyBwWCATqdD165dsXbt2rIqteLJHy4EwD5kyHj5TCArIiIiIiIiIqr0Ku1wodTUVERGRrq1R0VF4dq1a4VetmvXrnjwwQfRsGFDnD9/Hu+//z569eqFNWvWoEOHDl4vl56ejvT0grlLLly4UOL6A0mCAhplHtQKs3XyWykFOdfOB7osIiIiIiIiokqt0oYsACBJklubEMJju6M33njD6ffbb78dN910EyZPnlzoUKOpU6e6XbZyst4+BrURGSIEAJB3/XIgCyIiIiIiIiKq9CrtcKGoqCikpqa6taelpSEqKqpYxzIYDOjfvz+2b99e6H7jx4/HmTNn7P+2bt1arPNUFLYQyqA2Il0YAACWjJRAlkRERERERERU6VXanixJSUluc6+YTCYcO3YMo0ePLvbxhBBF7hMeHo7w8PBiH7visYUs2cgwWXuyCGNaAOshIiIiIiIiqvwqbU+Wfv36YeXKlUhJKeiBMX/+fJhMJvTr169Yx8rKysKiRYvQpk0bf5dZQTkOF7JOfKuUjTBmpBd2ISIiIiIiIiIqRKUNWR599FFERkZi4MCBWLZsGebMmYMxY8Zg+PDhTqsOPfTQQ1CpCjrsrFu3DgMHDsSsWbOwevVq/PDDD+jcuTMuXryI1157LRBXpdxJkvVuN6iz7asLaRUWXDvHZZyJiIiIiIiISqrSDheKjIzEqlWrMGbMGAwZMgR6vR733nsv3nnnHaf9LBYLLBaL/feaNWvCZDLhxRdfREpKCgwGA5KTk/HFF1+gbdu25X01AsRhuFB+Txat0owL58+idmKTQBZGREREREREVGlV2pAFABo1aoRly5YVus+sWbMwa9Ys++8NGjTA0qVLy7iyCs5h4tsMWOdk0SrMuHaePVmIiIiIiIiISqrSDheikpPye7KEqrOQLhyHC50JZFlERERERERElRpDlqBkDVn0aqN9ThaN0oLU86cDWRQRERERERFRpcaQJRjZJ77NQoYIsTcbr5yHOTc3UFURERERERERVWoMWYKQZJ/4NsvekwUANIo8pF08H6iyiIiIiIiIiCo1hizBKH/iW72qYHUhgJPfEhEREREREZUGQ5Yg5L0niwXXzjFkISIiIiIiIioJhixByRqyhKiMyJJ0kIX1d62SPVmIiIiIiIiISoohSzDKn/hWggXhIVpkwjr5rVZhYchCREREREREVEIMWYKQbbgQIBAZokZ6/pAhrdKMa+fOQggRuOKIiIiIiIiIKimGLEFJsv8UEaK2L+OsUZiRZ8pBRsrVQBVGREREREREVGkxZAlGkkvIkt+TRae0AACHDBERERERERGVAEOWICQ59GSJ1KvtyzgbQpQAwBWGiIiIiIiIiEqAIUtQKrjbI0JUyMif+DbUoAbAnixEREREREREJcGQJRg5DBeKDFHZe7LotdaHQ+r5MwEpi4iIiIiIiKgyY8gShByHC4WHqArmZFFZVxXicCEiIiIiIiKi4mPIEpRcVxeyhiwaKQ8AkJl6DabsrIBURkRERERERFRZMWQJRq7DhfLnZFHJRns752UhIiIiIiIiKh6GLEFIcpr4Von0/J4sUm4m1FodAA4ZIiIiIiIiIiouhixByXG4kBLp+XOySHlZiK5dCwB7shAREREREREVF0OWICRJLks45/dkAYCYGjEA2JOFiIiIiIiIqLgYsgS5MJ3SvroQAMRUiwLAnixERERERERExcWQJRg5THyrVUkwq0Ptv1epGg4ASLt4HhazudxLIyIiIiIiIqqsGLIEIcnpbpeh0EXYf4uIMFhbLRZcv3yxnCsjIiIiIiIiqrwYsgSlgp4sQgho9OGQhbUtzKC2z9nCeVmIiIiIiIiIfMeQJQg5TnwLyAjXa5CJEACA0pyNiOrVAXBeFiIiIiIiIqLiYMgS5ASAyBCNfRln5KSjSq1YAOzJQkRERERERFQcDFmCUsFwIQiBSL0aGcLakwWm66hSOw4AcO38mQDURkRERERERFQ5MWQJQq7DhSL06oJlnHPSUaV2QU8WIUT5F0hERERERERUCTFkCUoOE99CICJEjQyRH7KY0lGllrUniyk7C9nX0wJQHxEREREREVHlw5AlGDn2ZBEyIkM0yMif+NY6J0tt++Zr5zhkiIiIiIiIiMgXDFmCkOQ4JwuASL0a6cIAABCmdISEhSMkPAIAVxgiIiIiIiIi8hVDliAnhEBkiNrek0U2XgcArjBEREREREREVEwMWYKRp4lv8+dkkY1pAGCf/DaFw4WIiIiIiIiIfMKQJQg5DxfKn/jWYXUhAKgaFw8AOLV3F7bM/x9XGSIiIiIiIiIqAkOWoFRwtwshI1KvsfdkUeRmAABu6toTMfH1ACGw/qfv8Oe0/0NujjEg1RIRERERERFVBgxZgpAkOfdkMWiUyJKsIYvSnA1YzNDqDbh30nto3KEzAODwlg348dUJSLt0MQAVExEREREREVV8DFnIGrrowgsaTNYhQ2qdDv2feg6d7xsJSBKunj6JH14ah1N7dgWkTiIiIiIiIqKKjCFLEMrMzLb/LIRs/a/WPWQBrAFM24FDMeT516HVG5CTmYFfp7yG7YsWcJ4WIiIiIiIiIgcMWYLQjPmzMPm8DlfNEgBrUKIMiSjYISfd7TL1Wt6C+96aiiq14yCEjL+/+xpLP5uKvFxTOVVNREREREREVLExZAlCy5QbkGJR4M0LIcjOtfZqURsiC3YwuYcsAFClVm3c9+YHSLilHQDgwLrV+Pn1F5B+9UpZl0xERERERERU4TFkCUKp6gz7z+9t/gIAEKIPhyzyJ8T10JPFRqvXY+AzL6P9nfcCAC4dP4IfXhqHs4f2l13BRERERERERJUAQ5Yg9M89y9AjLA8AsPTyOmy/tB3hBi0yEWLdwUtPFhtJoUDHu4fjjvEvQa3VIft6GuZNehm7Vywp69KJiIiIiIiIKiyGLEFJQt+IPFRXyRAAXl3/KgxaGemwLuNcWE8WRw3bJeO+N99HRPUakC1m/PX1Z1jx1aewmPPKrnQiIiIiIiKiCoohSzCSJKgl4N4quZAEcCbzDPYZf0aGyA9ZTNd9PlTVOnUxfMo0xN/cEgCwZ+VS/G/Sy8hKSy2LyomIiIiIiIgqLIYsQUjKv9vramU0McYBAHak/Y4dWq11hxzfQxYACAkNw5AXJuKWAUMAAOf/PYDvX3waF48e9l/RRERERERERBUcQ5agJNl/apFVF6G5oRAQmFktDzmSBNno23AhRwqlEl3vH41+Tz4DlVqDzGsp+Gni89i/ZqU/CyciIiIiIiKqsBiyBCFJKghZwkIMuOXqLQAkXNHI+DwyAnnZaSU+dlLn7hg26V2ERcfAkpeHpZ9Pw+rZMyBbLKUvnIiIiIiIiKgCY8gSlApCloYNGyLaFI2ErKYAgNkRYdhlvFSqo1ev3wD3vz0NsUnWY+5YvBC/TnkV2enFG4ZEREREREREVJkwZAlKBSFL48YNAQANLzdCRK4WsiRhsnQJJoupVGfQR0Ri6CtvokXv/gCA0/v24IeXxuPyyeOlOi4RERERERFRRcWQJQhJUsHdHhkZgdq1ayNEAG0vNoQkBE4pLPh81+elPo9SpULP0Y/jtkfHQqlSIf3KJfz42gT8u2ldqY9NREREREREVNEwZAlKBT1ZBARatmwJhQSE5lTD8PQMAMCs/bOw7+o+v5ytWY/bcPfrb8MQVQVmkwl/fvgO1v04G7LMeVqIiIiIiIjoxsGQJQg59mSBEGjatClUKhWM0GJs6nXE5lkgCxmvrH8FuZZcv5yzVqMk3D9lGmo2aAwA2LpgHha8Oxk5WZl+OT4RERERERFRoDFkCXICAjqdDklJSTBBixAh8OaVq5Ag4dj1Y5iyZQqMZqNfzhVaJRp3v/42burWCwBwYuc2zH35GaScPeOX4xMREREREREFEkOWoFQwXAhCAABatmwJEzQAgNYmE+5rMAQA8OuRXzFg/gD8efxPyEIu9ZlVGg16P/YUeox6FJJCgdQL5zD3lfE4tn1LqY9NREREREREFEgMWYKQ03AhWIOTunXrwqI22FufrjsUo2sNgQoKXMq+hBfXvYgHFj+A3Vd2++H8Elr2GYC7XnkTIWHhyDUaseC9N7H5158g5NIHOURERERERESBIAmR35WBiu3s2bOIi4vDmTNnEBsbG+hyfJZz/hT2vH8rpFwgRt8dKqMGlrTrOHPsFKobL8CSq4CwWHu7SLG1sKx7OL6pdQSywtrWr14/jGs9DjUMNUpdS/qVy1jw/pu4kr+0c8O2yejzxDhodCGlPjYRERERERFRaRXnuz9DllKorCHLmaefQubS5cW6jKV2NfySLGF+/auQFRJ0Sh1GNh2JUTeNgl6tL1U9eaYcLPviY/y7cS0AoGpcPAY++woia9Qs1XGJiIiIiIiISqs43/05XCgISUql/WdNp+aIGDwYVUaOxMmB96Na6+uonXwNqUPaIW7m1wjt3h0AoDx3GffMu4RZ30Wg9yEdcvOM+GL3FxgwfwD+OPZHqeZrUWt16D92AjrfNxKQJFw9cwo/vDQOJ/fsLO1VJSIiIiIiIio37MlSCpW1J4ss52L130kAgBYtZiO6SicAwP/+OYPef7ZFhJSN+eiNHuNmICIiAsZ9+3H1s8+QuXq1/RiZ1cPxXVsj1jaRISskNKvaDM+1eQ4tqrUoVW0ndm3Hoo/fhSkrC5KkQJfhI9H69sGQJKnoCxMRERERERH5GXuyUBEc7naHHigRejUyYB36oxUm7N5tneQ2pOlNiJv+OerOm4fQbt0AAKGX0vHfP/Iw/RsNOu+Vsf/yHjyw5AE8t/Y5XMi8UOLK6rVojeFvTUV0bB0IIWPN999gyWdTkZdrKvExiYiIiIiIiMoDQ5Yg5NwrpKAjU0SIGhnCGrKokYddu3bBsaNTSLOmiPtiulPYEnXFiDF/yvhkpgKd98lYdmwxBiwYgE93forsvOwS1RdVszbue/N9JNzSHgBwcN1q/PTac0i/erlExyMiIiIiIiIqDwxZglLB3S4cerJE6tVIz+/JokIerl27htOnT7td2lPYEnM1D2P+kPHh1wJtdxsxY5d1vpbfj/1eovlaNCF6DHzmJXQYeh8A4PKJY/j+xXE4e2BfsY9FREREREREVB4YsgQhb/ObRIZokCGsSyeHaqz7rF27Funp6R73Lwhb/ofQrl0BADVSZIz5Q8bUGTIa/3MRr6x9Cfctug87Lxd/EltJoUDyXfdh4LOvQK0LgTH9Oua9+TJ2LVsETiVEREREREREFQ1DliB0eeo0h98KwopIhzlZqhjUAIBjx47hww8/xPz583Hp0iWPxwtp1gxxX37hFLbUuiYw5g8Z02ZYELVmL0YsegAT1kzA+czzxa63QZv2GP7WB4isUROyxYKV30zHiq8+gTkvr9jHIiIiIiIiIiorDFmCUMpXXwH5I3gchwvp1EpkSwYAQJgG6Ny5M7RaLWRZxu7duzF9+nTMmTMHx44d89iTxHPYAoz9Q8bUGRZk/rkYA38bgI93fFzs+VqiY+tg+FvTULdFawDA3lXL8b9JLyIz9VpJbgIiIiIiIiIiv2PIEoQMHTvaO7AIi9lpW64qFAAg5aajZ8+eGDduHHr37o2IiAgA1p4tc+bMwRdffIFdu3bBbHa+POAQtvzvZxi6dgEA1M4PW97+IhsHf/wSA37tj4VHFxZrvhZdaCgGP/8a2gwcCgC4cPgQfnjxaVw48m+xbwMiIiIiIiIif5MEJ7coseKslV2RmI4fx/qjtwIqIME4EnX7v2rfNuP/xuKRnNm4pq+LKs/ttrdbLBYcOHAAGzduxIULBUs0h4WFoV27dmjdujVCQkI8ns+4Zw+ufPYZstastbedqwL80kmBtE434bl2L6BV9VbFug6HNqzBsi8+hjnXBKVKhV6PPImm3XoV6xhERERERERERSnOd3+GLKVQWUMWAFi5ogGgFIj6SoVaTYaj2rPPQqHX46upr+A/6Z8gQ10VYS8fc7ucEAKnTp3Cxo0bcfjwYXu7Wq1Gq1at0L59e0RFRXk8Z2FhS1jfPni6zXjUDq3t83W4dOIYFr7/JjKuXgEAtOw7AF3vfwhKlcrnYxAREREREREVhiFLOanMIcuq1YkQIg9RX6kQsksBdXwd1Hr7//D95hX4z+W3kCvpoHnd80S3NleuXMHmzZuxa9cuWCwWANaVi5o0aYIOHTp4vU28hS0LOmvQ6K5ReKj5IzCoDT5dj+z06/hz2v/hzIG9AIC4m27G7U8/D314hE+XJyIiIiIiIioMQ5ZyUplDltV/3wRZzkGdU31hfm81IMuAQoHVdw3Ef6XPrDu9ehVQqos8VmZmJv755x/8888/yM4umNC2Tp06SE5ORqNGjaBQuE//Y9y9G5c//RTZ69bb285GA8u7RyD5/gkY2HgwFFLR0wZZzGasmTMTO5f+AQAIj6mGgc++gmp16xd5WSIiIiIiIqLCMGQpJ5U7ZGkKWTai6U0fI/xiLM4//wJyT57EijZtMDZhoXWn504A+io+HzMvLw+7d+/Gxo0bce1awao/0dHRaN++PZo3bw6NRuN2OePu3bjwyUcwrd9kbzsbDWzqHYf+D7+F1rXa+HT+fatX4K+vP4PFbIZKo0Xvx59CYnIXn+snIiIiIiIicsWQpZxU5pDl7zU3w2LJwk03fYga1QdANhpxeeo0zNt9AGOaWHuEXIt5AVGPToBUzDlOZFnG4cOHsXHjRpw+fdreHhISgrZt26JNmzYIDQ11u5xx926c/ugDyBv/sbedjQYOD2qBOx75P8RFxhd57vOHD+H3qVOQlb+0c5uBQ9Fp2ANQKJTFug5EREREREREAEOWclO5Q5bmsFgycVOTaahR4w57+4/f/YJ7jz8EADi+NAYWfR2E9+mL8L59oGvaFJIkFes8Z8+exaZNm3DgwAHYHmpKpRLNmzdHhw4dEBMT43YZ465dODJ1CtRb99rbzlWVcHVYD9z+8BSE6sILPWdm6jX8/sFb9qWd67VojX5jJ0BncA92iIiIiIiIiArDkKWc3Bghy1TUqDHQ3r5o2xH0//MWAMCpVdHIvqy1b1PXro3wvn0Q1qcvdDc1KVbgkpqais2bN2PHjh3Iy8uztzdq1AjJycmIj493O17Gzu04+N5EhO04am+7EKOEPHIouj34ElRq96FHNua8PKycOR37Vi8HAETVrIWBz76C6Ng6PtdMRERERERExJClnFTmkGXN2pYwm9PRpMkHqFljkL197b+X0XFuIyglgcz2byNrbxYylixF3vnzTpdXx8UhvE9vhPXpA10T3wMXo9GI7du3Y8uWLcjIyLC316xZE8nJyWjSpAmUSuehPVf/2Yj9772OanvO2tsuV9Mi/NGH0GLYfyEpPQ8FEkJg9/LFWD37K8gWC9S6EPR78hk0aNPep1qJiIiIiIiIGLKUk8odsrSC2XwdTZLeR82ag+3te86mIX5GEiKkbKT3+QTh7R+EEAI5e/cifekypC9dAvP5C07HUtepg/A+fRDetw+0iYk+BS5msxn79u3Dpk2bcOlSwVLRERERaNeuHVq1agWdTud0mRPrl+Lw1DdR50CKvS21ZihqPDkW9Qbd5zVsOXNgL/6Y9n8wpl8HAHQYeh863DkMkocVj4iIiIiIiIgcMWQpJ5U5ZFm77hbk5aWiSdK7qFnzTnv76ZRsKD5uhljpKi53moRqvZ5yupwQAjl79iB9yVKkL10K88WLTts18fEI69sH4X36QNu4cZGBixACx48fx8aNG3Hs2DF7u1arRevWrdGuXTtEREQ4XWbbXz/g3MfT0Ohwlr0to3YU6j71LGL6D/QYtqRfvYyF77+Fyyes52jQpj36PjEemhB9EbcUERERERERBTOGLOWkcocsbZCXdw1JSe+gVs2h9vbrxjycf7sVkhSncbbleMQOfN3rMYQsw7h7NzKWLkX60mUwO/RIAQBN3br5gUtfaBs1LDJwuXTpEjZt2oQ9e/ZAlmUAgEKhwE033YTk5GTUrFnTvq9FtmDpnx/B+NVs3HQ0196eE1cN9Z6egIi+/dx6quSZcrD8y09waMMaAEB0bB0MnPAKomrUKuLWIiIiIiIiomDFkKWc3BAhS+L/oVatu+ztsiywbWJ7tFUcwslGo1H3vmk+HU/IMoy7diN96RJkLF0G8+XLTts19esXDClq2LDQY6Wnp2Pr1q3Ytm0bcnJy7O316tVDcnIyGjRoYA9sMnIzMO/XN2GY8yduPi7b97XUrY06Tz2DsN69ncIWIQS2/zkfa3+YBSFkaA0G3D72OdRt0dqn60lERERERETBhSFLOanMIcu69e2Qm3sVSYlvo1atu522/T2xB7phO47H3Yn6D31T7GMLWYZx506kL1mKjGXLYL5yxWm7JiGhIHBp0MDrcUwmE3bt2oVNmzYhLS3N3h4TE4MOHTrg5ptvhkqlAgCcST+DH/73KuJ/3YoWJwoe0or68ag55im3sOXk7h1Y9NG7yMnKhCQp0Pm+EbhlwJBiL1FNRERERERENzaGLOWkcocs7ZGbewWJiVNQu9Y9TtuWT74Dt1nW4Hi1W1H/v7+U6jzCYoFxxw7rpLnLl8Fy5arTdm3DBgjrkz+HS0KCx2PIsoyDBw9i48aNOHfunL3dYDCgXbt2uOWWW6DXW+dW2XphK36cNxFtl5x0CltUCfVR/cknncKWtIsXsOC9yUg5exoAkNixK257dAzUWucJd4mIiIiIiCh4MWQpJ5U5ZFm/Phmm3EtIbPwmate+12nbov8bjv45f+JERDvUG7fcb+cUFguyt2+3zuGybDksKSlO27UNGxbM4VK/nvvlhcCZM2ewceNGHDp0yN6uVqvRokULdOjQAVWqVIFFtmDB0QVYtPB93LbyOpqfLHiIaxo0QMyTTyDsttsgKRTINWZjyWfTcPSfTQCAanUTMPDZlxEeU81v15uIiIiIiIgqL4Ys5aSyhiwHUw7izN77oJTT0bjxZMTWvs9p++9TH8Md6T/ijL4J4p7bVCY1CIsF2f9ss87hsnwFLNeuOW3XNm6M8L59ENa7N7T13AOXlJQUbN68GTt37oTZbLa3JyUloUOHDqhTpw4yczMxY+8MbFk2C4PW5jmFLdqGDVD1CWvYAgCb5/+Mjf/7AQAQEhaOAeNfRFyTZmVx1YmIiIiIiKgSYchSTipryNJsdjO8XtOIKJVA40aTEBs73Gn7wk+fw8CrX+Kipg5qvLS3zOsRZjOyt22zzuGyfDksqalO27VJSdY5XPr0hiY+3mlbVlYWtm3bhq1btyIrq2BJ59jYWCQnJyMxMRHnss5h2vZpOL1hOYauk72GLcd2/IMln76PXKMRCqUS3UY8gha39ec8LUREREREREGMIUs5qcwhy2s1jaiiEmjc6A3Ext7vtP33mW/ijjPvIVVRBVGvnSjX2oTZjOytW62By4oVsDhMeAsA2iZJCO/T1xq41Kljb8/Ly8PevXuxceNGXL1aMO9LVFQU2rdvj5YtW2L3td149593IXYfxF3rZdzsFLY0RNUnnkBuk0T8PvUtpF44DwBo2v1W9Hzov1Cp1WV7xYmIiIiIiKhCYshSTipryPLK+lfQPPsnVFEJNGo0EXGxDzhtXzT3E/Q//ApyoIVu4mUvRyl7Ii8PWVu3ImPpUuuQouvXnbbrbrrJOqSoTx9o8m9/WZZx9OhRbNy4ESdPnizYV6dDmzZt0LpNa6y6tAof7/gYVY9c9Ri2RDz8ENbs344Tu3cAAGo2bIw7xr+E0CrRZX+liYiIiIiIqEJhyFJOKmvIMm37NNRK+QxVVQKNGr6GuLgRTtuXLZiD3ruetP7y6lVAGfheHCIvD1mbt1jncPlrJWTXwKVp0/w5XPpAE1sbAHD+/Hls2rQJ+/btg+1hrlQq0axZMzRv0xwLLy7Edwe+Q/1TuW5hi6ZhQ1xt3gTrD+8FJAmGqCq4Y/xLqNUosfyuNBEREREREQUcQ5ZyUllDlu8PfA/12Yn5IcuriIsb6bR99Yo/0H1D/hCi504A+irlX2QhRG4usrZssQ4p+usvyOnpTtt1N99sncOl921Q166NtLQ0bNmyBdu3b0dubq59vwYNGiChVQLmXZ6HFadWIPGMwFCXsAWxtbFLJ+G8XgOlWo2eD/0XzXrcVl5XlYiIiIiIiAKMIUs5qawhy9ITS5F2+EnEqAUaNngZdeqMdtq+adN6dFjWHwBgGbMLymj31X0qCpGbi6xNm6yBy8qVkDMynLbrmt9sn8PFEhWFHTt2YPPmzUh3CGZq1KiBqGZR+CXlFxxKPYTEMwJ3rxdoelK275MVqse/0WG4GGFAiz63o9uDj0CpUpXb9SQiIiIiIqLAKM53f35LDEJVQ6rCtn5PjiXHbbs+PMr+c/b1qwirwCGLpNEgtGtXhHbtCjk3F1kbNiBj6TJr4JKZiZzde5Czew8uv/MOQlq0QGLfPmh1zz04nJKCTZs24cKFC7h48SIuXryItmFt0bZJWyzSLcKkuBQknpFw7wYFkk7kwZCZjVaZ2UjXaXD0+s/45fRJDBj/EvThEYG+CYiIiIiIiKiCYMgShGL0MTiS/3NWbqbb9tCIguFBWempCCunukpLodEgrHt3hHXvbg1c1m9A+tIlyFy5CnJWFoy7dsG4axfw9v8hvFUrDO19G1LvuANbDh7EkSNHkJWRBWwBumu741rDa1gfvx6vx+Ui6bQSD27WIuFYNsJzctHq1CWkX1qKJfsPoePb76FGg0aBvupERERERERUATBkCUJVQ6rCNkYsMy/DbXt4eBQsQoJSEjBmpLptrwwUGg3CenRHWI/ukE0mZK1fj/QlS5G5ahXk7GwYd+yAcYd19aCOrVujXY8e2BdqwN7Dh2ExWRC1Lwo91T1xOv409tfZjxfrWMOWR/4JR+zhVITn5KLJ3sM4fdfdSB01EolPjoWkUAT4WhMREREREVEgMWQJQga1AYACgAVZeVlu2yP0GmRAj0hkwZSVVt7l+Z1Cq0VYz54I69kTck6OPXDJWL0aIjsbxu3bge3b0ViSkNi2LY63boW92dlADpB4NBFVtVVxqOYhHKxzCePrZKDpGQ0e3RqO6oevIsxoAj7/Ent/+Q3xL7+E8FtvY9hCREREREQUpBiyBCmlQgnAgguZ5yCEgCRJ9m0alQKX80OWvKzK2ZPFG4VOh7BevRDWqxfknBxkrl2LjKVLkbH6bwijEWLLFtTbsgVxKhXOd+2Cg7VqAaaq6HiyI06FnsKB6APYF2fEmLg0tDkfjuHLLah1IQvqy1dw/qlxuNqoIWLGjEFYz54MW4iIiIiIiIIMQ5YgpVOFACIXu6/sxisbXsGr7V+FTqWzb89WGABxBWbj9QBWWbYUOh3Cb7sN4bfdBtloRObaddY5XP5eA5XRiDorVyFWknC+dm0cvaU1JNRFbFYs/o38F4cjDuOfWtn4ZyTQ6WQEhi41olZqLnIPH8G5MWOhTUxE1Sf+y7CFiIiIiIgoiFTqb3+HDx9Gnz59YDAYUK1aNTz11FMwGo0+XXb27NlITEyETqdD06ZNMW/evDKutmKJCakGAJAA/H7sdzy45EFcyLxg325ShgIAhDHd08VvOIqQEIT3vg2x06ah0Yb1qP3hNIT17g2lVovYs2fRbcFC9Fq+AvVOX0DTa01w29nbEJtpXbprfd0sPP2YjM/66XEpXAsAMB06hHNjxuLEkDuRvmIFhCwXdnoiIiIiIiK6AVTanixpaWno0aMH4uPj8euvv+Ly5csYP348UlJS8P333xd62V9++QUjR47ECy+8gNtuuw0LFizAPffcg4iICNx2223ldA0CS6mw3vXtarbFXxk7cfDaQdzz5z14v+v7aFuzLUxKA2AGYAqOkMWRQq9HeJ8+CO/TB3JWFjLXrkX6kqWQ1qxB9IaNyDQYcLhRI0QktMZFQwL2RO9BqjYVa5rnYm0zCX22huL2f8yIycyxhy3apCRU/c8jUNeuDUgSAMn6XwnWoVqO/1B4O+BhW/526398PF7+ELFiHUuSrCV4ancYckZERERERBSMJCGEKHq3iuedd97BpEmTcOrUKVStWhUAMHfuXAwfPhwHDhxAUlKS18smJSWhWbNm+N///mdv6927N65fv47Nmzf7XMPZs2cRFxeHM2fOIDY2tuRXJgC2bB2AzMwDqF9vHI4rk/Dy+peRlZcFpaTEM7c8g4aLF6B95l/YFd4dLcYvCHS5FYKclYWMv/9GxtKlyFyzFiYhcKxBAv5t1BCHY65gX9Q+5KhyAACaPCUGbAzB7Sc0MFy4HODKy1lxghlP7flt3i5jzYz81O4UeJXjOWBtsl7P4tRW/PaCAMyXdh/O4cux7PedwzYPlytuu+dj+XgOl8t4a3c6ln2b6zng8/GKF6KW5DIe2vO3SZKn51dhl3G87eHb8SQGr0RERHTjK853/0rbk2Xx4sXo1auXPWABgDvvvBOjR4/G4sWLvYYsJ06cwKFDhzBlyhSn9vvuuw+jRo3C1atXnY55o8r/WAwBgZ51eqJev3p4avVTOJl+Eu/+8y4mm+MAAKq84OvJ4o3CYEBE//6I6N8flswsZK5ejSpLl6Lx0uU4VbMmkpq0wz91LuFwxGHkqi34tWsm/mqjwz17EtD3mgF5u/cE+iqUDyGs/xybvO1a9tUQUaAVJ5gpZnuJA1GPxwMCFrzmB1j+Cl2tV6+Q87ht89buw/l9PpZDu4dtxQ5d4e14Pp7H5TKlCl59PFaxAlT7Y7SYl/PUnr9Nkjw87n0NXn05lsTQlYgIqMQhy8GDBzF69GinNq1Wi4SEBBw8eLDQywFwC2GaNGkCIQQOHTqETp06+b/gisb+Zmf9mls/sj7m9p+Ll9a/hL/P/I0LFuvSzorc61h6cimk/P8pJEX+h0DY2ySp4L8AnNsc93Vo87hv/n+t5Ukej+/Lfh5rK2Ydjm0KKArabPtoJKj6dEd0nx6IysxEtTXr0GTZCrT5IxXbmrTEqsRLOBt6Ftf1Ofiq/Sn8eT0K4+8Zj55dh9hDCCFE/s0vCoIJ+zZv7Z4vU2S7PfQoyeV8bXc/llN7sY4Fh7Cm8GPZO+MVernitrtv89bu8VhOl/HW7us54OPxfGwXAgIezuPTZUrf7nYOoGzOI0T+w7H07VRKHm5Hb7cqb22iG5xDgONTOFPMdttnPb+0u4V0xTiWW33FPQ/yr2fxLlOuvV09XUeHIK5Y5/GwLeC9XZ0er16OZ9/mrd2H83g4Vnn0drVdPY/bvF7O+/E8Hktyf64KAHkWGbIsEKLTlOrlpCKrtCFLamoqIiMj3dqjoqJw7dq1Qi8HwO2yUVFRAFDoZdPT05GeXtCz48KFC173reiuZORCB+DEiY9w4sRH9vZBAAbFAcZrUcB1oInlKJrMuidQZVYaoQBiqgN1qwPd8Q8mXAF2pWvwTnQU9mm1OB+RimczPgb+/DjQpQafgvcSIh95eNAIYW0R+Vvz0wAp/3dP7bYjeb1MEZcvVntpLuva7nEf5+uP4hy3ol1PH/fxvE0E4Lb3/23kaZvvt5eoVNfL34/HSr1iREXgJbxm8EoUXHY002L4vF2BLqPMVNqQBUBByuhACOGxvajL2v4aXthlp06dijfeeKOYVVZMh65WQYtCRkXlRZiB6+VXz42ohSkXP5y/hEWhenwYFYnLqkr9dCMKbvl/fYEUrB/6mVQSOSlB8Fp24Z+Hdn/UVIzg1R/Xs0S1ltdtX8rQtcS1luT6+OE2Kk7oihIcP1DXq7j3ve08DF79T9zgHysq7be+qKgoe68UR2lpaYVOemvrsZKamorq1as7Xc5xuyfjx4/Hww8/bP/9woULaNu2bXFLD7hrWbmYvvMuNIxqjfva1kTtyBBojJdQ69jPCE+xzhsii3Ssq9ULGcoYAGYIyBCwwLrkkAUCFoj8nwHZ+rOw5O+Tv628nzxCAetLnTL/X8HPAkpAKCCghBAK+3Zh31eCgCq/TQFZWNusx7C+oto+AwiXr1iOvwun/1rffPMuVMGQCwqcDz0BqDP9f72JKjNJeGgs+PTjIUr3ur/3lxzHT0rFr0dyeWYXfRyXYzjW5vCJ2+thnDYUdvt4qtXTL56O4Xp+4dzgrQaPRRdSR5HXBQ63ecF2T6eRPF0fb/UUeh851+F23xRyu3k+rKd6PFxXbzVJwvP1dTuOl+t1g39QrXQkl/8SOXB/tavgvLwFWRU82AvdzdO3aY83gORhm2+fApwvW/Czr6/izgeWvLQXbBOeCrEPOwYkSNbtjj/D9nYnCtoBQC54+xG2M9j++O9wfYSQIEMBGUpYHP8r5f8TKghJAQuUkCFBhhIyFLBICshCgkVSFlwDh4Cs4COFS49VUfDe5ByqCod9rL9LAlDKFus3LiGglGUohAylLEMJAYUsQyms/xRChlJYoAwv+B5+I6q0IUtSUpLb3CsmkwnHjh1zm6vF9XKAdW6WxMREe/uBAwcgSZJTm6vw8HCEh4eXsvLA23/+OsxCjYPXGmNA8w6I3PYRsOkzQM6z7hDbBuj7LqrVblXicwghIEQuLJZsmM3ZsFiyYLFku/yztpktjtvz/2v2vF2Wc/x0K/hGkjRQKvVQKfVQqgxQKkKgtP2s1Of/MxTsozQ4tV2/JLBq9kmoocVd3QYhKbkWrLGMDPucHrD1pJKt2+ztLj9D2C/j+LN1P7ngWE77yfYX6oJ22eXycLh8UedxaM/f5niOgsvIDj/DpRbb5QEI2elYHs+ffzzrYdyvc0GglX8Op8vDuRb7fkX87OG6Oddi+9n5uhVc3vk2Ldjmcp0dt7lcZ+vl4XJ523ng4b4X+f933M/LfSxc63K5zvm3tXA7Bxwu7/h4hXstsM0t5P64JiLyP+vfxyVJ4fCzrd02t5r9b+gu+0mef4YE+3wDTj8r8g/jeBmFw89wr8Wettou73geAPn7ej9n/v6Sc7vzeeCwTeHws3M9BceCtZbCzuntOkMCbPP0WW9Qp/aCr5C2ml3PA4fLe75ubtfZrR6H6+xye1v/n3+/OF7e8b53uZ7utSjs163g/A7X2elyjucBXK9zQbuX6+zys7XG4j3G7PNfuD3evT3GFQ7PEefbkBMV+48QAjmyQIbZgnSLBelmCzLMcv5/rb+nWyxIz7Mg3ZSH9FwL0vPM1n0sFmTIMjKEQF4Z3SVKWSDUDISaBQxm689hAgiDhDBJgTCFhDClEuEqJcLVSoRr1QjXqhARoka4Xo0IvQZhBjWUejUktbJsiqyEKm3I0q9fP0yePBkpKSmIjo4GAMyfPx8mkwn9+vXzerl69eohMTERP//8MwYPHmxv//HHH9G2bdugWFlo//l0AAKjw7YicuZ4IPOidUNodaDXG8DN9wCK0nV+kyQJkqSFQqGFWh1V+qLzCWFxCmrMliynQMZ7eJP/s7ngcrLFaL28JRuwfbF0O18uzOZcmM1pgKlkNdfrbf1vigDWbyjZMYjoRuKPL4Mu7V6+GBX+4drhg7rTF6MK8GXQ6cuM53rcvrQU8UXZ8QuT+3WGQ82B+jLocp3za3W/zs7Xz9uXNLcvahXyy6BLu+t95+Vnx/PwyyARlRUhBLJl2WMo4tiWkR+epOdZkJFnDUnSzRZkWGRkyDLySluIl5c5lSwQmh+MWAMSgdA8gVALECYkhEoSwhUKhCkVBSGJRo1wnQoROjUi9GroQ6wBiUKvgiJEDUnD11V/qLQhy6OPPopPPvkEAwcOxKuvvorLly9j/PjxGD58uNNwoYceegizZ8+G2Wy2t02aNAn33HMPEhIScOutt2LhwoVYvnw5li5dGoirUu7+b8khjFfNw9i8BUAeAIUaaP840GUCoKvYPXUkSQmVKgwqVZjfjimEgCyb3AIZs0sw47jd7CHUsfbAsV0uG0Lk+q3GwPH0odmx3fHDMTx8uK54XwYd6yn0y6D9PHCpueALk+N+FebLoLcvM96us9v94XCd3c7j2F6Bvgx6vM7ezlP0Y8z9PB7O4fVY/DJIREQUaEIIZFvk/N4jckFAYg9FPLXlByl51p8zLTLMRZ+qRNRyfiCS34uk4B8KwhJICFMoEK5UICw/JInQqBGWH5KEGFTWgCREZf2X/7OkVUJS8DNHIFXakCUyMhKrVq3CmDFjMGTIEOj1etx777145513nPazWCywWCxObXfddReys7MxZcoUvP/++2jQoAF+/vln3HbbbeV5FQJqsCK/S0WdZOCOj4GqDQNbUABJkgSlUgelUgcg2i/HNOda8MMb65Gdno7YJB26P1jXPtSpIn0ZLPqLIhERERFR+ZGFQJZFLghAzBakW1xCEZc2+3/z2zLMFliKPlWJaC0if3iNQyBidmnL/xcmJIQpFdYhNxprT5IIrQohIfnhSITKHpJIDkGJQqeCpORn8cpKEgUD6qmYzp49i7i4OJw5cwaxsbGBLsdn+09dRJNvEyFBAPfNAxoFT7hUXrYvPYnNC45DkoB7XmmL6NqhgS6JiIiIiKhMyUIg0+IyvCY//PCtzToUp6y+oNoCkiJ7kTj+LsOhJ4kK2hC1czASosofbuPco0QRooKk4vpDN4rifPevtD1ZqORu0lyCffLJmEYBreVGlJ2ei+1LTgEAkjrVYsBCRERERBWeRQinHiFuAYhtMtZC2jItnuc59IeQIgIRg+P2PCDU4rDdAoSpldCGqAuCEdu/cM9BiW0/Sc0hv1Q8DFmC0ZXD1v+qdEBEXGBruQFt+eM48kwWqHVKtBtQP9DlEBEREdENziwLjwGI01wjDr97assqw4BE7xqA2FezcelR4tqLxGEYjkoAkk7p1FNEEaKCIrQgJCkIUBznKsmfp4RBCZUThizB6Gp+yBLdEFBwqS1/SjmXiYPrzwMAWveJhz5cE+CKiIiIiKgiy5OF0+SrRYYi9hVubNtkGOWyCUgkIaD3dViNS4hi+6c3A47fOCSNwh6CSLYeJJ56k7gGJToVJ3SlSoEhSzDa+b31v3KpFxQjB0IIrJ93BEIAYVV0aN6TvYSIiIiIbmQmWS4YNmOfkNU9FCnoUSK7rWZjlMtmBhKFAAyW/BAkT0ZonvvErO69SNwDEo+ziqgk5xAk1GUITogKkmuPE33+hK6cp4RucAxZglGGtacFrhwKbB03mFP7UnD2UCoAoMOQBKjU7CVEREREVFHlWBx7ijisXuPQS8Q1FHFtM5VhQBIqA6GWgrlFDCa5oPeIx4lbnXuR6C1Aof0+FJJzABKucpmvRO1hrhLbPCX8nEvkDUOWYHTrJGDT50DvtwJdyQ3DYpGx8dejAIAa9cPRoHW1AFdEREREdGMSQsAoC+fley0uQYmn3iP2AMW6X24ZLbKqAhAqJITZQpL8UMSQK1uDEpPsvtyvS2gSUlRAYiMBki4/EHHrTeIckriuhCNpOE8JUVlgyBKMOj5l/Ud+c2DdeaRezAYAdBzakG9YRERERB4IIZBtkd1Xr7G4hCFOPUoKwhNbcGIuozV+1QDCICEUDiGJBTDkCoTmhySGHBmhORaHOUlsQ3KsP2tlHwMSB5JW6bzSjcsKN85zlTgMyeE8JUQVDkMWolLKycrD1j9OAAAatqmOGvUjAlwRERERkf8JIZCVH454DEW8Lf1rcZ6bxFJGAYlWkhAmSQiVFAgTEsJEQU8SQ541JAk1CRhyLDAYzdBny9Y2hyWASxKQ2EhqBRShLksE69XuQ208hSVKzlNCdKNgyEJUStuXnEROVh6UagXaD+KSzURERFTxyEIg00MAYmsrGE4jOw/DcRliU1aL/OoUEsKVSoRJEsIkBQwuIUlonkBorsjvSWKBwWiBIdsMfZYZoSbrdo0/whul5ByAOIQkzuGJ+z6c0JWIAIYsRKWSdjkbe1afBQC06BmH8OiQAFdERERENxqLEMh0CUA8hSKelv7NcAhTyqgDCUIUCoSrFAhTKREmKRAu2YbbSAiVC4bS2OckyZGhN1oQmh+S6DPNUJn8GN9IcA5GXFe5cetZonaY0FXBYd9EVCoMWYhKYdP8Y5AtAiHhGrTqEx/ocoiIiKiCMcvCJfCQXVaqKWhzWtHG4hyQlBWDUoFwlRJhSqVTUBImJISK/JVt8idkNeRag5LQHAsMRhmGbDNCMs1QGnMhG80QORa/1ibplJ6H3XiYxNVxkldJo+Q8JUQUMAxZiEro/JFUHN95BQDQ/o760Oj4dCIiIrqR5OUHJM49ReT8lWy8hyKObdllGJCE2gISldI61EZVEJiEKWw9SRyG2+Q5DreRoTeaIWWbIRtzIYxmyPn/itvlpbBoRdIo7CGI9+E2DiGJLUDRqSApGZQQUeXDb4VEJSBkgfXzrEs2R9c2IDG5ZoArIiIiIke5slywKo2nAMSl3T6Jq8Oyv0a5bAISCUCYSpHfe0RZEJSolAjLD07C83uU2EMSs4DeZJ2o1ZAjIyTHAkWGxRqMZOdBNubYQxLZaIYvs8vm+lqwSnLuLeJhtRvJy5AczlNCRMGGIQtRCfy79SKunM4AYF2yWcEuqURERH6TY5Gdwg5bUOI0vKaQtgyzBTly2cxAogCsQ2pUCoQrXQISlRLhSoX993CVEmEKhXWojbmgJ4k+xwIYLU6hiJxtdPpdGM0QeZ5DHgEguwSFOwYlkltQ4iVA0asgqZWlvNWIiIIHQxaiYsozWbB5wXEAQN1m0YhLqhLgioiIiCoGIQRyZOESgLisaGNxCUU8tOWKsglIlBLyh9XYQhHH+UgcAxPnXiahCgXCLNbVbXQmC0SOrQeJGfJ1W0hichpyYw9LTM6DaXJRjB4kriRA0noaaqMqPECxzVPCCV2JiMocQxaiYtq54jSy0kxQKCQk39kg0OUQERH5hRAC2bLsMRTJNDss8+spPHFoyyujgEQtSfZQxDEoCfXYo8RDm1KCziysAUl2QW8R28/Wfw69SRzaRY4ZQgAZsP4rLUmrdB9W42kVHNchOToVJ3QlIqrgGLIQFUNmqgk7l58CANzUtTaiahgCXBEREVF+QGKxTcjqsqSv1zbnoCTDYoG5jNb41UhSQQ+R/JDEqdeIW5vSLVDRKSRIkgSRZ3ELQeR0288mp+E2jvukGs2AH4cQSWqF80SunlbB0as87iMpOU8JEdGNiiELUTFsWXgM5lwZWr0KbfvXC3Q5RER0A5CFQJbFoaeI2YJ0i0so4tCW4SE8ybBYfJnntER0Cslh9RqHUMRLW5hDm+13nUuoIMyy27Aa2WiGyHaevNUWklw3mpFqzLNO6OrPJEgpuYck+UGJWzjislSwpGZQQkRE7hiyEPno8ql0HNp8EQBwS7+60IWqA1wREREFmiwEMi0uw2vMFmT43GbtTVJG+QhCbAGJw7wj9nlInHqPKJznJHEISjQKz2GCkEVBjxGjGXKGdSlg114mmdlmpNv3swYlItePq/ZIcB5y46lHiZchOZJGwXlKiIjIrxiyEPlACIENv1iXbI6ICUGzbrEBroiIiErLIoRDrxAPAYhZ9rz0b35bhtmCTEvZBSR6pSI/7PAUgCichtZ42i9MqYS6iPk7hBAQpoI5SuTrDksBZ5thNJqR5drjJDs/KMmxFHrs4pK0SpfJWtXuwYm9R4naeUJXzlNCREQVBEMWIh+c2HUV54+kAQCShzSAUsUuwkREgWSWhVMAkmEuWPLXaUnfQtqyLH7sTeEiVKlwC0Wce5S4LPOrdB9yo/IxOBBCQOTlD7/JNEPkT96am21GjochOXJ2ntMqOP5MiSS1wh6USIUuC+wSoOhUkJQMSoiIqPJjyEJUBItZxobfrL1YajWMRL0WVQNcERFR5ZYnC6fJV4sMRZyW+LW2GeWyCUgkuAQk3kIRlRLhSs9toSollCUYgmKfpyTdBIvRjDzXFW489CaxByX+nJBFKbnNP+JxIldPw3H4RwgiIgpyDFmIirD377NIv2IEJKDTXQ05dpuIgppJlguGzbgt3+s+xMa+n8M+Rj+u8OJIAViHyXhc0rcgFCkIT1yG4aiUCFUqoCjF67ywCMjZZuTZhtR4mMTVbdiNLUTJ82NwpIBTSCK5DbdxCVEcep9Ias5TQkREVFIMWYgKYczMxT+LTgIAEtvVQEydsMAWRERUCjkWx54iDqvXFBKKuLaZyjAgcVrSV6l0C0A8hSKOgYpB6Z9wQMgCIsfDMBuHoMQ+iatLcCJMfpynRAIkrWso4h6SSB7aJa2SQQkREVEAMGQhKsQ/i04i12iGSqNAu4EJgS6HiIKUEAJG2WGSVnvvEdltpZp0swWZ+aFIQXhi3S9XlE1AopLgsnqNw/Aatx4lzr1MbL/r/RSQ2AghIHItHoIRxx4leZ4DlBw/z1OiUbr1FvG0JLBbUKJTcUJXIiKiSoYhC5EXqRezsG/NOQBAy9viERqlDXBFRFQZCSGQLcvOw2vsAYinNufwxBacmMtoCRuNJDmFHU5hiENw4hieOO+nRIhCKrNeEyLP4nm4TbZzSOIeoJgBf/a6USk89CLxMpGryz6SkvOUEBERBQuGLERebPz1KIQsYIjQoOWtdQJdDhEFgBACWRbZeyjibelfh14mGRaLX+ckdaRVSA69RxyG0ri0ufcoKQhQdOUQAAiL7HFOEuEyeaunMAVmf85TInkMSSRPk7i69DKR1AxKiIiIqGgMWYg8OHPwGk7uTQEAtB+cALVWGeCKiKi4ZCGQ6RKAZFhchteYLUh3aHPtZZJhtqCsFvkNUUguq9c4hyJuK9p46GWiVZTfF3/7PCVOQUme114mwmEfkevHW1GC+0SuXla7cV0FR9JwQlciIiIqWwxZiFzIssCGX44AAGLqhKFx2xoBrogo+FiEQKZLAOIpFPG09K9tW6ZF9ue0Gk5CFIqC3iBOAYjLkr6elv5VWkMSTTkGJDZCCAiTxWNQIjytfuOwCo7I8eOErgAkrdJjrxGpqOE4WiXnKSEiIqIKiyELkYtDGy8g5VwWAKDTXQ34YZ6omMyycAk8ZJeVajz1KHFe9jfTUlb9RwCDUlFoAOItFHHsYaIO4OuCEAIiT3YIRjxP3uo0LMe2X44Z/uyaI6kL5imRXCdwdZ3E1bGniU4FScnXViIiIrrxMGQhcpCbY8bm348DAOq3jEGthlEBroiofJll4RR2OAYgTsNuXEIRx7bsMgxIwpSK/Elabb1HXJb09dTmsPRvmEoJZQUZLiLMslNPEc9LBJs97uPXSV6UkkMg4mG4jb6Q4TgqzlNCRERE5IghC5GDHUtPwZieC4VSQofBXLKZKpdcWS5YlcZTAOLSnpHfw6RgPxlGuWwCEglAmErhYaWaggCkqLZQpQKKChKQ2AiLgJzjMKSm0B4leU5zlYg8/89TotCrvcxV4vi72qHniXVCV85TQkREROQfDFmI8qWnGLHrrzMAgJu7xyKymj7AFVEwMcmyUxhiC0qchtwU0pZhtiDHn8vVOlAATqvSOAYloSolwpUuw2s8tBkqYEBiI+T8eUo8Db2xr4LjMMmrQ3giTH6ep0SndF/lxiEokRyDEsd2rZJBCREREVEFwJCFKN/mBcdhMcvQGdS4pV/dQJdDlYQQAjmycAlAXJb0tbiEIh7ackXZBCRKCR5XpXHvUeKpl4kC4Uol9MqK39NBCAGRK9t7i7gNt3EMSVznKjGa4c8ZciWN0ksw4qFHieN+OhXngCIiIiKq5BiyEAG4ePw6jvxzCQDQdkA9aPXqAFdE5UEIgWxZdgpFrBO0ukzK6ik8cWjLK6OARC1JBfOLFBGUhOYHIk5DblQK6BUVPyBxZJ3Q1duywHnu4YnDPvBnTx6VVBCCFLLajeQanug4TwkRERFRMGPIQkFPiIIlm6Nq6NGkc60AV0S+EEIg22KbkNVTKFJ0UJJhscBcRmv8aiTJeUlfpUuvEbc2pVugolNIlSogsREW2S0EES5BifsSwflBidmP85QoJLceJM7zlahdJnV1mNBVrfRfHUREREQUNBiyUNA7uv0yLh5PBwAk39kASiX/Cl3WZCGQZZGdlvRNd1vS18Myvw7hSYbF4tcFVhzpFJLDSjUuS/oW2qa0T+6qq+SPIyELiBwPvUk89DIRrvOU5PpxnhIJkHSehtqo3HqauPYqkTScp4SIiIiIyhdDFgpq5jwLNv12DAAQlxSF+KbRAa6o4pOFQKbFZc6R/EDEtzZrb5IyykcQolBY5xJRKRGqdBle49R7xNPSv9bwRKOo3AGJjRCOE7o6ByXC6ClAceh5YvLzPCVapctQG2tI4rZEsOtwHK2S85QQERERUaVRopBl0qRJePjhh1GrlvuwigsXLmDGjBl47bXXSl0cUVnbvfIMMq7lQJKAjkMb3vB/9bYIUbB8r6cAxCx7XvrXYkFm/u+ZlrILSPRKRX7Y4SkAUTgNrfG0X5hSCfUN9oVcCAGRJ3sIRbzMW2KfsyQvf54S/9UiqRUuPUbUHoIT114laus8Jcob634hIiIiIvKkRCHLG2+8gT59+ngMWc6fP4833niDIQtVeNnpudi+9BQAIKlTLUTXDg1wRYUzy8JhXpH8YTMW5+E1RbVlWfz4jdtFqFLhMRRxbAt1bFM6D7kJUyqhusECEkfC7DpPiXNI4jaZq8NywX4dF6WU3HqLuAUjrr1L8vfhhK5ERERERIUrUcgihPD6F/8LFy4gMjKyNDURlYstfxxHXo4Faq0S7QbUL/PzXc8zI9XsYyjitMSvtc0ol01AIsElIPEQgBQEJZ7bQlVKKG/wXkAAICwCco7jPCTee5PYh+TY5i3J82eXEhQEI669STwEJZLDBK+SunKtNkREREREVJn4HLL8+OOP+PHHHwEAkiThmWeecQtTcnJysG3bNnTs2NGvRRL5W8q5TBxcfx4A0LpvPPThmjI936enLuHN4xf8flwFYB0m43H5Xu+hSJjDfqFKBRRB9KVbyA7zlHhZ7cZbgCJMfpzQFYCkU3oedmPrVeI0V0nBJK+ShvOUEBERERFVRD6HLLm5ucjIyABg7cmSlZUFpdJ5iUuNRoMHH3wQzz33nH+rJPIj25LNQgBhVXRo3jOuzM836/xVt3alBPtkq7YVaZzCEJUSYUqFe5tDoGJQBmevBCEERK7sFJK4D7dxD1Bs+/h1QleNwh6CuK5u4/yz+7AcBiVERERERDcWn0OWESNGYMSIEQCA7t27Y/r06UhMTCyzwojKyql9KThzMBUA0GFwAlRqZRGXKJ2TxlyczckDAHx5UzzaRYQiTKWAXhGcAYkjkSe7zT/iGpJ4DE+Mfp6nRCW5BSGuK954G5bDeUqIiIiIiMimRHOyrF692t91EJULi0XGxl+PAgCq1wtHg1uqlfk516Rae4AZlAr0qxp5461+Y5Hdh9tke+9N4jgEB2Y/zlOigFtI4jSRq7cARa+CVMZBGxERERERBYcShSwAcOjQIfz22284e/YscnJynLZJkoSZM2eWujgifzuw7jxSL2YDADrdVT5LNq+9Zg1ZkiNDK2zAImQBkeMegjitdONpBZxsM0SuH+cpkQBJ52WFG28Bim1CV40y6HsGERERERFRYJUoZJkzZw5GjRoFjUaDuLg4aDTOk4byiw5VRKbsPGz94wQAoOEt1VCjfkSZn9MiBNanWUOWrlXCyvRcQrhO6Oo4D0khq+BkmyFMfp6nRKv0MpGr9+E4ihAVJB3nKSEiIiIiosqrRCHL5MmTMXjwYHz77bcIDQ31d01EZWLbklPIycqDUqVA+8EJ5XLO3enZSM8fEtM5quiQRQgBkScX9Bhx7U3iMUAp2AZ/rhKsVrgMt7GFI4UNyckPS5Scp4SIiIiIiIJPiUKW8+fPY/r06QxYqNK4fiUbe1adAQA07xWH8OiQcjmvbT6WGhoVYo9cR0ZWSpEBCsx+7FKilLyGJG7hiMsqOJKaQQkREREREVFxlChk6dKlC/bt24eePXv6ux6iMrHpt2OQLQIhYWq07hNfbuddmx+ytEuVkfrH4ZIdRILb0r8KLyvdWHuWqB0mdOUKRkREREREROWlRCHLW2+9hQceeAA6nQ633norIiMj3fapUqVKaWsj8ovzR1JxbOcVAEC7O+pDoyvxfM/FkmW2YNt16yS7txzLAgAowzVQhKp96FHiEJRolJynhIiIiIiIqBIo0bfN1q1bAwAef/xxr38lt1j8uOIIUQkJWWD9POuSzdG1DUjqWKvczr3pehbyhHXoT5sUC5SRWtSYcAvnKyEiIiIiIrpBlShk+eabbzgEgSqFw1sv4spp65CdjkMbQlGOPULW5S/d3CDDgqq5AmG9azNgISIiIiIiuoGVKGQZOXKkn8sg8r88kwWbFhwHAMQ3i0ZcUvkOYbNNetsuxQKFQQV9mxrlen4iIiIiIiIqX6X6s3pqairWrVuHuXPnIjU1FQCQk5MDWfbjOrJEJbTrr9PISjNBUkjoeGeDcj33JVMeDmXlAADappgRmlwbCo2yXGsgIiIiIiKi8lWikMViseCll15CXFwcunbtigceeAAnTpwAAAwZMgSTJ0/2a5FExZWZasKOZacAAE271EZUDUO5nn9dfi8WtSzQOlMgtEPNcj0/ERERERERlb8ShSyvv/46Pv30U7z33ns4cOAARP7kngBwxx134I8//vBbgUQlseX3YzDnytCEqNDm9rrlfv41V9MBADenWVD1lppQ6NXlXgMRERERERGVrxLNyTJr1ixMmTIFjz/+uNsqQgkJCTh27JhfiiMqiSunM3Bo80UAQJv+dRESqinX8wshsOaKNWRpe82C0Ltrl+v5iYiIiIiIKDBK1JMlJSUFSUlJHrfJsoy8vLxSFUVUUkIIrJ93BBBAeEwImnWNLfca/k034jKs8xJ1jQmHKkJb7jUQERERERFR+StRyNKoUSOsWLHC47bVq1ejadOmpSqKqKRO7L6K80fSAAAdhzSAUl3+Syb/te8CACAsT6B9hzrlfn4iIiIiIiIKjBINFxo3bhweeeQRqNVqDB06FABw9uxZbNq0CR9//DFmzZrlzxqJfGIxy9j461EAQK2GkajXomq51yBkgTVXrgMRCrTLU0BXvXwn3CUiIiIiIqLAKVHIMnLkSFy7dg0TJ07ElClTAACDBg2CXq/Hm2++ibvvvtuvRRL5Yu/fZ3H9ihGQgI5DG0CSpHKvIX3/VWwzWM/bPT663M9PREREREREgVOikAUAxo8fj//85z/YuHEjrl69iipVqiA5ORnh4eH+rI/IJzmZedi2+CQAILFdDVSLL//HoRACG/85C2M9a8jSMyGm3GsgIiIiIiKiwClxyAIAoaGhuO222/xVC1GJbV10AqZsM1QaBdoNTAhIDaZj17FBzgWgRaxSiXhd+a5qRERERERERIHlc8jy22+/oUePHoiMjMRvv/1W5P5DhgwpVWFEvkq9mIV9a84BAFreFo/QqMCs5pOx5gy2RFufUl2rRQRkuBIREREREREFjs8hy9ChQ7F582a0bdvWPtmtN5IkwWKxlLo4Il9s/O0YhCxgiNCg5a2BWc0n92wGUk6kYX+9UABA1yocNkdERERERBRsfA5ZTpw4gZo1a9p/JqoIzhy6hpN7rgIA2g9KgFqrDEgdGWvOYlsVFWRJggSgU1RoQOogIiIiIiKiwPE5ZImPj/f4M1GgyLLAhnnWJZtj6oShcbsaAakj76oRxn1XsSXROkypWVgIqqhLNd0RERERERERVUKKklxo9+7dWLx4scdtixcvxp49e0pVFJEvDm28gJRzmQCATnc1gKQIzBwomWvPAgLYGpM/H0tUWEDqICIiIiIiosAqUcgybtw4bNq0yeO2rVu34plnnilVUURFyc0xY/PvxwEA9VvGoFbDqIDUYUk3IWv7JVzUSTgVYn06da3CkIWIiIiIiCgYlShk2bVrFzp27OhxW4cOHbBjx45SFUVUlB3LTsGYnguFUkKHwYFZshkAMtafBywCW2qoAQA6hYRbwg0Bq4eIiIiIiIgCp0Qhi8lkQm5urtdtOTk5pSqKqDAZ13Kw668zAIBm3WMRWU0fkDpkoxlZWy4AAHY0sE502z4iFDpliZ5WREREREREVMmV6Ntgy5Yt8d1333nc9t1336F58+alKoqoMJvmH4MlT4bOoEabfnUDVkfm5gsQJgtklYRNWhkA0IVDhYiIiIiIiIJWiZZAefHFF3HHHXegf//+GDVqFGrVqoXz58/j22+/xbJly7Bw4UJ/10kEALh44jqO/HMJANDm9nrQ6tUBqUPkWZC54RwA4EzbGFwzGwEAXbh0MxERERERUdAqUcjSv39/zJ07FxMmTMDdd98NSZIghEBsbCzmzp2L/v37+7tOIgghsGHeEQBAVA09bupSK2C1ZG2/BDkzD5CAHQ1DgYtGRKtVaBIaErCaiIiIiIiIKLBKFLIAwD333IN77rkH//77L1JSUhAdHY3GjRv7szYiJ0e3X8bF4+kAgOQ7G0AZoLlPhEUgY621F0vIzTFYb7LOQdQlKhQKKTDLSBMREREREVHglThksWGwQuXBnGfBpvnHAACxiVGIbxodsFqMe6/Acs0arKg718KWYycAAJ05HwsREREREVFQ8zlkmTp1KoYPH47q1atj6tSphe4rSRLGjRtX6uKIbPasOouMlBxIEtDproaQAtRjRAiBjL/PAgB0jaOwSy8hRxYAgK5RDFmIiIiIiIiCmc8hy7PPPotOnTqhevXqePbZZwvdlyEL+VN2ei62LTkJAEjqWAvRtQM3uWzO4VTkXcwCAIR1jcPa1AwAQAO9FrV1moDVRURERERERIHnc8giy7LHn4nK2tY/jiMvxwK1Vol2d9QPaC0Zf58BAGjqhEFTLxxrt10EAHRhLxYiIiIiIqKg5/PMoa1atcL+/fsBAJMmTcL58+fLrCgim5RzmTiw3vpYa903HvrwwPUWMZ1KR+4J68S7Yd3icC3Pgr2ZtqWbGbIQEREREREFO59Dln379iEjwzo04o033sDZs2fLrCgiIH/J5l+PQgggtIoWzXvEBbQeWy8WVTU9dIlVsD4tAwKAUgKSowI3hImIiIiIiIgqBp+HC9WtWxdff/01cnJyIITAzp07kZOT43X/Ll26+KVACl6n91/DmQPXAADJgxtApVEGrJa8S1nIOWitJaxrLCSFhLXXrKFjqzADwlWBq42IiIiIiIgqBp9DlokTJ+Khhx7Ct99+C0mS8Pjjj7vtI0kShBCQJAkWi8WvhVJwsVhkbPjlCACger1wNLilWkDryVhj7bmljNBC3yIGQgisyZ/0tnMV9mIhIiIiIiKiYoQs9913HwYMGIBjx46hVatW+Pbbb9G0adOyrI2C2IF155F6MRtAYJdsBgBzag6yd10BAIR2qQ1JqcCJbBPO5uQB4NLNREREREREZOVzyPLxxx9j2LBhaNGiBUaMGIEePXogLi6wc2TQjcmUnYetf54AADS8pRpq1I8IaD2Z684BsoBCr4KhTQ0AsPdiMSgVaBVuCGR5REREREREVEH4PPHtuHHjcPLkSQDAd999hwsXLpRVTRTkti05hZzMPChVCrQfnBDQWixZecj6x7pMc2hyLSjy54WxzceSHBkKtSJwvWyIiIiIiIio4vA5ZImOjsbx48cBwD7vCpG/Xb+SjT2rrav4NO8Vh/DokIDWk7nxPESeDEmjgKFDLQCARQisT7OGLF2rcKgQERERERERWfk8XKh///548MEH8cILL0CSJAwaNAhardbjvpIk4dixY34rkoLHpvnHIJsFQsLUaN07PqC1yCYLMjeeBwAY2taE0qAGAOxOz0a6WQYAdOF8LERERERERJTP55Dlq6++QocOHXDgwAF8/PHH6NixI6pXr16WtVGQOX8kDcd2WCeYbXdHfWhCfH54lomsrRchjGZAKSG0c217u20+lhoaNRrqPQeNREREREREFHx8/harVqvxn//8BwCwcOFCvPzyy2jevHmZFUbBRcjCvmRzdG0DkjrWCmw9ZhmZ66zLNutbVIMqoiBMWZsfsnSpEsphc0RERERERGRXoq4CJ06c8HcdFOQOb72Iy6es4UXHOxtCEeDJZLN3XYYlPReQgLCusfb2LLMF265bl5bm0s1ERERERETkyOeJb11dvXoVL7zwAnr27IlGjRph//79AICPPvoImzdv9luBdOPLy7Vg0wLrpMrxzaIR16RKQOsRskDGGmsvFl2TaKir6e3bNl3PQp4QAIAunPSWiIiIiIiIHJQoZNmxYwcaNGiAuXPnokaNGjh27BhMJhMA4Ny5c5g2bZpfi6Qb264Vp5GVZoKkkJA8pEGgy0HOgRSYrxgBOPdiAQqWbk4y6BCjUZd7bURERERERFRxlShkGTduHJKTk3Hs2DHMnj0bIv8v+wDQrl079mQhn2WlmbBj2SkAQNMutVGlpiGg9QghkJ7fi0VbPwLaOuFO2wvmY2EvFiIiIiIiInJWopDln3/+wdixY6FWq90m/oyJicHly5f9UlxRFi9ejJYtW0Kn06FBgwb4/PPPfbqcJElu/2rUqFHG1ZInm38/DnOuDE2ICm1urxvocmA6fh15Z6xBSli3OKdtl0x5OJSVA4DzsRAREREREZG7Ek18azAYkJ6e7nHb6dOnER0dXaqifLFp0yYMHDgQDz74IKZOnYoNGzZgzJgx0Gg0ePjhh4u8/JgxY3DffffZf9doNGVZLnlw5XQGDm26AAC4pV9dhIQG/j7I+PsMAEBdywBtw0inbbZeLBpJQrvIwPa4ISIiIiIiooqnRCFL79698eabb6Jnz56IjIwEYO0dYjQa8dFHH6Ffv37+rNGjSZMmoVWrVpg5cyYAoHv37jh9+jRee+01jB49GgpF4Z106tSpg/bt25d5neSZEPlLNgsgPCYEN3eLLfpCZSz3XCZMR9IAWHuxuPbSsoUst0QYYFAqy7s8IiIiIiIiquBKNFzonXfeQXp6Oho2bIi7774bkiThlVdeQZMmTZCSkoI333zT33U6MZlMWLVqFYYNG+bUPnz4cFy4cAE7d+4s0/NT6Z3YfRXnDqcBAJKHJECpLvFCV36Tscbai0UZrUNI06pO24QQ9klvOVSIiIiIiIiIPCnRN9vatWtj165dGPP/7N15WFXl+v/x92YzyowigjilYZqamvNI4pQzppYeLSy11KzsWFnmESyHyjx2NH9ap9IyzaGszCxLA81Zv1rHsiwVjzgrg4BMe7N/fyD7uANlZoN+XtfFdbnXetZa91oKtW6e574nTeLs2bPUr1+fy5cv87e//Y39+/dTvXr10o7TxrFjx8jMzKRRo0Y22xs3bgzAkSNHCjzH3LlzcXJywsfHhwcffJD//ve/ZRKr5GU2ZbPz0z8BCLrThzua+9s5Isi6lEbafy4B4NklGIOD7SyW36+mcz7TBEBnP49yj09EREREREQqvmItFwLw8fEhKiqKqKio0oynUBISEqwxXM/X1xeA+Pj4mx7/8MMP069fPwICAjh8+DCvvPIKnTp14qeffrKeIz9XrlyxqUVz9uzZYt7B7e1wzGmSrrVI7jikQZ5lOfaQsi0OLODg6YR7y4A8+7fHpwDg42jkHs8q5R2eiIiIiIiIVALFTrIAxMbGsmPHDuLj46latSodO3akTp06xTpXUlJSoZIW9erVs/75Ri/nBb20L1++3PrnLl260KlTJ1q2bMm7777L888/f8Pj5s+fb5ek0q0kPSWLfRtPANCwXQ2q1/Eq4IiyZ76SSeqB8wB4dKyJIZ+lSzHX6rF09PXAWAGSQiIiIiIiIlLxFCvJYjabeeKJJ/jggw/Izs62bndwcODRRx9lyZIlBRae/av169czevToAscdPHjQOtskd0ZLrtzPN5uNkp9mzZrRsGFDDhw4cNNxzz77rE3norNnz9KmTZsiXet2t2/jCTKumnB0cqDdwPr2DgeA5B2nwWzB4GLEo11gnv2Z2dnsTMyZydJF9VhERERERETkBopVkyUyMpIPP/yQV199lRMnTpCWlsaJEyeYNWsWH374YbFme0RERGCxWAr8at68OfXr18fZ2TlP7ZVff/0VIE+tlsKwWCwFjvHy8iI4ONj6FRiY94VcbizhXCqHY04D0KJnbTx8XewcEWSnmUjdnTODyqN9IA6uefOO/3flKlfNOcnErn5KsoiIiIiIiEj+ipVkyU2kTJ06lTp16uDi4kKdOnV44YUXiIyMZNmyZaUcpi0XFxe6devGmjVrbLavWrWKwMBAWrRoUaTzHTp0iKNHj9K6devSDFP+Yudnx8jOtuDu7UyLnsVbVlbaUnafxZJhBkcDHh1r5jsm5lpXodquztR1s39iSERERERERCqmYi0XOn/+PPfee2++++69917Onz9foqAK4x//+AddunRh7Nix/O1vf2PHjh28++67LF261GapUoMGDahTpw5btmwBYN68eRw/fpyuXbtSvXp1Dh8+zKxZs6hVq5bNUiApXad+iyf255zuPe0G1cfJxWjniMCSZSZlR87MGvd7AzB6Ouc7btu1eixaKiQiIiIiIiI3U6yZLHfccQcbNmzId9+GDRu44447ShRUYbRv354vvviCffv20atXL95//33+9a9/5UmUmEwmzGaz9XPDhg05ePAg48ePp2fPnsyZM4e+ffuyc+fOPN2KpHRkZ1vYsTanZbN/bU8atq1h54hypB44T3ZKFhhy2jbn54rJzMErVwHooqVCIiIiIiIichPFmsnyzDPP8MQTT3Dx4kWGDRtGjRo1OH/+PGvWrGH16tUsWbKktOPMV58+fejTp89Nx8TGxtp87t+/P/379y/DqOSvftt1lsuncwrHdhzSAIOD/bvzWMwWkrflzGJxa+aPY1W3fMftSEgmGzAAnXw9yi9AERERERERqXSKlWQZN24cGRkZvPLKK6xevRqDwYDFYsHf359//etfjB07trTjlEoqM93Eni+OA3BHc39qhhSt81NZSfvPRczx6QB4ds1/FgtATEJOcqiZpxt+TiXqeC4iIiIiAuQ03bh06RLp6ek2s+5FpHwZjUZcXV2pVq0aBkPpTAYo9lvjpEmTmDhxIr/99hsJCQn4+fnRsGHDIrdullvb/317kqtXMnEwGmg/uGK0bLZYLCRHxwHgEuKLc9CNZ6hsi1c9FhEREREpPRaLhdOnT5OcnIyzszNGo/1rFYrcrjIzM0lJSSEjI4OaNWuWSqKlRL+ad3BwoHHjxiUOQm5NyfHpHPr+FABN7wvGp3oVO0eUI/1oAlnnUgHwCr3xLJZT6ZkcT8sA1LpZRERERErHpUuXSE5Opnr16lStWtXe4Yjc9i5fvsyFCxe4dOkS/v7+JT5fsaadTJs2jccffzzffY8//jj/+Mc/ShSU3Bp2rT+GOSsbV3cnWt1f197hWCVH5yR+nGt74lzP+4bjtl+bxeLmYKCVl3u5xCYiIiIit7b09HScnZ2VYBGpIKpWrYqzszPp6emlcr5iJVlWrVpFp06d8t3XuXNnVq1aVaKgpPI7dyKJP/bltPJu3a8eru5Odo4oR8bJK2SeuAKAZ9daN50OFnOtdXNbbw9cjVoGJyIiIiIlZzabtURIpIIxGo2lVh+pWG+OZ86coVatWvnuCw4OJi4urkRBSeVmsfyvZbNPQBXu7hJk54j+J3cWi2N1N1wb+d1wXLbFwvZrSRa1bhYREREREZHCKFaSxd/fn8OHD+e77/Dhw/j53fjlVW59fx64wLnjSQB0fKABxgoyCyTrfCrpR+KBa7NYbtJK+peUNOKzcjKZqsciIiIiIiIihVGst99BgwYRGRnJ3r17bbbv3buXmTNnEh4eXirBSeVjyjKza/0xAILv8qVO04qz1jQ5JmeGldHbhSr33LygUcy1eixVnRxp5O5a5rGJiIiIiIhI5VesJMurr75K7dq1ad++PU2aNKFnz540adKE9u3bU6tWLWbNmlXacUol8fPWOJIvp2MwQMchd5Zar/GSMiWmc/XQRQA8OtfE4Hjzf/rbE1IA6OLrgUMFuQcRERERkcrGYDAwb968Ep3j888/Z/HixXm2R0ZG4uHhUaRzhYaG0q9fvxLFA7BgwQK+/vrrEp9Hbj3FSrJ4e3uze/dulixZQtOmTQFo2rQp77zzDrt27cLb+8YdW+TWdfVKJvs3xQLQqGMQ1YKL9gOvLKVsPw3ZFhyqOOLepsZNx6abs9mTdC3JoqVCIiIiIiJ2daMky5gxY/jhhx/sEJGSLHJjjsU90NnZmbFjxzJ27NjSjEcqsb1fnSAr3YyTi5E2/evZOxwrc2oWqXvPAeDRIQgH55tXc9+blEp6tgWALr5KsoiIiIiIVETBwcEEBwfbOwwRGxWjIqlUepdPp/Dr9tMAtOxdB3dvFztH9D8pO89gycrG4OSAe/uCOx1tu9ZVqEEVF2q6Opd1eCIiIiIilVJERARNmjQhOjqaFi1a4O7uTps2bThw4IDNOJPJxPPPP4+/vz+enp5ERESQnJxc6GssX76cX375BYPBgMFgICIiAsh/uVBiYiKTJk0iODgYFxcX6tWrx4svvnjD86enp9O/f3/q1q3Ln3/mdEiNi4tj5MiRVKtWDTc3N7p06WJzT3Xr1uXkyZO8/fbb1piWLVsGwJdffkmrVq3w8PDAx8eHVq1aacbLbabYM1lErrfz0z+xWMDDz4XmYfm397aH7AwzqbvOAODepgZGd6cCj9l2reitZrGIiIiISHnINGVzOjHNrjHU9HHDuYC6hfk5d+4cTz31FFOnTsXLy4upU6cSHh7OsWPHcHLK+X/vhQsX0rJlS5YvX86JEyeYOnUq6enpfPLJJwWef/r06Vy8eJHffvuNjz/+GMjpdpufjIwMunXrRmxsLDNmzKBp06acOnWKH3/8Md/xKSkpDBw4kLi4OLZv306tWrVISEigU6dOeHh4sHDhQry9vVm4cCHdunXjjz/+oHr16qxfv54+ffrQqVMn/v73vwNQv359jh07xpAhQxg+fDhz5swhOzubn376iYSEhCI/V6m8lGSREjv5y2X++2tOa+T24fVxLGA5TnlK3XeO7KsmcDDg0bngqYSXM038JyXnP3Bq3SwiIiIi5eF0Yhr3zYu2aww/TAmlXjX3Ih8XHx9PTEwMd999NwCurq706NGDPXv20KlTJwBcXFz4/PPPMRqN1jFjx44lMjKSu+6666bnr1+/Pv7+/pw8eZJ27drddOyHH37IwYMH2blzJ+3bt7duf+SRR/KMTUxM5P777+fq1ats376d6tWrAzm1VhITE9m7d691W1hYGA0aNGDevHm8/vrrtGjRAhcXFwICAmxiiomJISsri0WLFuHpmfMu0atXr5vGLLceLReSEsk2Z7NjXc60uoB6XtzZKsDOEf2PxZRNyvacts1VWlTH0afgJUw/JiZjAYwGaO9TcQr3ioiIiIhUREFBQdYEC0Djxo2BnCU3ufr3729NsAAMHjwYi8XC3r17SzWWLVu20KhRI5sES34uXbpEaGgoFouF6OhoazIFYPPmzdx33334+flhMpkwmUwYjUY6d+7Mvn37bnreZs2aYTQaGTFiBBs2bCApKalU7ksqF81kkRL59cczJJxNBaDT0IrTshng6qGLmJMyAfDsWriCWLlLhVp6uuPlWHFm5IiIiIjIraumjxs/TAm1ewzF4ePjY/PZ2TmnpmF6erp12/VJDABfX1+cnJw4e/Zssa55I5cvXyYoqOAajEePHiUhIYEFCxbg6+trs+/SpUvs3r3butTpevXr17/peUNCQvjqq6+YPXs24eHhODg40Lt3bxYtWkTt2rWLdjNSaRUryfLf//63wDH6R3Try7iaxZ4NJwBo0Ko6Ne6oOK27LdkWkmNOAeDauCpO1asUfIzFQsy1ordd/DSLRURERETKh7OjQ7GW6lQWFy5csPmckJBAVlYWgYGBpXqdqlWr8vPPPxc4rkOHDnTv3p1nn30WPz8/Ro0aZd3n5+dH7969eeWVV/Ic5+JS8Mz43r1707t3b65cucI333zD5MmTGT16NFu2bCnazUilVawkS926dQucsWA2m4sVkFQeBzadJD0lC6OjA+0H3TyrW97Sj1zGdDGntopnaOFmsZxIyyQuPQtQ0VsRERERkdKyYcMG5s+fb10y9Nlnn2EwGGjdunWhjnd2draZGXMj3bt3Z/Xq1ezevbvA+i3PPPMMaWlpjB49GhcXF4YNG2Y9x4oVK2jUqBHu7jdOfBUUk5eXF8OGDWPPnj2sWrWqwNjl1lGsJMvatWvzbIuPj2fz5s3s27ePWbNmlTgwqdiSLqbx0w85M0XuCauFV7XiTS8sCxaLhSvROWtAXe7wxqW2V6GOy23d7GF0oKXXrfubBBERERGR8pSRkcGgQYOYMGECJ06c4IUXXmDIkCE0atSoUMc3atSI999/n1WrVnHnnXdSrVo16tatm2fcqFGjWLx4Mf369WPGjBk0adKE06dPs23bNt55550841988UXS0tIYOXIkrq6uDBgwgGeffZaPP/6Yrl278vTTT1O7dm0uXrzInj17CAoKYvLkydaYtm7dynfffYevry/16tVj3bp17Ny5k/vvv5/AwEBOnDjBihUr6NmzZ4men1QuxUqyPPDAA/luHzt2LJMnT2bHjh387W9/K1FgUrHtWv8n2SYLbp5O3Nu7jr3DsZFxPImsUzkJE8/QwreTzq3H0sHHAyeHilNbRkRERESkMps0aRIXL15k5MiRZGZmEh4ezqJFiwp9/GOPPcbevXuZNGkSly9f5pFHHmHZsmV5xrm4uLBlyxamTZvG7NmziY+PJzg4mOHDh9/w3DNnziQtLY1hw4bxxRdf0KtXL3bv3s3LL7/MCy+8wOXLl6levTrt2rUjPDzcetzs2bMZP348DzzwAMnJyXzwwQc0a9aMDRs28Oyzz3L58mVq1KjB8OHD8116JLcug8VisZTmCb///nuGDRtGfHx8aZ62QoqLi6NWrVqcOnWK4ODCLUm5FZz5M5H18/4PgNC/NeTuzjXtHJGti+8fJuNoAk6B7lR/qkWhivGasi003vEfrpiyefXOmowJ9i+HSEVERETkdhMbGwuQ70wMEbGPgr4vi/LuX+otnHfu3Imrq2tpn1YqCEu2hR1r/wDAL8idRh1Kt1hVSWWeTiHjaAKQM4ulsN2Ofk6+yhVTNqB6LCIiIiIiIlI8xVou9NRTT+XZlpmZyZEjR/jxxx+ZMmVKiQOTiunovvNcOJmzrKbTkDtxMJZ6nq5EcjsKGau64takWqGPy+0qFOjixJ1VCq4aLiIiIiIiJWc2m7nZ4gpHx2K9sorYTbH+xW7YsCHPNldXV4KDg1m8eDFjxowpcWBS8WRlmtn9+TEA6jSpSq3GfnaOyJbpUhpp/7kEgGfnYAzGwtdViblWj6Wzr0ehZ7+IiIiIiEjJhIWFERMTc8P9J06c0NIqqVSKlWQ5ceJEacchlcCh7/5LSkIGBgcDHR5oYO9w8kjeHgcWcPBwwv3egEIfl2oyc+DKVQC6aqmQiIiIiEi5Wbp0KcnJyTfcHxQUVI7RiJSc5l5JoaQmZvB/354EoEnnIPwCK1aLY/OVTFL3nwfAo1NNDE6FX8a0KymVrGtTFLv4KckiIiIiIlJeGjZsaO8QREpVoZMsM2fOLPRJDQYD06dPL1ZAUjHt/vI4psxsnN0cad2/nr3DySNlx2kwWzC4GPFoV7RivLmtmxu5u+Lv7FQW4YmIiIiIiMhtoNBJljfeeMPms8lkIiMjI+ckjo6YTCYgpze5k5OTkiy3kIv/Tea3XWcBaNWnLm4eznaOyFZ2uomU3TnxebQLxMG1aBO0tl0reqtZLCIiIiIiIlIShV5TkZycbP364YcfCAwMZOnSpVy+fJnMzEwuX77MkiVLCAwMZMuWLWUZs5Qji8XCjk//AAt4+bvRLPTmPcHtIWX3WSwZZnA04NGxZpGOPZ+RxW+p6YDqsYiIiIiIiEjJFKsmy5NPPsmUKVMYO3asdZuvry/jxo0jKyuLiRMnsnfv3lILUuznxE+XOP17IgAdBtfHWIRaJ+XBkmUm5cfTALjfG4DRq2izbHJnsTgbDLT1qVh1ZkRERERERKRyKdYb808//cQdd9yR77769etz+PDhEgUlFYPZlM3Oz/4EILCBN3c097dzRHmlHrhAdkoWGHLaNhdVbpKllbc77kZjaYcnIiIiIiIit5FiJVnq1q3LkiVLsFzryJLLYrGwePFi6tSpUyrBiX0djjlN0oU0ADoNvRODwWDniGxZzBaSt8UB4Na0Go7V3Ip2vMViLXqrpUIiIiIiIqXPYDAwb948e4dRKkJDQ+nXr5+9w5AKrljLhebOncuQIUO488476d+/P9WrV+fChQts2LCBkydPsm7dutKOU8pZemoW+zaeAKBhuxpUr+Nl54jySjt8EXN8Tj0Vz661inz871fTOZ+ZU7BZRW9FRERERESkpIqVZBk4cCD79u1j7ty5fPHFF5w9e5bAwEDatGnDunXraN68eSmHKeXt993nyLhqwtHJgXYD818aZk8Wi4Xk6JxZLC4hvjjX9CjyOXJnsfg4GmnmWbRZMCIiIiIicmtIS0vDzU3vA1I6il3FtHnz5nzyySccP36ctLQ0jh8/zieffKIEyy3i9NEEAOo0qYqHr6udo8kr42gCWWdTAfDsWryOR9sSUgDo6OuBsYIthRIRERERqegiIiJo0qQJ0dHRtGjRAnd3d9q0acOBAwdsxplMJp5//nn8/f3x9PQkIiKC5OTkIl9n06ZNNGnSBFdXV+699152795tMy6/pUnz5s2zKXsQHR2NwWBg48aNDBkyBC8vL4YOHQpAYmIikyZNIjg4GBcXF+rVq8eLL76YJ561a9fSsGFDPDw86NatG8eOHbPZP3XqVJo2bYqHhwc1a9Zk+PDhnD171mbMjh076NKlC97e3nh6etK0aVOWL19uM2bjxo20bdsWNzc3/P39GT9+PKmpqdb9WVlZPPfcc9SpUwcXFxcCAwPp378/SUlJhX62UvqKNZNFbm2WbAtn/kwEIPBOH7vGciNXrs1ica7licsd3kU+PjM7m52JOUkW1WMRERERESmec+fO8dRTTzF16lS8vLyYOnUq4eHhHDt2DCcnJwAWLlxIy5YtWb58OSdOnGDq1Kmkp6fzySefFPo6Z8+eZcKECURGRuLr68vcuXPp1asXf/zxB9WrVy9y3I8//jgjR45k/PjxODg4kJGRQbdu3YiNjWXGjBk0bdqUU6dO8eOPP9ocd+jQIS5evMjcuXMxm80888wzjBw5kl27dlnHXLhwgZdeeomgoCAuXrzIm2++SdeuXfn1119xdHTkypUr9O3bl06dOrFq1SpcXFz49ddfSUxMtJ5j3bp1PPjgg4wePZqoqCjOnj3L1KlTSUhIsD63OXPmsGTJEl577TXuvvtuLl26xObNm8nIyCjy85DSoySL5HH5TCoZqTm1SmqG+Ng3mHxknLxC5omc7KxnaHCxCvIeuHKVq+ZsQPVYRERERMTOTJmQdMq+MXjXAkfnIh8WHx9PTEwMd999NwCurq706NGDPXv20KlTJwBcXFz4/PPPMV7r5unq6srYsWOJjIzkrrvuKvR11q5dS7du3QDo0qULtWrVYsGCBcyePbvIcQ8cOJC5c+daP7/77rscPHiQnTt30r59e+v2Rx55xOa4xMREDh48iL+/v/Xz2LFjiYuLIzg4Z4b9+++/bx1vNptp3749wcHBbN26lZ49e3L06FGSkpKYM2cOTZs2BSAsLMx6jMViYcqUKTz44IP8+9//tm4PCAigX79+TJ8+nbvvvpu9e/fSs2dPJkyYYB3zwAMPFPlZSOlSkkXyOPNHIgAuVRypGlT0WidlLTkmZxaLo78bro2qFuscufVYars6U9fNpdRiExEREREpsqRTsLClfWOY9H9QtX6RDwsKCrImWAAaN24MQFxcnHVb//79rQkWgMGDBzNmzBj27t1b6CSLt7e3NcEC4OPjQ7du3fIsGSqsPn362HzesmULjRo1skmw5Kd58+bWBAvY3m9ukmXTpk288sor/PLLL1y5csU69ujRo/Ts2ZP69evj5eXF+PHjeeqpp7jvvvtsznn06FFOnjzJggULMJlM1u1du3bFYDCwf/9+7r77blq2bMkbb7xBZGQkffv25d5778XBodgVQaSU6G9A8jjzR049lsAGPhgcKlatkqzzqaT/ehnI6ShU3Pi2JVxr3axZLCIiIiIixebj42Pz2dk5ZzZMenq6ddtfl/P4+vri5OSUp07JzVyfhLj+vEU5x1+Pvd7ly5cJCgoq8LiC7nffvn0MGDCAoKAgPvroI3bt2mVNBOWO8fX15bvvvsPT05NRo0ZRo0YNQkND+c9//gPApUuXAAgPD8fJycn65eHhQXZ2NqdO5cx6mjZtGi+88ALLly+nTZs21KhRg6ioKCwWS7GeiZSOIs9kMZlM/PTTT9SqVatYa9+kYrNYLNaZLEEVsB5L7iwWo7czVZrn/UFbGElZJg5euQpAZ9VjERERERF7866VM5PE3jGUkQsXLth8TkhIICsri8DAwEKf4+LFi/me9/pzuLi4kJmZaTMmPj4+3/P9teRA1apV+fnnnwsdz42sX78eb29v1qxZY51VcvLkyTzj2rRpw6ZNm0hLS+OHH35gypQpDBo0iGPHjuHn5wfAokWLaNu2bZ5jc5NBLi4uREZGEhkZyZ9//sn7779PZGQkd9xxB6NGjSrxvUjxFDnJ4uDgQPv27fn666/p3r17WcQkdpRw7ippyVlAxavHYkpM5+qhnB+uHp2DMTgWbyLWzsQUsgED0Mm34i2HEhEREZHbjKNzsZbqVBYbNmxg/vz51iVDn332GQaDgdatWxf6HElJSWzdutW6ZCj385NPPmkdExwczJEjR2yO+/777wt1/u7du7N69Wp2795Nu3btCh3XX6WlpeHk5GSTxPn4449vON7NzY0+ffpw7Ngxnn76adLT07nrrrsIDg7m+PHjTJw4sVDXbdCgAbNnz2bp0qV5noGUr2IlWe644w6bysdy68idxeLkaqRacMVKQKRsPw3ZFhyqOOLeukaxzxNzrXVzM083/JxUlkhEREREpCxlZGQwaNAgJkyYwIkTJ3jhhRcYMmQIjRo1KvQ5/Pz8eOyxx4iKisLHx8datPaZZ56xjhkyZAgLFiygTZs2hISE8OGHH3Lu3LlCnX/UqFEsXryYfv36MWPGDJo0acLp06fZtm0b77zzTqHj7NGjBwsWLGDSpEmEh4eza9cuPvroI5sxGzdu5L333iM8PJzatWtz7tw5Fi5cSMeOHXF1dQVg/vz5jBgxgtTUVPr27Yu7uzsnT55k48aNzJ49m5CQEAYNGsS9995rbZ+9YcMG4uPjbWrXSPkr1hvmSy+9xKuvvkrHjh2LNMVLKr7cJEtgfW8cjBWnZI85NYvUvTk/IN3bB+HgYizgiBvLLXqr1s0iIiIiImVv0qRJXLx4kZEjR5KZmUl4eDiLFi0q0jkCAwN57bXXeO655zh27Bh333033377LQEBAdYx06dP58KFC0RGRmI0Ghk3bhz33HMPL7zwQoHnd3FxYcuWLUybNo3Zs2cTHx9PcHAww4cPL1Kcffr04bXXXmPhwoV88MEHdOzYka+++oqQkBDrmAYNGuDg4MC0adM4f/481apVo2fPnsyZM8c6ZujQofj4+DBr1ixWrFgBQN26dendu7f1njt27MiaNWt48803MZlMNGzYkJUrV2rFiZ0ZLMWoitO/f3/2799PYmIizZo1o3r16jbToQwGA1988UWpBloRxcXFUatWLU6dOmWtJF2ZWSwWlk/dQWpSJu0G3cG9vevaOySrpO9OkrzlvxicHKgxtQ1Gd6dinedUeiatd/0KwLrm9emkRIuIiIiIlKPY2Fgg54VZCiciIoL9+/dz+PBhe4cit6iCvi+L8u5frJksKSkpNq22UlJSinMaqWCSLqaRmpRTKKpmiK+do/mf7AwzqbvOAODepkaxEywA26/NYnFzMNDa271U4hMRERERERGBYiZZfvjhh9KOQyqA3KVCjk4O+NeuODM8UvedI/uqCRwMeHSuWaJzxVxr3dzOxwMX9ZAXEREREbErs9l805bDjo6qoSiVi/7FilVukqVGfW+MxezcU9ospmxStue0ba7S3B9HH9dinyvbYmH7tSSLWjeLiIiIiNhfWFgYMTExN9x/4sQJli1bVn4BiZRQsZIsM2fOLHDMP/7xj+KcWuzozNFEAILu9LFrHNe7eugi5mtLmDy7lqzuzS8pacRnmQHo6qcki4iIiIiIvS1dupTk5OQb7g8KCirHaERKrlhJljfeeCPPtqtXr2KxWHBxccHJyUlJlkrmyuU0kuPTAagZ4mPfYK6xZFtI3nYKANfGVXEKKFkNlZhr9ViqOTnSyL34M2JERERERKR0NGzY0N4hiJSqYq0JSU5OzvOVlpbGhg0bCAkJYceOHaUdp5Sxs9eWChkdHahe18u+wVyTfiQe04U0ADxDS969aZt1qZAHDtd1wxIREREREREpDaVWk8XZ2Zm+ffty/vx5nnjiCSVaKpnT15IsAfW8cHQy2jcYctpJJ0fnzGJxrueNS+2SJX7SzNnsSUoFoIuWComIiIiIiEgZKPXqpsHBwRw6dKi0TytlrKLVY8k8kUTmqZyZJ16lMItlX1IqGdk5Vcu7qOitiIiIiIiIlIFSTbKcOHGC1157jfr165fmaaWMpSZmkHQxZ1lORUmyXInO6SjkFOiOS4hvic+X27q5QRUXaro6l/h8IiIiIiIiIn9VrOVCnp6eGP5S0yIrK4vMzEyqVKnCZ599VirBSfnIbd3s4GCgxh3e9g0GyDyTQsbRBCCnFstf/60Vx/ZrRW81i0VERERERETKSrGSLH//+9/zvPi6uroSHBzM/fffj5+fX6kEJ+Ujtx5L9bqeOLnYvx5LckzOLBajnytuTfxLfL7LmSb+k5IzU0etm0VERERERKSsFCvJEhkZWcphiD2duTZrpCIsFTJdTiPt54sAeHapicFYCrNYEpKxAEYDdPDxKPH5REREREQEPv/8c86cOcOECROKdFxsbCzLli1j3LhxBAUFFfm6oaGheHh48NVXXxX52FtFZGQkPXv2pEOHDvYORf6iRDVZEhIS2L59OytXriQhIedFPT09nezs7FIJTsre1SuZJJy7CkDQnSWvfVJSydviwAIOHk643xtQKufcfq0eS0tPdzwd7T9TR0RERETkVvD555+zePHiIh8XGxtLVFQUZ86cKYOobg9RUVHs3LnT3mFIPoqVZDGbzbz00kvUqlWLrl27MmrUKE6cOAHA4MGDeeWVV0o1SCk7Z/9MBMBggMD69q3HYk7OJPXAeQA8OtbEUAqtpC0Wi7XobRc/zWIRERERERGRslOsJMuMGTNYtGgRb7zxBr/++isWi8W6b8CAAWzYsKHUApSylVuPxb+2J85uxVo9VmpSdpwGkwWDixGPdoGlcs4TaZnEpWcB0FVFb0VERERESkVERATLly/nl19+wWAwYDAYiIiIAHJmuLRo0QJXV1dq1KjBxIkTSUlJASA6Opr77rsPgNatW1uPBUhNTeXJJ5+kYcOGVKlShbp16/LEE0+QlJRUolg//PBDOnXqhJ+fH76+voSGhrJ3716bMZGRkXh4eHDgwAHatm2Lm5sbLVq04MCBA6SnpzN+/Hj8/PwIDg5mwYIFea5xs3sGWLZsGQaDgUuXLtkc16RJE+tzy32uTZo0ITo6mhYtWuDu7k6bNm04cOCAdUzu83ruueeszy86OrpEz0hKT7GSLMuWLWP27NmMHz+eO++802Zf/fr1OXbsWKkEJ2Uvt7NQoJ3rsWSnm0jZdRYA93aBOJRSwmfbtVksHkYHWni5l8o5RURERERud9OnT6dPnz7ccccd7Nq1i127djF9+nS+/PJLBg8eTEhICOvXr2f69Ol89NFHDBo0CICWLVvy9ttvA/DBBx9YjwW4evUqZrOZWbNmsWnTJl599VViYmIIDw8vUayxsbE8/PDDrF27lpUrV1KrVi26dOnC0aNHbcZlZWXx6KOPMn78eD799FNMJhODBw/msccew83NjdWrVzNo0CAmT55ss1SnoHsuqnPnzvHUU0/x3HPPsXr1aq5evUp4eDhZWTm/PM59XpMmTbI+v5YtWxbv4UipK9ab7OXLl2nUqFG++7Kzs61/+VKxpadmcfl0Tna1pp2TLCm7z2LJMIPRgGfHmqV23m3XWjd38PHAyaHkRXRFREREREpbljmLM6n2rU8S5B6Ek9Gp0OPr16+Pv78/J0+epF27dtbtQ4cOpXXr1qxevdq6zc/PjxEjRhAdHU1oaCiNGzcGcmZxtGrVyjrO39+f//f//p/1s8lkol69enTq1ImjR48SEhJSrHv7xz/+Yf1zdnY2PXr0YN++fdbJA7kyMzN57bXX6N27t3Vs//79MZvNzJ8/H4Bu3bqxdu1a1q5day06GxkZWeA9F0V8fDwxMTHcfffdQE4n3x49erBnzx46depkfd61a9e2efZSMRQryRISEsJ3331HWFhYnn0//PADTZo0KXFgUvbO/pkIFsAAgQ187BaHJSublB9PA+B+bwBGL+dSOa8p28KPibn1WLRUSEREREQqpjOpZ+i3vp9dY/gq/CvqeNUp0TlSUlI4dOgQb7zxhs32oUOH8vDDD7N9+/YCEw4fffQR8+fP548//iA1NdW6vSRJliNHjvDSSy+xc+dOLly4YHPO6zk4ONCtWzfr59zrde/e3brNaDRSv359Tp06BZTOPf9VUFCQNcECWJNScXFxRTqP2EexkiyTJ09m7NixODk5MWTIECDnL3zXrl3861//YtmyZaUZo5SR3HosVYM8cHUvfNa6tKX+33myU7LAAJ5dgkvtvD8nX+WKKafTVRfVYxERERERKVOJiYlYLBZq1Khhs93R0ZGqVasSHx9/0+PXr1/Pww8/zLhx45g1axZVq1bl7NmzhIeHk56eXqyYkpOT6dmzJ/7+/syfP586derg6urKmDFj8pzTzc0NZ+f//cI3988+Pj4245ydna3HlvSe85Pf9YBiPwMpX8VKskRERBAfH09kZKR1etWgQYOoUqUKr776KsOGDSvVIKVsnL2WZAkK8bFbDBazheSYnIysW9NqOFZzK7Vz53YVCnRx4s4qLqV2XhERERGR0hTkHsRX4V/ZPYaS8vHxwWAwcP78eZvtJpOJy5cv4+fnd9Pj165dS/PmzVm6dKl1W0xMTIli2rVrF3FxcXz11Vfcc8891u1JSUkEB5f8F7yFvWdXV1cgZ0nS9YqThJGKrdjVRZ999lnGjRvHzp07uXTpEn5+fnTo0AEvL6/SjE/KSGaaiYv/zUlC2LMeS9rhS5jjczKynl1rleq5Y67VY+ni62mtwC0iIiIiUtE4GZ1KvFTHHq6f0QHg4eFB8+bNWbNmDc8++6x1e24R2c6dO1uPg7wzM9LS0mxmkgB8/PHHJYoxLS3N5poAO3fuJDY21mZJTnEV9p5zEzpHjhwhKCgnoXX48GHOnTtXrOs6OTlpZksFVaIWLh4eHvTs2bO0YpFydPZYErmdt4PslGSxWCwkR+esZXS50wfnmh6ldu5Uk5kDV64C0MW39M4rIiIiIiI5GjVqxPvvv8+qVau48847qVatGpGRkQwaNIjhw4fzyCOPcPz4cV588UXCwsKstUlCQkIwGo28//77GI1GnJycaNWqFT169GDixInMnDmTDh06sGnTJrZs2VKiGNu1a4eHhwcTJ05k6tSpnD59msjISGrWLL1mG4W557Zt21KrVi0mT57MnDlzuHLlCnPnzi1wds+NNGrUiC+++ILOnTvj7u5Ow4YN8fRUiYSKoNBJls8++6xIJx48eHCRg5Hyc+aPBAB8a1TBzbN0Cs0WVcYfiWSdzSlm5RlaurNYdiWlknUti6SityIiIiIipe+xxx5j7969TJo0icuXL/PII4+wbNkyPv30U2bOnMnAgQPx8fFh5MiRvPbaa9bjqlWrxttvv83rr7/ORx99hMlkwmKx8Pjjj3P8+HEWLVrEvHnz6NWrFytXrixRB52AgADWrl3LlClTGDhwICEhISxZssQmnpIaMGBAgffs5OTE+vXrGT9+PEOHDqVBgwYsWLCAp556qljXfPvtt3n66ae5//77SUtL44cffihygV0pGwaLJXc+w805ODgU/qQGA2azudhBVRZxcXHUqlWLU6dOlcp6vvL02bwDnP0zibs7BxH6t7vsEsPFd34m43gSTrU8qT7hnlJd0vOPP07zTtxFGru7srWNfe5PREREROSvYmNjAahbt65d4xCR/yno+7Io7/6Fnsly4sSJQgcoFV/i+ZylNNVq2WeWR8Z/r5BxPAkAr67BpV4zJbfobWfNYhEREREREZFyUugkS506la8Qk+QvI81EWnIWAN7VS6+bT1EkR+d0FHL0d8O1cdVSPff5jCx+T80pAtVVrZtFRERERG5ZJpPphvsMBgNGo7EcoxEpYeFbqZySLly1/tmnepVyv37Whauk/3oZAM+uwRgcSncWy7Zrs1icDQba+ajorYiIiIjIrcrJyemG++rUqWNdBiJSXoqdZFmxYgVLlizh6NGj+baOunLlSokCk7KTdCGnjZnR0QEPH5dyv35yTM4sFqOXM1WaVy/18+e2bm7t7U4VY+FrCYmIiIiISOWyb9++G+5zcSn/dx2RYiVZVqxYwZgxY4iIiGDnzp08+uijmM1mNmzYgI+PDw8//HBpxymlKOlizkwWL3+3Up9FUhBTYgZXD14AwKNzMAbH0k2CWCwWtl+bydJFS4VERERERG5prVq1sncIIjaK9Yb75ptvMn36dN5++20AJkyYwAcffMCJEyfw9/fHw0NLNCqyPV/mFDFOuNY+uTylbI+DbAsGN0fc29Qo9fP/fjWd85k56zLVullERERERETKU7GSLH/88QcdO3bEaDRiNBqtS4M8PT154YUX+Ne//lWqQcqtwZyaRerecwB4dAjCwaX0i1Btu7ZUyMfRSDNP+xT1FRERERERkdtTsZIs3t7eZGRkAFCzZk1+/fVX6z6z2czly5dLJzopEw++3JqgO314ZE7Hcr1u6q4zWLKyMTg54NEhqEyusS0hBYCOvh4YS7kttIiIiIiIiMjNFKsmS6tWrfj555/p1asXAwYMICoqiuzsbJycnJg7dy5t27Yt7TilFFUL9iT87y3L9ZrZmWZSdp4BwL11DYzuN64CXlyZ2dnsTMxJsqh1s4iIiIiIiJS3YiVZXnzxRU6ePAnAzJkzOXnyJJMnT8ZsNtO6dWveeeedUg1SKr/UvefIvmoCBwMenWuWyTUOXLnKVXM2AF1Vj0VERERERETKWbGSLO3ataNdu3YA+Pj48MUXX5CRkUFGRgZeXl6lGqBUfhZTNinbTwNQpbk/jr6uZXKd3HostV2dqeOmdm0iIiIiIiJSvopVk2XJkiXEx8fbbHNxcVGCRfJ19aeLmJNyavh4dg0us+tsu9a6WbNYREREREQqBoPBwLx58+wdRqlbtmwZBoOBS5cuWbfdqvcqRVOsJMvTTz9NYGAgffr04eOPPyYlJaW045JbhCXbQnLMKQBcG/nhFOBeJtdJyjJx8MpVALqoHouIiIiIiJSzXbt28be//c3eYYidFSvJcu7cORYtWkRGRgaPPPIIAQEBDBs2jC+++ILMzMzSjlEqsfQj8ZgupAHgGVqrzK6zIzGFbMBATmchERERERGR8tSuXTsCAwNLfJ60tLRSiEbspVhJFl9fX8aOHcuWLVs4ffo0s2fPJi4ujvDwcAICAnjsscdKO06phCwWC8nRObNYnOt54VKn7JaT5bZububphp9TsUoNiYiIiIhIEURERNCkSROio6Np0aIF7u7utGnThgMHDtiMM5lMPP/88/j7++Pp6UlERATJycmFvs4vv/xCnz59qFq1KlWqVKFhw4a8/vrr1v2hoaH069fP5pj9+/djMBiIjo62bjMYDMydO/emsURHR2MwGPj6668ZPHgw7u7uBAYGMnv27ALjzG+50MaNG2nbti1ubm74+/szfvx4UlNT81xv48aNDBkyBC8vL4YOHQrAl19+SatWrfDw8MDHx4dWrVrx9ddfF/q5iX2U+G00ICCAp59+mqeffprNmzfz6KOPsmzZMt57773SiE8qscwTSWSeyvmBVZazWOB/RW/VullEREREKhtLZiZZZ87YNQanoCAMzs5FPu7cuXM89dRTTJ06FS8vL6ZOnUp4eDjHjh3DyckJgIULF9KyZUuWL1/OiRMnmDp1Kunp6XzyySeFusaAAQOoXr067733Ht7e3vz555/ExcUVOdaixDJu3DiGDx/OZ599xvfff8+0adPw8/PjiSeeKPS11q1bx4MPPsjo0aOJiori7NmzTJ06lYSEhDzXe/zxxxk5ciTjx4/HwcGBY8eOMWTIEIYPH86cOXPIzs7mp59+IiEhoVj3LeWnxEmWuLg4PvnkEz755BMOHjxItWrVGD9+fGnEJpXcleicH3xONdxxDfEts+ucSs/keFpOYd0uKnorIiIiIpVM1pkzHOt9v11jqP/NJpzr1i3ycfHx8cTExHD33XcD4OrqSo8ePdizZw+dOnUCcpqkfP755xiNRuuYsWPHEhkZyV133XXT81+6dInjx4+zYMEC+vfvD8B9991X5DhzFTaWbt268cYbbwDQq1cvzp07x6xZsxg3bhwODgUvCLFYLEyZMoUHH3yQf//739btAQEB9OvXj+nTp1ufGcDAgQOZO3eu9fO6devIyspi0aJFeHp6WuOQiq9Yy4UuXrzI4sWL6dy5M3Xr1uXVV1+lSZMmfP3115w5c4ZFixaVdpxSyWSeSSHjaE6W1TM0GIPBUGbX2n5tFoubg4HW3mVTWFdERERERPIKCgqySRY0btwYwGamSf/+/a1JDYDBgwdjsVjYu3dvgeevWrUqderU4cUXX2T58uXFnsFS1FjCw8NtPg8ePJi4uLhCX//o0aOcPHmSYcOGYTKZrF9du3bFYDCwf/9+m/F9+vSx+dysWTOMRiMjRoxgw4YNJCUlFeU2xY6KNZMlKCgIJycn+vTpw+rVq+nXrx8uLi6lHZtUYskxOT98jL4uuDX1L9NrxVxr3dzOxwOXQmSVRUREREQqEqegIOp/s8nuMRSHj4+PzWfna0uO0tPTrduqV69uM8bX1xcnJyfOnj1b4PkNBgPffvstL7/8MhMnTiQ1NZWWLVvyz3/+ky5duhQ53sLG8tdxuZ/Pnj1L7dq1C7xObmvnvyZrcp06deqm1wsJCeGrr75i9uzZhIeH4+DgQO/evVm0aFGhri/2U6wky7///W8GDx5snbYkcj3T5TTSfr4IgGeXYAzGspvFkm2xsP1akkWtm0VERESkMjI4OxdrqU5lceHCBZvPCQkJZGVlFboTT8OGDVm7di1ZWVns3LmTl156if79+3P69Gk8PDxwdXXN0+U2Pj6+RLH8dVzu58LG7OfnB8CiRYto27Ztnv1Bf0lq5Tfzv3fv3vTu3ZsrV67wzTffMHnyZEaPHs2WLVsKFYPYR7F+7f/II48owSI3lLwtDizg4O6Ee6uAMr3WLylpxGeZAdVjERERERGpiDZs2IDZbLZ+/uyzzzAYDLRu3bpI53FycqJr165MnTqVK1eucOZaseDg4GB+//13LBaLdex3331XoljWr19v8/mzzz4jKCiI4ODgQsV61113ERwczPHjx2nVqlWer78mWW7Gy8uLYcOG8dBDD3HkyJFCHyf2oV63UqrMyZmkHjgPgEenIAxOxgKOKJmYa/VYqjk50sjdtUyvJSIiIiIiRZeRkcGgQYOYMGECJ06c4IUXXmDIkCE0atSowGN//vln/v73v/Pggw9Sv359kpKSmDNnDnXr1qV+/foADBkyhPfee49JkyYxaNAgduzYwWeffVaiWLZu3cpzzz1Hjx49+O6771ixYgVvv/12oYreQs7MlPnz5zNixAhSU1Pp27cv7u7unDx5ko0bNzJ79mxCQkJuePzSpUvZuXMn999/P4GBgZw4cYIVK1bQs2fPQl1f7EdJFilVKTtOg8mCwcWIR7viressim25S4X8PHEow+K6IiIiIiJSPJMmTeLixYuMHDmSzMxMwsPDC90spUaNGtSoUYM5c+Zw+vRpvL296dy5MytWrLAWsO3duzevv/46CxcuZNmyZfTt25f/9//+X77deAoby9KlS1m6dCmLFy/G09OTV155hQkTJhTpvocOHYqPjw+zZs1ixYoVANStW5fevXsTEHDzGf/NmjVjw4YNPPvss1y+fJkaNWowfPhwXnnllSLFIOXPYLl+TpUUSVxcHLVq1eLUqVOFnjZ2K8tON3F2zl4sGWY8ugTj06demV4vzZzNXT/+h4xsC/+8qxbDA6uW6fVEREREREoqNjYWyHnZlvJlMBh44403mDJlyg3HREdHc99997Fv3z5atWpVjtGJPRX0fVmUd3+1YpFSk7rnLJYMMxgNeHYq+1ks+5JSycjOyRF2VdFbERERERERsTMtF5JSYcnKJvnH0wC43xuA0avsW3rntm6+s4oLQa7OZX49EREREREpXWazmZstrnB01CurVC76FyulIvX/zpOdnAUG8OhSPkuntl8rettZs1hERERERCqlsLAwYmJibrj/xIkTpba0qjCVMkJDQws1TuRGKm2S5bvvvuODDz5gz549HD9+nIkTJxa6eFJWVhb/+Mc/WLZsGUlJSbRt25a33nqLZs2alXHUtyZLtiWnbTPg1qQaTtXcyvyalzNN/CclDYCuat0sIiIiIlIpLV26lOTk5BvuL0qrY5GKoNImWTZt2sShQ4fo2rUr8fHxRTp28uTJfPjhh7z55pvUrVuX119/nbCwMP7zn/9Qo0aNMor41pV2+BLmy+kAeHYtp1ksCclYAKMBOvh4lMs1RURERESkdDVs2NDeIYiUqkpb+HbevHn8+uuvvP/++3h7exf6uNOnT7NkyRLmzp3L2LFj6dGjB5999hkWi4UFCxaUXcC3KIvFQnL0KQBc7vTBObh8ZpXktm5u6emOp6OxXK4pIiIiIiIicjOVNsni4FC80Ddv3ozZbOahhx6ybvP09KR///5s3LixtMK7bWT8kUjWmVQAPLvWKpdrWiwWYq7VY+nip1ksIiIiIiIiUjFU2iRLcR05coSAgAD8/Pxstjdu3Jjff/+d7OxsO0VWOeXOYnEK9sClfuFnFJXEibRMTmdkAWrdLCIiIiIiIhVHpa3JUlwJCQn4+Pjk2e7r60tWVhYpKSl4eXnle+yVK1e4cuWK9fPZs2fLKsxKIeO/V8g4ngSAV2gtDAZDuVw3t3Wzh9GBFl7u5XJNERERERERkYJUmCRLUlJSoZIW9erVw8XFpUTXyi8ZkNum62aJgvnz5xMVFVWia99KkmNyOgo5+rvh2rhquV03t3VzBx8PnBzKJ7EjIiIiIiIiUpAKk2RZv349o0ePLnDcwYMHad68ebGv4+vrS0JCQp7tiYmJODk54e5+45kRzz77LGPGjLF+Pnv2LG3atCl2LJVZ1oWrpP9yGQDPLsEYyinZYcq28GNibj0WLRUSERERERGRiqPC1GSJiIjAYrEU+FWSBAtAo0aNuHDhQp62z7/++isNGza8aUFdLy8vgoODrV+BgYEliqUyy53FYvRypkqL6uV23Z+Sr3LFlFM3R/VYRERERERuD9HR0cyePbvMzm0wGNi/f3+Rjjt06BCRkZFcvXq1TOIqDZ9//jmLFy+2dxi3lQqTZCkvPXv2xMHBgTVr1li3paSksGHDBvr27WvHyCoPU2IGVw9dAMCjc00MjuX3zyi3dXOgixMNqpRs2ZiIiIiIiFQOZZlkadmyJbt27aJRo0ZFOu7QoUNERUUpySI2KsxyoaI6efIk+/btA+Dq1ascO3aMdevWATBkyBDruAYNGlCnTh22bNkCQM2aNXniiSd44YUXcHR0pE6dOsybNw+AZ555pnxvopJK+fE0mC0Y3Bxxb1OjXK9tbd3s61luhXZFREREROTW5eXlRbt27ewdBpmZmTg6Ot50dYVUfJX2b++HH35g6NChDB06lIsXL/LNN99YP1/PZDJhNpttts2fP5/x48fz8ssvM2DAADIyMtiyZQs1apRvwqAyMqdmkbo3p0CxR/tAHFzKL0+XajJz4EpOlrir6rGIiIiIiNjNsmXLcHR05Pz58zbb4+PjcXZ2ts6e2LVrF926dcPd3R1vb29GjBjBhQsXrONjY2MxGAysWLGCJ598El9fXwIDA5kyZQomkwmAyMhIoqKiSE1NxWAwYDAYCA0NtZ7jyJEjDBw4EG9vb9zd3enbty/Hjh0r9L3kt1zIYDDw+uuvM2PGDAICAqhWrRqjR48mNTXVev+5NUX9/f0xGAzUrVvXenxcXBwjR46kWrVquLm50aVLFw4cOGBz3bp16/Lkk0/yxhtvUKdOHdzc3Lh8+TKhoaH069ePtWvX0rBhQzw8POjWrVuee8rIyOCll16iTp06uLi40KhRI1auXGndHxERwfLly/nll1+szy0iIqJQz8RgMPDaa68xdepU/P398fHxYcqUKVgsFrZs2ULz5s2tcZ06dcrm2KlTp9K0aVM8PDyoWbMmw4cPt2ly89///hdvb2+mTJlic1y/fv244447SElJKVSMFVWlnckSERFRqH8gsbGxebY5Ozszd+5c5s6dW/qB3eJSd53BkpmNwckBjw5B5XrtXUmpZF3rAtXZ16Ncry0iIiIiUlbMpmySL6fbNQbPqq4Yi1AGYPDgwYwfP561a9fy5JNPWrd/+umnWCwWhg4dyq5duwgNDaVPnz6sXr2a1NRU6y+6d+/ebXO+adOmMXDgQNasWcOOHTuIioqiQYMGPPHEE4wZM4a4uDhWrlzJ1q1bgZzZJwDHjx+nQ4cONGnShGXLluHg4MCsWbMICwvj999/L1Fn2kWLFtG5c2eWL1/O77//zvPPP09AQABz586lb9++vPzyy7z66qt88803eHt7W6+VkJBAp06d8PDwYOHChXh7e7Nw4UK6devGH3/8QfXq/6tp+emnnxISEsJbb72F0WikSpUqQM5SpIsXLzJ37lzMZjPPPPMMI0eOZNeuXdZjhw0bxo8//siMGTNo1KgRX3/9NSNHjsTX15f777+f6dOnc/HiRX777Tc+/vhjICchVJT779atGytWrGDPnj3MmDEDs9nMli1bmDZtGs7Ozjz11FM89thjbN682XrchQsXeOmllwgKCuLixYu8+eabdO3alV9//RVHR0dq167Nv/71Lx599FH69+9P165deeedd9i0aRMxMTF4eFTud71Km2SR8pedaSZl5xkA3FvXwOjhXK7X33ZtqVBjd1f8nZ3K9doiIiIiImUl+XI6H8/YXfDAMvS3qHb4BFQp9HgvLy/69OnDqlWrbJIsq1atIiwsDH9/f4YMGUKrVq347LPPrEv9mzRpQtOmTfn666/p06eP9bi2bdvyr3/9C4AePXrw/fffs27dOp544glr4xEHB4c8y3qioqLw9fXlu+++w9XVFYAOHTpQr1493nvvPSZMmFDsZ1KjRg1rcqJ3797s27ePdevWMXfuXPz9/alfvz4A9957L9WqVbMet2DBAhITE9m7d681oRIWFkaDBg2YN28er7/+unWsyWRi06ZN1uRKrsTERA4ePGhNiiQmJjJ27Fji4uIIDg7mhx9+4Msvv+Tbb7+lZ8+e1ud2+vRpZsyYwf3330/9+vXx9/fn5MmTxVoOVbNmTZYvXw5Ar169+PLLL3nrrbf45ZdfrPVrTp8+zaRJk0hMTMTHxweA999/33oOs9lM+/btCQ4OZuvWrdZYH3nkEb744gseeeQR1q9fz9///neee+45OnXqVOQ4K5pKu1xIyl/qvnNkXzWBQ07B2/IWk6DWzSIiIiIiFcXw4cPZtWsX//3vfwE4d+4cMTExjBgxgqtXr7Jjxw6GDh2K2WzGZDJhMplo2LAhgYGB1vqauXJfvnM1btyYuLi4AmPYvHkzAwcOxNHR0XoNX19f7rnnnjzXKKqSxHTffffh5+dnjcloNNK5c+c8MYWGhuZJsAA0b97cZtZJ48aNAazX37x5M35+fnTr1s16DZPJRFhYGAcPHsxTMqM4unfvbvM5JCSEoKAgmwLBISEhNnEBbNq0iQ4dOuDt7Y2joyPBwcEAHD161OZ877zzDunp6bRv35769eszc+bMEsdcEWgmixSKxZxNyrbTAFS5pzqOvq7lev3zGVn8npozhbKLWjeLiIiIyC3Es6orf4uyb+FVz6pF///7fv364enpySeffMLzzz/P6tWrcXZ2ZtCgQSQkJGA2m5k8eTKTJ0/Oc+xf63jkzoLI5ezsTHp6wUuoLl26xIIFC1iwYEGefW5ubkW6n7/KL6aMjIxCxbR7926cnPLOvs+d/ZLr+qVDBV0bsD6TS5cuER8fn+81AM6ePWtNbhRXfjEUFNe+ffsYMGAAAwcOZOrUqVSvXh2DwUC7du3y/H1Wq1aNHj16sGLFCsaNG2c9V2WnJIsUytVDFzEn5fxA8exasm/W4sht3exsMNDOp3Kv0RMRERERuZ7R0aFIS3UqCldXVwYNGmRNsnzyySf07dsXLy8vjEYjBoOBl156iUGDBuU59vrlNSXh5+dH3759810W5Olpn1/O+vn50bt3b1555ZU8+/5aI6a4HVP9/Pzw9/fn66+/znf/jZI3ZW39+vV4e3uzZs0aa5ekkydP5jt28+bNfPzxx7Ro0YIZM2bwwAMPEBAQUJ7hlgklWaRAlmwLyTE5079cG/nhVMO93GPIbd3c2tudKkatchMRERERqQiGDx/Ohx9+yLfffsvu3bv59NNPAXB3d6d9+/YcOXKEV199tcTXudEsku7du3P48GFatGiB0Wgs8XWKGhOQZ4ZG9+7dWbFiBY0aNcLdvWzenbp3787rr7+Os7MzzZo1u2mMhZkRVFrS0tJwcnKySR7l1rW5XkJCAo8++igPPfQQS5YsoVmzZowdO5Yvv/yy3GItK3pblQKl/xaP6UJO62TP0Frlfn2LxcL2azNZ1LpZRERERKTi6N69O/7+/jz66KPWYri53njjDTZu3MiDDz7I+vXriY6OZsWKFTzyyCNER0cX6TqNGjXCZDLx1ltvsW/fPn7//Xcgp/DtH3/8Qa9evVizZg0xMTGsXr2aCRMmsGrVqtK81XxjAnj77bfZs2cP//nPfwB49tlnMRgMdO3alY8++oiYmBjWrVvHc889xz//+c9SuXaPHj3o378/vXv3ZsGCBWzdupUNGzYwd+5cxowZYxNjbGwsq1atYv/+/fl23y1NPXr04Ny5c0yaNIktW7bw6quvWovnXm/ChAlYLBbefvttvLy8WL58ORs3buS9994r0/jKg5IsclMWi4Xk6Jz1ks51vXCp41XuMfx+NZ3zmSYAOqsei4iIiIhIheHo6MjQoUM5c+YM4eHh1g4/kNPl58cffyQlJYXRo0fTp08fZs6cSZUqVWjQoEGRrtO/f38mTJjAnDlzaNu2LY8//jgADRo0YO/evVStWpUJEybQq1cvpk6dSmpq6k1neJSGFi1aEBkZyYoVK+jQoQP9+/cHoGrVquzevZvmzZvzwgsv0LNnTyZPnkxsbCxt27Yttevndl9avHgx999/v7WVcteuXa1jHnvsMYYOHcqkSZNo3bo1kZGRpXb9/PTp04fXXnuNL774ggEDBrBt2za++uormzGrV6/mk08+4b333sPX1xeArl27Wuv3lHUiqKwZLBaLxd5BVFZxcXHUqlWLU6dOlbioUEWVcTyJi+/8DEDViLtxu8uv3GN459QF/vHnGXwcjfzSqQnGYq5bFBERERGxt9wXyLp169o1DhH5n4K+L4vy7q+ZLHJTyTE5s1gcA6rg2tDXLjHExKcA0MnXQwkWERERERERqbBU+FZuKPNMCum/JwDgFVqr2JWvSxRDdja7knKSLGrdLCIiIiIiRZGdnU12dvYN9+d2QbqdmEymG+4zGAzlXkD4VqOZLHJDuR2FjL4uuDXzt0sMB65c5ao554eiit6KiIiIiEhRzJw5Eycnpxt+5VeU9VYWGxt70+cRFhZm7xArPc1kkXyZLqeR9vNFADy7BGMw2ie7u+1a6+Y6rs7UcXMpYLSIiIiIiMj/jBs3jn79+t1wf7169coxGvsLCgpi3759N9zv6alfbJeUkiySr7Qj8WABhyqOVLk3wG5xbLvWurmLZrGIiIiIiEgRBQUFERQUZO8wKgxnZ2datWpl7zBuaVouJPkyx6cD4FTDHQdn+6zJS8oycfDKVUD1WERERERERKTiU5JF8mW6lmQx+rkWMLLs7EhMIRswkNNZSERERERERKQiU5JF8pWbZHG0Y5JlW0JOV6Fmnm74Omllm4iIiIiIiFRsSrJIHhaLBXNCBUiyXCt621VLhURERERERKQSUJJF8shOycKSldM22V7LhU6lZ3I8LQNQ0VsRERERERGpHJRkkTxylwoBOPraJ8my/dosFjcHA6293e0Sg4iIiIiIiEhRKMkieeR2FjI4OeDg4WSXGGKutW5u5+OBi4P+mYqIiIiISF6hoaH069fP3mGUyKVLlzAYDCxbtqxIx0VHRzN79uyyCaoEli1bhsFg4NKlS/YOxS709ip5XN9ZyGAwlPv1sy0Wtl9Lsqh1s4iIiIiISF4VNcnSt29fdu3ahY+Pj71DsQu1bJE87N1Z6HBKGvFZZgC6qh6LiIiIiMhtJy0tDTc3N3uHIcXg7++Pv7+/vcOwG81kkTysSRY71WPJ7SpUzcmRu9zt191IRERERERuLCIigiZNmrBp0yaaNGmCq6sr9957L7t377aOMRgMzJs3z+a4efPm2cyYj46OxmAwsHHjRoYMGYKXlxdDhw4FIDExkUmTJhEcHIyLiwv16tXjxRdfzBPL2rVradiwIR4eHnTr1o1jx47Z7J86dSpNmzbFw8ODmjVrMnz4cM6ePWszZseOHXTp0gVvb288PT1p2rQpy5cvtxmzceNG2rZti5ubG/7+/owfP57U1NQiPbd3332XunXrUqVKFcLCwvjzzz/zjPnwww/p1KkTfn5++Pr6Ehoayt69e637IyMjiYqKIjU1FYPBgMFgIDQ01Lr/yJEjDBw4EG9vb9zd3enbt2+eZ3IzuUt+9u7dS1hYGFWqVCEkJIRvv/2W7Oxspk+fTo0aNahevTovvvgi2dnZeY7NXS4UGxuLwWBgxYoVPPnkk/j6+hIYGMiUKVMwmUxFenaVgWaySB657Zvt1VloW+5SIT9PHOywXElEREREpDyZTVlcuXjBrjF4+VfH6Fj0eoxnz55lwoQJREZG4uvry9y5c+nVqxd//PEH1atXL9K5Hn/8cUaOHMn48eNxcHAgIyODbt26ERsby4wZM2jatCmnTp3ixx9/tDnu0KFDXLx4kblz52I2m3nmmWcYOXIku3btso65cOECL730EkFBQVy8eJE333yTrl278uuvv+Lo6MiVK1fo27cvnTp1YtWqVbi4uPDrr7+SmJhoPce6det48MEHGT16NFFRUZw9e5apU6eSkJDAJ598Uqh7/Oqrrxg3bhwRERE89NBD7N+/n4ceeijPuNjYWB5++GHq169PZmYmK1eupEuXLvz888+EhIQwZswY4uLiWLlyJVu3bgXAy8sLgOPHj9OhQweaNGnCsmXLcHBwYNasWYSFhfH777/j4uJS6L+TiIgIxo8fz/PPP8/cuXMZMmQIERERXLlyheXLl7Nnzx7r382IESNueq5p06YxcOBA1qxZw44dO4iKiqJBgwY88cQThY6nMlCSRWxYTNmYk3JaJ9tjuVCaOZs9STmZ4C6+HuV+fRERERGR8nbl4gXef+Zxu8bw6IKl+AbWLPJx8fHxrF27lm7dugHQpUsXatWqxYIFC4pcL2TgwIHMnTvX+vndd9/l4MGD7Ny5k/bt21u3P/LIIzbHJSYmcvDgQesSlcTERMaOHUtcXBzBwcEAvP/++9bxZrOZ9u3bExwczNatW+nZsydHjx4lKSmJOXPm0LRpUwDCwsKsx1gsFqZMmcKDDz7Iv//9b+v2gIAA+vXrx/Tp07n77rsLvMdXX32Vzp0788EHHwDQq1cvUlNTmTNnjs24f/zjH9Y/Z2dn06NHD/bt28eyZcuYPXs2wcHBBAcH4+DgQLt27WyOjYqKwtfXl++++w5X15x3ug4dOlCvXj3ee+89JkyYUGCcuZ566ilrEqRmzZo0bdqUffv2WWcr9erViy+//JK1a9cWmGRp27Yt//rXvwDo0aMH33//PevWrbvlkixaLiQ2zIkZYMn5sz2SLPuSUsnIzglARW9FRERERCo2b29va4IFwMfHh27dutksGSqsPn362HzesmULjRo1skmw5Kd58+Y2NUAaN24MQFxcnHXbpk2b6NChA97e3jg6OlqTL0ePHgWgfv36eHl5MX78eNasWcPFixdtrnH06FFOnjzJsGHDMJlM1q+uXbtiMBjYv39/gfdnNps5cOAA4eHhNtuHDBmSZ+yRI0cIDw8nICAAo9GIk5MTv//+uzXem9m8eTMDBw7E0dHRGqevry/33HMP+/btK/D463Xv3t3655CQkDzbcrefOnWqwHP17NnT5nPjxo1t/o5uFZrJIjZy67EAGO1QkyW3dfOdVVwIcnUu9+uLiIiIiJQ3L//qPLpgqd1jKI78CpxWr169UMmA/I673uXLlwkKCirwuL92sXF2znmPSE/PebfZt28fAwYMYODAgUydOpXq1atjMBho166ddUzuzI8ZM2YwatQoTCYTnTt3ZuHChTRt2tRaX+SvCZJchUkyXLx4EZPJlOc+AwICbD4nJyfTs2dP/P39mT9/PnXq1MHV1ZUxY8ZY472ZS5cusWDBAhYsWJBnX1GLCV//bHOfa37PuzBxFfe4ykZJFrFhulaPxcHDCQcXY7lfP7forWaxiIiIiMjtwujoVKylOhXBX2d8QE79k8DAQABcXFzIzMy02R8fH5/vuQx/qcdYtWpVfv755xLHuH79ery9vVmzZg0ODjmLOU6ePJlnXJs2bdi0aRNpaWn88MMPTJkyhUGDBnHs2DH8/PwAWLRoEW3bts1zbGGSQf7+/jg6OnLhgm39nfPnz9t83rVrF3FxcXz11Vfcc8891u1JSUnWGTg34+fnR9++ffNdFuTpqfessqYki9gw27Gz0OVME/9JSQNyit6KiIiIiEjFlpSUxNatW61LhnI/P/nkkwAEBwdz5MgRm2O+//77Qp27e/furF69mt27d+epO1IUaWlpODk52SRxPv744xuOd3Nzo0+fPhw7doynn36a9PR07rrrLoKDgzl+/DgTJ04sVhxGo5GWLVuyfv16Jk+ebN2+bt26PPHC/2aOAOzcuZPY2Fibui/Ozs5kZGTkuU737t05fPgwLVq0wGgs/1+c3+6UZBEbucuF7NFZaPu1pUJGA3TwUdFbEREREZGKzs/Pj8cee4yoqCh8fHyshWufeeYZIKfeyIIFC2jTpg0hISF8+OGHnDt3rlDnHjVqFIsXL6Zfv37MmDGDJk2acPr0abZt28Y777xT6Bh79OjBggULmDRpEuHh4ezatYuPPvrIZszGjRt57733CA8Pp3bt2pw7d46FCxfSsWNHa/HY+fPnM2LECFJTU+nbty/u7u6cPHmSjRs3Mnv2bGvNkpvJ7bAzevRoa3ehlStX2oxp164dHh4eTJw4kalTp3L69GkiIyOpWdN2tlOjRo0wmUy89dZbdOjQAS8vLxo2bEhUVBStW7emV69ejBs3joCAAM6dO0dMTAydO3dm+PDhhX52UnQqfCs2cpcL2aPobW7r5nu93PF0VMZVRERERKSiCwwMZNGiRcydO5ehQ4eSnp7Ot99+a60zMn36dEaMGEFkZCSjRo2iXr161lkuBXFxcWHLli0MGzaM2bNn07t3b2bMmFHk1tB9+vThtdde44svvmDAgAFs27aNr776ymZMgwYNcHBwYNq0afTs2ZNnn32Wjh07snbtWuuYoUOH8vXXX/Pbb78xfPhwBgwYwJtvvkndunXz1FW5kQEDBrBkyRK2bNnCoEGD+O6771i1apXNmICAANauXcuFCxcYOHAgCxYsYMmSJTRo0MBmXP/+/ZkwYQJz5syhbdu2PP7449Z72bt3L1WrVmXChAn06tWLqVOnkpqaSrNmzYr07KToDBaLxWLvICqruLg4atWqxalTpwq1Nq4yODNzF9lXTfg+cCfurWuU23UtFgutdv3K6Yws/l43gOfqBZbbtUVEREREyktsbCwAdevWtWscpSEiIoL9+/dz+PBhe4ciUiIFfV8W5d1fM1nEKjvdRPZVE1D+nYVOpGVyOiMLgK4qeisiIiIiIiKVkGqyiNX17ZvLe7lQbutmD6MDLbzcy/XaIiIiIiIiJWU2m7nZQhFHx4rx+p2dnU12dvYN9xuNxjydnqTwNJNFrHI7C+EARm+Xcr329mutmzv6euDkoG9oEREREZGKbtmyZVoqdJ2wsDCcnJxu+JW7JMXeZs6cedM4ly9fbu8QK7WKkUqTCsHaWcjHFYOx/BIdpmwLPybmJFk6a6mQiIiIiIhUQkuXLiU5OfmG+4OCgsoxmhsbN24c/fr1u+H+evXqlWM0tx4lWcTKXp2Ffkq+yhVTznQ11WMREREREZHKqGHDhvYOoVCCgoIqTMLnVqTlQmKVu1zIsZyL3ubWYwlycaJBlfJdpiQiIiIiIiJSWpRkESvrcqFynsmyLf5/S4VUYElEREREREQqKyVZBABLtuW65ULlN5sk1WTmwJWrAHT101IhERERERERqbyUZBEAslMywZTTbszRz63crrszMYWsa23OOvt6lNt1RUREREREREqbkiwC/G+pEIDRt/xmsmxPSAGgsbsr/s5O5XZdERERERERkdKmJIsA/0uyGJyNOLiXX7Ijt+htFy0VEhERERERkUpOSRYBruss5OdSbsVnz2Vk8XtqznXVullERERERIoqNDSUfv362TuMErl06RIGg4Fly5YV6bjo6Ghmz55dNkFJsSnJIsD1nYXKrx7L9muzWJwNBtr6qB6LiIiIiIhIYSnJUjEpySIA/+ssVI71WGKutW5u7e1OFaP+KYqIiIiISI60tDR7hyBSLHqzFeD65UKu5XI9i8Vincmi1s0iIiIiIpVPREQETZo0YdOmTTRp0gRXV1fuvfdedu/ebR1jMBiYN2+ezXHz5s2zKVEQHR2NwWBg48aNDBkyBC8vL4YOHQpAYmIikyZNIjg4GBcXF+rVq8eLL76YJ5a1a9fSsGFDPDw86NatG8eOHbPZP3XqVJo2bYqHhwc1a9Zk+PDhnD171mbMjh076NKlC97e3nh6etK0aVOWL19uM2bjxo20bdsWNzc3/P39GT9+PKmpqUV6bu+++y5169alSpUqhIWF8eeff+YZ8+GHH9KpUyf8/Pzw9fUlNDSUvXv3WvdHRkYSFRVFamoqBoMBg8FAaGiodf+RI0cYOHAg3t7euLu707dv3zzP5GaWLVuGwWBg7969hIWFUaVKFUJCQvj222/Jzs5m+vTp1KhRg+rVq/Piiy+SnZ1tPfa3337joYceolatWlSpUoXGjRvz5ptv2oxZsGABzs7OHDx40LrtxIkTeHp68vzzzxc6zorI0d4BiP1ZTNmYr2QCYCynJMvvV9M5n2kCoIvqsYiIiIjIbcxiysaUmGHXGBx9XDA4Fv138GfPnmXChAlERkbi6+vL3Llz6dWrF3/88QfVq1cv0rkef/xxRo4cyfjx43FwcCAjI4Nu3boRGxvLjBkzaNq0KadOneLHH3+0Oe7QoUNcvHiRuXPnYjabeeaZZxg5ciS7du2yjrlw4QIvvfQSQUFBXLx4kTfffJOuXbvy66+/4ujoyJUrV+jbty+dOnVi1apVuLi48Ouvv5KYmGg9x7p163jwwQcZPXo0UVFRnD17lqlTp5KQkMAnn3xSqHv86quvGDduHBERETz00EPs37+fhx56KM+42NhYHn74YerXr09mZiYrV66kS5cu/Pzzz4SEhDBmzBji4uJYuXIlW7duBcDLywuA48eP06FDB5o0acKyZctwcHBg1qxZhIWF8fvvv+PiUvjVCxEREYwfP57nn3+euXPnMmTIECIiIrhy5QrLly9nz5491r+bESNGAHD69GkaNmzI3/72Nzw9PTl06BAzZswgNTWVf/zjHwA8/fTTbNiwgZEjR3LgwAGcnZ15+OGHqVevHq+88kqh46uIlGSRnKVClpw/l9dMlm3Xlgr5OBpp6ll+dWBERERERCoaU2IG5+ftt2sMAVNa4VSt6P9fHh8fz9q1a+nWrRsAXbp0oVatWixYsKDI9UIGDhzI3LlzrZ/fffddDh48yM6dO2nfvr11+yOPPGJzXGJiIgcPHsTf39/6eezYscTFxREcHAzA+++/bx1vNptp3749wcHBbN26lZ49e3L06FGSkpKYM2cOTZs2BSAsLMx6jMViYcqUKTz44IP8+9//tm4PCAigX79+TJ8+nbvvvrvAe3z11Vfp3LkzH3zwAQC9evUiNTWVOXPm2IzLTUYAZGdn06NHD/bt28eyZcuYPXs2wcHBBAcH4+DgQLt27WyOjYqKwtfXl++++w5X15z3uw4dOlCvXj3ee+89JkyYUGCcuZ566imeeOIJAGrWrEnTpk3Zt2+fdbZSr169+PLLL1m7dq01yRIWFmZ9dhaLhU6dOnH16lUWLVpkva/cQr9NmzblpZdeIiAggL1797J3794iJYEqIi0XEswJ/8uaG33LJ8kSE58CQCdfD4zl1M1IRERERERKl7e3tzXBAuDj40O3bt1slgwVVp8+fWw+b9myhUaNGtkkWPLTvHlza4IFoHHjxgDExcVZt23atIkOHTrg7e2No6OjNfly9OhRAOrXr4+Xlxfjx49nzZo1XLx40eYaR48e5eTJkwwbNgyTyWT96tq1KwaDgf37C06Smc1mDhw4QHh4uM32IUOG5Bl75MgRwsPDCQgIwGg04uTkxO+//26N92Y2b97MwIEDcXR0tMbp6+vLPffcw759+wo8/nrdu3e3/jkkJCTPttztp06dsn5OT09nxowZNGjQABcXF5ycnJg2bRpnz54lJSXFOq5WrVosXLiQBQsWMH36dF555RXuueeeIsVXEWkmi2CKzykq5eDhhIOzscyvl5mdza6knG8u1WMRERERkdudo48LAVNa2T2G4rg+uZGrevXqhUoG5Hfc9S5fvkxQUFCBx/n4+Nh8dnZ2BnJe9gH27dvHgAEDGDhwIFOnTqV69eoYDAbatWtnHZM782PGjBmMGjUKk8lE586dWbhwIU2bNuXSpUsAeRIkua5PMtzIxYsXMZlMee4zICDA5nNycjI9e/bE39+f+fPnU6dOHVxdXRkzZow13pu5dOkSCxYsYMGCBXn2ubkVbbbS9c8297nm97yvj+uFF17g3XffZcaMGdx77734+PjwxRdf8Oqrr5Keno6Hx/86y/bv3x8PDw8yMzMZM2ZMkWKrqJRkEUzxOTNZymup0IErV7lqzil6pHosIiIiInK7Mzg6FGupTkXw1xkfkFP/JDAwEAAXFxcyMzNt9sfHx+d7LsNfZrhXrVqVn3/+ucQxrl+/Hm9vb9asWYODQ85ijpMnT+YZ16ZNGzZt2kRaWho//PADU6ZMYdCgQRw7dgw/Pz8AFi1aRNu2bfMcW5hkkL+/P46Ojly4cMFm+/nz520+79q1i7i4OL766iubmR1JSUnWGTg34+fnR9++ffNdFuTpWfbvX2vXruXxxx/nhRdesG7buHFjvmMnTpyIl5cXWVlZPPPMM3z44YdlHl9ZU5JFMF+byVJeRW9z67HUcXWmjlvlXm8nIiIiInI7S0pKYuvWrdYlQ7mfn3zySQCCg4M5cuSIzTHff/99oc7dvXt3Vq9eze7du/PUHSmKtLQ0nJycbJI4H3/88Q3Hu7m50adPH44dO8bTTz9Neno6d911F8HBwRw/fpyJEycWKw6j0UjLli1Zv349kydPtm5ft25dnnjhfzNHAHbu3ElsbKxN3RdnZ2cyMvIWTO7evTuHDx+mRYsWGI1lv1Lhr9LS0mxiN5vN+RYGXrNmDStXruSbb74hIyODgQMHMmjQIAYPHlye4ZY6JVkEU0L5zmSJUetmEREREZFbgp+fH4899hhRUVH4+PhYC9c+88wzQE69kQULFtCmTRtCQkL48MMPOXfuXKHOPWrUKBYvXky/fv2YMWMGTZo04fTp02zbto133nmn0DH26NGDBQsWMGnSJMLDw9m1axcfffSRzZiNGzfy3nvvER4eTu3atTl37hwLFy6kY8eO1uKx8+fPZ8SIEaSmptK3b1/c3d05efIkGzduZPbs2daaJTczbdo0Bg4cyOjRo63dhVauXGkzpl27dnh4eDBx4kSmTp3K6dOniYyMpGbNmjbjGjVqhMlk4q233qJDhw54eXnRsGFDoqKiaN26Nb169WLcuHEEBARw7tw5YmJi6Ny5M8OHDy/0syuOHj168O6779K4cWP8/f15++238ySDzp49y/jx43niiSfo1asXAI8++iiPP/44HTt2zLOEqjJR4VvBdDln/ZxjORS9TcoycejKVQA6a6mQiIiIiEilFhgYyKJFi5g7dy5Dhw4lPT2db7/91vqSPH36dEaMGEFkZCSjRo2iXr161lkuBXFxcWHLli0MGzaM2bNn07t3b2bMmFHk1tB9+vThtdde44svvmDAgAFs27aNr776ymZMgwYNcHBwYNq0afTs2ZNnn32Wjh07snbtWuuYoUOH8vXXX/Pbb78xfPhwBgwYwJtvvkndunULnRQYMGAAS5YsYcuWLQwaNIjvvvuOVatW2YwJCAhg7dq1XLhwgYEDB7JgwQKWLFlCgwYNbMb179+fCRMmMGfOHNq2bcvjjz9uvZe9e/dStWpVJkyYQK9evZg6dSqpqak0a9asSM+uOBYuXEjXrl2ZNGkSjz76qLWD0PUeffRRfH19mTdvnnXbggUL8PDwYOzYsWUeY1kyWCwWi72DqKzi4uKoVasWp06dKtTauIoo+2oWZ2bmVP6uNrYprvV9yvR6X19M5NHDsRiAXzs1wddJk6lERERE5PYRGxsLQN26de0aR2mIiIhg//79HD582N6hiJRIQd+XRXn310yW25zpuvbN5bFcKOZaPZZ7PKsowSIiIiIiIiK3FL3l3uZM8ddabTkYMHqXfRHa7Qk5rZu7+HoUMFJERERERKTyMJvN3GyhiKNjxXj9zs7OJjs7+4b7jUZjnk5PUniayXKbM19Lshh9XTA4lO030qn0TI6n5cyc6aKityIiIiIildqyZcu0VOg6YWFhODk53fArd0mKvc2cOfOmcS5fvtzeIVZqFSOVJnZjSrhW9LYclgrltm52czDQ2tu9zK8nIiIiIiJSXpYuXUpycvIN9wcFBZVjNDc2btw4+vXrd8P99erVK8dobj1KstzmcpcLlUdnoW3XWje38/HAxUGTqERERERE5NbRsGFDe4dQKEFBQRUm4XMr0pvubc66XKiMZ7JkWyxsv5Zk6aLWzSIiIiIiInILUpLlNmbJtpTbcqHDKWnEZ5kB6Kp6LCIiIiIiInILUpLlNmZOzgRzTvXrsk6y5NZjqebkSCP3sl+aJCIiIiIiIlLelGS5jeUuFQIwlnFNltx6LF38PNUOTERERERERG5JSrLcxnKL3hpcjDhUKbsayGnmbPYkpQLQxdejzK4jIiIiIiIiYk9KstzGrJ2F/FzLdHbJvqRUMrJzliWp6K2IiIiIyO3DYDAwb968Ep3j888/Z/HixXm2R0ZG4uFRtF/ihoaG3rR9cWEtWLCAr7/+usTnuV5sbCwGg4F169YV+bjIyEjOnDlTqvGUpujoaGbPnm3vMMqFkiy3MWtnoTJeKhRzbanQnVVcCHJ1LtNriYiIiIjIreVGSZYxY8bwww8/2CGiskmyBAYGsmvXLrp161ak42JjY4mKilKSpYIouzUiUuGVV2eh3KK3msUiIiIiIiKlJTg4mODgYHuHUWpcXFxo166dvcPAbDaTnZ2Nk5OTvUOplDST5TZ2/XKhsnIp08R/UtIAtW4WEREREbmVRERE0KRJE6Kjo2nRogXu7u60adOGAwcO2IwzmUw8//zz+Pv74+npSUREBMnJyYW+xvLly/nll18wGAwYDAYiIiKA/JcLJSYmMmnSJIKDg3FxcaFevXq8+OKLNzx/eno6/fv3p27duvz5558AxMXFMXLkSKpVq4abmxtdunSxuae6dety8uRJ3n77bWtMy5YtA+DLL7+kVatWeHh44OPjQ6tWrQo94yW/5UJ169blySefZNGiRdSpUwdvb28GDRrExYsXgZwZIvfddx8ArVu3tsZz/fOYMGECgYGBuLi4cO+997J582ab6+YuoVq+fDkNGzbExcWFQ4cOFfrv12KxMG/ePEJCQnBxceGOO+7gn//8p3V/ZGQkUVFRpKamWuMLDQ0t1DOpjDST5TZlycom+0omAMYyTLL8eG2pkNEA7X1U9FZERERE5FZy7tw5nnrqKaZOnYqXlxdTp04lPDycY8eOWWdCLFy4kJYtW7J8+XJOnDjB1KlTSU9P55NPPinw/NOnT+fixYv89ttvfPzxxwD4+/vnOzYjI4Nu3boRGxvLjBkzaNq0KadOneLHH3/Md3xKSgoDBw4kLi6O7du3U6tWLRISEujUqRMeHh4sXLgQb29vFi5cSLdu3fjjjz+oXr0669evp0+fPnTq1Im///3vANSvX59jx44xZMgQhg8fzpw5c8jOzuann34iISGhOI/W6ssvv+SPP/7g7bff5tKlSzzzzDNMmjSJTz75hJYtW/L2228zceJEPvjgA+666y7rcZmZmfTo0YPz588za9YsatasyYoVK+jbty//93//R9OmTa1j9+/fz3//+19eeeUVfHx8qFWrFlC4v9+nn36af//730ybNo22bduyc+dOXnjhBdzc3HjiiScYM2YMcXFxrFy5kq1btwLg5eVVomdSkSnJcpvKXSoEZTuTJbd1871e7ng6GsvsOiIiIiIilZXJZCIpKcmuMXh7e+PoWPTXw/j4eGJiYrj77rsBcHV1pUePHuzZs4dOnToBOctgPv/8c4xGo3XM2LFjiYyMtEkK5Kd+/fr4+/tz8uTJApfSfPjhhxw8eJCdO3fSvn176/ZHHnkkz9jExETuv/9+rl69yvbt26levTqQU2slMTGRvXv3WreFhYXRoEED5s2bx+uvv06LFi1wcXEhICDAJqaYmBiysrJYtGgRnp45s/h79ep105gLw2Kx8OWXX+Li4gLAn3/+yeuvv052djZeXl40btwYgCZNmtCqVSvrcR9//DGHDh3ip59+so7p1asXR48e5ZVXXmHNmjXWsQkJCezfvz/P8quC/n6PHTvGokWLWLJkCePGjQOge/fupKSkEBUVxbhx46zLuhwcHCrEcqiypiTLbcomyeLrUibXsFgsxKgei4iIiIjITSUlJbFw4UK7xjBp0iSqVq1a5OOCgoKsL+CA9WU+Li7Ouq1///7WBAvA4MGDGTNmDHv37i0wyVIUW7ZsoVGjRjYJlvxcunSJ0NBQXF1diY6OxtfX17pv8+bN3Hffffj5+WEymQAwGo107tyZffv23fS8zZo1w2g0MmLECMaNG0eXLl3w9vYu8X117drVmmCBnGeclZXFhQsXqFGjxg2P27x5M02bNiUkJMR6L5CTNFq1alWe2POrb1PQ3+/3338PwAMPPJDnGm+88QanTp2iTp06RbndSk9JlttUbmchB09nDE5lM8PkRFompzOyAOjiq6VCIiIiIiK3Gh8fH5vPzs453UTT0//3S93cGSG5fH19cXJy4uzZs6Uay+XLlwkKCipw3NGjR0lISGDBggU2CRbIScDs3r0736Kv9evXv+l5Q0JC+Oqrr5g9ezbh4eE4ODjQu3dvFi1aRO3atYt2M9cpzDPOz6VLlzh48GC+93J90gvy/h0V9tqXLl3CYrFQrVq1fI9XkkVuG+VR9Da3dbOH0YEWXu5ldh0RERERkcrM29ubSZMm2T2GsnLhwgWbzwkJCWRlZREYGFiq16latSo///xzgeM6dOhA9+7defbZZ/Hz82PUqFHWfX5+fvTu3ZtXXnklz3HXzya5kd69e9O7d2+uXLnCN998w+TJkxk9ejRbtmwp2s2UAj8/P5o1a8Z7771X4Njri+UW9RoGg4Eff/zRmoC5XsOGDYt13spMSZbblLkckiy5rZs7+nrg5FC8b1oRERERkVudo6NjsZbqVBYbNmxg/vz51tkTn332GQaDgdatWxfqeGdn5wJnbUBOLZDVq1eze/fuAmt/PPPMM6SlpTF69GhcXFwYNmyY9RwrVqygUaNGuLvf+BfFBcXk5eXFsGHD2LNnT56lOaXtRjNbunfvztdff01QUFChZvgUR1hYGJAzi6h///43jTEjI6NMYqholGS5TeXOZDGWUT0WU7aFHYmqxyIiIiIicrvLyMhg0KBBTJgwgRMnTvDCCy8wZMgQGjVqVKjjGzVqxPvvv8+qVau48847qVatGnXr1s0zbtSoUSxevJh+/foxY8YMmjRpwunTp9m2bRvvvPNOnvEvvvgiaWlpjBw5EldXVwYMGMCzzz7Lxx9/TNeuXXn66aepXbs2Fy9eZM+ePQQFBTF58mRrTFu3buW7777D19eXevXqsW7dOnbu3Mn9999PYGAgJ06cYMWKFfTs2bNEz68gISEhGI1G3n//fYxGI05OTrRq1YqHH36YpUuXEhoaypQpUwgJCSExMZGDBw+SmZnJnDlzSuXaEydOZNSoUTz33HO0bduWrKwsjh49yg8//MDnn38O5Dwvk8nEW2+9RYcOHfDy8rplZ7koyXKbyi186+jnVibn/yn5KldM2YCSLCIiIiIit7NJkyZx8eJFRo4cSWZmJuHh4SxatKjQxz/22GPs3buXSZMmcfnyZR555BGWLVuWZ5yLiwtbtmxh2rRpzJ49m/j4eIKDgxk+fPgNzz1z5kzS0tIYNmwYX3zxBb169WL37t28/PLLvPDCC1y+fJnq1avTrl07wsPDrcfNnj2b8ePH88ADD5CcnMwHH3xAs2bN2LBhA88++yyXL1+mRo0aDB8+PN+lR6WpWrVqvP3227z++ut89NFHmEwmLBYLLi4ubN26lcjISGbNmsXZs2epVq0aLVq0YMKECaV2/X/96180bNiQpUuXMnPmTNzd3WnYsKF1dhDkFD+eMGECc+bM4cKFC3Tp0oXo6OhSi6EiMVgsFou9g6is4uLiqFWrFqdOncq3EnNFlX01izMzdwPgP64pLnf4lPo15see4/UT5whyceJA+8bFXuMnIiIiInIriY2NBch3JoaI2EdB35dFefd3KOXYpBIwJfxvLZyxjGqybLuudbMSLCIiIiIiInI70HKh25ApPi3nD0YDRq/Sr8mSajJz4MpVALr4aamQiIiIiIjkz2w2c7PFFY6Ot8Yrq8ViwWw233C/g4MDDg6aA3Er0N/ibcgcnzOTxejjgqEMuv7sTEwh69oPys6+HqV+fhERERERuTWEhYXh5OR0w6/cZRyV3fLly296nzNnzrR3iFJKbo20oBRJ0qYTAJgvF9wGrTi2J6QAcLeHK/7OTmVyDRERERERqfyWLl1KcnLyDfeXVevh8ta/f3/27dt3w/23yn2KkixSBmIScn5IdlZXIRERERERuYlbtY3vX1WtWpWqVavaOwwpB1oudBvy6lEHAL+/Fa4vfVGcy8ji99ScGTJdlWQRERERERGR24hmstyGvMJq4xVWu0zOve3aLBZng4G2PqrHIiIiIiIiIrcPzWSRUpXburm1tztVjPrnJSIiIiIiIrcPvQVLqbFYLGy/NpOlq1o3i4iIiIiIyG1GSRYpNb+lpnM+0wRAF9VjERERERERkduMkixSanJnsfg6Gmnq6WbnaERERERERETKl5IsUmpi4lMA6OjrgdFgsHM0IiIiIiJSliIjI/HwuLWaXYSGhtKvXz/r52XLlmEwGLh06VKhjo+Ojmb27NllFZ5UAkqySKnIzM5mV1JOkkX1WEREREREbn1jxozhhx9+sHcYpWrx4sW8+eabxT5eSRZRC2cpFQeuXOWqORtQPRYRERERkdtBcHAwwcHB9g6jVDVu3LjcrpWeno6rq2u5XU/Kh2aySKnIbd1cx9WZOm4udo5GRERERETK2vXLhbKysnjuueeoU6cOLi4uBAYG0r9/f5KSkgp9vl27dtGtWzfc3d3x9vZmxIgRXLhwwbo/NjYWg8HAhx9+yNixY/Hx8cHf35958+YB8Mknn9CwYUO8vLwYPHgwiYmJ1mNTU1N58sknadiwIVWqVKFu3bo88cQTeeL763Khoj6PqKgoUlNTMRgMGAwGQkNDbZ7V3r17ad++Pa6urixcuJDo6GgMBgP79++3OVe/fv2sx+Y6cuQIAwcOxNvbG3d3d/r27cuxY8eKFauUHc1kkVIRo9bNIiIiIiK3rTlz5rBkyRJee+017r77bi5dusTmzZvJyMgo1PG7du0iNDSUPn36sHr1alJTU3n55ZcZMGAAu3fvthn78ssvM3ToUNauXcvnn3/Oc889x6VLl4iJieH111/nypUrTJo0ieeff5533nkHgKtXr2I2m5k1axb+/v6cOnWKWbNmER4eztatW0vlGYwZM4a4uDhWrlxpPaeXl5d1f2ZmJn/729+YPHkyc+bMwdfXl4SEhEKd+/jx43To0IEmTZqwbNkyHBwcmDVrFmFhYfz++++4uOgX3RVFpU2yfPfdd3zwwQfs2bOH48ePM3HiRBYtWlSoYw35FGUNCAjg3LlzpR3mbSEpy8ShK1cBLRUSERERESmq7OxM0tNP2zUGV9eaODg4F/v4vXv30rNnTyZMmGDd9sADDxT6+KlTp9KqVSs+++wz6/takyZNaNq0KV9//TV9+vSxju3QoYO1bkq3bt349NNPWbRoESdPnqRq1aoA/PTTT7z33nvWJIu/vz//7//9P+s5TCYT9erVo1OnThw9epSQkJBi33uu3OVTDg4OtGvXLs/+rKwsZs+ezdChQ63boqOjC3XuqKgofH19+e6776xLjDp06EC9evV47733bJ672FelTbJs2rSJQ4cO0bVrV+Lj44t8/KRJkxgxYoT1s7Nz8X+g3O52JKaQDRjI6SwkIiIiIiKFl55+ml27u9s1hvbtvqdKlXrFPr5ly5a88cYbREZG0rdvX+69914cHApXneLq1avs2LGDefPmYTabrdsbNmxIYGAg+/bts0mydO/+v2dlNBq54447cHBwsCZYAEJCQkhMTCQlJcW6pOmjjz5i/vz5/PHHH6SmplrHllaSpTCuv4+i2Lx5Mw899BCOjo6YTCYARA6P1AAARpVJREFUfH19ueeee9i3b19phiglVGlrssybN49ff/2V999/H29v7yIfX7t2bdq1a2f9atmyZRlEeXuIuVaP5R7PKvg6Vdq8nYiIiIiIFNO0adN44YUXWL58OW3atKFGjRpERUVhsVgKPDYhIQGz2czkyZNxcnKy+Tpz5gynTp2yGe/j42Pz2dnZOd9tkFNcFmD9+vU8/PDDtGnThjVr1rB7927Wr19vM6asValSBXd392Ide+nSJRYsWJDn+ezcuTPP8xH7qrRvxIXNikrZ256g1s0iIiIiIsXl6lqT9u2+t3sMJeHi4kJkZCSRkZH8+eefvP/++0RGRnLHHXcwatSomx7r4+ODwWDgpZdeYtCgQXn2V6tWrUSxAaxdu5bmzZuzdOlS67aYmJgSn7co8itbkbv0JzMz02Z7fHy8zWoLPz8/+vbtm++yIE9PvYdVJJU2yVJSc+fO5cUXX8Td3Z1evXrxxhtvULt2bXuHVemcSs/keFpOMavOWiokIiIiIlJkDg7OJVqqU9E0aNCA2bNns3TpUo4cOVLgeHd3d9q3b8+RI0d49dVXyySmtLS0PCUiPv7441K/jrOzc6GL/QLWFthHjhyhQ4cOAFy4cIGff/6ZVq1aWcd1796dw4cP06JFC4xGY+kGLaXqtkyyPPzww/Tr14+AgAAOHz7MK6+8QqdOnfjpp5/w9fW94XFXrlzhypUr1s9nz54tj3ArtNzWzW4ODrT2Lt7UNxERERERqdwGDRrEvffeS4sWLXB3d2fDhg3Ex8fTrVu3Qh3/xhtv0K1bNx588EEeeughfH19iYuL47vvvmP06NF52hkXVY8ePZg4cSIzZ86kQ4cObNq0iS1btpTonPlp1KgRJpOJt956iw4dOuDl5UXDhg1vOD44OJi2bdsSFRWFt7c3RqORuXPn5imJERUVRevWrenVqxfjxo2zNm6JiYmhc+fODB8+vNTvRYqnwiRZkpKSCpW0qFevXonbUy1fvtz65y5dutCpUydatmzJu+++y/PPP3/D4+bPn09UVFSJrn2ryW3d3M7HHRct4RIRERERuS117NiRNWvW8Oabb2IymWjYsCErV660KVJ7Mx06dODHH39kxowZjB49mszMTIKDgwkLC6NBgwYlju/xxx/n+PHjLFq0iHnz5tGrVy9WrlyZbxegkujfvz8TJkxgzpw5XLhwgS5duhTYQejjjz9m7NixREREEBgYyKuvvspHH31ESkqKdUyDBg3Yu3cvL7/8MhMmTCAlJYXAwEC6dOlCs2bNSvUepGQMlsJUIioHy5YtY/To0QWOO3jwIM2bN7fZVrduXfr161foFs75ufvuu2nSpAmrV6++4Zj8ZrK0adOGU6dOWad53U6yLRaa7DhMfJaZGfWDGF+7ur1DEhERERGp0GJjY4GcdxgRqRgK+r6Mi4ujVq1ahXr3rzAzWSIiIoiIiLDb9QuTa/Ly8sLLy6scoqkcDqekEZ+V02JNRW9FRERERETkdldhkiz2dOjQIY4ePcqjjz5q71AqldzWzf7OjjRyd7VzNCIiIiIiUhGZzeab/lLb0bFyvJZmZ2eTnZ19w/1GozHfDkJye6kc/5rzcfLkSfbt2wfA1atXOXbsGOvWrQNgyJAh1nENGjSgTp061qJG8+bN4/jx43Tt2pXq1atz+PBhZs2aRa1atRgzZkz530gltv1aPZYuvp76YSIiIiIiIvkKCwu7abvkEydOVIrlU48++qhNfc+/+uGHH0pcoFcqv0qbZPnhhx9sarh88803fPPNN4Dt0h+TyYTZbLZ+btiwIZ9++imffPIJycnJ+Pv707dvX1599VV8fHzKLf7KLs2czZ6kVECtm0VERERE5MaWLl1KcnLyDfcHBQWVYzTFFxkZyZNPPnnD/TfrIiS3jwpT+LYyKkrxm1tNTHwyD/50DICDHRoT6OJcwBEiIiIiIqLCtyIVT2kWvlXPXSmWbdeWCt1ZxUUJFhERERERERGUZJFi2hb/v3osIiIiIiIiIqIkixTDpUwT/0lJA9S6WURERERERCSXkixSZD9eWypkNEAHHxW9FREREREREQElWaQYcuux3Ovljoej0c7RiIiIiIiIiFQMSrJIkVgsFmJUj0VEREREREQkDyVZpEhOpGVyOiMLUD0WEREREREpuejoaGbPnl3k40JDQ+nXr18ZRCRSfEqySJHEXFsq5GF0oLlnFTtHIyIiIiIilV1xkyyLFy/mzTffLIOIRIrP0d4BSOWS27q5o68HTg4GO0cjIiIiIiK3q8aNG9s7BJE8NJNFCs2UbbF2FlI9FhERERER+fzzz2nRogWurq7UqFGDiRMnkpKSAuTMUDEYDHz99dcMHjwYd3d3AgMDbWatREZGEhUVRWpqKgaDAYPBQGhoaKGu/dflQpGRkXh4ePDzzz/TqVMnqlSpQpMmTfj2229L9Z5FbkZJFim0n5KvkmzOBlSPRURERETkdvfll18yePBgQkJCWL9+PdOnT+ejjz5i0KBBNuPGjRtH/fr1+eyzzxg5ciTTpk1jyZIlAIwZM4bHHnsMNzc3du3axa5du1i8eHGxY8rKymLkyJFERESwfv16qlWrxgMPPMDly5dLcqsihablQlJoufVYglycqO/mYudoRERERERuDZnZ2cSlZ9k1hmBXJ5wdivY7+MjISFq3bs3q1aut2/z8/BgxYgTR0dHWbd26deONN94AoFevXpw7d45Zs2Yxbtw4goODCQ4OxsHBgXbt2pX4PjIzM5k7dy59+vQBoH79+tx5551s2rSJkSNHlvj8IgVRkkUKbdt1rZsNBtVjEREREREpDXHpWXTYc8SuMexs24g7qhT+F6kpKSkcOnTImjzJNXToUB5++GG2b99O586dAQgPD7cZM3jwYFasWEFcXBy1a9cuefDXcXBwoHv37tbPDRo0wNnZmbi4uFK9jsiNaLmQFEqqycz+K6mAlgqJiIiIiNzuEhMTsVgs1KhRw2a7o6MjVatWJT4+3rqtevXqNmNyP589e7bU43Jzc8PZ2dlmm5OTE+np6aV+LZH8aCaLFMrOxBRMlpw/d/L1sG8wIiIiIiK3kGBXJ3a2bWT3GIrCx8cHg8HA+fPnbbabTCYuX76Mn5+fdduFCxdsxuR+DgwMLGa0IhWXkixSKNuu1WO528MVf+ei/QAWEREREZEbc3ZwKNJSnYrAw8OD5s2bs2bNGp599lnr9k8//RSTyWRdKgSwfv16myVDn332GUFBQQQHBwPg7OxMRkZG+QUvUoa0XEgKZVtCThs2tW4WERERERHIKXy7d+9ehg8fzjfffMPixYsZN24cYWFhNm2Yt27dynPPPcfmzZt57rnnWLFiBdOmTcPhWqHdRo0aYTKZeOutt9i3bx+///67ne5IpOSUZJECncvI4vfUnDWMSrKIiIiIiAjAgAED+PTTT/ntt98YOHAgUVFRjBw5ks8//9xm3NKlS/n9998JDw/no48+4pVXXmHChAnW/f3792fChAnMmTOHtm3b8vjjj5fznYiUHoPFYrHYO4jKKi4ujlq1anHq1CnrVLdb0Zpz8Tx15L84Gwz81rkpVYzKzYmIiIiIFEdsbCwAdevWtWsc5SE6Opr77ruPffv20apVK3uHI3JDBX1fFuXdX2/LUqDc1s1tvN2VYBERERERERG5ARW+lZuyWCxsv1b0totaN4uIiIiISDkwmUw33GcwGDAajeUYjUjhKckiN/VbajrnM3N+wKkei4iIiIiIFFZoaCjFrU7h5HTjjqZ16tSxLu8QqWiUZJGbyp3F4utopKmnm52jERERERGR28G+fftuuM/FpXK1u5bbi5IsclMx8Tmtmzv6emA0GOwcjYiIiIiI3A5UKFcqK1UxlRvKzM5mV1JOkqWr6rGIiIiIiIiI3JSSLHJD+5OuctWcDagei4iIiIiIiEhBlGSRG8qtx1LXzZk6blr3KCIiIiIiInIzSrLIDcXktm7WLBYRERERERGRAinJIvlKzDJx6MpVQEkWERERERERkcJQkkXytTMxhWzAAHTy9bB3OCIiIiIiIiIVnpIskq9fU9IBaOjuio+TOn2LiIiIiEjFs3//fgwGA9HR0eV2zZUrV3LnnXfi5ORE8+bNy+26BYmOjsZgMLB//357h3Jb09uz5Cs2LQOAeip4KyIiIiIiAsCVK1d49NFHGT58OMuWLcPLy8veIUkFoySL5Cs3yVLXzdnOkYiIiIiIiJS99PR0XF1dbzrm+PHjZGRkMGrUKDp27FhOkUllouVCkq/YtEwA6momi4iIiIiI3MDSpUupU6cOVapUISwsjD179mAwGFi2bJl1zLJly2jWrBmurq7UrFmTadOmYTKZbPYbDAb+7//+j/vvvx93d3fuvPNOPvzwwzzXe/XVV6lRowYeHh4MHjyYCxcu5BljsViYN28eISEhuLi4cMcdd/DPf/7TZkxkZCQeHh7s3buX9u3b4+rqysKFC296r5GRkbRo0QKAsLAwDAYDkZGRAGRkZPDSSy9Rp04dXFxcaNSoEStXrrQ5PiIigiZNmvDtt9/StGlT3Nzc6Ny5MydOnCA+Pp4HH3wQLy8v6tevz+rVq22O3bhxIz169KB69ep4eXnRtm1bvvnmm5vGW9hnIaVLM1kkjxSTmUtZOT/0lGQRERERESlbmaZsTiem2TWGmj5uODsW7XfwX375JU888QRjxoxhyJAhHDx4kBEjRtiMmT9/Ps8//zyTJ0/mzTff5MiR/9/encdFVe5/AP8MzACy78R2wTQRXAKuipndZFUUIdyuJSZpGD/XSyFw00LNFEPUciUtMytLTdQElRKsDM0lWrV4RYigoCiLoLIN5/eHl5PjsI0OjMDn/XrxauY5z3PO9xye8cV8e5bzWLhwIeRyORISEhTqhoWFISIiAi+//DKSk5MRHh6OQYMGwc3NDQCwfv16vPbaa4iOjoafnx/S09Mxc+ZMpbjmz5+PrVu3YuHChfDy8kJWVhZiY2PRo0cPREZGivVqa2sxZcoUREVFYcWKFTAzM2vxfl988UU4OzvjhRdewIYNG+Dp6QkHBwcAwKRJk3D8+HHEx8fD1dUVaWlpCAsLg5mZGQIDA8VzFBUVITY2Fq+99hqkUinmzZuHKVOmwNDQEE899RRefPFFbNmyBWFhYRg6dCicnJwAAHl5eRg7diyio6OhpaWFQ4cOYfTo0cjIyMCIESOajbmtz4LUh0kWUtI4VQjgdCEiIiIiovZ2qfw2vFcd02gMmdEj0NPSQKU2y5Ytg4+PD7Zs2QIAGDlyJKqrq7FkyRIAQGVlJeLj4xETE4Ply5cDAPz9/SGVShEdHY0FCxbAwsJCPN+cOXMwa9YsAMDQoUORmpqKvXv3ws3NDXK5HCtWrMDUqVORmJgoXq+oqAg7d+4Uz5Gbm4v169dj8+bNYgLGz88PVVVVWLJkCWbOnAktrTvJpLq6OixfvhwTJ05s0/06ODigf//+AAA3NzcMHTr0zrPLzMSBAwdw5MgRBAQEiPd56dIlxMfHKyRZysrKcPz4cbi6ugIALl++jLlz54qJFwAYPHgw9u7di3379mH+/Pnis2nU0NAAb29v/Pbbb3j33XebTbKo8ixIffhESUnjVCGpBLDXZZKFiIiIiIgUyeVyZGdnIzg4WKE8JCREfJ2VlYWqqipMnDgR9fX14o+Pjw9u376NX3/9VaFtY4ICAIyMjODo6IjCwkIAQGFhIS5fvozQ0FCFNhMmTFB4/9VXXwEAxo8fr3BNX19fFBcXo6CgQKH+6NGj7/MJ/C09PR3m5ubw8fFRumZ2djbkcrlY187OTkywAECfPn0A3El+NDI1NYW1tbVCrIWFhZg2bRrs7e0hlUohk8mQnp6OnJycZuNS9VmQenAkCynJ+99IFkc9HUi1JBqOhoiIiIioa7M37YHM6BEaj0EVJSUlqK+vh5WVlUK5tbW1+PratWsAAE9PzybPce+XfFNTU4X3Ojo6qK6uBnBnms295wcAGxsbhffXrl2DIAiwtLRs9pqNU3D09fVhYKDa6J2mXLt2DaWlpZDJZE0eLyoqEqcVNXWPzZU33ntDQwOCg4NRUVGBpUuXonfv3jAwMMDrr7+OixcvthhXW58FqQ+TLKQkn4veEhERERF1GB2plspTdTTNysoKUqkUJSUlCuV3L0Rrbm4OANi7dy8cHR2VztGzZ882X8/W1lbp/ABw5coVhffm5uaQSCQ4fvy4mMC4m4uLi/haIlHP/1A2NzeHlZUV0tLSmjx+b2JIVX/++Seys7Oxb98+hZFCt2+3vI6PKs+C1IdJFlLy9/bNTLIQEREREZEybW1teHh4YP/+/eK6IQCwb98+8fWwYcOgr6+PwsJCpWk+qnJwcICtrS1SUlIUzrVnzx6Fer6+vgCA69evY+zYsQ90zbby8/PDW2+9BR0dHQwcOFDt529MptydKMnPz8d3330nTjdqiiaeBTHJQk3IE5MsXI+FiIiIiIiatmjRIoSEhCAiIgITJ05EdnY2duzYAQDQ0tKCiYkJli5dipiYGBQWFsLb2xtaWlr466+/sH//fnz++efQ19dv07W0tbURFxeH+fPnw8bGBv7+/jhy5Ai++eYbhXp9+vTB7NmzMXXqVCxYsABeXl6oq6tDTk4OMjMzFZJA6uLv74+xY8di1KhRiImJwcCBA3Hz5k389ttv+PPPP7F169YHOn/fvn3h4OCAuLg4yOVy3Lx5E/Hx8bC3t2+xnSaeBTHJQveoaWjA5Zo6AEBPjmQhIiIiIqJmBAcHY9OmTVi+fDk++ugjeHl5YePGjQgMDISJiQkA4JVXXoG9vT1Wr16NdevWQSaToVevXggKCmpyCktL5s6di/LycmzYsAEbN26En58fkpOTERQUpFDvnXfegYuLC5KTk7F06VIYGBjAxcUFkyZNUtu932vPnj1ISEjAxo0bkZ+fDxMTE/Tv3x8vvPDCA59bV1cXe/fuxezZszFx4kQ4Ojpi0aJFyMjIwJkzZ1psq4ln0d1JBEEQNB1EZ1VYWAhHR0cUFBSICxl1dn/eqsbw738HAHw9pC9cDPQ0HBERERERUddx4cIFAICzs7NG42gvW7duRUREBPLy8rrsPVLX09rnUpXv/hzJQgrybtWIr/+hx+lCRERERETUtNLSUixZsgQ+Pj4wMjLC6dOn8eabbyIkJIQJFuq2mGQhBfnVd3YWstOVoYe2loajISIiIiKih5VMJkNubi527tyJsrIyWFlZYerUqVi5cqWmQ7svDQ0NaGhoaPa4tra22nYkoq6LSRZS0LizkBMXvSUiIiIiohYYGRnh4MGDmg5DbaZPn47t27c3ezwzMxMjRozouICoU2KShRTk3bozkoXbNxMRERERUXeyePFizJkzp9njLi4uHRgNdVZMspCC/Oo7I1m4sxAREREREXUnzs7OXEuGHhgX3SCRXBBw8fadkSycLkRERERERESkGiZZSHS5pg61/9vRm9OFiIiIiIiIiFTDJAuJ8m//vX2zM7dvJiIiIiIiIlIJkywkuvC/qULmMm2YyLhcDxEREREREZEqmGQhUV7j9s16nCpEREREREREpComWUh04X9Jlp76TLIQERERERERqYpJFhLlN+4sxPVYiIiIiIioEzhz5gwkEgmOHTum6VDU4sKFC5BIJNizZ4+mQ6H7xCQLAQAEQRCnC3FnISIiIiIiIiLVMclCAIBrdfW4KW8AAPTswZEsRERERETUvVRXV2s6BOoCmGQhAH9PFQI4koWIiIiIiNomOTkZTk5O0NfXh6+vL77//ntIJBJ88MEHYp0PPvgAAwcOhJ6eHuzt7bFw4ULU19crHJdIJPjhhx8QGBgIAwMDPPbYY/jwww+Vrrds2TI88sgjMDQ0xLhx43D16lWlOoIgYNWqVejTpw90dXXx6KOPYs2aNQp1Fi9eDENDQ5w6dQpPPPEE9PT0sG7dulbvt7Hd2bNn4eXlhR49esDDwwNnz55FdXU1/u///g/m5uZwcHDA2rVrFdqeOHECwcHBsLOzg4GBAdzd3bFjx45Wr9mWZ0gPD+7TSwD+3llIX1sLVjrsFkREREREHaa+Fqgo0GwMJo6AVLUR7QcOHEBkZCRefPFFTJgwAdnZ2XjuuecU6qxevRoxMTGIiopCUlISzp8/j4ULF0IulyMhIUGhblhYGCIiIvDyyy8jOTkZ4eHhGDRoENzc3AAA69evx2uvvYbo6Gj4+fkhPT0dM2fOVIpr/vz52Lp1KxYuXAgvLy9kZWUhNjYWPXr0QGRkpFivtrYWU6ZMQVRUFFasWAEzM7M23XddXR2mT5+OqKgoWFtbIzY2FuPGjcPw4cNhY2ODzz77DPv370dUVBSGDBmCYcOGAQDy8/Px5JNPIjIyEnp6evjuu+8wY8YMCIKA559/vtnrqfIMSfP4bZoA/L2zkLOeDiQSiYajISIiIiLqRioKgHWemo1h7g+ARS+Vmixbtgw+Pj7YsmULAGDkyJGorq7GkiVLAACVlZWIj49HTEwMli9fDgDw9/eHVCpFdHQ0FixYAAsLC/F8c+bMwaxZswAAQ4cORWpqKvbu3Qs3NzfI5XKsWLECU6dORWJioni9oqIi7Ny5UzxHbm4u1q9fj82bN4sJGD8/P1RVVWHJkiWYOXMmtLTuTOioq6vD8uXLMXHiRJXuu7a2FitXrsSoUaMAAA0NDRg7dizkcjlWr14NAPDx8cHu3buxe/duMckyefJk8RyCIOBf//oXCgsLsXnz5maTLKo+Q9I8ThciAH9PF+JUISIiIiIiao1cLkd2djaCg4MVykNCQsTXWVlZqKqqwsSJE1FfXy/++Pj44Pbt2/j1118V2gYEBIivjYyM4OjoiMLCQgBAYWEhLl++jNDQUIU2EyZMUHj/1VdfAQDGjx+vcE1fX18UFxejoEBxxNDo0aNVvnctLS34+PiI7/v06QPgTjKnkba2Nnr16qVwvbKyMsybNw9OTk6QyWSQyWR49913kZOT0+y1VH2GpHkcyUIAwJ2FiIiIiIg0xcTxzkgSTceggpKSEtTX18PKykqh3NraWnx97do1AICnZ9OjdO5NeJiamiq819HRERejLSoqUjo/ANjY2Ci8v3btGgRBgKWlZbPXdHJyAgDo6+vDwMCgyXot6dGjB3R0/p5a1fi6pfgBIDw8HFlZWXj99dfRr18/GBsbY9OmTfjss8+avZaqz5A0j0kWAgBcEEeycGchIiIiIqIOJdVReaqOpllZWUEqlaKkpESh/O6FaM3NzQEAe/fuhaOjchKnZ8+ebb6era2t0vkB4MqVKwrvzc3NIZFIcPz4cYVESCMXFxfxdUcuk1BdXY3U1FQkJSVh7ty5YnlDQ0OL7dT5DKljMMlCqKyX43rdnZWpOZKFiIiIiIhao62tDQ8PD+zfvx/z588Xy/ft2ye+HjZsGPT19VFYWKg0zUdVDg4OsLW1RUpKisK59uzZo1DP19cXAHD9+nWMHTv2ga6pTjU1NZDL5QqJn8rKShw4cKDFdup8htQxmGQhcdFbgCNZiIiIiIiobRYtWoSQkBBERERg4sSJyM7OFrck1tLSgomJCZYuXYqYmBgUFhbC29sbWlpa+Ouvv7B//358/vnn0NfXb9O1tLW1ERcXh/nz58PGxgb+/v44cuQIvvnmG4V6ffr0wezZszF16lQsWLAAXl5eqKurQ05ODjIzMxWSQB3JxMQEgwcPRkJCgjgKKCEhASYmJk1uQ313O3U9Q+oYTLKQOFVIJpHAXo9JFiIiIiIial1wcDA2bdqE5cuX46OPPoKXlxc2btyIwMBAmJiYAABeeeUV2NvbY/Xq1Vi3bh1kMhl69eqFoKCgJqfztGTu3LkoLy/Hhg0bsHHjRvj5+SE5ORlBQUEK9d555x24uLggOTkZS5cuhYGBAVxcXDBp0iS13fv9+OSTTzBz5kxMmzYNFhYWmDdvHqqqqrBq1aoW26nzGVL7kwiCIGg6iM6qsLAQjo6OKCgogIODg6bDuW/r8q/gzb+K8GgPXWQNddV0OEREREREXdaFCxcAAM7OzhqNo71s3boVERERyMvL67L3SF1Pa59LVb77cyQLidOFOFWIiIiIiIjaqrS0FEuWLIGPjw+MjIxw+vRpvPnmmwgJCWGChbotJlnorp2FuOgtERERERG1jUwmQ25uLnbu3ImysjJYWVlh6tSpWLlypaZDuy8NDQ0t7vajra3doTsSUefEJAtxJAsREREREanMyMgIBw8e1HQYajN9+nRs37692eOZmZkYMWJExwVEnRKTLN1cTUMDLtfUAeBIFiIiIiIi6r4WL16MOXPmNHvcxcWlA6OhzopJlm7u4u1aNK58zCQLERERERF1V87OzlxLhh6YlqYDIM1qnCokAfAPbt9MREREREREdN+YZOnmGhe9tdOVQU+b3YGIiIiIiIjofvFbdTfXOJLFiVOFiIiIiIiIiB4Ikyzd3N/bN3OqEBEREREREdGDYJKlm2scydKTI1mIiIiIiIiIHgiTLN2YXBBwsfrOSBZOFyIiIiIiIiJ6MEyydGOXa+pQJ9zZwJnThYiIiIiISN0kEglWrVql6TAeKuHh4ejfv7+mw6B2ItV0AKQ5F27ViK+dOZKFiIiIiIio3b322mu4efOmpsOgdsIkSzd2ofpOksVcpg1jqbaGoyEiIiIiIur6evXqpekQqB1xulA39vfOQhzFQkREREREqmmc9nLs2DF4eHjAwMAAQ4YMwdmzZxXq1dfXIyYmBlZWVjAyMkJ4eDgqKytVutaJEycQEBAAY2NjGBkZwcvLC19++aV4PC4uDgMGDIChoSHs7e3x7LPPoqioSOEcI0aMQFBQED766CP07t0b+vr6CAoKQmlpKfLz8zFy5EgYGhqiX79+yMzMVGjr7OyMOXPmIDExEfb29tDX10dISIjSNdoSR1PThY4fPw4PDw/o6emhf//+OHz4MPr374/w8HCVn/f777+Pfv36oUePHrCwsMDw4cNx+vRplZ433T+OZOnGuLMQEREREZHm1cnrcPnmZY3GYGdgB5m2TOV2xcXFmDdvHuLi4mBsbIy4uDiEhoYiNzcXMtmd861btw6enp7Yvn078vLyEBcXh+rqanz66adtusZ3330HHx8fDB06FFu3boWpqSnOnDmDixcvinWuXr2KV199FXZ2digpKUFSUhKefvppnDt3DlLp3197s7OzUVpaitWrV6O8vBzz5s3Diy++iIKCAjz//PN45ZVXsGLFCowfPx4XL16EoaGh2DYlJQVOTk7YtGkTysrKEBcXh3HjxuHEiRMqx3G3oqIijBo1Cp6enti1axcqKiowe/ZsVFRUqPy8v/nmG8yYMQPR0dEYPXo0bt26hVOnTqG8vLxNz5oeHJMs3VhjksWJi94SEREREWnM5ZuXEZQSpNEYDoYehJOxk8rtSktL8fXXX6Nfv34AAD09Pfj7++P777/H8OHDAQC6urrYt28ftLW1xToRERFYvHgx+vbt2+o1YmJi0Lt3b2RkZIjnCAgIUKjz/vvvi6/lcjmeeOIJODg4ICMjQ6FuRUUFvvjiC1hYWAAAfv75ZyQlJWHTpk2IjIwEANjZ2WHAgAE4evQoQkJCxLaVlZVIS0uDqakpAMDBwQF+fn5IT08Xr9HWOO62Zs0aSKVSpKamwsjICADg6OgIb29vpbqtPe9Tp07B3NwciYmJYpsxY8a09HhJzThdqJsSBIHThYiIiIiI6IHY2dmJX/gBwM3NDQBQWFgolo0dO1ZMjgDAuHHjIAgCTp061er5b926hZMnT2LatGkK57jXoUOHMGzYMJiYmEAqlcLBwQEAkJOTo1DP3d1dTLAAQJ8+fQAAfn5+SmUFBQUKbb29vcUECwD4+vrC2NgYJ0+eVDmOu50+fRre3t5iggW4M7XJxMREqW5rz9vT0xOlpaUIDw/Hl19+iVu3bjV7XWofHMnSTV2rq8dNeQMAThciIiIiItIkOwM7HAw9qPEY7sfdSQcA0NG5M0q+urpaLLO2tlaoY2ZmBplMprRWSVPKysrQ0NAAO7vm4zt9+jSCg4MREhKCuLg4WFtbQyKRYOjQoQpxtBTv3eVN3UNT99FY1ngfqsRxt6KiIjz22GNK5VZWVkplrT1vHx8f7NixA2+//TZGjhwJPT09TJgwAWvXroW5uXmzMZD6MMnSTTWOYgEAZ04XIiIiIiLSGJm27L6m6nQWV69eVXhfVlaGuro62NrattrW1NQUWlpauHy5+TVrUlJSYGJigl27dkFL685kjfz8/AcLugn33kdjWeN93G8ctra2KCkpUSpvqqwtwsLCEBYWhmvXrmH//v2IioqCTCbDe++9d1/nI9VwulA31bgei762FixlzLUREREREVH7+OKLLyCXy8X3e/fuhUQiweDBg1tta2BggCeeeAIffvihwjnudvv2bchkMkgkErHs448/fvDA75GZmamwGO3Ro0dx48YNeHl5PVAcgwcPRkZGhsKOS/de635YWlpixowZ8Pf3x/nz5x/oXNR2/HbdTeWJOwvpKPwjQEREREREpE41NTV45plnMGvWLOTl5SE2NhYTJkyAq6trm9onJCTAx8cHfn5+mDVrFszMzPDDDz/A0tIS06dPh7+/P9auXYu5c+ciNDQUJ06cwI4dO9R+H0ZGRggMDERcXBzKy8sRGxuLIUOGYOTIkQBw33FERUVh48aNGDNmDBYsWIDy8nIsXrwYFhYW4oiYtoqPj8f169cxYsQIWFtb45dffsHhw4fx8ssv39c9k+o4kqWbyueit0RERERE1AHmzp2LPn36ICwsDLGxsQgNDcXWrVvb3H748OE4duwYJBIJwsPDMW7cOHE7ZQAYPXo0Vq5cif379yM4OBjffPMNDh5U/xo3oaGhCA4ORmRkJF566SUMGjQIKSkp4vH7jcPW1haHDh1CZWUlJkyYgBUrVmDdunXQ19dvcvHblgwePBi///47Zs2ahYCAAKxZswYLFixAfHy8yvdL90ciCIKg6SA6q8LCQjg6OqKgoEBcNbqzCDqbgzM3bmGWozVe731/i1wREREREZFqLly4AABwdnbWaBykGmdnZwQFBWH9+vUdcr2cnBz07dsX27Ztw7Rp0zrkmt1Za59LVb77c7pQN1VcWwcAsNOTaTgSIiIiIiKi7u2///0vBg4cCDs7O/z1119Yvnw57OzsMH78eE2HRipikqUbEgQBV2vqAQDWOkyyEBERERGRZsjlcrQ0uUIq7R5fWWtraxEXF4fi4mL06NEDI0aMQGJiIgwNDTUdGqmoe/RYUlBeL0ft//4hs9ZhFyAiIiIiIs3w9fXF119/3ezxvLy8h2JqVeN0kvaSlJSEpKSkdr0GdQx+w+6GrtbWi69tOJKFiIiIiIg0JDk5WWHr4nvZ2XH9SOpcOmWSRS6XIykpCampqTh37hzq6+sxYMAAxMfHw9fXt9X2dXV1eP311/HBBx+goqICXl5eePvttzFw4MAOiF7zrtbUia+tdTtlFyAiIiIioi7AxcVF0yEQqVWn3ML59u3bWL58Odzd3bFt2zZ8+umnsLe3h7+/f5u2yIqKisKGDRuwdOlS7N+/H1KpFL6+viguLu6A6DXvyv8WvTXU1oKBtraGoyEiIiIiIiLqGjrlMIYePXogLy8PZmZmYllAQABycnKQlJSEoKCgZtteunQJmzdvxjvvvIOIiAgAwNChQ9GzZ0+sXbsWCQkJ7R6/pjVOF+Kit0RERERERETq0ylHsmhrayskWABAIpHA3d0dly9fbrFteno65HI5Jk+eLJYZGRlh7NixSE1NbZd4HzaNI1m46C0RERERERGR+nTKJEtTGhoakJWVBVdX1xbrnT9/HjY2NjA3N1cod3Nzwx9//IGGhob2DPOhkFxQAgA4WXFTw5EQERERERERdR1dZijDunXr8McffyA5ObnFemVlZTA1NVUqNzMzQ11dHaqqqmBsbNxk2xs3buDGjRvi+6KiogeKWVMsZFJcr6vHcFPuuU5ERERERESkLg9NkqWioqJNSYuePXtCV1dXoezrr79GTEwMoqOj8a9//avVc0gkEqUyQRCaPdZo9erVWLJkSavnf9gdGdQHaSXlmPiIeeuViYiIiIiIiKhNHprpQikpKXB1dW315/z58wrtfv75Z4SEhOCZZ57BypUrW72OmZkZysrKlMrLy8shk8lgYGDQbNuXX34ZBQUF4s+pU6dUv9GHgIOeDmY6WsNM9tDk2IiIiIiIqAuSSCRYtWqVpsN4qISHh6N///6aDqPbuHbtGiQSCT744IMOud5D8y07PDwc4eHhKrXJzc3FyJEj4enpiR07drQ4CqWRq6srrl69itLSUoV1Wc6dOwcXFxdoaTWfdzI2Nm52KhERERERERFRa1577TXcvMn1Mbuqh2Yki6qKi4sREBCARx55BPv27YOOjk6b2gUEBEBLSwu7du0Sy6qqqvDFF19gzJgx7RUuEREREREREXr16oWBAwdqOgxqJ50yyXL79m2MGjUKV69exeLFi3Hu3DmcPHlS/Llb79694evrK763t7dHZGQkYmNjsXXrVnz55ZcYP348AOA///lPR94GERERERFRp9U47eXYsWPw8PCAgYEBhgwZgrNnzyrUq6+vR0xMDKysrGBkZITw8HBUVlaqdK0TJ04gICAAxsbGMDIygpeXF7788kvxeFxcHAYMGABDQ0PY29vj2WefVVrzc8SIEQgKCsJHH32E3r17Q19fH0FBQSgtLUV+fj5GjhwJQ0ND9OvXD5mZmQptnZ2dMWfOHCQmJsLe3h76+voICQlRukZb4mhqutDx48fh4eEBPT099O/fH4cPH0b//v0VZnu09Xm///776NevH3r06AELCwsMHz4cp0+fbvOz/vXXXzFq1CgYGhrC2NgYISEh+PPPPxXqSCQSJCQktPp7LS8vx6xZs2BrawtdXV3885//RHp6ukKdxt/L7t274eLiAkNDQ/j4+CA3N1ehXk1NDV599VU4OTlBV1cXrq6u+OSTT5Ti37JlC5ydnaGvrw9fX1+l2NvbQzNdSBVXrlzBTz/9BAB45plnlI43LmIL3PlAy+VyheOrV6+GoaEhFi1ahIqKCnh5eeHo0aN45JFH2jVuIiIiIiKiewm1tai7fFmjMcjs7CBp4+yAuxUXF2PevHmIi4uDsbEx4uLiEBoaitzcXMhkMgB3doL19PTE9u3bkZeXh7i4OFRXV+PTTz9t0zW+++47+Pj4YOjQodi6dStMTU1x5swZXLx4Uaxz9epVvPrqq7Czs0NJSQmSkpLw9NNP49y5c5BK//7am52djdLSUqxevRrl5eWYN28eXnzxRRQUFOD555/HK6+8ghUrVmD8+PG4ePEiDA3/3pE1JSUFTk5O2LRpE8rKyhAXF4dx48bhxIkTKsdxt6KiIowaNQqenp7YtWsXKioqMHv2bFRUVKj8vL/55hvMmDED0dHRGD16NG7duoVTp06hvLy8Tc+6oKAATz31FJydnbF9+3bI5XLEx8fjqaeews8//wwrKyuxbmu/19raWvj7++PKlSt48803YW9vj48++ghjxozBDz/8gAEDBojn+vHHH1FSUoKEhATI5XL85z//QVhYmMKznTRpEo4fP474+Hi4uroiLS0NYWFhMDMzQ2BgIADg4MGDmDlzJsLDwzF58mScOXMGkydPbtO9q0unTLI4OzsrJFJacuHCBaUyHR0dJCQkICEhQc2RERERERERqabu8mXkjgrUaAy9Dh+CjrOzyu1KS0vx9ddfo1+/fgAAPT09+Pv74/vvv8fw4cMBALq6uti3bx+0tbXFOhEREVi8eDH69u3b6jViYmLQu3dvZGRkiOcICAhQqPP++++Lr+VyOZ544gk4ODggIyNDoW5FRQW++OILWFhYALizkUpSUhI2bdqEyMhIAICdnR0GDBiAo0ePIiQkRGxbWVmJtLQ0mJqaAgAcHBzg5+eH9PR08RptjeNua9asgVQqRWpqKoyMjAAAjo6O8Pb2Vqrb2vM+deoUzM3NkZiYKLZRZVmMNWvWoLa2Funp6WJCxcvLC4899hg2bNiAxYsXi3Vb+71+/PHH+PHHH/HTTz/Bzc0NADBy5Ejk5OTgjTfeUFjCo7y8HNnZ2eI1y8vLERERgcLCQjg4OCAzMxMHDhzAkSNHxOfo7++PS5cuIT4+XkyyLFu2DE899RS2bdsmXu/mzZtYsWJFm5/Bg+qU04WIiIiIiIhI8+zs7MQv/ADEL9OFhYVi2dixY8Uv4gAwbtw4CILQpt1ab926hZMnT2LatGkK57jXoUOHMGzYMJiYmEAqlcLBwQEAkJOTo1DP3d1dTLAAQJ8+fQAAfn5+SmUFBQUKbb29vcUECwD4+vrC2NhYYcmKtsZxt9OnT8Pb21tMsAB3ptCYmJgo1W3teXt6eqK0tBTh4eH48ssvcevWrWav25Rvv/0WPj4+CiNWnJycMGzYMHz77bcKdVv7vaanp2PAgAHo06cP6uvrxR9fX1+l6Uvu7u4K17z3vtLT02Fubg4fHx+lc2VnZ0Mul0Mul+Ps2bMIDQ1VOPeECRNUegYPqlOOZCEiIiIiIuoqZHZ26HX4kMZjuB93Jx0AiBuSVFdXi2XW1tYKdczMzCCTyZTWKmlKWVkZGhoaYNdCfKdPn0ZwcDBCQkIQFxcHa2trSCQSDB06VCGOluK9u7ype2jqPhrLGu9DlTjuVlRUhMcee0yp/O6kQ2vxN57fx8cHO3bswNtvv42RI0dCT08PEyZMwNq1axV2121OWVkZ3N3dlcofeeQR/PHHHwplrf1er127huzsbHHa2N3uTZi1dl/Xrl1DaWlpk+cC7jxDqVSK+vp6pbhsbGyabNNemGQhIiIiIiLSIImOzn1N1eksrl69qvC+rKwMdXV1sLW1bbWtqakptLS0cLmFNWtSUlJgYmKCXbt2QUvrzmSN/Pz8Bwu6CffeR2NZ433cbxy2trYoKSlRKm+qrC3CwsIQFhaGa9euYf/+/YiKioJMJsN7773Xaltzc3NcuXJFqby4uFgpSdPa79Xc3BwDBw5s03XbEpeVlRXS0tKaPG5tbQ1tbW1IpVKluJq6n/bE6UJERERERETUbr744guFzUj27t0LiUSCwYMHt9rWwMAATzzxBD788EOlDU0a3b59GzKZDBKJRCz7+OOPHzzwe2RmZiosRnv06FHcuHEDXl5eDxTH4MGDkZGRobAzz73Xuh+WlpaYMWMG/P39cf78+Ta1GT58OI4ePYrr16+LZQUFBcjKysJTTz2lULe136ufnx/++usv2NnZYdCgQUo/qvDz80NJSQl0dHSaPJeOjg60tbXh6emJlJQUhbZ79uxR6VoPiiNZiIiIiIiIqN3U1NTgmWeewaxZs5CXl4fY2FhMmDABrq6ubWqfkJAAHx8f+Pn5YdasWTAzM8MPP/wAS0tLTJ8+Hf7+/li7di3mzp2L0NBQnDhxAjt27FD7fRgZGSEwMBBxcXEoLy9HbGwshgwZgpEjRwLAfccRFRWFjRs3YsyYMViwYAHKy8uxePFiWFhYiCNi2io+Ph7Xr1/HiBEjYG1tjV9++QWHDx/Gyy+/3Kb2UVFR2LZtGwICArBw4UJxdyFzc3PMnj1boW5rv9fnn38eycnJGDFiBKKjo9GnTx9xgdva2lqVFqP19/fH2LFjMWrUKMTExGDgwIG4efMmfvvtN/z555/YunUrAGDhwoUICQnBCy+8IO4u1NQ2z+2JSRYiIiIiIiJqN3PnzkVJSQnCwsJQW1uL0NBQrF+/vs3thw8fjmPHjmHRokUIDw+HtrY2+vXrh2XLlgEARo8ejZUrV2LdunXYtm0bnnzySRw8eFBcwFZdQkND4eDggMjISJSVlcHPzw/Jycni8fuNw9bWFocOHcK8efMwYcIE9OrVC+vWrUNkZGSTi9+2ZPDgwVi7di127dqFGzduwMHBAQsWLMCiRYva1N7R0RHffPMNoqOjMXXqVGhpacHb2xtJSUlKa8S09nvV1dVFRkYGFi9ejDfffBNFRUWwtLSEh4cHZs2apdJ9AXdGpCQkJGDjxo3Iz8+HiYkJ+vfvjxdeeEGsExwcjM2bN+PNN9/Ep59+Ci8vL+zcuRPDhg1T+Xr3SyK0dS9kUlJYWAhHR0cUFBSIq0YTERERERE158KFCwAA5y68BktX5OzsjKCgIJWSQw8iJycHffv2xbZt2zBt2rQOuaYqJBIJEhMTER0drelQ1KK1z6Uq3/05koWIiIiIiIhIg/773/9i4MCBsLOzw19//YXly5fDzs4O48eP13RopCImWYiIiIiIiEgj5HI5WppcIZV2j6+stbW1iIuLQ3FxMXr06IERI0YgMTERhoaGartGQ0MDGhoamj2ura2tsGgv3Z/u0WOJiIiIiIjooePr64uvv/662eN5eXkPxdSqxukk7SUpKQlJSUnteo2lS5diyZIlzR7ftm0bwsPD23QurjrSPCZZiIiIiIiISCOSk5MVti6+l52dXQdG07XNnDkTQUFBzR7v2bNnB0bTdTHJQkRERERERBrh4uKi6RC6DTs7OyatOoBqm24TEREREREREVGTmGQhIiIiIiLqINra2pDL5ZoOg4juIpfLoa2trZZzMclCRERERETUQfT09FBbW4vr169rOhQiAnD9+nXU1tZCT09PLefjmixEREREREQdxNLSEjU1Nbh69SrKy8vV9n/PiUh1crkctbW1MDIygqWlpVrOySQLERERERFRB5FIJLC3t8e1a9dQXV3NqUNEGqSjowNjY2NYWlpCIpGo5ZxMshAREREREXUgiUQCKysrTYdBRO2Aa7IQEREREREREakBkyxERERERERERGrAJAsRERERERERkRowyUJEREREREREpAZc+PYB1NfXAwCKioo0HAkRERERERERtYfG7/yNOYCWMMnyAEpKSgAAQ4YM0XAkRERERERERNSeSkpK4Ozs3GIdiSAIQseE0/VUV1fjl19+gZWVFaTSzpOvKioqwpAhQ3Dq1CnY2tpqOhyidsF+Tt0B+zl1B+zn1B2wn1N30Jn7eX19PUpKSjBgwADo6em1WLfzZAYeQnp6ehg8eLCmw7hvtra2cHBw0HQYRO2K/Zy6A/Zz6g7Yz6k7YD+n7qCz9vPWRrA04sK3RERERERERERqwCQLEREREREREZEaMMnSDRkbGyM+Ph7GxsaaDoWo3bCfU3fAfk7dAfs5dQfs59QddJd+zoVviYiIiIiIiIjUgCNZiIiIiIiIiIjUgEkWIiIiIiIiIiI1YJKFiIiIiIiIiEgNmGQhIiIiIiIiIlIDJlm6mZycHIwaNQoGBgawtrbG/Pnzcfv2bU2HRd3Y7t278cwzz8DR0REGBgYYOHAgNm3ahIaGBoV6aWlp8PDwgJ6eHnr37o2NGzc2eb5Vq1bB2dkZenp6GDx4MI4dO6ZUp7KyEi+99BIsLCxgaGiI4OBg5OfnK9Xj54XaS1VVFRwcHCCRSHDmzBmFY+zr1Nm99957ePzxx6Gnpwdra2sEBwcrHGcfp85u37598PLygrGxMWxsbDBu3Dj88ccfSvXY16mz+PPPPxEZGQl3d3dIpVL079+/yXoPc59ua2wdQqBuo6ysTLC3txeGDRsmHDp0SNi+fbtgYWEhTJkyRdOhUTfm5eUlTJo0Sdi5c6eQkZEhvPbaa4JUKhWio6PFOllZWYJUKhWmT58uZGRkCG+88YagpaUlbNmyReFciYmJgkwmExITE4WjR48KkydPFvT09ISff/5Zod6YMWMEW1tb4ZNPPhEOHjwoeHp6Cr179xZu3bol1uHnhdpTTEyMYGNjIwAQTp8+LZazr1NnFx8fLxgbGwsrV64Ujh07Juzdu1eYOXOmeJx9nDq7L7/8UpBIJMLUqVOF9PR0YdeuXYKbm5vg4OAgVFRUiPXY16kz2bdvn+Dg4CCMHz9eGDBggNCvXz+lOg9zn25rbB2FSZZuJCEhQdDX1xdKSkrEso8//lgAIJw7d06DkVF3dvXqVaWyqKgoQU9PT6iurhYEQRBGjRolDBkyRKFORESEYGtrK8jlckEQBKG6ulowMTERFixYINapr68XXF1dhX//+99i2cmTJwUAQmpqqliWn58vSKVSYdOmTWIZPy/UXs6fPy8YGBgImzdvVkqysK9TZ3bu3DlBW1tbOHLkSLN12Meps5sxY4bg7OwsNDQ0iGXff/+9AEBIS0sTy9jXqTNp7JOCIAjTpk1rMsnyMPfptsTWkThdqBtJS0uDn58fLC0txbLx48dDV1cXaWlpGoyMujMrKyulMg8PD1RXV6O0tBQ1NTXIyMjA5MmTFepMmTIFRUVFyM7OBgBkZWWhoqICzz77rFhHW1sb//73v5GWlgZBEADc+RyYmpoiMDBQrPePf/wDw4cPR2pqqljGzwu1l3nz5iEyMhIuLi4K5ezr1Nl98MEHePTRRxEQENDkcfZx6grq6upgZGQEiUQilpmamgKA2DfZ16mz0dJqOS3wMPfptsbWkZhk6UbOnz8PV1dXhTJdXV306tUL58+f11BURMq+/fZbmJubw9raGrm5uaitrVXqu25ubgAg9t3G//bt21epXmVlJS5duiTWc3FxUfjjqLHe3Z8Dfl6oPezZswc//fQTXn/9daVj7OvU2Z08eRIDBgzAG2+8AWtra+jo6ODpp5/Gjz/+CIB9nLqGGTNm4Pz581i3bh3Ky8tx4cIFREdHw9XVFb6+vgDY16nreZj7dFtj60hMsnQjZWVlYqb9bmZmZigtLe34gIiacObMGWzbtg1RUVHQ1tZGWVkZACj1XTMzMwAQ+25ZWRl0dXXRo0ePVuu15XPAzwup261bt/Dyyy9jxYoVMDY2VjrOvk6dXXFxMdLT0/Hxxx9j8+bN2Lt3L27dugV/f3+Ul5ezj1OX8K9//QspKSlYuHAhzMzM0LNnT+Tm5iI9PR26uroA+O85dT0Pc59ua2wdiUmWbubebCFwZ2hjU+VEHa24uBjjx4/HkCFDEBsbq3CsuT56d3lz/but9e4t5+eF1GnZsmWwsbFBeHh4i/XY16mzamhoQFVVFT7//HOMGzcOQUFBOHDgACorK/Huu++K9djHqTPLyspCWFgYpk+fjqNHj2Lv3r3Q19dHYGAgbty4oVCXfZ26moe5T7clto7CJEs3YmZmJmb67lZeXi5m+og0paKiAoGBgdDX18eBAwcgk8kA/J2FvrfvNr5vPG5mZobq6mpUV1cr1CsvL1eq15bPAT8vpE75+flISkrCkiVLcOPGDZSXl6OqqgrAne2cq6qq2Nep0zM3N4eNjQ369esnltna2qJv37747bff2MepS5g3bx58fHywdu1a+Pj4IDQ0FGlpacjJycHWrVsB8G8X6noe5j7d1tg6EpMs3Yirq6vSnLSamhrk5uYqzWEj6kjV1dUIDg7GlStXcPjwYVhYWIjHevXqBR0dHaW+e+7cOQAQ+27jf5uqZ2RkBHt7e7HeH3/8IWbU76539+eAnxdSp7y8PNTW1mLMmDEwMzODmZkZxo4dCwDw9vaGn58f+zp1es31F0EQoKWlxT5OXcK5c+fg7u6uUGZlZQU7Ozvk5uYC4N8u1PU8zH26rbF1JCZZupHRo0fj6NGjuH79uliWkpKCmpoajB49WoORUXdWX1+PSZMm4aeffsLhw4fh5OSkcFxXVxc+Pj7YtWuXQvnOnTtha2sLDw8PAMCwYcNgYmKCzz77TKwjl8uxa9cujB49WhwqOHr0aJSXl+PIkSNivYKCAhw/fhxjxowRy/h5IXVyd3dHZmamws+aNWsAAJs3b8bGjRvZ16nTCwoKwpUrV/Drr7+KZZcuXcLvv/+Oxx9/nH2cugQnJyecPXtWoay4uBiXLl2Cs7MzAP7tQl3Pw9yn2xpbh+qYnaLpYVBWVibY29sLTz75pHD48GHhww8/FCwtLYUpU6ZoOjTqxmbOnCkAEN566y3hxIkTCj8VFRWCIAhCVlaWIJVKhRdffFHIzMwUli1bJmhpaQlbtmxROFdiYqIgk8mEVatWCRkZGcJzzz0n6OnpCT///LNCvTFjxgh2dnbCzp07hdTUVOGf//yn0Lt3b+HWrVtiHX5eqL1lZmYKAITTp0+LZezr1JnV19cLnp6ewmOPPSZ89tlnQkpKiuDh4SHY29sLVVVVgiCwj1Pnt27dOgGAMHv2bCE9PV3YtWuX4O7uLpiZmQmXL18W67GvU2dy8+ZNYffu3cLu3buFESNGCI6OjuL7q1evCoLwcPfptsbWUZhk6Wb++OMPISAgQNDX1xcsLS2FuXPnKnRkoo7m5OQkAGjyJzMzU6yXmpoqPP7444KOjo7w6KOPCuvXr1c6V0NDg/DWW28J//jHPwRdXV1h0KBBQkZGhlK9iooKISIiQjAzMxMMDAyEsWPHChcuXFCqx88LtaemkiyCwL5OnduVK1eE5557TjAxMRH09fWFwMBA4ffff1eowz5OnVlDQ4OQnJwsPP7444KBgYFgY2MjjB07VukLpCCwr1PnkZeX1+n/Hm9LbB1FIgj3TIQiIiIiIiIiIiKVcU0WIiIiIiIiIiI1YJKFiIiIiIiIiEgNmGQhIiIiIiIiIlIDJlmIiIiIiIiIiNSASRYiIiIiIiIiIjVgkoWIiIiIiIiISA2YZCEiIiIiIiIiUgMmWYiIiIiIiIiI1IBJFiIiIur2Lly4AIlEgj179nRIOyIiIuqamGQhIiIiIiIiIlIDJlmIiIiIiIiIiNSASRYiIiLq8k6cOIHg4GDY2dnBwMAA7u7u2LFjR4ttnJ2dMWfOHCQmJsLe3h76+voICQlBUVGRUt3q6mrMmTMHZmZmsLW1RXR0NOrr68Xjv//+OyZPngxHR0fo6+vDzc0NSUlJaGhoUPu9EhERkeZINR0AERERUXvLz8/Hk08+icjISOjp6eG7777DjBkzIAgCnn/++WbbpaSkwMnJCZs2bUJZWRni4uIwbtw4nDhxQqHewoULERISgl27duG7777DkiVL0Lt3b0RGRgIALl26BBcXF0yZMgVGRkb48ccfER8fj5s3b+L1119v13snIiKijiMRBEHQdBBEREREHUUQBMjlcsyePRu//PILsrKycOHCBfTs2RO7d+/GhAkTANwZyVJaWoqLFy/C1NQUAHD06FH4+fnhyJEjCAgIENtNnDgRu3btEq8xfPhw6Onp4auvvmr2+m+99RbWr1+Py5cvd8h9ExERUfvjdCEiIiLq8srKyjBv3jw4OTlBJpNBJpPh3XffRU5OTovtvL29xQQLAPj6+sLY2BgnT55UqBcQEKDw3s3NDYWFheL76upqxMfHo3fv3tDV1YVMJsPChQtRVFSEqqqqB79BIiIieigwyUJERERdXnh4OHbu3Ino6Gikp6fj9OnTmD59Oqqrq1tsZ21t3WTZveuy3J2IAQAdHR2Fc8fGxiIxMRERERFIS0vD6dOnsWjRIgBoNQYiIiLqPLgmCxEREXVp1dXVSE1NRVJSEubOnSuWt2XR2atXrzZZZmtrq1IMu3fvxksvvYTY2FixLDU1VaVzEBER0cOPI1mIiIioS6upqYFcLoeOjo5YVllZiQMHDrTaNjMzExUVFeL7o0eP4saNG/Dy8lIphtu3bytcXy6X49NPP1XpHERERPTw40gWIiIi6tJMTEwwePBgJCQkwMrKClKpFAkJCTAxMWlypMrdjIyMEBgYiLi4OJSXlyM2NhZDhgzByJEjVYrB398fW7ZsgZubG6ysrLBhwwbU1NQ8yG0RERHRQ4gjWYiIiKjL++STT9CrVy9MmzYN8+bNw4QJE1rcurlRaGgogoODERkZiZdeegmDBg1CSkqKytdft24dnn76acydOxfTp0/HgAED8Oqrr97PrRAREdFDjFs4ExERETXB2dkZQUFBWL9+vaZDISIiok6CI1mIiIiIiIiIiNSASRYiIiIiIiIiIjXgdCEiIiIiIiIiIjXgSBYiIiIiIiIiIjVgkoWIiIiIiIiISA2YZCEiIiIiIiIiUgMmWYiIiIiIiIiI1IBJFiIiIiIiIiIiNWCShYiIiIiIiIhIDZhkISIiIiIiIiJSAyZZiIiIiIiIiIjUgEkWIiIiIiIiIiI1YJKFiIiIiIiIiEgN/h99l95z2V5ilQAAAABJRU5ErkJggg==",
"text/plain": [
"<Figure size 1320x880 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# graphique\n",
"\n",
"plt.figure(figsize=[12,8], dpi=110)\n",
"\n",
"for i in range(len(X_colnames)) :\n",
" var_name = X_colnames[i]\n",
" plt.plot(alphas_sorted, [results[p][0][i] for p in range(len(results))], label = var_name)\n",
"\n",
"plt.legend()\n",
"plt.title(\"Evolution de la valeur des coefficents du logit LASSO en fonction du paramètre de pénalité alpha\")\n",
"plt.xlabel(\"alpha\")\n",
"plt.ylabel(\"valeur du coefficient\")\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 444,
"id": "4771b91f-baff-493b-a6f7-ddce02164333",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1320x880 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# hide right part of the graphic\n",
"# some coefficients are still strictly positive even for alpha =10k, which makes the graphic quite confusing\n",
"# alternative syntax\n",
"\n",
"endpoint = 9\n",
"\n",
"fig, ax = plt.subplots(figsize=[12,8], dpi=110)\n",
"\n",
"for i in range(len(X_colnames)) :\n",
" var_name = X_colnames[i]\n",
" ax.plot(alphas_sorted[:endpoint], [results[p][0][i] for p in range(len(results[:endpoint]))], label=var_name)\n",
" \n",
"ax.set(xlabel=\"alpha\",\n",
" ylabel=\"valeur du coefficient\",\n",
" title = \"Evolution de la valeur des coefficents du logit LASSO en fonction du paramètre de pénalité alpha\")\n",
"ax.legend()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"id": "c3c9bb8c-5d8b-47a6-b0b5-273217ff2664",
"metadata": {},
"source": [
"A retenir : \\\n",
"D'après le premier tableau de résultats, toutes les variables sont significatives au seuil de 5%, et à l'exception de nb tickets, elles sont même significatives à 0.1%. \\\n",
"Le graphique ci-dessus confirme que opt in, purchase date max, ventes internet max sont très importantes dans le modèle (on l'avait déjà remarqué car les valeurs des coefficients étaient élevées). \\\n",
"Au contraire, des variables qui avaient un fort coefficient comme is email true (0.87) se trouvent finalement fortement pénalisées et tombent plus vite à 0 que les autres. "
]
}
],
"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": "3.11.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue View Git Blame Copy Permalink