Skip to content
Permalink
main
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?

creditcardfrauddetection/Credit_Card_Fraud_Detection.ipynb

Go to file
 
 
Cannot retrieve contributors at this time
1235 lines (1235 sloc) 179 KB
Raw Blame
Open in GitHub Desktop
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "gIW_RYlDN2Hm"
},
"source": [
"**Student ID: 12975712 ** \\\n",
"**Name: Saisruthikesineni **"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "caePUCqlggVj"
},
"source": [
"Dataset link: https://www.kaggle.com/datasets/mlg-ulb/creditcardfraud"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "su04G1y-DkhB"
},
"source": [
"# Importing Required Libraries"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "BnMrBP_1H_ZS",
"outputId": "bfc38676-10b8-451b-9e3e-0bab18dafe1e"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: scikit-learn==1.2.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (1.2.0)\n",
"Requirement already satisfied: scipy>=1.3.2 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from scikit-learn==1.2.0) (1.9.1)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from scikit-learn==1.2.0) (2.2.0)\n",
"Requirement already satisfied: numpy>=1.17.3 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from scikit-learn==1.2.0) (1.21.5)\n",
"Requirement already satisfied: joblib>=1.1.1 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from scikit-learn==1.2.0) (1.2.0)\n",
"Requirement already satisfied: imblearn in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (0.0)\n",
"Requirement already satisfied: imbalanced-learn in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from imblearn) (0.10.1)\n",
"Requirement already satisfied: scikit-learn>=1.0.2 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from imbalanced-learn->imblearn) (1.2.0)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from imbalanced-learn->imblearn) (2.2.0)\n",
"Requirement already satisfied: joblib>=1.1.1 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from imbalanced-learn->imblearn) (1.2.0)\n",
"Requirement already satisfied: numpy>=1.17.3 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from imbalanced-learn->imblearn) (1.21.5)\n",
"Requirement already satisfied: scipy>=1.3.2 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from imbalanced-learn->imblearn) (1.9.1)\n",
"Requirement already satisfied: tensorflow in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (2.11.0)\n",
"Requirement already satisfied: tensorflow-intel==2.11.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow) (2.11.0)\n",
"Requirement already satisfied: wrapt>=1.11.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.14.1)\n",
"Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.51.3)\n",
"Requirement already satisfied: opt-einsum>=2.3.2 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (3.3.0)\n",
"Requirement already satisfied: astunparse>=1.6.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.6.3)\n",
"Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (2.2.0)\n",
"Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (0.31.0)\n",
"Requirement already satisfied: packaging in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (21.3)\n",
"Requirement already satisfied: keras<2.12,>=2.11.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (2.11.0)\n",
"Requirement already satisfied: tensorflow-estimator<2.12,>=2.11.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (2.11.0)\n",
"Requirement already satisfied: tensorboard<2.12,>=2.11 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (2.11.2)\n",
"Requirement already satisfied: google-pasta>=0.1.1 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (0.2.0)\n",
"Requirement already satisfied: typing-extensions>=3.6.6 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (4.3.0)\n",
"Requirement already satisfied: protobuf<3.20,>=3.9.2 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (3.19.6)\n",
"Requirement already satisfied: absl-py>=1.0.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.4.0)\n",
"Requirement already satisfied: gast<=0.4.0,>=0.2.1 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (0.4.0)\n",
"Requirement already satisfied: libclang>=13.0.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (15.0.6.1)\n",
"Requirement already satisfied: flatbuffers>=2.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (23.1.21)\n",
"Requirement already satisfied: numpy>=1.20 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.21.5)\n",
"Requirement already satisfied: six>=1.12.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (1.16.0)\n",
"Requirement already satisfied: setuptools in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (63.4.1)\n",
"Requirement already satisfied: h5py>=2.9.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.11.0->tensorflow) (3.7.0)\n",
"Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from astunparse>=1.6.0->tensorflow-intel==2.11.0->tensorflow) (0.37.1)\n",
"Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (0.4.6)\n",
"Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (0.6.1)\n",
"Requirement already satisfied: google-auth<3,>=1.6.3 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2.16.1)\n",
"Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (1.8.1)\n",
"Requirement already satisfied: markdown>=2.6.8 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (3.3.4)\n",
"Requirement already satisfied: requests<3,>=2.21.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2.28.1)\n",
"Requirement already satisfied: werkzeug>=1.0.1 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2.0.3)\n",
"Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from packaging->tensorflow-intel==2.11.0->tensorflow) (3.0.9)\n",
"Requirement already satisfied: pyasn1-modules>=0.2.1 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (0.2.8)\n",
"Requirement already satisfied: cachetools<6.0,>=2.0.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (5.3.0)\n",
"Requirement already satisfied: rsa<5,>=3.1.4 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (4.9)\n",
"Requirement already satisfied: requests-oauthlib>=0.7.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (1.3.1)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (1.26.11)\n",
"Requirement already satisfied: idna<4,>=2.5 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (3.3)\n",
"Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2022.9.14)\n",
"Requirement already satisfied: charset-normalizer<3,>=2 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (2.0.4)\n",
"Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (0.4.8)\n",
"Requirement already satisfied: oauthlib>=3.0.0 in c:\\users\\sruthikesineni\\anaconda3\\lib\\site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.12,>=2.11->tensorflow-intel==2.11.0->tensorflow) (3.2.2)\n"
]
}
],
"source": [
"!pip install scikit-learn==1.2.0\n",
"!pip install imblearn\n",
"!pip install tensorflow"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"id": "kVfL04w3_fdv"
},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.compose import ColumnTransformer\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"from imblearn.under_sampling import RandomUnderSampler\n",
"from imblearn.over_sampling import SMOTE\n",
"\n",
"from tensorflow.keras.models import Sequential\n",
"from tensorflow.keras.layers import Dense\n",
"from tensorflow.keras.optimizers import Adam\n",
"from tensorflow.keras import metrics as m\n",
"\n",
"import matplotlib.pyplot as plt\n",
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "k3y3STtODq6n"
},
"source": [
"# Data Loading and Exploration"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"id": "p_nf04yODX1u"
},
"outputs": [],
"source": [
"data = pd.read_csv('creditcard.csv')"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 297
},
"id": "LYW14n9RDauI",
"outputId": "9e5bbab0-a43c-44d7-d47e-75bcb99b2c10"
},
"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>Time</th>\n",
" <th>V1</th>\n",
" <th>V2</th>\n",
" <th>V3</th>\n",
" <th>V4</th>\n",
" <th>V5</th>\n",
" <th>V6</th>\n",
" <th>V7</th>\n",
" <th>V8</th>\n",
" <th>V9</th>\n",
" <th>...</th>\n",
" <th>V21</th>\n",
" <th>V22</th>\n",
" <th>V23</th>\n",
" <th>V24</th>\n",
" <th>V25</th>\n",
" <th>V26</th>\n",
" <th>V27</th>\n",
" <th>V28</th>\n",
" <th>Amount</th>\n",
" <th>Class</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.0</td>\n",
" <td>-1.359807</td>\n",
" <td>-0.072781</td>\n",
" <td>2.536347</td>\n",
" <td>1.378155</td>\n",
" <td>-0.338321</td>\n",
" <td>0.462388</td>\n",
" <td>0.239599</td>\n",
" <td>0.098698</td>\n",
" <td>0.363787</td>\n",
" <td>...</td>\n",
" <td>-0.018307</td>\n",
" <td>0.277838</td>\n",
" <td>-0.110474</td>\n",
" <td>0.066928</td>\n",
" <td>0.128539</td>\n",
" <td>-0.189115</td>\n",
" <td>0.133558</td>\n",
" <td>-0.021053</td>\n",
" <td>149.62</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.0</td>\n",
" <td>1.191857</td>\n",
" <td>0.266151</td>\n",
" <td>0.166480</td>\n",
" <td>0.448154</td>\n",
" <td>0.060018</td>\n",
" <td>-0.082361</td>\n",
" <td>-0.078803</td>\n",
" <td>0.085102</td>\n",
" <td>-0.255425</td>\n",
" <td>...</td>\n",
" <td>-0.225775</td>\n",
" <td>-0.638672</td>\n",
" <td>0.101288</td>\n",
" <td>-0.339846</td>\n",
" <td>0.167170</td>\n",
" <td>0.125895</td>\n",
" <td>-0.008983</td>\n",
" <td>0.014724</td>\n",
" <td>2.69</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.0</td>\n",
" <td>-1.358354</td>\n",
" <td>-1.340163</td>\n",
" <td>1.773209</td>\n",
" <td>0.379780</td>\n",
" <td>-0.503198</td>\n",
" <td>1.800499</td>\n",
" <td>0.791461</td>\n",
" <td>0.247676</td>\n",
" <td>-1.514654</td>\n",
" <td>...</td>\n",
" <td>0.247998</td>\n",
" <td>0.771679</td>\n",
" <td>0.909412</td>\n",
" <td>-0.689281</td>\n",
" <td>-0.327642</td>\n",
" <td>-0.139097</td>\n",
" <td>-0.055353</td>\n",
" <td>-0.059752</td>\n",
" <td>378.66</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1.0</td>\n",
" <td>-0.966272</td>\n",
" <td>-0.185226</td>\n",
" <td>1.792993</td>\n",
" <td>-0.863291</td>\n",
" <td>-0.010309</td>\n",
" <td>1.247203</td>\n",
" <td>0.237609</td>\n",
" <td>0.377436</td>\n",
" <td>-1.387024</td>\n",
" <td>...</td>\n",
" <td>-0.108300</td>\n",
" <td>0.005274</td>\n",
" <td>-0.190321</td>\n",
" <td>-1.175575</td>\n",
" <td>0.647376</td>\n",
" <td>-0.221929</td>\n",
" <td>0.062723</td>\n",
" <td>0.061458</td>\n",
" <td>123.50</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2.0</td>\n",
" <td>-1.158233</td>\n",
" <td>0.877737</td>\n",
" <td>1.548718</td>\n",
" <td>0.403034</td>\n",
" <td>-0.407193</td>\n",
" <td>0.095921</td>\n",
" <td>0.592941</td>\n",
" <td>-0.270533</td>\n",
" <td>0.817739</td>\n",
" <td>...</td>\n",
" <td>-0.009431</td>\n",
" <td>0.798278</td>\n",
" <td>-0.137458</td>\n",
" <td>0.141267</td>\n",
" <td>-0.206010</td>\n",
" <td>0.502292</td>\n",
" <td>0.219422</td>\n",
" <td>0.215153</td>\n",
" <td>69.99</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 31 columns</p>\n",
"</div>"
],
"text/plain": [
" Time V1 V2 V3 V4 V5 V6 V7 \\\n",
"0 0.0 -1.359807 -0.072781 2.536347 1.378155 -0.338321 0.462388 0.239599 \n",
"1 0.0 1.191857 0.266151 0.166480 0.448154 0.060018 -0.082361 -0.078803 \n",
"2 1.0 -1.358354 -1.340163 1.773209 0.379780 -0.503198 1.800499 0.791461 \n",
"3 1.0 -0.966272 -0.185226 1.792993 -0.863291 -0.010309 1.247203 0.237609 \n",
"4 2.0 -1.158233 0.877737 1.548718 0.403034 -0.407193 0.095921 0.592941 \n",
"\n",
" V8 V9 ... V21 V22 V23 V24 V25 \\\n",
"0 0.098698 0.363787 ... -0.018307 0.277838 -0.110474 0.066928 0.128539 \n",
"1 0.085102 -0.255425 ... -0.225775 -0.638672 0.101288 -0.339846 0.167170 \n",
"2 0.247676 -1.514654 ... 0.247998 0.771679 0.909412 -0.689281 -0.327642 \n",
"3 0.377436 -1.387024 ... -0.108300 0.005274 -0.190321 -1.175575 0.647376 \n",
"4 -0.270533 0.817739 ... -0.009431 0.798278 -0.137458 0.141267 -0.206010 \n",
"\n",
" V26 V27 V28 Amount Class \n",
"0 -0.189115 0.133558 -0.021053 149.62 0 \n",
"1 0.125895 -0.008983 0.014724 2.69 0 \n",
"2 -0.139097 -0.055353 -0.059752 378.66 0 \n",
"3 -0.221929 0.062723 0.061458 123.50 0 \n",
"4 0.502292 0.219422 0.215153 69.99 0 \n",
"\n",
"[5 rows x 31 columns]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "d2LkRDvpDcR7",
"outputId": "49fccba8-5661-46ed-b607-3f2de60f1bb0"
},
"outputs": [
{
"data": {
"text/plain": [
"(284807, 31)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.shape"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "J6aBIu1pDdGQ",
"outputId": "c31f537f-3c4b-4a6a-9b3b-85f6a51a9976"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 284807 entries, 0 to 284806\n",
"Data columns (total 31 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Time 284807 non-null float64\n",
" 1 V1 284807 non-null float64\n",
" 2 V2 284807 non-null float64\n",
" 3 V3 284807 non-null float64\n",
" 4 V4 284807 non-null float64\n",
" 5 V5 284807 non-null float64\n",
" 6 V6 284807 non-null float64\n",
" 7 V7 284807 non-null float64\n",
" 8 V8 284807 non-null float64\n",
" 9 V9 284807 non-null float64\n",
" 10 V10 284807 non-null float64\n",
" 11 V11 284807 non-null float64\n",
" 12 V12 284807 non-null float64\n",
" 13 V13 284807 non-null float64\n",
" 14 V14 284807 non-null float64\n",
" 15 V15 284807 non-null float64\n",
" 16 V16 284807 non-null float64\n",
" 17 V17 284807 non-null float64\n",
" 18 V18 284807 non-null float64\n",
" 19 V19 284807 non-null float64\n",
" 20 V20 284807 non-null float64\n",
" 21 V21 284807 non-null float64\n",
" 22 V22 284807 non-null float64\n",
" 23 V23 284807 non-null float64\n",
" 24 V24 284807 non-null float64\n",
" 25 V25 284807 non-null float64\n",
" 26 V26 284807 non-null float64\n",
" 27 V27 284807 non-null float64\n",
" 28 V28 284807 non-null float64\n",
" 29 Amount 284807 non-null float64\n",
" 30 Class 284807 non-null int64 \n",
"dtypes: float64(30), int64(1)\n",
"memory usage: 67.4 MB\n"
]
}
],
"source": [
"data.info()"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "wMOYC2reDd0X",
"outputId": "6bd772c9-9864-45ba-87ba-93facd8e8953"
},
"outputs": [
{
"data": {
"text/plain": [
"Time 0\n",
"V1 0\n",
"V2 0\n",
"V3 0\n",
"V4 0\n",
"V5 0\n",
"V6 0\n",
"V7 0\n",
"V8 0\n",
"V9 0\n",
"V10 0\n",
"V11 0\n",
"V12 0\n",
"V13 0\n",
"V14 0\n",
"V15 0\n",
"V16 0\n",
"V17 0\n",
"V18 0\n",
"V19 0\n",
"V20 0\n",
"V21 0\n",
"V22 0\n",
"V23 0\n",
"V24 0\n",
"V25 0\n",
"V26 0\n",
"V27 0\n",
"V28 0\n",
"Amount 0\n",
"Class 0\n",
"dtype: int64"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#check missing values\n",
"data.isna().sum()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"id": "T-IQuiTkOy0v"
},
"outputs": [],
"source": [
"#dropping 1 missing row\n",
"data.dropna(inplace = True)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "XVW_P4LaPKYy",
"outputId": "867c95c0-0a45-4de3-8dda-95334d8d80da"
},
"outputs": [
{
"data": {
"text/plain": [
"1081"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#check duplicate rows\n",
"data.duplicated().sum()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"id": "sfVE-NitPVzR"
},
"outputs": [],
"source": [
"#dropping duplicated rows\n",
"data.drop_duplicates(inplace = True)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 390
},
"id": "DZ3uVyJXD7m-",
"outputId": "b0ef8c1f-f2cf-48b9-8718-ae999aa0b06a"
},
"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>Time</th>\n",
" <th>V1</th>\n",
" <th>V2</th>\n",
" <th>V3</th>\n",
" <th>V4</th>\n",
" <th>V5</th>\n",
" <th>V6</th>\n",
" <th>V7</th>\n",
" <th>V8</th>\n",
" <th>V9</th>\n",
" <th>...</th>\n",
" <th>V21</th>\n",
" <th>V22</th>\n",
" <th>V23</th>\n",
" <th>V24</th>\n",
" <th>V25</th>\n",
" <th>V26</th>\n",
" <th>V27</th>\n",
" <th>V28</th>\n",
" <th>Amount</th>\n",
" <th>Class</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>...</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" <td>283726.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>94811.077600</td>\n",
" <td>0.005917</td>\n",
" <td>-0.004135</td>\n",
" <td>0.001613</td>\n",
" <td>-0.002966</td>\n",
" <td>0.001828</td>\n",
" <td>-0.001139</td>\n",
" <td>0.001801</td>\n",
" <td>-0.000854</td>\n",
" <td>-0.001596</td>\n",
" <td>...</td>\n",
" <td>-0.000371</td>\n",
" <td>-0.000015</td>\n",
" <td>0.000198</td>\n",
" <td>0.000214</td>\n",
" <td>-0.000232</td>\n",
" <td>0.000149</td>\n",
" <td>0.001763</td>\n",
" <td>0.000547</td>\n",
" <td>88.472687</td>\n",
" <td>0.001667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>47481.047891</td>\n",
" <td>1.948026</td>\n",
" <td>1.646703</td>\n",
" <td>1.508682</td>\n",
" <td>1.414184</td>\n",
" <td>1.377008</td>\n",
" <td>1.331931</td>\n",
" <td>1.227664</td>\n",
" <td>1.179054</td>\n",
" <td>1.095492</td>\n",
" <td>...</td>\n",
" <td>0.723909</td>\n",
" <td>0.724550</td>\n",
" <td>0.623702</td>\n",
" <td>0.605627</td>\n",
" <td>0.521220</td>\n",
" <td>0.482053</td>\n",
" <td>0.395744</td>\n",
" <td>0.328027</td>\n",
" <td>250.399437</td>\n",
" <td>0.040796</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>0.000000</td>\n",
" <td>-56.407510</td>\n",
" <td>-72.715728</td>\n",
" <td>-48.325589</td>\n",
" <td>-5.683171</td>\n",
" <td>-113.743307</td>\n",
" <td>-26.160506</td>\n",
" <td>-43.557242</td>\n",
" <td>-73.216718</td>\n",
" <td>-13.434066</td>\n",
" <td>...</td>\n",
" <td>-34.830382</td>\n",
" <td>-10.933144</td>\n",
" <td>-44.807735</td>\n",
" <td>-2.836627</td>\n",
" <td>-10.295397</td>\n",
" <td>-2.604551</td>\n",
" <td>-22.565679</td>\n",
" <td>-15.430084</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>54204.750000</td>\n",
" <td>-0.915951</td>\n",
" <td>-0.600321</td>\n",
" <td>-0.889682</td>\n",
" <td>-0.850134</td>\n",
" <td>-0.689830</td>\n",
" <td>-0.769031</td>\n",
" <td>-0.552509</td>\n",
" <td>-0.208828</td>\n",
" <td>-0.644221</td>\n",
" <td>...</td>\n",
" <td>-0.228305</td>\n",
" <td>-0.542700</td>\n",
" <td>-0.161703</td>\n",
" <td>-0.354453</td>\n",
" <td>-0.317485</td>\n",
" <td>-0.326763</td>\n",
" <td>-0.070641</td>\n",
" <td>-0.052818</td>\n",
" <td>5.600000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>84692.500000</td>\n",
" <td>0.020384</td>\n",
" <td>0.063949</td>\n",
" <td>0.179963</td>\n",
" <td>-0.022248</td>\n",
" <td>-0.053468</td>\n",
" <td>-0.275168</td>\n",
" <td>0.040859</td>\n",
" <td>0.021898</td>\n",
" <td>-0.052596</td>\n",
" <td>...</td>\n",
" <td>-0.029441</td>\n",
" <td>0.006675</td>\n",
" <td>-0.011159</td>\n",
" <td>0.041016</td>\n",
" <td>0.016278</td>\n",
" <td>-0.052172</td>\n",
" <td>0.001479</td>\n",
" <td>0.011288</td>\n",
" <td>22.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>139298.000000</td>\n",
" <td>1.316068</td>\n",
" <td>0.800283</td>\n",
" <td>1.026960</td>\n",
" <td>0.739647</td>\n",
" <td>0.612218</td>\n",
" <td>0.396792</td>\n",
" <td>0.570474</td>\n",
" <td>0.325704</td>\n",
" <td>0.595977</td>\n",
" <td>...</td>\n",
" <td>0.186194</td>\n",
" <td>0.528245</td>\n",
" <td>0.147748</td>\n",
" <td>0.439738</td>\n",
" <td>0.350667</td>\n",
" <td>0.240261</td>\n",
" <td>0.091208</td>\n",
" <td>0.078276</td>\n",
" <td>77.510000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>172792.000000</td>\n",
" <td>2.454930</td>\n",
" <td>22.057729</td>\n",
" <td>9.382558</td>\n",
" <td>16.875344</td>\n",
" <td>34.801666</td>\n",
" <td>73.301626</td>\n",
" <td>120.589494</td>\n",
" <td>20.007208</td>\n",
" <td>15.594995</td>\n",
" <td>...</td>\n",
" <td>27.202839</td>\n",
" <td>10.503090</td>\n",
" <td>22.528412</td>\n",
" <td>4.584549</td>\n",
" <td>7.519589</td>\n",
" <td>3.517346</td>\n",
" <td>31.612198</td>\n",
" <td>33.847808</td>\n",
" <td>25691.160000</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>8 rows × 31 columns</p>\n",
"</div>"
],
"text/plain": [
" Time V1 V2 V3 \\\n",
"count 283726.000000 283726.000000 283726.000000 283726.000000 \n",
"mean 94811.077600 0.005917 -0.004135 0.001613 \n",
"std 47481.047891 1.948026 1.646703 1.508682 \n",
"min 0.000000 -56.407510 -72.715728 -48.325589 \n",
"25% 54204.750000 -0.915951 -0.600321 -0.889682 \n",
"50% 84692.500000 0.020384 0.063949 0.179963 \n",
"75% 139298.000000 1.316068 0.800283 1.026960 \n",
"max 172792.000000 2.454930 22.057729 9.382558 \n",
"\n",
" V4 V5 V6 V7 \\\n",
"count 283726.000000 283726.000000 283726.000000 283726.000000 \n",
"mean -0.002966 0.001828 -0.001139 0.001801 \n",
"std 1.414184 1.377008 1.331931 1.227664 \n",
"min -5.683171 -113.743307 -26.160506 -43.557242 \n",
"25% -0.850134 -0.689830 -0.769031 -0.552509 \n",
"50% -0.022248 -0.053468 -0.275168 0.040859 \n",
"75% 0.739647 0.612218 0.396792 0.570474 \n",
"max 16.875344 34.801666 73.301626 120.589494 \n",
"\n",
" V8 V9 ... V21 V22 \\\n",
"count 283726.000000 283726.000000 ... 283726.000000 283726.000000 \n",
"mean -0.000854 -0.001596 ... -0.000371 -0.000015 \n",
"std 1.179054 1.095492 ... 0.723909 0.724550 \n",
"min -73.216718 -13.434066 ... -34.830382 -10.933144 \n",
"25% -0.208828 -0.644221 ... -0.228305 -0.542700 \n",
"50% 0.021898 -0.052596 ... -0.029441 0.006675 \n",
"75% 0.325704 0.595977 ... 0.186194 0.528245 \n",
"max 20.007208 15.594995 ... 27.202839 10.503090 \n",
"\n",
" V23 V24 V25 V26 \\\n",
"count 283726.000000 283726.000000 283726.000000 283726.000000 \n",
"mean 0.000198 0.000214 -0.000232 0.000149 \n",
"std 0.623702 0.605627 0.521220 0.482053 \n",
"min -44.807735 -2.836627 -10.295397 -2.604551 \n",
"25% -0.161703 -0.354453 -0.317485 -0.326763 \n",
"50% -0.011159 0.041016 0.016278 -0.052172 \n",
"75% 0.147748 0.439738 0.350667 0.240261 \n",
"max 22.528412 4.584549 7.519589 3.517346 \n",
"\n",
" V27 V28 Amount Class \n",
"count 283726.000000 283726.000000 283726.000000 283726.000000 \n",
"mean 0.001763 0.000547 88.472687 0.001667 \n",
"std 0.395744 0.328027 250.399437 0.040796 \n",
"min -22.565679 -15.430084 0.000000 0.000000 \n",
"25% -0.070641 -0.052818 5.600000 0.000000 \n",
"50% 0.001479 0.011288 22.000000 0.000000 \n",
"75% 0.091208 0.078276 77.510000 0.000000 \n",
"max 31.612198 33.847808 25691.160000 1.000000 \n",
"\n",
"[8 rows x 31 columns]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#check distribution of data\n",
"data.describe()"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "JAyeg8X4PL6X",
"outputId": "e1dd6247-d826-453b-a64e-921586ffb349"
},
"outputs": [
{
"data": {
"text/plain": [
"0 283253\n",
"1 473\n",
"Name: Class, dtype: int64"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#checking target value counts\n",
"data['Class'].value_counts()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "nxPukLAxgnw8"
},
"source": [
"## Data Preprocessing"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"id": "rLrG54FjP14b"
},
"outputs": [],
"source": [
"# Standard Scaler\n",
"transformer = ColumnTransformer(transformers = [('scaler', StandardScaler(), data.columns[:-1])], \n",
" remainder = 'passthrough'\n",
")\n",
"transformer.set_output(transform = 'pandas')\n",
"transformed_data = transformer.fit_transform(data)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mpxMvpUdbOc-",
"outputId": "699167ce-701f-4bb6-dcd4-8f998c93ad57"
},
"outputs": [
{
"data": {
"text/plain": [
"(283726, 31)"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"transformed_data.shape"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"id": "ipiczz4nMzmq"
},
"outputs": [],
"source": [
"#separating features and targets\n",
"X = transformed_data.drop('remainder__Class', axis = 1)\n",
"y = transformed_data['remainder__Class']"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"id": "OABdAqEgaqkV"
},
"outputs": [],
"source": [
"#sampling to tackle class imbalance\n",
"over_sampler = SMOTE(sampling_strategy = 0.3, random_state = 101)\n",
"X, y = over_sampler.fit_resample(X, y)\n",
"\n",
"under_sampler = RandomUnderSampler(sampling_strategy = 0.7, random_state = 101)\n",
"X, y = under_sampler.fit_resample(X, y)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"id": "n9d7yytGM7-4"
},
"outputs": [],
"source": [
"#train test split\n",
"X_train, X_test, y_train, y_test = train_test_split(X, \n",
" y, \n",
" test_size = 0.2, \n",
" stratify = y,\n",
" random_state = 101)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "YLQKuUBUNiKb"
},
"source": [
"# Model Training and Evaluation"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Uyi8TPMWNbRT",
"outputId": "cc55c770-3364-4a6b-906d-270bbae3fa7d"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: \"sequential\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense (Dense) (None, 8) 248 \n",
" \n",
" dense_1 (Dense) (None, 8) 72 \n",
" \n",
" dense_2 (Dense) (None, 1) 9 \n",
" \n",
"=================================================================\n",
"Total params: 329\n",
"Trainable params: 329\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
}
],
"source": [
"ann = Sequential()\n",
"\n",
"ann.add(Dense(8, input_shape = (X.shape[1],), activation = 'relu'))\n",
"ann.add(Dense(8, activation = 'relu'))\n",
"ann.add(Dense(1, activation = 'sigmoid'))\n",
"\n",
"Metrics = [m.Precision(name = 'precision'), m.Recall(name = 'recall')]\n",
"\n",
"ann.compile(optimizer = Adam(), loss = 'binary_crossentropy', metrics = Metrics)\n",
"ann.summary()"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "K_oJ02cxOhKl",
"outputId": "00ac59cd-0a7c-4401-c098-71b2d9084151"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/15\n",
"645/645 [==============================] - 4s 4ms/step - loss: 0.2213 - precision: 0.9524 - recall: 0.8443 - val_loss: 0.1014 - val_precision: 0.9673 - val_recall: 0.9301\n",
"Epoch 2/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0861 - precision: 0.9716 - recall: 0.9416 - val_loss: 0.0741 - val_precision: 0.9735 - val_recall: 0.9529\n",
"Epoch 3/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0654 - precision: 0.9738 - recall: 0.9622 - val_loss: 0.0593 - val_precision: 0.9752 - val_recall: 0.9679\n",
"Epoch 4/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0532 - precision: 0.9759 - recall: 0.9756 - val_loss: 0.0498 - val_precision: 0.9737 - val_recall: 0.9826\n",
"Epoch 5/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0450 - precision: 0.9766 - recall: 0.9845 - val_loss: 0.0432 - val_precision: 0.9772 - val_recall: 0.9842\n",
"Epoch 6/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0392 - precision: 0.9784 - recall: 0.9893 - val_loss: 0.0385 - val_precision: 0.9793 - val_recall: 0.9899\n",
"Epoch 7/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0353 - precision: 0.9799 - recall: 0.9916 - val_loss: 0.0353 - val_precision: 0.9798 - val_recall: 0.9928\n",
"Epoch 8/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0324 - precision: 0.9810 - recall: 0.9932 - val_loss: 0.0327 - val_precision: 0.9791 - val_recall: 0.9949\n",
"Epoch 9/15\n",
"645/645 [==============================] - 2s 2ms/step - loss: 0.0301 - precision: 0.9820 - recall: 0.9940 - val_loss: 0.0312 - val_precision: 0.9799 - val_recall: 0.9962\n",
"Epoch 10/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0281 - precision: 0.9832 - recall: 0.9950 - val_loss: 0.0293 - val_precision: 0.9814 - val_recall: 0.9958\n",
"Epoch 11/15\n",
"645/645 [==============================] - 2s 2ms/step - loss: 0.0263 - precision: 0.9839 - recall: 0.9957 - val_loss: 0.0277 - val_precision: 0.9824 - val_recall: 0.9965\n",
"Epoch 12/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0249 - precision: 0.9841 - recall: 0.9957 - val_loss: 0.0265 - val_precision: 0.9824 - val_recall: 0.9964\n",
"Epoch 13/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0235 - precision: 0.9867 - recall: 0.9943 - val_loss: 0.0252 - val_precision: 0.9869 - val_recall: 0.9941\n",
"Epoch 14/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0223 - precision: 0.9895 - recall: 0.9930 - val_loss: 0.0242 - val_precision: 0.9884 - val_recall: 0.9938\n",
"Epoch 15/15\n",
"645/645 [==============================] - 1s 2ms/step - loss: 0.0213 - precision: 0.9904 - recall: 0.9932 - val_loss: 0.0223 - val_precision: 0.9902 - val_recall: 0.9938\n"
]
}
],
"source": [
"model = ann.fit(X_train, y_train, validation_data = (X_test, y_test), epochs = 15, batch_size = 256)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 350
},
"id": "QryGOZYNO88N",
"outputId": "a20d2cad-2d58-4bc8-87e9-74d80704f04b"
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA2AAAAHUCAYAAABcVkvuAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAACJJUlEQVR4nOzdd3hUVf7H8feUJJOekIQUSEIR6RCKVFFcEUQsWBEV0MXCWlZEV0Us2GDFsugqWFZBVkX82V1RAQVEqSJBEFZwKaEkUpNJnZnM3N8fkwwMCRBCyITk83qe+2TmzJlzvpME5cO591yTYRgGIiIiIiIicsqZA12AiIiIiIhIQ6EAJiIiIiIiUksUwERERERERGqJApiIiIiIiEgtUQATERERERGpJQpgIiIiIiIitUQBTEREREREpJYogImIiIiIiNQSBTAREREREZFaogAmIhIAJpOpSseiRYtOap6JEydiMpmq9d5FixbVSA113Y033kizZs2O+vrevXsJDg7m2muvPWofu91OWFgYl156aZXnnTlzJiaTiW3btlW5lsOZTCYmTpxY5fnK7d69m4kTJ5KZmVnhtZP5fTlZzZo14+KLLw7I3CIitcka6AJERBqiZcuW+T1/8sknWbhwId99951fe7t27U5qnptvvpkLL7ywWu/t2rUry5YtO+kaTncJCQlceumlfPrppxw8eJDY2NgKfd5//32Ki4sZPXr0Sc31yCOPcPfdd5/UGMeze/duHn/8cZo1a0ZGRobfayfz+yIiIlWjACYiEgC9evXye56QkIDZbK7QfqSioiLCwsKqPE/Tpk1p2rRptWqMioo6bj0NxejRo/noo4949913ufPOOyu8/tZbb5GYmMiQIUNOap6WLVue1PtP1sn8voiISNXoFEQRkTqqf//+dOjQge+//54+ffoQFhbGn//8ZwDmzJnDwIEDSU5OJjQ0lLZt2/Lggw9SWFjoN0Zlp5SVn+r19ddf07VrV0JDQ2nTpg1vvfWWX7/KTkG88cYbiYiI4Pfff+eiiy4iIiKC1NRU7r33XhwOh9/7d+7cyVVXXUVkZCQxMTFcf/31rFq1CpPJxMyZM4/52ffu3cvtt99Ou3btiIiIoHHjxvzpT39iyZIlfv22bduGyWTiueee44UXXqB58+ZERETQu3dvli9fXmHcmTNn0rp1a0JCQmjbti2zZs06Zh3lBg0aRNOmTZkxY0aF1zZu3MiKFSsYOXIkVquV+fPnc9lll9G0aVNsNhtnnHEGt912G/v27TvuPJWdgmi327nllluIi4sjIiKCCy+8kE2bNlV47++//85NN91Eq1atCAsLo0mTJlxyySWsW7fO12fRokWcddZZANx0002+U13LT2Ws7PfF4/EwZcoU2rRpQ0hICI0bN2bkyJHs3LnTr1/57+uqVavo168fYWFhtGjRgr///e94PJ7jfvaqKCkpYfz48TRv3pzg4GCaNGnCHXfcQW5url+/7777jv79+xMXF0doaChpaWlceeWVFBUV+fpMnz6dzp07ExERQWRkJG3atOGhhx6qkTpFRI5FK2AiInVYdnY2N9xwA/fffz+TJk3CbPb+u9nmzZu56KKLGDt2LOHh4fz3v//lmWeeYeXKlRVOY6zM2rVruffee3nwwQdJTEzkX//6F6NHj+aMM87gnHPOOeZ7XS4Xl156KaNHj+bee+/l+++/58knnyQ6OppHH30UgMLCQs477zwOHDjAM888wxlnnMHXX3/NsGHDqvS5Dxw4AMBjjz1GUlISBQUFfPLJJ/Tv359vv/2W/v37+/V/5ZVXaNOmDVOnTgW8p/JddNFFbN26lejoaMAbvm666SYuu+wynn/+efLy8pg4cSIOh8P3fT0as9nMjTfeyFNPPcXatWvp3Lmz77XyUFYejv/3v//Ru3dvbr75ZqKjo9m2bRsvvPACZ599NuvWrSMoKKhK3wMAwzAYOnQoS5cu5dFHH+Wss87ixx9/ZPDgwRX67t69m7i4OP7+97+TkJDAgQMHePvtt+nZsydr1qyhdevWdO3alRkzZnDTTTfx8MMP+1bsjrXq9Ze//IXXX3+dO++8k4svvpht27bxyCOPsGjRIn7++Wfi4+N9fXNycrj++uu59957eeyxx/jkk08YP348KSkpjBw5ssqf+1jfi2+//Zbx48fTr18/fvnlFx577DGWLVvGsmXLCAkJYdu2bQwZMoR+/frx1ltvERMTw65du/j6669xOp2EhYXx/vvvc/vtt3PXXXfx3HPPYTab+f3339mwYcNJ1SgiUiWGiIgE3KhRo4zw8HC/tnPPPdcAjG+//faY7/V4PIbL5TIWL15sAMbatWt9rz322GPGkf+pT09PN2w2m7F9+3ZfW3FxsdGoUSPjtttu87UtXLjQAIyFCxf61QkYH3zwgd+YF110kdG6dWvf81deecUAjK+++sqv32233WYAxowZM475mY5UWlpquFwu4/zzzzcuv/xyX/vWrVsNwOjYsaNRWlrqa1+5cqUBGLNnzzYMwzDcbreRkpJidO3a1fB4PL5+27ZtM4KCgoz09PTj1rBlyxbDZDIZf/3rX31tLpfLSEpKMvr27Vvpe8p/Ntu3bzcA47PPPvO9NmPGDAMwtm7d6msbNWqUXy1fffWVARgvvvii37hPP/20ARiPPfbYUestLS01nE6n0apVK+Oee+7xta9ateqoP4Mjf182btxoAMbtt9/u12/FihUGYDz00EO+tvLf1xUrVvj1bdeunTFo0KCj1lkuPT3dGDJkyFFf//rrrw3AmDJlil/7nDlzDMB4/fXXDcMwjA8//NAAjMzMzKOOdeeddxoxMTHHrUlE5FTQKYgiInVYbGwsf/rTnyq0b9myheuuu46kpCQsFgtBQUGce+65gPeUuOPJyMggLS3N99xms3HmmWeyffv2477XZDJxySWX+LV16tTJ772LFy8mMjKywoYOw4cPP+745V599VW6du2KzWbDarUSFBTEt99+W+nnGzJkCBaLxa8ewFfTb7/9xu7du7nuuuv8TrFLT0+nT58+VaqnefPmnHfeebz77rs4nU4AvvrqK3JycnyrXwB79uxhzJgxpKam+upOT08HqvazOdzChQsBuP766/3ar7vuugp9S0tLmTRpEu3atSM4OBir1UpwcDCbN28+4XmPnP/GG2/0a+/Rowdt27bl22+/9WtPSkqiR48efm1H/m5UV/nK7pG1XH311YSHh/tqycjIIDg4mFtvvZW3336bLVu2VBirR48e5ObmMnz4cD777LMqnR4qIlJTFMBEROqw5OTkCm0FBQX069ePFStW8NRTT7Fo0SJWrVrFxx9/DEBxcfFxx42Li6vQFhISUqX3hoWFYbPZKry3pKTE93z//v0kJiZWeG9lbZV54YUX+Mtf/kLPnj356KOPWL58OatWreLCCy+stMYjP09ISAhw6Huxf/9+wBsQjlRZ29GMHj2a/fv38/nnnwPe0w8jIiK45pprAO/1UgMHDuTjjz/m/vvv59tvv2XlypW+69Gq8v093P79+7FarRU+X2U1jxs3jkceeYShQ4fyxRdfsGLFClatWkXnzp1PeN7D54fKfw9TUlJ8r5c7md+rqtRitVpJSEjwazeZTCQlJflqadmyJQsWLKBx48bccccdtGzZkpYtW/Liiy/63jNixAjeeusttm/fzpVXXknjxo3p2bMn8+fPP+k6RUSOR9eAiYjUYZXdk+m7775j9+7dLFq0yLfqBVTYiCCQ4uLiWLlyZYX2nJycKr3/nXfeoX///kyfPt2vPT8/v9r1HG3+qtYEcMUVVxAbG8tbb73Fueeey3/+8x9GjhxJREQEAOvXr2ft2rXMnDmTUaNG+d73+++/V7vu0tJS9u/f7xduKqv5nXfeYeTIkUyaNMmvfd++fcTExFR7fvBei3jkdWK7d+/2u/7rVCv/Xuzdu9cvhBmGQU5Ojm9zEYB+/frRr18/3G43P/30E//85z8ZO3YsiYmJvvu53XTTTdx0000UFhby/fff89hjj3HxxRezadMm34qliMipoBUwEZHTTHkoK1/lKffaa68FopxKnXvuueTn5/PVV1/5tb///vtVer/JZKrw+X755ZcK90+rqtatW5OcnMzs2bMxDMPXvn37dpYuXVrlcWw2G9dddx3z5s3jmWeeweVy+Z1+WNM/m/POOw+Ad99916/9vffeq9C3su/Zl19+ya5du/zajlwdPJby01/feecdv/ZVq1axceNGzj///OOOUVPK5zqylo8++ojCwsJKa7FYLPTs2ZNXXnkFgJ9//rlCn/DwcAYPHsyECRNwOp38+uuvp6B6EZFDtAImInKa6dOnD7GxsYwZM4bHHnuMoKAg3n33XdauXRvo0nxGjRrFP/7xD2644QaeeuopzjjjDL766iu++eYbgOPuOnjxxRfz5JNP8thjj3Huuefy22+/8cQTT9C8eXNKS0tPuB6z2cyTTz7JzTffzOWXX84tt9xCbm4uEydOPKFTEMF7GuIrr7zCCy+8QJs2bfyuIWvTpg0tW7bkwQcfxDAMGjVqxBdffFHtU9sGDhzIOeecw/33309hYSHdu3fnxx9/5N///neFvhdffDEzZ86kTZs2dOrUidWrV/Pss89WWLlq2bIloaGhvPvuu7Rt25aIiAhSUlJISUmpMGbr1q259dZb+ec//4nZbGbw4MG+XRBTU1O55557qvW5jiYnJ4cPP/ywQnuzZs244IILGDRoEA888AB2u52+ffv6dkHs0qULI0aMALzXDn733XcMGTKEtLQ0SkpKfLdYGDBgAAC33HILoaGh9O3bl+TkZHJycpg8eTLR0dF+K2kiIqeCApiIyGkmLi6OL7/8knvvvZcbbriB8PBwLrvsMubMmUPXrl0DXR7gXVX47rvvGDt2LPfffz8mk4mBAwcybdo0LrroouOeEjdhwgSKiop48803mTJlCu3atePVV1/lk08+8bsv2YkYPXo0AM888wxXXHEFzZo146GHHmLx4sUnNGaXLl3o0qULa9as8Vv9AggKCuKLL77g7rvv5rbbbsNqtTJgwAAWLFjgt+lJVZnNZj7//HPGjRvHlClTcDqd9O3bl7lz59KmTRu/vi+++CJBQUFMnjyZgoICunbtyscff8zDDz/s1y8sLIy33nqLxx9/nIEDB+JyuXjsscd89wI70vTp02nZsiVvvvkmr7zyCtHR0Vx44YVMnjy50mu+Tsbq1au5+uqrK7SPGjWKmTNn8umnnzJx4kRmzJjB008/TXx8PCNGjGDSpEm+lb2MjAzmzZvHY489Rk5ODhEREXTo0IHPP/+cgQMHAt5TFGfOnMkHH3zAwYMHiY+P5+yzz2bWrFkVrjETEalpJuPwczFEREROoUmTJvHwww+TlZV1zHtPiYiI1FdaARMRkVPi5ZdfBryn5blcLr777jteeuklbrjhBoUvERFpsBTARETklAgLC+Mf//gH27Ztw+FwkJaWxgMPPFDhlDgREZGGRKcgioiIiIiI1BJtQy8iIiIiIlJLFMBERERERERqiQKYiIiIiIhILdEmHNXk8XjYvXs3kZGRmEymQJcjIiIiIiIBYhgG+fn5pKSkYDYfe41LAayadu/eTWpqaqDLEBERERGROmLHjh3HvdWKAlg1RUZGAt5vclRUVICrERERERGRQLHb7aSmpvoywrEogFVT+WmHUVFRCmAiIiIiIlKlS5O0CYeIiIiIiEgtUQATERERERGpJQpgIiIiIiIitUTXgImIiIhIveF2u3G5XIEuQ+oZi8WC1WqtkdtPBTyATZs2jWeffZbs7Gzat2/P1KlT6devX6V9P/74Y6ZPn05mZiYOh4P27dszceJEBg0a5OvzxhtvMGvWLNavXw9At27dmDRpEj169PD1mThxIo8//rjf2ImJieTk5JyCTygiIiIitaGgoICdO3diGEagS5F6KCwsjOTkZIKDg09qnIAGsDlz5jB27FimTZtG3759ee211xg8eDAbNmwgLS2tQv/vv/+eCy64gEmTJhETE8OMGTO45JJLWLFiBV26dAFg0aJFDB8+nD59+mCz2ZgyZQoDBw7k119/pUmTJr6x2rdvz4IFC3zPLRbLqf/AIiIiInJKuN1udu7cSVhYGAkJCTWyUiEC3pssO51O9u7dy9atW2nVqtVxb7Z8LCYjgP9E0LNnT7p27cr06dN9bW3btmXo0KFMnjy5SmO0b9+eYcOG8eijj1b6utvtJjY2lpdffpmRI0cC3hWwTz/9lMzMzGrXbrfbiY6OJi8vT9vQi4iIiARYSUkJW7dupVmzZoSGhga6HKmHioqK2L59O82bN8dms/m9diLZIGCbcDidTlavXs3AgQP92gcOHMjSpUurNIbH4yE/P59GjRodtU9RUREul6tCn82bN5OSkkLz5s259tpr2bJlyzHncjgc2O12v0NERERE6hatfMmpcjKrXn7j1Mgo1bBv3z7cbjeJiYl+7SdyLdbzzz9PYWEh11xzzVH7PPjggzRp0oQBAwb42nr27MmsWbP45ptveOONN8jJyaFPnz7s37//qONMnjyZ6Oho35GamlqlGkVERERERMoFfBv6I/+VwjCMKv3LxezZs5k4cSJz5syhcePGlfaZMmUKs2fP5uOPP/ZbJhw8eDBXXnklHTt2ZMCAAXz55ZcAvP3220edb/z48eTl5fmOHTt2VOXjiYiIiIiI+AQsgMXHx2OxWCqsdu3Zs6fCqtiR5syZw+jRo/nggw/8VrYO99xzzzFp0iTmzZtHp06djjleeHg4HTt2ZPPmzUftExISQlRUlN8hIiIiIlLX9O/fn7Fjx1a5/7Zt2zCZTCe1P4JUXcACWHBwMN26dWP+/Pl+7fPnz6dPnz5Hfd/s2bO58cYbee+99xgyZEilfZ599lmefPJJvv76a7p3737cWhwOBxs3biQ5OfnEPoSIiIiISDWZTKZjHjfeeGO1xv3444958sknq9w/NTWV7OxsOnToUK35qkpBzyug29CPGzeOESNG0L17d3r37s3rr79OVlYWY8aMAbyn/e3atYtZs2YB3vA1cuRIXnzxRXr16uVbPQsNDSU6Ohrwnnb4yCOP8N5779GsWTNfn4iICCIiIgC47777uOSSS0hLS2PPnj089dRT2O12Ro0aVdvfghpV1dM3RURERCTwsrOzfY/nzJnDo48+ym+//eZrO3I3R5fLRVBQ0HHHPdYGdZWxWCwkJSWd0Huk+gJ6DdiwYcOYOnUqTzzxBBkZGXz//ffMnTuX9PR0wPtLmZWV5ev/2muvUVpayh133EFycrLvuPvuu319pk2bhtPp5KqrrvLr89xzz/n67Ny5k+HDh9O6dWuuuOIKgoODWb58uW/e083kuRs5+5nvWPjbnkCXIiIiIlInGIZBkbM0IEdV7/KUlJTkO6KjozGZTL7nJSUlxMTE8MEHH9C/f39sNhvvvPMO+/fvZ/jw4TRt2pSwsDA6duzI7Nmz/cY98hTEZs2aMWnSJP785z8TGRlJWloar7/+uu/1I1emFi1ahMlk4ttvv6V79+6EhYXRp08fv3AI8NRTT9G4cWMiIyO5+eabefDBB8nIyKjWzwu8Z6X99a9/pXHjxthsNs4++2xWrVrle/3gwYNcf/31JCQkEBoaSqtWrZgxYwbg3WH9zjvvJDk5GZvNRrNmzap8W6vaFtAVMIDbb7+d22+/vdLXZs6c6fd80aJFxx1v27Ztx+3z/vvvV6Gy08feAgc7DxaTuSOPP7U59vVzIiIiIg1BsctNu0e/CcjcG54YRFhwzfw1+4EHHuD5559nxowZhISEUFJSQrdu3XjggQeIioriyy+/ZMSIEbRo0YKePXsedZznn3+eJ598koceeogPP/yQv/zlL5xzzjm0adPmqO+ZMGECzz//PAkJCYwZM4Y///nP/PjjjwC8++67PP3000ybNo2+ffvy/vvv8/zzz9O8efNqf9b777+fjz76iLfffpv09HSmTJnCoEGD+P3332nUqBGPPPIIGzZs4KuvviI+Pp7ff/+d4uJiAF566SU+//xzPvjgA9LS0tixY0ed3TQv4AFMTl5Gagwf/7yLzB25gS5FRERERGrQ2LFjueKKK/za7rvvPt/ju+66i6+//pr/+7//O2YAu+iii3yLHg888AD/+Mc/WLRo0TED2NNPP825554LeG/tNGTIEEpKSrDZbPzzn/9k9OjR3HTTTQA8+uijzJs3j4KCgmp9zsLCQqZPn87MmTMZPHgwAG+88Qbz58/nzTff5G9/+xtZWVl06dLFt8dDs2bNfO/PysqiVatWnH322ZhMpjp9ZpsCWD2QkRoDwNoduboOTERERAQIDbKw4YlBAZu7phy5oZzb7ebvf/87c+bMYdeuXTgcDhwOB+Hh4ccc5/BdwctPddyz59iXrxz+nvLN6vbs2UNaWhq//fZbhbPYevTowXfffVelz3Wk//3vf7hcLvr27etrCwoKokePHmzcuBGAv/zlL1x55ZX8/PPPDBw4kKFDh/o277vxxhu54IILaN26NRdeeCEXX3wxAwcOrFYtp5oCWD3QJimKYKuZvGIX2/cX0Sz+2H8ARUREROo7k8lUY6cBBtKRwer555/nH//4B1OnTqVjx46Eh4czduxYnE7nMcc5cvMOk8mEx+Op8nvK/4H/8PdUdj/f6ip/77HuETx48GC2b9/Ol19+yYIFCzj//PO54447eO655+jatStbt27lq6++YsGCBVxzzTUMGDCADz/8sNo1nSoBvxGznLxgq5n2Kd77kuk0RBEREZH6a8mSJVx22WXccMMNdO7cmRYtWhzzXranSuvWrVm5cqVf208//VTt8c444wyCg4P54YcffG0ul4uffvqJtm3b+toSEhK48cYbeeedd5g6darfZiJRUVEMGzaMN954gzlz5vDRRx9x4MCBatd0qpz+/ywgAHRuGsOarFwyd+QytEuTQJcjIiIiIqfAGWecwUcffcTSpUuJjY3lhRdeICcnxy+k1Ia77rqLW265he7du9OnTx/mzJnDL7/8QosWLY773iN3UwRo164df/nLX/jb3/5Go0aNSEtLY8qUKRQVFTF69GjAe51Zt27daN++PQ6Hg//85z++z/2Pf/yD5ORkMjIyMJvN/N///R9JSUnExMTU6OeuCQpg9USXtBhmLtUKmIiIiEh99sgjj7B161YGDRpEWFgYt956K0OHDiUvL69W67j++uvZsmUL9913HyUlJVxzzTXceOONFVbFKnPttddWaNu6dSt///vf8Xg8jBgxgvz8fLp3784333xDbGwsAMHBwYwfP55t27YRGhpKv379fLubR0RE8Mwzz7B582YsFgtnnXUWc+fOxWyueyf8mYyTOVmzAbPb7URHR5OXl0dUVFSgy2HbvkL6P7eIYIuZ9Y8PItha937ZRERERE6VkpIStm7dSvPmzbHZbIEup0G64IILSEpK4t///negSzkljvU7diLZQCtg9UR6XBgxYUHkFrnYmG2nc9nOiCIiIiIiNa2oqIhXX32VQYMGYbFYmD17NgsWLGD+/PmBLq3O0zJJPWEymejcNAaAtTtzA1qLiIiIiNRvJpOJuXPn0q9fP7p168YXX3zBRx99xIABAwJdWp2nFbB6JCM1hsWb9pKZlcvI3oGuRkRERETqq9DQUBYsWBDoMk5LWgGrR8pvyJypFTARERERkTpJAawe6dQ0GoAtewvJK3IFuBoRERERETmSAlg9EhcRQlqjMAB+2ZUb2GJERERERKQCBbB6pnz3w7W6H5iIiIiISJ2jAFbP+K4DUwATEREREalzFMDqmYxU73VgmTvy0D22RURERETqFgWweqZ9SjRWs4l9BQ525RYHuhwREREROcX69+/P2LFjfc+bNWvG1KlTj/kek8nEp59+etJz19Q4DYkCWD1jC7LQJjkSgLU78gJcjYiIiIgczSWXXHLUGxcvW7YMk8nEzz//fMLjrlq1iltvvfVky/MzceJEMjIyKrRnZ2czePDgGp3rSDNnziQmJuaUzlGbFMDqoUPXgR0MbCEiIiIiclSjR4/mu+++Y/v27RVee+utt8jIyKBr164nPG5CQgJhYWE1UeJxJSUlERISUitz1RcKYPVQ56YxgFbAREREpAEzDHAWBuao4nX4F198MY0bN2bmzJl+7UVFRcyZM4fRo0ezf/9+hg8fTtOmTQkLC6Njx47Mnj37mOMeeQri5s2bOeecc7DZbLRr14758+dXeM8DDzzAmWeeSVhYGC1atOCRRx7B5fLeV3bmzJk8/vjjrF27FpPJhMlk8tV85CmI69at409/+hOhoaHExcVx6623UlBQ4Hv9xhtvZOjQoTz33HMkJycTFxfHHXfc4ZurOrKysrjsssuIiIggKiqKa665hj/++MP3+tq1aznvvPOIjIwkKiqKbt268dNPPwGwfft2LrnkEmJjYwkPD6d9+/bMnTu32rVUhfWUji4B0SUtBoB1u/IodXuwWpSzRUREpIFxFcGklMDM/dBuCA4/bjer1crIkSOZOXMmjz76KCaTCYD/+7//w+l0cv3111NUVES3bt144IEHiIqK4ssvv2TEiBG0aNGCnj17HncOj8fDFVdcQXx8PMuXL8dut/tdL1YuMjKSmTNnkpKSwrp167jllluIjIzk/vvvZ9iwYaxfv56vv/6aBQsWABAdHV1hjKKiIi688EJ69erFqlWr2LNnDzfffDN33nmnX8hcuHAhycnJLFy4kN9//51hw4aRkZHBLbfcctzPcyTDMBg6dCjh4eEsXryY0tJSbr/9doYNG8aiRYsAuP766+nSpQvTp0/HYrGQmZlJUFAQAHfccQdOp5Pvv/+e8PBwNmzYQERExAnXcSIUwOqhFvERRIZYyXeUsumPAtqlRAW6JBERERGpxJ///GeeffZZFi1axHnnnQd4Tz+84ooriI2NJTY2lvvuu8/X/6677uLrr7/m//7v/6oUwBYsWMDGjRvZtm0bTZs2BWDSpEkVrtt6+OGHfY+bNWvGvffey5w5c7j//vsJDQ0lIiICq9VKUlLSUed69913KS4uZtasWYSHewPoyy+/zCWXXMIzzzxDYmIiALGxsbz88stYLBbatGnDkCFD+Pbbb6sVwBYsWMAvv/zC1q1bSU1NBeDf//437du3Z9WqVZx11llkZWXxt7/9jTZt2gDQqlUr3/uzsrK48sor6dixIwAtWrQ44RpOlAJYPWQ2m+iUGs2Pv+8nc0euApiIiIg0PEFh3pWoQM1dRW3atKFPnz689dZbnHfeefzvf/9jyZIlzJs3DwC3283f//535syZw65du3A4HDgcDl/AOZ6NGzeSlpbmC18AvXv3rtDvww8/ZOrUqfz+++8UFBRQWlpKVNSJ/R1y48aNdO7c2a+2vn374vF4+O2333wBrH379lgsFl+f5ORk1q1bd0JzHT5namqqL3wBtGvXjpiYGDZu3MhZZ53FuHHjuPnmm/n3v//NgAEDuPrqq2nZsiUAf/3rX/nLX/7CvHnzGDBgAFdeeSWdOnWqVi1VpXPT6qlD14HlBrQOERERkYAwmbynAQbiKDuVsKpGjx7NRx99hN1uZ8aMGaSnp3P++ecD8Pzzz/OPf/yD+++/n++++47MzEwGDRqE0+ms0tiV3RfWdER9y5cv59prr2Xw4MH85z//Yc2aNUyYMKHKcxw+15FjVzZn+el/h7/m8XhOaK7jzXl4+8SJE/n1118ZMmQI3333He3ateOTTz4B4Oabb2bLli2MGDGCdevW0b17d/75z39Wq5aqUgCrpzqX7YS4dmduQOsQERERkWO75pprsFgsvPfee7z99tvcdNNNvvCwZMkSLrvsMm644QY6d+5MixYt2Lx5c5XHbteuHVlZWezefWg1cNmyZX59fvzxR9LT05kwYQLdu3enVatWFXZmDA4Oxu12H3euzMxMCgsL/cY2m82ceeaZVa75RJR/vh07dvjaNmzYQF5eHm3btvW1nXnmmdxzzz3MmzePK664ghkzZvheS01NZcyYMXz88cfce++9vPHGG6ek1nIKYPVUl7IAtumPfAodpYEtRkRERESOKiIigmHDhvHQQw+xe/dubrzxRt9rZ5xxBvPnz2fp0qVs3LiR2267jZycnCqPPWDAAFq3bs3IkSNZu3YtS5YsYcKECX59zjjjDLKysnj//ff53//+x0svveRbISrXrFkztm7dSmZmJvv27cPhcFSY6/rrr8dmszFq1CjWr1/PwoULueuuuxgxYoTv9MPqcrvdZGZm+h0bNmxgwIABdOrUieuvv56ff/6ZlStXMnLkSM4991y6d+9OcXExd955J4sWLWL79u38+OOPrFq1yhfOxo4dyzfffMPWrVv5+eef+e677/yC26mgAFZPNY6ykRxtw2N4d0MUERERkbpr9OjRHDx4kAEDBpCWluZrf+SRR+jatSuDBg2if//+JCUlMXTo0CqPazab+eSTT3A4HPTo0YObb76Zp59+2q/PZZddxj333MOdd95JRkYGS5cu5ZFHHvHrc+WVV3LhhRdy3nnnkZCQUOlW+GFhYXzzzTccOHCAs846i6uuuorzzz+fl19++cS+GZUoKCigS5cufsdFF13k2wY/NjaWc845hwEDBtCiRQvmzJkDgMViYf/+/YwcOZIzzzyTa665hsGDB/P4448D3mB3xx130LZtWy688EJat27NtGnTTrreYzEZlZ0YKsdlt9uJjo4mLy/vhC9QrC1/eWc1X63P4cHBbRhzbstAlyMiIiJyypSUlLB161aaN2+OzWYLdDlSDx3rd+xEsoFWwOox33Vg2ohDRERERKROUACrxzLKAlimApiIiIiISJ2gAFaPdWwSjdkE2Xkl/GEvCXQ5IiIiIiINngJYPRYeYuXMxEhAq2AiIiIiInWBAlg9pxsyi4iISEOi/eXkVKmp362AB7Bp06b5dhLp1q0bS5YsOWrfjz/+mAsuuICEhASioqLo3bs333zzTYV+H330Ee3atSMkJMTvTtfVnfd0lpEWA2gFTEREROo3i8UCgNPpDHAlUl8VFRUBEBQUdFLjWGuimOqaM2cOY8eOZdq0afTt25fXXnuNwYMHs2HDBr/7H5T7/vvvueCCC5g0aRIxMTHMmDGDSy65hBUrVtClSxfAe2fvYcOG8eSTT3L55ZfzySefcM011/DDDz/Qs2fPas17OitfAftlZx4ej4HZbApsQSIiIiKngNVqJSwsjL179xIUFITZHPB1BqknDMOgqKiIPXv2EBMT4wv71RXQ+4D17NmTrl27Mn36dF9b27ZtGTp0KJMnT67SGO3bt2fYsGE8+uijAAwbNgy73c5XX33l63PhhRcSGxvru2FcdeZ1OBx+d/y22+2kpqbW6fuAAZS6PXScOI9il5v595xDq7JrwkRERETqG6fTydatW/F4PIEuReqhmJgYkpKSMJkqLmicyH3AArYC5nQ6Wb16NQ8++KBf+8CBA1m6dGmVxvB4POTn59OoUSNf27Jly7jnnnv8+g0aNIipU6ee1LyTJ0/23TH7dGK1mOnYJJqV2w6QuSNXAUxERETqreDgYFq1aqXTEKXGBQUFnfTKV7mABbB9+/bhdrtJTEz0a09MTCQnJ6dKYzz//PMUFhZyzTXX+NpycnKOOWZ15x0/fjzjxo3zPS9fATsddE71BrC1O3O5uvvpUbOIiIhIdZjNZmw2W6DLEDmqgF4DBlRYwjMMo9JlvSPNnj2biRMn8tlnn9G4ceMTHvNE5w0JCSEkJOS4ddVFGamxwFZtxCEiIiIiEmABuzoxPj4ei8VSYdVpz549FVanjjRnzhxGjx7NBx98wIABA/xeS0pKOuaYJzPv6apzajQA/83Op8TlDnA1IiIiIiINV8ACWHBwMN26dWP+/Pl+7fPnz6dPnz5Hfd/s2bO58cYbee+99xgyZEiF13v37l1hzHnz5vnGrO68p7MmMaHER4RQ6jH4dXdeoMsREREREWmwAnoK4rhx4xgxYgTdu3end+/evP7662RlZTFmzBjAe93Vrl27mDVrFuANXyNHjuTFF1+kV69evlWs0NBQoqO9qzx3330355xzDs888wyXXXYZn332GQsWLOCHH36o8rz1jclkIiM1mgUb95C5I49u6Y2O/yYREREREalxAQ1gw4YNY//+/TzxxBNkZ2fToUMH5s6dS3p6OgDZ2dlkZWX5+r/22muUlpZyxx13cMcdd/jaR40axcyZMwHo06cP77//Pg8//DCPPPIILVu2ZM6cOb57gFVl3vooIzWmLIDlBroUEREREZEGK6D3ATudnche/3XBks17GfHmStIahfH9/ecFuhwRERERkXrjRLKBbhHeQHRqGgNA1oEi9hc4jt1ZREREREROCQWwBiI6NIgWCeEA/LJTG3GIiIiIiASCAlgDkpEaA8AaXQcmIiIiIhIQCmANSHkAW6sAJiIiIiISEApgDUjnsuvA1u7MRXuviIiIiIjUPgWwBqRtchTBFjO5RS627y8KdDkiIiIiIg2OAlgDEmw10y7Fuy3m2p25gS1GRERERKQBUgBrYHwbcWTlBrQOEREREZGGSAGsgfFtxKEVMBERERGRWqcA1sCUB7Bfd9txlnoCW4yIiIiISAOjANbApMeFERMWhLPUw39z7IEuR0RERESkQVEAa2BMJpNvO/pM3Q9MRERERKRWKYA1QJ3LTkNUABMRERERqV0KYA1QFwUwEREREZGAUABrgDo1jQZgy95C8opdAa5GRERERKThUABrgOIiQkhrFAbAup15Aa5GRERERKThUABroA5dB3YwsIWIiIiIiDQgCmANVOey0xAzd2gFTERERESktiiANVBd0mIA70YchmEEthgRERERkQZCAayBap8SjdVsYl+Bg915JYEuR0RERESkQVAAa6BsQRbaJEcCkJmVG9hiREREREQaCAWwBqxz0xgA1u7MDWgdIiIiIiINhQJYA5ZRvhOiVsBERERERGqFAlgDVh7A1u3Ko9TtCWwxIiIiIiINgAJYA9YyIYKIECvFLjeb/igIdDkiIiIiIvWeAlgDZjab6FR2PzBdByYiIiIicuopgDVwug5MRERERKT2KIA1cJ3LAphWwERERERETj0FsAauS1kA2/RHPoWO0sAWIyIiIiJSzymANXCNo2wkR9vwGN7dEEVERERE5NRRAJNDN2TekRvQOkRERERE6jsFMCEjLQaATAUwEREREZFTKuABbNq0aTRv3hybzUa3bt1YsmTJUftmZ2dz3XXX0bp1a8xmM2PHjq3Qp3///phMpgrHkCFDfH0mTpxY4fWkpKRT8fFOC1oBExERERGpHQENYHPmzGHs2LFMmDCBNWvW0K9fPwYPHkxWVlal/R0OBwkJCUyYMIHOnTtX2ufjjz8mOzvbd6xfvx6LxcLVV1/t1699+/Z+/datW1fjn+900alpNGYT7M4rYY+9JNDliIiIiIjUWwENYC+88AKjR4/m5ptvpm3btkydOpXU1FSmT59eaf9mzZrx4osvMnLkSKKjoyvt06hRI5KSknzH/PnzCQsLqxDArFarX7+EhIQa/3yni/AQK60aRwI6DVFERERE5FQKWABzOp2sXr2agQMH+rUPHDiQpUuX1tg8b775Jtdeey3h4eF+7Zs3byYlJYXmzZtz7bXXsmXLlmOO43A4sNvtfkd94rshswKYiIiIiMgpE7AAtm/fPtxuN4mJiX7tiYmJ5OTk1MgcK1euZP369dx8881+7T179mTWrFl88803vPHGG+Tk5NCnTx/2799/1LEmT55MdHS070hNTa2RGusK3ZBZREREROTUC/gmHCaTye+5YRgV2qrrzTffpEOHDvTo0cOvffDgwVx55ZV07NiRAQMG8OWXXwLw9ttvH3Ws8ePHk5eX5zt27NhRIzXWFeUrYL/syMPjMQJbjIiIiIhIPRWwABYfH4/FYqmw2rVnz54Kq2LVUVRUxPvvv19h9asy4eHhdOzYkc2bNx+1T0hICFFRUX5HfXJmYgShQRbyHaVs2VcQ6HJEREREROqlgAWw4OBgunXrxvz58/3a58+fT58+fU56/A8++ACHw8ENN9xw3L4Oh4ONGzeSnJx80vOerqwWMx2beDc2ydyRF+BqRERERETqp4Cegjhu3Dj+9a9/8dZbb7Fx40buuecesrKyGDNmDOA97W/kyJF+78nMzCQzM5OCggL27t1LZmYmGzZsqDD2m2++ydChQ4mLi6vw2n333cfixYvZunUrK1as4KqrrsJutzNq1KhT80FPE51TywPYwQBXIiIiIiJSP1kDOfmwYcPYv38/TzzxBNnZ2XTo0IG5c+eSnp4OeG+8fOQ9wbp06eJ7vHr1at577z3S09PZtm2br33Tpk388MMPzJs3r9J5d+7cyfDhw9m3bx8JCQn06tWL5cuX++ZtqHwbcWgFTERERETklDAZhqEdF6rBbrcTHR1NXl5evbkebOfBIs5+ZiFWs4n1jw/CFmQJdEkiIiIiInXeiWSDgO+CKHVHk5hQ4iOCKfUY/Lq7ft3nTERERESkLlAAEx+TyaQbMouIiIiInEIKYOKnc9MYANYqgImIiIiI1DgFMPGTkRYDaAVMRERERORUUAATP53KVsCyDhRxoNAZ2GJEREREROoZBTDxEx0aRIuEcECnIYqIiIiI1DQFMKkgo2wVTKchioiIiIjULAUwqaD8OrC1O3MDWoeIiIiISH2jACYVHL4Tou7TLSIiIiJScxTApIK2yVEEW8wcLHKRdaAo0OWIiIiIiNQbCmBSQbDVTLuUKEDXgYmIiIiI1CQFMKlURmoMoAAmIiIiIlKTFMCkUgpgIiIiIiI1TwFMKtW5LID9utuOs9QT2GJEREREROoJBTCpVLO4MKJDg3CWevhvjj3Q5YiIiIiI1AsKYFIpk8nkWwVbq9MQRURERERqhAKYHFX5dWBrFMBERERERGqEApgcVUZqNKAVMBERERGRmqIAJkfVuWkMAP/bW0hesSuwxYiIiIiI1AMKYHJUcREhpDYKBWDdzrwAVyMiIiIicvpTAJNjykiNBWDtztzAFiIiIiIiUg8ogMkxdW7qvQ5sTVZuYAsREREREakHFMDkmLqkxQCQuSMXwzACW4yIiIiIyGlOAUyOqX1KNBaziX0FDnbnlQS6HBERERGR05oCmByTLchCm6RIQNvRi4iIiIicLAUwOa7yGzJnKoCJiIiIiJwUBTA5rs4KYCIiIiIiNUIBTI6rS1kAW7czj1K3J7DFiIiIiIicxhTA5LhaJEQQEWKl2OVm856CQJcjIiIiInLaUgCT47KYTXQqux+YTkMUEREREak+BTCpkvLrwLQTooiIiIhI9SmASZVoJ0QRERERkZOnACZVUh7ANv2RT6GjNLDFiIiIiIicpgIewKZNm0bz5s2x2Wx069aNJUuWHLVvdnY21113Ha1bt8ZsNjN27NgKfWbOnInJZKpwlJSUVHtegcQoG8nRNjwGrN+VF+hyREREREROSwENYHPmzGHs2LFMmDCBNWvW0K9fPwYPHkxWVlal/R0OBwkJCUyYMIHOnTsfddyoqCiys7P9DpvNVu15xatz0xhApyGKiIiIiFRXQAPYCy+8wOjRo7n55ptp27YtU6dOJTU1lenTp1fav1mzZrz44ouMHDmS6Ojoo45rMplISkryO05mXvHybcSxMzegdYiIiIiInK4CFsCcTierV69m4MCBfu0DBw5k6dKlJzV2QUEB6enpNG3alIsvvpg1a9ac9LwOhwO73e53NDS+jTiycgNah4iIiIjI6SpgAWzfvn243W4SExP92hMTE8nJyan2uG3atGHmzJl8/vnnzJ49G5vNRt++fdm8efNJzTt58mSio6N9R2pqarVrPF11bBqNyQS780rYYy85/htERERERMRPwDfhMJlMfs8Nw6jQdiJ69erFDTfcQOfOnenXrx8ffPABZ555Jv/85z9Pat7x48eTl5fnO3bs2FHtGk9XESFWzmwcCeg6MBERERGR6ghYAIuPj8disVRYddqzZ0+F1amTYTabOeuss3wrYNWdNyQkhKioKL+jIeqc6r32TteBiYiIiIicuIAFsODgYLp168b8+fP92ufPn0+fPn1qbB7DMMjMzCQ5OblW562vMlJjAa2AiYiIiIhUhzWQk48bN44RI0bQvXt3evfuzeuvv05WVhZjxowBvKf97dq1i1mzZvnek5mZCXg32ti7dy+ZmZkEBwfTrl07AB5//HF69epFq1atsNvtvPTSS2RmZvLKK69UeV45uvIVsF925OHxGJjN1T9dVERERESkoQloABs2bBj79+/niSeeIDs7mw4dOjB37lzS09MB742Xj7w3V5cuXXyPV69ezXvvvUd6ejrbtm0DIDc3l1tvvZWcnByio6Pp0qUL33//PT169KjyvHJ0rRMjsQWZyXeUsmVfIWc0jgh0SSIiIiIipw2TYRhGoIs4HdntdqKjo8nLy2tw14Nd/epSVm07yHNXd+aqbk0DXY6IiIiISECdSDYI+C6Icvopvx/YWl0HJiIiIiJyQhTA5IR1Lr8hswKYiIiIiMgJUQCTE1a+ArYx206Jyx3YYkRERERETiMKYHLCmsSEEh8RTKnH4Nfd9kCXIyIiIiJy2lAAkxNmMpno3DQG0HVgIiIiIiInQgFMqiVD14GJiIiIiJwwBTCplvKNONbuzA1oHSIiIiIipxMFMKmW8lMQt+8v4kChM7DFiIiIiIicJhTApFqiw4JoER8OaBVMRERERKSqFMCk2nzXgWXlBrQOEREREZHThQKYVJuuAxMREREROTEKYFJt5Stga3fkYhhGYIsRERERETkNKIBJtbVJjiTYYuZgkYusA0WBLkdEREREpM5TAJNqC7FaaJcSBeh+YCIiIiIiVaEAJidFN2QWEREREak6BTA5KYdfByYiIiIiIsemACYnpXwnxPW77ThLPYEtRkRERESkjlMAk5PSLC6M6NAgnKUefsvJD3Q5IiIiIiJ1mgKYnBSTyeRbBcvccTCwxYiIiIiI1HEKYHLSMppGA5C5Iy/AlYiIiIiI1G0KYHLSMtJiAK2AiYiIiIgcjwKYnLTOTWMA+N/eQuwlrsAWIyIiIiJShymAyUmLiwghtVEoAOt26jREEREREZGjUQCTGlG+CqYbMouIiIiIHJ0CmNSIDN9OiLkBrUNEREREpC5TAJMacXgAMwwjsMWIiIiIiNRRCmBSIzo0icZiNrE330F2XkmgyxERERERqZMUwKRG2IIstEmKBHQaooiIiIjI0SiASY3pXHYa4loFMBERERGRSimASY0pvw5sjQKYiIiIiEilFMCkxpQHsHU78yh1ewJbjIiIiIhIHaQAJjWmZUIEESFWil1uNu8pCHQ5IiIiIiJ1TrUC2I4dO9i5c6fv+cqVKxk7diyvv/56jRUmpx+L2UTHJtGArgMTEREREalMtQLYddddx8KFCwHIycnhggsuYOXKlTz00EM88cQTJzTWtGnTaN68OTabjW7durFkyZKj9s3Ozua6666jdevWmM1mxo4dW6HPG2+8Qb9+/YiNjSU2NpYBAwawcuVKvz4TJ07EZDL5HUlJSSdUt1QuIy0GgLU7cwNah4iIiIhIXVStALZ+/Xp69OgBwAcffECHDh1YunQp7733HjNnzqzyOHPmzGHs2LFMmDCBNWvW0K9fPwYPHkxWVlal/R0OBwkJCUyYMIHOnTtX2mfRokUMHz6chQsXsmzZMtLS0hg4cCC7du3y69e+fXuys7N9x7p166pctxxd56YxAKzJyg1oHSIiIiIidVG1ApjL5SIkJASABQsWcOmllwLQpk0bsrOzqzzOCy+8wOjRo7n55ptp27YtU6dOJTU1lenTp1fav1mzZrz44ouMHDmS6OjoSvu8++673H777WRkZNCmTRveeOMNPB4P3377rV8/q9VKUlKS70hISKhy3XJ0XcpWwDb9kU+RszSwxYiIiIiI1DHVCmDt27fn1VdfZcmSJcyfP58LL7wQgN27dxMXF1elMZxOJ6tXr2bgwIF+7QMHDmTp0qXVKatSRUVFuFwuGjVq5Ne+efNmUlJSaN68Oddeey1btmw55jgOhwO73e53SEWJUTaSomx4DO9uiCIiIiIicki1AtgzzzzDa6+9Rv/+/Rk+fLjvdMDPP//cd2ri8ezbtw+3201iYqJfe2JiIjk5OdUpq1IPPvggTZo0YcCAAb62nj17MmvWLL755hveeOMNcnJy6NOnD/v37z/qOJMnTyY6Otp3pKam1liN9U35dvS6DkxERERExJ+1Om/q378/+/btw263Exsb62u/9dZbCQsLO6GxTCaT33PDMCq0VdeUKVOYPXs2ixYtwmaz+doHDx7se9yxY0d69+5Ny5Ytefvttxk3blylY40fP97vNbvdrhB2FJ1TY/j61xwytROiiIiIiIifagWw4uJiDMPwha/t27fzySef0LZtWwYNGlSlMeLj47FYLBVWu/bs2VNhVaw6nnvuOSZNmsSCBQvo1KnTMfuGh4fTsWNHNm/efNQ+ISEhvuve5Nh8K2A7dAqiiIiIiMjhqnUK4mWXXcasWbMAyM3NpWfPnjz//PMMHTr0qBtoHCk4OJhu3boxf/58v/b58+fTp0+f6pTl8+yzz/Lkk0/y9ddf07179+P2dzgcbNy4keTk5JOaV7w6No3GZIJducXsyS8JdDkiIiIiInVGtQLYzz//TL9+/QD48MMPSUxMZPv27cyaNYuXXnqpyuOMGzeOf/3rX7z11lts3LiRe+65h6ysLMaMGQN4T/sbOXKk33syMzPJzMykoKCAvXv3kpmZyYYNG3yvT5kyhYcffpi33nqLZs2akZOTQ05ODgUFBb4+9913H4sXL2br1q2sWLGCq666CrvdzqhRo6rz7ZAjRIRYadU4AtAqmIiIiIjI4ap1CmJRURGRkZEAzJs3jyuuuAKz2UyvXr3Yvn17lccZNmwY+/fv54knniA7O5sOHTowd+5c0tPTAe+Nl4+8J1iXLl18j1evXs17771Heno627ZtA7w3dnY6nVx11VV+73vssceYOHEiADt37mT48OHs27ePhIQEevXqxfLly33zysnLSI1h0x8FZO44yAXtTv6UUhERERGR+sBkGIZxom/q1KkTN998M5dffjkdOnTg66+/pnfv3qxevZohQ4bU6C6GdZXdbic6Opq8vDyioqICXU6d8+6K7Uz4ZD1nnxHPOzf3DHQ5IiIiIiKnzIlkg2qdgvjoo49y33330axZM3r06EHv3r0B72rY4StU0nAd2ogjF4/nhDO+iIiIiEi9VK1TEK+66irOPvtssrOzffcAAzj//PO5/PLLa6w4OX21TozEFmQm31HKln2FnFF2TZiIiIiISENWrQAGkJSURFJSEjt37sRkMtGkSZMq34RZ6j+rxUzHJtGs2naQtTtyFcBERERERKjmKYgej4cnnniC6Oho0tPTSUtLIyYmhieffBKPx1PTNcppqnPTGADdkFlEREREpEy1VsAmTJjAm2++yd///nf69u2LYRj8+OOPTJw4kZKSEp5++umarlNOQxlpMQCs3Zkb0DpEREREROqKagWwt99+m3/9619ceumlvrbOnTvTpEkTbr/9dgUwAQ6tgG3MtlPicmMLsgS2IBERERGRAKvWKYgHDhygTZs2FdrbtGnDgQMHTrooqR+axoYSHxGMy22wIdse6HJERERERAKuWgGsc+fOvPzyyxXaX375ZTp16nTSRUn9YDKZDl0HlpUb0FpEREREROqCap2COGXKFIYMGcKCBQvo3bs3JpOJpUuXsmPHDubOnVvTNcppLCM1hm//u0fXgYmIiIiIUM0VsHPPPZdNmzZx+eWXk5uby4EDB7jiiiv49ddfmTFjRk3XKKexzmU3ZNZOiCIiIiIiYDIMw6ipwdauXUvXrl1xu901NWSdZbfbiY6OJi8vj6ioqECXU2flFbno/MQ8ANY8cgGx4cEBrkhEREREpGadSDao1gqYSFVFhwXRIj4cgEydhigiIiIiDZwCmJxy5achrtVpiCIiIiLSwCmAySmXoQAmIiIiIgKc4C6IV1xxxTFfz83NPZlapJ46fCMOwzAwmUyBLUhEREREJEBOKIBFR0cf9/WRI0eeVEFS/7RNjiTYYuZgkYsdB4pJiwsLdEkiIiIiIgFxQgFMW8xLdYRYLbRNiWLtjlzW7DioACYiIiIiDZauAZNa0cV3HVheYAsREREREQkgBTCpFZ1TvaevZu44GOBKREREREQCRwFMakVGaiwA63fbcbk9Aa5GRERERCQwFMCkVjSLCyPKZsVZ6uG/2fmBLkdEREREJCAUwKRWmEymQ9vR78wNaC0iIiIiIoGiACa1pnwjjsys3IDWISIiIiISKApgUmvKV8DWagVMRERERBooBTCpNeUB7H97C7CXuAJbjIiIiIhIACiASa2JjwihaWwohgHrdup+YCIiIiLS8CiASa3KKL8ObEduQOsQEREREQkEBTCpVQpgIiIiItKQKYBJrTo8gBmGEdhiRERERERqmQKY1Kr2KdFYzCb25jvIzisJdDkiIiIiIrVKAUxqVWiwhTZJkQCs1WmIIiIiItLAKIBJreus68BEREREpIFSAKsP3KWwZXGgq6gybcQhIiIiIg1VwAPYtGnTaN68OTabjW7durFkyZKj9s3Ozua6666jdevWmM1mxo4dW2m/jz76iHbt2hESEkK7du345JNPTmreOs3jgS/+CrMuhZVvBLqaKikPYOt25eH2aCMOEREREWk4AhrA5syZw9ixY5kwYQJr1qyhX79+DB48mKysrEr7OxwOEhISmDBhAp07d660z7Jlyxg2bBgjRoxg7dq1jBgxgmuuuYYVK1ZUe946zWQCW7T38dz7YMkLga2nClomRBAebKHI6WbznvxAlyMiIiIiUmtMRgD3Au/Zsyddu3Zl+vTpvra2bdsydOhQJk+efMz39u/fn4yMDKZOnerXPmzYMOx2O1999ZWv7cILLyQ2NpbZs2dXe16Hw4HD4fA9t9vtpKamkpeXR1RUVJU/8ylhGLBwEnw/xfv87HFw/qPecFZHDX99Ocu27OfvV3Tk2h5pgS5HRERERKTa7HY70dHRVcoGAVsBczqdrF69moEDB/q1Dxw4kKVLl1Z73GXLllUYc9CgQb4xqzvv5MmTiY6O9h2pqanVrrHGmUzwpwlwwRPe5z+8AF894D09sY4q34hj7c7cgNYhIiIiIlKbAhbA9u3bh9vtJjEx0a89MTGRnJycao+bk5NzzDGrO+/48ePJy8vzHTt27Kh2jadM37thyPPexytfg8/vBI87sDUdxaGNOPICW4iIiIiISC2yBroA0xGnyRmGUaHtVIx5ovOGhIQQEhJyUnXVirNuhuAI+PQvkPkuOAvhijfAGhzoyvyUB7DfcuwUOUsJCw74r6KIiIiIyCkXsBWw+Ph4LBZLhVWnPXv2VFidOhFJSUnHHPNUzVundL4Wrn4bzEGw4VOYcwO4igNdlZ+kaBtJUTY8BqzfZQ90OSIiIiIitSJgASw4OJhu3boxf/58v/b58+fTp0+fao/bu3fvCmPOmzfPN+apmrfOaXcpXPc+WENh8zfw7tXgqFs7DnZO9e7emLnjYIArERERERGpHQE972vcuHGMGDGC7t2707t3b15//XWysrIYM2YM4L3uateuXcyaNcv3nszMTAAKCgrYu3cvmZmZBAcH065dOwDuvvtuzjnnHJ555hkuu+wyPvvsMxYsWMAPP/xQ5XnrjTMGwA0fwXvDYNsSmDUUbvgQQmMDXRkAGamxfPPrH6zVdWAiIiIi0kAENIANGzaM/fv388QTT5CdnU2HDh2YO3cu6enpgPfGy0fem6tLly6+x6tXr+a9994jPT2dbdu2AdCnTx/ef/99Hn74YR555BFatmzJnDlz6NmzZ5XnrVea9YVRn8E7V8Kun2DmxTDiE4hoHOjKDlsByw1sISIiIiIitSSg9wE7nZ3IXv91wh8bYNZlULgH4s6AkZ9BdNOAllTgKKXjxG8wDFg54XwaR9oCWo+IiIiISHWcFvcBk1qW2A7+/DVEp8L+3+GtwXBgS0BLigix0qpxBIBOQxQRERGRBkEBrCGJawk3fQWNWkJeljeE7dkY0JLKt6Nfq9MQRURERKQBUABraGJSvSGscXsoyIEZF8HuNQErp7Pvhsy5AatBRERERKS2KIA1RJGJcON/oEk3KD4Ab18K25cFpJTOTWMAWLszF49HlyOKiIiISP2mANZQhTXybsSRfjY47PDvy+F/39V6Ga2TIrEFmckvKWXr/sJan19EREREpDYpgDVkIZFw/f/BGRdAabH3fmEb/1OrJQRZzHRIKduOPiu3VucWEREREaltCmANXXAYXPsetL0U3E74YCT88kGtluDbiGNnbq3OKyIiIiJS2xTABKzBcNUM6HwdGG74+Fb46a1am14bcYiIiIhIQ6EAJl4WK1z2Cpx1C2DAf+6BH1+qlanLV8A2ZtspcblrZU4RERERkUBQAJNDzGa46Fk4+x7v8/mPwMJJYJza3QmbxoYSFx6My22wIdt+SucSEREREQkkBTDxZzLBgIlw/qPe54ufgW8mnNIQZjKZdENmEREREWkQFMCkcv3uhcFTvI+XvwJf/BU8p+70QF0HJiIiIiINgQKYHF3P27zXhZnM8PMs7+YcbtcpmUorYCIiIiLSECiAybF1uQGuegvMVlj/oXebeldJjU/Tqan3XmDb9hdxsNBZ4+OLiIiIiNQFCmByfO0vh2tng9UGv82F964BR0GNThETFkzz+HBA9wMTERERkfpLAUyq5syBcP2HEBwBWxfDO1dAcW6NTpGh68BEREREpJ5TAJOqa94PRn4GtmjYsQLevgQK99XY8J3LTkOcs2oHP2cdrLFxRURERETqCgUwOTFNu8ONcyE8AXJ+gRkXgX13jQx9SecUmsaGkp1XwtWvLuPl7zbj9pzae5CJiIiIiNQmBTA5cUkd4KavIKoJ7PsN3roQDm476WHjIkKYe3c/Lumcgttj8Ny8TQx/Yzm7c4tPvmYRERERkTpAAUyqJ76VN4TFNofc7d4Qtve3kx42yhbES9dm8PzVnQkPtrBy6wEunPo9c9dl10DRIiIiIiKBpQAm1RebDn/+GhLaQn42zBgM2WtPeliTycSV3Zry5V/70blpNPaSUm5/92ce+PAXipylNVC4iIiIiEhgKIDJyYlMghu/hOQMKNoPMy+BHStrZOhm8eF8+Jc+3N6/JSYTzPlpBxe/9APrd+XVyPgiIiIiIrVNAUxOXngcjPoc0nqDIw9mDYUti2pk6CCLmfsvbMN7N/ciKcrGln2FXD7tR17//n94tEGHiIiIiJxmFMCkZtii4YaPoOWfwFUI714Dv31VY8P3bhnHV3f3Y1D7RFxug0lz/8uoGSvZYy+psTlERERERE41BTCpOcHhMPx9aHMxuB0w5wZY/1GNDR8bHsyrN3Rj0uUdsQWZWbJ5Hxe+uIQFG/6osTlERERERE4lBTCpWdYQuPpt6DQMPKXw4Wj4eVaNDW8ymbiuZxr/uets2iVHcaDQyc2zfuLRz9ZT4nLX2DwiIiIiIqeCApjUPIsVhr4K3f8MGPD5XbB8eo1OcUbjSD65ow83n90cgFnLtnPpyz/w3xx7jc4jIiIiIlKTFMDk1DCbYcgL0Ocu7/OvH4TFz4JRcxtnhFgtPHxxO97+cw/iI0LY9EcBl778I28v3YZRg/OIiIiIiNQUBTA5dUwmuOBJOG+C9/nCp2DBYzUawgDOPTOBr8f247zWCThLPTz2+a+Mfvsn9hc4anQeEREREZGTpQAmp5bJBOfeD4Mme5//+CJ8eS94PDU6TXxECG/deBYTL2lHsNXMd//dw4UvLuH7TXtrdB4RERERkZOhACa1o/ftcMlLgAl+ehM+/Qu4S2t0CpPJxI19m/PZHX1p1TiCvfkORr61kqe/3ICjVBt0iIiIiEjgKYBJ7ek2Cq78F5it8Mv78OGNUFrzpwm2TY7ii7vOZkSvdADeWLKVK6Yt5fc9BTU+l4iIiIjIiQh4AJs2bRrNmzfHZrPRrVs3lixZcsz+ixcvplu3bthsNlq0aMGrr77q93r//v0xmUwVjiFDhvj6TJw4scLrSUlJp+TzyRE6XgXD3gFLCGz8AmYPB2dRjU9jC7Lw5NAOvDGyO7FhQfy6284l//yB91dmaYMOEREREQmYgAawOXPmMHbsWCZMmMCaNWvo168fgwcPJisrq9L+W7du5aKLLqJfv36sWbOGhx56iL/+9a989NGhm/1+/PHHZGdn+47169djsVi4+uqr/cZq3769X79169ad0s8qh2k9GK7/AILC4H/fwjtXQsmp2T7+gnaJfD32HPqeEUexy82DH6/j9nd/JrfIeUrmExERERE5FpMRwOWAnj170rVrV6ZPP3SPqLZt2zJ06FAmT55cof8DDzzA559/zsaNG31tY8aMYe3atSxbtqzSOaZOncqjjz5KdnY24eHhgHcF7NNPPyUzM7PatdvtdqKjo8nLyyMqKqra4zRoWSvg3avBkQcpXeCGjyGs0SmZyuMxeGPJFp795jdKPQbJ0TZeuCaD3i3jTsl8IiIiItJwnEg2CNgKmNPpZPXq1QwcONCvfeDAgSxdurTS9yxbtqxC/0GDBvHTTz/hcrkqfc+bb77Jtdde6wtf5TZv3kxKSgrNmzfn2muvZcuWLces1+FwYLfb/Q45SWk94cYvICwOdq+BGRdBfs4pmcpsNnHbuS355Pa+NI8PJzuvhOv+tZxnv/kvLnfN7sgoIiIiInI0AQtg+/btw+12k5iY6NeemJhITk7lfwnPycmptH9paSn79u2r0H/lypWsX7+em2++2a+9Z8+ezJo1i2+++YY33niDnJwc+vTpw/79+49a7+TJk4mOjvYdqampVf2ocizJneHGuRCZDHs3wozBcODYYfhkdGwazX/uOpth3VMxDHhl4f+46tVlbN9feMrmFBEREREpF/BNOEwmk99zwzAqtB2vf2Xt4F396tChAz169PBrHzx4MFdeeSUdO3ZkwIABfPnllwC8/fbbR513/Pjx5OXl+Y4dO3Yc+4NJ1TVuAzd9BTFp3vD1Sk/46gHI/+OUTBceYuWZqzrxynVdibJZWbsjl4teXMLHP+/UBh0iIiIickoFLIDFx8djsVgqrHbt2bOnwipXuaSkpEr7W61W4uL8r+UpKiri/fffr7D6VZnw8HA6duzI5s2bj9onJCSEqKgov0NqUKPm8OdvoPk54HbCilfhpQyY/xgUHTglUw7plMxXY8+hR7NGFDrdjPtgLWPnZGIvqfx0VhERERGRkxWwABYcHEy3bt2YP3++X/v8+fPp06dPpe/p3bt3hf7z5s2je/fuBAUF+bV/8MEHOBwObrjhhuPW4nA42LhxI8nJySf4KaRGRaXAqC9g5OfQ9CxwFcGPU+HFzrDo76dkp8QmMaHMvrUX915wJhazic8yd3PRi0tYvf1gjc8lIiIiIhLQUxDHjRvHv/71L9566y02btzIPffcQ1ZWFmPGjAG8p/2NHDnS13/MmDFs376dcePGsXHjRt566y3efPNN7rvvvgpjv/nmmwwdOrTCyhjAfffdx+LFi9m6dSsrVqzgqquuwm63M2rUqFP3YaXqWpwLo+fDdR9AUkdw2GHRZHixE/zwD3DW7PVaFrOJu85vxQe39aZpbCg7DxZzzWvLeOnbzbg9OiVRRERERGpOQAPYsGHDmDp1Kk888QQZGRl8//33zJ07l/T0dACys7P97gnWvHlz5s6dy6JFi8jIyODJJ5/kpZde4sorr/Qbd9OmTfzwww+MHj260nl37tzJ8OHDad26NVdccQXBwcEsX77cN6/UASYTnDkIbv0erp4J8WdC8UFYMBFezIDlr0Kpo0an7JYey9y7+3FZRgpuj8EL8zcx/PXl7MotrtF5RERERKThCuh9wE5nug9YLfO4Yd3/eVfCDm7ztkU1hXP/BhnXgyXomG8/UZ+s2cnDn6yn0Okm0mZl8hUdubhTSo3OISIiIiL1w4lkAwWwalIACxC3C9a8A98/C/Zd3rbY5tB/PHS8CsyWGptq+/5C7n4/k8wduQBc070pj13SnvAQa43NISIiIiKnPwWwWqAAFmCuElg9A5Y8D4V7vW0JbeC8h6DNJWCumbNrXW4PLy7YzCuLfscwoHl8OC9em0GnpjE1Mr6IiIiInP4UwGqBAlgd4SyEFa/Bjy9CSa63LakT/OlhaDXQey1ZDVi+ZT/3zMkkO68Eq9nEfYNac2u/FpjNNTO+iIiIiJy+FMBqgQJYHVOSB8umwbJXwJnvbWvawxvEWpxbI1PkFjkZ//E6vlrvvRdd3zPieOGaDBKjbDUyvoiIiIicnhTAaoECWB1VuB+WvggrXofSst0Lm58Df3oEUnuc9PCGYTBn1Q4e/2IDxS43sWFBTLmqMxe0q/zm4SIiIiJS/ymA1QIFsDouPweWvOC9Tszt9La1GuhdEUvufNLD/76ngLvfX8Ovu703h76hVxoTLmpHaHDNbQIiIiIiIqcHBbBaoAB2msjdAd9PgTXvguH2trW9FM6bAI3bnNTQjlI3z33zG28s2QpAq8YRvDS8C22T9fsgIiIi0pAogNUCBbDTzP7/waK/e+8lhgGYoNM1cO4DENfypIb+ftNe7v2/tezNdxBsNTN+cBtu7NMMUw1tACIiIiIidZsCWC1QADtN7dkIC5+GjV94n5ss0OUGOOdvEJNa7WH3Fzi4/8Nf+Pa/ewA4r3UCz17dmfiIkJqoWkRERETqMAWwWqAAdprbvQa+exp+n+99bgmGbjdBv3shsnobahiGwb+Xb+epLzfiLPUQabNydbdURvZOp1l8eA0WLyIiIiJ1iQJYLVAAqyeylsN3T8G2Jd7n1lDoeSv0HQthjao15H9z7Ix9P5P/5uT72vq3TmBUn2ac2ypB9w4TERERqWcUwGqBAlg9YhiwdTF8+yTs+snbFhwJve+A3reDLfqEh/R4DBZv3suspdtY+NteX3t6XBgjeqVzdfdUokODauoTiIiIiEgAKYDVAgWwesgwYNM33hWxP9Z520Jjoe/d0ONWCK7eaYTb9hXy7+Xb+eCnHeSXlHqHDbJwedcmjOrdjNZJkTX1CUREREQkABTAaoECWD3m8cDGz2DhJNi3ydsW3th7fVi3GyHIVq1hi5ylfLpmN28v3cZvfxw6PbFXi0aM6t2MC9olYrWYa+ADiIiIiEhtUgCrBQpgDYDH7d22ftFkOLjN2xbVxLtjYpcbwFK9UwgNw2DF1gO8vXQb8zb8gdvj/SOYHG3jhl7pDDsrVbsnioiIiJxGFMBqgQJYA+J2wZp34Ptnwb7L2xbbDPqPh45Xg9lS7aF35xbz7ortzF65gwOFTgCCLWYu7pzMqN7N6Jwac/L1i4iIiMgppQBWCxTAGiBXCayeAUueh8KyjTXiW8N5D0HbS8Fc/dMHS1xu5q7L5u2l21i7M8/XnpEaw6g+6VzUMZkQa/WDnoiIiIicOgpgtUABrAFzFsKK1+DHF6Ek19uW1An+9DC0Ggimk9tmPnNHLm8v3caXv2TjdHsAiI8IZniPNK7rmUZydOhJfgARERERqUkKYLVAAUwoyYNl02DZK+As21SjaQ9vEGtx7kkPvzffwZxVWbyzPIscewkAFrOJC9snMbJ3Oj2aN8J0kmFPRERERE6eAlgtUAATn8L98ONUWPkGlBZ725r1827W0ezsk7pGDMDl9jB/wx+8vXQbK7Ye8LW3SYpkVJ9mXJaRQliw9aTmEBEREZHqUwCrBQpgUkF+jvf6sJ9mgMflbYtI9F4f1u4ySO9z0mFsY7adWcu288manZS4vKcnRtmsXNM9lZG9m5EWF3ayn0JERERETpACWC1QAJOjys2CJS/A+o/BcWhDDcIToO0lZWHsbLBUf9Uqr8jF/63ewaxl28k6UAR4Lz07r3VjRvVpRr8z4jGbdXqiiIiISG1QAKsFCmByXKVO2LoYfv0U/vufQxt2AITFQZuLvWGs+TnVvqeYx2OwaNMe3l66ncWb9vram8eHM6JXOld1b0qUrXpji4iIiEjVKIDVAgUwOSFulzeMbfgMNv4Hig9dy0VoLLQZAu2GQvNzwRpcrSm27itk1rJtfPjTTvIdpQCEBVu4omsTRvVuRqvEyBr4ICIiIiJyJAWwWqAAJtXmLoXtP3hXxjZ+AUX7Dr1mi4bWQ7wrYy3PA2vICQ9f6CjlkzW7eHvpNjbvKfC192kZx8jezRjQtjFWS/XvWSYiIiIi/hTAaoECmNQIjxu2L4UNn3rDWMEfh14LiYLWg8vC2PkQZDuhoQ3DYNmW/by9dBvzN/yBp+xPepOYUK7vlca1Z6XRKLx6q20iIiIicogCWC1QAJMa53HDjhVlK2OfQ372odeCI+DMC71h7IwBEHxiux3uyi3m3eXbeX/VDg4UOr1DWs1c2jmFUb2b0bFpdA1+EBEREZGGRQGsFiiAySnl8cDOVd6VsQ2fgX3XodeCwuHMgd4w1mogBIdXedgSl5v//JLN20u3sW7XoR0au6bFMKpPMwZ3SCbYqtMTRURERE6EAlgtUACTWuPxwO6f4ddPYMPnkJd16DVrKLS6wBvGzhwEIVXbaMMwDNbsyGXW0m18uS4bl9v7n4H4iBCu65nG9T3TSIw6sVMeRURERBoqBbBaoAAmAWEYsHvNoZWxg9sOvWYJ8Z6e2H6oN4zZqnZa4Z78Et5fuYN3V2znD7sDAKvZxIUdkhjVpxnd02MxmXRPMREREZGjUQCrBQpgEnCGATm/eK8Z2/ApHNhy6DVLMLT8k3dr+9aDITTmuMO53B6++TWHWUu3s3LboW3y2yRFMqh9Ev1bJ9CpaQwW3eBZRERExI8CWC1QAJM6xTDgj1+9QezXT2H/5kOvmYOgRX/vyljriyCs0XGH27Dbzqxl2/g0cxclLo+vvVF4MP1axXNe68acc2aCdlEUERERQQGsViiASZ1lGLD3v2UrY5/B3o2HXjNbofk53pWxNhdDeNwxh8otcvLNrzks+m0vP2ze57vBM4DJBJ2axtD/zAStjomIiEiDdiLZIODbnU2bNo3mzZtjs9no1q0bS5YsOWb/xYsX061bN2w2Gy1atODVV1/1e33mzJmYTKYKR0lJyUnNK3LaMJmgcVs4bzzcsRzuWAnnTYDEDuAphf99B1/8FZ5rBW9fCj+9BQV7Kx0qJiyYYWelMf2Gbvz86AXMubUXf+nfkrbJURgGrN2Ry4vfbubyaUvp/tR87n5/DZ+s2cn+Akctf2gRERGR00NAV8DmzJnDiBEjmDZtGn379uW1117jX//6Fxs2bCAtLa1C/61bt9KhQwduueUWbrvtNn788Uduv/12Zs+ezZVXXgl4A9jdd9/Nb7/95vfepKSkas9bGa2AyWlp3++HNvDI+eVQu8kM6X29uym2vQQik446RLk/7CUs/m0vizbtYcnmfeSXHLE61iSac1s3pn/rBDprdUxERETqsdPmFMSePXvStWtXpk+f7mtr27YtQ4cOZfLkyRX6P/DAA3z++eds3HjolKoxY8awdu1ali1bBngD2NixY8nNza2xeSujACanvQNbvEFsw2fenRV9TJDW23vNWNtLICrluEO53B7WZOWy6Lc9LPptLxuy7X6vx4YF0a+V91TFc85MID4ipGY/i4iIiEgAnUg2sNZSTRU4nU5Wr17Ngw8+6Nc+cOBAli5dWul7li1bxsCBA/3aBg0axJtvvonL5SIoKAiAgoIC0tPTcbvdZGRk8OSTT9KlS5dqzwvgcDhwOA6dVmW324/aV+S00KgFnH2P9zi4/VAY2/UTZC31Hl/dD03PgmZnQ2pP71HJJh5BFjM9mjeiR/NG3H9hG/bYS1i0aS+Lf9vL95v3crDIxedrd/P52t2YTNCxSTT9z0zg3NaNyUjV6piIiIg0HAELYPv27cPtdpOYmOjXnpiYSE5OTqXvycnJqbR/aWkp+/btIzk5mTZt2jBz5kw6duyI3W7nxRdfpG/fvqxdu5ZWrVpVa16AyZMn8/jjj1fz04rUcbHp0Pev3iN3B2z83BvGdqyAnau8R7m4VpBWFsZSe0F8K+85h4dpHGXjmu6pXNM9lVK3hzU7cln430OrY7/szOOXnXm89N3vxJSvjp2ZwLmttTomIiIi9VvAAli5I2/wahjGMW/6Wln/w9t79epFr169fK/37duXrl278s9//pOXXnqp2vOOHz+ecePG+Z7b7XZSU1OP2l/ktBWTCr3v8B723fD7Am8Qy1rh3d6+/Fjzjrd/aGxZGOvhDWQpXSA4zDec1WLmrGaNOKtZ5atjuUUuvli7my/W7gbKVsdae09XzEiN1eqYiIiI1CsBC2Dx8fFYLJYKq0579uypsDpVLikpqdL+VquVuLjKt9M2m82cddZZbN68udrzAoSEhBASon+ZlwYmKgW6jvQeAIX7YedKbyDbsRJ2rYbig7Dpa+8B3q3ukzv7h7KoZN+Qla2OlV879utuO+t25bFuVx7//O53okOD6Ncqnv6tG3PumQkkROrPoIiIiJzeAhbAgoOD6datG/Pnz+fyyy/3tc+fP5/LLrus0vf07t2bL774wq9t3rx5dO/e3Xf915EMwyAzM5OOHTtWe14RKRMeB60Hew+AUifkrIMdyw+tkhXkeIPZrtWwfJq3X3TaYact9oTE9mC2+K2O/W2Qd3Vs8aa9LNq0lyWb9pJX7OI/v2Tzn1+yAa2OiYiIyOmvTmxD/+qrr9K7d29ef/113njjDX799VfS09MZP348u3btYtasWcChbehvu+02brnlFpYtW8aYMWP8tqF//PHH6dWrF61atcJut/PSSy/x73//mx9//JEePXpUad6q0C6IIpUwDMjNKlshKzv++BUMj3+/4Aho2v3QKlnTs8AW7del1O0hc0cui8q2ul+/y3/jG62OiYiISF1xWuyCCDBs2DD279/PE088QXZ2Nh06dGDu3Lm+EJSdnU1WVpavf/PmzZk7dy733HMPr7zyCikpKbz00ku+8AWQm5vLrbfeSk5ODtHR0XTp0oXvv//eF76qMq+IVJPJ5N3QIzYdOl3jbSuxe1fDfKFsFTjzYcsi7+F9IzRu57dKZo1tRvdmjejerBH3DWrNnvwSvt+0j0W/ee87duTqWIcmUfQ/s3HZ6lgMVkvA7zMvIiIiUkFAV8BOZ1oBE6kmjxv2bPRfJTu4rWK/8Mb+uy0mdwKrd5Wr1O1h7c5cFv638tWxKJuVfmce2lmxcaStFj6YiIiINFSnzY2YT2cKYCI1KD/Hu6lHeSDbnQkel38fS4h3h8XDryULjweodHXscO1ToujfOoGzmjWiY5No4rTVvYiIiNQgBbBaoAAmcgq5SmD3Gv9VsqL9Ffs1aglpvQ7tthh/JqUGrN1Zdu3Yb3tZtyuvwtuaxITSqWk0HZtG07GJ94gJC66FDyYiIiL1kQJYLVAAE6lFhgEHtkDW8kOBbO9/K/azxZSFsR7eFbIm3djrsPL9pr0s2byXX3bmsWVfYaVTpDUKo2PTaDqVBbL2TaKJDq18d1URERGRwymA1QIFMJEAKz4IO386FMp2rQZXkX8fkwWSOh5aJUvqjD2sCeuzC1m/K49fdnrvObZ9f1GlUzSPD6djk2jvallZKIsICfj960VERKSOUQCrBQpgInWM2wV/rPfei6x8lcy+q2I/SwjEt4KE1pDQFhJaY49syS9FcazLLmTdrlx+2ZnHzoPFFd5qMkGL+HA6NY3xBbN2KVGEBSuUiYiINGQKYLVAAUzkNJC389ANoneuhL2/VVwlK2cJhrgzIKENJLQhP+oM/utO4Sd7DJm7C1m3M4/deSUV3mY2wRmNI+jYJMZ3XVm75ChsQZZT/OFERESkrlAAqwUKYCKnIY8H8rK8QWzPRu/XvRth7yZwVX5tGOYgbzBr3IbCqDPYakolsySJJQeiydxdwB92R4W3WMwmWjWOKAtkMXRqEk2b5EhCrAplIiIi9ZECWC1QABOpRzweyNtxWCD7zbvJx97fwFlQ+XvMVog7g5KYVuwOSmeDO4Xl+Y1Z8Ec4OYUV/7MaZDHROimybNdF72rZmYmRBFt1w2gREZHTnQJYLVAAE2kAPB7vdWR7/+s99vz3sGCWX+lbDLOV0pjm7A9twVaa8nNJEosOxLK2OAEn/rsqBlvMtE2OpINvo48YWiVGEGRRKBMRETmdKIDVAgUwkQbMMLzBzBfIylbN9vz36MHMZKEwPI1dwelsdKWwLL8xax1JbDGS/YJZiNVMu5QoOjWJLgtmMZzROAKL2VRbn05EREROkAJYLVAAE5EKDAPsuw8LZIedzuiwV/4WzBywNeV/pJJZnMh6VzKbjaZsMZJx4L05dGiQhfYpUb4bR7dJiiI9LoxwbYkvIiJSJyiA1QIFMBGpMsOA/OwjTmMse+zIq/QtHszkWJLZWJrMRncTNnuasNloyv+MFF8wi48IJq1RmPeICye9URhpcWGkNwojITIEk0mrZiIiIrVBAawWKICJyEkzDMjPORTIfAFtI5QcLZiZ+IM4dnkakWM0Its48msce4ghOMgbzlIbhZEe5z1SG3nDWdPYMG3+ISIiUoMUwGqBApiInDKGAQV/VLJithFKco/7drdhYi8xlQS0OLKNRvxBI8xRKSTHRZMe5101S2sURnqjcNLiwogODTruHCIiInKIAlgtUAATkVpnGFCwB3KzvJuA2Hcf9rXsyN8NntIqDbfXiCLnsGBWHtQKQhKwxDQlNC6VlIRGZac5hpMeF0ZSlA2zNgQRERHxowBWCxTARKRO8nigcO8RwezQY8O+C/KzMZWWVGm4XCPcL5ztNcXjCE/CHJVCaFwakYnppDRu7DvF0Rakm02LiEjDowBWCxTAROS0ZRhQfLDSVTR37k5Kc3dhyd+N1V1UpeHyjVBfQMsLSsARmoQRlUJwo6ZENU4nLqU5TZKSaRShjUFERKR+UgCrBQpgIlKvGYZ36/zDApo7dxfF+3fgPLgTU/5ubEV/EOqufHv9IxUbwfxBHHlBCZSENsYdkYI1pgm2mGTC41KISWhCTOOmWGyRoJAmIiKnmRPJBrqJjIiIVGQygS3aezRuC4AFiDiyn7MQ7NkY9p0U7t2Bfc92HAd2YOTtIrgoh0jnHqI9eYSanDQjG0qzIR/vkV1x2hKCyTXHUhjUCEdIPO6wBEyRiQRFJxIWm0JUfAqR8U0xRzaG4PBT+z0QERE5BRTARESk+oLDIf4MTPFnENGikoAG4CrBcXAXe3dvITdnO0X7duDJ20VQYTahzgNElh4g1sglwlSCDSdJnj/A8Qc4ADuQU/nUxaZQ8i2xFIfEUxoaD+EJWKOTsMUkExGXQlijZEwRiRDRGIJCT933QERE5AQogImIyKkVZCOkcUuaNm5J06N0cXsM9hw8wIE/dpG/bzdFB3fjyvsDCv7AXLQXm2Mf4a4DxHoOkmDyrqiFGsWElhZD6W4oBPYdvYRiczhFQY1w2uLxhCdgjkwkOCaJ8EZNsMUkeUNaeGPvV2vIqfguiIiIAApgIiJSB1jMJhrHxdE4Lg7odNR+zlIP+/JL2HRgP3l7d1N0YBeO3Bzc9j8wFe0lpHgfoa79xHoOEm/KI4E8QkwuQj2FhDoKwbEDKr/HtU+xJRJHSDylYfGYIrynP4bGphAUlQgRiRCR4P0angAW3TNNREROjAKYiIicNoKtZlJiw0iJDYOWqUftV+Jyszffwbq8YvYf2E/+vl2U5GbjtudgFOwlqHgPNscBYsqDmimXePIINrkJdecTWpQPRVuPuaoGUBIUTaktHsMWjcUWiTU0kqDQKEwhkRASAcEREBJZ9rWy5+EQHAkW/e9YRKSh0H/xRUSk3rEFWUht5L03Gc3jgDMr7VfoKGVPvoMsewmr8orJO7CXwgPZuOw5ePL/wFq0h+CS/cR4cr0hzZRHgimPOOwEmdzYXHngyvNuKnIyrLbDQtnh4a0qIe6I50HhYDafZEEiInKqKICJiEiDFR5ipXmIlebx5TsqNgW6+PUxDIN8Ryl77CX8YXew2V7CH3nF5B/cgyM3G7f9D9wldjwl+ZhdhURQQripmHBKiKCYcJP3a5jJQTjFfq+HmEq9k5SWeI+i4yy5VVVwRMVVtqqEupAoCI2B0FiwxUCQrWbqERERHwUwERGRYzCZTETZgoiyBXFG48jDXmlVoa/L7eFgkZMDhU4OFDg5UORkX6GT3wqcHCxysr+svfxxQWERIZ4iIkwlhFMW2kz+X/0em7wBLsJUQrTFQaSphHBTCWFGMSGeYiy4vYU4C7xHwUl+eKvNG8RCY73BrMLjmENh7cjXdX2ciEilFMBERERqSJDFTONIG40jq7ZyZBgG9pJSb2ArdHCg0OX3dX+hk+2F3kC3v9DJwUInhU730UYjBJffqtvhoS0+2EVCsJO4ICexVifRZgeRZm+4CzWKsRnFhJQWYHXmYXbkYTI83lW5ghzvccLfjPCKAe3w4OYX5mIP6xsNZsuJzycicppQABMREQkQk8lEdGgQ0aFBh50GeWwlLndZYKt4lIc072MHOUUuDhY5MQygpOyoSl14iKCE5JASUkIcJAcX0ziohARrEY3MRcSYC4mmkAijgDB3PrZSO8GldqxOOxZH2TaTrkLvYd914t+YkKhKQlsVVt5ConT9m4jUeQpgIiIipxFbkIWUmFBSYqp2c2m3xyC3qOy0x4KysFbkPRVyf6HTd8rk/gInecUu8opdFDhKySeMfEcYmxwnVp8ZD5EUkWI7FN4Sg4qJtxQTaykixlRIlFHgDW+eAm94c9mxOvIwu8rOmXTYvUde1olNbjIfuo4tJKosyJV9DYksexx5/Ne0Aicip5ACmIiISD1mMZuIiwghLiKEMxpX7T0utwd7WRircBT5P88tdvn1LXJCHhHklUSwsYorbuWslBJtKqJJiIPksvCWEFRMvKWIWHMRsaZCIinwrbyFlIU3iyMPc2kxGB4oyfUeJ+PwTUl84az8cfRRXovyD3FBoWAynVwdIlIvKYCJiIiInyCL2RfaTpSz1OMX0A4PZ7lHhDd7sYvc4kMrbyUuK/uNKPaXwC8nGN6CcRFjKqSJzRveGgc7iLM6aGR1EGspJtpUTISpmAijiDCjCJun0HvNW2kBVlc+JmcBptKyScs3McnPPuHP72O2Vm21zRfqjrJKp3vEidQ7+lMtIiIiNSbYaiYhMoSEyBMPb45Sd6WrbIcHuCNX5nLLvjpLg9hjxLCnGNYUV6/2yCA3KTYXiSEuEoOdxAc5iLOW0MhSQrSlxBviKCaMQkI9hdjcRQSX5mN1FWB25WMqyfeeOokBnlIoPug9ToYlxLuaFhzu/RoU5j2Cww49ruz1qr7HEqyVOpFapgAmIiIidUKI1ULjSEuVd5E8XInL7RfU8ksOX4ErxX7Yc+/jUu/jYhf5Du/92PJdFn5zWfgt/8TnN5kgMsRKlM1KUmgpicFOGgc7iQsqoZHFQaylhGhzMVGmYsLxrsKFugsJdhcQVFqI2WnH5MiHkrLr38pX49wO73Gyp1UetXCzd8fKoNAaCHXlz0MPjRkUpo1RRI4Q8AA2bdo0nn32WbKzs2nfvj1Tp06lX79+R+2/ePFixo0bx6+//kpKSgr3338/Y8aM8b3+xhtvMGvWLNavXw9At27dmDRpEj169PD1mThxIo8//rjfuImJieTkVGObXREREQk4W5AFW5CFxKgTD09uj0FBSak3oJX4nzppL3FhL674mr28f7ELR6kHwwB7SSn2klJ25gKYAVvZcXzBFjNRoUFEhVqJig2ikQ0aBzuJCSol2uIiyuoiyuwkwuIi3OQg3OwkFAehOAkxigkxHAR7SrB6SjC5isBVDM5C71dXcdmulMXgLAJXEXhc3okNDzjzvUfhCX/rqsZqKwtn5TcGDyv7GlHWXvb4qO3l7yl7XP6aNkuR01RAA9icOXMYO3Ys06ZNo2/fvrz22msMHjyYDRs2kJaWVqH/1q1bueiii7jlllt45513+PHHH7n99ttJSEjgyiuvBGDRokUMHz6cPn36YLPZmDJlCgMHDuTXX3+lSZMmvrHat2/PggULfM8tFv0hFhERaYgsZhPRYUFEh1Xv5tElLneFoGavJKj5h7hSXz+PAU63h30FDvYVHG3bSStV+WubyQThwVbCQyxlX72PI8LKH1uJCLESYTWIDnIRbXERaXERaXYQbnYRZnIQZnJiM0qw4STYU4zJF+LKwlt5iKsQ9A57vfSw80BLS7xH8YFqfX+Pyhp6gmHueEEvzLtypxU7OcVMhmEYgZq8Z8+edO3alenTp/va2rZty9ChQ5k8eXKF/g888ACff/45Gzdu9LWNGTOGtWvXsmzZskrncLvdxMbG8vLLLzNy5EjAuwL26aefkpmZWe3a7XY70dHR5OXlERUVVe1xREREpOHyeAwKnaV+oezwwFbocFPoLKXAUUqho9T73FFasc1Zyqn4G53ZF+jKQl2I1fc8oux5RFmwCwu2+B5HBJuJtJQSYXESYXYShoMwk4MQTxGm8gDnLPCGN+dhj4/WfvhrhqfmP+jhfKdTHiWwBdm8q3pWm/c0S9/XEG8oDLL5f7WGHNGv7KvZquvv6pETyQYBWwFzOp2sXr2aBx980K994MCBLF26tNL3LFu2jIEDB/q1DRo0iDfffBOXy0VQUMV/uSoqKsLlctGoUSO/9s2bN5OSkkJISAg9e/Zk0qRJtGjR4qj1OhwOHI5D/yplt9uP+xlFREREjsVsNhFpCyLSFgSx1R/HMAyKXe6yUOYNab6A5iwLbYe1FZT1KfIFuYrvAfAYkO8o9V0nd9KftyzQhYXEEB4S731cFtzCykJdWJiV8Fgr4cGWQ23B3qAXFmQmwlpKhNlJOCWEUkKQu6QaYa7w0OPy1yhLsOUreUX7auQzH5XJXElgOzLYHSPEHf76Mcc4LBxaghT66oCABbB9+/bhdrtJTEz0az/WtVg5OTmV9i8tLWXfvn0kJydXeM+DDz5IkyZNGDBggK+tZ8+ezJo1izPPPJM//viDp556ij59+vDrr78SFxdX6dyTJ0+ucN2YiIiISF1gMpkIC7YSFmyFyJMfz+PxBrpDocx9WDirLLAdCnWH9yl/vajSQHeCd/k+imCLmfAQC2HBoYSHRBAeklLhNMwwm4XwqLKVvGCLb0XPL9hZXISZnYR5ijGXFh0lzJWdXukqO63SVQyljsPaDvta6ih7veTQ1/LNVcC7kucqC4O15fDQV37TclvMEV+jK2mLOXSDc117d9ICvgmH6YgUbhhGhbbj9a+sHWDKlCnMnj2bRYsWYbMdugh28ODBvscdO3akd+/etGzZkrfffptx48ZVOu/48eP9XrPb7aSmph7jk4mIiIicnsxmk++asSrev/uYPB6DIpeboiNW5A4Pc4VO7+sFzlKKDjvVssjpDXJFZYGuqOw9Trf3VESn24OzyMPBIlcNVOoVFlweziyEBUcTERJHWFmgCw22EBpk8X4NsRAaaSEs2LsJTNjhrwV5xwgNsmALNnsfW81YPM5KAluJf1A7PLBV2q/kxMYod3joK9oPJ3yXBFNZcKsspFXWFuv/mu5rBwQwgMXHx2OxWCqsdu3Zs6fCKle5pKSkSvtbrdYKK1fPPfcckyZNYsGCBXTq1OmYtYSHh9OxY0c2b9581D4hISGEhJz4PU1EREREGjqz2eTd/COk5v7q6Sz1UOx0lwW20rJw5q402BUeFtz8Xj8i7HnKzkIscropcrrZV1Bj5foEW81l4cw/rHm/RhMa3KiSQGclNOKIoFch7HlfC7Ga/RcmDKOSVbpi7y0PSnKhONf7tSTv0GO/r3nex64iwABHnvcgqxofPuLEVtwOf81af/4eHrAAFhwcTLdu3Zg/fz6XX365r33+/Plcdtlllb6nd+/efPHFF35t8+bNo3v37n7Xfz377LM89dRTfPPNN3Tv3v24tTgcDjZu3HjM7e9FREREpO4ItpoJtpqrvXvlkQzDoMTlKQtn3oBWfo3coVW4UopdHopdboqdpRS7vEGtpOxrsdNd9tqh9uKyo3yTFGepB2eph7zimluxO5zZxKHQFmwmLMiKLdhCaJDZtyIXGmzBFhSBzRqNLagFtiCz91YOsZayWzqYsVkPexxkwWYuJcxdQKg7n5DSfEJceVic+ZUEttyKYc6ZX/bhC7yHfeeJfzBr6KFwZov2D2qDJp1Wp0YGdB1w3LhxjBgxgu7du9O7d29ef/11srKyfPf1Gj9+PLt27WLWrFmAd8fDl19+mXHjxnHLLbewbNky3nzzTWbPnu0bc8qUKTzyyCO89957NGvWzLdiFhERQUREBAD33Xcfl1xyCWlpaezZs4ennnoKu93OqFGjavk7ICIiIiJ1gclk8q4mBVuIj6jZ1RbDMHCUerwhrTy8OT0UlYU4X4ArC2/FTjdFhz0+POj5h75S3+sutzfheQy8q35l192dSlZzOLagKGxBzXz34vMLb2FmQoIshFkMYi1FRFNEtKmISKOASAoI8xQQ7sknzJ1PiLsAW2k+wS47Qa48rE47FkceJocdE4Z35S6/GPKz/YuwhMDgZ075Z61JAQ1gw4YNY//+/TzxxBNkZ2fToUMH5s6dS3p6OgDZ2dlkZR1a3mzevDlz587lnnvu4ZVXXiElJYWXXnrJdw8w8N7Y2el0ctVVV/nN9dhjjzFx4kQAdu7cyfDhw9m3bx8JCQn06tWL5cuX++YVEREREakpJpPJF1BOFZfbuzJXclhgOzLQlTjLQpvLQ0lZ8PMeHkpKD3t8jHZH6aHbAJR6DAocpRz19nWVCgYalR3HZ8JDJMVEmQqJMxcRby0m3lJErLmIWEsRoWaDEcfZQ6KuCeh9wE5nug+YiIiIiDQ0Ho+B0+29/s4bzioGNkfZSt2h18q+lrpxuA5/7+GveXC4Dq3yVRb4KhMaZGHjkxfW0qc/utPiPmAiIiIiInJ6MZtN2MyndjXvcOWB7/CwVnxY4HN7Tr+1JAUwERERERGpk2o78NUGc6ALEBERERERaSgUwERERERERGqJApiIiIiIiEgtUQATERERERGpJQpgIiIiIiIitUQBTEREREREpJYogImIiIiIiNQSBTAREREREZFaogAmIiIiIiJSSxTAREREREREaokCmIiIiIiISC1RABMREREREaklCmAiIiIiIiK1RAFMRERERESkllgDXcDpyjAMAOx2e4ArERERERGRQCrPBOUZ4VgUwKopPz8fgNTU1ABXIiIiIiIidUF+fj7R0dHH7GMyqhLTpAKPx8Pu3buJjIzEZDIFupx6w263k5qayo4dO4iKigp0OQ2efh51j34mdY9+JnWLfh51j34mdY9+JjXPMAzy8/NJSUnBbD72VV5aAasms9lM06ZNA11GvRUVFaX/INQh+nnUPfqZ1D36mdQt+nnUPfqZ1D36mdSs4618ldMmHCIiIiIiIrVEAUxERERERKSWKIBJnRISEsJjjz1GSEhIoEsR9POoi/QzqXv0M6lb9POoe/QzqXv0MwksbcIhIiIiIiJSS7QCJiIiIiIiUksUwERERERERGqJApiIiIiIiEgtUQATERERERGpJQpgEnCTJ0/mrLPOIjIyksaNGzN06FB+++23QJclh5k8eTImk4mxY8cGupQGbdeuXdxwww3ExcURFhZGRkYGq1evDnRZDVJpaSkPP/wwzZs3JzQ0lBYtWvDEE0/g8XgCXVqD8f3333PJJZeQkpKCyWTi008/9XvdMAwmTpxISkoKoaGh9O/fn19//TUwxTYQx/qZuFwuHnjgATp27Eh4eDgpKSmMHDmS3bt3B67geu54f0YOd9ttt2EymZg6dWqt1deQKYBJwC1evJg77riD5cuXM3/+fEpLSxk4cCCFhYWBLk2AVatW8frrr9OpU6dAl9KgHTx4kL59+xIUFMRXX33Fhg0beP7554mJiQl0aQ3SM888w6uvvsrLL7/Mxo0bmTJlCs8++yz//Oc/A11ag1FYWEjnzp15+eWXK319ypQpvPDCC7z88susWrWKpKQkLrjgAvLz82u50objWD+ToqIifv75Zx555BF+/vlnPv74YzZt2sSll14agEobhuP9GSn36aefsmLFClJSUmqpMtE29FLn7N27l8aNG7N48WLOOeecQJfToBUUFNC1a1emTZvGU089RUZGhv51LEAefPBBfvzxR5YsWRLoUgS4+OKLSUxM5M033/S1XXnllYSFhfHvf/87gJU1TCaTiU8++YShQ4cC3tWvlJQUxo4dywMPPACAw+EgMTGRZ555httuuy2A1TYMR/5MKrNq1Sp69OjB9u3bSUtLq73iGqCj/Tx27dpFz549+eabbxgyZAhjx47V2S61QCtgUufk5eUB0KhRowBXInfccQdDhgxhwIABgS6lwfv888/p3r07V199NY0bN6ZLly688cYbgS6rwTr77LP59ttv2bRpEwBr167lhx9+4KKLLgpwZQKwdetWcnJyGDhwoK8tJCSEc889l6VLlwawMjlcXl4eJpNJK/kB4vF4GDFiBH/7299o3759oMtpUKyBLkDkcIZhMG7cOM4++2w6dOgQ6HIatPfff5/Vq1fz008/BboUAbZs2cL06dMZN24cDz30ECtXruSvf/0rISEhjBw5MtDlNTgPPPAAeXl5tGnTBovFgtvt5umnn2b48OGBLk2AnJwcABITE/3aExMT2b59eyBKkiOUlJTw4IMPct111xEVFRXochqkZ555BqvVyl//+tdAl9LgKIBJnXLnnXfyyy+/8MMPPwS6lAZtx44d3H333cybNw+bzRbocgTvv1R2796dSZMmAdClSxd+/fVXpk+frgAWAHPmzOGdd97hvffeo3379mRmZjJ27FhSUlIYNWpUoMuTMiaTye+5YRgV2qT2uVwurr32WjweD9OmTQt0OQ3S6tWrefHFF/n555/1ZyIAdAqi1Bl33XUXn3/+OQsXLqRp06aBLqdBW716NXv27KFbt25YrVasViuLFy/mpZdewmq14na7A11ig5OcnEy7du382tq2bUtWVlaAKmrY/va3v/Hggw9y7bXX0rFjR0aMGME999zD5MmTA12aAElJScChlbBye/bsqbAqJrXL5XJxzTXXsHXrVubPn6/VrwBZsmQJe/bsIS0tzff/+e3bt3PvvffSrFmzQJdX72kFTALOMAzuuusuPvnkExYtWkTz5s0DXVKDd/7557Nu3Tq/tptuuok2bdrwwAMPYLFYAlRZw9W3b98Kt2fYtGkT6enpAaqoYSsqKsJs9v83TIvFom3o64jmzZuTlJTE/Pnz6dKlCwBOp5PFixfzzDPPBLi6hqs8fG3evJmFCxcSFxcX6JIarBEjRlS4vnvQoEGMGDGCm266KUBVNRwKYBJwd9xxB++99x6fffYZkZGRvn+xjI6OJjQ0NMDVNUyRkZEVrsELDw8nLi5O1+YFyD333EOfPn2YNGkS11xzDStXruT111/n9ddfD3RpDdIll1zC008/TVpaGu3bt2fNmjW88MIL/PnPfw50aQ1GQUEBv//+u+/51q1byczMpFGjRqSlpTF27FgmTZpEq1ataNWqFZMmTSIsLIzrrrsugFXXb8f6maSkpHDVVVfx888/85///Ae32+37/32jRo0IDg4OVNn11vH+jBwZgIOCgkhKSqJ169a1XWrDY4gEGFDpMWPGjECXJoc599xzjbvvvjvQZTRoX3zxhdGhQwcjJCTEaNOmjfH6668HuqQGy263G3fffbeRlpZm2Gw2o0WLFsaECRMMh8MR6NIajIULF1b6/45Ro0YZhmEYHo/HeOyxx4ykpCQjJCTEOOecc4x169YFtuh67lg/k61btx71//cLFy4MdOn10vH+jBwpPT3d+Mc//lGrNTZUug+YiIiIiIhILdEmHCIiIiIiIrVEAUxERERERKSWKICJiIiIiIjUEgUwERERERGRWqIAJiIiIiIiUksUwERERERERGqJApiIiIiIiEgtUQATERERERH5//buNCSq740D+Peq5TK2uGGKoIG2jTkSSqWmleUSZUYRhMmYL0LTEpqEdpconbCyRSVfGEFR4QvTCi3aqJSyLMvcMlsw1DaFsKBSz//FH+/Pm2laNkZ9P3DgnuWe85zri+Fh7hwNhAkYERH9FV68eAFJklBZWTnSocjq6uowa9YsmJmZwdPTc6TDGZAkSTh79uxIh0FE9NdjAkZERMMiKioKkiQhPT1d0X727FlIkjRCUY2spKQkqFQq1NfX48qVK98d0/Pcvi0hISEGjpaIiAyBCRgREQ0bMzMz6PV6tLe3j3Qow+bLly8/fW9jYyP8/Pzg7OwMGxubfseFhISgpaVFUU6dOvXT6xIR0Z+LCRgREQ2bBQsWYMKECUhLS+t3THJycp/X8TIzM+Hi4iLXo6KiEB4ejj179sDe3h7jx49HSkoKOjs7kZiYCGtrazg5OSEvL6/P/HV1dfDx8YGZmRnUajWuX7+u6K+pqcGiRYtgaWkJe3t7REZG4t27d3L/3LlzER8fj40bN8LW1hYLFy787j66u7uRmpoKJycnmJqawtPTEyUlJXK/JEmoqKhAamoqJElCcnJyv8/E1NQUEyZMUBQrKyvFXDk5OQgNDYW5uTkmTpyI/Px8xRxVVVWYP38+zM3NYWNjg7Vr16Kjo0MxJi8vD2q1GqampnBwcEB8fLyi/927d1i2bBksLCzg5uaGoqIiua+9vR0RERGws7ODubk53NzccOzYsX73RERE38cEjIiIho2xsTH27NmDw4cP49WrV78019WrV9Hc3IwbN25g//79SE5OxuLFi2FlZYU7d+4gJiYGMTExaGpqUtyXmJgInU6HBw8ewMfHB2FhYXj//j0AoKWlBQEBAfD09MS9e/dQUlKC169fY+XKlYo5jh8/DhMTE5SWluLo0aPfje/gwYPYt28fMjIy8OjRIwQHByMsLAwNDQ3yWmq1GjqdDi0tLdi0adMvPY8dO3Zg+fLlePjwIVavXo1Vq1ahtrYWAPDp0yeEhITAysoKd+/eRX5+Pi5fvqxIsHJychAXF4e1a9eiqqoKRUVFcHV1VayRkpKClStX4tGjR1i0aBEiIiLQ1tYmr19TU4Pi4mLU1tYiJycHtra2v7QnIqJ/kiAiIhoGWq1WLF26VAghxKxZs0R0dLQQQoiCggLR++MmKSlJaDQaxb0HDhwQzs7OirmcnZ1FV1eX3DZ58mQxZ84cud7Z2SlUKpU4deqUEEKI58+fCwAiPT1dHvP161fh5OQk9Hq9EEKIHTt2iKCgIMXaTU1NAoCor68XQggREBAgPD09f7hfR0dHsXv3bkWbt7e3WLdunVzXaDQiKSlpwHm0Wq0wNjYWKpVKUVJTU+UxAERMTIzivpkzZ4rY2FghhBC5ubnCyspKdHR0yP0XLlwQRkZGorW1VY5327Zt/cYBQGzfvl2ud3R0CEmSRHFxsRBCiCVLlog1a9YMuBciIvoxkxHN/oiI6K+k1+sxf/586HS6n55DrVbDyOi/FzXs7e3h7u4u142NjWFjY4M3b94o7ps9e7Z8bWJiAi8vL/mbooqKCly7dg2WlpZ91mtsbMSkSZMAAF5eXgPG9uHDBzQ3N8PX11fR7uvri4cPHw5yh/+ZN28ecnJyFG3W1taKeu999dR7Tnysra2FRqOBSqVSxNLd3Y36+npIkoTm5mYEBgYOGIeHh4d8rVKpMGbMGPn5xsbGYvny5bh//z6CgoIQHh4OHx+fIe+ViOhfxwSMiIiGnb+/P4KDg7F161ZERUUp+oyMjCCEULR9/fq1zxyjRo1S1CVJ+m5bd3f3D+PpOYWxu7sbS5YsgV6v7zPGwcFBvu6dyAxm3h5CiJ868VGlUvV5HXAo6w+0riRJMDc3H9R8Az3f0NBQvHz5EhcuXMDly5cRGBiIuLg4ZGRkDDluIqJ/GX8DRkREv0VaWhrOnTuHsrIyRbudnR1aW1sVSdhw/u+u27dvy9ednZ2oqKjAlClTAAAzZsxAdXU1XFxc4OrqqiiDTboAYOzYsXB0dMStW7cU7WVlZZg6derwbOQbvffVU+/Z17Rp01BZWYmPHz/K/aWlpTAyMsKkSZMwZswYuLi49HsU/mDZ2dkhKioKJ06cQGZmJnJzc39pPiKifxETMCIi+i08PDwQERGBw4cPK9rnzp2Lt2/fYu/evWhsbERWVhaKi4uHbd2srCwUFBSgrq4OcXFxaG9vR3R0NAAgLi4ObW1tWLVqFcrLy/Hs2TNcunQJ0dHR6OrqGtI6iYmJ0Ov1OHPmDOrr67F582ZUVlYiISFhyDF//vwZra2titL7ZEYAyM/PR15eHp48eYKkpCSUl5fLh2xERETAzMwMWq0Wjx8/xrVr17B+/XpERkbC3t4ewP9Pn9y3bx8OHTqEhoYG3L9/v8/fZiA7d+5EYWEhnj59iurqapw/f/63JZtERH8zJmBERPTb7Nq1q8/rhlOnTkV2djaysrKg0WhQXl7+yycE9paeng69Xg+NRoObN2+isLBQPq3P0dERpaWl6OrqQnBwMNzd3ZGQkIBx48Ypfm82GBs2bIBOp4NOp8P06dNRUlKCoqIiuLm5DTnmkpISODg4KIqfn59iTEpKCk6fPg0PDw8cP34cJ0+exLRp0wAAFhYWuHjxItra2uDt7Y0VK1YgMDAQR44cke/XarXIzMxEdnY21Go1Fi9eLJ/YOBijR4/Gli1b4OHhAX9/fxgbG+P06dND3isR0b9OEt9+MhIREdEfRZIkFBQUIDw8fKRDISKiX8RvwIiIiIiIiAyECRgREREREZGB8Bh6IiKiPxx/LUBE9PfgN2BEREREREQGwgSMiIiIiIjIQJiAERERERERGQgTMCIiIiIiIgNhAkZERERERGQgTMCIiIiIiIgMhAkYERERERGRgTABIyIiIiIiMpD/AV8SYNo2xjGtAAAAAElFTkSuQmCC\n",
"text/plain": [
"<Figure size 1000x500 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.figure(figsize=(10,5))\n",
"train_loss = model.history['loss']\n",
"val_loss = model.history['val_loss']\n",
"epochs = range(1,16)\n",
"plt.plot(epochs, train_loss, label = 'Training Loss')\n",
"plt.plot(epochs, val_loss, label = 'Validation Loss')\n",
"plt.title('Training and Validation Loss')\n",
"plt.xlabel('Number of Epochs')\n",
"plt.ylabel('Loss')\n",
"plt.legend();"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 458
},
"id": "RFZxAHY3WE7R",
"outputId": "47f3625e-69be-41c1-c3eb-469be6630b0d"
},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1500x700 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.figure(figsize = (15,7))\n",
"\n",
"plt.subplot(1,2,1)\n",
"train_precision = model.history['precision']\n",
"val_precision = model.history['val_precision']\n",
"epochs = range(1,16)\n",
"plt.plot(epochs, train_precision, label = 'Training Precision')\n",
"plt.plot(epochs, val_precision, label = 'Validation Precision')\n",
"plt.title('Training and Validation Precision')\n",
"plt.xlabel('Number of Epochs')\n",
"plt.ylabel('Precision')\n",
"plt.legend()\n",
"\n",
"plt.subplot(1,2,2)\n",
"train_recall = model.history['recall']\n",
"val_recall = model.history['val_recall']\n",
"epochs = range(1,16)\n",
"plt.plot(epochs, train_recall, label = 'Training Recall')\n",
"plt.plot(epochs, val_recall, label = 'Validation Recall')\n",
"plt.title('Training and Validation Recall')\n",
"plt.xlabel('Number of Epochs')\n",
"plt.ylabel('Recall')\n",
"plt.legend();"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "_dI_5X4RWRkj"
},
"outputs": [],
"source": []
}
],
"metadata": {
"colab": {
"provenance": []
},
"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": "3.9.13"
}
},
"nbformat": 4,
"nbformat_minor": 1
}