Heart Attack Predicton_EDA_Modeling.ipynb

{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":7436271,"sourceType":"datasetVersion","datasetId":4327876}],"dockerImageVersionId":30648,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":5,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n%matplotlib inline","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:31.965951Z","iopub.execute_input":"2024-02-15T23:01:31.966661Z","iopub.status.idle":"2024-02-15T23:01:31.972090Z","shell.execute_reply.started":"2024-02-15T23:01:31.966632Z","shell.execute_reply":"2024-02-15T23:01:31.971138Z"},"trusted":true},"execution_count":59,"outputs":[]},{"cell_type":"markdown","source":"*Age*: Numeric (e.g., 52)\n\n*Sex*: Categorical (0: Female, 1: Male)\n\nChest Pain Type: Categorical (0: Typical Angina, 1: Atypical Angina, 2: Non-anginal Pain, 3: Asymptomatic)\n\nResting Blood Pressure: Numeric (e.g., 125)\n\nSerum Cholesterol: Numeric in mg/dL (e.g., 212)\n\nFasting Blood Sugar: Categorical (0: <= 120 mg/dL, 1: > 120 mg/dL)\n\nResting Electrocardiographic Results: Categorical (0: Normal, 1: Abnormality, 2: Hypertrophy)\n\nMaximum Heart Rate Achieved: Numeric (e.g., 168)\n\nExercise-Induced Angina: Categorical (0: No, 1: Yes)\n\nOldpeak (ST Depression): Numeric (e.g., 1.0)\n\nSlope of Peak Exercise ST Segment: Categorical (0: Upsloping, 1: Flat, 2: Downsloping)\n\nNumber of Major Vessels Colored by Fluoroscopy: Numeric (0 to 3)\n\nThalassemia: Categorical (0: Normal, 1: Fixed Defect, 2: Reversible Defect)","metadata":{}},{"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/heart-attack-prediction/heart.csv')","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:31.973655Z","iopub.execute_input":"2024-02-15T23:01:31.973974Z","iopub.status.idle":"2024-02-15T23:01:31.987978Z","shell.execute_reply.started":"2024-02-15T23:01:31.973951Z","shell.execute_reply":"2024-02-15T23:01:31.987184Z"},"trusted":true},"execution_count":60,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:31.991803Z","iopub.execute_input":"2024-02-15T23:01:31.992610Z","iopub.status.idle":"2024-02-15T23:01:32.006463Z","shell.execute_reply.started":"2024-02-15T23:01:31.992586Z","shell.execute_reply":"2024-02-15T23:01:32.005598Z"},"trusted":true},"execution_count":61,"outputs":[{"execution_count":61,"output_type":"execute_result","data":{"text/plain":"   age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  \\\n0   52    1   0       125   212    0        1      168      0      1.0      2   \n1   53    1   0       140   203    1        0      155      1      3.1      0   \n2   70    1   0       145   174    0        1      125      1      2.6      0   \n3   61    1   0       148   203    0        1      161      0      0.0      2   \n4   62    0   0       138   294    1        1      106      0      1.9      1   \n\n   ca  thal  target  \n0   2     3    0.23  \n1   0     3    0.37  \n2   0     3    0.24  \n3   1     3    0.28  \n4   3     2    0.21  ","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>age</th>\n      <th>sex</th>\n      <th>cp</th>\n      <th>trestbps</th>\n      <th>chol</th>\n      <th>fbs</th>\n      <th>restecg</th>\n      <th>thalach</th>\n      <th>exang</th>\n      <th>oldpeak</th>\n      <th>slope</th>\n      <th>ca</th>\n      <th>thal</th>\n      <th>target</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>52</td>\n      <td>1</td>\n      <td>0</td>\n      <td>125</td>\n      <td>212</td>\n      <td>0</td>\n      <td>1</td>\n      <td>168</td>\n      <td>0</td>\n      <td>1.0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>3</td>\n      <td>0.23</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>53</td>\n      <td>1</td>\n      <td>0</td>\n      <td>140</td>\n      <td>203</td>\n      <td>1</td>\n      <td>0</td>\n      <td>155</td>\n      <td>1</td>\n      <td>3.1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>3</td>\n      <td>0.37</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>70</td>\n      <td>1</td>\n      <td>0</td>\n      <td>145</td>\n      <td>174</td>\n      <td>0</td>\n      <td>1</td>\n      <td>125</td>\n      <td>1</td>\n      <td>2.6</td>\n      <td>0</td>\n      <td>0</td>\n      <td>3</td>\n      <td>0.24</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>61</td>\n      <td>1</td>\n      <td>0</td>\n      <td>148</td>\n      <td>203</td>\n      <td>0</td>\n      <td>1</td>\n      <td>161</td>\n      <td>0</td>\n      <td>0.0</td>\n      <td>2</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0.28</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>62</td>\n      <td>0</td>\n      <td>0</td>\n      <td>138</td>\n      <td>294</td>\n      <td>1</td>\n      <td>1</td>\n      <td>106</td>\n      <td>0</td>\n      <td>1.9</td>\n      <td>1</td>\n      <td>3</td>\n      <td>2</td>\n      <td>0.21</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df['age'].hist()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.015007Z","iopub.execute_input":"2024-02-15T23:01:32.015770Z","iopub.status.idle":"2024-02-15T23:01:32.192760Z","shell.execute_reply.started":"2024-02-15T23:01:32.015745Z","shell.execute_reply":"2024-02-15T23:01:32.191817Z"},"trusted":true},"execution_count":62,"outputs":[{"execution_count":62,"output_type":"execute_result","data":{"text/plain":"<Axes: >"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"sns.histplot(df,x='age')","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.194116Z","iopub.execute_input":"2024-02-15T23:01:32.194388Z","iopub.status.idle":"2024-02-15T23:01:32.430592Z","shell.execute_reply.started":"2024-02-15T23:01:32.194365Z","shell.execute_reply":"2024-02-15T23:01:32.429683Z"},"trusted":true},"execution_count":63,"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n  with pd.option_context('mode.use_inf_as_na', True):\n","output_type":"stream"},{"execution_count":63,"output_type":"execute_result","data":{"text/plain":"<Axes: xlabel='age', ylabel='Count'>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"sns.heatmap(df.corr())","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.431780Z","iopub.execute_input":"2024-02-15T23:01:32.432070Z","iopub.status.idle":"2024-02-15T23:01:32.820842Z","shell.execute_reply.started":"2024-02-15T23:01:32.432046Z","shell.execute_reply":"2024-02-15T23:01:32.819734Z"},"trusted":true},"execution_count":64,"outputs":[{"execution_count":64,"output_type":"execute_result","data":{"text/plain":"<Axes: >"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 2 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"df.info()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.823449Z","iopub.execute_input":"2024-02-15T23:01:32.823838Z","iopub.status.idle":"2024-02-15T23:01:32.836625Z","shell.execute_reply.started":"2024-02-15T23:01:32.823803Z","shell.execute_reply":"2024-02-15T23:01:32.835541Z"},"trusted":true},"execution_count":65,"outputs":[{"name":"stdout","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 1025 entries, 0 to 1024\nData columns (total 14 columns):\n #   Column    Non-Null Count  Dtype  \n---  ------    --------------  -----  \n 0   age       1025 non-null   int64  \n 1   sex       1025 non-null   int64  \n 2   cp        1025 non-null   int64  \n 3   trestbps  1025 non-null   int64  \n 4   chol      1025 non-null   int64  \n 5   fbs       1025 non-null   int64  \n 6   restecg   1025 non-null   int64  \n 7   thalach   1025 non-null   int64  \n 8   exang     1025 non-null   int64  \n 9   oldpeak   1025 non-null   float64\n 10  slope     1025 non-null   int64  \n 11  ca        1025 non-null   int64  \n 12  thal      1025 non-null   int64  \n 13  target    1025 non-null   float64\ndtypes: float64(2), int64(12)\nmemory usage: 112.2 KB\n","output_type":"stream"}]},{"cell_type":"code","source":"df.describe()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.837812Z","iopub.execute_input":"2024-02-15T23:01:32.838083Z","iopub.status.idle":"2024-02-15T23:01:32.886258Z","shell.execute_reply.started":"2024-02-15T23:01:32.838059Z","shell.execute_reply":"2024-02-15T23:01:32.885425Z"},"trusted":true},"execution_count":66,"outputs":[{"execution_count":66,"output_type":"execute_result","data":{"text/plain":"               age          sex           cp     trestbps        chol  \\\ncount  1025.000000  1025.000000  1025.000000  1025.000000  1025.00000   \nmean     54.434146     0.695610     0.942439   131.611707   246.00000   \nstd       9.072290     0.460373     1.029641    17.516718    51.59251   \nmin      29.000000     0.000000     0.000000    94.000000   126.00000   \n25%      48.000000     0.000000     0.000000   120.000000   211.00000   \n50%      56.000000     1.000000     1.000000   130.000000   240.00000   \n75%      61.000000     1.000000     2.000000   140.000000   275.00000   \nmax      77.000000     1.000000     3.000000   200.000000   564.00000   \n\n               fbs      restecg      thalach        exang      oldpeak  \\\ncount  1025.000000  1025.000000  1025.000000  1025.000000  1025.000000   \nmean      0.149268     0.529756   149.114146     0.336585     1.071512   \nstd       0.356527     0.527878    23.005724     0.472772     1.175053   \nmin       0.000000     0.000000    71.000000     0.000000     0.000000   \n25%       0.000000     0.000000   132.000000     0.000000     0.000000   \n50%       0.000000     1.000000   152.000000     0.000000     0.800000   \n75%       0.000000     1.000000   166.000000     1.000000     1.800000   \nmax       1.000000     2.000000   202.000000     1.000000     6.200000   \n\n             slope           ca         thal       target  \ncount  1025.000000  1025.000000  1025.000000  1025.000000  \nmean      1.385366     0.754146     2.323902     0.536390  \nstd       0.617755     1.030798     0.620660     0.285822  \nmin       0.000000     0.000000     0.000000     0.100000  \n25%       1.000000     0.000000     2.000000     0.260000  \n50%       1.000000     0.000000     2.000000     0.710000  \n75%       2.000000     1.000000     3.000000     0.810000  \nmax       2.000000     4.000000     3.000000     0.900000  ","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>age</th>\n      <th>sex</th>\n      <th>cp</th>\n      <th>trestbps</th>\n      <th>chol</th>\n      <th>fbs</th>\n      <th>restecg</th>\n      <th>thalach</th>\n      <th>exang</th>\n      <th>oldpeak</th>\n      <th>slope</th>\n      <th>ca</th>\n      <th>thal</th>\n      <th>target</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>count</th>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n      <td>1025.00000</td>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n      <td>1025.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>54.434146</td>\n      <td>0.695610</td>\n      <td>0.942439</td>\n      <td>131.611707</td>\n      <td>246.00000</td>\n      <td>0.149268</td>\n      <td>0.529756</td>\n      <td>149.114146</td>\n      <td>0.336585</td>\n      <td>1.071512</td>\n      <td>1.385366</td>\n      <td>0.754146</td>\n      <td>2.323902</td>\n      <td>0.536390</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>9.072290</td>\n      <td>0.460373</td>\n      <td>1.029641</td>\n      <td>17.516718</td>\n      <td>51.59251</td>\n      <td>0.356527</td>\n      <td>0.527878</td>\n      <td>23.005724</td>\n      <td>0.472772</td>\n      <td>1.175053</td>\n      <td>0.617755</td>\n      <td>1.030798</td>\n      <td>0.620660</td>\n      <td>0.285822</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>29.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>94.000000</td>\n      <td>126.00000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>71.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.100000</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>48.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>120.000000</td>\n      <td>211.00000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>132.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>1.000000</td>\n      <td>0.000000</td>\n      <td>2.000000</td>\n      <td>0.260000</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>56.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n      <td>130.000000</td>\n      <td>240.00000</td>\n      <td>0.000000</td>\n      <td>1.000000</td>\n      <td>152.000000</td>\n      <td>0.000000</td>\n      <td>0.800000</td>\n      <td>1.000000</td>\n      <td>0.000000</td>\n      <td>2.000000</td>\n      <td>0.710000</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>61.000000</td>\n      <td>1.000000</td>\n      <td>2.000000</td>\n      <td>140.000000</td>\n      <td>275.00000</td>\n      <td>0.000000</td>\n      <td>1.000000</td>\n      <td>166.000000</td>\n      <td>1.000000</td>\n      <td>1.800000</td>\n      <td>2.000000</td>\n      <td>1.000000</td>\n      <td>3.000000</td>\n      <td>0.810000</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>77.000000</td>\n      <td>1.000000</td>\n      <td>3.000000</td>\n      <td>200.000000</td>\n      <td>564.00000</td>\n      <td>1.000000</td>\n      <td>2.000000</td>\n      <td>202.000000</td>\n      <td>1.000000</td>\n      <td>6.200000</td>\n      <td>2.000000</td>\n      <td>4.000000</td>\n      <td>3.000000</td>\n      <td>0.900000</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df['sex'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.887703Z","iopub.execute_input":"2024-02-15T23:01:32.888112Z","iopub.status.idle":"2024-02-15T23:01:32.895403Z","shell.execute_reply.started":"2024-02-15T23:01:32.888076Z","shell.execute_reply":"2024-02-15T23:01:32.894537Z"},"trusted":true},"execution_count":67,"outputs":[{"execution_count":67,"output_type":"execute_result","data":{"text/plain":"sex\n1    713\n0    312\nName: count, dtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"df['cp'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.896532Z","iopub.execute_input":"2024-02-15T23:01:32.896818Z","iopub.status.idle":"2024-02-15T23:01:32.905212Z","shell.execute_reply.started":"2024-02-15T23:01:32.896795Z","shell.execute_reply":"2024-02-15T23:01:32.904337Z"},"trusted":true},"execution_count":68,"outputs":[{"execution_count":68,"output_type":"execute_result","data":{"text/plain":"cp\n0    497\n2    284\n1    167\n3     77\nName: count, dtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"df.memory_usage()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.906556Z","iopub.execute_input":"2024-02-15T23:01:32.906944Z","iopub.status.idle":"2024-02-15T23:01:32.916744Z","shell.execute_reply.started":"2024-02-15T23:01:32.906910Z","shell.execute_reply":"2024-02-15T23:01:32.915633Z"},"trusted":true},"execution_count":69,"outputs":[{"execution_count":69,"output_type":"execute_result","data":{"text/plain":"Index        128\nage         8200\nsex         8200\ncp          8200\ntrestbps    8200\nchol        8200\nfbs         8200\nrestecg     8200\nthalach     8200\nexang       8200\noldpeak     8200\nslope       8200\nca          8200\nthal        8200\ntarget      8200\ndtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"df.loc[0:4,['age','sex','cp']]","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.918079Z","iopub.execute_input":"2024-02-15T23:01:32.918469Z","iopub.status.idle":"2024-02-15T23:01:32.928844Z","shell.execute_reply.started":"2024-02-15T23:01:32.918428Z","shell.execute_reply":"2024-02-15T23:01:32.927995Z"},"trusted":true},"execution_count":70,"outputs":[{"execution_count":70,"output_type":"execute_result","data":{"text/plain":"   age  sex  cp\n0   52    1   0\n1   53    1   0\n2   70    1   0\n3   61    1   0\n4   62    0   0","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>age</th>\n      <th>sex</th>\n      <th>cp</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>52</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>53</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>70</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>61</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>62</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df.info()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.932919Z","iopub.execute_input":"2024-02-15T23:01:32.933219Z","iopub.status.idle":"2024-02-15T23:01:32.943623Z","shell.execute_reply.started":"2024-02-15T23:01:32.933186Z","shell.execute_reply":"2024-02-15T23:01:32.942665Z"},"trusted":true},"execution_count":71,"outputs":[{"name":"stdout","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 1025 entries, 0 to 1024\nData columns (total 14 columns):\n #   Column    Non-Null Count  Dtype  \n---  ------    --------------  -----  \n 0   age       1025 non-null   int64  \n 1   sex       1025 non-null   int64  \n 2   cp        1025 non-null   int64  \n 3   trestbps  1025 non-null   int64  \n 4   chol      1025 non-null   int64  \n 5   fbs       1025 non-null   int64  \n 6   restecg   1025 non-null   int64  \n 7   thalach   1025 non-null   int64  \n 8   exang     1025 non-null   int64  \n 9   oldpeak   1025 non-null   float64\n 10  slope     1025 non-null   int64  \n 11  ca        1025 non-null   int64  \n 12  thal      1025 non-null   int64  \n 13  target    1025 non-null   float64\ndtypes: float64(2), int64(12)\nmemory usage: 112.2 KB\n","output_type":"stream"}]},{"cell_type":"code","source":"df_cat = df[['sex','cp','fbs','restecg','exang','slope','thal']]\ndf_int = df.drop(columns=['sex','cp','fbs','restecg','exang','slope','thal'])","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.944711Z","iopub.execute_input":"2024-02-15T23:01:32.945029Z","iopub.status.idle":"2024-02-15T23:01:32.953257Z","shell.execute_reply.started":"2024-02-15T23:01:32.945003Z","shell.execute_reply":"2024-02-15T23:01:32.952442Z"},"trusted":true},"execution_count":72,"outputs":[]},{"cell_type":"code","source":"df_cat.info()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.954363Z","iopub.execute_input":"2024-02-15T23:01:32.954694Z","iopub.status.idle":"2024-02-15T23:01:32.966610Z","shell.execute_reply.started":"2024-02-15T23:01:32.954652Z","shell.execute_reply":"2024-02-15T23:01:32.965719Z"},"trusted":true},"execution_count":73,"outputs":[{"name":"stdout","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 1025 entries, 0 to 1024\nData columns (total 7 columns):\n #   Column   Non-Null Count  Dtype\n---  ------   --------------  -----\n 0   sex      1025 non-null   int64\n 1   cp       1025 non-null   int64\n 2   fbs      1025 non-null   int64\n 3   restecg  1025 non-null   int64\n 4   exang    1025 non-null   int64\n 5   slope    1025 non-null   int64\n 6   thal     1025 non-null   int64\ndtypes: int64(7)\nmemory usage: 56.2 KB\n","output_type":"stream"}]},{"cell_type":"code","source":"df_int.info()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.967751Z","iopub.execute_input":"2024-02-15T23:01:32.968032Z","iopub.status.idle":"2024-02-15T23:01:32.980077Z","shell.execute_reply.started":"2024-02-15T23:01:32.968003Z","shell.execute_reply":"2024-02-15T23:01:32.979009Z"},"trusted":true},"execution_count":74,"outputs":[{"name":"stdout","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 1025 entries, 0 to 1024\nData columns (total 7 columns):\n #   Column    Non-Null Count  Dtype  \n---  ------    --------------  -----  \n 0   age       1025 non-null   int64  \n 1   trestbps  1025 non-null   int64  \n 2   chol      1025 non-null   int64  \n 3   thalach   1025 non-null   int64  \n 4   oldpeak   1025 non-null   float64\n 5   ca        1025 non-null   int64  \n 6   target    1025 non-null   float64\ndtypes: float64(2), int64(5)\nmemory usage: 56.2 KB\n","output_type":"stream"}]},{"cell_type":"code","source":"#Since the categorical variables are already in numerical format, we don't need to one hot encode them","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:01:32.981246Z","iopub.execute_input":"2024-02-15T23:01:32.981882Z","iopub.status.idle":"2024-02-15T23:01:32.988589Z","shell.execute_reply.started":"2024-02-15T23:01:32.981849Z","shell.execute_reply":"2024-02-15T23:01:32.987784Z"},"trusted":true},"execution_count":75,"outputs":[]},{"cell_type":"code","source":"y = df['target']\nX = df.drop('target',axis=1)\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:32:46.609938Z","iopub.execute_input":"2024-02-15T23:32:46.610698Z","iopub.status.idle":"2024-02-15T23:32:46.626128Z","shell.execute_reply.started":"2024-02-15T23:32:46.610658Z","shell.execute_reply":"2024-02-15T23:32:46.625090Z"},"trusted":true},"execution_count":129,"outputs":[{"execution_count":129,"output_type":"execute_result","data":{"text/plain":"   age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  \\\n0   52    1   0       125   212    0        1      168      0      1.0      2   \n1   53    1   0       140   203    1        0      155      1      3.1      0   \n2   70    1   0       145   174    0        1      125      1      2.6      0   \n3   61    1   0       148   203    0        1      161      0      0.0      2   \n4   62    0   0       138   294    1        1      106      0      1.9      1   \n\n   ca  thal  target  \n0   2     3    0.23  \n1   0     3    0.37  \n2   0     3    0.24  \n3   1     3    0.28  \n4   3     2    0.21  ","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>age</th>\n      <th>sex</th>\n      <th>cp</th>\n      <th>trestbps</th>\n      <th>chol</th>\n      <th>fbs</th>\n      <th>restecg</th>\n      <th>thalach</th>\n      <th>exang</th>\n      <th>oldpeak</th>\n      <th>slope</th>\n      <th>ca</th>\n      <th>thal</th>\n      <th>target</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>52</td>\n      <td>1</td>\n      <td>0</td>\n      <td>125</td>\n      <td>212</td>\n      <td>0</td>\n      <td>1</td>\n      <td>168</td>\n      <td>0</td>\n      <td>1.0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>3</td>\n      <td>0.23</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>53</td>\n      <td>1</td>\n      <td>0</td>\n      <td>140</td>\n      <td>203</td>\n      <td>1</td>\n      <td>0</td>\n      <td>155</td>\n      <td>1</td>\n      <td>3.1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>3</td>\n      <td>0.37</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>70</td>\n      <td>1</td>\n      <td>0</td>\n      <td>145</td>\n      <td>174</td>\n      <td>0</td>\n      <td>1</td>\n      <td>125</td>\n      <td>1</td>\n      <td>2.6</td>\n      <td>0</td>\n      <td>0</td>\n      <td>3</td>\n      <td>0.24</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>61</td>\n      <td>1</td>\n      <td>0</td>\n      <td>148</td>\n      <td>203</td>\n      <td>0</td>\n      <td>1</td>\n      <td>161</td>\n      <td>0</td>\n      <td>0.0</td>\n      <td>2</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0.28</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>62</td>\n      <td>0</td>\n      <td>0</td>\n      <td>138</td>\n      <td>294</td>\n      <td>1</td>\n      <td>1</td>\n      <td>106</td>\n      <td>0</td>\n      <td>1.9</td>\n      <td>1</td>\n      <td>3</td>\n      <td>2</td>\n      <td>0.21</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.preprocessing import StandardScaler\n#pipeline helps in preventing leaks from test data to train data\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.metrics import accuracy_score,mean_squared_error,mean_absolute_error,r2_score\n\nX_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3,random_state=42)\n\npipe = Pipeline([('scaler',StandardScaler()),('Linear_Regression',LinearRegression())])\npipe.fit(X_train,y_train)\n\ny_pred = pipe.predict(X_test)\n\nmse = mean_squared_error(y_test,y_pred)\nprint('Mean Squared Error is', mse)\n\nrmse = np.sqrt(mean_squared_error(y_test,y_pred))\nprint('Root Mean Squared Error is', rmse)\n\nr2 = r2_score(y_test,y_pred)\nprint('R2 Score is', r2)","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:43:36.409886Z","iopub.execute_input":"2024-02-15T23:43:36.410785Z","iopub.status.idle":"2024-02-15T23:43:36.431823Z","shell.execute_reply.started":"2024-02-15T23:43:36.410754Z","shell.execute_reply":"2024-02-15T23:43:36.430942Z"},"trusted":true},"execution_count":139,"outputs":[{"name":"stdout","text":"Mean Squared Error is 0.0489678078477241\nRoot Mean Squared Error is 0.22128670960481134\nR2 Score is 0.39519765801601003\n","output_type":"stream"}]},{"cell_type":"markdown","source":"### Now, let's try using the XGBRegressor to see if there is any improvement in the scores","metadata":{}},{"cell_type":"code","source":"from xgboost.sklearn import XGBRegressor\nxgb = XGBRegressor()\n\npipeA = Pipeline([('scaler',StandardScaler()),('XGB',XGBRegressor())])\npipeA.fit(X_train,y_train)\n\ny_pred_xgb = pipeA.predict(X_test)\n\nxgb_mse = mean_squared_error(y_test,y_pred_xgb)\nprint(\"XGB MSE is\", xgb_mse)\n\nxgb_rmse = np.sqrt(mean_squared_error(y_test,y_pred_xgb))\nprint(\"XGB RMSE is\", xgb_rmse)\n\nxgb_r2 = r2_score(y_test,y_pred_xgb)\nprint(\"XGB R2 Score is\", xgb_r2)","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:43:54.021175Z","iopub.execute_input":"2024-02-15T23:43:54.021874Z","iopub.status.idle":"2024-02-15T23:43:54.098537Z","shell.execute_reply.started":"2024-02-15T23:43:54.021844Z","shell.execute_reply":"2024-02-15T23:43:54.097755Z"},"trusted":true},"execution_count":140,"outputs":[{"name":"stdout","text":"XGB MSE is 0.014349771934012873\nXGB RMSE is 0.11979053357428905\nXGB R2 Score is 0.8227656892541396\n","output_type":"stream"}]},{"cell_type":"code","source":"sns.regplot(x = y_test,y = y_pred_xgb)","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:04:44.271500Z","iopub.execute_input":"2024-02-15T23:04:44.272173Z","iopub.status.idle":"2024-02-15T23:04:44.602865Z","shell.execute_reply.started":"2024-02-15T23:04:44.272140Z","shell.execute_reply":"2024-02-15T23:04:44.601967Z"},"trusted":true},"execution_count":102,"outputs":[{"execution_count":102,"output_type":"execute_result","data":{"text/plain":"<Axes: xlabel='target'>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAiMAAAGwCAYAAAB7MGXBAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8WgzjOAAAACXBIWXMAAA9hAAAPYQGoP6dpAADAE0lEQVR4nOy9eZxddX3///p8znb32ZdkMiF7CBAWExJABNRosP3Rauu3VC1QqlYRrBqtgFr8upR8EYtpBcG616ViK2gVDWKUACUSCVsIyWSDrDOTWe9+z/b5/P449965Z+bembmTycxk8n4+OpU5c86555w7mc/7vt7v9+vNpJQSBEEQBEEQ0wSf7gsgCIIgCOLMhoIRgiAIgiCmFQpGCIIgCIKYVigYIQiCIAhiWqFghCAIgiCIaYWCEYIgCIIgphUKRgiCIAiCmFbU6b6A8SCEwPHjxxGNRsEYm+7LIQiCIAhiHEgpkUwmMXfuXHBeWf84LYKR48ePo729fbovgyAIgiCICXDkyBHMmzev4s9Pi2AkGo0C8G4mFotN89UQBEEQBDEeEokE2tvbi+t4JU6LYKSQmonFYhSMEARBEMRpxlglFlTAShAEQRDEtELBCEEQBEEQ0woFIwRBEARBTCsUjBAEQRAEMa1QMEIQBEEQxLRCwQhBEARBENMKBSMEQRAEQUwrFIwQBEEQBDGtUDBCEARBEMS0clo4sBIEQRCnD0JI7DqeQH/GQn1Ix7lzY+CchpwSlZmQMnLfffdhwYIFCAQCWLt2LbZv315xX9u28fnPfx6LFy9GIBDABRdcgM2bN0/4ggmCIIiZy9P7e3HDd7bjA99/Fp/4yYv4wPefxQ3f2Y6n9/dO96URM5iqg5EHH3wQGzZswGc/+1k899xzuOCCC7B+/XqcOHGi7P6f+cxn8PWvfx1f/epX8corr+CDH/wg3vGOd+D5558/6YsnCIIgZg5P7+/Fpx7eid2dCYQNFc1RA2FDxe7OJD718E4KSIiKMCmlrOaAtWvX4uKLL8a9994LABBCoL29HR/+8Idx2223jdh/7ty5+PSnP42bb765uO0v//IvEQwG8YMf/KDsa5imCdM0i98Xpv7F43EalEcQBDEDEULihu9sx+7OBFpjAd9gNCkluhImVsyJ4ns3rqGUzRlEIpFATU3NmOt3VcqIZVnYsWMH1q1bN3QCzrFu3Tps27at7DGmaSIQCPi2BYNBPPXUUxVfZ+PGjaipqSl+tbe3V3OZBEEQxBSz63gCB06kUBfSAQZkLRfJnI2s5QIMqA1pOHAihV3HEyf1OkJI7Dwax9a9Pdh5NA4hqvo8TcxQqipg7e3theu6aGlp8W1vaWnBnj17yh6zfv163HPPPbjiiiuwePFibNmyBQ899BBc1634Orfffjs2bNhQ/L6gjBAEQRAzk/6MBduVsFyBzngOpuNCSoAxwFAVNER02EKiP2NN+DWe3t+L+7cewIETKdiuhKYwLG6O4KYrF+OyJY2TeDfEVHPKW3v/9V//FUuXLsXZZ58NXddxyy234MYbbwTnlV/aMAzEYjHfF0EQBDFzqQ/pEFLi2EAWOdsFZwyqwsAZQ852cWwgCyEk6kP6hM4/mfUoZ6q6MpPvuyplpLGxEYqioLu727e9u7sbra2tZY9pamrCz372M+RyOfT19WHu3Lm47bbbsGjRoolfNUEQBDGjWNEahSslXCGhq14QAnjKCLiE5Ui4UmJFa7Tqcwshcf/WA0iZjq8eJcAVtMY4uhIm7t96AJcsahizHuVMVVdm+n1XpYzouo5Vq1Zhy5YtxW1CCGzZsgWXXnrpqMcGAgG0tbXBcRz89Kc/xZ//+Z9P7IoJgiCIGcfuriQUBqgKgyMAISWklBBSwhHedoV5+1VLaT1KaWEsADDGxl2PcqZ2+5wO91216dmGDRtwww03YPXq1VizZg02bdqEdDqNG2+8EQBw/fXXo62tDRs3bgQAPPPMMzh27BguvPBCHDt2DP/3//5fCCHwyU9+cnLvhCAIgphSSs3NXutJgzOOuTVB9KVNmI4o1owENY6GsIG05WDH4YGqzdAK9Si6Uv7zs6FwxMeoR5lMdWWmMB5zudL7bokaMB2JtOVA5RwtUR3dSWtG3HfVwci1116Lnp4e3HHHHejq6sKFF16IzZs3F4taDx8+7KsHyeVy+MxnPoODBw8iEongT/7kT/D9738ftbW1k3YTBEEQxNQyXPaXkEjmHOgqx4KGMHK2gCMEVM4R0Dj6MxYSWQf3/W4/AFSVJqgP6dAUBssVCHBlxM9NV0DjbNR6lGrUlZXzaoo/m6lusuNNuxTu21A5DvVnfEGioXLEguXve6qZkB38LbfcgltuuaXszx5//HHf91deeSVeeeWVibwMQRAEMQMpyP4p00FdSIeucJiOi3jWRmc8C01hiAY0AF7gkMzZ6IrnoHCGmpAKQ1FguaKYJrjzHStHDUjOnRvD4uYIdncm0RrjIzxMBjM2VsyJ4ty5lZsdJqKuVFrwP3DFItQE9WkLUMo9/0rPsz9jIW26yNoOXAmonIExQALI2gKWYyKoqyfV5TQZ0GwagiAIYtxUSncEdRVttUEc7s/g2GAWZzUwGIqCnOPi2GAWANBWG0RQ85adsdIjwxWJD1yxCJ/52cvoSpioDWkwFA7TFRjM2IgYCm66cvGoAUG16kqlBf/FI3G87z+ehaF659AVjuWtUXzoqqkpBK023VQb1JC1XbhCQlOGAjkGQOOA7QpkLRe1Qe2UX/toUDBCEARBjJvR0h3RgIbWmgB6kxbiGQdgDqSU4IyhuSaQV0uGqJQeqaRIvGftfGzd24uOriQsV0BXOM4eZyBQjbpSacF3bImM5cAREjlbQGFeuuOZVy3sO5HEV/7qwlMekJQzlyumw3Re9nkWb3V4rJb/nk1/1omCEYIgCGL8jJXuqAvqsByBm9+0BAsbw3itJ417f7+/4ifv4emR0VIQe7uTaIoYkJDw/k/CSziMDecMN125GJ96eOeY6srOo/ERAZeUEp3xLJwSbw5F4WAAHFegJ2li46934+c3X162iHR43QmAsrUoY9WoVGsuN5i1EdAUZISE40oo3NtXSsAVXqAY0BQMZu1xPcdTBQUjBEEQxLgZT7pDVzhq8ipILKiNOz0yWgoiYggc7s+gP23hrPoQDNWrO9nTlRpX3QkAXLakEXe+Y2VRdYkLCY0zrJgT9RV+lgu4srYL0xYAPEFBwvt/nDNoKoftCOztTmHnsTguaK8tHldO5WmIeKmgvpTlU36uWNqIJ/b1jlqUWmouBwAKZ2DcCy4K5nI1Qa2YbqoP6QjrCiKGinjW9oIX4QUkAU1BTVCDlBM3o5ssKBghCIIgxs1Y6Y6eZA6MMXxp827PX4QDWUcgbTlorwuNmh6plAKSkOhNWSVZBgbO2YTaci9b0ohLFjWMqj6UC7gyluvTYBiG0hsMDApnsF2BFw4PFoORcirPYNYu+qHMqQmgOWrAcgVeOjqIbQf6ENIVtMQCFYtSqzWXK32/zmoIwrRlMa1jaAzdCWvM4t+p4JTbwRMEQRCzh0K6I2Io6EqYyNouhJDI2i6ODGSQNr3vIwENzVEDkYAGIYC06f28dP+uhOlLj1RKAeUsAdNxoXAGKQFHiOLPqjE9Gy+FBXwgY0NIr8DTdIbmqUl4i7+v1iL/3zL/v8NVnoCmgHEgnrWLQVV/2kLKdCCkhO0IuELCcQWE8LxApARaojpSpov7tx6AELJqc7nS96s7YQEMCOsqwIDuhDWu4t+pgJQRgiAIoioqpTsYYwjpCubXh3wplvn1QRzuz4IxIGM6FdMjlVJAjsh7Y3BvzVeHzTYbj+lZgfH4cxQW8I/95AXs7U5BSglX+M+jKhwMQ/Ukriuhco6L8qpIOZWnEFRxxuAIiawtcHTAey6ukGDMa7c91J8BUN4LpD9jjWkul7Fd37MYb3pqOqFghCAIgqia4emO/pSFL23ejUhAK2sq1hwzkM7Z+Mf1Z6M+opdNj1RKAXnBh4TrAkFdQUDzByPjMT0DqvPn8MOgcPiKV4WU8K4qHywBWN4awco2r4OlnMrjCE/9kHKo7JbnPT8kvLqPAipnZb1ACgFbJXO5nCOguWLEs7hsSSPWLKjHL17qxLHBDNpqQ7jm/DlQ1ZmRIKFghCAIgpgQnLNi++jWvT1wBEY3FZNAfUTHlcuaKp6vXMcLmARjDEJKNEaMCZme+WzRYwZMu8QWPaajOzFkiw4A9289AFdILGuOwHS8OgvLFeiO5+BKwHVlsdCBM4b6iI7b37aiGFyVqjwG58hZAjnbRemgXJa/Zyn9HUGMASKvdqgccFxZ9ALxB2wGgrqCgrncaM+inCL00PNHSRkhCIIgZg+TYdkOVE4pnN0axYmkiZTpQlX4uEzPSttk+1NW3hZdwaG+7IiW2Jqgv+6kkGLhnCOoA4UF31AVdA5mYTkCAY0joCl5r5MlvkW9EDS8dHQQTr4VV4iRQUfBDbUU2/W0kmKRrByqT6mmRbnAaIrQ7Q+9hNuuXoE3ndNcNHKbDigYIQiCICZE6WJfG9SwqCmCPV0Tt2wvUKnj5Q8H+8Zd9zBcCXCFQCLnmbAxxka0xJq2A0NTsXXvCUQCGixHoC40UuWJGCoWNYZxPJHD+y5fiCuXNZe1g+ec4Yqljdh2oA+ukFAVBs4AtyTyKHTCyGH1KMCQP1khflEVVvQCqaYGZLR26eYoQ2fcxDf/91VcdXZ5tWqqoGCEIAiCqJpK/hkKR1WW7ZVMvkpTQAXG05ZbuLbhSkA8Z6E/4y3mOve3xEoGWK6EbTr45pOvQlM4EjkHhmahPmyMuHdLSIQ0BVcua/Zdo+OIYk3GnJogHu84gZCuwBV5ZWSYBOIWN4w0bpPIp3HyBmWOK33GceN9FuUKaWW+NdgVEtGAiiN9aezuTOJ1Z9WNuI6pgoIRgiAIoioKi30yZyOkq9AUDiEljg/moCoMc2oM9KWsqtWL8UzyLReklFJJCTCUoRSE7QowxvOFpDKfFvGoC2lQFIbBrIXOeA6awn029pVUnm88cQD3PX4AyawNgbwxmgQawhpa60PI2QK26+JE0oLlulAYg5BAc9QAY8CxwRyQP05XeTGFBHjOqXJkvDLmswD8hbRSerUnOceFwjyfEV1hSMrxdSKdSigYIQiCIMZNYbHvT1twhUQilysunLrCobgcNUENX3z7Sgxm7arUi2om+VaiknGaKyV4vjBUAjCdkbmRQmdLUPMP/ZtfzxBQlYoqzzeeOIC7NncU0zFqvlXXkUBv2oaqKGiKGghCAeccxwaycKUAZN4vpCQYKjymwrU4wnNZDeoTs2wv1PIMZi0MZixfK7CucEQCKjQ2di3PqWZm9PQQBEEQpwW7jifwyvE4sraLnCPAGYOaT3vkHIGs7WB3ZwKcMVy5rAkr59WUTc0MNwTj3JuR0hozfCZf1VLJOE3lfETL8XC87hXvuGhAw5yaIDhjiGdtnEiZyJgOVsyJ+gIlxxG47/EDRUdUlXNwxqGUeKH0JHMQeaO2iKGirS4IPa/UJHNO8XobwxqCupI3MPOMzIIaR2PUQFhXJhQwnDs3hvqwhuODOWRtMVQvk3+/epIWakMaVsyJVn3uyYSUEYIgCGLc9KZNJHKea6jGy4ykzxeK9qbNiucYbfJvpUm+46VSV89wbxJNKbi5lgQ8EjC0oeupDXqFrLe8cQkWNIXLqjy/eKkTyaydL1Adeg3GUFRiXAn0JC2EDAUq5whpHCFdwfLWKD765qWoC+u4+9E92NOVwln1gWIrsco5DJWhOzlxy/ZEzoZVUF4Kt1oYrlN9rHfKIGWEIAiCGDeDaRsiP+21XCDBmTd5djBdOaUw1uRfQ+G+ybPVUGrlXurfkbOF7/uCx8ewG4BpD+1jugKawvC6s+oqqjzHBjMQGEqvDJ2fQS25v960iaMDWbzWl8beEymoCsMn1y/HVWc344L2WnzoqiWeZXtymGV7cmKW7a6Q6Irn8IcD/RhMW2iKGghoStEtVkqJgOaljwbSFr711KvjPvepgIIRgiAIYtzUhbTiqHs57KO1hPQCFc5QF9IqnMGvXpRjvJ4k5ag0OyeTn/WicoaAxiHhpYsYCqqOZ+5emHtTKFRd3BwZVZFoqw2BI1+Lkp8R4+ZTLHKY6uIFQ+XliEK77oo5UWRMp2JaaDxkLAdHBzLIWA7iOQu2kIgFVLTVBTC3JoTWGu9/2+oCMFSG/qyNL/9mL369s3PcrzHZUJqGIAiCGDcNEQOxgIZ41objSig83x4rC/NVGGIBDQ2RkS2xBcaa/FuNJ0k5yvlwQAKawtEU1VEX1pGzRNFVtTdpwRWiqOxkbXfUduRSrjl/Dj73y10YzNhw8oHG8HCDA1jYFPYKXEum5Q6fNDzedt1KCCHRl7aQzA2pUjUBHRpnsF0JQ+UIaAyA11nTn7bRlx5Snz7zs5exZmH9qO/dqYKCEYIgCGLcnDs3hnPmxnzOolIMDXVTFYZz5sZGDST8LqI5BDWlGNBkbRcRQz3pSbLDF/baoFasy4CEz0ZdVziODWbBwJDI2dAVXmxHvmRRA3YejVcMDlSV40/Pa8UPtx+pWIJRE9IQ0v3LbaW6mErtupX8WArkbBc9SRP2MLVpSUsY7Q1hHOxJoTGig4HBdLyJycM7iq4+rxWGNj0urBSMEARBEOOmNJBImQ7qNX1EIPGBKxaN+en+siWNeM/a+bjv8QM4PpgtmnxFgxres3b+pMxLGb6wf+iqJWVt1FOmi7baIN73hkVorw/5HF9v+M72UX1QhJA4PJBFWFeQtVwMTzwxeL4mBefXApM1afjSxQ0YyNgYrHAezhjevaYd9zy2Fz1JExJed1ApdSEN9/zVBXjj2S3je7CnACaHT+iZgSQSCdTU1CAejyMWm5hsRxAEQUwevgUyb262uDmCK5Y24ol9vWMamRV8RhJZC5qiFL0vbFcgFtQm7DMy0euudH3DfVAG8umbwvXtPBrHB77/LBjzvDxylltUSKREPo3FcFZ9OK/GeGRtFxnTwdevWz1qx9Bo1xHWOTa8Zfm4Oo5+tbMTX3v8ADKW69t+ycJ6fPpPV2BZa/SUzKYZ7/pNyghBEARRNeXqG+JZC5/52csVjcy++PbzUBPU0ZcysWnLPvSnTbgCSJqWz4irP22PqKc4ldddSCkV0jG1QQ1fe3x/2XkurTGOroRZvL7+jIW05QUWEoCq8KJSZDnCMy1jMl8YO/Z03VJGmyvTFGHoSuTwH384hLv+cmXR3n44rpB48I9H8L1tr41wmv3k1cuxdmHDJDzVk4eCEYIgCGJClKZBhJC44TvbKy7gh/uzuOU/n0dIU5C1XcQzdlFBUBVWHAyXtV0oXGDXsUH8/IXjqI/oVRdyVnPdgKc+fO3x/djTlYTtSDAGpE0HzTFjTB+U2qCGnO16visqR+FOGPMKZi1XwJVel44QckKThofPlXGE17UUDWg40pfG/u40lrVGRtzna31p3LW5Ax1dSd/2t53XipuuWoyIMXNCgJlzJQRBEMRpy2hGZmnLRdZ24Aqvo0Pl8NVWlH5iZ/CGwg1kHHzhkVegMOZL9ZxMt0k5nt7fi4/95AX0p63i/BcpJVwJdCdy0FVlxKKtKwx9toute09gTk1waG5MofAlD2dDg+5yloDpmFVPGk6aDjSVI6B5A/ccIYrtOoW5MvGcv17EFRI/efYIvvu0Xw1pCOt418Xz0d4QxPGBHJa0hCsqKlMNBSMEQRDESVPJyExKiZ5kLu+9AfSmLL//xjBKf6IpDI1ho5jq+dhPXkBz1BvCN97BeqMhhMTGX+9GT9IsWsEzeI6privhCKAznsWSpkgxwEqZDrriOViOi28++So4A1zptQXbQkLlQwanjpB5XxMFt7x5KRY2lndxBcrXhiRyNgazNo72ZzC3LojgsJoOy5XQGENNYMiP5VBeDdkzTA25eEEdLFfgJ88eLtbKtDeE8e417bho/vRN6y1ApmcEQRDESVNqZCbhTYdN5mwMZmxkbYFC/FFQC8YDA5DOm5WFdY6epIk9XUmEdAXNUQNhQy3Wozy9v7fqa955LI6OrlTe9IwXXWUVPpQ2Mm2BbL7oM2U6ONqfQc52YagK5tYEEDZUSAkvTaMwuELCdgVcIRFQvbkyEUPFqvmVXVwrzeqpCWoIqNyzk0/kEM9a6EubiGdtuFIgmbPR3hDGkhbPw+THfzyCv//+Dl8g0hDW8d7LF+D4YBaH+zII6ioawjqCuoqDPSnc89hePH94oOpnN9mQMkIQBEGcNAUjM5//iBxKeQBecMHy81rGg6dYMO+Ywrjd/Jk4Z2ULSqtJ2Tx/ZNCbAaP4re0ZGDSVw3IEJIB4zoahcXTFc3CEF3S01ASgKN6E4v60V8Rq2gIKL2RrPMv1VM7FBe01oxaqlktxybyTa33EQHYgi5wjkUsOpWO6k0AsoOLda9pxdCCLL23uwCudCd9533pOC266ahG++MgeZCy36DMCAIbK0BjR0Zuy8I0nX0U0qGFOLDiptTnVQMEIQRAEcdJwznDF0kZsO9DnOY0qDAoHnJJOUgnAdoabyI8C8+zb3ZKABsLfmXIyg/VYhVoPAFAYg8oBR3hdMZ351ExQU9BSEyjWkTDGEA1oSJe09GoKg5BA1hZQXIkrljaOusAPT3FJKWHn58eUtgoPJ5lz8N87jmLH4UFYJQZm9WEdG96yFJctbsTerhSO9KURC2hgw24yawtkLBd7u5L4x5+8iLChnlTa62SgNA1BEARx0ggh8cS+XoR0BaG8n4YrRlqjV2NsVUiblC6iUnqBQinVDtYTQmLn0TgEJBTupVbKzdmR0nOV/ew15+K9ly9ENKBhQUPIV9AqpUTKtIupJwmGgglqSFcQNhQ8sa/XU3YqUJrickVBVZIQkOgvsWtXuTdDR1O8QEkC2Haw3xeIrFvRjG9evwqN4QD++Fo/dh2PezUiiv+ZZWwX3fEcbEcADKgJaied9joZSBkhCIIgTppCqqElFoChcuRsb/aL7Qgci+cmdM5Cp8dYDR/VDNYr7VixHC9aciUgbeG15ua7XxzXS9Esa4ngHRe1YdfxBH70jFf8qZTUkeZsAdMRUDiDIoGWmgBUzqByjoDuPYexVJtz58awqCmMXceTaIwMKRjJrFPsOipOGc5f7/AZg5wBCxvDWNIUwT//ag+O9KVh5wOglOlAUzhqg97wQgmJ/pQFIb17kRLQVQUB7eTSXicDBSMEQRDEhCj1xHi1Nw3LEagLeYPvCrNfMqYzrnOpnEFCjlhkC4pFoUPF614ZUhlGMxAbPs9luClbXYjD0DiOx3MQ0nN/LdS1cM7QENZx+9tWgHNWcbifI4ZqY4K6itqQPx0yHtv3nOPiL183D6/2dqA3ZSEa0KArDDl7KMelKl4gYrsj01wqZ6gPaeiK5/CNJw8iqCtoCBuIKQyW4xW69iRNaApDWFdh2hKW64IzQEiGoMYR0LxEycmkvU6GCQUj9913H+6++250dXXhggsuwFe/+lWsWbOm4v6bNm3C/fffj8OHD6OxsRHvfOc7sXHjRgQCgQlfOEEQBDF9DPfEAIBEzoGhWagPD019dcqkJwqBRSlCyKICwvND9xwhi0P4AtpQQWnW8kzGRhusV26eS8Z2IYTE/PpQMZioDxvQFI5jA1mAASFdha5wLG+N4kNXDdVO+If7Dc22cYSEkBKcMTRFjRF1GaOpNlJ6U3YTWRsXtNdiw1uW4Ufbj+BIXxpJKYc6kOCpF3aFVI+bn9ZbqPF1hYSueumtgKagJRbA8cEcuhM5zK0NwpUSQgCMeymvpmgAE52bM1lUHYw8+OCD2LBhAx544AGsXbsWmzZtwvr169HR0YHm5uYR+//oRz/Cbbfdhm9/+9u47LLLsHfvXvzt3/4tGGO45557JuUmCIIgiKmjnCeG6boYzFrojOegMsCVDLYrfPUMwFAgUlj6ikWfauHTubfHvLogTNsrVlU5h6ExvNabgekI9CRNgFUerFfJsyORtaFwhrTl+uo+ogEN8xu8AXIffuNSvO6suorD/e58x8oht1ZXQuNANOCdK6z7fUBGU21Mx8WJhH/K7kXz63DenBr8+I9HcCyeQWtNAP+94ygylhi15qRQP1IQjExHwLQlAhrLX5eKpqiOgbSNjOnClV7gZygKmmsMKIwhmbOLqaVq0l6TRdXByD333IP3v//9uPHGGwEADzzwAB555BF8+9vfxm233TZi/6effhqvf/3r8e53vxsAsGDBArzrXe/CM888c5KXThAEQUw1lealBLmKttogDvVlcGigfI2IpjBwxopzaIQQsPNrscIZNIWjNRZAT8pEd8JCbUjz0gquwNGBLExHIKRz1AR1cMYgpETGcvHDZw7j3Lk1uGxJY8XrK3iHiLwJW1gP+9SAgKogwRwsaAqPIzVRKKqVYIyjvc5AT8ocMQ24ku37YMbCQMbG8Dm1P/njEfxw+2Gkc16tSDkFaTgKAzjn+WDF21tIz4it2KPCgLqQDldI3PLmpVhQH8KmLftwsCeJnoRZbMMuzAZSFYbz59WO2o482VTVTWNZFnbs2IF169YNnYBzrFu3Dtu2bSt7zGWXXYYdO3Zg+/btAICDBw/iV7/6Ff7kT/6k4uuYpolEIuH7IgiCIKaf0Wzfc7YYdfF08+kcnvcNKQQinAGtsQDqQjq6EiYAoDVmIJ6xcXQwi8GMBQaGkK6gvS4EQ1W8T/aqgtaYgZTp4v6tB4o1IuWuT+UcnHvBUM72VIkTiRwG0haEEONSAwqKy56uBGpDGubVBlEb0orXPKfGQMZ0cCJlImM6WDEn6ps+7LgCxwezeev5kYHIN548iGTOAWPVBCIMokw3UCE9xpgX5LnSe16r5tfhqrOb8acrW5GxRHGKb8E4N2O5SJvumO3Ik01Vykhvby9c10VLS4tve0tLC/bs2VP2mHe/+93o7e3F5Zdf7g34cRx88IMfxKc+9amKr7Nx40Z87nOfq+bSCIIgiClgNNv3E0m/IjJ8QRXwlAkhhuohGLw6jZChgIEVh+odGchAyzuIOa5E2nRQE1RxqN9L1RQ+yRsqRyw4VHBZ6foCOoehKkjlC2pPpMziz47HPWVk1YK6imrAaBN0Cx0oNUEdX3z7Sgxm7RG27ynTQW/ShJAjQwzXlfjh9sNwZaFAd+TrGwrDR9ctw/OHB/Db3Sfyz3IowBuOyhlUhUPhbES6qLQNu9BK7OZrc0K6AoVzPLGvF++9fNGUBSSn3Gfk8ccfx5133omvfe1reO655/DQQw/hkUcewRe+8IWKx9x+++2Ix+PFryNHjpzqyyQIgiDGQaknRimDWXuksyob2ZYbMVQ0RQPgjIHnJ9uWFn4Whuolcw6CmoJ5dUGEdAWOkOhN28hYLjhjUPMqR9YW6E2aSFtusWum3PUxsBFeGwWE9Hw35tcFKy6+oylChQ6Ugz0pcMZ8tu9CSJxI5HAikSsbiADA7zpOIJVz8mkk/8848xQQ25XgnOEvXtee71QaXTlh+a+s7aIrYfrSRaVt2AsbwzirPox5dUGcVR/GwsYwmmNGMbibKqpSRhobG6EoCrq7u33bu7u70draWvaYf/qnf8J1112H973vfQCAlStXIp1O4+///u/x6U9/GpyPjIcMw4BhGCO2EwRBENNLpRbXgtxfjoJ3B+AVV3pdHxJBTUFzbMjNtDBUT0gJBq/Og3OvTbi48MqCrTzLz5TxWnKzlovaoFbx+oQUiGftkddW8t+PvNyFz/3ZeVDVketSJcWlQLkOlKzloidp5h1jyyOlxBN7e8oGFl7A5T0rx/WmCL9pefOYaoXnWuupP+WmBPvuZfip2GnQTaPrOlatWoUtW7bg7W9/OwCvAGnLli245ZZbyh6TyWRGBBxK3jFmeM6MIAiCmNlUanEVwxbcSkZlaxbWY15dEL98qRON+YFtBQoGYjxfNKGWrB2FlI/AMPd25n+9StfXm7KKqoOuetN5C6kexrx22GTWxi9e6sQ7Xtc24rpLFZcAV0b8vLTmRORbbZO5kcFPKd2JHP7lN3vx7CH/oDqet8EvBlLCC86kAH7+0nFI4XXQiHxap/BAhPQCuKih4JPrz0Z9RC87JbhwL4NZG/GsDdNxS9JeCmqC2szvptmwYQNuuOEGrF69GmvWrMGmTZuQTqeL3TXXX3892trasHHjRgDANddcg3vuuQcXXXQR1q5di/379+Of/umfcM011xSDEoIgCOL0odDiWvDxiAsJtYJiAAypIgDw8rE4Xj4aR8Z0ccjMoK02iGjAcwYdbiAW0L1zusLz8SiYnQkhwfLOod7PvHTPk/t6wBnDJYsaRlxfLq/caJwN2cmXBEycSbgAjg1myt5DJcXFu7+hmozFTWEcG8z6WnZHPg+JX+3sxH2/P4DcsNZnhQ0pSV5RqoQjvO2/eOkYcrZE2nK8ziSOfPGq51Yb0jgawgYytov6iI4rlzVVvJeGiI5dxxNgAFSFg3HvNbOWg4zl4Ny5sSntpqk6GLn22mvR09ODO+64A11dXbjwwguxefPmYlHr4cOHfUrIZz7zGTDG8JnPfAbHjh1DU1MTrrnmGvzzP//z5N0FQRAEMaVctqQRlyxqKBaN1gY1fOTHz+G1viwAfwBSgDPklQoFhuZ5khzuz2BOTRC1Qa2igZjXCeMNtvPm3XhpC8ZKhtJZDr755Kv40TOHi8PevnfjmuL1vXh4EJu27AXyaQ9XyKIaoHDvHAxAW22o7P1WUlwKLbxhnePda9rxxN5exHMWagI6lrSEiy3I+7vTiOcsCAF89+lX0dGd8p0/oHnW8W6xQ9f/AFXuBQ0BCGQsr4ZEYUBTzIChKp5HiMaRcwQ0V5RVNSzLxQNPHMShvjS6866zxRiy8HLjaeM5BTB5GuRKEokEampqEI/HEYtNXaRGEARBjJ+n9/fi5h89h8GMPWI9YwDOaggVVRAASOZsHBvMgjOGWECDyoGs4w2JKzU9UzhDVzyHjOUipCtojQXgSq8LpCdhwhFe/cmChhBsITGQ9/fwtdU6Aqvv/C0GM5VTJ7UhDc9+al3ZmpHSeyw6uwoJjTMsbArjovZabDvYX5wJo3GG9oYwLj6rDn88NIDDvSmkbTGitobnPUBytoO0VVlN0RVvoF/BZbXwTAOaguaYAY1zGCpDd9LCijlRfO/GNb7UzKcfegkPPnt0hCOuwuHzfil0J0ECX79u9UnbwY93/abZNARBEMSkcNmSRnzoqsX46u/2IZlzfYtmfVj3BSJA3vm03nM+veWNS/C6s+oQz1r4+H+9iL3dKUg5pF4U5tIonINxhpDC0d3rBSKawtBSE4CicCgKyg57U1WOVfNrsWVPT8XrXzW/dtRApHCPpYqQrnAcG8jgK7/di4zlIhbQEFMYbFeioyuBFw4PQM+fM2v7g42AyjGnJgBVYTg64BSfVak4Ufhfq0wLr4TXLXO0P1usfakP6yNM1j790Ev44fbyXamuAMIBjvqwUVRXZL74dSoLWE95ay9BEARxZvD0/l788JnD0BSebxUNoTGiAwxIZO2ix0cpAVUBY6zofMp9la+FIk6vjTcW1HBWQxAZ00FnPAfLcRHUFLTVhXz27sOHvQGeMrLj8OCo17/j8CAcp7I6UYDnO1SWtUTQFNXxn388gozlojGiw1A5OGPQVQbH9dIuWVuMCES8u5JQFQbTljDzrysBcO6ln8rVAJfb5rUMS9/3O4/GsXVvD3Yc6seDzx4teTYjz5HIuQhpHEHdey9OCzt4giAIghhOqSnYnJpgscBTUzjiWRtCSPQkTYTz5mYFhneh3L/1AFwhsaw5AtMpmU2TT0HUBDV88e0r8eS+HnzzyVcxN6+IDGd4e+ovXupEMmvnLem9zpOC6lL4frRumlJKDcz2d6dxpC+NWMA/rTdtujCd8lUQmgIADLaQ+VSU6/MXYfkgjHNvoN3QdpSt6WgIa6gNGTA0hqMDWdz8o+egcQbbBSzXLXFjLTnRsHP0pmy01CijztM5lVAwQhAEQZw0lUzBAhqHoXJkLRc520HOEkOmXVJiMONN+X28oxu/33MC+/Pn4JwjqAPAUNelZyyWzhuLNeNHzxyGLSTKNWYO/3R/bDADAUBlAGccI606xKjdNEB+Om7K9Ck88ZwFW0jE8oZqUkokTQfdSdO33jN4tSHxrAWgMCfHmyEzovGmcG3lYpky2zTVUzVSpmcWJ6Q3jbfQsuw7tqSRqPRUpiOQtd2K83RONRSMEARBECdNJVMwlh9Rf2wgA9uVyFgODNXrQukczCJru+hPWbjnt0mwfHFmc9RAQBsZYRgKR9yVeO7QAOY3htAcC+DoQMZnzw6Un5bbVhsCR4k3xzDG6qapZGBWE9DzKoSEwiS6826wvmcAYE5NAGFDQc52YTqu1x3EAIVxSEX49i2mUkrd4kaFQUKiM54dstnPe5VIKYv28sP9WQrPGwAsIYrzdEoN0qYKCkYIgiCIk2Y0U7CIoaIxaqA36QUsJ1ImTNstLtqF1IkrPE+N7qSZD2L8TtyDWRuJnI2v/n4fGBiEFEhbLo4MZNAUDYyYlvuBKxYVC00XNoQQCahIZB1wJsDZUNAkpIDjStSENFxz/hzfa0op0Z+2fO6tpa260YCGeXUhdHQnkbXdkZb4AAyVFdNT9REdXYNZ2C7yz8uBPbw4VSJf0SlHbB4OAxDSFGRNF2ZJXYqSN01TFQbXKa+OFLYqDPi3d12I1mhwhEHaVEHBCEEQBHHSjGUKZjkSaxbW4R/Xn42+lIl/ePAFAN5CXQgMGJdwhTf590Qyh8bIUMonmbPRGc9C4Qy1QQ2GqsByBWzXhOm4GEhb4JwV7c+vWNqIrz9x0GvBdb2Om/qwjmTOgeVIqIoo1oo4roTCGd5xURv+92Bf0bXUFgIn4iZ2HU8UvUOSpoUf//FosYVXAZBzxQg1xFA5FA6YtoDCFZiOhK54bbSayuHaArYr0ZXwaloUNjTcznQEXEfmLe+H5vFqitdWZJdEPEa+8LQvbRX34yUzgbyU1FCQVMbCBH99cTvesqL8SJepgoIRgiAI4qQZyxQsYij40FVLcEF7LR5+7hiyZt5FtEShKIy7t1xvfs2JpImmiAHTdXFs0DNTa6sNFi3kA1zB/PogOuM5tNeH8NE3L0VDxEA8a+EzP3sZKdNBXUiHnj/nQMZGTVCD5QrkLBcuPJEgbChoihp49OUu/PLFTmgKw/yGEC5qr8X21waKgYeUQMZ2oHGOhrAO5gj0pMwRaoihcgQ1jsVNUVy8wPMZOdKXRlJKSAE4+SIRjiGhQsILMhzpAnIoO8O5ZwPPOCtuU/JutIWWaSnhc3xVFe4rpjVULz00XFlROcO1q+fhn//i/JN56ycFCkYIgiCISaGcTXy5QW2lxaTDUTiDJgFbeB4aJ1Jmfjgew5waY4RXCWMMdWEdJxI5NEQMnDs3hhu+sx0p0/HVkgS4UvQfuXBODH/xunnojGeRtlw88uIxJHNe4KJxhoztYufRBP74aj+CuoKGsIGo4nWqWI6EYC56UuaIdl2FAWFDhRDIv67E0pYI3rl6HvZ3pzGYsfC1x/djMGsPzZ/xbgJ2PgCDLMylKdwfEAmpaKsNoCthFlWe1pgBxhj6Upb3jPL7okxNjIRnmc85wztXzYPlCJxVH8YHr1gEXZ8ZY1koGCEIgiAmjeGmYOUGtY1VTArGwCHx/ssX4YL5tXi1N417t+xDbbC870VpG2+lrh7vtJ7/yKu9aSxrieIdF7Xhhu9sR8YWaI0FvJSNEHmLec8jxBUSuup5gbhCQGGAIwHHHll06kogpCuIGCpsV+Jgbxr3PLYXG96yDBfNr8OeriQ64zlweDNyCqNTJKSvTrU1ZkBVuK+luTak45/fcT4Gs3bxmQLw2fF/+uGdeKUzAdsRnjqSr391XC/1tbwlir++eH7xHGMZvE0lFIwQBEEQkwrnbFQb8WvOn4PP/XIX4hl71GLSD121GKrKUR/Soat8XBNzK3X1FCgXuBTn4uTzLaYtYbsCKvfSH6YtYblufi6On6DGvZoYV4LDU3Y4YzBUhsaIjt6UhR9tP4IL2muxuzMBR0ioCnwz3IY3zLgSqCtRgAoGbgd70qiPDAVkw5/zp/5kBT72kxfQn7a82puCjwpniBgqGANu+sGOorpSmOEz1Z0z5Zg5YRFBEARxRqCqHDdftRgKZ7DyxmZCCjhCwHK8YtKb84EIMFQcO5CxMXycWqGNd3FzBOfOjfm6esoxPHCxHOF15pQUfrhyaCGXEkiZNk4M8w0BgJqgisawAUcU0iBeq24BBoZoQMORvjQO9WVQG9Dybbt+xUbK8p0yBWxHoDdt4YuPvIJP/ORFfOD7z+KG72zH0/t7fftdtqQRX/mrC7F2YQPqQgYiAQ11IQPLW6LQVY7OeA5hQ0Vz1EDYULG7M4lPPbxzxHmmAwpGCIIgiCnn/Vcsxq1XL0dNSIMQErbrKRM1IQ23Xr0c779icXHfQnFsxFDQlchhMGMhnrUwmLHQlcj5TLrGG7icMycKDi9NNDxwUZiX4hDCSyX1Z+xhDqlefUhNQIfIp1iEAHRFgaH5Aw1d4XDhFZWuXlgPTeHexOCS8KM0m1Ro1S2QMh0cj2fhComQrowZSFy2pBH/8Xdr8O2/vRj/9q6L8M0bVqM2pMEVEi1RA1ICacuBlEBLVEfKdHH/1gO+YGw6oDQNQRAEMSUIIX21JO+9fBFuvGwhfvFSJ44NZtBWG8I1588pW8tw2ZJGvGftfNz3+AEcH8wWu1CiQQ3vWTu/mGoYT1fPjZctwO87etCbNFEfMdAVz6EpqhcVC0PzUi3WsAW6MMROwAsuNIXBtGSx9qU+ovtUD84ZXFfAUDj6UxZEfhrxq71pX11HKYVWXcALnk4kcnBcLxCpCXmW86XFuKXDAMtxsCeNAydSMFSOQ/0ZmM6Q6lOY0FuY4XOyE3pPBgpGCIIgiFPO0/t7i102w2sWxpoFUzj+h88chsKAubVBcMYgpETGcvHDZw7j3Lk1xYCkUlfP2a0RXLygHvc9fmBEu+7xQYmGiA6FeaZrw6fkBlSOurCOZM6G5QoENY7+rAUVQCSgQkqJoJYPohigcs9yvjNugoHhi4/sguMCgITCvICmtK5Dyff56oqCnOMFMPGcjaztQuEMzTEDOUsUZ/UEdO4bBlgIJJ7e34uvPX4AHV1JWPnC1bRpF+3nFT4ULmUsF5YjENTVKZ3QWw4KRgiCIIhTytP7e/Gph3eO8P0opBrufMfKUYsoKw3hA4CaoERnPIcvPdqBjzqi2N47vKsnaqg43J/G3Y92IGO5iAU0xBTPxt0RApbroi+VQ8YWvoJSxoCwpkBVPZVjeWsM166ah4Gsje5EDi2xAOqCGv71d/vQm/IG+YU0z5CtJ5lDKud41usliomE5zgbyvul6ArH8tYorlzWiCf29RYDKNcVUPL1LT1JC6bjlqgaChoiOuySYYBP7+8tFrBKOdShUxpXiZJvGDzDt6zlojbob5meaigYIQiCIE4ZpYFEJd+PsVINo7Xrpi0XGcvFzqOD+NhPXkBQU3xdIivn1SCetdGbNPH9PxxGxnI9Z9dCSkZlaI4aODqQRdry146cMyeGT7xlGfb1pIqBR21Iw4PPDjmwapyhvSGMP79gLp4/OohDvRmkLRcaZ3DFUAqnoEhIeO3DrgAaIzr+6U/PKQZQnDO89/IhC/v+lFe0WnBX5cxzcJWQyNoujg1kURPUihOPN/56N3qSJhhQTAG5QsIdbjefRxa+xjX/5tRCwQhBEARxyhiP78dYNQuV2nVTpoNjA1m40gsiogEVhqoUFZcv/Pl5WNoSRcZysK87hSN9acQCmk+lSOUn7JZOt9UUhr97/UIsaQ7jvq0jUzoa52iMGEVl5dWeNHqTOfzzO1aiJuh16fQmTdz205fAGaDxIXt8Bu972xU40p9FXVj33Xdpu67jCHzul7vgCFmsVZGQvqG+rpRY0RrFzmNx7O1OeedXhxxY2ah9Oh6ulNOepqFuGoIgCOKUMR7fj9JUQznKtetKKdGTzMGVEgpj4JxBVxQENAWtMQPJnIN/3bIPKdMbcBfPWZ6SoXiLtCskuhI5HI/nfIFIe30Q37huNZa1RLDpt/twsCeFoK6iPqwja7uwHAnLcb3X5RwRQ8Xc2gDSlsDXnziIc+fGcOWyJiRNx9tHYWWDMEVhcITA80cGK9737q4kRH5KcEHFGP7fQgjs7krihcODsPNpHX9KaGyEBPpTFIwQBEEQs5RqfD8qUa5dN2cLmI6Awr3F1FAVBHTPgMwREmFDxeG+NPZ3pwF4bbga95SMtOngUH8GiZzje52wruD29Sswrz6IH20/UkzpGCqH7XgOrBr3ajD60yZU7ikZwxUeAGClkUM58tvZKNFCb9qznOfMW6wLIQYDim3JWVugN21Clv6w9GXKnL/QFVQaIyVLphJPBxSMEARBEKeMagzLKuH3GTGRtd3iLBfXleCMoSnvoVHwK9EVBltKxHPeJ/4lLWHMrQuhM57FsXgOTunkW5UjFlBx9pwYls2JYH93ekRKp2iExhnUfFBjOiXnGKbwXDi/tqynCOClWlwhoSkcF86vrXjfg2kbQngmcLrKvS+FF/9b4Z5Z22DaxkXttVA5h+tK33Me3jrsbSw8/6F9hqs3Uw0FIwRBEMQpo1wgIYRXgNmVMH2GZaNRaNddMSeKjOkgnrMBKaGrCubWBhBQOWxHFBdiy5XQGENNwFNcdhwawKu96REtuzVBDUGNIxpQ8e417eCMjUjpAENGaN4gOm+CriOG1J7hCs/Kthosa4l403gdASG9oERI6V0ngGUtEaxsq+ztURfSwPMBB/LFqwW7eTCvOJhzhrqQhpVtNVjemn89kX+9MrIIQ8lE4Lzioo8RFE0FFIwQBEEQp5ThgcSJlImM6WDFnOiYbb3Dz/O9G9fg69etxleuvRAr59UipHtqQWndh4REMmejvSGMObUGvvybDtz6052Il6QiVM4QC6owFIbFzdHiMDvAn9IBPNUgElQQ0FQICQhIsLyXCFBe4eGc4fa3rUBT1PDMz4SA7Qi4QoBzr4Pn9retGDUIa4gYnjrDGBxX+gIax5VgjCEW0NAQMfyvx7xOHkf4B/BxAKrCoCsMqlKYGDx2UDQVUDcNQRAEccoZzzTf8VDabeK6Ap/9n13oSZmIBjToCoPleoFISFew6qxavP8/duBE0iwer3KG6y49C6vn1yNl2agJ6FjSEvbUhjxLWsJobwjjYE8KLTEDar4upClq4Gh/BrYjEdAU6ApD1naLzq7DFZ7CrJhSE7KCp8iHrhp7QN25c2M4Z24MLx0dhO0IWPnUFGeemqGpHOfMjRUDoKHX2489XcmiuVxrzMCxwRxSpgMpvXbjwgC9hrA+ZlA0FTA5ExqMxyCRSKCmpgbxeByxWOW8IkEQBDH7cYVET9JExnLw/OEB/Gj7Ea/9Vnqpmbl1IQQ0jj8c7Pcdt7Q5gluvXo5FTZExX2Pn0TjueawDaUv4LOV7kjmYjkBYV8A5h8bHnn473Aa/miCs1MhMiEJrLwPnQH1Yx1f+6sIRr1vu9f5wsG/CQdHJMN71m5QRgiAI4rQhYznoKfEFuWh+HS5or8X+7jTiOQudgzn85x8PozsxpIYonOG6S+bj3WvmQ63QYlyAMa8G488vakNT1BhhKX/+vFp84IpFRT+R8QQXpWrOycCYN96XscJknvG/3mVLGrFmQf245gBNBxSMEARBEDMeIST60haSuZEtqJwxtNcH8asnOvE/Lx73/WxJk6eGLG4eWw0JaAoaIwb0/AI9WamliVJwr3WFxLKWCExbFmfTGBpDd8Ia0722QLnZQA89f3RURWcqoWCEIAiCmNHkbBc9SRN2Ba+S5w8P4O5H96IrkStuUzjDe9bOx3vWzoc2hhrCGUNdWEdNmfksk6VqTIRS91rOOII6ACjFn4/HvRY4+dlAUwEFIwRBEMSMpNClMlDBnTVru/jGEwfxsxf8asiixjBuvXo5lrZEx3yNkK6iMaKPmb6ZDsbjXhsfw712MmYDTQUUjBAEQRAzDssR6EmZMG237M9fPDKILz3agc74kBrCGfCetfPxN5ecNaYaonCG+rCOaGB6p9WORql7bYArI34+HvfayZgNNBVQMEIQBEHMKOIZG/0Zq6xpV9Z28a0nX8VDzx/zbV+YV0OWjUMNiRgqGiIGlGluZx2Lgnvt7s4kWmPcF0wUVKMVc6KjutdOhroyFVAwQhAEQcwIbFegJ2kiV0ENeemop4YcH/SrIe9aMx/XXXJWsfC0EprC0RDREdJPj6Wv4F77qYd3oith+lqMK3mbDGcy1JWpYEJJsvvuuw8LFixAIBDA2rVrsX379or7XnXVVWCMjfj60z/90wlfNEEQBDG7SORsHBvIlg1EcraL+36/Hx978EVfIHJWQwj3vvsivPfyhaMGIowx1AQ1zKsLnjaBSIGTda+djNlAU0HV78qDDz6IDRs24IEHHsDatWuxadMmrF+/Hh0dHWhubh6x/0MPPQTLGpJ/+vr6cMEFF+D//J//c3JXThAEQZz2OK5XG5K1yqshLx+L40uPduDoQLa4jTPg2ovbccOlC8ZUQwxNyU/eHakKnC6cTIvxZKgrU0HVDqxr167FxRdfjHvvvRcAIIRAe3s7PvzhD+O2224b8/hNmzbhjjvuQGdnJ8Lh8LhekxxYCYIgZh/JnI2+lAVRZhkybRff/t/X8N87jvpm3s6vD+HWq5djxZyhtUBIWTQ9K9i7q5xXbNedak7GgXWyzuvzGckbuI3lHDsZnBIHVsuysGPHDtx+++3FbZxzrFu3Dtu2bRvXOb71rW/hr//6r0cNREzThGkOueclEolqLpMgCIKYwTiuQG/KQsZyyv581/E4vrS5A0eGqSF/tbodf3uZXw3x2cHnF9kFTWF8+I1LsaBxfB94TyXlzMYmIwio9rzTbeA2FlXVjPT29sJ1XbS0tPi2t7S0oKura8zjt2/fjpdffhnve9/7Rt1v48aNqKmpKX61t7dXc5kEQRDEDCVlOjg2mC0biFiOwNe3HsBHfvyCLxBprwvi3/76Ivz9FYtGBCL3PLYXB3tSCOoqGsMGogENB3sy+Kefv4yn9/dOyT1VomA2trszgbChojlqIGyoRbOxiV7fRM9bMHC7clkTVs6rmTGBCDDBAtaJ8q1vfQsrV67EmjVrRt3v9ttvRzweL34dOXJkiq6QIAiCOBW4QuJEIocTiVxxrkwpuzsT+Pvv78CDzx5F4ccMwP9ZNQ//ft0qnDOswFJIiR9tP4KM5aIxoiOkKzA0jpChojVmIGW6uH/rAYgyrzUVDDcbC2gKOGcIaMpJXd+pOu90U1WaprGxEYqioLu727e9u7sbra2tox6bTqfx4x//GJ///OfHfB3DMGAYRjWXRhAEQcxQhg+3K8VyBL637TU8+McjKP3xvLogPrl+Oc5rK2/Etb87jSN9adQENeiqAl7iwTETzLxOldnY6WJiVi1VKSO6rmPVqlXYsmVLcZsQAlu2bMGll1466rH/9V//BdM08Td/8zcTu1KCIAjitEIIiRPJHLri5dWQPV0JfOAHO/Cf24/41JB3rmrDv1+3qmIgAgAJ04YrgbCu+gKRAobCYU+jmdd4zMYmcn2n6rzTTdWtvRs2bMANN9yA1atXY82aNdi0aRPS6TRuvPFGAMD111+PtrY2bNy40Xfct771Lbz97W9HQ0PD5Fw5QRAEMWMZbbid5Qh8/w+H8J/bD/vUkLm1Ady6/uwxP9GHdBXLmqMwVD5jzbxOldnY6WJiVi1VByPXXnstenp6cMcdd6CrqwsXXnghNm/eXCxqPXz4MDj3R2wdHR146qmn8Jvf/GZyrpogCIKYkUgp0Z+2EM/aZX++tzuJuzZ34NXetG/7X7yuDe+7fCECWmU/EJVz1Ed0RPJFmydrlX4qmQwr96k873RTtc/IdEA+IwRBEDMf0/HUEMsZqYbYrqeG/OgZvxoypyaAT65fjgvaa0c9dyyooT6k+zpACl0lKdMta+Y1HofSU8mpur6Zft+ljHf9pmCEIAiCOGlGG263rzuJux7twMEevxry9gvn4v1XLEJwFDVEVzkaI0ZFxWS6zLzGy6m6vpl+3wUoGCEIgiBOOaPZuduuwA+fOYwfPnPYV8DaGgvgH9cvw0Xz6yqelzGGupCGmqA2omtkOKfK4XSymAkOrNPFKXFgJQiCIIgCKdNBX6p8y+6BEynctbkD+3tSvu1/fsFc/P0VixDUK6shAU1BY8QYc+5MgYKZ10zlVF3fTL/vaqBghCAIgqgKISR60yZSuZEuqo4r8J/bj+A//nDIF6S0xAz84/rleN0oaghnbMbMkyGmFgpGCIIgiHEzWsvuwR5PDdl3wq+GXHP+HHzgykUI6ZWXnJCuojGiQ63gn0HMbigYIQiCIMZESomBjI3BMmZarpD4z+2H8R/bDsEpUUOaowY+8dZlWL2gvuJ5Fc5QH9YRDZAaciZDwQhBEAQxKpbjFama9sgi1Vd70/jS5g50dCd92/905Rx88MpFCBuVl5mIoaIhYkCZYUWXxNRDwQhBEARRkXjWRn96ZMuuKyQe/OMRfG/ba7DdoZ81RQx8Yv0yXDyKGqJyjsaoPmrahjizoN8EgiAIYgSukOhJmshYI4tUD/WlcdfmDuzp8qshbzuvFTddtRiRUdSQaEBDQ1ifcS2oxPRCwQhBEATho9KUXVdI/NezR/Cdp/1qSENExyfeugxrF1aePaYpnnnZaC29xJkLBSMEQRAEAK9lty9tIZkbOVfmcF8GX3p0D17p9Ksh689twc1XLUEkUHk5qQlqqA+PHHlPEAUoGCEIgiAqtuy6QuKnzx3Ft5561a+GhHV8/K3LcMmiymrIWFbuBFGAghGCIIgzmNFado/0Z/ClRzuw63jCt/2t57Tg5jcurtiOW42VO0EAFIwQBEGcsViOwIlkbsSUXVdIPPT8MXzrqVd9P6sP6/jYuqV4/SiD2Kq1cicIgIIRgiCIM5JKU3aPDmTwpc0deHmYGrJuRTNueeMSxCpYtZOVO3EyUDBCEARxBmG7Aj1JE7lhBmZCSjz8/DF888lXYZaoIXUhDR9btwyXL62shoR0FQ0RHRpZuRMThIIRgiCIM4REzkZ/yoIYpoYcG8zi7kc78NLRuG/7G5c34R/etBQ1ofJqx5lg5S6ExK7jCfRnLNSHdJw7N1a1R8pknGMqzzsdUDBCEAQxy3Fcgd6UNcLATEiJn79wHN944iByJWpIbVDDR9ctxRXLmiqe80ywcn96fy/u33oAB06kYLsSmsKwuDmCm65cjMtGqZuZ7HNM5XmnCyaHJwxnIIlEAjU1NYjH44jFYtN9OQRBEKcNKdNBX2qkgVln3FNDXjjiV0OuWtaEf3jzEtSG9LLnUzlHQ0QfdebMbODp/b341MM7kTId1IV06AqH5QoMZGxEDAV3vmPlmIv+ZJxjKs97Khjv+j27f5sIgiDOUISQ6E2ZSJkj1ZBfvNiJrz9xADl7SA2pCWr4yJuX4qrlldWQM8XKXQiJ+7ceQMp00BoLFNuTA1xBa4yjK2Hi/q0HcMmihorPYjLOMZXnnW4oGCEIgphlZC3PwMwR/pbdrngOd/+mA88fHvRtv2JpIz6ybinqKqghZ5qV+67jCRw4kUJdaKRrLGMMtSENB06ksOt4Aivn1Zyyc0zleacbCkYIgiBmCVJ6du6JrD1i+y9e6sTXtx5EtqSLJhZQi2pIJXOyM9HKvT9jwXYl9ArdQYbCERcS/WWM4ibzHFN53umGghGCIIhZQCU7965EDv/yaAd2DFNDLl/SiI+uW4r6cGU1pCl6Zlq514d0aAqD5QoE+Mj7N10BjTPUV1CSJuscU3ne6YaCEYIgiNOYSnbuUko8srMLD2w9gIzlV0M+/KaleNPZ5dUQxhhqgxpqQ2eulfu5c2NY3BzB7s4kWmPc9xyklBjM2FgxJ4pz51YuyJyMc0zleacbcqghCII4TbEcgWOD2RGByIlEDrf+dCfueWyvLxB5/eIGfPtvL8abVzSXDTQMTUFbbRB1Z1haZjicM9x05WJEDAVdCRNZ24UQElnbRVfCRMRQcNOVi0ctEJ2Mc0zleacbau0lCII4DSln5y6lxOaXu/C1xw8gXRKERAMqbnnjEqyrEIQw5sn6lczNzlR8Xh5CQuMn6TMywXNM5Xknm/Gu3xSMEARBnEZUsnPvSZr4l990YPtrA77tlyyqx4a3LENjxCh7vqDuDbYjK/fykAPryUE+IwRBELOMcnbuUko8uqsb9z2+H2lzKECJGCpueeNivOWclrJqCGcM9REdsVls5T4ZcM5OukV2Ms4xleedDigYIQiCmOFUsnPvTZm457G9+MPBft/2tQs9NaQpWl4NCRsqGsI6VFJDiBkCBSMEQRAzmHJ27lJKPPZKN+79/QGfw2pYV3DzG5dg/bnl1ZAzxcqdOP2g30iCIIgZiCsk+srYufelTNzz2D5sO9jn275mQR0+/tblFdWQWFBDfWj2W7kTpycUjBAEQcwwMpaD3qTls3OXUmLLnhP46u/2I5nzqyE3XbUYbzuvtawaciablxGnDxSMEARBzBCE8Ozckzm/nXt/2sJXHtuL/z3gV0NWn1WHT7x1GZpjgbLnOxOt3InTkwlVL913331YsGABAoEA1q5di+3bt4+6/+DgIG6++WbMmTMHhmFg2bJl+NWvfjWhCyYIgpiN5GwXxwazvkBESoktu0/g7777R18gEtIVbHjLMtz1lyvLBiKawjG3NoiGiEGBCHFaULUy8uCDD2LDhg144IEHsHbtWmzatAnr169HR0cHmpubR+xvWRbe8pa3oLm5Gf/93/+NtrY2HDp0CLW1tZNx/QRBEKc1Ukr0py3EsyPVkH/dsg9P7uv1bX/d/Fp8Yv1ytJYJQsjKnThdqdr0bO3atbj44otx7733AgCEEGhvb8eHP/xh3HbbbSP2f+CBB3D33Xdjz5490LTx9bObpgnTNIvfJxIJtLe3k+kZQRCzCtPxhttZjn+43eMdJ/CvW/b7ApSAxvHBKxfjmvPnlA00AppnXqar1K5LzBzGa3pW1W+tZVnYsWMH1q1bN3QCzrFu3Tps27at7DH/8z//g0svvRQ333wzWlpacN555+HOO++E67pl9weAjRs3oqampvjV3t5ezWUSBEHMeAYzFo4P5nyByGDGwv/9xS58/pe7fYHIRfNr8e0bLsafXTB3RCDCGUNj1MDc2iAFIsRpS1Vpmt7eXriui5aWFt/2lpYW7Nmzp+wxBw8exO9+9zu85z3vwa9+9Svs378fH/rQh2DbNj772c+WPeb222/Hhg0bit8XlBGCIIjTnUp27lv39uBff7sPg8PUkL9/wyL82YVzwcuoIWReRswWTnk3jRACzc3N+Pd//3coioJVq1bh2LFjuPvuuysGI4ZhwDDK98oTBEGcrpSzc49nbPzb7/bh9x09vn0vmFeDf1y/HHNrgyPOo3CGhoiBCJmXEbOEqn6TGxsboSgKuru7fdu7u7vR2tpa9pg5c+ZA0zQoylCP+4oVK9DV1QXLsqDr+gQumyAI4vTBFRK9KRPpYQZmT+zz1JCBTIkaonK8/4pF+PMKakgkoKIhbEAh8zJiFlGVtqfrOlatWoUtW7YUtwkhsGXLFlx66aVlj3n961+P/fv3Q5SY9+zduxdz5syhQIQgiFlP2nRwdCDjC0TiWRtffGQ3/u//vOILRFa21eAbN6zGOy5qGxGIaArHnJogmqMBCkSIWUfVGt+GDRtwww03YPXq1VizZg02bdqEdDqNG2+8EQBw/fXXo62tDRs3bgQA3HTTTbj33nvxkY98BB/+8Iexb98+3HnnnfiHf/iHyb0TgiCIGYQQEr1pE6mcXw353/29uOexvb4gxFA53veGhWWDEGB2W7kLIbHreAL9GQv1IR3nzo2Nep/V7n+6MdvvrxJVByPXXnstenp6cMcdd6CrqwsXXnghNm/eXCxqPXz4MDgfElza29vx6KOP4mMf+xjOP/98tLW14SMf+QhuvfXWybsLgiCIGUTW8lp2S+3cE1kb9/5+P367+4Rv33PnxnDr1csxry404jyz3cr96f29uH/rARw4kYLtSmgKw+LmCG66cjEuW9J40vufbsz2+xuNqn1GpoPx9ikTBEFMJ5UMzJ4+0It7HtuH/rRV3KarHO99/QL8xevmlU271IZ01M1i87Kn9/fiUw/vRMp0UBfSoSscliswkLERMRTc+Y6VvgW42v1PN2br/Y13/aZSbIIgiEnAdFycSJiw3SE1JJmzcd/vD+A3r/iL/s+ZE8Mnr16O+fUj1RBd9dQQQ52dagjgpSLu33oAKdNBayxQDLgCXEFrjKMrYeL+rQdwyaIGcM6q3v90Y7bf33igYIQgCOIkGcxYGMjYKBWa/3CwD//y2F70pYbUEE1h+LvXL8Q7V41UQxhjqAtpqAnOXjWkwK7jCRw4kUJdaOQQP8YYakMaDpxIYdfxBFbOq6l6/9ON2X5/44GCEYIgiAlSzsAslXNw3+P78eguvxqyYk4Ut64/G/MbRqohZ5qVe3/Ggu1K6BXM2gyFIy4k+jPWhPY/3Zjt9zceKBghCIKYAOUMzJ55tQ//8pu96B2mhtx42QL8n9XtI9QQhTPUhXXEAuOb2zVbqA/p0BQGyxUI8JHpKNMV0DhDfUif0P6nG7P9/sYDBSMEQRBV4LgCvSkLGWuoZTdlOrj/8QP49ctdvn2Xt0Zx69XLsaAhPOI8EUNFQ+TMNC87d24Mi5sj2N2ZRGuM+1ITUkoMZmysmBPFuXNjE9r/dGO23994ODM0QYIgiEkgZTo4Npj1BSJ/fK0f7/3us75AROUM77t8Ie5910UjAhGVc7TEAmiOnbnmZZwz3HTlYkQMBV0JE1nbhRASWdtFV8JExFBw05WLi8Wa1e5/ujHb7288UGsvQRDEGJSzc0+bDh7YehCP7Oz07bu0OYLb3nY2FjaWUUPIyt2Hz1dDSGi8Cp+Rcex/ujEb72+86zcFIwRBEKOQMh30pUy4YuhP5Y5DA7j70Q6cSJrFbSpnuO7Ss/Cui9tHTNFVOUdjVEdIp8z4cMiB1c9suz/yGSEIgjgJXCHRlzKRKlFDMpaDr289iF+85FdDljRFcOvblmNxU2TEeWazlftkwDmrql212v1PN2b7/VWCghGCIIhhZCwHvUnLZ+f+3KEB3P2bDnQnhtQQhTNcd8l8vHvN/BFqyGy3cieIyYSCEYIgiDzlhttlLRf//sRB/PzF4759FzeFcevVZ2NJ80g1pCaooT480sCKIIjyUDBCEAQBL+joTfnt3F84Moi7H+1AZzxX3KZwhvesnY/3rJ0PbZgaoqscjRFSQwiiWigYIQjijEZKib60hUTJcLus7eIbTxzEz17wqyGLGsO49erlWNoS9W0/k6zcCeJUQMEIQRBnLDnbRU/Sr4a8eHQQX9rsV0M4A96zdj7+5pKzRqghZ5qVO0GcCigYIQjijENKiYGMjcGSWR8528U3n3oVDz93DKV+BwsaQrjtbWdjWRk1pD6koyZ0Zlm5E8SpgIIRgiDOKHK2VxtiOUNqyMvH4rhrcweODWaL2zgD3rVmPq675KwRqkdAU9AUNUaoJARBTAwKRgiCOCOopIZ8+39fxU93+NWQsxpCuPXq5Ti71W/SRGoIQZwaKBghCGLWU6425OVjcXzp0Q4cHfCrIdde3I4bLl0wQg0J6l5tCKkhBDH5UDBCEMSspZwaYtouvvP0a/ivZ4/61JD59Z4asmKOXw1ROEN9WEc0QGoIQZwqKBghCGJWYjqeGlJaG/LK8QTu2rwHR4apIX+1uh1/e9lINSRsqGgI6yPcVQmCmFwoGCEIYtYxmLEwkLFRmANqOQLfffo1/OTZIyiZd4f2uiBuvfpsnDN3pBrSEDEQMehPJEFMBfQvjSCIWYPlCPSkTJi2W9y2pyuBu37dgUP9meI2BuCdq+bh716/AMYwt9SIoaIhYkChwXYEMWVQMEIQxKwgnrXRn7Z8ash/bHsNP/6jXw2ZVxfEJ9cvx3lt/smoKudoiOgIkxpCEFMO/asjCOK0xnE9NSRrDakhe7uT+H+/3oPX+vxqyF+8rg3vvXzhiNkxkYCKhjCpIQQxXVAwQhDEaUsiZ6M/ZUHk1RDbFfj+Hw7hR88c9qkhc2sD+OT65Th/Xq3veJVzNEZ1hHT6U0gQ0wn9CyQI4rTDdgV6y6ghX9rcgYO9ad++f3FRG977hoUIDlNDogENDWEdnNQQgph2KBghCOK0Ip6x0Z8Zqg2xXYEf/uEwfvDMIZ8aMqfGU0MuaK/1Ha8pHI0RA0HdH5wQBDF9UDBCEMRpge0K9CRN5Eo6ZfafSOGuzXtwoMevhvz5hXPx929YNCLgiAU11IdIDSGImQYFIwRBzHjiWRsDaX9tyA+fOYwfPnMYbokc0hoL4BPrl+F18+t8x2sKR1PUGFG4ShDEzICCEYIgZizlOmUOnEjhrs0d2N+T8u17zQVz8IErFo0oRq0N6agLaWCM1BCCmKlQMEIQxIxkeKeM4wr85/Yj+I8/HPKpIc1RA/+4fjlWneVXQ3TVqw0hNYQgZj4UjBAEMaNwXIHelIWM5RS3Hezx1JB9J/xqyP93vqeGlBqVMcZQG9RQS2oIQZw2TGj603333YcFCxYgEAhg7dq12L59e8V9v/vd74Ix5vsKBAITvmCCIGYvyZyNowPZYiDiCokf/OEQPviD53yBSHPUwF1/uRIb3rLMF4gYmoK5tQHUhXUKRAjiNKJqZeTBBx/Ehg0b8MADD2Dt2rXYtGkT1q9fj46ODjQ3N5c9JhaLoaOjo/g9/ZEgCKIUV0j0pkykzSE15NXeNL60uQMd3Unfvn+yshUfvHKxb4gdYwx1IQ21IX3KrpkgiMmj6mDknnvuwfvf/37ceOONAIAHHngAjzzyCL797W/jtttuK3sMYwytra0nd6UEQcxK0qaD3pRZrANxhcSDfzyC7217DbY7VBvSFDHwifXLcPGCet/xAU1BY8SArk5I6CUIYgZQVTBiWRZ27NiB22+/vbiNc45169Zh27ZtFY9LpVI466yzIITA6173Otx5550499xzK+5vmiZM0yx+n0gkqrlMgiBOA4SQ6E2bSOWG1JDX+jw1ZE+XXw1523mtuOmqkWpIfUhHTUibsmsmCOLUUFUw0tvbC9d10dLS4tve0tKCPXv2lD1m+fLl+Pa3v43zzz8f8XgcX/7yl3HZZZdh165dmDdvXtljNm7ciM997nPVXBpBEKcRWctFb8qE7QoAnhryX88ewXee9qshDREdH3/LMlyyqMF3vKEpaCI1hCBmDae8m+bSSy/FpZdeWvz+sssuw4oVK/D1r38dX/jCF8oec/vtt2PDhg3F7xOJBNrb20/1pRIEcYqRUqI/bSGetYvbDvdlcNeje7C706+GrD+3BR+6ajGigSHlg9QQgpidVBWMNDY2QlEUdHd3+7Z3d3ePuyZE0zRcdNFF2L9/f8V9DMOAYRjVXBpBEDOcnO2iJ+lXQ3763FF866lX/WpIWMeGtyzDpYtJDSGIM4Wq/lXruo5Vq1Zhy5YtxW1CCGzZssWnfoyG67rYuXMn5syZU92VEgRxWlJQQ44PZouByJH+DD764At4YOtBXyCybkUzvnXDal8gwhhDQ9hAW22QAhGCmKVUnabZsGEDbrjhBqxevRpr1qzBpk2bkE6ni901119/Pdra2rBx40YAwOc//3lccsklWLJkCQYHB3H33Xfj0KFDeN/73je5d0IQxIyjnBry0PPH8K2nXoXliOJ+9WEdH1u3FK9f0ug7ntQQgjgzqDoYufbaa9HT04M77rgDXV1duPDCC7F58+ZiUevhw4fB+dAfjoGBAbz//e9HV1cX6urqsGrVKjz99NM455xzJu8uCIKYUZSrDTk6kMGXNnfg5eP+7rg3n92MW960BDVBqg0hiDMVJqWUY+82vSQSCdTU1CAejyMWi0335RAEMQrD1RAhJR5+/hi++eSrMEvUkLqQho+uW4Y3LCU1hCBmK+Ndv2k2DUEQk0I5NeTYYBZ3P9qBl47Gffu+cXkT/uFNS33KB6khBHHmQsEIQRAnTTk15GfPH8c3nzyIXIkaUhvU8NF1S3HFsibf8eSiShBnNhSMEAQxYcqpIcfzasiLw9SQK5Y14qNvXuqbH0NqCEEQAAUjBEFMkHJqyC9e7MTXnziAnD2khsQCKj66bimuWu4fpBnQFDRFDWgKqSEEcaZDwQhBEFUhhER/xkKiRA3pSuTw5Uc78NzhQd++b1jaiI+8eSnqw0NqCGcMdWHd1z1DEMSZDQUjBEGMm+FqiJQSv3ypEw9sPYis7Rb3iwVU/MObl+KNy5vAGCtuD+kqGiM6VFJDCIIogYIRgiDGpJwa0p3I4cu/2YsdhwZ8+75+SQM+tm7ZCDWkIaL75swQBEEUoGCEIIhRGT5hV0qJX+3swv1bDyBjDakh0YCKD79pCd58djOpIQRBVAUFIwRBlKWcGnIikcO/PLYXf3zNr4ZctrgBH1u3FA2RoQGXCmeoD5MaQhDE2FAwQhDECMqpIZtf7sLXHj+AdIkaEjFU3PKmJXjLCr8aEjZUNIRJDSEIYnxQMEIQRBEhJPrSFpK5ITWkJ2niXx7bi+2v9vv2vWRRPTa8ZRkah6khDREDEYP+tBAEMX7oLwZBEADKqyGP7urGfY/vR9ocUkPChoJb3rgEbz2nxaeGRAwVDREDCmcjzk0QBDEaFIwQxBlOOTWkN2Xinsf24g8H/WrImoX1+PhblqEp6ldDGiMGwqSGEAQxQeivB0GcwZRTQx7bfQL3/m4/UqZT3C+sK/jQVYtx9XmtfjUkoKIhTGoIQRAnBwUjBHEGIqWnhpR2yvSlTNzz2D5sO9jn23f1WXX4xFuXoTkWKG5TOUdjVEdIpz8hBEGcPPSXhCDOMMq5qG7ZcwJf/d1+JHNDakhIV3DTlYvxJyv9akg0oKEhrIOTGkIQxCRBwQhBnCFIKTGQsTGYsYrb+tMWvvLbvfjf/X41ZNX8Wnxi/XK0lKghmsLRGDEQ1JUpu2aCIM4MKBghiDMAyxE4kczBcobUkN939ODftuxDokQNCWoKbrpqEf505RxSQwiCmDIoGCGIWc5gxsJAxoaUEgAwkLGw6bf78OS+Xt9+F82vxT++dTlaa0gNIQhiaqFghCBmKZYj0JMyYZZM03284wT+dct+xEsKVwMaxweuWIxrLpgDXqKGxIIa6kOkhhAEceqhYIQgZhlSSsSztk8NGcxY2LRlH57Y61dDLmyvxT+uX4Y5NcHiNlJDCIKYaigYIYhZhOl4nTKF2hAA2Lq3B//6230YLFVDVI6/v2IR/uzCuaSGEAQx7VAwQhCzgEKnTDw7pIbEMzb+7Xf78PuOHt++58+rwT+uX462Wr8a0hQ1ENBIDSEIYuqhYIQgTnOG+4YAwJP7erHpt3sxkBlSQwyV4/1vWIi3X9TmU0OoU4YgiOmGghGCOE2RUqI/bfmKUeNZG1/93X78bs8J374r22L45Pqz0VY3pIao3FNDqDaEIIjphoIRgjgNKaeG/O/+Xtzz2Eg15L2XL8Q7LmrzzY+JBFQ0hg1SQwiCmBFQMEIQpxFCSPRn/DNlElkb9/5+P36726+GnDs3hk+uX472+lBxG82UIQhiJkJ/kQjiNKGcGrLtQB/+5bG96E8PWbzrKsffvX4B/vJ18/xqiKGiIUITdgmCmHlQMEIQM5xytSHJnI37fn8Av3ml27fvOXOi+OTVZ2N+iRqicIbGiIGwQf/cCYKYmdBfJ4KYwZRTQ/5w0FND+lJDaoimMPzd6xfinatIDSEI4vSDghGCmIGUm7Cbyjn42uMHsHlXl2/fs1ujuPXq5TirIVzcRmoIQRCnE/SXiiBmGOVcVLe/2o8v/6YDvcPUkL+9bAH+anU7qSEEQZzW8IkcdN9992HBggUIBAJYu3Yttm/fPq7jfvzjH4Mxhre//e0TeVmCmNVIKTGQtnB8MFcMRNKmgy//pgO3PbTTF4gsb4nigb9ZhXetmV8MOhTO0BwLoDkWoECEmBKEkNh5NI6te3uw82gcQsjpvqRZS7lnPZuef9XKyIMPPogNGzbggQcewNq1a7Fp0yasX78eHR0daG5urnjca6+9hk984hN4wxvecFIXTBCzkXJqyLOv9ePLv9mLE0mzuE3lDDdcdhb++uL5voAjpKtojOhQlQl9viCIqnl6fy/u33oAB06kYLsSmsKwuDmCm65cjMuWNE735c0qyj3rhogOAOhLWbPi+TNZGGQxTtauXYuLL74Y9957LwBACIH29nZ8+MMfxm233Vb2GNd1ccUVV+Dv/u7v8OSTT2JwcBA/+9nPxv2aiUQCNTU1iMfjiMVi1VwuQcx4BjOWb8JuxnLwwNaD+OVLnb79lrVEcOvVZ2Nho782pD6sIxrQpvSaiTObp/f34lMP70TKdFAX0qErHJYrMJCxETEU3PmOlaflgjgTKfesB7MWOuM5AMCcmiBqg9qMff7jXb+r+hhlWRZ27NiBdevWDZ2Ac6xbtw7btm2reNznP/95NDc3473vfe+4Xsc0TSQSCd8XQcw2LEfg2GAW/WmrGIg8d2gA7/3es75AROUMN75+Ae5910W+QCRsqGirDVIgQkwpQkjcv/UAUqaD1lgAAU0B5wwBTUFrzEDKdHH/1gOndcpgplDuWTPmjX1gDGDI/zfHaf/8q0rT9Pb2wnVdtLS0+La3tLRgz549ZY956qmn8K1vfQsvvPDCuF9n48aN+NznPlfNpU0aQkjsOp5Af8ZCfUjHuXNjZJk9C5hp72s8Y6M/Y/nUkK8/cRC/eNGvhixpjuDWq5djcVOkuE3hDA0RAxHqlCGmgV3HEzhwIoW6kA7G/P+GGGOoDWk4cCKFXccTWDmvZpqucnZQ7lnnbAHTEVC5pyWYjoucJRDUldP6+Z/Sv2bJZBLXXXcdvvGNb6CxcfyS0e23344NGzYUv08kEmhvbz8Vl+iDcqCzk5n0vlqOQG/KRM52i9ueOzyALz+6F12JXHGbwhmuu2Q+3r1mvq8OhDpliOmmP+PVKOgV6pMMhSOeH1tAnBzlnrUjBKQEGAPAACm8bYA38PJ0ff5VBSONjY1QFAXd3X7Xx+7ubrS2to7Y/8CBA3jttddwzTXXFLcJ4RXoqaqKjo4OLF68eMRxhmHAMIxqLu2kqZQD3d2ZxKce3jmjcnDE+JlJ7+twNSRrufj3Jw7i5y8e9+23qCmM264+G0ua/WoI+YYQM4H6kA5NYbBcgQAfOfHZdAU0zlAf0qfh6mYX5Z61yjkYAyQA5IOSgkoCnL7Pv6qaEV3XsWrVKmzZsqW4TQiBLVu24NJLLx2x/9lnn42dO3fihRdeKH792Z/9Gd74xjfihRdemBK1YzxQDnR2MlPeV9sVOD6YRV/aLAYiLxwZxPv+41lfIMIZcP0lZ+H+97zOF4hEAirm1YUoECFmBOfOjWFxc8RXdF1ASonBjI3FzRGcO5eaDU6Wcs86oHEYKocjBBxXwFAVBHRvKT+dn3/Vf902bNiAG264AatXr8aaNWuwadMmpNNp3HjjjQCA66+/Hm1tbdi4cSMCgQDOO+883/G1tbUAMGL7dEI50NnJTHhfEzkb/SkLoqCG2C6+8cRB/OyFYWpIYxifvHo5lrVEi9tIDSFmIpwz3HTlYnzq4Z3oSpioDWkwFA7TFRjMd3PcdOViqrWbBCo961hQQ8byUr01QQ1SADnXPa2ff9V/5a699lr09PTgjjvuQFdXFy688EJs3ry5WNR6+PBhcH56eR1QDnR2Mp3vq+MK9KYsZCynuO2lo4O4a3NHsSUP8NSQd62Zj+suOQu6OnSdYUNFI9WGEDOUy5Y04s53rCzWYsWFhMYZVsyJUo3dJFPpWReUj76UhRMp87R//hP6yHXLLbfglltuKfuzxx9/fNRjv/vd707kJU8pszUHOhM6SKbzGqbrfR2uhuRsF9986lU8/NwxlIraCxpCuPXqs7G8dUgN4YyhPqIjRu26xAznsiWNuGRRw7T/jTkTqPSsAcya50/6L4bycrs7k2iNcZ+kX8jBrZgTPa1ycDOhg2S6r2Gq31fb9TplstZQp8zOo3F86dEOHBvMFrdxBvz1xe24/tIFPjUkoCloihrQyEWVOE3gnFHqeoqo9Kxny/Onv3oYystFDAVdCRNZ24UQElnbRVfCPO1ycIUOkt2dCYQNFc1Rr+6g0EHy9P7eM+IapvJ9jWdtHBvIFgORnO3ia4/vx0cffMEXiJxVH8JX33UR3veGRcVAhDGGhrCBubVBCkQIgjgjob98eQp5uRVzosiYDk6kTGRMByvmRKtu/5zO4UUzoYOk9BpaYgakBNKWAymBlpg+pd1Jk/m+lsNy8p0yKbOYltl1PI6///4O/PeOobRMQQ35+nWrsGLOkBKjqxxzawOoCVFahiCIMxdK05QwGTnQ6U5NzIQOksI1GKqCQ31ZmI5bNOkxVAU1wantTjoVuW0pJeJZ29dyZ9ouvvP0a/ivZ4/6akPm14dw69XLfUEIANSGdNSFtBHvE0EQxJkGBSPDOJkc6Eww2JoJnUH9GQtpy0XGdCDhtagyDkjppS9M20XIUKe0O6nS+zqRAttyE3Z3dybw/369B0cGhlIyDMBfrZ6Hv71sAQxtqIBWUziaogYC2siiWoIgiDMRCkYmieHpkcKn3QBX0Brj6EqYuH/rAVyyqOGU1p7MhM6g2qCGnO1CSAlN5WDw7pcxgCmA7QjkbBe1welNTVSrYkkpMZCxEc8OqSGWI/Ddp1/DT549gtKs07y6ID65fjnOa/MHQLGghvqQftrUHxEEQUwFFIxMEtOZHin9dF8b1LCoKYw9Xalp7QwqGjNKAKWPQw77+Tg4Fe3BBRUrmbMR0lVoCoeQEq8cT5RVsXK2p4bY7pAasqcrgbt+3YFD/ZniNgbgnavm4e9e71dDVM7RGNUR0umfHEEQxHDoL+MkMV3pkXKf7hsiOhSOaXNHHMzaCGoKsraELSRU7i3SEoAjJBTOENQVDGbtCd3fydbgFFSs/rQFV0gkcrliTYuucNiuLKpYgPfeJkqu1XIE/mPba/jxH/1qSFutp4YMDzYjARWNYYPUEIIgiApQMDJJTEd6pFKNSmfchMKBOTUG+lLWlLsj1od0hA0FkYCCeNaG6QxNmQxqnpUxJMZ8FqeqBmfX8QReOR73Wn0loHJWHDyVcwQ4E3jleBw7Dg2gtSbgU0P2difx/369B6/1+dWQv3hdG957+UJfHQjZuRMEQYwP+it5EoxMj0Swp2tyDLbGSk2Mp0alJqjji29ficGsPaXufKVmY2fVh2A6Eo4QUDmHoTJ0J60xn8WprMHpTZtI5ByvpoUPvVcMgMYByxWIZ23s70mhIeIFTLYr8P0/HMKPnjnsU0Pm1gbwyfXLcf68Wt9rRAwVDSdp5z4THHQJgiCmAgpGJsipTI+MJzUxnhqVgz0pcMZw5bKmU/IMKlE63Kk7aaE2pCGsqzBdge6kNa5ncSprcAbTNoSQ4JyVbavlDBACxdTM3u4kvrS5Awd707793nFRG973hoUIDlNDGiIGIiephkx3izhBEMRUQsHIBChNHwQ1BarCICXQGc9B4eyk0iPjTU3MhBbe0TjZQVrjuj9X4rlDA1UrB3UhDZwzCCEhuQQDK3bHCEgIAXAOhHUF3/3f1/DD7Yfhlsgh9SENN1y2EH96fit4STAzWcPtZkKLOEEQxFRCwUiVFNIHAxkLjivzbZ5DxY+qwlAT1CaUHqkmNTGdLbzjTR9MxGyscO5X8yqE6boI8pG/poNZG4mcja/+fh8YWFXKQUPEQCygIZ614bgSnEmAeR0+Qsh8bYuKB544iKMlviGAV/MipMQP//AantjXg3evaceqs+rRENERPYnhdo4j8IuXOnF0II1fvNSFVM5Ba830tYgTBEFMJRSMVIlX/JhA2vRmkJQaepmOgOkAuzuTE0qPVJOamK7hfqOlDyoFHuNNo5Se23IEEjkHg1kLbbVB30KfzNnojGehcIbaoAZDVapSDs6dG8M5c2N48cgAbFfCdgWk8AJKTWEQEkiaDpKmUzxG4QxBjaMhbEBTGGxX4mBPCl95bC82/sX5WNAYnvAz/cYTB3Df4weQzNpw8wIMZ4CaN0crMFUOugRBEFMNBSNV0pcykch5pleVDL0SORt9KbPqc1eTeimty5iqFt7R0gcf+8kLaI566amJ1DgMP3ddiMPQLHTGczjcn8GcmiBqgxpM1y0OnmurDSKY9+2oRjngnOFvL12AO3pSyFguaoIaGPNadgczQwFBgcaIDscVaIoaxffb0Bha9QB6Uhb+/cmDeP2Sxgk96288cQB3be6AKyRUhYFLCVsAQgJdiRwA+AKS6U6/EQRBnApoUF6VDGRKih8xTL0AK9YiDGTG9tAYTmnqpRzDUy+neghcKaMN4IsYCnqSJnZ3JsA5ENIVKJwVDcTGmtBb6dz1YQPz60NQOENvysSJpIl4xgEDw5yawIi0SEE52N+dxM9fOF52UKErJLoTOSxsCmPDW5ZhUVMEriswkLHRl/YHIs1RAx9501JwADVBvfh+c87yKTnuUyqqxXEE7nv8AFwhoasMKufgnPt+q3pSZrGeBZgaB12CIIiphpSRKqkN54sfpYSUckR6REgvUKkNV18/MJHUy6kYAleOSikkKSV6UyYgAUcCXXFPESpnIFbpmkZLT0UDGubXM8SzNm554xJIBty7ZR9qg+UXY9sR6E1b+OIjr4Azfy3J+e216EuZxWLUi+bXIRbU8IVf7kZP2h88/n/nz8EHrliEVzoTsIVETGEA85xUSwtUKykV46mr+cVLnUhmbU8RYd7nApZ/doX4wxUSg1kbdSF9Sh10CYIgphIKRqqkMWwgFlCRyDll3UU5Y4jlHTerZaKpl5MZ7jdeKqWQcrbwzMNKtqmcjTAQG63GYaz0VEBVkGAOFjSFUR/Soau8bOFuynRwPJ6FKyRCuoJYQIPlCrxyPIFP/vRFfGzdMlw0vw6At8g/+Mcj+N6212CXyCHNUQMff+syXLygHgBQE9ChcQZHSIQ1xdc9A5RXKsbblntsMAMBQC05JWOeQmK7ojj513JcZG13yhx0CYIgphoKRqrEK36swYtH4nCFgOUOuYsGVA6Fc5wzt2bC5maXLGo4qZbYiTLWJ/lK3Tu266I0q6TkvTsKBmK28ApRe9OVa2iq6QyqpB5JKXEikYPjeoFITUjzumzAUR/W0Zsy8aPtR3BBey0O92dw1+YOdHQlfa/zJ+e14oNXLfZ5hCxpCWNRcwT7ulMI6woGsjZsV0BTOGoC6gilYqy23C/82XnoTVs4NphB52AODF59SGls4SkvQwFJMudCShtnt0bxoavIZ4QgiNkHBSNVUqpeJHMO6sI6FMbgSoms5SIaUCfF3Ox7N66ZMvfN8XySrxQElAYinHlBWQHGGDjzamgG05VraKpJT1VSj+I5G1nbhcIZmmMBQHqBkBASDF6653BvCvf97gB+ufO4Tw1pjOj4+FuXYe3CBt91afluln9401Lc/KPn8EpnEqW1rccA1Ia04vs9Vmv2q71p3Pi9P3r+JgxgEhAAhCvBmSimagr3XXgtjTN431UxXZAgCOI0ggpYJ0ChcPScuTEIIZGxXQghcc7cWMXCUSEkdh6NF4sqn9rXg089vBO7OxMIGyqao94Mk8In6D8c7MPKeTW4clkTVs6rOaWByKce3olXjsehcFax+LQQBEQMBV0J00vNCAlXDkUjKue+ol4JWSz2rQtVrqGpdO6s7aIrYSKsc6w/txVP7u/FzqPxono0vHBX4QxtdUEENa/Vt7RwVUqJvoyNh1845gtE1p/bgm/fcPGIQCQa0NBWG0RAU7DreNzzkxl23RJAPGvj5WOD2Hk0ju9vO4TdnQnUBrURtS+9KQtpy/VSeRzQFQZFGdqnYJkvpIDturDz194Y1tFeH0JdSMeertS4CoIJgiBON5iU1Qxznx4SiQRqamoQj8cRi01P4V65NAaAcakX5ZSHQgAzvz40QgnoSphYMSeK79245pTWBgghccN3tuPFI4NwhfSlnHTFSzld0F7juw7fvQiviDeetfNmYSyfpvEKMAuFojVBDd+9cY2vZqTc8/zDwT7fuTXOirNhyrUMlxbu9qcsfGnzbgQ0BZriVxhOpEzEsw5K0RSGGy49C+9ee5Zv+/Dhdo4jsPrO3yKesaEpAGO8+IykFLBcr0amKWogY7lI5ryJxc2xQDHdI6XE7q5k8Xl4z9Z7nkIKmI63neeH9UnPgw3NMQPN0YDvXqbqd4MgCGIyGO/6TWmacXAyc0LK1RAkcjYSWRsKZ0hbrq9GYSqNrcY7vbb0OoZ379QGNdz9aAd2HhuE4+YDmryBmKF6jrTnzI35amjGm5460p/BN548iPQ4bNEHMxZ++MwhHOhJoTHiteFajsDxeBbWMOOQsO5Z+P/65S6smBMrFrWWs3Mv7XhReD7Iyf/YlRyAgCO8LqqGsI60aSNnuzg2kEVbXRARQ8Vg1i4GIoVumQKccWiKgOtKvOvi+WCc4ZcvHkdDRENIL9+6TKZnBEHMNihNMwaFYKJSOmU0ybySf4bCWb5wUaInmcNwccpQOOwpMLbyT6/16jsKdR5avn25XPFpoXvnymVNuKC9Fh+6ajHqQjqCuoLWWABzawNojQUQ1BXUhXRfDc2Yz/OA9zyFlPjvHUeRLuNr0hozkDJd3L/1AEzbRWc8i/60hXetaUdI9zxPTiRNHOrP+AIRzoC5NQG01QbRnFcyfrT9CACgMWqgJRYYMVem0PEyXISQ0kurlBIyFAQ0L7B0pSi+t3ZJYQ1jwHA9o6CIMA60xrwuLEMZWcjrbZ+a3w2CIIiphJSRUTjZMfaV/DM8cyvve9MRyNkCQX1o8ZkqY6vRpteOt/gUGDkUr5BiWTEn5lOPxnqeRwYyuOU/n0dQ5cjaAsmcDV1VKqpH+7qTeLyjB0tbIgA835DrLjkLX/39fqRNf1ompCuYUxJsMDBEAxqO9GcQz9hY1BQpe29ttSFwjOx4KaRTCmiKVy/TFDVwbEDAFd77mrFc334q5yOetSO88tRfvtQJBs/u/jVHoKUmMGL6L5meEQQxG6FgZBROdox9Jf+MgM5hqAqylgPGWP4TtheMTKWxVbnptQXGW3xaYDzma6M9z7TlIm26EFIiWhtEjaogaTqwHH/KA/CeEYe3MA9mPYXAFRIPPX8M33rqVVhOiRIBoCVqIBYcdg8MCGoKsraLxLDApZRrzp+Dz/1yF+IZ29fxIuVQb0thRg4ARAwVbXVBnEjkkLVd9KUthHQFat6rhDGJUm3EybdGM3jFqrrKi94txwYyaKsL+e6bTM8IgpiNUDAyCtXMiilHJf+MwifoI/3e4usIb+E/lXNlyjF8eq3C4Ss+ZYwhFtDQEBmfgdtY5muVnqeERE/Ssz3n+SJYlXOvVTgfLPUkTYQNBUIAjhDIOQIaY6gJ6Dg2kMWXHt2Dncf8luwXL6jHqz1JGJo/5cEYg6owmM7YKoOqctx81WLctbkDliOhKgKceWmkAk0RwxdcRQwVSm0A8YyDm9+0BKvm12HbgR586dG9vnO4QqIQNzVHjeKcndaaAI72Z2C7El3xHBY2hGAJSaZnBEHMWigYGYXSYMJg3idWRwionCOg8TEl89H8M8K6grChgDEG1xU4kTKnxNxs+PWdMzeGl46Ov/j0ZKgUnOUsAdNxiwts4fka+XSNwoCc7SCZdWCoHBISyZyNhY1hvHRsEN966lWYJWpIXUjDR9ctw+uXNODWn+7EwZKiViVfswNg3CrD+69YDABDk3UBIF/wa6gcjRH/++8pGN6MoOsvOasYpDHGRpyDMe+5NMeGumYihop59SF0xXOwHBfHEzmENGVKfzcIgiCmEgpGRqEQTJRzWy1tfa20mI1l714X0vHFt5+HmqA+JeZmo11fynRQr+lFZSRre3UaJ/spvLSFtzaoYVFTBHu6/MGZkzcnK6ROApr3s6aopxA4wsuJWK6bdyS1oSsMgxkbX3v8gO/13ri8Cf/wpqWoyaeW3r2mHfc8the9KRt1YQ0a48g51StQ779iMW68bCF+8VInjg1m0FYbQmNYxz/9z8vjtu4ffo5kzsFDzx31te8WiBgqFjaG0BnP4b2XL8SVy5qn9HeDIAhiKiGfkTEojHh3Rsyh8T4Z33r18uIn50oM9+bQ+Phbg6eCU3V95Vp4GyI6TiRNuALFBTyRs3FsMAuFM8wrqZEQeQ+TnqQJ2xGIBFQYCkPAUNEdz/k6ZWqCGj66bimuXNY04jr2diXxg2cO4WBPetKf/8k8u51H4/jA959F2FAR0EZ2z2RtFxnTwdevW01tvARBnJaQz8gkIITEE/t6YagMwh7K7wNeZ4WhMjyxrxfvvXzRqJ9Yp2qy7kQ5FddXaUZLZ9yEwoE5NQb6UlZx9k4sqEEIL30lpYQrJFwpEdQ4gpqChY1h/Nn5c/HzF4+jo9s/U+bKZU34yJuXoHZYukxTOBojBhY1RbBuRYtP1bjm/DlQ1ZPvbD+ZZzeRKc0EQRCzEQpGRqFgCma5Eox5M0KQb4YQUsJ0JF48MojvbzuE151VN+oiNBWTdU+Gaq5vrKF642mJrglq+OLbV2Iwa6M+pCOetfCZn72MzngOkYAKjTNYrlcbEtI5zp0bw7/9fh9y9lBEGAuo+Oi6pbhqefOIa4wGNDSEdXDO8PT+Xnzt8QPo6ErCcgV0heOnzx2dtKFzJ/PsPnDFInzmZ+NP9RAEQcxGKBgZBb8pmP+TqyMEbNczBfuXxzoQMdQZlXo5VZRb2JcPmyY7npbogz1pcMaKaRUpJW67+mx846lXcaQvjYSU0Jg3a8a0BX763DHfeS5f0oiPrluK+rBfDVE5R2NURyjfmfL0/l587CcvoD9tecPn8jU/z7xqYd+JJL7yVxdO2ftVyXn2PWvn44l9vVM6pZkgCGImMaFg5L777sPdd9+Nrq4uXHDBBfjqV7+KNWvWlN33oYcewp133on9+/fDtm0sXboUH//4x3Hddded1IVPBZVMwVwp4ZTUK0QDKkK6WtamfDYx3oW92pborOWiN2ViWWsUd/3lSuzvTmMwa2LnsQQeeu4YsrZbPDYWUPEPb16KNy5vGhHoRAwVDSV27kJIbPz1bvQkTTAAqsKLBbqOK9CTNLHx17vx85svP+XqQ6W01e7OJI70Z6a1kJkgCGK6qTpp/uCDD2LDhg347Gc/i+eeew4XXHAB1q9fjxMnTpTdv76+Hp/+9Kexbds2vPTSS7jxxhtx44034tFHHz3piz/V+EzB8hZXEhKOK4qGV4VFbrhNeenE2IkwfMqvyHuRDN82VZQu7EJIKJxDU72OooIPyMZf74YQ0tfCW45CS3Rv0sT/vHgcWzt6YDpewMEZQ01IxX/tOIYfPnPYF4i8fnEDvv23F+NNZzf7AhGFMzTHAmgeZue+81gce7tTYAA0lXt298jb3ascDMDe7hR2HoufkmdWoNJYgNLfma8/cRDnzo35pjRP5/tNEAQxlVStjNxzzz14//vfjxtvvBEA8MADD+CRRx7Bt7/9bdx2220j9r/qqqt833/kIx/B9773PTz11FNYv3592dcwTROmOTQPJZFIlN3vVFPOFEzCswYvwDmDlh+gNlmDzCp1oQDlp9dOhQozfGEvuLUy5n1vO6K4sK9sqykWZjZHgUTWhe0KaApHLKigJ5kDAPy/X++Gk09LtDeE8a6L56ErYeJrjx9AxhoKQqIBFR9+0xK8eVgQAgBBXUFTxIBaRoV54fAgbFd4AwCHTYQpeI7YrsALhwdxQXvt5D6wEsbr5PvzF46jPqIXa2i+/sTBCQ1nJAiCON2oKhixLAs7duzA7bffXtzGOce6deuwbdu2MY+XUuJ3v/sdOjo6cNddd1Xcb+PGjfjc5z5XzaWdEsqZghVmozF4HTVBzTPoKjCWK+tYlJPzB7MWdh33ArI5NUE0R/WK02tPFdUu7DdduRg3/+g57O5Mwfd5ftB7diFdQW1QhaYw2K7E/u4kPv2zXT7zMgC4dFE9PrpuKQbSDp49NICagI4lLWEonKM+pBf9RMohC5dZKdvBhu13ihgrbWW7Aj0pE1/45S5PaZISacuBrnC0xAKjTismCIKYDVQVjPT29sJ1XbS0tPi2t7S0YM+ePRWPi8fjaGtrg2maUBQFX/va1/CWt7yl4v633347NmzYUPw+kUigvb29mkudFMqZgtn5WgMAUDhHUzTg+7R7MoPMynWhyLzXBssbnMSznnnXeIf1TRbVLuy7jseRyNool1iQQNFhVUqJnO0iaTo+xYkBiBgKepM5/NPPXsZgxi76eJzVGMYtb1yChY3hUa/5ovZaqJzDdQW4Ike0zrquhMo5LjpJVWSs7qJKzrMAkDIdHBvIQkiJsKEiGlDxam8Gpu0ZwTlCIqCxKX+/CYIgppIp6aaJRqN44YUXkEqlsGXLFmzYsAGLFi0akcIpYBgGDGN881BONYWJtKUdJIVFYG6tf6rqyXpDlJPzc7aA6XgW9ABgOi5yljfld7LSQuOhmoXdcQTue/wAhPS8WKQsDJYb8moZSNuIGip6UhbSJSkZwLOinxMzkLEF9vdkAABNUR0NYR2uBA72pPHZ/9mFO9/BR1UIVrbVYHlrBLuOJ2DnbfyHTOu8up/lrRGsbJv4c6vUIVOaTqnkJyIhcSKRgyskQrqCmqBWHDmgKQyuBHqSOYT1MBhjU/p+EwRBTCVVFbA2NjZCURR0d3f7tnd3d6O1tbXyi3COJUuW4MILL8THP/5xvPOd78TGjRsndsXTRr6IVQIhTQFnwEDGQtZ2IYRE1nbRlTBPyhuinJzviLwFPYaG2DliKJVhKBz2SaSFxkthYZcAbCEgpISUEkJK2MMW9l+81Ilk1oaqeCkdxpjXkVQiqwgAh/qzIwIRBqAhrEFTOVI5p3jfKdOBrnJEDBVzagLjKhTmnOH2t61AU9QAZyw/mM4zVOPMG1Z4+9tWTFhhKKTUdncmoHCGoM6hcIbdnQl86uGdeHp/b/E6brpyMSKGgq6EWfydiWdsZG0XquIV4BYmOEvpHaNyb5hfqbfKVL3fBEEQU0lVwYiu61i1ahW2bNlS3CaEwJYtW3DppZeO+zxCCF+B6kymsODs6UqiLqRjXl0QzbEADFWF6QgMpC2cSJnImN5gtJPJ55frQlF5vh0VyC+8EqYjkLVcSClPKi1UDdUs7McGM3AlwOAFK0JKX0dSgdLvGACFAQoHVK7AtCUs14WieIuy5QhYjnfEcIVgNC5b0oiv/NWFWLuwHrUhDWFDRW1Iw9qF9fjKX12ISxY1lO1YGauTpZBSG8hYyFouuhI5HB/MoSuRQ9ZyMZCxfMFSQWFbMSeKjOl4vzOWC4UzzK0JFhW24vudD0CHB59T9X4TBEFMJVWnaTZs2IAbbrgBq1evxpo1a7Bp0yak0+lid83111+Ptra2ovKxceNGrF69GosXL4ZpmvjVr36F73//+7j//vsn905OAaM5ic6vD6IznkN7fQgfffNSNESMk/aGKCfnF2orMpaL/Cw59CRN9DJzXMP6JpPCwv61x/djT1eymJY4uzWKD121BJctaYSUErVBHRze/B4ph4cgfjjzvEMSWQdSAoaqwNAYMpYLKb3ghIFBFBdlr+aimkLhSpbtfzjYhxu+s31EiuWKpY1FE7JKqRfPnTeBtOkpOwpnYNwLHkxHwHSAV44nfOmU4dfRn7Lwpc27oZfY0gd0DkNVkLNdcO6pQoUUHVnEEwQxW6k6GLn22mvR09ODO+64A11dXbjwwguxefPmYlHr4cOHwfnQH9d0Oo0PfehDOHr0KILBIM4++2z84Ac/wLXXXjt5d3GKGKslsy6s40Qih4aIMSn5+0pTfg2VI1Vc9LwvIZH/ZC1wxdLGKStmHG0Wi+m46EmaWLuwHobGkbXL+4wUMFSO1piBnCMgsw44A+ojOhhY3vEW8PQV/6IMDCkE/SkLW/f2jGkUNtyyvZIJ2UtHB7HtQB9CujJqJ0tfykQiZ0NKOaLVmSmA7Qgkcjb6UmbF6xBC4qHnj/qCTwZPZTran4HtSAQ0BbrCkLVdsognCGLWMqEC1ltuuQW33HJL2Z89/vjjvu+/+MUv4otf/OJEXmbaqdZJdDIoyPmFoshBVyCZc730BQNcCdiuLLYVayof17C+ApU6P8bqCCll+MIupUR/2kI86y3OjAMNER1HB3IVr0PhQFTnSJgOVACRgAopJYKaAlXh0DWOQFpF1nIABgQ1pdhCLaVETzIHxhi+tHk3HIGqfDgqKV4G53Dc/JA+IWGoeXWqTCfLQKbEnbdMq3PhmQ5k7IrXUSn4VDhDyFBgOgIhnaMnbZFFPEEQsxqaTTOM0kW5P2VB5Sjbkgmcuvx9qfqw4/AA7vvdfmgqQzxrw7VFQSsA4wxhQx13d0Wlzo/xpCVKKX1GYV1Bc9SAU1JTsb87jZzpQskHT8MJahxRQ8V737AItSENNQEdSdPCv/52H/rTFurCOgxw1AQ1ZCwHkEAsqEFKIOe46EnmkDZdhHQFkYBWtQ9HJcUrZwlYroCar9vJ2V7XEjCyTqU2nHfnzRfyDu8uEtILVGrDlX1QgJHBZ2E2zfnzavGBKxaRRTxBEGcEFIyUUG6xzjoC6YSJ+fXBKR3xXlAf+jMWLEcgnnXgShRNxyS8tl/bMRHU1THVmUppiRePxLHtQB/ChoLm6NgGW4VntL87CcvxXGnbG8J495p2XDS/DlJKbN13Ar2jKAKmLaBwgdqQhosX1IMzhvqIjrba0IhFufBs+1JeobCWnxMU0hXMrw+VnQg8lg9HJcWr0MmicMAV/hoVwK+ENYYNr9Yl58AWEipHSduwV9QbC6hoDI/doj5a6osgCOJMgIKRPJUW67TlIGO5ONyfRXPMmPIR77VBDVnbhSskNGXIo4IB0Ljn3pm1XNQGK38Cr5iWYByuEF5njCthaF7tQ6WFvfCMkjkb0YCGsOG5px7sSeGex/bi/W9YhN/tOYEn9vWOek8CQM52EA1oCOoKGiMGNIVXXJQBjCj6jAS0Ua3VR1OKKpmQFTpZhBxZowL4lTDPnbcGLx6JwxWeolIYHBjIz+w5Z+74C4uHp74IgiDOJCgYwehdM+11IRwZyIAxIJ2zEZeY8vx9cc0dHvOwYT+vQMW0hD0sLWFVTkucOzeGrz2+H4msjYZ8kSngmZo1RnQcH8zhi4/s9qVrRsMRXhfNnJqgb3ulRbmwbeveHjgCVdfxlKaWaoMaFjWFsacr5TMhC+gcuuJ1LoV0xWfzP1wJK633SOYc1IV1KIzBlRJZy0U0oFKhKUEQxDihYARjd800RQPImA7+cf3ZxUFmUyWjD2ZtBDQFmbx6ofAh87OCx0dAUzCYrZwWmYy0xLOvDWBvdxLRgOYr2HSExImkOcK8bDzs70nj8qVNVR0zmrU6UL6Op9LgQYXDVzhq5gMzhTMonCPniFGVsOH1HqbwXvucuTEqNCUIgqgCCkYw/q6Z+oiOK5dVt3ieLPUhHWFdQcRQEc/ayNnuUDpA8yzEhRCjtrieTFpCzRdCvNrnLeSxwNB5kzkHJ5ImXDmkhmgKw6WLGvDEvl4o+XOPMDfLtyaz8YkoPipZqwPl63gqpd864yYUDsypMdCXsnyFo6UFvYXtlZQwqvcgCII4eSgYwfg/bY/X06Ic1bTOllJYfF86Oggp/b4dUgoMZkxoqoK7H91T9WyUgDYsLaH70xL9aQuLGsNoqwsga7nQuFcjonLgRNJE0nR816Nxhjv+9Fw0RHVsO9jnzatRAMCzkGXM+3Jcr/7lwvm1VT+nSu2w5dSL0dJvhZqYmqCOL759JQaztu/13nv5ogm3OhMEQRDVQcEIxv60fTKeFsD4hqlVgnOGK5Y2YtuBPrhC5tMInrKQtrzgJAyGcMSo2Akz2gKucA6Fe+mJnO2lJXKOi/60jZDO8a417eCMYUlLGO0NYezpTCBnu76WXQYvsFkxJ4ZLl9QDABY2hLDvRBquC6gKwLi3p+N6c2yWtYwcUDfe51SpHXa4ejFW+q02pOFgTwqcsSlTvCYalBIEQcxmzthgZPii8IErFuEzP3t5xGI9EU+L0nMf6c/gG08eRHpYmmC8nhhCSDyxrxchXYErJCxXwBtd4xmfFepFx+qEKSzg9/1+H3YdT8ByJXSFYWVbDFctb8bWvT3Y05WE5QgonGFRYxjvXjsfF82vA+ClZISUZSfsGipHNKDiPWvng+cX/Q9cuRgbf70HgxnL8+IQAGOe90ZDWB8xoK5SOqXScxotPVJ4/lv3nkDWdlEbKt9pVKnY9WSCx9E4VeclCII43Tkjg5FKi8J71s4fUStQradF6bktRyCRcyAh0VYbREBTxjx+OIVP9y2xAAyVF0fMO65EdzIHBRizE6aQQth1PI5dx5PeNUkgx4Bdx5NY0BCGkIAQXnCTP0vxGv53fy++kjckKyWoc0Q0BfMbI0WfkQJvPLsFrbEA7t96EB1dSViugK5wLG+N4kNX+Rff8aRTyj2ncumR0uefsVwkczZytkBrTaA4jK5ApWLXaoKi8XKqzksQBDEbOOOCkdEWhSP9GXzx7ecVXS+r9bQYfu6AJjGYt0g/PphDWx0rLojj9cQoLa5ljOUDDgXJnD3uThgA+MYTB3DX5o5iqqegqgxmbfxw+xEENc/x1NAUSAkc7E3hy492YG5dEDsODfqu6Zw5MVy7uh0BnaMmoGNJS7ioiGgKR1PUQEBT8PqlTbh0ceOYaYnxpFPG4zI7/PnXBjW85ghkbRdH+9Noys+aUTmHobERxa4TDYrG4lSdlyAIYrZwRgUj41kUvv7EQXzvxjXgnPk8LaSURVVC5dybpluy4JeeuyVqwHQk0qYDKWW+xkOiJ2kibChDHh0Kx6ArsOPwQMXFejIMuhxH4L7HD8AVErrKwFl+35KC2GzezbUwlI4zhsGMRGfCLHlNhvdevhDvXDUPSplFMxbUUB/Sq15QJ2MGUKX3tqUmgCP9GdjCCwgVViik9dJFpa26YwVFNUEVuzsT+P62Q3jdWXWj1nsMHyuwvzs5ZrD18xeOT3nrOEEQxEzgjApGqv0EXggEBrPeEDjTGXLZNFSOWFArLviFcxsqx6H+DExHQAhvNotwAZUDpuP60ikDWQuJrIP7frcfQPnC2Il2wpR+6v/5C8eRzNp5RcQLrADPCbUUCYBzz5BsuHmZwj1782cPDWBZS8SXklG5p4YU7qvAeGskJuIdUs1766ekOHnYT0YLilKmgxOJHLK2i3t+uxdhXalY7zH8voWUSORs6KpSTNWVYrsCPSkTX/jlLiicUy0JQRBnHOU/is5SxvMJ3C75BH7u3BgaIjo6494ixBmDyhk480a6d8VzCOoK+lImdhweQCrnoCdpImsLb19laF6JnZ8E66VTgGTORlc8BwmJmpCK5qiBsKEWawie3u9Zqhc6YSKGgq6EiaztQgiJnFPohGHFThghpHddCdPX4npsMAMBgDMvUJH5a5LSvxxLCdiu97+lBDWOpogGXeVF6/fnDw8AACKGinl1wbKByKce3ondnQkonCGoe9e6uzOBTz28E0/t68HOo3Fs3dsDISUWNYXzk3A9e/tkzkbWciGE17K7uDkywlpdCFk8x3OHBka8t4VOKAlAVwCFAY0RHQsawljWHIErgPu3HoDIB16lQVEpKdPBsYEscrYLzoCGsF72vRp+32HDe18LxcfH41mkhrVDF87tClncv9K5CYIgZitnlDJyUp/ACwt0ProQwtt0uC+DT/zXiwADkqYDBkBXCwoGg6ZKWI63uAnpHZ6xHBwbzAIA2mqDCGre2zBWJ8zwVtYL2mvGZdDVVhsCyzu2lkuvFBiulBSfiy3Q41hgzKsJsV2B/9x+BG85pxWxMjNxCimTgYwFx5WIZ+2ioqQrHFnLwf/f3rlHt1Ff+/47M9JoJFmynfgROzjvB6Hk1YTkJkCSctLmHHo5cNpTQuEEyKVwWpKuQi7nAKWQAs0DyIGwSIA2EKAtkD5IuW2hCSUQKBAIDQlNnBd2EpyXnfglWa+RZuZ3/xhJlmTJ1siSJdv7s5ZX4rE82nvG9m/P/n333stf3QubWYjriKpqGo6e88QFQxwHDEnYTgG6Zh8YGDoCCkQTjyF2/f4FQhpkRYOJ1+8Fz7PoPBwAXTJhybJQkYBGDW9pSWYTbOGttsR7BSDpVlGxzYxWbxC+oIpz7gDsZXb93GA45w5A1Rhsot7AjuNSV0QRBEEMVAZVMGK0e2ftGTdaPEFUFVvD2zQqWDgIAQfw4e6iTqtZH5QG/XOVMZjC5xY4LiqSBYA2X2S7hENFsQSHFL+YpxJsdlfKmqpBV0S3YBN5WEUB3qAKjtNiNCPpXTeeA3iBA2OIBlbHznvwZYsvqaC09owbB8+44ZVVfesnrEFh0DM3GgO4oAZHqQmlNhFBVUNDqw+egAJw4XiPRWbudF2Ek4mQZUWFyx/CWZcfZoGDQzJH292DY1A1vWNt7HZWohYlWT8WTdO1QmCAEN6Oimh+Eu8VgKRbRRw4VDh17Yo/pKLdH0KxZIY7EII/pMIk6F+P+x4Dwl2C6M8Ueu+dQrevtxSKf4MqGDHSvRPo3NapcIgotZsRCOoC1ia3jJCqQRD0ShaNMX37Bnp2IaQycNDA8/oCrjEGMw9YzCZ87/LRcFjM2PBuXcpJu6kEm6k6faYqcX16Zx2+aPLEbTuEVMDE65+rSYIRLvwRmyXheA4cOF3YKugdVDtkBS0euesJALR4ZLgDIaga0zuuagBLiHwYdF2KN6hA4DmEFA0aA2xmAcOckh7QhatemtzBpNmHqFA4qMDE86gulnCyzY/T7X6MHMpFK3z0mT7xgQSQPBOWmIXyBlVojMFqFlDh7FoenHivUm0DFllMGF5qxZl2P3yyEtYU6Zmq6mJrl/MmOzdBDDQKvfdOodvXWwrJv0EVjADpd+8Eum7rWEUB/qBeRhvZ7uA4Fq1kEQQOPGPRAEVT42fIMMYwf0IFAPRasNkdH9U1456t/0BHQIFTMsMhmXQhZYcfgRCDkmI/ho8IXGLgEK4+iXzO8eB5fSFt8yUfztfm0wMRXZfSGeAkxj7n3HJ04rCqMfC83jOF4zg4YhbnZNmHWKFwrKi41GZGR0CFy6f3d+E5DowDqkviA4lkmbAIsVmoPQ1t2PhOHYptpuh2WiyJ9ypyXy08Hw1eTTwPSeT1suciS3TgYqR0XDQl1zD19ueAIAqZQu+9U+j29ZZC82/QBSNA+sPNkm3rxKb+FU0Xd0pmHuAAi0mAP/ykX+6wwGLi457uYxc+I9tFRlAUDU/u+AIdAQVlRWJnGbFJfwI/2eZHMCElYhY4SCYBNosAgePgCypo9+tCS4EHeHBRGxnTq0N4nkOJPXlmx2kzxYtgI+4lBjqcXi6shAMXVQMYx3rsmeKVVfhDClSmfz+nj76BP6QhqGiQzAKWXTEOo8vs0Q64HlmFSeC7zYTFEsk2faXaiR2HmnDobAckp9DjvYrMEVJUvVturFbGJOiD+K6eVh3dRtu691ROfg4IopAp9N47hW5fbylE/wZVNU0skcVm/oRyTL6gOOWClFjJoqf+mZ765ziUO/QbyUEPQDiOg8b0yhnGgICiotEVX92SqkImWSWMEbyygnePnMfx8x44JXPcloQvqODL1vhAxMRzWDp3FFZdczEmDHOAaQx+RQXHcRA4RBujRSpvNMYQ0vRsg1MyocxuSWqH26fEKT0Y61qhA3T2+4gV1TKm62xiic0QlFjN8IdUqOGMFs/pgRLPcTDzHFSNIRBSo5mVqReUYNU1F2NSlQM+WcE5jwyfrGBSlSOtyN/IvYrMEfLKKnzhtvmRHRtfUIVXVjFvfFn0vubq54AgCh0jbRbIvuxTiP4NysyIERK3dUJh/YHGWJfUv10UYDHxkBUNzR0yGKdHew6rGTfMHmFo2Nv/GjMU+0+54jI3AJJmc1SNocUjwyMraPXJCGkMTkH/AdM0hvNeGS5/fElpdbGEB6/+CsaWFwEAvjqyFHVNXrgCQTglM1786DgOnfVA1bS4J3zJpJfo1gyxo8UjY/8pV5esUqnNDEHgdFEKFw5GklzbTiEo4ubsyIraqRkxxXdK3X/aFd3a6aJtDZ9D0xjW/OUQOHDRPdD/nDcm2lnXqEgr3a29VHOEOA6wiQIEnsf7XzTjlsvGRN87cu6nd9bHtc2/MEnbfIIYKGSj0WEuKXT7eksh+kfBSBokbuucbPVh0/v1XVL/5zsCkBUtpkxTX4j9IRW//vhLWEUTaobYoothqu2ij4+14KYXdseJioYW6bqBFk8wTmh085xRGFdZBDW8khdLIsw8h5DKoGr6E3ZiAzO7KOC+Ky+KBiKAXu0yYVgRRBOPCoeEYqsZP/7DfnQEFJTaRQgcB5UxuHwhBFUNJ1t9+K/f/yOp4GlokQVOyRwu6WV6YAKEM0addjDE60r0Y8AZVyAqPk0s7W33hyCZBfi0cHaKR/Q66yW+AMf0bZFIpc6hsx34yesHsPrfJmc8nTedrb1Uc4QiHXsDitZNdUz4arCI2DfNUieC6Idko9FhLil0+3pLIfpHwUiaJFasjCmzd3lSTjZUDwCEQAin2/14+M8H4ZTMXRbw2PMmExW1+4PRdFlVsRUVDhGyoqL2tBsP/PEAVnx9QrQj6rhKO6pLbTh01g05QakqhifsTqh0YGJVERIpsYkotem9LhKzAbKmQdM0hDQNlnAvj1SCp69UO3FRtbOrdgKdQUdkEVdUveJGDGeUIr1YGGNJS3uH2ETYRQFFFlNcuXVEaMszXUhsE03g+cx7dqQqd+uuxDbVHKEIyZ42UonIDjd6BoRIjiCSYbTNAtmXXQrRPwpGMiTxSTnVUD2PrOBMewCaxsA4BodkCnci7apYTiYqYkxvGhaWqsDlD8Fp1RfaoUVmNHuCeGX3SUytKQHPcdh/yoWT4SqTWJySCTwH2C0mXD+rJpp5AOKH26Xysdkr48m3v8CpNl9agqdICbVHVjDELOpzdDSGpg4ZqsZQUyrBxAvRyqRGlx+M6Vmb7kp7Y3+JRg61Qg7pgldFY2h0+cNC4rCoOIzRnh2ZlrsZfdooRBEZQfQFRtsskH3ZpRD9G7QC1mwQK4IdUiRGh+pF6OzeqU/KBXRxq2QWMMxpgUdW49qRJxMVdXYR1bUagZACb0AFmK65cEhmnGzxova0GxveqcOdv/0cLd7OJ2+B5+CQTJBMPMZWOOKyKADgkMwYXmJNOjMl1scyuwXn3IG0BU+RzMqkKidUjcEf0rMeFw5zoNxhgUfW0xl20YSgosEf0qLNv2wWU7RTKs/xceeOFX02uYPRc2iavgWkVzJJXWxMbPWfimTt3NNtzx4JlNp8oSSt9lmXtvaFKCIjiL6i829EZuLywW5fbyk0/ygzkiWSPRXHtyOP70mS7Gk9magoWkqMsBhUQ7g1uf4aUeDQqqh46M8H44IQngOum1WDOaPL4AspKJZEjKu0RzMiAs+hrEhfaNMhE8FTd5qY2C0uo82/kglKwSIZHjHpOVLtgcZux5RYzXh6Z13GmYpMm+oVkoiMIPqSdNss5ItCt6+3FJJ/FIxkiZ56kqTTjjxZQCOE92c06M00OA4Qwu3cNcbQ5JbhkVV4oEbPO3KoDff884UYX1mEuiYvkNCbzG4xoazI0u2cmkQyFTwl01mk2uIy0vwr8RwlVjMe234Yhxs9Yb1J/B5omzeImiG2uAqg2KAoFC55dvlDKHekN9U5Gb1pqpfuNSWIgURPWqx8U+j29ZZC8Y+CkSyR7KnYaDvyxIBGYwDP61s/gXCnUdHEQ2EaXH41+mQdtYEDrp1Zg5vnjkLtGRfufm0/TrZ4EQoviCOG2vH9+WOw8KJhhv3LtuAp9hcg0+Zfib9Ety8YlzQrcc4tI6iqcRVAQ4tEnAvrVyLC0TZfECFVw/kOGaJJ6LH1eyp601SvN9eUIAiiv0KakSySuAfnDoTAc3ozrFTtyGM1BJGAxi7yON0egEdWwBhQJJmizceCioaz7QE0dchxgciIITY89d3puG3eGNSeceHxvx7FsfMevaLEzEMQeBxv9uBnbxzKaCx9Lht0ZevcyfZA27x6IBKpAKpwWGCzCDjc2IHzHTKKLCZIZgE8r1fgCLzemv58R6CL7sNIpiLTpnrU9IwgiMEIxxL/4hYgbrcbxcXFcLlccDoL/ykxVocQaUfuldWkGoJEoVC7L4gdh87hld0NelaDMTCNwSsr4YFzXVkwsRz3/POFEE16M7a7X9uPI41uqBpDKFxWy/NcXEvyl5bOymiRi6s0CWdcsjVYKVvnjlz/VBVA/qCKEy0eMAZYRQGjhtr1yiUwnGj2wR9UwPMcRg6xh8tz9eCx0S1jUpWjy7Xr7dTLXF5TgiCIfJLu+k3bNDkgnZ4kiRoCWVHR7AlCDqmYPqIEU2uKUdfkRZs/iBc+PI4vW3xgWny5rj5ThkdHQAlX6wB1TV7Un/PAH21HzoEX9OnBsqJBVoCDZ9wZj6XPpeApW+eOXP/9p1xJK4D02TccBEG/JoGQBqsoRFv6n2pVoxOFLabuy92yMfWykERkBEEQ+YCCkT6gu8Umsl3T7o8vB410RN1+oAn15zxImG2HUqsZQ4tEBFWGky1e1DV5MWFYEdp9QXjkkK4vMfNxLdc5AQgpGtyBEFo8csb+5FLwlM1zp6pWMfF8tG8LY4gbzFdkMaHCKaHZIyOkajjnkVMKULM59bJQRGQEQRD5IKNgZOPGjXjsscfQ2NiIqVOn4qmnnsKsWbOSvnbTpk345S9/iQMHDgAAZsyYgdWrV6d8fb5JlXJPdhxIPismGckWm0BIRbNHRjChQRmga0Ne2nUCW3afjNuaMQschjmk6PaBKAAdjMEVCE+0DarQNL0LKZfQvZQDF/WlzZdQYmPwevQHUlWrSCIfnbDM81y03BrQt2NkRcMlo4bgvxZNRLs/lNRvalhGEASRPQwHI7/5zW+wYsUKPPvss5g9ezbWr1+PRYsW4ciRI6ioqOjy+p07d+K73/0u5s6dC0mS8Mgjj+Ab3/gGamtrMXz48Kw4kS1SpdznjS/D+180pzUrJp30PGMMrd4gXP7kAcHhRjce2XYEX7b44o6XWM0oKxLjuqcGVQYzx6FYElFiEzG63AZB0JurJStx1RgDz3MosZszvh79RcuQqlqFA4eyIhENrfrwQAa910nsdsztC8Ziak1JynMbaVhGGQ+CIIjuMSxgnT17Ni655BJs2LABAKBpGmpqavDDH/4Q99xzT4/fr6oqSktLsWHDBtx4441pvWdfCFhTpdzPdQTglVXYRAGVTik6K+asKwBAnxVTYjUjqGpoSyFKjcUfVKNbAIDeKyQyLddmNmHXsWZs+fRkdIJtBIEDhhVLsIsxFTlgaPYEMa6iCC8tnQWbxYT9p1y4+YVP4A4o0Bhg4vX8CAOgaAw8p7eGf3Hp7G4XyVTXIx0fY8l3ZqXTj64CYhMPlDssekBpUDj63tHzuOu3n6PCYUnqj6YxnPPIWPedqRkP5yMIgujv5ETAGgwGsWfPHtx7773RYzzPY+HChdi1a1da5/D5fAiFQhgyZEjK18iyDFnu1DS43blth50q5W7heSgqg6rpH5ZwU67EWTGldnOP6XlNY2jxBtER6MyG7G1owyu7T+Jkixd+RYMvqEan70YotpogChyaPSGcaQ+g3GGBUzIhqDJ0BEIospjwo38aD1u4bFgfUleMz0+6oGpa55A6DpBMPASex0XVxd32rsjWFkS2MitGts4S7empCZkR4Wjs+7V6gtSwjCAIIksYCkaam5uhqioqKyvjjldWVuLw4cNpnePuu+9GdXU1Fi5cmPI1a9aswYMPPmjEtF6RKuUeCOqLuSm86ARCejYjMitG/7+KQDBcjZEiPe+RFbR6gmGhpM7ehjY8/tej8IZ7iXQElDibBJ5DlVOCLaINMQlocgeijbn0BdWJ5V8bF7ewxzZf6wgoKLWLEDgOKmPwB1U4JFOPvSuysQWRLXGnka2zVIFOT9Uq6WyjJNph4gG/osEbVFBTaqOGZQRBEL2gT6tp1q5diy1btmDnzp2QJCnl6+69916sWLEi+rnb7UZNTU3O7EpVdRFp5643wkI0mIhkGiKzYmKrMWK7dCqqhhZvEF45PtDQGMMru0/CHVAgK1pSAavIc7DGtI63iyZUFVvhkRX8n0tH4/Lx5ZiSoplWJBvw9M46HG7siC7Wk6ocuH3BuB6DgN7OTMlmZiVZQPOPU+3YVd8St3WWaRVLOqSyw+uW4QuqONnmQ7lD6tJDZtFXhuFvdc39TvhLEATR1xgKRsrKyiAIApqamuKONzU1Ydiw7luMr1u3DmvXrsXbb7+NKVOmdPtai8UCi8VixLRekarqIlICqoWDj84hd+HmYwnHgc70vCjwONXmh5ZEknP4TAcOnXHBF4oPQgSeA9MYBB4IaRrkEINk7lzALCYBvpCKKTUlmDaiJA3PIhU1LPxveothb2emZCOzYmTrjOO4bgOd3mwXdRdYjRhiRUOrHxwH+GQlugVUVaz/7D79bl2/FP4SBEH0NYbawYuiiBkzZmDHjh3RY5qmYceOHZgzZ07K73v00Ufx8MMPY9u2bZg5c2bm1uaIVKPfJZGHKOiLnyjwkMz6h8XEQ9E0KKoGi6lz+F1kINsFpVaUO8SkgUj9OQ9W/eVQl0Ck2GpGlVMCz0PPuLDIdF4dntc7hFoEvkcdQuRJ/nCjGyU2My4osaLEZsbhRj1z0FM7+FTXI+JjYhv7RNLJrIR6mPFidOsM6BroxF6LQ2fdsFtMqHDok4ojWZSerkVPgVWF0wKricd/LboQ674zFbd/bRzc/hDOugIZvR9BEMRgxPBsmhUrVmDTpk146aWXcOjQIfzgBz+A1+vF0qVLAQA33nhjnMD1kUcewf3334/Nmzdj1KhRaGxsRGNjIzweT/a86CWpZoQEQvqiJ/AcBL5zWJ3TagYLz4optprBNMAfUnHGFYBk5rH4kpq48lsAUFQNL310At9/+bNoJQ6gV7tcUCKh0mGBNRz8qOEBvALHAxxgEniYeA4uv9JtEAB0fZKPzF2RzAKGOS3wyCqeea8eWmK5ThrXI92ZKbGZlWSkI+7saeuM52IblnUSG+hk41qkE1gpDBhSJOLycWXYXtsIb1DN+P0IgiAGI4Y1I4sXL8b58+fxwAMPoLGxEdOmTcO2bduiotaGhgbwMdsWzzzzDILBIP793/897jwrV67ET3/6095Zn0VSVV1MuaAkTiwZOR4JCFo8QTR1BMBzHEaX2XH9rBpMH1Ead+768x48su0I6s7FB2CiiccFxRIUDfAGFQgcjxKbGWddMngO4HgGgdMX9XZfCHaR71GHEPskD+ilxIqmC24lM592/4vuqlD+c94YOCQz3jt6Pqkd2ZhGGxvQWDgegZAWzkYxAAwa47pskQHxgU6620X/b98ZDCkSk/piZMuKeo8QBEFkRkYC1uXLl2P58uVJv7Zz5864z0+cOJHJW+SF7qoubrlsTJfjjDHsOtaK0+1+FEtmjKu0x2VEFFXDq5+exK92fQkl5mm4wmHBNdOr8dqeU2ho8yF2J4TjAIdkwvASCe2+EHzBYI86hFibjzd7EVQ0mAUNZ11+yEpnaa/FxGOo3dLjFkl318PlD+Ln7x/rVn8RW9HT6A7AahZ0nQ3TM0hFlp4reiIBTbISZY3pGSC7KEAyx3dPjQ10/lbX3G1WI6RqOO+R8fCfayHwfFJfjARWPb2fReDRrmrY09DWLzvaEgRB5AqaTZNAqhkhiccjzcuqSyRUl8RXBmmM4b0jzdj84TGcbg/Efe3KycPwg/ljcbSpI+54tEIHgGTmcd83L0KxVUyY/Nu1TPbO3+5DRaRxV3iATbs/hLZwd1cTz0UFt/6QhjMuP5ySKe3+F7F+f1TXjJ+8fiCtct2548pww+wR2LizHmfa/WDQ5bMOqxk3zB7Ro5CT5znMG1+GXfUtUDUW3i7TA5FI8MYYEFC0LlUskUCnu6yGR1ZwOiwwtltMcErmpL7EB1Zy0snL6bwfALT5g3D7FWx8pw4ASNhKEAQRxrBmZLCjagznOgI46/JHu6jG8vcTrbhx8248/MbBuECk2GrGI9+ejLu+MRFWUcAru/Uuq6PK7BheYkNViYQRQ+yYUFkEjXH4+fvH8JVqZ6cOIYnuocgi4HyHjMONHbCJAiocFjitQrTShIc+cI/jOPAcBxMPvRKFAZOGOQz5bVR/8VFdM17+pAECB1SXWFFTakN1iRUCx+HlTxp6FHJqGsP7XzTDbhGivVYil9smCrCLAkQzD28ghHMeGT5ZwaQqR1xAlEqIy8Bwzh2AqjFYzQKKreZufYlsWU2qcsAnK4bfDwA6AiE0ugJgYCi2kbCVIAgiFsqMGKAjEEKrN9ilS2qEvxw4i/VvfxHNUEQQBQ42URehAkBdkxcnW7xwSmbw0PuJmHhTNF1fYkNcRUgyHUKkFXznEX0IHgcePM9B1Zje/p1n0S0SVdPLhwWOw6HGDkO6BSN6iK9UO6OBS1WxNe71xVaWVp+RyPtVOCRYzDwCQa1T+yLqGhKfrOC/Fl2YUu+RKqvhDoTgD6kwCRwqYsp1k/kSuUY9NU7r7v0CiorT7X4AwPASK6xm/deOhuoRBEHoUGYkDUKqhkZXAOc75KSBiKoxvPJJA9ZtPxoXiAg8h+piCSOH2hAIaeFsiD5hN6Tpegue56L/RoitCElVzREIapAVVe9NElNVomgaOADhzvV6UKLqA/Iks4DhpVbwPJeWZiQWI+W6RgKXdN6PAwerKMAhmfVOt+Ci7zekSMT8CeWY3EMDuLisRlAN3xsriixd4/FUpceRLSuj7+fyh8BzHKqKrXBI8QMK070eBEEQAxnKjPSAyxdCmy+YtGcIADS0+PDI9sM4dDZeA+KUTCgvskAIL1gOyYyTLV7UNXlRLIkwh4MIc5LFXVY1mDig1ROE2x8CA4OsqLDGDMmLlLiGq3+jVSWRRm0cx4EB+mLL6QtsucOCgKLBzGtpa0Yi81iON3vDtqmw8l1/bGKrSnrbwRXofeO1WBKzGq2eIB7ddgiiKbl9qc6d7tC/xPc7cd6LDe/WocSafFJyOteDIAhiIEPBSAqCil5pIYfUpF9XNYbf7zmFzR8e75INqXRYujxxiwKHjnBWZN74ckwY5sDhRk90pk0ExhjOuWXwPPDY9sMIqQwdAQUufwjDSzqfrPXgg0FVAWtMVUmkKZtXVsGgi1kjnPfIsJoFfHVkaVozU2I7lwYVDe6AgnZ/MM6OiM2xVSW1Z9xJy3Ij5cXpBBLZKA+OJVaIq2kMW/eeMnRuo11cY98vm4EVQRDEQIS2aRKIdFE93e5PGYicbPXhR1v24efvH4sLRCQTjyqnlDT1H1QZzByHUUPtqCqx4vYF45I2FWto9cMXVMDCVR4VDgvKiixQNYaGVh9avLIurORYNPtRVmSJLqgcx8Es8EiWx9EY4A2qGBHequmOxM6llU4J5Q4xakerN5iyEVokkGhyyzje7MWXrV6cavPjy1Yvjjd7cc4tY0y5Xa86Onoe+0+5ujQC623jte4weu7ednHtbUdbgiCIgQ7HEv86FiButxvFxcVwuVxwOnP3BzsQ0st1kw2uA/RsyNbPTuH5D0/EvWaIXcSdC8fj9X1ncOy8B2VFYngWjI4uNg3hK9UO/PL/zE4+M0VjMHH6JFjGWJdJsB2BEE63+8GBg9NqgijwGFok4lyHDFVDVCzpDyk43uyLltLq7x///xKbGX//8UKYUmxTaBrDTS/sxqGz7rh5LLF28BwHp2ROmSHY9H49Htl2JFqWy4f7gyiqLqgdOdQGOaT1mGVIvEZmPnvlsOmcu7trwZguxp1U5cBLS2elOfRPTVoenO3hfgRBEIVAuus3BSPQF5VWbxCumC2NRE61+fDotiM4kCAyXDipAsu/Ng5Oqxl7G9rw+F+PwhdU4ZDMEAUOQZXBIytwSqakC06sDqHVE8Rj2w/DbjFBMndN5/tDClw+BcuuGIcZI/Stlo+PtcQtqCFFRbtfgYnXt3IYOnuYcABUxqBpDOu+Mw3/9tXhSX3df8qF//zV31Pa4Qvq20Y//Nr46JZP7EIcWcD/caodisriGpZFOsoKPIeRQ22wCAKCqoa2bhbldLUamdDTuXu6Fv6QCp+s4OdLZvZYnZTLwIogCKIQSXf9HvSakUjzsmQ9QwC9gdkf9p7Gc387DjkmG1JqM2PF1yfg0phFZPqIUqz4+gS8svskTrZ44WGARdC3LdLRFrx39HwPwk8B4BSMLrOnLDl9u7YJv979JQRe7y/CAXHDenkwqABOt/tSXpOeBKiSSYCbUzCq3J50AU5VlitwHBo7AuBUPQAE06uIeipxTdWILhv0dO5siHEjpFMeTBAEMRgZ9MFIuz+YMhA53ebHo9uPYP9pV9zxf7qwAsuvGIfiJNUR00eUYlpNKRpdAYQ0DUPtlrQXnEyFjrELaqsniFd2fwktPEwuEY3pscnwElvW7YiQrCwXEOAPqggqGgSBg6ZFypH18xfq7JZsi09zGVgRBEH0VwZ9MJIMjTG8vvcMnvvbMQQSsiF3LJyAy8enTqmbwyW0YyuKDL9vNipIrppShQf/XAuXLwSe08BznU/0GtMHzRXbzLhqSlXO7Ei1gEfLkYGkQ+4KscQ121U9BEEQRFeomiaBM+1+/N/ffo4N79bFBSILJpRj802XdBuIFFvNuKDUmlRbkA7ZqCAxmXgsWzAWAs8hqDAomqYHIZqGoMIg8ByWLRibUryaDTtSVY9EeqCoGoPFJEASU0/cLRRyWdVDEARB6Ax6AetZlx/+oAqNMfxx3xn84m/HEAh1BiHFVjPuWDge8yeUpzyHWeBRVmQJb0f0nmwIHTe9X4+NO+vR4Q/FDalbtmAsbp03Nud2JKseCSgqGlp9UDWGEUNsXXqVpFuZkg+6uxakAyEIgkgOVdOkyVmXH8fOe/DY9iPYdzJeGzJvfBl+tHA8Srt5Ui+STCizW7K++GSjgkRRNPzpH2dxut2H4SU2XDWlqtuMSLbtSLaAJytH7i8lrsmuRVw1UxrN0AiCIAYTFIykgT6Jtg5PvVMXlw1xSib86J/GY8HE8i6zVSIIPIeyIr35FZGaHhfwflzi2pn9UVBqEyEKfI9lygRBEIMJKu3tgVNtPtz92j/wYV1L3PHLxpXhjoXjMcSeOhtiE00od3TOnSFSk6x6ZCCUuOqBrD6ZOLYZGk3iJQiCMM6gDUbW/uVwXCDilEz44RXjccWFqbMhPMdhSJEIp5R84BmRPv29xNXIZOL+7CdBEERfMGiDkfv/90V4/+h5uAMKLh07FHd+fUK32RCLWUCFw5J0ym6+yWeH0sFKNpuhAXSdCYIY3AzaYKTSKWH1tybjfIeMeePLUmZDOI5DidWM0m4ClVyQ7uJkdJqsEXJ57v5ObC+VTCcTR6DrTBDEYGdQC1iBztLeZEQamGXaNyRT0l2ccimgJHFm90Tm73x+0gVV0+Lm74gCD4HnMbWm2MAAPbrOBEEMPNJdvwtvz6FAcPaygVmmpDuuPlFAKZkFfc6LWcAwpwUeWcUz79VD04zHmrk890CB5znMG18GX1CBLxzMRnZsfEEVvqCCeePLug1E6DoTBEHoUDCSgInnMaxYQlmRJeXWTa4wsjgZEVAaJZfnHihoGsP7XzTDbhFgCze7i4w4sokC7BYB73/R3G0gQdeZIAhCZ9BqRpJRZDFhaFH+SnaNLE7ZFlDGkstzDxRSTSY28TwkUdeQ9FRNQ9eZIAhCh4IR6CW7Q4vEuPbk+cDI4pTtabKx5PLcA4VUk4kjpBNI0HUmCILQGfTbNFazgAtKrXkPRID4xSkZsYtTqmF0QOc02bEVRRlNk83luQcKRu5VKug6EwRB6Az6YKTEJsJUIL1DjCxOuZwmS5NqeyYbgQRdZ4IgCJ3CWIUJAMYXp7njyrD63yZjUpUDPlnBOY8Mn6xgUpWj1yWhuTz3QCBbgQRdZ4IgCOozUpB0N64+2eJEHVjzh9F7lQq6zgRBDERoam8/hxan/gPdK4IgiOTQ1N5+Tn8fJDeYoHtFEATRO0gzQhAEQRBEXskoGNm4cSNGjRoFSZIwe/Zs7N69O+Vra2tr8e1vfxujRo0Cx3FYv359prYSBEEQBDEAMRyM/OY3v8GKFSuwcuVKfPbZZ5g6dSoWLVqEc+fOJX29z+fDmDFjsHbtWgwbNqzXBhMEQRAEMbAwHIw8/vjjuPXWW7F06VJcdNFFePbZZ2Gz2bB58+akr7/kkkvw2GOP4brrroPFYum1wQRBEARBDCwMBSPBYBB79uzBwoULO0/A81i4cCF27dqVNaNkWYbb7Y77IAiCIAhiYGIoGGluboaqqqisrIw7XllZicbGxqwZtWbNGhQXF0c/ampqsnZugiAIgiAKi4Ksprn33nvhcrmiHydPnsy3SQRBEARB5AhDfUbKysogCAKamprijjc1NWVVnGqxWEhfQhAEQRCDBEOZEVEUMWPGDOzYsSN6TNM07NixA3PmzMm6cQRBEARBDHwMd2BdsWIFbrrpJsycOROzZs3C+vXr4fV6sXTpUgDAjTfeiOHDh2PNmjUAdNHrwYMHo/8/ffo09u3bh6KiIowbNy6LrhAEQRAE0R8xHIwsXrwY58+fxwMPPIDGxkZMmzYN27Zti4paGxoawPOdCZczZ85g+vTp0c/XrVuHdevWYf78+di5c2fvPSAIgiAIol/TLwbluVwulJSU4OTJk4NmUB5BEARB9HfcbjdqamrQ3t6O4uLUM7z6xaC8jo4OAKASX4IgCILoh3R0dHQbjPSLzIimaThz5gwcDgc4Lnuj2SMR20DOuAx0H8m//s9A95H86/8MdB9z6R9jDB0dHaiuro6TcCTSLzIjPM/jggsuyNn5nU7ngPwBi2Wg+0j+9X8Guo/kX/9noPuYK/+6y4hEKMimZwRBEARBDB4oGCEIgiAIIq8M6mDEYrFg5cqVA7rb60D3kfzr/wx0H8m//s9A97EQ/OsXAlaCIAiCIAYugzozQhAEQRBE/qFghCAIgiCIvELBCEEQBEEQeYWCEYIgCIIg8sqAD0Y2btyIUaNGQZIkzJ49G7t370752traWnz729/GqFGjwHEc1q9f33eG9gIjPm7atAmXX345SktLUVpaioULF3b7+kLAiH9bt27FzJkzUVJSArvdjmnTpuFXv/pVH1prHCP+xbJlyxZwHIdrrrkmtwZmASM+vvjii+A4Lu5DkqQ+tNY4Ru9he3s7li1bhqqqKlgsFkyYMAFvvvlmH1lrHCP+LViwoMv94zgO3/zmN/vQYuMYvYfr16/HxIkTYbVaUVNTgzvvvBOBQKCPrDWOEf9CoRAeeughjB07FpIkYerUqdi2bVtuDWQDmC1btjBRFNnmzZtZbW0tu/XWW1lJSQlrampK+vrdu3ezu+66i7366qts2LBh7IknnuhbgzPAqI/XX38927hxI9u7dy87dOgQu/nmm1lxcTE7depUH1ueHkb9e/fdd9nWrVvZwYMHWV1dHVu/fj0TBIFt27atjy1PD6P+RTh+/DgbPnw4u/zyy9nVV1/dN8ZmiFEfX3jhBeZ0OtnZs2ejH42NjX1sdfoY9U+WZTZz5kx25ZVXsg8++IAdP36c7dy5k+3bt6+PLU8Po/61tLTE3bsDBw4wQRDYCy+80LeGG8Cojy+//DKzWCzs5ZdfZsePH2fbt29nVVVV7M477+xjy9PDqH///d//zaqrq9kbb7zB6uvr2dNPP80kSWKfffZZzmwc0MHIrFmz2LJly6Kfq6rKqqur2Zo1a3r83pEjR/aLYKQ3PjLGmKIozOFwsJdeeilXJvaK3vrHGGPTp09nP/nJT3JhXq/JxD9FUdjcuXPZc889x2666aaCD0aM+vjCCy+w4uLiPrKu9xj175lnnmFjxoxhwWCwr0zsFb39HXziiSeYw+FgHo8nVyb2GqM+Llu2jF1xxRVxx1asWMEuvfTSnNqZKUb9q6qqYhs2bIg79q1vfYvdcMMNObNxwG7TBINB7NmzBwsXLowe43keCxcuxK5du/JoWfbIho8+nw+hUAhDhgzJlZkZ01v/GGPYsWMHjhw5gnnz5uXS1IzI1L+HHnoIFRUVuOWWW/rCzF6RqY8ejwcjR45ETU0Nrr76atTW1vaFuYbJxL8//vGPmDNnDpYtW4bKykpcfPHFWL16NVRV7Suz0yYbf2Oef/55XHfddbDb7bkys1dk4uPcuXOxZ8+e6FbHsWPH8Oabb+LKK6/sE5uNkIl/six32Rq1Wq344IMPcmZnvxiUlwnNzc1QVRWVlZVxxysrK3H48OE8WZVdsuHj3Xffjerq6rgf1EIhU/9cLheGDx8OWZYhCAKefvppfP3rX8+1uYbJxL8PPvgAzz//PPbt29cHFvaeTHycOHEiNm/ejClTpsDlcmHdunWYO3cuamtrczowMxMy8e/YsWN45513cMMNN+DNN99EXV0dbr/9doRCIaxcubIvzE6b3v6N2b17Nw4cOIDnn38+Vyb2mkx8vP7669Hc3IzLLrsMjDEoioLvf//7+PGPf9wXJhsiE/8WLVqExx9/HPPmzcPYsWOxY8cObN26NacB84DNjBA9s3btWmzZsgV/+MMfCl4gaASHw4F9+/bh008/xapVq7BixQrs3Lkz32b1mo6ODixZsgSbNm1CWVlZvs3JGXPmzMGNN96IadOmYf78+di6dSvKy8vx85//PN+mZQVN01BRUYFf/OIXmDFjBhYvXoz77rsPzz77bL5NyzrPP/88Jk+ejFmzZuXblKyyc+dOrF69Gk8//TQ+++wzbN26FW+88QYefvjhfJuWFZ588kmMHz8eF154IURRxPLly7F06VLwfO5ChgGbGSkrK4MgCGhqaoo73tTUhGHDhuXJquzSGx/XrVuHtWvX4u2338aUKVNyaWbGZOofz/MYN24cAGDatGk4dOgQ1qxZgwULFuTSXMMY9a++vh4nTpzAVVddFT2maRoAwGQy4ciRIxg7dmxujTZINn4PzWYzpk+fjrq6ulyY2Csy8a+qqgpmsxmCIESPTZo0CY2NjQgGgxBFMac2G6E398/r9WLLli146KGHcmlir8nEx/vvvx9LlizB9773PQDA5MmT4fV6cdttt+G+++7L6aJtlEz8Ky8vx+uvv45AIICWlhZUV1fjnnvuwZgxY3JmZ+FcsSwjiiJmzJiBHTt2RI9pmoYdO3Zgzpw5ebQse2Tq46OPPoqHH34Y27Ztw8yZM/vC1IzI1j3UNA2yLOfCxF5h1L8LL7wQ+/fvx759+6If//qv/4qvfe1r2LdvH2pqavrS/LTIxj1UVRX79+9HVVVVrszMmEz8u/TSS1FXVxcNJAHg6NGjqKqqKqhABOjd/fvd734HWZbxH//xH7k2s1dk4qPP5+sScESCS1Zg4956cw8lScLw4cOhKApee+01XH311bkzNGfS2AJgy5YtzGKxsBdffJEdPHiQ3XbbbaykpCRaJrhkyRJ2zz33RF8vyzLbu3cv27t3L6uqqmJ33XUX27t3L/viiy/y5UKPGPVx7dq1TBRF9vvf/z6u/K6joyNfLnSLUf9Wr17N3nrrLVZfX88OHjzI1q1bx0wmE9u0aVO+XOgWo/4l0h+qaYz6+OCDD7Lt27ez+vp6tmfPHnbdddcxSZJYbW1tvlzoFqP+NTQ0MIfDwZYvX86OHDnC/vznP7OKigr2s5/9LF8udEumP6OXXXYZW7x4cV+bmxFGfVy5ciVzOBzs1VdfZceOHWNvvfUWGzt2LLv22mvz5UK3GPXv448/Zq+99hqrr69n77//PrviiivY6NGjWVtbW85sHNDBCGOMPfXUU2zEiBFMFEU2a9Ys9vHHH0e/Nn/+fHbTTTdFPz9+/DgD0OVj/vz5fW+4AYz4OHLkyKQ+rly5su8NTxMj/t13331s3LhxTJIkVlpayubMmcO2bNmSB6vTx4h/ifSHYIQxYz7ecccd0ddWVlayK6+8Mqf9DbKB0Xv40UcfsdmzZzOLxcLGjBnDVq1axRRF6WOr08eof4cPH2YA2FtvvdXHlmaOER9DoRD76U9/ysaOHcskSWI1NTXs9ttvz+li3VuM+Ldz5042adIkZrFY2NChQ9mSJUvY6dOnc2ofx1iB5ZQIgiAIghhUDFjNCEEQBEEQ/QMKRgiCIAiCyCsUjBAEQRAEkVcoGCEIgiAIIq9QMEIQBEEQRF6hYIQgCIIgiLxCwQhBEARBEHmFghGCIAiCIPIKBSMEQRAEQeQVCkYIgjDMggULcMcdd+TbjCiFZg9BEMagYIQgiLwQDAbzbQJBEAUCBSMEQRji5ptvxnvvvYcnn3wSHMeB4zjU19fjlltuwejRo2G1WjFx4kQ8+eSTXb7vmmuuwapVq1BdXY2JEycCAD766CNMmzYNkiRh5syZeP3118FxHPbt2xf93gMHDuBf/uVfUFRUhMrKSixZsgTNzc0p7Tlx4kRfXQ6CILKAKd8GEATRv3jyySdx9OhRXHzxxXjooYcAAKWlpbjgggvwu9/9DkOHDsVHH32E2267DVVVVbj22muj37tjxw44nU789a9/BQC43W5cddVVuPLKK/HKK6/gyy+/7LLd0t7ejiuuuALf+9738MQTT8Dv9+Puu+/Gtddei3feeSepPeXl5X1zMQiCyAoUjBAEYYji4mKIogibzYZhw4ZFjz/44IPR/48ePRq7du3Cb3/727hgxG6347nnnoMoigCAZ599FhzHYdOmTZAkCRdddBFOnz6NW2+9Nfo9GzZswPTp07F69erosc2bN6OmpgZHjx7FhAkTktpDEET/gYIRgiCywsaNG7F582Y0NDTA7/cjGAxi2rRpca+ZPHlyNBABgCNHjmDKlCmQJCl6bNasWXHf8/nnn+Pdd99FUVFRl/esr6/HhAkTsusIQRB9DgUjBEH0mi1btuCuu+7C//zP/2DOnDlwOBx47LHH8Mknn8S9zm63Gz63x+PBVVddhUceeaTL16qqqjK2mSCIwoGCEYIgDCOKIlRVjX7+4YcfYu7cubj99tujx+rr63s8z8SJE/HrX/8asizDYrEAAD799NO413z1q1/Fa6+9hlGjRsFkSv4nK9EegiD6F1RNQxCEYUaNGoVPPvkEJ06cQHNzM8aPH4+///3v2L59O44ePYr777+/S1CRjOuvvx6apuG2227DoUOHsH37dqxbtw4AwHEcAGDZsmVobW3Fd7/7XXz66aeor6/H9u3bsXTp0mgAkmiPpmm5c54giKxDwQhBEIa56667IAgCLrroIpSXl2PRokX41re+hcWLF2P27NloaWmJy5Kkwul04k9/+hP27duHadOm4b777sMDDzwAAFEdSXV1NT788EOoqopvfOMbmDx5Mu644w6UlJSA5/mk9jQ0NOTOeYIgsg7HGGP5NoIgCCLCyy+/jKVLl8LlcsFqtebbHIIg+gDSjBAEkVd++ctfYsyYMRg+fDg+//zzaA8RCkQIYvBAwQhBEHmlsbERDzzwABobG1FVVYXvfOc7WLVqVb7NIgiiD6FtGoIgCIIg8goJWAmCIAiCyCsUjBAEQRAEkVcoGCEIgiAIIq9QMEIQBEEQRF6hYIQgCIIgiLxCwQhBEARBEHmFghGCIAiCIPIKBSMEQRAEQeSV/w/2HFXAGcJuDAAAAABJRU5ErkJggg=="},"metadata":{}}]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.preprocessing import StandardScaler\n\n#pipeline helps in preventing leaks from test data to train data\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.metrics import accuracy_score,mean_squared_error,mean_absolute_error,r2_score\n\nX_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3,random_state=42)\nsc = StandardScaler()\nsc_X_train = sc.fit_transform(X_train)\nsc_X_test = sc.fit_transform(X_test)\n\nfrom sklearn.decomposition import PCA\npca = PCA(n_components=3)\nX_train_pca = pca.fit_transform(X_train)\nX_test_pca = pca.fit_transform(X_test)\n\n\nlr = LinearRegression()\nlr.fit(X_train_pca,y_train)\n\ny_pred = lr.predict(X_test_pca)\n\nprint(\"MSE Score after PCA is \", mean_squared_error(y_test,y_pred))\nprint(\"RMSE Score after PCA is \", np.sqrt(mean_squared_error(y_test,y_pred)))\nprint(\"R2 Score after PCA is \", r2_score(y_test,y_pred))","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:44:57.066582Z","iopub.execute_input":"2024-02-15T23:44:57.067506Z","iopub.status.idle":"2024-02-15T23:44:57.108950Z","shell.execute_reply.started":"2024-02-15T23:44:57.067475Z","shell.execute_reply":"2024-02-15T23:44:57.107467Z"},"trusted":true},"execution_count":141,"outputs":[{"name":"stdout","text":"MSE Score after PCA is  0.07031204424491692\nRMSE Score after PCA is  0.2651641835635366\nR2 Score after PCA is  0.13157458138114042\n","output_type":"stream"}]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\npca = PCA().fit(sc_X_train)  # Assuming X_scaled is your standardized dataset\nexplained_variance = pca.explained_variance_ratio_\n\nplt.figure(figsize=(8, 4))\nplt.plot(range(1, len(explained_variance) + 1), explained_variance, marker='o', linestyle='--')\nplt.title('Scree Plot')\nplt.xlabel('Number of Components')\nplt.ylabel('Variance Explained')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:44:59.910582Z","iopub.execute_input":"2024-02-15T23:44:59.911450Z","iopub.status.idle":"2024-02-15T23:45:00.180438Z","shell.execute_reply.started":"2024-02-15T23:44:59.911416Z","shell.execute_reply":"2024-02-15T23:45:00.179576Z"},"trusted":true},"execution_count":142,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 800x400 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"print(\"MSE Score after PCA is \", mean_squared_error(y_train,lr.predict(X_train_pca)))\nprint(\"RMSE Score after PCA is \", np.sqrt(mean_squared_error(y_train,lr.predict(X_train_pca))))\nprint(\"R2 Score after PCA is \", r2_score(y_train,lr.predict(X_train_pca)))","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:46:20.906362Z","iopub.execute_input":"2024-02-15T23:46:20.906750Z","iopub.status.idle":"2024-02-15T23:46:20.915795Z","shell.execute_reply.started":"2024-02-15T23:46:20.906719Z","shell.execute_reply":"2024-02-15T23:46:20.914925Z"},"trusted":true},"execution_count":145,"outputs":[{"name":"stdout","text":"MSE Score after PCA is  0.0662076291075095\nRMSE Score after PCA is  0.25730843186244307\nR2 Score after PCA is  0.19006238267436248\n","output_type":"stream"}]},{"cell_type":"code","source":"# We can observe that the model is perfroming not so different in training data as well","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:12:14.591959Z","iopub.execute_input":"2024-02-15T23:12:14.592930Z","iopub.status.idle":"2024-02-15T23:12:14.598632Z","shell.execute_reply.started":"2024-02-15T23:12:14.592896Z","shell.execute_reply":"2024-02-15T23:12:14.597751Z"},"trusted":true},"execution_count":115,"outputs":[{"name":"stdout","text":"RMSE Score after PCA is  0.25730843186244307\n","output_type":"stream"}]},{"cell_type":"code","source":"X.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:27:12.044302Z","iopub.execute_input":"2024-02-15T23:27:12.045128Z","iopub.status.idle":"2024-02-15T23:27:12.058283Z","shell.execute_reply.started":"2024-02-15T23:27:12.045097Z","shell.execute_reply":"2024-02-15T23:27:12.057296Z"},"trusted":true},"execution_count":119,"outputs":[{"execution_count":119,"output_type":"execute_result","data":{"text/plain":"   age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  \\\n0   52    1   0       125   212    0        1      168      0      1.0      2   \n1   53    1   0       140   203    1        0      155      1      3.1      0   \n2   70    1   0       145   174    0        1      125      1      2.6      0   \n3   61    1   0       148   203    0        1      161      0      0.0      2   \n4   62    0   0       138   294    1        1      106      0      1.9      1   \n\n   ca  thal  \n0   2     3  \n1   0     3  \n2   0     3  \n3   1     3  \n4   3     2  ","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>age</th>\n      <th>sex</th>\n      <th>cp</th>\n      <th>trestbps</th>\n      <th>chol</th>\n      <th>fbs</th>\n      <th>restecg</th>\n      <th>thalach</th>\n      <th>exang</th>\n      <th>oldpeak</th>\n      <th>slope</th>\n      <th>ca</th>\n      <th>thal</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>52</td>\n      <td>1</td>\n      <td>0</td>\n      <td>125</td>\n      <td>212</td>\n      <td>0</td>\n      <td>1</td>\n      <td>168</td>\n      <td>0</td>\n      <td>1.0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>53</td>\n      <td>1</td>\n      <td>0</td>\n      <td>140</td>\n      <td>203</td>\n      <td>1</td>\n      <td>0</td>\n      <td>155</td>\n      <td>1</td>\n      <td>3.1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>70</td>\n      <td>1</td>\n      <td>0</td>\n      <td>145</td>\n      <td>174</td>\n      <td>0</td>\n      <td>1</td>\n      <td>125</td>\n      <td>1</td>\n      <td>2.6</td>\n      <td>0</td>\n      <td>0</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>61</td>\n      <td>1</td>\n      <td>0</td>\n      <td>148</td>\n      <td>203</td>\n      <td>0</td>\n      <td>1</td>\n      <td>161</td>\n      <td>0</td>\n      <td>0.0</td>\n      <td>2</td>\n      <td>1</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>62</td>\n      <td>0</td>\n      <td>0</td>\n      <td>138</td>\n      <td>294</td>\n      <td>1</td>\n      <td>1</td>\n      <td>106</td>\n      <td>0</td>\n      <td>1.9</td>\n      <td>1</td>\n      <td>3</td>\n      <td>2</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"y.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:27:17.224938Z","iopub.execute_input":"2024-02-15T23:27:17.225271Z","iopub.status.idle":"2024-02-15T23:27:17.232876Z","shell.execute_reply.started":"2024-02-15T23:27:17.225248Z","shell.execute_reply":"2024-02-15T23:27:17.231747Z"},"trusted":true},"execution_count":120,"outputs":[{"execution_count":120,"output_type":"execute_result","data":{"text/plain":"0    0.23\n1    0.37\n2    0.24\n3    0.28\n4    0.21\nName: target, dtype: float64"},"metadata":{}}]},{"cell_type":"code","source":"print(\"Shape of X is\", X.shape)\nprint(\"Shape of y is\", y.shape)","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:27:51.315767Z","iopub.execute_input":"2024-02-15T23:27:51.316464Z","iopub.status.idle":"2024-02-15T23:27:51.321414Z","shell.execute_reply.started":"2024-02-15T23:27:51.316437Z","shell.execute_reply":"2024-02-15T23:27:51.320401Z"},"trusted":true},"execution_count":122,"outputs":[{"name":"stdout","text":"Shape of X is (1025, 13)\nShape of y is (1025,)\n","output_type":"stream"}]},{"cell_type":"code","source":"#Using cross-validation for better evaluation of the model\n\nfrom sklearn.model_selection import KFold\n\nmodel = LinearRegression()\nk = 5\nkf = KFold(n_splits=k, shuffle=True, random_state=1)\n\nmse_scores = []\nrmse_scores = []\nr2_scores = []\n\nfor train_index, test_index in kf.split(X):\n    X_train, X_test = X.iloc[train_index], X.iloc[test_index]\n    y_train, y_test = y.iloc[train_index], y.iloc[test_index]\n    \n    model.fit(X_train,y_train)\n    y_pred = model.predict(X_test)\n    \n    mse = mean_squared_error(y_test,y_pred)\n    mse_scores.append(mse)\n    \n    rmse = np.sqrt(mse)\n    rmse_scores.append(rmse)\n    \n    r2 = r2_score(y_test,y_pred)\n    r2_scores.append(r2)\n\naverage_mse = np.mean(mse_scores)\nprint(f\"Average MSE is {average_mse}\")\nstd_mse = np.std(mse_scores)\nprint(f\"Standard Deviation of MSE is {std_mse}\")\n\naverage_rmse = np.mean(rmse_scores)\nprint(f\"Average RMSE is {average_rmse}\")\nstd_rmse = np.std(rmse_scores)\nprint(f\"Standard Deviation of RMSE is {std_rmse}\")\n\naverage_r2 = np.mean(r2_scores)\nprint(f\"Average R2 is {average_r2}\")\nstd_r2 = np.std(r2_scores)\nprint(f\"Standard Deviation of R2 is {std_r2}\")","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:47:39.930552Z","iopub.execute_input":"2024-02-15T23:47:39.930931Z","iopub.status.idle":"2024-02-15T23:47:39.971095Z","shell.execute_reply.started":"2024-02-15T23:47:39.930900Z","shell.execute_reply":"2024-02-15T23:47:39.969928Z"},"trusted":true},"execution_count":146,"outputs":[{"name":"stdout","text":"Average MSE is 0.044857656897393405\nStandard Deviation of MSE is 0.003363270620965198\nAverage RMSE is 0.21164807882697975\nStandard Deviation of RMSE is 0.007921339927181142\nAverage R2 is 0.44830803707670663\nStandard Deviation of R2 is 0.040992223533728514\n","output_type":"stream"}]},{"cell_type":"code","source":"# We can observe that PCA did increase the R2 score and now the model can explain more variance in the dep variable that before","metadata":{"execution":{"iopub.status.busy":"2024-02-15T23:48:57.027929Z","iopub.execute_input":"2024-02-15T23:48:57.028575Z","iopub.status.idle":"2024-02-15T23:48:57.033516Z","shell.execute_reply.started":"2024-02-15T23:48:57.028546Z","shell.execute_reply":"2024-02-15T23:48:57.032644Z"},"trusted":true},"execution_count":147,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}