{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"authorship_tag":"ABX9TyMGnhGk2whuZ/KRzXsaWsYW"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","execution_count":1,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":224},"id":"pR7uT2jT-GKr","executionInfo":{"status":"ok","timestamp":1744091920823,"user_tz":-330,"elapsed":27804,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"1ce56e47-347a-4869-c52d-2b0bbf1d61e4"},"outputs":[{"output_type":"stream","name":"stdout","text":["Mounted at /content/drive\n"]},{"output_type":"execute_result","data":{"text/plain":["   match_id  inning           batting_team                 bowling_team  over  \\\n","0    335982       1  Kolkata Knight Riders  Royal Challengers Bangalore     0   \n","1    335982       1  Kolkata Knight Riders  Royal Challengers Bangalore     0   \n","2    335982       1  Kolkata Knight Riders  Royal Challengers Bangalore     0   \n","3    335982       1  Kolkata Knight Riders  Royal Challengers Bangalore     0   \n","4    335982       1  Kolkata Knight Riders  Royal Challengers Bangalore     0   \n","\n","   ball       batter   bowler  non_striker  batsman_runs  extra_runs  \\\n","0     1   SC Ganguly  P Kumar  BB McCullum             0           1   \n","1     2  BB McCullum  P Kumar   SC Ganguly             0           0   \n","2     3  BB McCullum  P Kumar   SC Ganguly             0           1   \n","3     4  BB McCullum  P Kumar   SC Ganguly             0           0   \n","4     5  BB McCullum  P Kumar   SC Ganguly             0           0   \n","\n","   total_runs extras_type  is_wicket player_dismissed dismissal_kind fielder  \n","0           1     legbyes          0              NaN            NaN     NaN  \n","1           0         NaN          0              NaN            NaN     NaN  \n","2           1       wides          0              NaN            NaN     NaN  \n","3           0         NaN          0              NaN            NaN     NaN  \n","4           0         NaN          0              NaN            NaN     NaN  "],"text/html":["\n","  <div id=\"df-d6d1ad34-ebe4-44b2-93c6-b4235536c184\" class=\"colab-df-container\">\n","    <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>match_id</th>\n","      <th>inning</th>\n","      <th>batting_team</th>\n","      <th>bowling_team</th>\n","      <th>over</th>\n","      <th>ball</th>\n","      <th>batter</th>\n","      <th>bowler</th>\n","      <th>non_striker</th>\n","      <th>batsman_runs</th>\n","      <th>extra_runs</th>\n","      <th>total_runs</th>\n","      <th>extras_type</th>\n","      <th>is_wicket</th>\n","      <th>player_dismissed</th>\n","      <th>dismissal_kind</th>\n","      <th>fielder</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>335982</td>\n","      <td>1</td>\n","      <td>Kolkata Knight Riders</td>\n","      <td>Royal Challengers Bangalore</td>\n","      <td>0</td>\n","      <td>1</td>\n","      <td>SC Ganguly</td>\n","      <td>P Kumar</td>\n","      <td>BB McCullum</td>\n","      <td>0</td>\n","      <td>1</td>\n","      <td>1</td>\n","      <td>legbyes</td>\n","      <td>0</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>335982</td>\n","      <td>1</td>\n","      <td>Kolkata Knight Riders</td>\n","      <td>Royal Challengers Bangalore</td>\n","      <td>0</td>\n","      <td>2</td>\n","      <td>BB McCullum</td>\n","      <td>P Kumar</td>\n","      <td>SC Ganguly</td>\n","      <td>0</td>\n","      <td>0</td>\n","      <td>0</td>\n","      <td>NaN</td>\n","      <td>0</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>335982</td>\n","      <td>1</td>\n","      <td>Kolkata Knight Riders</td>\n","      <td>Royal Challengers Bangalore</td>\n","      <td>0</td>\n","      <td>3</td>\n","      <td>BB McCullum</td>\n","      <td>P Kumar</td>\n","      <td>SC Ganguly</td>\n","      <td>0</td>\n","      <td>1</td>\n","      <td>1</td>\n","      <td>wides</td>\n","      <td>0</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>335982</td>\n","      <td>1</td>\n","      <td>Kolkata Knight Riders</td>\n","      <td>Royal Challengers Bangalore</td>\n","      <td>0</td>\n","      <td>4</td>\n","      <td>BB McCullum</td>\n","      <td>P Kumar</td>\n","      <td>SC Ganguly</td>\n","      <td>0</td>\n","      <td>0</td>\n","      <td>0</td>\n","      <td>NaN</td>\n","      <td>0</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>335982</td>\n","      <td>1</td>\n","      <td>Kolkata Knight Riders</td>\n","      <td>Royal Challengers Bangalore</td>\n","      <td>0</td>\n","      <td>5</td>\n","      <td>BB McCullum</td>\n","      <td>P Kumar</td>\n","      <td>SC Ganguly</td>\n","      <td>0</td>\n","      <td>0</td>\n","      <td>0</td>\n","      <td>NaN</td>\n","      <td>0</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","    <div class=\"colab-df-buttons\">\n","\n","  <div class=\"colab-df-container\">\n","    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d6d1ad34-ebe4-44b2-93c6-b4235536c184')\"\n","            title=\"Convert this dataframe to an interactive table.\"\n","            style=\"display:none;\">\n","\n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n","    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n","  </svg>\n","    </button>\n","\n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    .colab-df-buttons div {\n","      margin-bottom: 4px;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","    <script>\n","      const buttonEl =\n","        document.querySelector('#df-d6d1ad34-ebe4-44b2-93c6-b4235536c184 button.colab-df-convert');\n","      buttonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","      async function convertToInteractive(key) {\n","        const element = document.querySelector('#df-d6d1ad34-ebe4-44b2-93c6-b4235536c184');\n","        const dataTable =\n","          await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                    [key], {});\n","        if (!dataTable) return;\n","\n","        const docLinkHtml = 'Like what you see? Visit the ' +\n","          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","          + ' to learn more about interactive tables.';\n","        element.innerHTML = '';\n","        dataTable['output_type'] = 'display_data';\n","        await google.colab.output.renderOutput(dataTable, element);\n","        const docLink = document.createElement('div');\n","        docLink.innerHTML = docLinkHtml;\n","        element.appendChild(docLink);\n","      }\n","    </script>\n","  </div>\n","\n","\n","<div id=\"df-54c59ebe-0339-4ea6-ac3f-8b4c967864eb\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-54c59ebe-0339-4ea6-ac3f-8b4c967864eb')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-54c59ebe-0339-4ea6-ac3f-8b4c967864eb button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","\n","    </div>\n","  </div>\n"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"dataframe","variable_name":"deliveries_df"}},"metadata":{},"execution_count":1}],"source":["# Mount Google Drive\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","# Load deliveries data\n","import pandas as pd\n","\n","deliveries_path = '/content/drive/MyDrive/Colab Notebooks/IPLPrediction/deliveries.csv'\n","deliveries_df = pd.read_csv(deliveries_path)\n","\n","# Show initial structure\n","deliveries_df.head()"]},{"cell_type":"code","source":["# STEP 1: Mount Google Drive\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","# STEP 2: Load deliveries.csv\n","import pandas as pd\n","deliveries_path = '/content/drive/MyDrive/Colab Notebooks/IPLPrediction/deliveries.csv'\n","deliveries_df = pd.read_csv(deliveries_path)\n","\n","# STEP 3: Aggregate total runs and wickets per over for each match\n","over_stats = deliveries_df.groupby(['match_id', 'inning', 'over']).agg(\n","    total_runs=('total_runs', 'sum'),\n","    wickets=('player_dismissed', lambda x: x.notna().sum())\n",").reset_index()\n","\n","# Filter only 1st innings\n","over_stats = over_stats[over_stats['inning'] == 1]\n","\n","# Get final score per match\n","final_scores = over_stats.groupby('match_id')['total_runs'].sum().reset_index()\n","final_scores.rename(columns={'total_runs': 'final_score'}, inplace=True)\n","\n","# Merge to create training target\n","over_sequence = pd.merge(over_stats, final_scores, on='match_id')\n","\n","# Add cumulative runs per match\n","over_sequence['cumulative_runs'] = over_sequence.groupby('match_id')['total_runs'].cumsum()\n","\n","# STEP 4: Visualize runs per over using seaborn\n","import seaborn as sns\n","import matplotlib.pyplot as plt\n","\n","plt.figure(figsize=(12, 6))\n","sns.boxplot(data=over_sequence, x='over', y='total_runs')\n","plt.title('📊 Runs per Over (1st Innings) across Matches')\n","plt.ylabel('Runs in Over')\n","plt.xlabel('Over Number')\n","plt.grid(True)\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":619},"id":"3zPua4b0Aimo","executionInfo":{"status":"ok","timestamp":1744092426967,"user_tz":-330,"elapsed":13226,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"75d8483b-c5de-4b78-8d72-d8ad8af2331e"},"execution_count":2,"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 128202 (\\N{BAR CHART}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 1200x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["import pandas as pd\n","\n","# Load deliveries.csv\n","deliveries_path = '/content/drive/MyDrive/Colab Notebooks/IPLPrediction/deliveries.csv'\n","deliveries_df = pd.read_csv(deliveries_path)\n","\n","# Aggregate total runs and wickets per over\n","over_stats = deliveries_df.groupby(['match_id', 'inning', 'over']).agg(\n","    total_runs=('total_runs', 'sum'),\n","    wickets=('player_dismissed', lambda x: x.notna().sum())\n",").reset_index()\n","\n","# Use only first innings\n","over_stats = over_stats[over_stats['inning'] == 1]\n","\n","# Final score per match\n","final_scores = over_stats.groupby('match_id')['total_runs'].sum().reset_index()\n","final_scores.rename(columns={'total_runs': 'final_score'}, inplace=True)\n","\n","# Merge and add cumulative runs\n","over_sequence = pd.merge(over_stats, final_scores, on='match_id')\n","over_sequence['cumulative_runs'] = over_sequence.groupby('match_id')['total_runs'].cumsum()"],"metadata":{"id":"jfP3NCALAijQ","executionInfo":{"status":"ok","timestamp":1744092574758,"user_tz":-330,"elapsed":5615,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}}},"execution_count":3,"outputs":[]},{"cell_type":"code","source":["import numpy as np\n","\n","# Step 2: Pivot the data to have 20 time steps (overs) per match\n","# Each row = one match; each column = cumulative runs at that over\n","pivot_df = over_sequence.pivot(index='match_id', columns='over', values='cumulative_runs')\n","\n","# Drop incomplete matches (less than 20 overs)\n","pivot_df = pivot_df.dropna()\n","\n","# Prepare features (X) and target (y)\n","X = pivot_df.values  # Shape: (num_matches, 20)\n","y = over_sequence.groupby('match_id')['final_score'].first().loc[pivot_df.index].values  # Aligned final scores\n","\n","# Reshape X for LSTM: (samples, time_steps, features)\n","X_lstm = X.reshape((X.shape[0], X.shape[1], 1))  # 1 feature = cumulative_runs per over\n","\n","# Print the shapes to confirm\n","X_lstm.shape, y.shape\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"xSsjHaZMAic_","executionInfo":{"status":"ok","timestamp":1744092641324,"user_tz":-330,"elapsed":81,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"1b2df5cb-251c-4ff2-98c3-79c95e68c424"},"execution_count":4,"outputs":[{"output_type":"execute_result","data":{"text/plain":["((1044, 20, 1), (1044,))"]},"metadata":{},"execution_count":4}]},{"cell_type":"code","source":["#LSTM Model\n","from sklearn.preprocessing import MinMaxScaler\n","from sklearn.model_selection import train_test_split\n","from tensorflow.keras.models import Sequential\n","from tensorflow.keras.layers import LSTM, Dense\n","from sklearn.metrics import mean_absolute_error, mean_squared_error\n","import matplotlib.pyplot as plt\n","import numpy as np\n","\n","# Step 1: Scale X using MinMaxScaler\n","scaler_X = MinMaxScaler()\n","num_samples, num_timesteps, num_features = X_lstm.shape\n","\n","X_scaled = scaler_X.fit_transform(X_lstm.reshape(num_samples, num_timesteps))\n","X_scaled = X_scaled.reshape(num_samples, num_timesteps, 1)\n","\n","# Step 2: Scale y (final scores)\n","scaler_y = MinMaxScaler()\n","y_scaled = scaler_y.fit_transform(y.reshape(-1, 1)).flatten()\n","\n","# Step 3: Train/test split\n","X_train, X_test, y_train, y_test = train_test_split(X_scaled, y_scaled, test_size=0.2, random_state=42)\n","\n","# Step 4: Build LSTM model\n","lstm_model = Sequential([\n","    LSTM(64, input_shape=(num_timesteps, 1)),\n","    Dense(1)\n","])\n","\n","lstm_model.compile(optimizer='adam', loss='mse')\n","lstm_model.fit(X_train, y_train, epochs=50, batch_size=32, validation_split=0.2, verbose=0)\n","\n","# Step 5: Predict and inverse scale\n","y_pred_scaled = lstm_model.predict(X_test).flatten()\n","y_pred = scaler_y.inverse_transform(y_pred_scaled.reshape(-1, 1)).flatten()\n","y_actual = scaler_y.inverse_transform(y_test.reshape(-1, 1)).flatten()\n","\n","# Step 6: Evaluate\n","mae = mean_absolute_error(y_actual, y_pred)\n","rmse = np.sqrt(mean_squared_error(y_actual, y_pred))\n","\n","# Step 7: Plot\n","plt.figure(figsize=(10, 6))\n","plt.scatter(y_actual, y_pred, alpha=0.6)\n","plt.plot([min(y_actual), max(y_actual)], [min(y_actual), max(y_actual)], 'r--')\n","plt.title(\"📊 LSTM (Scaled): Actual vs Predicted Final Scores\")\n","plt.xlabel(\"Actual Final Score\")\n","plt.ylabel(\"Predicted Final Score\")\n","plt.grid(True)\n","plt.show()\n","\n","(mae, rmse)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":712},"id":"DMCe5GHCAiZG","executionInfo":{"status":"ok","timestamp":1744093340587,"user_tz":-330,"elapsed":26280,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"d8df3da9-cb96-47a8-d2ba-3c76f1b0f6df"},"execution_count":8,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/keras/src/layers/rnn/rnn.py:200: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(**kwargs)\n","WARNING:tensorflow:5 out of the last 15 calls to <function TensorFlowTrainer.make_predict_function.<locals>.one_step_on_data_distributed at 0x7db95c97a520> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.\n"]},{"output_type":"stream","name":"stdout","text":["\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step\n"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 128202 (\\N{BAR CHART}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 1000x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["(2.6241655121579686, np.float64(3.1895911253691205))"]},"metadata":{},"execution_count":8}]},{"cell_type":"code","source":["#All Models\n","from tensorflow.keras.layers import GRU, Conv1D, Flatten, Bidirectional\n","from tensorflow.keras.models import Sequential\n","from tensorflow.keras.layers import Dense\n","import matplotlib.pyplot as plt\n","\n","# Dictionary to store evaluation results\n","results = {}\n","\n","# Helper function to build, train, and evaluate a model\n","def evaluate_model(name, model_fn):\n","    model = model_fn()\n","    model.compile(optimizer='adam', loss='mse')\n","    model.fit(X_train, y_train, epochs=50, batch_size=32, validation_split=0.2, verbose=0)\n","\n","    y_pred_scaled = model.predict(X_test).flatten()\n","    y_pred = scaler_y.inverse_transform(y_pred_scaled.reshape(-1, 1)).flatten()\n","    y_actual = scaler_y.inverse_transform(y_test.reshape(-1, 1)).flatten()\n","\n","    mae = mean_absolute_error(y_actual, y_pred)\n","    rmse = np.sqrt(mean_squared_error(y_actual, y_pred))\n","\n","    results[name] = {'mae': mae, 'rmse': rmse, 'y_pred': y_pred, 'y_actual': y_actual}\n","\n","# Define each model\n","evaluate_model(\"LSTM\", lambda: Sequential([\n","    LSTM(64, input_shape=(num_timesteps, 1)),\n","    Dense(1)\n","]))\n","\n","evaluate_model(\"GRU\", lambda: Sequential([\n","    GRU(64, input_shape=(num_timesteps, 1)),\n","    Dense(1)\n","]))\n","\n","evaluate_model(\"1D_CNN\", lambda: Sequential([\n","    Conv1D(64, kernel_size=3, activation='relu', input_shape=(num_timesteps, 1)),\n","    Flatten(),\n","    Dense(1)\n","]))\n","\n","evaluate_model(\"BiLSTM\", lambda: Sequential([\n","    Bidirectional(LSTM(64), input_shape=(num_timesteps, 1)),\n","    Dense(1)\n","]))\n","\n","# Create table of results\n","results_table = pd.DataFrame([\n","    {\"Model\": name, \"MAE\": r[\"mae\"], \"RMSE\": r[\"rmse\"]}\n","    for name, r in results.items()\n","]).sort_values(by=\"RMSE\")\n","\n","# Plot compariso\n","plt.figure(figsize=(10, 5))\n","sns.barplot(data=results_table.melt(id_vars='Model'), x='Model', y='value', hue='variable')\n","plt.title(\"📊 MAE & RMSE Comparison Across Models\")\n","plt.ylabel(\"Error\")\n","plt.grid(True)\n","plt.show()\n","\n","results_table.reset_index(drop=True)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":921},"id":"RGsVr7RyAiPz","executionInfo":{"status":"ok","timestamp":1744093468151,"user_tz":-330,"elapsed":103459,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"ac1bd455-d114-4657-f4cf-5e1b13ba3e5b"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/keras/src/layers/rnn/rnn.py:200: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(**kwargs)\n"]},{"output_type":"stream","name":"stdout","text":["\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 58ms/step\n"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/keras/src/layers/rnn/rnn.py:200: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(**kwargs)\n"]},{"output_type":"stream","name":"stdout","text":["\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"]},{"output_type":"stream","name":"stdout","text":["\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step\n"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/keras/src/layers/rnn/bidirectional.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(**kwargs)\n"]},{"output_type":"stream","name":"stdout","text":["\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 70ms/step\n"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 128202 (\\N{BAR CHART}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 1000x500 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["    Model       MAE      RMSE\n","0     GRU  1.334374  1.641954\n","1  1D_CNN  1.360876  1.764524\n","2    LSTM  2.417546  2.909603\n","3  BiLSTM  2.552074  3.047109"],"text/html":["\n","  <div id=\"df-019d199e-f2cc-4bf3-bba2-98ae65298bb5\" class=\"colab-df-container\">\n","    <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>Model</th>\n","      <th>MAE</th>\n","      <th>RMSE</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>GRU</td>\n","      <td>1.334374</td>\n","      <td>1.641954</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>1D_CNN</td>\n","      <td>1.360876</td>\n","      <td>1.764524</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>LSTM</td>\n","      <td>2.417546</td>\n","      <td>2.909603</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>BiLSTM</td>\n","      <td>2.552074</td>\n","      <td>3.047109</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","    <div class=\"colab-df-buttons\">\n","\n","  <div class=\"colab-df-container\">\n","    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-019d199e-f2cc-4bf3-bba2-98ae65298bb5')\"\n","            title=\"Convert this dataframe to an interactive table.\"\n","            style=\"display:none;\">\n","\n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n","    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n","  </svg>\n","    </button>\n","\n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    .colab-df-buttons div {\n","      margin-bottom: 4px;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","    <script>\n","      const buttonEl =\n","        document.querySelector('#df-019d199e-f2cc-4bf3-bba2-98ae65298bb5 button.colab-df-convert');\n","      buttonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","      async function convertToInteractive(key) {\n","        const element = document.querySelector('#df-019d199e-f2cc-4bf3-bba2-98ae65298bb5');\n","        const dataTable =\n","          await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                    [key], {});\n","        if (!dataTable) return;\n","\n","        const docLinkHtml = 'Like what you see? Visit the ' +\n","          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","          + ' to learn more about interactive tables.';\n","        element.innerHTML = '';\n","        dataTable['output_type'] = 'display_data';\n","        await google.colab.output.renderOutput(dataTable, element);\n","        const docLink = document.createElement('div');\n","        docLink.innerHTML = docLinkHtml;\n","        element.appendChild(docLink);\n","      }\n","    </script>\n","  </div>\n","\n","\n","<div id=\"df-dbbdbaa9-2cde-468d-b283-8e002fe57755\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-dbbdbaa9-2cde-468d-b283-8e002fe57755')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-dbbdbaa9-2cde-468d-b283-8e002fe57755 button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","\n","    </div>\n","  </div>\n"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"dataframe","summary":"{\n  \"name\": \"results_table\",\n  \"rows\": 4,\n  \"fields\": [\n    {\n      \"column\": \"Model\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          \"1D_CNN\",\n          \"BiLSTM\",\n          \"GRU\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MAE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.658936270780583,\n        \"min\": 1.3343735836339337,\n        \"max\": 2.552074049078106,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          1.3608755084316129,\n          2.552074049078106,\n          1.3343735836339337\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"RMSE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.7400199516181788,\n        \"min\": 1.6419538934366036,\n        \"max\": 3.047108564421537,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          1.7645240509710225,\n          3.047108564421537,\n          1.6419538934366036\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"}},"metadata":{},"execution_count":10}]},{"cell_type":"code","source":["# Rebuild and retrain all models before saving\n","\n","from tensorflow.keras.models import Sequential\n","from tensorflow.keras.layers import LSTM, GRU, Conv1D, Flatten, Dense, Bidirectional\n","import os\n","\n","model_dir = '/content/drive/MyDrive/Colab Notebooks/IPLPrediction'\n","\n","# Function to train and save a model\n","def build_train_save(model_name, model_fn):\n","    model = model_fn()\n","    model.compile(optimizer='adam', loss='mse')\n","    model.fit(X_scaled, y_scaled, epochs=50, batch_size=32, verbose=0)\n","    model_path = os.path.join(model_dir, f'{model_name}_score_predictor.h5')\n","    model.save(model_path)\n","    print(f\"✅ {model_name} model saved at: {model_path}\")\n","\n","# Save LSTM\n","build_train_save(\"lstm\", lambda: Sequential([\n","    LSTM(64, input_shape=(num_timesteps, 1)),\n","    Dense(1)\n","]))\n","\n","# Save GRU\n","build_train_save(\"gru\", lambda: Sequential([\n","    GRU(64, input_shape=(num_timesteps, 1)),\n","    Dense(1)\n","]))\n","\n","# Save 1D CNN\n","build_train_save(\"cnn\", lambda: Sequential([\n","    Conv1D(64, kernel_size=3, activation='relu', input_shape=(num_timesteps, 1)),\n","    Flatten(),\n","    Dense(1)\n","]))\n","\n","# Save BiLSTM\n","build_train_save(\"bilstm\", lambda: Sequential([\n","    Bidirectional(LSTM(64), input_shape=(num_timesteps, 1)),\n","    Dense(1)\n","]))\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"kGAjjJp0EKl5","executionInfo":{"status":"ok","timestamp":1744093869993,"user_tz":-330,"elapsed":107132,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"9abd2646-df99-4125-8354-bdb9090ce915"},"execution_count":11,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/keras/src/layers/rnn/rnn.py:200: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(**kwargs)\n","WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"]},{"output_type":"stream","name":"stdout","text":["✅ lstm model saved at: /content/drive/MyDrive/Colab Notebooks/IPLPrediction/lstm_score_predictor.h5\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n","/usr/local/lib/python3.11/dist-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"]},{"output_type":"stream","name":"stdout","text":["✅ gru model saved at: /content/drive/MyDrive/Colab Notebooks/IPLPrediction/gru_score_predictor.h5\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n","/usr/local/lib/python3.11/dist-packages/keras/src/layers/rnn/bidirectional.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(**kwargs)\n"]},{"output_type":"stream","name":"stdout","text":["✅ cnn model saved at: /content/drive/MyDrive/Colab Notebooks/IPLPrediction/cnn_score_predictor.h5\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"]},{"output_type":"stream","name":"stdout","text":["✅ bilstm model saved at: /content/drive/MyDrive/Colab Notebooks/IPLPrediction/bilstm_score_predictor.h5\n"]}]},{"cell_type":"code","source":["from sklearn.preprocessing import MinMaxScaler\n","from tensorflow.keras.models import load_model\n","import numpy as np\n","import matplotlib.pyplot as plt\n","import pandas as pd\n","\n","# Load GRU model with compile=False to avoid deserialization issues\n","gru_model_path = '/content/drive/MyDrive/Colab Notebooks/IPLPrediction/gru_score_predictor.h5'\n","gru_model = load_model(gru_model_path, compile=False)\n","gru_model.compile(optimizer='adam', loss='mse')\n","\n","# Pick a valid match with full 20 overs\n","sample_match = over_sequence.groupby('match_id').filter(lambda x: len(x) == 20).sample(1, random_state=42)\n","sample_match_id = sample_match['match_id'].iloc[0]\n","sample_match_seq = over_sequence[over_sequence['match_id'] == sample_match_id].sort_values('over')\n","\n","# Extract cumulative runs\n","cumulative_runs = sample_match_seq['cumulative_runs'].values.reshape(-1, 1)\n","\n","# Scale cumulative runs globally (using MinMax from the entire dataset)\n","scaler_input = MinMaxScaler()\n","scaler_input.fit(over_sequence['cumulative_runs'].values.reshape(-1, 1))\n","\n","# Scale final scores\n","scaler_output = MinMaxScaler()\n","scaler_output.fit(y.reshape(-1, 1))\n","\n","# Predict over-by-over\n","over_predictions = []\n","for i in range(1, 21):\n","    current_seq = cumulative_runs[:i]\n","\n","    # Pad to 20 timesteps\n","    padded_seq = np.pad(current_seq, ((0, 20 - i), (0, 0)), mode='constant')\n","\n","    # Scale padded input using the scaler fit on global cumulative data\n","    padded_scaled = scaler_input.transform(padded_seq)\n","    model_input = padded_scaled.reshape(1, 20, 1)\n","\n","    # Predict and inverse scale\n","    pred_scaled = gru_model.predict(model_input, verbose=0)\n","    pred_actual = scaler_output.inverse_transform(pred_scaled)[0][0]\n","    over_predictions.append(pred_actual)\n","\n","# Plot prediction evolution\n","plt.figure(figsize=(10, 5))\n","plt.plot(range(1, 21), over_predictions, marker='o', label='Predicted Final Score')\n","plt.axhline(y=cumulative_runs[-1][0], color='green', linestyle='--', label='Actual Final Score')\n","plt.title(\"📈 GRU Predicted Score Over Time (Fixed Scaling)\")\n","plt.xlabel(\"Overs Completed\")\n","plt.ylabel(\"Predicted Final Score\")\n","plt.legend()\n","plt.grid(True)\n","plt.show()\n","\n","# Print final predicted vs actual score\n","over_predictions[-1], cumulative_runs[-1][0]"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":542},"id":"88cNAuGYG39p","executionInfo":{"status":"ok","timestamp":1744094261458,"user_tz":-330,"elapsed":3646,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"5c55cfc6-e9b9-4330-a88b-1a903e6cc7d5"},"execution_count":14,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 128200 (\\N{CHART WITH UPWARDS TREND}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 1000x500 with 1 Axes>"],"image/png":"iVBORw0KGgoAAAANSUhEUgAAA1IAAAHWCAYAAAB9mLjgAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAiwBJREFUeJzs3XlcVNX7B/DPDAwz7AiCgALiiguhuYV7bijmlpaaJS5p5ZaZS37NXNPsZ6VtauWSqZWWmqapuO/7rqhoCG6IiuzbMHN+f9CMjjAwg8wCfN6vF8Xce+bOc5+5c52Hc+65EiGEABERERERERlMaukAiIiIiIiIShsWUkREREREREZiIUVERERERGQkFlJERERERERGYiFFRERERERkJBZSRERERERERmIhRUREREREZCQWUkREREREREZiIUVERERERGQkFlJERCVs0KBBqFq1qs4yiUSC6dOnWySeghQUI5Vu1naMaYSHh2PYsGFGPcdS+1K1alUMGjTI7K9riL1790IikWDv3r3aZeb4HD969AiOjo7YunWrSV+HqDRiIUVERklJScGnn36Kxo0bw9XVFXK5HAEBAejbty+2bNmi01bzD7/mx8bGBl5eXujTpw+ioqLybbtt27aoX79+ga/78OFDg75c3bx5M99r+vv7o1evXjh79mxxd9siLl++jOnTp+PmzZsWi0GtVmPlypVo1qwZ3N3d4ezsjFq1amHgwIE4evSoxeJ6Hunp6Zg1axZeeOEFODg4wNXVFa1atcLKlSshhLB0eForVqzQOZb1/VhzQXzo0CHs2LEDkyZN0i579rzw9E+/fv0sGK3h0tLSMG3aNNSvXx+Ojo7w8PBAgwYN8P777+Pu3buWDq9EeXh44O2338bUqVMtHQqR1bG1dABEZB6XLl1Cw4YNYWdnV+D6nJwcREVFoXr16nq3cf36dYSFhSE2Nha9evXCwIED4eTkhFu3bmHr1q145ZVXsHLlSrz11ls6zxszZgyaNGkCpVKJ8+fPY/Hixdi7dy8uXrwIb2/vEt1Pjf79+yM8PBwqlQpRUVFYtGgR/vnnHxw9ehQNGjQwyWsWJjMzE7a2xp1yL1++jBkzZqBt27YW+7I8ZswYfPfdd+jRowcGDBgAW1tbXL16Ff/88w+qVauGl156ySJxFdf9+/fRvn17REVFoV+/fhg1ahSysrLw559/IiIiAlu3bsXq1athY2Nj6VDRunVr/PLLLzrL3n77bTRt2hTDhw/XLnNycgJQvGPM1P7v//4P7du3R40aNfKt05wXnqY5zq1xXzSUSiVat26NK1euICIiAqNHj0ZaWhouXbqENWvWoFevXvD19TVLLD/++CPUarXJX+fdd9/F119/jd27d6Ndu3Ymfz2i0sI6z1JEVOKEEGjatCkOHjxY4PqXXnqp0L/G5+bmolevXrh//z727duHFi1a6KyfNm0aduzYAZVKle+5rVq1Qp8+fbSPa9eujffeew8rV67ExIkTi7lHhXvxxRfx5ptvah+3aNEC3bt3x6JFi7BkyZICn5Oeng5HR0eTxKNQKEyyXVO6f/8+vv/+ewwbNgw//PCDzroFCxbgwYMHZoslNzcXarVa7x8CDBUREYGoqChs2LAB3bt31y4fM2YMJkyYgPnz56Nhw4Y6PSimplarkZOTk+8YqVatGqpVq6az7N1330W1atV0jm0NazvGEhISsGXLFixevLjA9c+eF55mbfvytI0bN+LMmTNYvXo13njjDZ11WVlZyMnJMVssMpnMLK9Tp04d1K9fHytWrGAhRfQUDu0jIoOsW7cOFy9exNSpU/MVURqdOnVCly5ditxWq1atAAA3btwo0RgLo/nHPyYmBsCTYVP79u3DiBEj4OXlhSpVqmjb//PPP2jVqhUcHR3h7OyMrl274tKlS/m2u3HjRtSvXx8KhQL169fHhg0bCnz9goYl3rlzB0OHDoWvry/kcjkCAwPx3nvvIScnBytWrMBrr70GAHj55Ze1Q5+evj6ipGN8VkxMDIQQBb7fEokEXl5eOsuSkpLwwQcfoGrVqpDL5ahSpQoGDhyIhw8fatskJCRg6NChqFSpEhQKBUJCQvDzzz/rbEczPHP+/PlYsGABqlevDrlcjsuXLwMArly5gj59+sDd3R0KhQKNGzfGpk2bityfo0ePYvv27Rg0aJBOEaUxd+5c1KxZE/PmzUNmZiaUSiXc3d0xePDgfG1TUlKgUCgwfvx47bLs7GxMmzYNNWrUgFwuh5+fHyZOnIjs7Ox8uRs1ahRWr16NevXqQS6XY9u2bUXGX5Rnj7Hp06dDIpHg2rVrePPNN+Hq6gpPT09MnToVQgjcunULPXr0gIuLC7y9vfHFF1/k26ah+1SQLVu2IDc3Fx06dHiufcnMzERQUBCCgoKQmZmpbZOYmAgfHx80b95c+wcctVqNBQsWoF69elAoFKhUqRLeeecdPH78WGf7QgjMnj0bVapUgYODA15++eUCPzsF0Zy3CvpcKBQKuLi46Cy7cuUKXn/9dXh6esLe3h61a9fGlClTtOtjY2MxYsQI1K5dG/b29vDw8MBrr71m0JDeZ6+Revqz88MPP2g/O02aNMGJEyfyPX/dunWoW7euzrlB33VXHTt2xObNm61q+CuRpbFHiogMsnnzZgAo8C/hxtJ8QahQocJzb8tQmi8/Hh4eOstHjBgBT09PfPLJJ0hPTwcA/PLLL4iIiEBYWBjmzZuHjIwMLFq0CC1btsSZM2e0XzJ27NiB3r17o27dupg7dy4ePXqEwYMH6xRk+ty9exdNmzZFUlIShg8fjqCgINy5cwd//PEHMjIy0Lp1a4wZMwZff/01/ve//6FOnToAoP2/OWIMCAgAkPdl67XXXoODg4PetmlpaWjVqhWioqIwZMgQvPjii3j48CE2bdqE27dvo2LFisjMzETbtm1x/fp1jBo1CoGBgVi3bh0GDRqEpKQkvP/++zrbXL58ObKysjB8+HDI5XK4u7vj0qVLaNGiBSpXroyPPvoIjo6OWLt2LXr27Ik///wTvXr10huj5hgeOHBggettbW3xxhtvYMaMGTh06BA6dOiAXr16Yf369ViyZIlOb9jGjRuRnZ2tvaZHrVaje/fuOHjwIIYPH446dergwoUL+Oqrr3Dt2jVs3LhR57V2796NtWvXYtSoUahYsaJJh2727dsXderUwWeffYYtW7Zg9uzZcHd3x5IlS9CuXTvMmzcPq1evxvjx49GkSRO0bt26WPv0rMOHD8PDw0N7HD0rNTVVp8gGAHd3d0ilun/jtbe3x88//4wWLVpgypQp+PLLLwEAI0eORHJyMlasWKEdivnOO+9gxYoVGDx4MMaMGYOYmBh8++23OHPmDA4dOqTtwfnkk08we/ZshIeHIzw8HKdPn0anTp0M6k3S7M/KlSvx8ccfQyKR6G17/vx5tGrVCjKZDMOHD0fVqlVx48YNbN68GZ9++ikA4MSJEzh8+DD69euHKlWq4ObNm1i0aBHatm2Ly5cvF/q502fNmjVITU3FO++8A4lEgs8//xyvvvoq/v33X20OtmzZgr59+yI4OBhz587F48ePMXToUFSuXLnAbTZq1AhfffUVLl26pPdaVqJyRxBRuXDhwgXRokULveubNWsmoqOj9a5v2LChcHNzy7c8LS1NPHjwQPuTnJysXbdnzx4BQCxbtkw8ePBA3L17V2zbtk3UqFFDSCQScfz4cZ1ttWnTRtSrV6/A13/w4IEAIKZNm1bofsbExAgAYsaMGeLBgwciPj5e7N27VzRs2FAAEH/++acQQojly5cLAKJly5YiNzdX+/zU1FTh5uYmhg0bprPd+Ph44erqqrO8QYMGwsfHRyQlJWmX7dixQwAQAQEBOs9/NvaBAwcKqVQqTpw4kW8f1Gq1EEKIdevWCQBiz549OutNFWNBBg4cKACIChUqiF69eon58+eLqKiofO0++eQTAUCsX79e7/4sWLBAABCrVq3SrsvJyRGhoaHCyclJpKSkCCGevIcuLi4iISFBZ1vt27cXwcHBIisrS2f7zZs3FzVr1ix0X3r27CkAiMePH+tts379egFAfP3110IIIbZv3y4AiM2bN+u0Cw8PF9WqVdM+/uWXX4RUKhUHDhzQabd48WIBQBw6dEi7DICQSqXi0qVLhcZbEEdHRxEREVHgumePsWnTpgkAYvjw4dplubm5okqVKkIikYjPPvtMu/zx48fC3t5eZ9vG7FNBWrZsKRo1apRvuea8UNBPTExMgfsihBCTJ08WUqlU7N+/X/vZWLBggXb9gQMHBACxevVqnedt27ZNZ3lCQoKws7MTXbt21R6bQgjxv//9TwDQm1+NjIwMUbt2be1naNCgQWLp0qXi/v37+dq2bt1aODs7i9jYWJ3lT79uRkZGvucdOXJEABArV67Ml7enzwcRERE6n2PNZ8fDw0MkJiZql//111/5juPg4GBRpUoVkZqaql22d+9eveeGw4cPCwDi999/LzgxROUQh/YRkUFSUlK0F7U/bcqUKfD09NT+PHvNAAAMGTIEnp6e8PX1RefOnZGcnIxffvkl34XmJWnatGnw9PSEt7c32rZtixs3bmDevHl49dVXddoNGzZMZ2KByMhIJCUloX///nj48KH2x8bGBs2aNcOePXsAAPfu3cPZs2cREREBV1dX7fM7duyIunXrFhqbWq3Gxo0b0a1bNzRu3Djf+sL+wm2uGDWWL1+Ob7/9FoGBgdiwYQPGjx+POnXqoH379rhz54623Z9//omQkJACe4Q0+7N161Z4e3ujf//+2nUymQxjxoxBWloa9u3bp/O83r17w9PTU/s4MTERu3fvxuuvv67tzXj48CEePXqEsLAwREdH68T0rNTUVACAs7Oz3jaadSkpKQDyhoRWrFgRv//+u7bN48ePERkZib59+2qXrVu3DnXq1EFQUJDOe6IZUqp5TzTatGlj8HvwvN5++23t7zY2NmjcuDGEEBg6dKh2uZubG2rXro1///1Xu8zYfXrWo0ePCu11/uSTTxAZGanzU9jkM9OnT0e9evUQERGBESNGoE2bNhgzZoxOvK6urujYsaNOvI0aNYKTk5M23p07dyInJwejR4/W+ayNHTu20P3RsLe3x7FjxzBhwgQAecOEhw4dCh8fH4wePVo77PHBgwfYv38/hgwZAn9/f51tPP269vb22t+VSiUePXqEGjVqwM3NDadPnzYopmf17dtXJ/ea4dSa9/fu3bu4cOGCdsIgjTZt2iA4OLjAbWq292wvIlF5xqF9RGQQZ2dnPHr0KN/yESNG4JVXXgGgf9jfJ598glatWiEtLQ0bNmzAb7/9lm/4jqGKKjI0hg8fjtdeew1SqRRubm7aa1GeFRgYqPM4OjoaAPReUK25/iE2NhYAULNmzXxtateuXegXoAcPHiAlJaXYw2PMEaOGVCrFyJEjMXLkSDx69AiHDh3C4sWL8c8//6Bfv344cOAAgLyhk7179y50W7GxsahZs2a+914zXFETr8az783169chhMDUqVP1TsWckJCgd2iSpkhKTU2Fm5tbgW2eLbZsbW3Ru3dvrFmzBtnZ2ZDL5Vi/fj2USqVOIRUdHY2oqCidwu/ZuArbN1N69ku8q6srFAoFKlasmG/5059xY/epIKKQ62mCg4ONun7Kzs4Oy5YtQ5MmTaBQKLB8+XKd80F0dDSSk5PzXbv3bLz6Pheenp4GDzd2dXXF559/js8//xyxsbHYtWsX5s+fj2+//Raurq6YPXu2tmgp6nOemZmJuXPnYvny5bhz545OzpKTkw2K51nPvuea/dJcK6bJQUGzKdaoUaPAc4MmLkPPwUTlAQspIjJIUFAQzp49izt37uh8Ua1VqxZq1aoFQP9MW09/YerZsycyMjIwbNgwtGzZEn5+ftp2CoVC52Lyp2VkZBT6Gs+qWbOmQV/Snv5rMADtVMK//PJLgX8dt4YpmS0Vo4eHB7p3747u3bujbdu22LdvH2JjY/VeA/O89L0348ePR1hYWIHPKeiLoUadOnWwceNGnD9/Xnsd0LPOnz8PADq9Rf369cOSJUvwzz//oGfPnli7di2CgoIQEhKiE1twcLD2+p1nPX2cF7RvplTQVO76pnd/+ku8sfv0LA8Pj3yTPDyv7du3A8ibHS86OlqnIFWr1fDy8sLq1asLfK6+gvB5BQQEYMiQIejVqxeqVauG1atXY/bs2QY/f/To0Vi+fDnGjh2L0NBQuLq6au+pVdypzQ15f42leS+fLcCJyjPLfyMgolLhlVdewW+//YbVq1c/95Tln332GTZs2IBPP/1UZ2rkgIAA7N69G5mZmfm+aF69elXbxpQ099Hy8vIqtBDTxKHpHXqaJlZ9PD094eLigosXLxbaTt9ffs0RY1EaN26Mffv24d69ewgICED16tWL3J+AgACcP38earVap1fqypUrOvHqo5kKXCaTFWsmuFdeeQVz587FypUrCyykVCoV1qxZgwoVKujMyNa6dWv4+Pjg999/R8uWLbF7926dWdeAvPfk3LlzaN++fZn5i/3z7lNQUBD+/PPPEovn/PnzmDlzJgYPHoyzZ8/i7bffxoULF7TDVqtXr46dO3eiRYsWhRaqT38unp5e/sGDB89V+FWoUEHnc6DZdlGfiz/++AMRERE6syZmZWUhKSmp2LEURZOD69ev51tX0DLgyYynmh5kIuL050RkoNdffx1169bFrFmzcPTo0QLbGPrXzurVq6N3795YsWIF4uPjtcvDw8OhVCrz3edJrVZj0aJFsLOzQ/v27Yu/EwYICwuDi4sL5syZA6VSmW+95t5JPj4+aNCgAX7++Wed4TeRkZHaabr1kUql6NmzJzZv3oyTJ0/mW6/Jo+aeVs9+oTJHjAAQHx9fYLucnBzs2rULUqlU2wPUu3dvnDt3rsCp1TX7Ex4ejvj4eJ3rjXJzc/HNN9/AyckJbdq0KTQeLy8vtG3bFkuWLMG9e/f07rc+zZs3R4cOHbB8+XL8/fff+dZPmTIF165dw8SJE3W+iEulUvTp0webN2/GL7/8gtzcXJ1hfUDe5+POnTv48ccf8203MzNTOyNkafK8+xQaGorHjx/rXHdVXEqlEoMGDYKvry8WLlyIFStW4P79+/jggw904lWpVJg1a1a+5+fm5mo/Rx06dIBMJsM333yjc85asGCBQbGcO3euwOuEYmNjcfnyZdSuXRtA3h9MWrdujWXLliEuLk6n7dOva2Njk+/c+c033xR4T76S4uvri/r162PlypVIS0vTLt+3bx8uXLhQ4HNOnToFV1dX1KtXz2RxEZU27JEiIoPIZDJs2LABYWFhaNmyJV599VXtPYzu3LmDTZs2IS4uDl27djVoexMmTMDatWuxYMECfPbZZwCAbt26oVOnTvjggw9w/PhxNG/eHBkZGdi0aRMOHTqE2bNnm2x4joaLiwsWLVqEt956Cy+++CL69esHT09PxMXFYcuWLWjRogW+/fZbAHn3HeratStatmyJIUOGIDExEd988w3q1aun8+WkIHPmzMGOHTvQpk0b7dTS9+7dw7p163Dw4EG4ubmhQYMGsLGxwbx585CcnAy5XI527drBy8vLLDHevn0bTZs2Rbt27dC+fXt4e3sjISEBv/76K86dO4exY8dqh/lMmDABf/zxB1577TUMGTIEjRo1QmJiIjZt2oTFixcjJCQEw4cPx5IlSzBo0CCcOnUKVatWxR9//IFDhw5hwYIFhU4CofHdd9+hZcuWCA4OxrBhw1CtWjXcv38fR44cwe3bt3Hu3LlCn79y5Uq0b98ePXr0wBtvvIFWrVohOzsb69evx969e9G3b1/tJAJP69u3L7755htMmzYNwcHB+f4q/9Zbb2Ht2rV49913sWfPHrRo0QIqlQpXrlzB2rVrsX379gInFrFmz7tPXbt2ha2tLXbu3Inhw4c/VyyzZ8/G2bNnsWvXLjg7O+OFF17AJ598go8//hh9+vRBeHg42rRpg3feeQdz587F2bNn0alTJ8hkMkRHR2PdunVYuHAh+vTpA09PT4wfPx5z587FK6+8gvDwcJw5cwb//POPQcPWIiMjMW3aNHTv3h0vvfQSnJyc8O+//2LZsmXIzs7WuZfX119/jZYtW+LFF1/E8OHDERgYiJs3b2LLli04e/YsgLye0l9++QWurq6oW7cujhw5gp07d+a7VUNJmzNnDnr06IEWLVpg8ODBePz4Mb799lvUr1+/wHNDZGQkunXrVmZ6XIlKhEXmCiQis3ve6c81kpKSxMyZM0XDhg2Fk5OTsLOzE35+fqJPnz75pojWTNe7bt26ArfVtm1b4eLiojM1d1ZWlpg+fboICgoScrlcODo6ipdeeklnyuzCaKb//b//+79C22mmPy9o+nFN7GFhYcLV1VUoFApRvXp1MWjQIHHy5Emddn/++aeoU6eOkMvlom7dumL9+vX5piQWouDpnGNjY8XAgQOFp6enkMvlolq1amLkyJEiOztb2+bHH38U1apVEzY2NvmmPi7pGJ+VkpIiFi5cKMLCwkSVKlWETCYTzs7OIjQ0VPz44486UzgLIcSjR4/EqFGjROXKlYWdnZ2oUqWKiIiIEA8fPtS2uX//vhg8eLCoWLGisLOzE8HBwWL58uU62ynqPbxx44YYOHCg8Pb2FjKZTFSuXFm88sor4o8//ih0fzRSU1PF9OnTRb169YS9vb1wdnYWLVq0ECtWrMi3TxpqtVr4+fkJAGL27NkFtsnJyRHz5s0T9erVE3K5XFSoUEE0atRIzJgxQ+e2AADEyJEjDYr1WcWZ/vzBgwc67SIiIoSjo2O+5xd0+wFD90mf7t27i/bt2+ssK+q88Oy+nDp1Stja2orRo0frtMnNzRVNmjQRvr6+OlPa//DDD6JRo0ba9zY4OFhMnDhR3L17V9tGpVKJGTNmCB8fH2Fvby/atm0rLl68KAICAoqc/vzff/8Vn3zyiXjppZeEl5eXsLW1FZ6enqJr165i9+7d+dpfvHhR9OrVS7i5uQmFQiFq164tpk6dql3/+PFj7WfCyclJhIWFiStXruSLxZjpzwv67BR0Dvrtt9+059r69euLTZs2id69e4ugoCCddlFRUQKA2LlzZ6G5ISpvJELwFtVE5cHFixfx7rvv4uDBgwWuf+mll7Bq1apCL9YnIjLGgQMH0LZtW1y5cqXA2SPJ+jRo0ACenp6IjIzULhs7diz279+PU6dOsUeK6Cm8RoqIiIhMolWrVujUqRM+//xzS4dCz1AqlcjNzdVZtnfvXpw7dw5t27bVLnv06BF++uknzJ49m0UU0TPYI0VUTly8eBENGjQo8Ka6AJCWloYrV66wR4qIqBy4efMmOnTogDfffBO+vr64cuUKFi9eDFdXV1y8eNHk12gRlQUspIiIiIjKmeTkZAwfPhyHDh3CgwcP4OjoiPbt2+Ozzz7T3mKBiArHQoqIiIiIiMhIvEaKiIiIiIjISCykiIiIiIiIjMQb8gJQq9W4e/cunJ2dOSMNEREREVE5JoRAamoqfH19IZXq73diIQXg7t278PPzs3QYRERERERkJW7duoUqVaroXc9CCoCzszOAvGS5uLhYOJqyTalUYseOHejUqRNkMpmlwynzmG/zY87Njzk3L+bb/Jhz82POzc+acp6SkgI/Pz9tjaAPCylAO5zPxcWFhZSJKZVKODg4wMXFxeIfkvKA+TY/5tz8mHPzYr7Njzk3P+bc/Kwx50Vd8sPJJoiIiIiIiIzEQoqIiIiIiMhILKSIiIiIiIiMxGukDKRSqaBUKi0dRqmnVCpha2uLrKwsqFQqS4dT5pVUvm1sbGBra8vbAxARERH9h4WUAdLS0nD79m0IISwdSqknhIC3tzdu3brFL+VmUJL5dnBwgI+PD+zs7EooOiIiIqLSi4VUEVQqFW7fvg0HBwd4enryy/9zUqvVSEtLg5OTU6E3OKOSURL5FkIgJycHDx48QExMDGrWrMn3joiIiMo9FlJFUCqVEELA09MT9vb2lg6n1FOr1cjJyYFCoeCXcTMoqXzb29tDJpMhNjZWuz0iIiKi8ozfZA3Enigq71j4EhERET3Bb0ZERERERERGYiFFREREREQWo1ILHItJxKmHEhyLSYRKXTomeGMhZSYqtcCRG4/w19k7OHLjUak5QAwxaNAg9OzZU/u4bdu2GDt2rNnj2Lt3LyQSCZKSkor1fIlEgo0bN5ZoTJbKBREREVFpsO3iPbSctxtvLjuJldE2eHPZSbSctxvbLt6zdGhFYiFlBpoDpP+PR/H+b2fR/8ejJj9ABg0aBIlEAolEAjs7O9SoUQMzZ85Ebm6uyV5TY/369Zg1a5ZBbZ+3+DFW1apVtXnR/FSpUgUAcO/ePXTp0sUscWioVCp89tlnCAoKgr29Pdzd3dGsWTP89NNPZo2DiIiIyNy2XbyH91adxr3kLJ3l8clZeG/Vaasvpjhrn4lpDpBn+580B8iiN19E5/o+Jnntzp07Y/ny5cjOzsbWrVsxcuRIyGQyTJ48OV/bnJycErs/kLu7e4lsx1RmzpyJYcOGaR/b2NgAALy9vc0ey4wZM7BkyRJ8++23aNy4MVJSUnDy5Ek8fvzYZK9Zku81ERERUXGo1AIzNl/O9x0ZAAQACYAZmy+jY11v2Eitc9I39kgZSQiBjJxcg35Ss5SYtumS3gMEAKZvuozULKVB2zP2hsByuRze3t4ICAjAe++9hw4dOmDTpk0AngzH+/TTT+Hr64vatWsDAG7duoXXX38dbm5ucHd3R48ePXDz5k3tNlUqFcaNGwc3Nzd4eHhg4sSJ+eJ6djhbdnY2Jk2aBD8/P9jb2+PFF1/E0qVLcfPmTbz88ssAgAoVKkAikWDQoEEA8qbtnjt3LgIDA2Fvb4+QkBD88ccfOq+zdetW1KpVC/b29nj55Zd14iyMs7MzvL29tT+enp4AdIf23bx5ExKJBOvXr8fLL78MBwcHhISE4MiRI9rtPHr0CP3790flypXh4OCA4OBg/PrrrwbFoLFp0yaMGDECr732GgIDAxESEoKhQ4di/Pjx2jZqtRqff/45atSoAblcDn9/f3z66afa9RcuXEC7du1gb28PDw8PDB8+HGlpadr1I0aMQK9evYx+r4mIiIhM5XhMYr6eqKcJAPeSs3A8JtF8QRmJPVJGylSqUPeT7SWyLQEgPiULwdN3GNT+8swwONgV/y2zt7fHo0ePtI937doFFxcXREZGAsi7Z1ZYWBhCQ0Nx4MAB2NraYvbs2ejcuTPOnz8POzs7fPHFF1ixYgWWLVuGOnXq4IsvvsCGDRvQrl07va87cOBAHDlyBF9//TWCg4Nx6dIlZGRkwM/PD3/++Sd69+6Nq1evwsXFRXuvrrlz52LVqlVYvHgxatasif379+PNN9+Ep6cn2rRpg1u3buHVV1/FyJEjMXz4cJw8eRIffvhhsXOjz5QpUzB//nzUrFkTU6ZMQf/+/XH9+nXY2toiKysLjRo1wqRJk+Di4oItW7bgrbfeQvXq1dG0aVODtu/t7Y3du3djxIgR2oLuWZMnT8aPP/6Ir776Ci1btsS9e/dw5coVAEB6err2PTtx4gQSEhLw9ttvY9SoUVixYoV2G7t374arq6tR7zURERGRqSSk6i+iitPOElhIlQNCCOzatQvbt2/H6NGjtcsdHR3x008/ab80r1q1Cmq1Gj/99JP2vlnLly+Hm5sb9u7di06dOmHBggWYPHkyXn31VQDA4sWLsX27/sLy2rVrWLt2LSIjI9GhQweo1WpUrFgRLi4ukEql2mGAXl5ecHNzA5DXgzVnzhzs3LkToaGhAIBq1arh4MGDWLJkCdq0aYNFixahevXq+OKLLwAAtWvXxoULFzBv3rwi8zFp0iR8/PHH2sdz5szBmDFjCmw7fvx4dO3aFUDeMLx69erh+vXrCAoKQuXKlXV6jkaPHo3t27dj7dq1BhdSX375Jfr06QNvb2/Uq1cPzZs3R48ePbTXaqWmpmLhwoX49ttvERERAQCoXr06WrZsCQBYs2YNsrKysHLlSjg6OgIAvv32W3Tr1g3z5s3TFmfFea+JiIiITMXLWVGi7SyBhZSR7GU2uDwzzKC2x2MSMWj5iSLbrRjcBE0Di76uyF5mY9Dravz9999wcnKCUqmEWq3GG2+8genTp2vXBwcH6/Q8nDt3DtevX4ezs7POdrKysnDjxg0kJyfj3r17aNasmXadra0tGjdurHfY4dmzZ2FjY4M2bdoYHPf169eRkZGBjh076izPyclBw4YNAQBRUVE6cQDQFl1FmTBhgnYIIQBUrFhRb9sXXnhB+7uPT961bAkJCQgKCoJKpcKcOXOwdu1a3LlzBzk5OcjOzoaDg4NBcQBA3bp1cfHiRZw6dQqHDh3C/v370a1bNwwaNAg//fQToqKikJ2djfbt2xf4/KioKISEhGiLKABo0aIF1Go1rl69qi2k6tevb9R7TURERGRKTQPd4eOqQHxyVoGXwUgAeLsqDPqObCkspIwkkUgMHl7XqqanQQdIq5qeJrmI7uWXX8aiRYtgZ2cHX19f2Nrqxv30l28ASEtLQ6NGjbB69ep829I37KwomqF6xtBc37NlyxZUrlxZZ51cLi9WHE+rWLEiatSoYVBbmUym/V3Tc6NWqwEA//d//4eFCxdiwYIFCA4OhqOjI8aOHYucnByj4pFKpWjSpAmaNGmCsWPHYtWqVXjrrbcwZcqUYuWvIOZ4r4mIiIgMZSOVYFq3unhv1el86zTfiqd1q2u1E00AnGzCpDQHCPDkgNAwxwHi6OiIGjVqwN/fP18RVZAXX3wR0dHR8PLyQo0aNXR+XF1d4erqCh8fHxw7dkz7nNzcXJw6dUrvNoODg6FWq7Fv374C12t6SVQqlXZZ3bp1IZfLERcXly8OPz8/AECdOnVw/PhxnW0dPXq0yH0sSYcOHUKPHj3w5ptvIiQkBNWqVcO1a9eee7t16+YdM+np6ahZsybs7e2xa9euAtvWqVMH586dQ3p6uk5cUqlUO6lEQYp6r4mIiIhMrXN9H8x/7YV8y71dFSad2bqkWLSQ0gxj8vX1LfBmqGlpaRg1ahSqVKkCe3t71K1bF4sXL9Zpk5WVhZEjR8LDwwNOTk7o3bs37t+/b8a9KFzn+j5Y9OaL8HbVHd9pjQfIgAEDULFiRfTo0QMHDhxATEwM9u7dizFjxuD27dsAgPfffx+fffYZNm7ciCtXrmDEiBGF3gOqatWqiIiIwJAhQ7Bx40bExMTg4MGDWLt2LQAgICAAEokEf//9Nx48eIC0tDQ4Oztj/Pjx+OCDD/Dzzz/jxo0bOH36NL755hv8/PPPAIB3330X0dHRmDBhAq5evYo1a9boTK5gDjVr1kRkZCQOHz6MqKgovPPOO0Yfe3369MFXX32FY8eOITY2Fnv37sXIkSNRq1YtBAUFQaFQYNKkSZg4cSJWrlyJGzdu4OjRo1i6dCmAvPdMoVAgIiICFy9exJ49ezB69Gi89dZbqFSpkt7XNeS9JiIiIjK1WpVcAACuClsMrKnCqiGNcXBSO6v6jqyPRQup9PR0hISE4Lvvvitw/bhx47Bt2zasWrUKUVFRGDt2LEaNGqWdwhsAPvjgA2zevBnr1q3Dvn37cPfuXe1ECNaic30fHJzUDr8OewkL+zXAr8NessoDxMHBAfv374e/vz9effVV1KlTB0OHDkVWVhZcXPIO8g8//BBvvfUWIiIiEBoaCmdnZ/Tq1avQ7S5atAh9+vTBiBEjULduXbz//vvaHpTKlStjxowZ+Oijj1CpUiWMGjUKADBr1ixMnToVc+fORZ06ddC5c2ds2bIFgYGBAAB/f3/8+eef2LhxI0JCQrB48WLMmTPHhNnJ7+OPP8aLL76IsLAwtG3bFt7e3ujZs6dR2wgLC8PmzZvRrVs31KpVCxEREQgKCsKOHTu0vYhTp07Fhx9+iE8++QR16tRB3759kZCQACDvPdu+fTsSExPRpEkT9OnTB+3bt8e3335b6Osa8l4TERERmVpcYgYAoLqXExpVFGgW6G7Vw/meJhHG3pzIRCQSCTZs2KDzRbR+/fro27cvpk6dql3WqFEjdOnSBbNnz0ZycjI8PT2xZs0a9OnTBwBw5coV1KlTB0eOHMFLL71k0GunpKTA1dUVycnJ+b5EZmVlISYmBoGBgVAorHfWkNJCrVYjJSVFO2sfmVZJ5pufBcMolUps3boV4eHhOtfYkekw5+bFfJsfc25+zLn5LNp7A/O2XUGPEB+0c7hlFTkvrDZ4mlVPNtG8eXNs2rQJQ4YMga+vL/bu3Ytr167hq6++AgCcOnUKSqUSHTp00D4nKCgI/v7+hRZS2dnZyM7O1j5OSUkBkPehUSqVOm2VSiWEEFCr1dpJBqj4NHW7JqdkWiWZb7VaDSEElEolbGyMm0GyPNGcQ549l5DpMOfmxXybH3Nufsy5+dx8mDfJmK+LHZBrHTk3NAarLqS++eYbDB8+HFWqVIGtrS2kUil+/PFHtG7dGgAQHx8POzs77f2HNCpVqoT4+Hi92507dy5mzJiRb/mOHTvyTV1ta2sLb29vpKWlGT0bG+mXmppq6RDKlZLId05ODjIzM7F//37k5uaWQFRlm+bmx2Q+zLl5Md/mx5ybH3NuemejpQCkSL77L+BlHTnPyMgwqJ3VF1JHjx7Fpk2bEBAQgP3792PkyJHw9fXV6YUy1uTJkzFu3Djt45SUFPj5+aFTp04FDu27desWnJycOJypBAghkJqaCmdnZ+104mQ6JZnvrKws2Nvbo3Xr1vwsFEKpVCIyMhIdO3a0+NCE8oI5Ny/m2/yYc/Njzs3ni6sHAGSic8vGeHzthFXkXDNarShWW0hlZmbif//7HzZs2ICuXbsCyLs56tmzZzF//nx06NAB3t7eyMnJQVJSkk6v1P379+Ht7a1323K5vMD7EclksnxvnEqlgkQigVQq5TU9JUAzvEyTUzKtksy3VCqFRCIp8HNC+TFP5secmxfzbX7Mufkx56aVq1LjblIWAKCqpzMeX7OOnBv6+lb7TVZzvdKzX/5sbGy0Xw4bNWoEmUymc4+dq1evIi4uDqGhoWaNl4iIiIiIDHcvOQu5agE7GykqOefv5LB2Fu2RSktLw/Xr17WPY2JicPbsWbi7u8Pf3x9t2rTBhAkTYG9vj4CAAOzbtw8rV67El19+CQBwdXXF0KFDMW7cOLi7u8PFxQWjR49GaGiowTP2ERERERGR+d16nHctUpUK9pCWkinPn2bRQurkyZN4+eWXtY811y1FRERgxYoV+O233zB58mQMGDAAiYmJCAgIwKeffop3331X+5yvvvoKUqkUvXv3RnZ2NsLCwvD999+bfV+IiIiIiMhwt/67h5Sfu0MRLa2TRQuptm3borDbWHl7e2P58uWFbkOhUOC7777Te1NfIiIiIiKyPpqb8fqX0kLKaq+RIiIiIiKisisuMRMA4Odub+FIioeFFFmEjY0NNm7cWKzntm3bFmPHji3ReKZPn44GDRqU6DaJiIiISD/2SJFVO3LkCGxsbLRTyBujatWqWLBgQckHZYBBgwZBIpHk+7l+/TrWr1+PWbNmmT2mDRs24KWXXoKrqyucnZ1Rr169Ei/oiIiIiMqL26X8GikWUmXc0qVLMXr0aOzfvx937961dDhG6dy5M+7du6fzExgYCHd3dzg7O5s1ll27dqFv377o3bs3jh8/jlOnTuHTTz+FUqk02WuqVCrtVP9EREREZUladi4epecAYCFV7qTnpOv9ycrNMrhtpjLToLbFkZaWht9//x3vvfceunbtihUrVuRrs3nzZjRp0gQKhQIVK1ZEr169AOQNn4uNjcUHH3yg7Q0CCh4Ct2DBAlStWlX7+MSJvLtSV6xYEa6urmjTpg1Onz5tdPxyuRze3t46PzY2NvmG9lWtWhVz5szBkCFD4OzsDH9/f/zwww8625o0aRJq1aoFBwcHVKtWDVOnTjWqCNq8eTNatGiBCRMmoHbt2qhVqxZ69uyZb5ITffkEgMePH2PgwIGoUKECHBwc0KVLF0RHR2vXr1ixAm5ubti0aRPq1q0LuVyOuLg4ZGdnY/z48ahcuTIcHR3RrFkz7N2717hkEhEREVkRzYx9FRxkcFGUzpses5AqJqe5Tnp/eq/trdPWa76X3rZdVnfRaVt1YdUC2xXH2rVrERQUhNq1a+PNN9/EsmXLdGZJ3LJlC3r16oXw8HCcOXMGu3btQtOmTQEA69evR5UqVTBz5kxtb5ChUlNTERERgYMHD+Lo0aOoWbMmwsPDkZqaWqz9MMQXX3yBxo0b48yZMxgxYgTee+89XL16Vbve2dkZK1aswOXLl7Fw4UL8+OOP+Oqrrwzevre3Ny5duoSLFy/qbVNYPoG84YonT57Epk2bcOTIEQghEB4erlPQZWRkYN68efjpp59w6dIleHl5YdSoUThy5Ah+++03nD9/Hq+99ho6d+6sU4QRERERlSZxpXxYH2Dh6c/JtJYuXYo333wTQN4wueTkZOzbtw9t27YFAHz66afo168fZsyYoX1OSEgIAMDd3R02NjZwdnaGt7e3Ua/brl07ncc//PAD3NzcsG/fPoSHhxu8nb///htOTk+KyC5dumDdunUFtg0PD8eIESMA5PU+ffXVV9izZw9q164NAPj444+1batWrYrx48fjt99+w8SJEw2KZfTo0Thw4ACCg4MREBCAl156CZ06dcKAAQMgl+fdibuwfEZHR2PTpk04dOgQmjdvDgBYvXo1/Pz8sHHjRrz22msAAKVSie+//177vLi4OCxfvhxxcXHw9fUFAIwfPx7btm3D8uXLMWfOHIPiJyIiIrImpf0eUgALqWJLm5ymd52N1EbnccL4BL1tpRLdTsGb7998rrg0rl69iuPHj2PDhg0AAFtbW/Tt2xdLly7VFlJnz57FsGHDSuT1nnb//n18/PHH2Lt3LxISEqBSqZCRkYG4uDijtvPyyy9j0aJF2seOjo56277wwgva3yUSCby9vZGQ8CTvv//+O77++mvcuHEDaWlpyM3NhYuLi8GxODo6YsuWLbhx4wb27NmDo0eP4sMPP8TChQtx5MgRODg4FJrPqKgo2NraolmzZtplHh4eqF27NqKiorTL7OzsdPblwoULUKlUqFWrls72srOz4eHhYXD8RERERNbkVimfsQ9gIVVsjnb6v9Sbq21hli5ditzcXG0vBgAIISCXy/Htt9/C1dUV9vbGz9kvlUrz3UT52WuNIiIi8OjRIyxcuBABAQGQy+UIDQ1FTk6OUa/l6OiIGjVqGNRWJtMdWyuRSLQTNRw5cgQDBgzAjBkzEBYWBldXV/z222/44osvjIoHAKpXr47q1avj7bffxpQpU1CrVi38/vvvGDx4cLHy+Sx7e3vt9WhA3nVuNjY2OHXqFGxsdAv0p3vriIiIiEqT0j71OcBrpMqk3NxcrFy5El988QXOnj2r/Tl37hx8fX3x66+/Asjrxdm1a5fe7djZ2UGlUuks8/T0RHx8vE4xdfbsWZ02hw4dwpgxYxAeHo569epBLpfj4cOHJbeDRjp8+DACAgIwZcoUNG7cGDVr1kRsbOxzb7dq1apwcHBAenreZCCF5bNOnTrIzc3FsWPHtMsePXqEq1evom7dunpfo2HDhlCpVEhISECNGjV0fowdcklERERkLbTXSFUovYUUe6TKoL///huPHz/G0KFD4erqqrOud+/eWLp0Kd59911MmzYN7du3R/Xq1dGvXz/k5uZi69atmDRpEoC8QmH//v3o168f5HI5KlasiLZt2+LBgwf4/PPP0adPH2zbtg3//POPzjC5mjVr4pdffkHjxo2RkpKCCRMmlEhvTXHVrFkTcXFx+O2339CkSRNs2bJFO+TRUNOnT0dGRgbCw8MREBCApKQkfP3111AqlejYsSMAFJrPmjVrokePHhg2bBiWLFkCZ2dnfPTRR6hcuTJ69Oih93Vr1aqFAQMGYODAgfjiiy/QsGFDPHjwALt27cILL7xQrPuDEREREVmSWi1w+3HezNXskSKrsnTpUnTo0CFfEQXkFVInT57E+fPn0bZtW6xbtw6bNm1CgwYN0K5dOxw/flzbdubMmbh58yaqV68OT09PAHk9K99//z2+++47hISE4Pjx4xg/fny+13/8+DFefPFFvPXWWxgzZgy8vLxMu9OF6N69Oz744AOMGjUKDRo0wOHDhzF16lSjttGmTRv8+++/GDhwIIKCgtClSxfEx8djx44d2gktisrn8uXL0ahRI7zyyisIDQ2FEAJbt27NNyzxWcuXL8fAgQPx4Ycfonbt2ujZsydOnDgBf39/45NBREREZGEP0rKRnauGjVQCHzeFpcMpNol49oKXciglJQWurq5ITk7ONwFBVlYWYmJiEBgYCIWi9L7R1kKtViMlJQUuLi6QSlnHm1pJ5pufBcMolUps3boV4eHhRRbJVDKYc/Nivs2POTc/5ty0TtxMxGuLj8DP3R4HJubN9mxNOS+sNngav8kSEREREZHZxD0q/RNNACykiIiIiIjIjMrCRBMACykiIiIiIjKjW49L/814ARZSRERERERkRmXhZrwACymDcU4OKu/4GSAiIqKSUBZuxguwkCqSjY0NACAnJ8fCkRBZVkZG3knP0jPpEBERUemVpVThfko2gNI/tI835C2Cra0tHBwc8ODBA8hkMk7Z/ZzUajVycnKQlZXFXJpBSeRbCIGMjAwkJCTAzc1N+8cFIiIiImNpbsTrJLdFBYfS/cdZFlJFkEgk8PHxQUxMDGJjYy0dTqknhEBmZibs7e0hkUgsHU6ZV5L5dnNzg7e3dwlFRkREROWR5vooP3eHUv9dkIWUAezs7FCzZk0O7ysBSqUS+/fvR+vWrTlEzAxKKt8ymYw9UURERPTcnlwfZW/hSJ4fCykDSaVSKBQKS4dR6tnY2CA3NxcKhYKFlBkw30RERGRNyso9pABONkFERERERGainfrcg4UUERERERGRQeISy8bNeAEWUkREREREZAZCiDJzM16AhRQREREREZlBYnoO0nNUkEiAym6lf7IJFlJERERERGRymmF9lZwVUMhK/2zALKSIiIiIiMjkbv13M96yMKwPYCFFRERERERmcKsMTTQBsJAiIiIiIiIziHtUdiaaAFhIERERERGRGTyZ+rz0TzQBsJAiIiIiIiIzuPWYPVJEREREREQGU6rUuJvEySaIiIiIiIgMdjcpE2oByG2l8HSWWzqcEsFCioiIiIiITEpzfZS/uwMkEomFoykZLKSIiIiIiMikbiXmDesrK1OfAyykiIiIiIjIxJ7ukSorWEgREREREZFJlbWb8QIspIiIiIiIyMTYI0VERERERGSksnYzXoCFFBERERERmVByphLJmUoAgF8F9kgREREREREVSXN9VEUnOzjKbS0cTclhIUVERERERCZTFieaAFhIERERERGRCZXFiSYAFlJERERERGRCtx7/1yNVhq6PAlhIERERERGRCcUlZgJgjxQREREREZHBeI0UERERERGREVRqgdv/De3z92AhRUREREREVKT7KVlQqgRkNhJ4uygsHU6JYiFFREREREQmoZmxr7KbPWykEgtHU7JYSBERERERkUnEldHrowAWUkREREREZCK3yug9pAAWUkREREREZCLskSIiIiIiIjISe6SIiIiIiIiMVFZvxgtYuJDav38/unXrBl9fX0gkEmzcuDFfm6ioKHTv3h2urq5wdHREkyZNEBcXp12flZWFkSNHwsPDA05OTujduzfu379vxr0gIiIiIqJnZeTk4mFaNgAO7Stx6enpCAkJwXfffVfg+hs3bqBly5YICgrC3r17cf78eUydOhUKxZM56D/44ANs3rwZ69atw759+3D37l28+uqr5toFIiIiIiIqwK3/eqNc7WVwtZdZOJqSZ2vJF+/SpQu6dOmid/2UKVMQHh6Ozz//XLusevXq2t+Tk5OxdOlSrFmzBu3atQMALF++HHXq1MHRo0fx0ksvFbjd7OxsZGdnax+npKQAAJRKJZRK5XPtExVOk1/m2TyYb/Njzs2POTcv5tv8mHPzY85LRsyDvO/YVSooisylNeXc0BgkQghh4lgMIpFIsGHDBvTs2RMAoFar4erqiokTJ+LgwYM4c+YMAgMDMXnyZG2b3bt3o3379nj8+DHc3Ny02woICMDYsWPxwQcfFPha06dPx4wZM/ItX7NmDRwcyl63IxERERGRue29J8GGmzZo4K7G4NpqS4djsIyMDLzxxhtITk6Gi4uL3nYW7ZEqTEJCAtLS0vDZZ59h9uzZmDdvHrZt24ZXX30Ve/bsQZs2bRAfHw87OzudIgoAKlWqhPj4eL3bnjx5MsaNG6d9nJKSAj8/P3Tq1KnQZNHzUyqViIyMRMeOHSGTlb0uXmvDfJsfc25+zLl5Md/mx5ybH3NeMk5tuQLcjEOTutUQHlar0LbWlHPNaLWiWG0hpVbnVa09evTQ9iw1aNAAhw8fxuLFi9GmTZtib1sul0Mul+dbLpPJLP7GlRfMtXkx3+bHnJsfc25ezLf5Mefmx5w/nztJWQCAqp5OBufRGnJu6Otb7fTnFStWhK2tLerWrauzvE6dOtpZ+7y9vZGTk4OkpCSdNvfv34e3t7e5QiUiIiIiomfcevzfzXgrlM1LZ6y2kLKzs0OTJk1w9epVneXXrl1DQEAAAKBRo0aQyWTYtWuXdv3Vq1cRFxeH0NBQs8ZLRERERER5hBCIK8M34wUsPLQvLS0N169f1z6OiYnB2bNn4e7uDn9/f0yYMAF9+/ZF69at8fLLL2Pbtm3YvHkz9u7dCwBwdXXF0KFDMW7cOLi7u8PFxQWjR49GaGio3hn7iIiIiIjItB6kZSNLqYZUAvi62Vs6HJOwaCF18uRJvPzyy9rHmgkgIiIisGLFCvTq1QuLFy/G3LlzMWbMGNSuXRt//vknWrZsqX3OV199BalUit69eyM7OxthYWH4/vvvzb4vRERERESU59Z/vVE+rvaws7XaQXDPxaKFVNu2bVHU7OtDhgzBkCFD9K5XKBT47rvv9N7Ul4iIiIiIzKusD+sDrPgaKSIiIiIiKp1uJWYCAPzcy+awPoCFFBERERERlTD2SBERERERERlJU0j5sZAiIiIiIiIyzC32SBERERERERkuO1eF+JQsAOyRIiIiIiIiMsidx5kQAnCws4GHo52lwzEZFlJERERERFRinp5oQiKRWDga02EhRUREREREJeZWOZhoAmAhRUREREREJejW47x7SJXliSYAFlJERERERFSC4h791yNVoezejBdgIUVERERERCVIe42UB3ukiIiIiIiIiiSEKBf3kAJYSBERERERUQlJylAiNTsXAFClAgspIiIiIiKiIt16nNcb5eUsh0JmY+FoTIuFFBERERERlYi4cjKsD2AhRUREREREJYSFFBERERERkZHKy814ARZSRERERERUQm4l5t2Ml4UUERERERGRgTi0j4iIiIiIyAi5KjXuJOX1SLGQIiIiIiIiMsC95Cyo1AJ2tlJ4OcstHY7JFauQys3Nxc6dO7FkyRKkpqYCAO7evYu0tLQSDY6IiIiIiEoH7UQTFewhlUosHI3p2Rr7hNjYWHTu3BlxcXHIzs5Gx44d4ezsjHnz5iE7OxuLFy82RZxERERERGTF4srRjH1AMXqk3n//fTRu3BiPHz+Gvb29dnmvXr2wa9euEg2OiIiIiIhKh/I00QRQjB6pAwcO4PDhw7Czs9NZXrVqVdy5c6fEAiMiIiIiotKjvBVSRvdIqdVqqFSqfMtv374NZ2fnEgmKiIiIiIhKl/J0M16gGIVUp06dsGDBAu1jiUSCtLQ0TJs2DeHh4SUZGxERERERlRK3Hv93M94K5aOQMnpo3/z589G5c2fUrVsXWVlZeOONNxAdHY2KFSvi119/NUWMRERERERkxVKzlEhMzwEA+LnbF9G6bDC6kPLz88O5c+fw+++/49y5c0hLS8PQoUMxYMAAnckniIiIiIiofLiVmNcb5e5oB2eFzMLRmIdRhZRSqURQUBD+/vtvDBgwAAMGDDBVXEREREREVEqUt6nPASOvkZLJZMjKyjJVLEREREREVArdfly+ZuwDijHZxMiRIzFv3jzk5uaaIh4iIiIiIipltD1SFcrPpT5GXyN14sQJ7Nq1Czt27EBwcDAcHR111q9fv77EgiMiIiIiIutX3u4hBRSjkHJzc0Pv3r1NEQsREREREZVCLKQMsHz5clPEQUREREREpZBaLXBbcw8pFlJFe/DgAa5evQoAqF27Njw9PUssKCIiIiIiKh0SUrORk6uGjVQCH1eFpcMxG6Mnm0hPT8eQIUPg4+OD1q1bo3Xr1vD19cXQoUORkZFhihiJiIiIiMhKaYb1VXazh62N0eVFqWX0no4bNw779u3D5s2bkZSUhKSkJPz111/Yt28fPvzwQ1PESEREREREVqo8Xh8FFGNo359//ok//vgDbdu21S4LDw+Hvb09Xn/9dSxatKgk4yMiIiIiIitWHm/GCxSjRyojIwOVKlXKt9zLy4tD+4iIiIiIypnb2kKq/NxDCihGIRUaGopp06YhKytLuywzMxMzZsxAaGhoiQZHRERERETWjUP7DLRw4UKEhYWhSpUqCAkJAQCcO3cOCoUC27dvL/EAiYiIiIjIerGQMlD9+vURHR2N1atX48qVKwCA/v37Y8CAAbC3L1/deURERERE5VmWUoWE1GwALKQM4uDggGHDhpV0LEREREREVIrcfpzXG+WssIWrvczC0ZiX0ddIzZ07F8uWLcu3fNmyZZg3b16JBEVERERERNZPO2NfBQdIJBILR2NeRhdSS5YsQVBQUL7l9erVw+LFi0skKCIiIiIisn5xj8rn9VFAMQqp+Ph4+Pj45Fvu6emJe/fulUhQRERERERk/eISMwEA/h7lr5Ay+hopPz8/HDp0CIGBgTrLDx06BF9f3xILzBLSc9Jhk2OTb7mN1AYKW4VOO32kEinsZfbFapuhzIAQosC2EokEDjKHYrXNVGZCLdR643C0cyxW26zcLKjUKqPaKpVKZKmykJ6TDpl4Mo7WQfakOzg7Nxu56ly92zWmrb3MHlJJ3t8LclQ5UKqUJdJWYauAjdTG6LZKlRI5qhy9beW2cthKbY1um6vORXZudr42mnwrVUrIZLJC22rY2dhBZpPXVqVWISs3S29bmY0MdjZ2RrdVCzUylZkl0tZWagu5rRwAIIRAhlL//eyMaWvM5/7ZtgUd4xo8RxSvbWGf+2fPKzxH5G9rzOe+qLYS9ZOhOzxHFO8cYez3CH3/dvIc8URJf4/Q5PzpfeE5ouBzxL+PHkGNLHi55B2vz/U9opB/P815jijsM6rzXINaPWXYsGEYO3YslEol2rVrBwDYtWsXJk6ciA8//NDYzVkV3y98AUX+5eE1w7HljS3ax17zvfSeXNsEtMHeQXu1j6surIqHGQ8LbNvYtzFODDuhfVz3u7qITY4tsG1dz7q4NOKS9nGTH5vg8oPLBbYNcA3AzbE3tY9br2iNk3dPFti2okNFPJjwQPu4y+ou2Be7r8C2DjIHpP/vyYHVe21vbI3eWmBbABDTnpyg39rwFv64/MeTlRd026ZNTtOeMN/5+x38fO5nvdtNGJ8AT0dPAMC47ePw/cnv9baNeT8GVd2qAgCm7JqC+Ufm62178b2LqOdVDwAw58AczNg3Q2/b428fR5PKTQAAC48uxMSdE/W23ROxB22rtgUA/HDqB4z6Z5Tetn/3/xtda3UFAKy+sBqD/xqst+3aPmvxWr3XAAAbojbg9T9e19v2p4CfMLTRUADA9uvb8cqvr+ht+22XbzGy6UgAwIG4A3j555f1tv28w+eY0GICAOD0vdNo+lNTvW2ntZmG6W2nAwCiHkSh/qL6etuODx2P/+v0fwCAuOQ4BC4M1Nt2ROMR+K7rdwCAhxkP4TXfS2/biJAIrOi5AkDelwinuU562/ap2wfrXlunfVxY22fPERGXIpB9oeB/kHiOeKLQc8QzDDpH/Hde4TkijzHniOU9lmNQg0EAij5HLOy0EAEIAMBzRHHPEcX+HvHMv508Rzxhqu8R11pdQ03PmgB4jij0HGEPDNuV91Pc7xFn4s+g34V++Y5zDbOeI/TXfjqMLqQmTJiAR48eYcSIEcjJyatyFQoFJk2ahMmTJxu7OSIiIiIiolJHIvT16xYhLS0NUVFRsLe3R82aNSGXy0s6NrNJSUmBq6sr7j64CxcXl3zrObSv4LbFHdq3fft2hIWFaYeaARzap2GKoX3bt29Ht/BucFA4FNpWg0P78hR32I5SqcT6zevzHeMaPEcUr21RQ/uePq/wHJG/bUkP7YvcHonw8HBIbaQ8R/zH1EP7Cvq3k+eIJ0wxtG/79u3o+UpPyO3yjgmeI/KfIx6mZ6PVvD2QSIAzUztCbmtT7O8RWdlZ+GvLX3r//TTnOSIlJQW+nr5ITk4usDbQPlfvmiI4OTmhSZMmiI2NxY0bNxAUFASp1Oi5K6yKo52jzoe2sHbGbNNQT5+0SrLt0yfZkmz79D8KhrZVSpRQ2CjgaOdY4IcEyPtgy2FYYW5MWzsbO+2HylJtZTYy7cmlJNvaSm1ha5f/46zJ99Pb0de2IDZSG4OPYWPaSiVSk7SVSCQmaQsY91ku6hgv7nbLwznCEM9+7gs7r/AckceYz31RbZXKJ1/4eI54wpRtDfm3E+A5QqMkvkdocq4pjACeIwpqezU+B1Io4OuigLtDwZ0RxpwjDP3309TnCJWd/qJdZ9sGtULefaK+/PJLnWXDhw9HtWrVEBwcjPr16+PWrVuGbo6IiIiIiEqxW5p7SJXDqc8BIwqpH374ARUqVNA+3rZtG5YvX46VK1fixIkTcHNzw4wZ+i+qIyIiIiKisqO8F1IGD+2Ljo5G48aNtY//+usv9OjRAwMGDAAAzJkzB4MH658ZhIiIiIiIyo64xPJ7M17AiB6pzMxMnYutDh8+jNatW2sfV6tWDfHx8Ua9+P79+9GtWzf4+vpCIpFg48aNetu+++67kEgkWLBggc7yxMREDBgwAC4uLnBzc8PQoUORlpZmVBxERERERGQcFlIGCggIwKlTpwAADx8+xKVLl9CiRQvt+vj4eLi6uhr14unp6QgJCcF3331XaLsNGzbg6NGjBd7wd8CAAbh06RIiIyPx999/Y//+/Rg+fLhRcRARERERkXFuJebNhsehfUWIiIjAyJEjcenSJezevRtBQUFo1KiRdv3hw4dRv77+G2MVpEuXLujSpUuhbe7cuYPRo0dj+/bt6Nq1q866qKgobNu2DSdOnNAOO/zmm28QHh6O+fPnF1h4ERERERHR88nJVeNesqaQMny2xrLE4EJq4sSJyMjIwPr16+Ht7Y1169bprD906BD69+9fosGp1Wq89dZbmDBhAurVq5dv/ZEjR+Dm5qZz7VaHDh0glUpx7Ngx9OrVq8DtZmdnIzv7yVz5KSkpAPKmdH16WlcqeZr8Ms/mwXybH3Nufsy5eTHf5secmx9zXrS4RxlQC0Ahk8JNLn3uXFlTzg2NweBCSiqVYubMmZg5c2aB658trErCvHnzYGtrizFjxhS4Pj4+Hl5eXjrLbG1t4e7uXuj1WnPnzi1whsEdO3bAwaF8dk2aW2RkpKVDKFeYb/Njzs2POTcv5tv8mHPzY871u5IkAWADN1sV/vnnnxLbrjXkPCND/824n1bsG/Ka2qlTp7Bw4UKcPn1ae/fpkjJ58mSMGzdO+zglJQV+fn7o1KlToXcvpuenVCoRGRmJjh07GnSzUno+zLf5Mefmx5ybF/Ntfsy5+THnRUs+cQuIikJdfy+Ehzd87u1ZU841o9WKYrWF1IEDB5CQkAB/f3/tMpVKhQ8//BALFizAzZs34e3tjYSEBJ3n5ebmIjExEd7e3nq3LZfLIZfnv4u1TCaz+BtXXjDX5sV8mx9zbn7MuXkx3+bHnJsfc67fneS8y2QCKjqWaI6sIeeGvr7VFlJvvfUWOnTooLMsLCwMb731lvZ+VaGhoUhKSsKpU6e0E1/s3r0barUazZo1M3vMRERERETlgfZmvBXK72UxFi2k0tLScP36de3jmJgYnD17Fu7u7vD394eHh4dOe5lMBm9vb9SuXRsAUKdOHXTu3BnDhg3D4sWLoVQqMWrUKPTr148z9hERERERmUh5v4cUYMR9pEzh5MmTaNiwIRo2zBtXOW7cODRs2BCffPKJwdtYvXo1goKC0L59e4SHh6Nly5b44YcfTBUyEREREVG5F/fov0LKo/wWUgb1SD09MUNRvvzyS4Pbtm3bFkIIg9vfvHkz3zJ3d3esWbPG4G0QEREREVHxJWcokZKVC4BD+4p05swZgzZW0rPrERERERGRdbn1OK83qqKTHPZ2NhaOxnIMKqT27Nlj6jiIiIiIiKgUeHJ9lL2FI7Esi14jRUREREREpQsnmshTrFn7Tp48ibVr1yIuLg45OTk669avX18igRERERERkfW5xUIKQDF6pH777Tc0b94cUVFR2LBhA5RKJS5duoTdu3fD1dXVFDESEREREZGV0PRIVWEhZZw5c+bgq6++wubNm2FnZ4eFCxfiypUreP311+Hv72+KGImIiIiIyEqwRyqP0YXUjRs30LVrVwCAnZ0d0tPTIZFI8MEHH/D+TUREREREZZhKLXAnKRMACymjC6kKFSogNTUVAFC5cmVcvHgRAJCUlISMjIySjY6IiIiIiKxGfEoWlCoBOxspKrkoLB2ORRk92UTr1q0RGRmJ4OBgvPbaa3j//fexe/duREZGon379qaIkYiIiIiIrEDco/+uj6pgDxtp+b6HrNGF1LfffousrCwAwJQpUyCTyXD48GH07t0bH3/8cYkHSERERERE1uEWJ5rQMrqQcnd31/4ulUrx0UcflWhARERERERknXgz3ieKdR8ptVqN69evIyEhAWq1Wmdd69atSyQwIiIiIiKyLrwZ7xNGF1JHjx7FG2+8gdjYWAghdNZJJBKoVKoSC46IiIiIiKzHrccspDSMLqTeffddNG7cGFu2bIGPjw8kkvJ9kRkRERERUXmhvUaqAgspowup6Oho/PHHH6hRo4Yp4iEiIiIiIiuUnp2Lh2k5AAB/DxZSRt9HqlmzZrh+/bopYiEiIiIiIiulGdbn5iCDi0Jm4Wgsz+geqdGjR+PDDz9EfHw8goODIZPpJvGFF14oseCIiIiIiMg63ErMBMDrozSMLqR69+4NABgyZIh2mUQigRCCk00QEREREZVRmhn7/FhIAShGIRUTE2OKOIiIiIiIyIppJprw40QTAIpRSAUEBJgiDiIiIiIismK8h5QugwqpTZs2oUuXLpDJZNi0aVOhbbt3714igRERERERkfW4xUJKh0GFVM+ePREfHw8vLy/07NlTbzteI0VEREREVPYIIdgj9QyDCim1Wl3g70REREREVPY9SM1Gdq4aUgng46awdDhWweD7SPn7++PRo0fax99++y1SUlJMEhQREREREVkPTW+Ur5s9ZDZG34q2TDI4C7dv39YZtve///0PDx8+NElQRERERERkPTisL79il5NCiJKMg4iIiIiIrBRvxpsf++WIiIiIiKhQvBlvfkbdR+qnn36Ck5MTACA3NxcrVqxAxYoVddqMGTOm5KIjIiIiIiKLu8VCKh+DCyl/f3/8+OOP2sfe3t745ZdfdNpIJBIWUkREREREZQyvkcrP4ELq5s2bJgyDiIiIiIisUZZShfupWQBYSD2N10gREREREZFed5IyIQTgJLdFBQeZpcOxGiykiIiIiIhIL82wvioV7CGRSCwcjfVgIUVERERERHrd4vVRBWIhRUREREREerGQKhgLKSIiIiIi0ks7Y58HC6mnGTRrX0pKisEbdHFxKXYwRERERERkXeISMwEAfhVYSD3NoELKzc3N4AvLVCrVcwVERERERETWQQjBm/HqYVAhtWfPHu3vN2/exEcffYRBgwYhNDQUAHDkyBH8/PPPmDt3rmmiJCIiIiIis3ucoURadi6AvFn76AmDCqk2bdpof585cya+/PJL9O/fX7use/fuCA4Oxg8//ICIiIiSj5KIiIiIiMxO0xvl7aKAQmZj4Wisi9GTTRw5cgSNGzfOt7xx48Y4fvx4iQRFRERERESWF8cZ+/QyupDy8/PDjz/+mG/5Tz/9BD8/vxIJioiIiIiILE97M153Dut7lkFD+5721VdfoXfv3vjnn3/QrFkzAMDx48cRHR2NP//8s8QDJCIiIiIiy+A9pPQzukcqPDwc165dQ7du3ZCYmIjExER069YN165dQ3h4uCliJCIiIiIiC7j1mIWUPkb3SAF5w/vmzJlT0rEQEREREZEV4TVS+hndIwUABw4cwJtvvonmzZvjzp07AIBffvkFBw8eLNHgiIiIiIjIMpQqNe4mZQHgPaQKYnQh9eeffyIsLAz29vY4ffo0srOzAQDJycnspSIiIiIiKiPuJWVBpRaQ20rh6SS3dDhWx+hCavbs2Vi8eDF+/PFHyGQy7fIWLVrg9OnTJRocERERERFZhub6KD93B0ilEgtHY32MLqSuXr2K1q1b51vu6uqKpKSkkoiJiIiIiIgsjNdHFc7oQsrb2xvXr1/Pt/zgwYOoVq1aiQRFRERERESWxUKqcEYXUsOGDcP777+PY8eOQSKR4O7du1i9ejXGjx+P9957zxQxEhERERGRmWlvxluBN+MtiNHTn3/00UdQq9Vo3749MjIy0Lp1a8jlcowfPx6jR482RYxERERERGRmvBlv4YwupCQSCaZMmYIJEybg+vXrSEtLQ926deHk5GSK+IiIiIiIyAK0hZQHC6mCGD20b8iQIUhNTYWdnR3q1q2Lpk2bwsnJCenp6RgyZIgpYiQiIiIiIjNKyVLicYYSAOBXgYVUQYwupH7++WdkZmbmW56ZmYmVK1eWSFBERERERGQ5mt4oD0c7OMqNHsRWLhiclZSUFAghIIRAamoqFAqFdp1KpcLWrVvh5eVlkiCJiIiIiMh8NIWUH6+P0svgQsrNzQ0SiQQSiQS1atXKt14ikWDGjBklGhwREREREZnfrcS8EWicaEI/g4f27dmzB7t27YIQAn/88Qd2796t/Tl48CDi4uIwZcoUo158//796NatG3x9fSGRSLBx40btOqVSiUmTJiE4OBiOjo7w9fXFwIEDcffuXZ1tJCYmYsCAAXBxcYGbmxuGDh2KtLQ0o+IgIiIiIqIneA+pohncI9WmTRsAQExMDPz9/SGRSJ77xdPT0xESEoIhQ4bg1Vdf1VmXkZGB06dPY+rUqQgJCcHjx4/x/vvvo3v37jh58qS23YABA3Dv3j1ERkZCqVRi8ODBGD58ONasWfPc8RERERERlUdx2qF9vIeUPkZfObZ79244OTnhtdde01m+bt06ZGRkICIiwuBtdenSBV26dClwnaurKyIjI3WWffvtt2jatCni4uLg7++PqKgobNu2DSdOnEDjxo0BAN988w3Cw8Mxf/58+Pr6Frjt7OxsZGdnax+npKQAyOsFUyqVBsdPxtPkl3k2D+bb/Jhz82POzYv5Nj/m3PyYcyDuUToAwNdFbpY8WFPODY1BIoQQxmy4Vq1aWLJkCV5++WWd5fv27cPw4cNx9epVYzb3JBCJBBs2bEDPnj31ttm5cyc6deqEpKQkuLi4YNmyZfjwww/x+PFjbZvc3FwoFAqsW7cOvXr1KnA706dPL/B6rjVr1sDBgd2XRERERFR+qQUw/pgNVEKCaS/mwl1u6YjMKyMjA2+88QaSk5Ph4uKit53RPVJxcXEIDAzMtzwgIABxcXHGbs5gWVlZmDRpEvr376/dofj4+HwzBdra2sLd3R3x8fF6tzV58mSMGzdO+zglJQV+fn7o1KlTocmi56dUKhEZGYmOHTtCJpNZOpwyj/k2P+bc/Jhz82K+zY85N7/ynvN7yVlQHd0PW6kE/Xt0gY30+S/pKYo15VwzWq0oRhdSXl5eOH/+PKpWraqz/Ny5c/Dw8DB2cwZRKpV4/fXXIYTAokWLnnt7crkccnn+0lomk1n8jSsvmGvzYr7Njzk3P+bcvJhv82POza+85vzef4VElQr2UMjtzPra1pBzQ1/f6EKqf//+GDNmDJydndG6dWsAecP63n//ffTr18/YzRVJU0TFxsZi9+7dOj1G3t7eSEhI0Gmfm5uLxMREeHt7l3gsRERERERlXRzvIWUQowupWbNm4ebNm2jfvj1sbfOerlarMXDgQMyZM6dEg9MUUdHR0dizZ0++Hq/Q0FAkJSXh1KlTaNSoEYC8yTDUajWaNWtWorEQEREREZUHvBmvYYwupOzs7PD7779j1qxZOHfuHOzt7REcHIyAgACjXzwtLQ3Xr1/XPo6JicHZs2fh7u4OHx8f9OnTB6dPn8bff/8NlUqlve7J3d0ddnZ2qFOnDjp37oxhw4Zh8eLFUCqVGDVqFPr166d3xj4iIiIiItLv1mPejNcQRhdSGrVq1UKtWrWe68VPnjypM/ufZgKIiIgITJ8+HZs2bQIANGjQQOd5e/bsQdu2bQEAq1evxqhRo9C+fXtIpVL07t0bX3/99XPFRURERERUXvFmvIYxqJAaN24cZs2aBUdHR53Z7gry5ZdfGvzibdu2RWGzrxsyM7u7uztvvktEREREVEK010hVYCFVGIMKqTNnzmhvTHXmzBm97SQS00+NSEREREREppGZo8KD1GwA7JEqikGF1J49ewr8nYiIiIiIyo7bj/N6o1wUtnB1KH9TvxtDaukAiIiIiIjIOmivj/Jgb1RRDOqRevXVVw3e4Pr164sdDBERERERWQ4nmjCcQT1Srq6u2h8XFxfs2rULJ0+e1K4/deoUdu3aBVdXV5MFSkREREREpsWJJgxnUI/U8uXLtb9PmjQJr7/+OhYvXgwbGxsAgEqlwogRI+Di4mKaKImIiIiIyOR4M17DGX2N1LJlyzB+/HhtEQUANjY2GDduHJYtW1aiwRERERERkfncSuTNeA1ldCGVm5uLK1eu5Ft+5coVqNXqEgmKiIiIiIjMSwjBa6SMYNDQvqcNHjwYQ4cOxY0bN9C0aVMAwLFjx/DZZ59h8ODBJR4gERERERGZ3sO0HGQqVZBIAF83e0uHY/WMLqTmz58Pb29vfPHFF7h37x4AwMfHBxMmTMCHH35Y4gESEREREZHpaXqjfF3tYWfLuyQVxehCSiqVYuLEiZg4cSJSUlIAgJNMEBERERGVcpqb8fq5szfKEMUqNXNzc7Fz5078+uuvkEgkAIC7d+8iLS2tRIMjIiIiIiLziHvE66OMYXSPVGxsLDp37oy4uDhkZ2ejY8eOcHZ2xrx585CdnY3FixebIk4iIiIiIjIh3kPKOEb3SL3//vto3LgxHj9+DHv7J91+vXr1wq5du0o0OCIiIiIiMg/tjH0eLKQMYXSP1IEDB3D48GHY2dnpLK9atSru3LlTYoEREREREZH53H6cdw8p3ozXMEb3SKnVaqhUqnzLb9++DWdn5xIJioiIiIiIzCcnV427ybwZrzGMLqQ6deqEBQsWaB9LJBKkpaVh2rRpCA8PL8nYiIiIiIjIDO4kZUIIwMHOBh6OdkU/gYp3H6nOnTujbt26yMrKwhtvvIHo6GhUrFgRv/76qyliJCIiIiIiE3p6ognNrNxUOKMLKT8/P5w7dw6///47zp07h7S0NAwdOhQDBgzQmXyCiIiIiIhKB20hxWF9BjOqkFIqlQgKCsLff/+NAQMGYMCAAaaKi4iIiIiIzOR2Iu8hZSyjrpGSyWTIysoyVSxERERERGQB2qnP3TnCzFBGTzYxcuRIzJs3D7m5uaaIh4iIiIiIzIxD+4xn9DVSJ06cwK5du7Bjxw4EBwfD0dFRZ/369etLLDgiIiIiIjK9OA7tM5rRhZSbmxt69+5tiliIiIiIiMjMkjOUSM3KG21WpQILKUMZXUgtX77cFHEQEREREZEFaHqjvJzlsLezsXA0pYfB10ip1WrMmzcPLVq0QJMmTfDRRx8hMzPTlLEREREREZGJcVhf8RhcSH366af43//+BycnJ1SuXBkLFy7EyJEjTRkbERERERGZGCeaKB6DC6mVK1fi+++/x/bt27Fx40Zs3rwZq1evhlqtNmV8RERERERkQrces5AqDoMLqbi4OISHh2sfd+jQARKJBHfv3jVJYEREREREZHq3OLSvWAwupHJzc6FQKHSWyWQyKJXKEg+KiIiIiIjMg9dIFY/Bs/YJITBo0CDI5XLtsqysLLz77rs695LifaSIiIiIiEqHXJUadx7nTSDn525v4WhKF4MLqYiIiHzL3nzzzRINhoiIiIiIzOdechZy1QJ2NlJUclYU/QTSMriQ4v2jiIiIiIjKFs1EE1Xc7SGVSiwcTeli8DVSRERERERUtnCiieJjIUVEREREVE5xooniYyFFRERERFROxSX+N9FEBRZSxmIhRURERERUTmmG9vFmvMZjIUVEREREVE7xGqniYyFFRERERFQOpWXn4lF6DgDeQ6o4WEgREREREZVDmt6oCg4yOCtkFo6m9GEhRURERERUDnFY3/NhIUVEREREVA7FcaKJ58JCioiIiIioHGKP1PNhIUVEREREVA6xR+r5sJAiIiIiIiqH4tgj9VxYSBERERERlTNqtcDtx5kAWEgVFwspIiIiIqJy5kFaNrJz1bCRSuDjqrB0OKUSCykiIiIionJGM6yvsps9bG1YEhQHs0ZEREREVM7EPdJMNGFv4UhKLxZSRERERETlzK3HnGjiebGQIiIiIiIqZzj1+fNjIUVEREREVM7wZrzPj4UUEREREVE5o+2RqsBCqrhYSBERERERlSNZShXup2QDYI/U82AhRURERERUjmhuxOsst4Wbg8zC0ZReFi2k9u/fj27dusHX1xcSiQQbN27UWS+EwCeffAIfHx/Y29ujQ4cOiI6O1mmTmJiIAQMGwMXFBW5ubhg6dCjS0tLMuBdERERERKXHracmmpBIJBaOpvSyaCGVnp6OkJAQfPfddwWu//zzz/H1119j8eLFOHbsGBwdHREWFoasrCxtmwEDBuDSpUuIjIzE33//jf3792P48OHm2gUiIiIiolIljhNNlAhbS754ly5d0KVLlwLXCSGwYMECfPzxx+jRowcAYOXKlahUqRI2btyIfv36ISoqCtu2bcOJEyfQuHFjAMA333yD8PBwzJ8/H76+vmbbFyIiIiKi0uDJ1Oe8Ge/zsGghVZiYmBjEx8ejQ4cO2mWurq5o1qwZjhw5gn79+uHIkSNwc3PTFlEA0KFDB0ilUhw7dgy9evUqcNvZ2dnIzs7WPk5JSQEAKJVKKJVKE+0RAdDml3k2D+bb/Jhz82POzYv5Nj/m3PzKes7jHqUDACq7yq1mH60p54bGYLWFVHx8PACgUqVKOssrVaqkXRcfHw8vLy+d9ba2tnB3d9e2KcjcuXMxY8aMfMt37NgBBwd2cZpDZGSkpUMoV5hv82POzY85Ny/m2/yYc/Mrqzm/FGsDQIL465ew9dFFS4ejwxpynpGRYVA7qy2kTGny5MkYN26c9nFKSgr8/PzQqVMnuLi4WDCysk+pVCIyMhIdO3aETMZZYkyN+TY/5tz8mHPzYr7Njzk3v7Kac5Va4MTNRDw6fhqAQI+OrVDDy8nSYQGwrpxrRqsVxWoLKW9vbwDA/fv34ePjo11+//59NGjQQNsmISFB53m5ublITEzUPr8gcrkccrk833KZTGbxN668YK7Ni/k2P+bc/Jhz82K+zY85N7+ylPNtF+9hxubLuJf8ZNK2wT+fwvTu9dC5vk8hzzQva8i5oa9vtfeRCgwMhLe3N3bt2qVdlpKSgmPHjiE0NBQAEBoaiqSkJJw6dUrbZvfu3VCr1WjWrJnZYyYiIiIisjbbLt7De6tO6xRRAHA/JRvvrTqNbRfvWSiy0s2iPVJpaWm4fv269nFMTAzOnj0Ld3d3+Pv7Y+zYsZg9ezZq1qyJwMBATJ06Fb6+vujZsycAoE6dOujcuTOGDRuGxYsXQ6lUYtSoUejXrx9n7CMiIiKick+lFpix+TJEAesEAAmAGZsvo2Ndb9hIeU8pY1i0kDp58iRefvll7WPNdUsRERFYsWIFJk6ciPT0dAwfPhxJSUlo2bIltm3bBoVCoX3O6tWrMWrUKLRv3x5SqRS9e/fG119/bfZ9ISIiIiKyNsdjEvP1RD1NALiXnIXjMYkIre5hvsDKAIsWUm3btoUQBdXHeSQSCWbOnImZM2fqbePu7o41a9aYIjwiIiIiolItIVV/EVWcdvSE1V4jRUREREREz8fLWVF0IyPa0RMspIiIiIiIyqimge7wcVVA39VPEgA+rgo0DXQ3Z1hlAgspIiIiIqIyykYqwbRudQucbEJTXE3rVpcTTRQDCykiIiIiojKstrcLbAr41u/tqsCiN1+0qvtIlSZWe0NeIiIiIiJ6fnO3RkGlBtrUqoh329RAQmoWvJzzhvOxJ6r4WEgREREREZVRh288xI7L92EjlWDqK3VRw8vZ0iGVGRzaR0RERERUBqnUArP+jgIAvNnMn0VUCWMhRURERERUBq07eQtR91LgorDF2A61LB1OmcNCioiIiIiojEnNUmL+jqsAgPc71EIFRzsLR1T2sJAiIiIiIipjvt97Aw/TclCtoiPeeinA0uGUSSykiIiIiIjKkFuJGVh6IAYA8L/wOrCz5Vd+U2BWiYiIiIjKkM/+uYIclRota1RE+zpelg6nzGIhRURERERURhyPScSWC/cglQAfv1IHEgnvE2UqLKSIiIiIiMoAtVpg1t+XAQD9mvojyNvFwhGVbSykiIiIiIjKgPVn7uDCnWQ4y20xriOnOzc1FlJERERERKVcenYu/m/7FQDAqHY1UNFJbuGIyj4WUkREREREpdySfTdwPyUb/u4OGNSiqqXDKRdYSBERERERlWJ3kjKxZP+/AID/hQdBbmtj4YjKBxZSRERERESl2OfbriA7V41mge4Iq+dt6XDKDRZSRERERESl1Om4x/jr7F1IJMDUV+pyunMzYiFFRERERFQKCSEwc3PedOevNaqC+pVdLRxR+cJCioiIiIioFNp07i7O3kqCg50Nxneqbelwyh0WUkREREREpUxmjgrz/smb7nzkyzXg5aKwcETlDwspIiIiIqJS5scD/+JuchYqu9ljaMtAS4dTLrGQIiIiIiIqRe6nZGHR3hsAgI+6BEEh43TnlsBCioiIiIioFPl821VkKlVoFFABr7zgY+lwyi0WUkREREREpcT520n48/RtAMAnnO7colhIERERERGVAkIIzPo7b7rzVxtWRoifm2UDKudYSBERERERlQJbL8TjxM3HUMikmNCZ051bGgspIiIiIiIrl6VUYe4/UQCAd9tUh4+rvYUjIhZSRERERERWbtmhGNx+nAlvFwWGt65m6XAILKSIiIiIiKxaQmoWvt+TN935pC614WBna+GICGAhRURERERk1b7ccQ1p2bkI8XNDj5DKlg6H/sNCioiIiIjISl26m4zfT94CAHzySh1IpZzu3FqwkCIiIiIiskKa6c6FALqF+KJRgLulQ6KnsJAiIiIiIrJCOy7fx9F/EyG3lWISpzu3OiykiIiIiIisTHauCnO25k13PqxVNVSp4GDhiOhZLKSIiIiIiKzMysOxiH2UAU9nOd5rW93S4VABWEgREREREVmRR2nZ+Hp3NABgQlhtOMo53bk1YiFFRERERGRFvtp5DalZuajn64I+L1axdDikBwspIiIiIiIrcTU+FWuOxQEApr5Sl9OdWzEWUkREREREVkAIgdlbLkMtgC71vfFSNQ9Lh0SFYCFFRERERGQF9l59gAPRD2FnI8XkLnUsHQ4VgYUUEREREZGFKVVqzNpyGQAwuGVV+HtwunNrx0KKiIiIiMjCVh2Nxb8P0uHhaIdRL9ewdDhkABZSREREREQWlJSRgwU786Y7/7BTbTgrZBaOiAzBQoqIiIiIyIIW7IxGcqYSQd7O6NvEz9LhkIFYSBERERERWcj1hDSsOhoLIG+6cxtOd15qsJAiIiIiIrKQOVujkKsW6FDHCy1qVLR0OGQEFlJERERERBaw/9oD7L6SAFupBP8L53TnpQ0LKSIiIiIiM8tVqTH7v+nOI5pXRTVPJwtHRMZiIUVEREREZGa/nbiFa/fTUMFBhjHtalo6HCoGFlJERERERGaUnKnEl5HXAAAfdKwFVwdOd14a2Vo6AHpCpRY4HpOIhNQseDkr0DTQ3eIztzCm0h3TsZhEnHoogUdMIkJreFlFTNaYJ2uLyVrjssaYiIhKo293RyMxPQc1vJzwRlN/S4dDxcRCykpsu3gPMzZfxr3kLO0yH1cFpnWri871fRgTY3qOmGywMvqklcWUhzGVnrisMSaAfzBgTGU/Jip7bj5Mx4rDNwEAH3etA1sbDhArrVhIWYFtF+/hvVWnIZ5ZHp+chfdWncaiN180+xcVxsSYGJP5Y7LWuKwxJk1c/IMBYyrLMVHZNGdrFJQqgTa1PNG2tpelw6HnYNUlsEqlwtSpUxEYGAh7e3tUr14ds2bNghBP/jkXQuCTTz6Bj48P7O3t0aFDB0RHR1swauOo1AIzNl/O9wUFgHbZjM2XoVIX1IIxMSbGVFZiAqwzLmuMCXhS3D39pRd4Utxtu3jPrPEwJsZkKk/3uh6LSTT7Z41K1uEbD7Hj8n3YSCX4uCunOy/trLpHat68eVi0aBF+/vln1KtXDydPnsTgwYPh6uqKMWPGAAA+//xzfP311/j5558RGBiIqVOnIiwsDJcvX4ZCobDwHhTteExivhP30wSAe8lZeG/VKXi7mmd/4pOzTBaTWq1G7E0pTvwdBanU8DrelDEVF2Mq2ZhGWGNMq0/Bx9XeqG2r/jvGT225YtQxDgD3kjMNimvkGt24JDBs6JHEgGbPNrmbZFhM7/92Br5u+XNV4EsWsFDfPhQUsxACvxyNLbS4G7/uPM7fTtYZlqWzKUn+5U+/1tPx6C4vODYBYMm+fwuNacIf5xHzMB02Uol2+zrblkh0YpH8t+zpx5oHuu0k2u1IntqmEMDcf64UGtNH6y8gJ1cNWxup9vUkEkD632tIpU/ikv63Tq1S4Vpy3lBKW1tbSCUSSCX/xfJMW83/JZBAKgXUauDjjRcLjWnapktoVs0DclspbKQS2EgkeTkz5AAuhqL+WCBB3h8LOtb1NvswP2vsdaXiU6kFZv0dBQAY0MwfNSs5Wzgiel4S8XT3jpV55ZVXUKlSJSxdulS7rHfv3rC3t8eqVasghICvry8+/PBDjB8/HgCQnJyMSpUqYcWKFejXr1+B283OzkZ2drb2cUpKCvz8/PDw4UO4uLiYdqeesfn8PYxbd8Gsr0lERFTa2EjzCirbZ/7/dLGls85G87sUUgn+WyfVeZ6tVILHGTk4GvO4yNd/t3VV1Pd1hb2dDRQyKRxktlDIpLC3s4G9LO9HIZOWWMG3/dJ9jP7tXL4CT7P1b/qFIKxepRJ5LcpPqVQiMjISHTt2hExWMjPqrTt1G//beBkuCltEjm0Jd0e7EtluWWGKnBdXSkoKKlasiOTk5EJrA6vukWrevDl++OEHXLt2DbVq1cK5c+dw8OBBfPnllwCAmJgYxMfHo0OHDtrnuLq6olmzZjhy5IjeQmru3LmYMWNGvuU7duyAg4ODaXZGj3+TJQBsimzXpKIa7mbqYEvMAk48LPov6YyplMckN0NAABKzS29MjUs4pqL+apWYDZwyIK4X9cVVjD+LFfWUx9nA6UdFx9TQQ40Kz8ZUwMYL64kwhACQkAlEJRUdU5CrGl72BbyGyL9MXwwFPa+g9g+zgOiUomOq5qyGh/zJNnRi0LN98dQCY56TlA3cySg6pkr2Ak62T7YtxJNtqZ9+XfHM/5+KQf1fo2e3ofkdyGujVAHZ6uIVGiq1gEotkFOsZz+/xftvGtTOTiogkwJ2UsDO5r//SwE7m7zlcikg07f8v+fYSoDV16X/5Vg3X+K//368/iyUN1WwxFwYagHcSJEgRQm4yIDqLsIicZhDZGRkiWwnSwXMPWMDQIL23tk4um9niWy3LCqpnD+PjIwMg9pZdSH10UcfISUlBUFBQbCxsYFKpcKnn36KAQMGAADi4+MBAJUq6f5FplKlStp1BZk8eTLGjRunfazpkerUqZPZe6RUaoE/vtiP+ynZBf5DLgHg7SrHL6Nbm21IgUot0NZEMRX3rw2mjKm4GFPZj2mVGY9xY+JaY4W5+nWM+WI6FpOIN5edLLLdx72bolmguxkiMjymma9ZX0xf9G9iVEzPc4wbGtOyiBfRyN/tv+Ipb8hs7n+F1NP/Vz/1+Nl1KrUaKgGoVAK5anW+NiqR9/8bD9Kx6titImOq7+sCua0UmUoVspQqZOSokKVUI1OpQnauWtsuRy1BjhpIz7eFkvx8SJCUA6xL8EKtSk7wcLSD+38/T36XwUluW+JDIrdfuo+5W68gPuXJyB5vFzk+Dg8qUz1kJdE7olILnIx9jITUbBy8+gCpynhU9XDA7IjmsLO16mkKLMLaeqQMYdWF1Nq1a7F69WqsWbMG9erVw9mzZzF27Fj4+voiIiKi2NuVy+WQy/P/OVcmk5n9jZMBmN69Ht5bdRoS6P5FUXPqm9atHhRy83X/miMmY3NdXvPEmEpvTMU5n5TXXBkrtIYXfFwViE/OKqS4U5h1KvTyGFNxjnFDY2pT23zXI6nUAruuPCgypr9GtdQbk0otkKVUIVOpQmbOk//nFVt5jzP+W56V89TvShUycnKRqVT/97xcZOaoEJ+SjbtJmUXGfvjfRBz+N1Hvejsb6ZMCy0lTZMmf+l2zXA53Jzs4F1F4bbt4r8DhhvdTsjH6t3MWm8HTlIr73bCgWSABoEt9Hzjam2n4RSllie/jBcVgCKsupCZMmICPPvpIO0QvODgYsbGxmDt3LiIiIuDt7Q0AuH//Pnx8nnxw79+/jwYNGlgi5GLpXN8Hi958Md8HztuCF5QyJsbEmCzzZcAa47K2mGykEkzrVreI4q6uWScGYEzlOyYbqQSOcls4ykvma9WRG4/Q/8ejRbZ7s5k/HBW2SEzLQWJ6Dh6m5yAxPRuJaTlIz1EhR6VGfEoW4lP0TxjzNDsbKSo4yuDxX7GV18OV97ubgwzzt1+1ykk5rI2+W0YAwOJ9NxDi51rmCs7yyqoLqYyMjHyzXtnY2ECtzutCDwwMhLe3N3bt2qUtnFJSUnDs2DG899575g73uXSu74OOdb2t6kaAjKn0x3TkegJ2HDiGTq2aWfxGpdacJ2uKyVrjsraYrK24Y0yMqSQ1DXQ3qOduRo/6ej+DWUoVHqXnIDEtBw//K67yiq3sQguv+ynZuP/UsD1DaWbw/HTLZbSoURE+rvbwdVPA1V5mshkXn2YtN1NOzVJi6sZLhV77yYKz7LDqQqpbt2749NNP4e/vj3r16uHMmTP48ssvMWTIEAB506yOHTsWs2fPRs2aNbXTn/v6+qJnz56WDb4YbKQShFb3sHQYOhiTYaw1pmaB7ngUJdDMCooDTUzWmCdriwmwzrisLSb+wYAxldWYSqKXTCGzQWU3e1Qu4LYEBSmq8Lp8LwWX7hZ93ciyQzex7NBN7WN7mQ18XBXwcVPkFVeuCvi42cPbVQFfV3v4uCngoni+YVzmuJlyRk4uElKycT8lCwmpef9/8N//76dkIyE1Cwkp2UjNzi10O5qC83hMolWdT6l4rLqQ+uabbzB16lSMGDECCQkJ8PX1xTvvvINPPvlE22bixIlIT0/H8OHDkZSUhJYtW2Lbtm2l4h5SRET0fPgHA8MwJsNYU0zm7iUrqvAydLjhi/4VkJ2rQnxyFh6l5yBTqcK/D9Px78P8029oOMlt/yu27OHjkld0aYosTc+Wg13BX1n1DaPT3Ey5qOu2MnJy8wqhlCzcT837f0JqNu4lZeDKTSkWRh/Eg9ScIgskYyWkGjbckqybVRdSzs7OWLBgARYsWKC3jUQiwcyZMzFz5kzzBUZERERkYtbU62rocMN174Zq48tS5hVUd5MzcS8pS3vT8XvJWdqbfSdnKpGWnYvohDREJ6TpfX0XhS183ey1BZevqwJeLgp8VsRNp6dsuIgspRoP07K1PUmaXqWElGykFVogSQE8mQbbXmaDSi5yeLkoUMlFAS9ned5jZwW8/vt/3KN0DPm56JkpvZz5B/+ywKoLKSIiIqLyzFp6XYsz3FAhs0HVio6oWtFR73YzcnLziqukggquvMep2blIycpFSnwqrsSnGhX3o/QcjP39bKFtHOxstIWRl4sClZzl8HCU4e6NKHRq1Qy+7o7wcpYbNJ18YEVHgwrOpma6DQKZFgspIiIiIiqSKYYbOtjZorqnE6p7Oultk5ql1PZi5fVwZeFeUibO307G1ftFF1bVPR1Rz9f1vx6kJ71Hmt4lpwJmW1QqldiachkvVXM3aipua5yZkkyHhRQRERERGcQSk3I4K2RwVshQq5KzznJDr9ua3TPYrNe+WdsskGQ6LKSIiIiIyGDWMimHoddtWWIYnTXNAkmmw0KKiIiIiEodax9GZy0FJ5mOtOgmRERERETWRzOMzttVdxY8b1dFkVOfEz0v9kgRERERUanFYXRkKSykiIiIiKhU4zA6sgQO7SMiIiIiIjISCykiIiIiIiIjsZAiIiIiIiIyEgspIiIiIiIiI7GQIiIiIiIiMhILKSIiIiIiIiOxkCIiIiIiIjISCykiIiIiIiIjsZAiIiIiIiIyEgspIiIiIiIiI9laOgBrIIQAAKSkpFg4krJPqVQiIyMDKSkpkMlklg6nzGO+zY85Nz/m3LyYb/Njzs2POTc/a8q5pibQ1Aj6sJACkJqaCgDw8/OzcCRERERERGQNUlNT4erqqne9RBRVapUDarUad+/ehbOzMyQSiaXDKdNSUlLg5+eHW7duwcXFxdLhlHnMt/kx5+bHnJsX821+zLn5MefmZ005F0IgNTUVvr6+kEr1XwnFHikAUqkUVapUsXQY5YqLi4vFPyTlCfNtfsy5+THn5sV8mx9zbn7MuflZS84L64nS4GQTRERERERERmIhRUREREREZCQWUmRWcrkc06ZNg1wut3Qo5QLzbX7Mufkx5+bFfJsfc25+zLn5lcacc7IJIiIiIiIiI7FHioiIiIiIyEgspIiIiIiIiIzEQoqIiIiIiMhILKSIiIiIiIiMxEKKSszcuXPRpEkTODs7w8vLCz179sTVq1cLfc6KFSsgkUh0fhQKhZkiLt2mT5+eL3dBQUGFPmfdunUICgqCQqFAcHAwtm7daqZoy4aqVavmy7lEIsHIkSMLbM/j23j79+9Ht27d4OvrC4lEgo0bN+qsF0Lgk08+gY+PD+zt7dGhQwdER0cXud3vvvsOVatWhUKhQLNmzXD8+HET7UHpU1jOlUolJk2ahODgYDg6OsLX1xcDBw7E3bt3C91mcc5P5UVRx/igQYPy5a5z585FbpfHuH5F5byg87pEIsH//d//6d0mj3H9DPk+mJWVhZEjR8LDwwNOTk7o3bs37t+/X+h2i3v+NyUWUlRi9u3bh5EjR+Lo0aOIjIyEUqlEp06dkJ6eXujzXFxccO/ePe1PbGysmSIu/erVq6eTu4MHD+pte/jwYfTv3x9Dhw7FmTNn0LNnT/Ts2RMXL140Y8Sl24kTJ3TyHRkZCQB47bXX9D6Hx7dx0tPTERISgu+++67A9Z9//jm+/vprLF68GMeOHYOjoyPCwsKQlZWld5u///47xo0bh2nTpuH06dMICQlBWFgYEhISTLUbpUphOc/IyMDp06cxdepUnD59GuvXr8fVq1fRvXv3IrdrzPmpPCnqGAeAzp076+Tu119/LXSbPMYLV1TOn871vXv3sGzZMkgkEvTu3bvQ7fIYL5gh3wc/+OADbN68GevWrcO+fftw9+5dvPrqq4Vutzjnf5MTRCaSkJAgAIh9+/bpbbN8+XLh6upqvqDKkGnTpomQkBCD27/++uuia9euOsuaNWsm3nnnnRKOrPx4//33RfXq1YVarS5wPY/v5wNAbNiwQftYrVYLb29v8X//93/aZUlJSUIul4tff/1V73aaNm0qRo4cqX2sUqmEr6+vmDt3rkniLs2ezXlBjh8/LgCI2NhYvW2MPT+VVwXlOyIiQvTo0cOo7fAYN5whx3iPHj1Eu3btCm3DY9xwz34fTEpKEjKZTKxbt07bJioqSgAQR44cKXAbxT3/mxp7pMhkkpOTAQDu7u6FtktLS0NAQAD8/PzQo0cPXLp0yRzhlQnR0dHw9fVFtWrVMGDAAMTFxelte+TIEXTo0EFnWVhYGI4cOWLqMMuknJwcrFq1CkOGDIFEItHbjsd3yYmJiUF8fLzOcezq6opmzZrpPY5zcnJw6tQpnedIpVJ06NCBx34xJScnQyKRwM3NrdB2xpyfSNfevXvh5eWF2rVr47333sOjR4/0tuUxXrLu37+PLVu2YOjQoUW25TFumGe/D546dQpKpVLnmA0KCoK/v7/eY7Y4539zYCFFJqFWqzF27Fi0aNEC9evX19uudu3aWLZsGf766y+sWrUKarUazZs3x+3bt80YbenUrFkzrFixAtu2bcOiRYsQExODVq1aITU1tcD28fHxqFSpks6ySpUqIT4+3hzhljkbN25EUlISBg0apLcNj++SpTlWjTmOHz58CJVKxWO/hGRlZWHSpEno378/XFxc9LYz9vxET3Tu3BkrV67Erl27MG/ePOzbtw9dunSBSqUqsD2P8ZL1888/w9nZuchhZjzGDVPQ98H4+HjY2dnl+2NMYcdscc7/5mBrsVemMm3kyJG4ePFikeOFQ0NDERoaqn3cvHlz1KlTB0uWLMGsWbNMHWap1qVLF+3vL7zwApo1a4aAgACsXbvWoL+k0fNZunQpunTpAl9fX71teHxTWaJUKvH6669DCIFFixYV2pbnp+Lr16+f9vfg4GC88MILqF69Ovbu3Yv27dtbMLLyYdmyZRgwYECREwPxGDeMod8HSyv2SFGJGzVqFP7++2/s2bMHVapUMeq5MpkMDRs2xPXr100UXdnl5uaGWrVq6c2dt7d3vhlx7t+/D29vb3OEV6bExsZi586dePvtt416Ho/v56M5Vo05jitWrAgbGxse+89JU0TFxsYiMjKy0N6oghR1fiL9qlWrhooVK+rNHY/xknPgwAFcvXrV6HM7wGO8IPq+D3p7eyMnJwdJSUk67Qs7Zotz/jcHFlJUYoQQGDVqFDZs2IDdu3cjMDDQ6G2oVCpcuHABPj4+JoiwbEtLS8ONGzf05i40NBS7du3SWRYZGanTY0KGWb58Oby8vNC1a1ejnsfj+/kEBgbC29tb5zhOSUnBsWPH9B7HdnZ2aNSokc5z1Go1du3axWPfQJoiKjo6Gjt37oSHh4fR2yjq/ET63b59G48ePdKbOx7jJWfp0qVo1KgRQkJCjH4uj/Enivo+2KhRI8hkMp1j9urVq4iLi9N7zBbn/G8WFpvmgsqc9957T7i6uoq9e/eKe/fuaX8yMjK0bd566y3x0UcfaR/PmDFDbN++Xdy4cUOcOnVK9OvXTygUCnHp0iVL7EKp8uGHH4q9e/eKmJgYcejQIdGhQwdRsWJFkZCQIITIn+tDhw4JW1tbMX/+fBEVFSWmTZsmZDKZuHDhgqV2oVRSqVTC399fTJo0Kd86Ht/PLzU1VZw5c0acOXNGABBffvmlOHPmjHaGuM8++0y4ubmJv/76S5w/f1706NFDBAYGiszMTO022rVrJ7755hvt499++03I5XKxYsUKcfnyZTF8+HDh5uYm4uPjzb5/1qiwnOfk5Iju3buLKlWqiLNnz+qc27Ozs7XbeDbnRZ2fyrPC8p2amirGjx8vjhw5ImJiYsTOnTvFiy++KGrWrCmysrK02+AxbpyizitCCJGcnCwcHBzEokWLCtwGj3HDGfJ98N133xX+/v5i9+7d4uTJkyI0NFSEhobqbKd27dpi/fr12seGnP/NjYUUlRgABf4sX75c26ZNmzYiIiJC+3js2LHC399f2NnZiUqVKonw8HBx+vRp8wdfCvXt21f4+PgIOzs7UblyZdG3b19x/fp17fpncy2EEGvXrhW1atUSdnZ2ol69emLLli1mjrr02759uwAgrl69mm8dj+/nt2fPngLPI5q8qtVqMXXqVFGpUiUhl8tF+/bt870XAQEBYtq0aTrLvvnmG+170bRpU3H06FEz7ZH1KyznMTExes/te/bs0W7j2ZwXdX4qzwrLd0ZGhujUqZPw9PQUMplMBAQEiGHDhuUriHiMG6eo84oQQixZskTY29uLpKSkArfBY9xwhnwfzMzMFCNGjBAVKlQQDg4OolevXuLevXv5tvP0cww5/5ubRAghTNPXRUREREREVDbxGikiIiIiIiIjsZAiIiIiIiIyEgspIiIiIiIiI7GQIiIiIiIiMhILKSIiIiIiIiOxkCIiIiIiIjISCykiIiIiIiIjsZAiIiIiIiIyEgspIiIiM9u7dy8kEgmSkpIs8vpVq1bFggULLPLaRERlBQspIiIq0q1btzBkyBD4+vrCzs4OAQEBeP/99/Ho0SNLh6bX9evXMXjwYFSpUgVyuRyBgYHo378/Tp48aenQioXFDxGRdWEhRUREhfr333/RuHFjREdH49dff8X169exePFi7Nq1C6GhoUhMTDTp6yuVSqOfc/LkSTRq1AjXrl3DkiVLcPnyZWzYsAFBQUH48MMPTRAlERGVNyykiIioUCNHjoSdnR127NiBNm3awN/fH126dMHOnTtx584dTJkyBQDwv//9D82aNcv3/JCQEMycOVP7+KeffkKdOnWgUCgQFBSE77//Xrvu5s2bkEgk+P3339GmTRsoFAqsXr0asbGx6NatGypUqABHR0fUq1cPW7duLTBeIQQGDRqEmjVr4sCBA+jatSuqV6+OBg0aYNq0afjrr7+0bS9cuIB27drB3t4eHh4eGD58ONLS0rTrBw0ahJ49e2LOnDmoVKkS3NzcMHPmTOTm5mLChAlwd3dHlSpVsHz58nz78Ntvv6F58+ZQKBSoX78+9u3bV2ieDx48iFatWsHe3h5+fn4YM2YM0tPTAQBt27ZFbGwsPvjgA0gkEkgkEoOeBwAJCQno1q0b7O3tERgYiNWrVxcaBxERGUgQERHp8ejRIyGRSMScOXMKXD9s2DBRoUIFoVarxcWLFwUAcf36de16zbLo6GghhBCrVq0SPj4+4s8//xT//vuv+PPPP4W7u7tYsWKFEEKImJgYAUBUrVpV2+bu3buia9euomPHjuL8+fPixo0bYvPmzWLfvn0FxnT69GkBQKxZs6bQfUtLSxM+Pj7i1VdfFRcuXBC7du0SgYGBIiIiQtsmIiJCODs7i5EjR4orV66IpUuXCgAiLCxMfPrpp+LatWti1qxZQiaTiVu3bunsQ5UqVcQff/whLl++LN5++23h7OwsHj58KIQQYs+ePQKAePz4sRBCiOvXrwtHR0fx1VdfiWvXrolDhw6Jhg0bikGDBmnfhypVqoiZM2eKe/fuiXv37hn0PCGE6NKliwgJCRFHjhwRJ0+eFM2bNxf29vbiq6++KjQ/RERUOBZSRESk19GjRwUAsWHDhgLXf/nllwKAuH//vhBCiJCQEDFz5kzt+smTJ4tmzZppH1evXj1fgTNr1iwRGhoqhHhShCxYsECnTXBwsJg+fbpBMf/+++8CgDh9+nSh7X744QdRoUIFkZaWpl22ZcsWIZVKRXx8vBAir5AKCAgQKpVK26Z27dqiVatW2se5ubnC0dFR/Prrrzr78Nlnn2nbKJVKUaVKFTFv3jwhRP5CaujQoWL48OE68R04cEBIpVKRmZkphBAiICAgX/FT1POuXr0qAIjjx49r10dFRQkALKSIiJ4Th/YREVGRhBAGtRswYADWrFmjfc6vv/6KAQMGAADS09Nx48YNDB06FE5OTtqf2bNn48aNGzrbady4sc7jMWPGYPbs2WjRogWmTZuG8+fPP3esUVFRCAkJgaOjo3ZZixYtoFarcfXqVe2yevXqQSp98s9lpUqVEBwcrH1sY2MDDw8PJCQk6Gw/NDRU+7utrS0aN26MqKioAmM5d+4cVqxYoZOXsLAwqNVqxMTE6N2Hop4XFRUFW1tbNGrUSPucoKAguLm5FZ0gIiIqlK2lAyAiIutVo0YNSCQSREVFoVevXvnWR0VFoUKFCvD09AQA9O/fH5MmTcLp06eRmZmJW7duoW/fvgCgvfboxx9/zHctlY2Njc7jp4sbAHj77bcRFhaGLVu2YMeOHZg7dy6++OILjB49Ol9MtWrVAgBcuXIFDRs2LOaePyGTyXQeSySSApep1epiv0ZaWhreeecdjBkzJt86f3//Yj/v2rVrxY6JiIgKxx4pIiLSy8PDA//f3r2Ewt7HcRz/OIsJS4kalGEYo1yLnSZpYoUkFpKSW80oZWGnqMlsWGjYUGMzpRSxkFlN5FrjfsmlUFIWLjtSdJ7FydScx4M5p6dTz/N+1dTU//trfv/f7tP3N7+f3W7X6Oionp6ewp7d3NzI5/Opvr4+dPhBcnKybDabfD6ffD6f7Ha7EhISJP3o5BiNRp2fn8tsNod9TCbTp3NJSUlRR0eHpqen1d3drbGxsXfr8vPzlZ2drcHBwXfDzdvdTVarVbu7u2EHM6ysrOjbt2+yWCxfWp+PrK+vh76/vLxoc3NTVqv13drCwkIdHR39bV3MZrMMBoMkyWAw6PX1NaJxWVlZod9+c3Jy8sfurwKA/xKCFADgQx6PR8/PzyovL9fS0pKurq60sLAgu92upKQkuVyusPqGhgZNTk5qamoqtK3vTV9fnwYGBjQ8PKzT01Pt7+/L6/VqaGjowzl0dXXJ7/fr4uJCW1tbCgQC/xhKoqKi5PV6dXp6qpKSEs3Pz+v8/Fx7e3tyuVyqqqoKzTM6OlpNTU06ODhQIBBQZ2enGhsblZiY+Bsr9sPIyIhmZmZ0fHwsh8Ohh4cHNTc3v1vb09Oj1dVVOZ1O7ezs6OzsTLOzs3I6naGa1NRULS0t6fr6Wre3t18aZ7FYVFFRofb2dm1sbGhzc1MtLS2KiYn57fcDgP87ghQA4EMZGRkKBoNKS0tTXV2d0tPT1dbWptLSUq2trSkuLi6svra2Vnd3d3p8fFR1dXXYs5aWFo2Pj8vr9SonJ0c2m00TExOfdqReX1/lcDhktVpVUVGhzMzMsGPTf1ZcXKxgMCiz2azW1lZZrVZVVlbq8PAwdKltbGys/H6/7u/vVVRUpNraWpWVlcnj8fzSOv3M7XbL7XYrLy9Py8vLmpubU3x8/Lu1ubm5WlxcDIW/goIC9fb2ymg0hmr6+/t1eXmp9PT00FbKr4zzer0yGo2y2WyqqalRW1tbqEsIAPh1Ud+/+q9cAADwqcvLS5lMJm1vbys/P/9PTwcA8C+hIwUAAAAAESJIAQAAAECE2NoHAAAAABGiIwUAAAAAESJIAQAAAECECFIAAAAAECGCFAAAAABEiCAFAAAAABEiSAEAAABAhAhSAAAAABAhghQAAAAAROgvMSvokTSPLooAAAAASUVORK5CYII=\n"},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["(np.float32(182.64113), np.int64(143))"]},"metadata":{},"execution_count":14}]},{"cell_type":"code","source":["print(\"⚠️ No high-scoring matches found. Trying threshold > 150...\")\n","high_score_ids = first_innings_scores[first_innings_scores > 150].index\n","chosen_matches = list(set(valid_match_ids) & set(high_score_ids))\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"3_6Hko0eJJyp","executionInfo":{"status":"ok","timestamp":1744094667975,"user_tz":-330,"elapsed":76,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"5b919208-85ad-418c-f8f4-64264e761b39"},"execution_count":18,"outputs":[{"output_type":"stream","name":"stdout","text":["⚠️ No high-scoring matches found. Trying threshold > 150...\n"]}]},{"cell_type":"code","source":["import os\n","import openai\n","\n","# Store your encrypted API key securely as an environment variable\n","os.environ[\"OPENAI_API_KEY\"] = \"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\"\n","\n","# Assign it to openai\n","openai.api_key = os.getenv(\"OPENAI_API_KEY\")\n"],"metadata":{"id":"jhAVxD77G30O","executionInfo":{"status":"ok","timestamp":1744096273529,"user_tz":-330,"elapsed":2283,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}}},"execution_count":19,"outputs":[]},{"cell_type":"code","source":["!pip install --upgrade openai"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"U9kfBj9-G3kH","executionInfo":{"status":"ok","timestamp":1744096434226,"user_tz":-330,"elapsed":5633,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"1c3c648e-c60f-48f9-bfbd-f95f259c3ec9"},"execution_count":22,"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: openai in /usr/local/lib/python3.11/dist-packages (1.70.0)\n","Collecting openai\n","  Downloading openai-1.71.0-py3-none-any.whl.metadata (25 kB)\n","Requirement already satisfied: anyio<5,>=3.5.0 in /usr/local/lib/python3.11/dist-packages (from openai) (4.9.0)\n","Requirement already satisfied: distro<2,>=1.7.0 in /usr/local/lib/python3.11/dist-packages (from openai) (1.9.0)\n","Requirement already satisfied: httpx<1,>=0.23.0 in /usr/local/lib/python3.11/dist-packages (from openai) (0.28.1)\n","Requirement already satisfied: jiter<1,>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from openai) (0.9.0)\n","Requirement already satisfied: pydantic<3,>=1.9.0 in /usr/local/lib/python3.11/dist-packages (from openai) (2.11.2)\n","Requirement already satisfied: sniffio in /usr/local/lib/python3.11/dist-packages (from openai) (1.3.1)\n","Requirement already satisfied: tqdm>4 in /usr/local/lib/python3.11/dist-packages (from openai) (4.67.1)\n","Requirement already satisfied: typing-extensions<5,>=4.11 in /usr/local/lib/python3.11/dist-packages (from openai) (4.13.1)\n","Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.11/dist-packages (from anyio<5,>=3.5.0->openai) (3.10)\n","Requirement already satisfied: certifi in /usr/local/lib/python3.11/dist-packages (from httpx<1,>=0.23.0->openai) (2025.1.31)\n","Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.11/dist-packages (from httpx<1,>=0.23.0->openai) (1.0.7)\n","Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.11/dist-packages (from httpcore==1.*->httpx<1,>=0.23.0->openai) (0.14.0)\n","Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pydantic<3,>=1.9.0->openai) (0.7.0)\n","Requirement already satisfied: pydantic-core==2.33.1 in /usr/local/lib/python3.11/dist-packages (from pydantic<3,>=1.9.0->openai) (2.33.1)\n","Requirement already satisfied: typing-inspection>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from pydantic<3,>=1.9.0->openai) (0.4.0)\n","Downloading openai-1.71.0-py3-none-any.whl (598 kB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m599.0/599.0 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hInstalling collected packages: openai\n","  Attempting uninstall: openai\n","    Found existing installation: openai 1.70.0\n","    Uninstalling openai-1.70.0:\n","      Successfully uninstalled openai-1.70.0\n","Successfully installed openai-1.71.0\n"]}]},{"cell_type":"code","source":["\n","\n","import pandas as pd\n","import numpy as np\n","import matplotlib.pyplot as plt\n","from sklearn.preprocessing import MinMaxScaler\n","from tensorflow.keras.models import load_model\n","import openai, os, time\n","from openai import OpenAI\n","\n","# ✅ 1. Load your OpenAI Key securely\n","os.environ[\"OPENAI_API_KEY\"] = \"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\"\n","client = OpenAI(api_key=os.getenv(\"OPENAI_API_KEY\"))\n","\n","# ✅ 2. Load the deliveries data\n","deliveries_path = '/content/drive/MyDrive/Colab Notebooks/IPLPrediction/deliveries.csv'\n","deliveries_df = pd.read_csv(deliveries_path)\n","\n","# ✅ 3. Build over_sequence dataframe\n","over_stats = deliveries_df.groupby(['match_id', 'inning', 'over']).agg(\n","    total_runs=('total_runs', 'sum'),\n","    wickets=('player_dismissed', lambda x: x.notna().sum())\n",").reset_index()\n","\n","final_scores = over_stats.groupby(['match_id', 'inning'])['total_runs'].sum().reset_index()\n","final_scores.rename(columns={'total_runs': 'final_score'}, inplace=True)\n","\n","over_sequence = pd.merge(over_stats, final_scores, on=['match_id', 'inning'])\n","over_sequence['cumulative_runs'] = over_sequence.groupby(['match_id', 'inning'])['total_runs'].cumsum()\n","\n","# ✅ 4. Pick a match with 2 innings & 1st innings > 150\n","match_ids = over_sequence.groupby('match_id')['inning'].nunique()\n","valid_match_ids = match_ids[match_ids == 2].index\n","\n","first_innings_scores = over_sequence[over_sequence['inning'] == 1].groupby('match_id')['final_score'].first()\n","high_score_ids = first_innings_scores[first_innings_scores > 150].index\n","\n","chosen_matches = list(set(valid_match_ids) & set(high_score_ids))\n","if not chosen_matches:\n","    raise ValueError(\"❌ No match found with both innings and 1st innings > 150.\")\n","match_id = chosen_matches[0]\n","\n","# ✅ 5. Extract match data\n","match_data = over_sequence[over_sequence['match_id'] == match_id]\n","inning1 = match_data[match_data['inning'] == 1].sort_values('over')\n","inning2 = match_data[match_data['inning'] == 2].sort_values('over')\n","\n","target_score = inning1['final_score'].iloc[0]\n","cumulative_runs_in2 = inning2['cumulative_runs'].values.reshape(-1, 1)\n","\n","# ✅ 6. Prepare scaling and load GRU model\n","scaler_input = MinMaxScaler().fit(over_sequence['cumulative_runs'].values.reshape(-1, 1))\n","scaler_output = MinMaxScaler().fit(over_sequence['final_score'].values.reshape(-1, 1))\n","\n","gru_model_path = '/content/drive/MyDrive/Colab Notebooks/IPLPrediction/gru_score_predictor.h5'\n","gru_model = load_model(gru_model_path, compile=False)\n","gru_model.compile(optimizer='adam', loss='mse')\n","\n","# ✅ 7. Predict over-by-over + win probability (REVISED)\n","over_preds, win_probs = [], []\n","for i in range(1, 21):\n","    current_seq = cumulative_runs_in2[:i]\n","    padded_seq = np.pad(current_seq, ((0, 20 - i), (0, 0)), mode='constant')\n","    padded_scaled = scaler_input.transform(padded_seq)\n","    model_input = padded_scaled.reshape(1, 20, 1)\n","\n","    pred_scaled = gru_model.predict(model_input, verbose=0)\n","    pred_final = scaler_output.inverse_transform(pred_scaled)[0][0]\n","\n","    # 🔒 Sanitize prediction\n","    actual_so_far = cumulative_runs_in2[i - 1][0]\n","    pred_final = round(max(pred_final, actual_so_far, 0))   # Never predict below current score\n","    pred_final = min(pred_final, 260)  # Optional cap\n","\n","    # ✅ Calculate win probability\n","    win_prob = 1 / (1 + np.exp(-(pred_final - target_score) / 10))\n","    win_prob = round(np.clip(win_prob * 100, 0, 100))\n","\n","    over_preds.append(pred_final)\n","    win_probs.append(win_prob)\n","\n","# ✅ 8. Generate GPT-3.5 Commentary per Over\n","for i in range(1, 21):\n","    runs = int(cumulative_runs_in2[i-1][0])\n","    pred_score = over_preds[i-1]\n","    win_prob = win_probs[i-1]\n","\n","    print(f\"\\n📊 [DEBUG] Over {i}: Runs = {runs}, Predicted = {pred_score}, WinProb = {win_prob}%\")\n","\n","    prompt = f\"\"\"\n","    You're a cricket commentator. Generate IPL-style cricket commentary.\n","\n","    Overs completed: {i}\n","    Runs: {runs}\n","    Predicted final score: {pred_score}\n","    Win probability: {win_prob}%\n","\n","    Describe the match in a fun, sharp, energetic tone. Say if the team is on track, dominant, or under pressure.\n","    \"\"\"\n","\n","    try:\n","        response = client.chat.completions.create(\n","            model=\"gpt-3.5-turbo\",\n","            messages=[{\"role\": \"user\", \"content\": prompt}],\n","            temperature=0.8,\n","            max_tokens=100\n","        )\n","        commentary = response.choices[0].message.content\n","        print(f\"🟡 Over {i} Commentary:\\n{commentary}\")\n","        time.sleep(1.2)\n","\n","    except Exception as e:\n","        print(f\"❌ Error generating commentary for Over {i}: {e}\")\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"rhLPuuf6P-uP","executionInfo":{"status":"ok","timestamp":1744097507933,"user_tz":-330,"elapsed":60239,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"3364cabd-f955-4e8d-ad22-bf29876e9594"},"execution_count":29,"outputs":[{"output_type":"stream","name":"stdout","text":["\n","📊 [DEBUG] Over 1: Runs = 1, Predicted = 2, WinProb = 0%\n","🟡 Over 1 Commentary:\n","And we are off to a fiery start in this IPL-style match! After 1 over, the team has managed to score just 1 run. It's a slow start, but they are showing some promising signs. \n","\n","At this rate, the predicted final score is just 2 runs, but we all know there's plenty of cricket left to play! The win probability may be at 0% right now, but anything can happen in this unpredictable game.\n","\n","The team is definitely feeling the pressure\n","\n","📊 [DEBUG] Over 2: Runs = 6, Predicted = 6, WinProb = 0%\n","🟡 Over 2 Commentary:\n","Ladies and gentlemen, what a cracking start to this match we have here! The batsmen are looking sharp as they take on the bowlers in this high-octane clash. With 2 overs completed, the runs are flowing and the energy is electric!\n","\n","The team is on track to set a decent score here with 6 runs on the board already. They are looking dominant out there, taking on the opposition with ease. The bowlers are under pressure to stem the flow of runs,\n","\n","📊 [DEBUG] Over 3: Runs = 16, Predicted = 16, WinProb = 0%\n","🟡 Over 3 Commentary:\n","Well folks, we're three overs into this IPL-style match and things are heating up! The batsmen are swinging for the fences and the bowlers are firing on all cylinders. With 16 runs on the board, the team is on track for a decent total but they'll need to keep the momentum going if they want to dominate this game.\n","\n","As of now, the win probability stands at 0%, but don't count this team out just yet. They've got plenty of firepower left in\n","\n","📊 [DEBUG] Over 4: Runs = 19, Predicted = 19, WinProb = 0%\n","🟡 Over 4 Commentary:\n","\"Welcome back to the electrifying action here at the IPL! After 4 thrilling overs, the team has managed to score 19 runs. They're looking steady, but will need to pick up the pace if they want to set a competitive total. The win probability is currently at 0%, but as we all know, anything can happen in the game of cricket! Will they turn the tide and come out on top, or will they need to dig deep to avoid being under pressure? Stay\n","\n","📊 [DEBUG] Over 5: Runs = 34, Predicted = 34, WinProb = 0%\n","🟡 Over 5 Commentary:\n","What a cracking start to this match! After 5 overs, the team has scored a solid 34 runs. They're on track for a decent total, but they'll need to keep up the momentum to dominate the game. The win probability may be currently at 0%, but there's plenty of time for them to turn things around. The pressure is on, but this team has the talent to come out on top. Stay tuned for more thrilling action in this IPL-style cricket showdown!\n","\n","📊 [DEBUG] Over 6: Runs = 45, Predicted = 45, WinProb = 0%\n","🟡 Over 6 Commentary:\n","Ladies and gentlemen, what a thrilling start to this match we have here! The team at the crease is certainly on track for a big total with 45 runs on the board after 6 overs. They are looking dominant out there, smashing boundaries left, right, and center.\n","\n","But hold on to your hats folks, because the opposition is feeling the pressure. Their bowlers are struggling to contain the onslaught and their fielders are scrambling to stop the flow of runs. The win probability might\n","\n","📊 [DEBUG] Over 7: Runs = 59, Predicted = 59, WinProb = 0%\n","🟡 Over 7 Commentary:\n","Ladies and gentlemen, what a cracking match we have on our hands here! With 7 overs completed, the score stands at a mighty 59 runs. The predicted final score is also 59, can you believe it? It's like the stars have aligned for an epic showdown today.\n","\n","The team at the crease is looking dominant, smashing boundaries left, right, and center. They are on track to set a massive total here and put the opposition under immense pressure. The fielding side\n","\n","📊 [DEBUG] Over 8: Runs = 65, Predicted = 65, WinProb = 0%\n","🟡 Over 8 Commentary:\n","\"And we're halfway through the innings here folks, with 8 overs completed and the team sitting at 65 runs on the board! The energy on the field is palpable as the players give it their all in this high-stakes match.\n","\n","With a predicted final score of 65, it's safe to say that the team is right on track to set a competitive target for the opposition. They are looking dominant out there, showcasing some fantastic batting skills and strategic gameplay.\n","\n","But let's not get\n","\n","📊 [DEBUG] Over 9: Runs = 74, Predicted = 74, WinProb = 0%\n","🟡 Over 9 Commentary:\n","Ladies and gentlemen, buckle up for some electrifying cricket action here at the IPL! After 9 thrilling overs, the scoreboard reads 74 runs with a predicted final score of...you guessed it, 74! The win probability, however, stands at a big fat 0% for the team in the spotlight.\n","\n","This team is definitely under pressure as they struggle to get their groove on. The bowlers are on fire, the fielders are sharp as ever, and the batting side is\n","\n","📊 [DEBUG] Over 10: Runs = 82, Predicted = 82, WinProb = 0%\n","🟡 Over 10 Commentary:\n","Ladies and gentlemen, what a rollercoaster of a match we have on our hands here at the IPL! Ten overs down, 82 runs on the board, and the predicted final score matching the current total. Can you believe it?!\n","\n","The team out in the middle is looking sharp, confident, dominating the field with their aggressive batting display. They're on track, setting the stage on fire with their explosive shots and quick singles. The opposition seems to be scrambling, under pressure to break this\n","\n","📊 [DEBUG] Over 11: Runs = 92, Predicted = 92, WinProb = 0%\n","🟡 Over 11 Commentary:\n","Well, folks, we're into the 11th over here and the runs are flowing like a river! The batsmen are really putting on a show for us today. With 92 runs on the board, they are certainly on track for a big total.\n","\n","The atmosphere is electric as the crowd is on their feet, cheering every boundary and six. The team looks dominant out there, showing no signs of slowing down.\n","\n","However, let's not forget the unpredictability of cricket. Anything can happen\n","\n","📊 [DEBUG] Over 12: Runs = 97, Predicted = 97, WinProb = 0%\n","🟡 Over 12 Commentary:\n","\"Ladies and gentlemen, what a thrilling match we have on our hands here! With 12 overs completed, the team has put up a whopping 97 runs on the board. The predicted final score? A solid 97! But hold onto your seats, folks, because the win probability currently stands at 0%!\n","\n","This team is looking dominant out there, showcasing some incredible batting skills and precision. Every shot is being timed to perfection, every run is being scrambled with urgency. They are definitely\n","\n","📊 [DEBUG] Over 13: Runs = 106, Predicted = 106, WinProb = 1%\n","🟡 Over 13 Commentary:\n","\"And just like that, we've reached the end of the 13th over! The score stands at 106 runs, and the predicted final score is also 106. Can you believe it? The win probability is a mere 1% but hey, in cricket, anything can happen!\n","\n","The team seems to be on track, but they need to keep the momentum going if they want to dominate this match. It's all about staying focused and seizing every opportunity that comes their way. The pressure\n","\n","📊 [DEBUG] Over 14: Runs = 107, Predicted = 107, WinProb = 1%\n","🟡 Over 14 Commentary:\n","\"Welcome back to the cricketing extravaganza, folks! We're witnessing an absolute nail-biter of a match here. With 14 overs completed, the scoreboard reads 107 runs. Can you believe it? The predicted final score is matching the current score, talk about neck-to-neck action!\n","\n","The team on the field is showing some serious grit and determination. They've been dominating the game so far, but with a win probability of just 1%, the pressure is definitely on. Can\n","\n","📊 [DEBUG] Over 15: Runs = 116, Predicted = 116, WinProb = 2%\n","🟡 Over 15 Commentary:\n","And we're into the 15th over here folks, with the score at 116 runs. The predicted final score is also 116, so it's all to play for in this nail-biter of a match! The win probability is a mere 2%, but hey, anything can happen in cricket!\n","\n","The team is definitely under pressure here, with the target looking like a tough one to defend. But hey, cricket is a game of uncertainties, and who knows, they might just pull\n","\n","📊 [DEBUG] Over 16: Runs = 117, Predicted = 117, WinProb = 2%\n","🟡 Over 16 Commentary:\n","Well folks, we're in for a nail-biter of a match here at the IPL! With 16 overs completed, the team has managed to score 117 runs. It's not looking too good for them though, as the win probability stands at a mere 2%. \n","\n","The team is definitely under pressure here, but hey, in cricket anything can happen! Will they be able to turn things around in the remaining overs and set a competitive final score? Or will the opposition continue to dominate\n","\n","📊 [DEBUG] Over 17: Runs = 123, Predicted = 123, WinProb = 3%\n","🟡 Over 17 Commentary:\n","Well folks, we're into the business end of this thrilling match and things are heating up! With 17 overs completed, the batsmen have managed to score 123 runs so far. The predicted final score is also 123, but hey, cricket is a game of uncertainties!\n","\n","The team is definitely under pressure here with a win probability of just 3%. They'll need to pull out all the stops and put on a dazzling display of cricket if they want to come out on top in this\n","\n","📊 [DEBUG] Over 18: Runs = 128, Predicted = 128, WinProb = 5%\n","🟡 Over 18 Commentary:\n","Well folks, we're in for a thrilling match here! With 18 overs completed, the team has managed to put up a total of 128 runs on the board. The predicted final score is also 128, but with a win probability of just 5%, they'll need to pull off something extraordinary to come out on top.\n","\n","The team is definitely under pressure at this point, as they'll need to really up their game in the remaining overs if they want to stand a chance. It\n","\n","📊 [DEBUG] Over 19: Runs = 147, Predicted = 147, WinProb = 27%\n","🟡 Over 19 Commentary:\n","Ladies and gentlemen, we are witnessing a thrilling match here at the IPL! With 19 overs completed, the team has managed to score 147 runs and are looking to set a challenging target for their opponents. The predicted final score is 147, and with a win probability of 27%, anything can happen in the remaining overs!\n","\n","It's safe to say that the team is on track for a competitive total, but they'll need to keep up the momentum and stay focused to ensure they come\n","\n","📊 [DEBUG] Over 20: Runs = 153, Predicted = 154, WinProb = 43%\n","🟡 Over 20 Commentary:\n","Ladies and gentlemen, we've got a cracker of a match on our hands here! After 20 overs, the team has managed to put up a total of 153 runs on the board. With a predicted final score of 154, it's going to be a nail-biter till the end!\n","\n","The team is looking confident and in control, but with a win probability of just 43%, they can't afford to let their guard down. Will they be able to maintain their dominance\n"]}]},{"cell_type":"code","source":["import matplotlib.pyplot as plt\n","\n","# Prepare data\n","overs = list(range(1, 21))\n","actual_scores = [int(x[0]) for x in cumulative_runs_in2]\n","pred_scores = over_preds\n","win_probs_pct = win_probs\n","\n","# Create figure and axis\n","fig, ax1 = plt.subplots(figsize=(14, 6))\n","\n","# 🟦 Plot actual and predicted runs\n","ax1.plot(overs, actual_scores, 'o-', label='Actual Runs (Cumulative)', color='tab:blue', linewidth=2)\n","ax1.plot(overs, pred_scores, 's--', label='GRU Predicted Final Score', color='tab:orange', linewidth=2)\n","ax1.set_xlabel(\"Overs Completed\", fontsize=12)\n","ax1.set_ylabel(\"Runs / Predicted Score\", fontsize=12)\n","\n","# 📝 Annotate each point on actual/predicted\n","for i, (a, p) in enumerate(zip(actual_scores, pred_scores)):\n","    ax1.annotate(f'{a}', (overs[i], a), textcoords=\"offset points\", xytext=(0, 6), ha='center', fontsize=8, color='blue')\n","    ax1.annotate(f'{int(p)}', (overs[i], p), textcoords=\"offset points\", xytext=(0, -12), ha='center', fontsize=8, color='orange')\n","\n","# 🟠 Plot win probability on second axis\n","ax2 = ax1.twinx()\n","ax2.plot(overs, win_probs_pct, 'x-', color='orange', label='Win Probability (%)', linewidth=2)\n","ax2.set_ylabel(\"Win Probability (%)\", fontsize=12, color='orange')\n","\n","# 📝 Annotate win probability\n","for i, prob in enumerate(win_probs_pct):\n","    ax2.annotate(f'{int(prob)}%', (overs[i], prob), textcoords=\"offset points\", xytext=(0, 6), ha='center', fontsize=8, color='darkorange')\n","\n","# 📋 Legends\n","lines1, labels1 = ax1.get_legend_handles_labels()\n","lines2, labels2 = ax2.get_legend_handles_labels()\n","ax1.legend(lines1 + lines2, labels1 + labels2, loc='upper left')\n","\n","plt.title(\"📊 Over-by-Over Match Progress & GRU Predictions\", fontsize=16)\n","plt.grid(True, linestyle='--', alpha=0.3)\n","plt.tight_layout()\n","plt.show()\n","# Save plot as PNG\n","fig.savefig(\"/content/drive/MyDrive/Colab Notebooks/IPLPrediction/gru_match_simulation_plot.png\", dpi=300)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":680},"id":"fT5tLtS8UbTo","executionInfo":{"status":"ok","timestamp":1744097879546,"user_tz":-330,"elapsed":1530,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"e0503aa9-256b-4ef3-e25a-cd019d07cac3"},"execution_count":33,"outputs":[{"output_type":"stream","name":"stderr","text":["<ipython-input-33-3b37e156111d>:39: UserWarning: Glyph 128202 (\\N{BAR CHART}) missing from font(s) DejaVu Sans.\n","  plt.tight_layout()\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 1400x600 with 2 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stderr","text":["<ipython-input-33-3b37e156111d>:42: UserWarning: Glyph 128202 (\\N{BAR CHART}) missing from font(s) DejaVu Sans.\n","  fig.savefig(\"/content/drive/MyDrive/Colab Notebooks/IPLPrediction/gru_match_simulation_plot.png\", dpi=300)\n"]}]},{"cell_type":"code","source":["import pandas as pd\n","\n","# Prepare DataFrame\n","df_export = pd.DataFrame({\n","    \"Over\": list(range(1, 21)),\n","    \"Cumulative_Runs\": [int(x[0]) for x in cumulative_runs_in2],\n","    \"Predicted_Final_Score\": [round(x, 2) for x in over_preds],\n","    \"Win_Probability (%)\": [round(x, 2) for x in win_probs]\n","})\n","\n","# Save CSV\n","csv_path = \"/content/drive/MyDrive/Colab Notebooks/IPLPrediction/gru_match_simulation_overwise.csv\"\n","df_export.to_csv(csv_path, index=False)\n"],"metadata":{"id":"cFo9z9txUbRM","executionInfo":{"status":"ok","timestamp":1744097915027,"user_tz":-330,"elapsed":69,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}}},"execution_count":34,"outputs":[]},{"cell_type":"code","source":["!pip install docx"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"PTdqBWqHXQyT","executionInfo":{"status":"ok","timestamp":1744098380445,"user_tz":-330,"elapsed":6492,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"2fdc851b-9066-430b-a545-e3a791bbf739"},"execution_count":36,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting docx\n","  Downloading docx-0.2.4.tar.gz (54 kB)\n","\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/54.9 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.9/54.9 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n","Requirement already satisfied: lxml in /usr/local/lib/python3.11/dist-packages (from docx) (5.3.1)\n","Requirement already satisfied: Pillow>=2.0 in /usr/local/lib/python3.11/dist-packages (from docx) (11.1.0)\n","Building wheels for collected packages: docx\n","  Building wheel for docx (setup.py) ... \u001b[?25l\u001b[?25hdone\n","  Created wheel for docx: filename=docx-0.2.4-py3-none-any.whl size=53893 sha256=3c64c6c9a3c406a768df86c329989c83d1e56e4cd0556789c5337a43f1f011ba\n","  Stored in directory: /root/.cache/pip/wheels/c1/3e/c3/e81c11effd0be5658a035947c66792dd993bcff317eae0e1ed\n","Successfully built docx\n","Installing collected packages: docx\n","Successfully installed docx-0.2.4\n"]}]},{"cell_type":"code","source":["!pip uninstall -y docx\n","!pip install python-docx\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"weZNt_IYXk48","executionInfo":{"status":"ok","timestamp":1744098612834,"user_tz":-330,"elapsed":13606,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"3dad738c-7d35-49d9-8f45-e1920a07f2c1"},"execution_count":40,"outputs":[{"output_type":"stream","name":"stdout","text":["Found existing installation: docx 0.2.4\n","Uninstalling docx-0.2.4:\n","  Successfully uninstalled docx-0.2.4\n","Collecting python-docx\n","  Downloading python_docx-1.1.2-py3-none-any.whl.metadata (2.0 kB)\n","Requirement already satisfied: lxml>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from python-docx) (5.3.1)\n","Requirement already satisfied: typing-extensions>=4.9.0 in /usr/local/lib/python3.11/dist-packages (from python-docx) (4.13.1)\n","Downloading python_docx-1.1.2-py3-none-any.whl (244 kB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m244.3/244.3 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hInstalling collected packages: python-docx\n","Successfully installed python-docx-1.1.2\n"]}]},{"cell_type":"code","source":["import os\n","os.listdir()\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"VHg3wDizXk75","executionInfo":{"status":"ok","timestamp":1744098564843,"user_tz":-330,"elapsed":16,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"f9286139-1a47-4a3b-e0f8-2ead3e43bb20"},"execution_count":39,"outputs":[{"output_type":"execute_result","data":{"text/plain":["['.config', 'drive', 'sample_data']"]},"metadata":{},"execution_count":39}]},{"cell_type":"code","source":["from docx import Document\n","from datetime import datetime\n","\n","# Create a new Word document\n","doc = Document()\n","doc.add_heading('🏏 IPL Match Prediction & Commentary Project Summary', 0)\n","\n","# Timestamp\n","doc.add_paragraph(f\"Last Updated: {datetime.now().strftime('%d-%b-%Y %I:%M %p')}\")\n","\n","# Section 1: Overview\n","doc.add_heading('1. Project Overview', level=1)\n","doc.add_paragraph(\"\"\"This project involves building a deep learning-based prediction system for IPL matches.\n","It predicts the final score in real-time using GRU and generates commentary using GPT-3.5. It includes spot-checking across DL models and a live match simulation dashboard.\"\"\")\n","\n","# Section 2: Phase Summary\n","doc.add_heading('2. Completed Phases', level=1)\n","\n","# Phase 1\n","doc.add_heading('2.1 Phase 1 - Score Prediction (Option A)', level=2)\n","doc.add_paragraph(\"\"\"- Preprocessed `deliveries.csv` for 1st innings scoring trends.\n","- Reshaped cumulative runs into 20-step sequences.\n","- Trained the following DL models on scaled data:\n","    • GRU\n","    • LSTM\n","    • BiLSTM\n","    • 1D_CNN\n","- Performance Comparison (MAE & RMSE): GRU performed best.\n","- All models saved in Drive: `gru_score_predictor.h5`, etc.\"\"\")\n","\n","# Phase 2\n","doc.add_heading('2.2 Phase 2 - Live Match Simulation (Option B)', level=2)\n","doc.add_paragraph(\"\"\"- Used actual match data (2 innings, 1st innings > 150).\n","- Used GRU model to predict score over-by-over.\n","- Calculated win probability using sigmoid based on target score.\n","- Exported simulation to CSV and plotted actual vs predicted vs win probability.\n","- Saved match dashboard as PNG and CSV.\"\"\")\n","\n","# Phase 3 (Initiation)\n","doc.add_heading('2.3 Phase 3 - GenAI Commentary Integration (Ongoing)', level=2)\n","doc.add_paragraph(\"\"\"- Used GPT-3.5 Turbo via `openai>=1.0.0` for generating commentary.\n","- Commentary reflects overs, runs, predicted score, and win chance.\n","- Sample commentary generated for each over.\n","- Planning to save commentary CSV and visualize alongside dashboard.\"\"\")\n","\n","# Save the document\n","summary_path = \"/content/drive/MyDrive/Colab Notebooks/IPLPrediction/IPL_Project_Summary.docx\"\n","doc.save(summary_path)\n","\n","summary_path\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":36},"id":"RFCSuht4UbOf","executionInfo":{"status":"ok","timestamp":1744098630538,"user_tz":-330,"elapsed":209,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"d1d3b31e-f936-42c7-924c-83e134e8ea24"},"execution_count":41,"outputs":[{"output_type":"execute_result","data":{"text/plain":["'/content/drive/MyDrive/Colab Notebooks/IPLPrediction/IPL_Project_Summary.docx'"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":41}]},{"cell_type":"code","source":["commentary_list = []  # 🟡 Initialize list to store all 20 commentaries\n","\n","for i in range(1, 21):\n","    runs = cumulative_runs_in2[i-1][0]\n","    pred_score = over_preds[i-1]\n","    win_prob = win_probs[i-1]\n","\n","    prompt = f\"\"\"\n","    You're a cricket commentator. Generate IPL-style cricket commentary.\n","\n","    Overs completed: {i}\n","    Runs: {runs}\n","    Predicted final score: {pred_score:.0f}\n","    Win probability: {win_prob:.0f}%\n","\n","    Describe the match in a fun, sharp, energetic tone. Say if the team is on track or under pressure.\n","    \"\"\"\n","\n","    try:\n","        response = client.chat.completions.create(\n","            model=\"gpt-3.5-turbo\",\n","            messages=[{\"role\": \"user\", \"content\": prompt}],\n","            temperature=0.8,\n","            max_tokens=100\n","        )\n","        commentary = response.choices[0].message.content\n","        commentary_list.append(commentary)  # ✅ Save response\n","        print(f\"\\n📊 [DEBUG] Over {i}: Runs = {runs}, Predicted = {round(pred_score)}, WinProb = {round(win_prob)}%\")\n","        print(f\"🟡 Over {i} Commentary:\\n{commentary}\")\n","        time.sleep(1.2)\n","\n","    except Exception as e:\n","        commentary_list.append(f\"❌ Error generating commentary for Over {i}: {e}\")  # Save error\n","        print(f\"❌ Error generating commentary for Over {i}: {e}\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"p1f088kDUbL0","executionInfo":{"status":"ok","timestamp":1744098973827,"user_tz":-330,"elapsed":47618,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"8681af6a-ad93-418a-8158-3a19e78829ba"},"execution_count":43,"outputs":[{"output_type":"stream","name":"stdout","text":["\n","📊 [DEBUG] Over 1: Runs = 1, Predicted = 2, WinProb = 0%\n","🟡 Over 1 Commentary:\n","And here we go, ladies and gentlemen! The first over of the match has been bowled and just 1 run on the board. It's a slow start but hey, it's all about building momentum, right?\n","\n","The predicted final score at this rate is 2 runs, so we definitely need to see some big hits soon. The win probability currently stands at 0%, but hey, it's early days!\n","\n","The team seems to be under a bit of pressure to get those runs flowing\n","\n","📊 [DEBUG] Over 2: Runs = 6, Predicted = 6, WinProb = 0%\n","🟡 Over 2 Commentary:\n","And we're off to a cracking start here at the IPL! Two overs down and the team has managed to put up a total of 6 runs on the board. It's early days yet, but they're definitely looking to set a solid foundation for a big score.\n","\n","The win probability may be at 0% right now, but don't count them out just yet! The pressure is on, but this team is no stranger to pulling off extraordinary comebacks. They just need to keep their\n","\n","📊 [DEBUG] Over 3: Runs = 16, Predicted = 16, WinProb = 0%\n","🟡 Over 3 Commentary:\n","And we've reached the end of the 3rd over here at the IPL, folks! The runs are coming in steadily for the team, but they'll need to pick up the pace if they want to set a challenging total.\n","\n","At this rate, the predicted final score is looking like 16, and the win probability is currently at 0%. The pressure is definitely on for the batting side to up their game and start scoring some boundaries.\n","\n","It's still early days in this match, but\n","\n","📊 [DEBUG] Over 4: Runs = 19, Predicted = 19, WinProb = 0%\n","🟡 Over 4 Commentary:\n","\"Welcome back to the thrilling action here at the stadium! We're four overs in and the team has put up a total of 19 runs on the board. It's a slow start but there's plenty of cricket left to play. Can they pick up the pace and set a competitive target?\n","\n","The team is currently on track for a predicted final score of 19, but they better watch out because the opposition is bringing the heat! With a win probability of 0%, the pressure is on\n","\n","📊 [DEBUG] Over 5: Runs = 34, Predicted = 34, WinProb = 0%\n","🟡 Over 5 Commentary:\n","Welcome back to the IPL action folks! We're 5 overs down and the score is at 34 runs. The team is looking solid at the moment but they need to keep the momentum going to reach their predicted final score of 34.\n","\n","The batsmen are showing some great form out there, hitting boundaries left, right, and center. The fielding team is feeling the pressure as they struggle to break this partnership.\n","\n","With a win probability of 0%, the team needs to keep pushing forward\n","\n","📊 [DEBUG] Over 6: Runs = 45, Predicted = 45, WinProb = 0%\n","🟡 Over 6 Commentary:\n","Ladies and gentlemen, what a thrilling match we have here today at the IPL! After 6 overs, the team has scored 45 runs and they are looking absolutely unstoppable! The batsmen are on fire and the runs are flowing like a river.\n","\n","With a predicted final score of 45, this team is definitely on track for a massive total. The opposition better watch out because these batters mean business!\n","\n","As for the win probability, it's currently sitting at 0% for the opposition\n","\n","📊 [DEBUG] Over 7: Runs = 59, Predicted = 59, WinProb = 0%\n","🟡 Over 7 Commentary:\n","Welcome back to the electrifying action of the IPL! We've just completed 7 overs and the runs are flowing like water here. The team has put up a solid 59 runs on the board and they are looking to set a big target for the opposition.\n","\n","The batsmen are playing with flair and confidence, smashing boundaries left, right, and center. The crowd is on their feet, cheering every run scored. It's an absolute treat to watch!\n","\n","With the current run rate, the predicted\n","\n","📊 [DEBUG] Over 8: Runs = 65, Predicted = 65, WinProb = 0%\n","🟡 Over 8 Commentary:\n","Ladies and gentlemen, what a rollercoaster of a match we have here today at the IPL! After 8 overs, the team has managed to score a total of 65 runs. They are on track to set a solid target for their opponents, but let's not get ahead of ourselves just yet!\n","\n","The batsmen are looking confident out there, playing their shots with precision and power. The bowlers, on the other hand, are feeling the pressure as they try to break through this\n","\n","📊 [DEBUG] Over 9: Runs = 74, Predicted = 74, WinProb = 0%\n","🟡 Over 9 Commentary:\n","Ladies and gentlemen, we are witnessing an absolute cracker of a match here at the IPL! After 9 overs, the team has managed to score 74 runs on the board. The batsmen are showcasing some incredible shots and the crowd is going wild!\n","\n","But hold on, folks, the win probability is currently at 0%! The pressure is on for the team to maintain their momentum and push towards a big total. Can they keep up the pace and set a challenging target for the opposition\n","\n","📊 [DEBUG] Over 10: Runs = 82, Predicted = 82, WinProb = 0%\n","🟡 Over 10 Commentary:\n","Ladies and gentlemen, we are witnessing a nail-biting match here at the IPL! After 10 overs, the team has managed to score 82 runs, but wait, the win probability is currently at 0% - talk about pressure!\n","\n","The batsmen are on fire, hitting boundaries left and right, but can they keep up this momentum? The bowlers are giving it their all, not making it easy for the opposition. It's a seesaw battle out there on the pitch!\n","\n","\n","\n","📊 [DEBUG] Over 11: Runs = 92, Predicted = 92, WinProb = 0%\n","🟡 Over 11 Commentary:\n","Ladies and gentlemen, we are witnessing an absolute cracker of a match here at the IPL! With 11 overs completed, the batting team has managed to amass 92 runs on the board. They are looking sharp and energetic out there on the field.\n","\n","But hold on, the win probability is currently at 0%! The pressure is on for the batting side to keep up the momentum and push for a big total. Every run from here on out will be crucial in determining the outcome of\n","\n","📊 [DEBUG] Over 12: Runs = 97, Predicted = 97, WinProb = 0%\n","🟡 Over 12 Commentary:\n","Ladies and gentlemen, buckle up your seatbelts because we are in for a rollercoaster ride here at the IPL today! The batsmen are swinging for the fences, the bowlers are sweating bullets, and the crowd is on the edge of their seats.\n","\n","After 12 overs, the team has managed to rack up 97 runs on the board. What a display of power hitting and finesse! But hold on to your hats folks, because the predicted final score is also 97\n","\n","📊 [DEBUG] Over 13: Runs = 106, Predicted = 106, WinProb = 1%\n","🟡 Over 13 Commentary:\n","\"Welcome back to the IPL madness, folks! We're into the 13th over and we've got a total of 106 runs on the board. The team is currently on track, showing some solid batting skills out there on the pitch. But let's not get too comfortable just yet, the win probability is at a mere 1% - so the pressure is definitely on to keep up the momentum and push for more runs. This match is far from over, and anything can happen in\n","\n","📊 [DEBUG] Over 14: Runs = 107, Predicted = 107, WinProb = 1%\n","🟡 Over 14 Commentary:\n","Well folks, we're into the business end of this match and things are looking grim for the batting side! With 14 overs completed, they've only managed to put up a measly 107 runs on the board. The predicted final score is also 107, so it looks like they're right on track...but for what, I'm not so sure!\n","\n","The win probability is a mere 1%, so it's safe to say that the pressure is on for these batsmen to start\n","\n","📊 [DEBUG] Over 15: Runs = 116, Predicted = 116, WinProb = 2%\n","🟡 Over 15 Commentary:\n","What a match we have here today folks! With 15 overs completed, the team has managed to score 116 runs. The energy on the field is electric, but the win probability stands at a mere 2%. It's safe to say they are definitely the underdogs in this match.\n","\n","The team is under immense pressure to perform in these final overs if they want to have any chance of pulling off a miracle. The bowlers are on fire, the fielders are sharp, but can they\n","\n","📊 [DEBUG] Over 16: Runs = 117, Predicted = 117, WinProb = 2%\n","🟡 Over 16 Commentary:\n","Ladies and gentlemen, we are witnessing a nail-biting match here at the IPL! With 16 overs completed, the team has managed to score 117 runs. The predicted final score is also 117, but with a win probability of just 2%, they sure have their work cut out for them!\n","\n","The team is definitely under pressure here, folks. They need to up their game if they want to turn this around and secure a victory. The bowlers are bringing the heat, and\n","\n","📊 [DEBUG] Over 17: Runs = 123, Predicted = 123, WinProb = 3%\n","🟡 Over 17 Commentary:\n","Ladies and gentlemen, we are witnessing a thrilling match here at the IPL! With 17 overs completed, the team has managed to score 123 runs. The predicted final score is 123 - can they keep up the momentum or will the pressure get to them?\n","\n","At a win probability of just 3%, this team is definitely the underdog in this match. But as we all know, cricket is a game of uncertainties and anything can happen!\n","\n","The players are giving it their all out there\n","\n","📊 [DEBUG] Over 18: Runs = 128, Predicted = 128, WinProb = 5%\n","🟡 Over 18 Commentary:\n","Welcome back to the IPL extravaganza, folks! We're witnessing a nail-biting encounter here as the overs are ticking away and the runs are piling up. The current score stands at 128 after 18 overs, and it looks like the team is on track to reach a predicted final score of... 128. \n","\n","But wait, hold on to your seats because the win probability is at a mere 5%! The pressure is on, folks, the pressure is on! Will they\n","\n","📊 [DEBUG] Over 19: Runs = 147, Predicted = 147, WinProb = 27%\n","🟡 Over 19 Commentary:\n","Ladies and gentlemen, what a nail-biter we have on our hands here at the IPL! The team has completed 19 overs and they have managed to score 147 runs. The predicted final score is also 147, talk about neck and neck!\n","\n","But hold onto your hats folks, because the win probability is at a mere 27%! The pressure is on, the tension is palpable, and the players are feeling the heat. Will they be able to hold their nerve and pull off\n","\n","📊 [DEBUG] Over 20: Runs = 153, Predicted = 154, WinProb = 43%\n","🟡 Over 20 Commentary:\n","Well folks, we're halfway through the game and it's been an absolute rollercoaster of a match so far! The team has managed to put up a total of 153 runs on the board after completing 20 overs. With a predicted final score of 154, they're definitely on track to set a competitive target for the opposition.\n","\n","But hold on tight, because the win probability currently stands at 43%, so it's all to play for in the second half of this innings. The\n"]}]},{"cell_type":"code","source":["import pandas as pd\n","\n","# Build DataFrame\n","commentary_df = pd.DataFrame({\n","    'Over': list(range(1, 21)),\n","    'Cumulative Runs': [x[0] for x in cumulative_runs_in2],\n","    'Predicted Final Score': [round(x) for x in over_preds],\n","    'Win Probability (%)': [round(x) for x in win_probs],\n","    'Commentary': commentary_list\n","})\n","\n","# Export path\n","csv_path = '/content/drive/MyDrive/Colab Notebooks/IPLPrediction/gru_match_simulation_commentary.csv'\n","\n","# Save to CSV\n","commentary_df.to_csv(csv_path, index=False)\n","print(f\"✅ Commentary CSV saved to: {csv_path}\")\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"cRcFAjZrUbI3","executionInfo":{"status":"ok","timestamp":1744099037060,"user_tz":-330,"elapsed":51,"user":{"displayName":"Dinesh Kumar","userId":"18299454607260962281"}},"outputId":"d8fb42ba-75a5-46de-b4d5-ab9025775b2b"},"execution_count":44,"outputs":[{"output_type":"stream","name":"stdout","text":["✅ Commentary CSV saved to: /content/drive/MyDrive/Colab Notebooks/IPLPrediction/gru_match_simulation_commentary.csv\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"XYTlk9wJUbBG"},"execution_count":null,"outputs":[]}]}