{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## Football Match Probability Prediction - Run on GPU\n\n**Competition Description**\n\nFootball has been at the heart of data science for more than a decade. If today's algorithms focus on event detection, player style, or team analysis, predicting the results of a match stays an open challenge.\n\nPredicting the outcomes of a match between two teams depends mostly (but not only) on their current form. The form of a team can be viewed as their recent sequence of results versus the other teams. So match probabilities between two teams can be different given their calendar.\n\nThis competition is about predicting the probabilities of more than 150000 match outcomes using the recent sequence of 10 matches of the teams.\n\n> **Upvote Please**","metadata":{"_uuid":"7cd960c6-91d4-4ca0-a69a-9e4e520d184a","_cell_guid":"eab67375-a4a9-4e08-bb4a-3c099e21dfa9","trusted":true}},{"cell_type":"markdown","source":"## Import modules and loading the data\nFirst let's import modules, the training and the test set. The test set contains the same columns than the training set without the target.","metadata":{"_uuid":"a1e98e57-05f8-42b9-815d-023b303cd789","_cell_guid":"000b4f69-0b86-45f3-9560-8c549acb8e78","trusted":true}},{"cell_type":"code","source":"# Import libraries\n# import gc\nimport numpy as np\nimport pandas as pd\nimport datetime as dt\n#\nfrom sklearn.model_selection import KFold\nfrom sklearn.preprocessing import RobustScaler, LabelEncoder\nfrom sklearn.metrics import accuracy_score, log_loss\n#\nimport tensorflow as tf\nfrom tensorflow.keras.utils import plot_model, to_categorical\nfrom tensorflow.keras.models import Model, load_model\nfrom tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, LearningRateScheduler\nfrom tensorflow.keras.optimizers.schedules import ExponentialDecay\nfrom tensorflow.keras import layers\n","metadata":{"_uuid":"920e6d1a-69cf-46e8-a78b-24f7fe780f73","_cell_guid":"c6c6ebe4-3bf5-4a40-8f8e-3f065ecd9e16","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-06T09:32:08.842083Z","iopub.execute_input":"2022-05-06T09:32:08.842369Z","iopub.status.idle":"2022-05-06T09:32:14.849381Z","shell.execute_reply.started":"2022-05-06T09:32:08.842291Z","shell.execute_reply":"2022-05-06T09:32:14.848592Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#loading the data\ntrain = pd.read_csv('/kaggle/input/football-match-probability-prediction/train.csv')\ntest = pd.read_csv('/kaggle/input/football-match-probability-prediction/test.csv')\nsubmission = pd.read_csv('/kaggle/input/football-match-probability-prediction/sample_submission.csv')","metadata":{"_uuid":"f9cd6673-ccc8-4e4c-bce0-c4e7e1d8e98a","_cell_guid":"e5fbcac1-440c-4d84-8f6f-6ef0f1102c70","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-06T09:32:14.853213Z","iopub.execute_input":"2022-05-06T09:32:14.853458Z","iopub.status.idle":"2022-05-06T09:32:23.759788Z","shell.execute_reply.started":"2022-05-06T09:32:14.85343Z","shell.execute_reply":"2022-05-06T09:32:23.759007Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Parameters\nSet some parameters that will be used later.","metadata":{"_uuid":"ac3c4d94-2456-491c-b634-480be3505386","_cell_guid":"62203296-73b6-416a-b8af-83919edc6721","trusted":true}},{"cell_type":"code","source":"# Set seed\nnp.random.seed(123)\ntf.random.set_seed(123)\n\n#Some parameters\nMASK = -666 # fill NA with -666 (the number of the beast)\nT_HIST = 10 # time history, last 10 games\nCLASS = 3 #number of classes (home, draw, away)\n\nDEBUG = False\n# Run on a small sample of the data\nif DEBUG:\n    train = train[:10000]","metadata":{"_uuid":"9bc24db5-b55a-4e16-87c3-ce6b4cd8a552","_cell_guid":"72e32380-622d-40ce-b35a-674120f981b1","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-06T09:32:39.922179Z","iopub.execute_input":"2022-05-06T09:32:39.922446Z","iopub.status.idle":"2022-05-06T09:32:39.929676Z","shell.execute_reply.started":"2022-05-06T09:32:39.922415Z","shell.execute_reply":"2022-05-06T09:32:39.928885Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# exclude matches with no history at date 1 - full of NA (1159 rows excluded)\n#train.dropna(subset=['home_team_history_match_date_1'], inplace = True)\n# exclude leagues with less than 15 matches: This change has no effect on the final log loss\nif False:\n    train['league_id_count'] = train.groupby('league_id')['id'].transform('count')\n    train = train.loc[train['league_id_count'] > 15]","metadata":{"execution":{"iopub.status.busy":"2022-05-06T09:32:57.235848Z","iopub.execute_input":"2022-05-06T09:32:57.236787Z","iopub.status.idle":"2022-05-06T09:32:57.242389Z","shell.execute_reply.started":"2022-05-06T09:32:57.23674Z","shell.execute_reply":"2022-05-06T09:32:57.241436Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f\"Train: {train.shape} \\n Submission: {submission.shape}\")\ntrain","metadata":{"_uuid":"f98d00e1-b8db-475f-926b-3f27fc07bc55","_cell_guid":"36d932ff-1cf7-4fa3-97c3-2657a83150a9","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-06T09:32:58.291164Z","iopub.execute_input":"2022-05-06T09:32:58.291426Z","iopub.status.idle":"2022-05-06T09:32:58.377907Z","shell.execute_reply.started":"2022-05-06T09:32:58.291397Z","shell.execute_reply":"2022-05-06T09:32:58.377195Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.home_team_history_match_date_2.isnull().value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-05-06T09:33:02.354777Z","iopub.execute_input":"2022-05-06T09:33:02.355663Z","iopub.status.idle":"2022-05-06T09:33:02.378088Z","shell.execute_reply.started":"2022-05-06T09:33:02.355614Z","shell.execute_reply":"2022-05-06T09:33:02.377334Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Feature Engineering\nThe **most** important part of Machine Learning.","metadata":{"_uuid":"91794a39-6ab8-4fac-bf6a-833de1182b06","_cell_guid":"838bf7ec-34de-46d8-8de9-0c9be9cb1fea","trusted":true}},{"cell_type":"code","source":"# for cols \"date\", change to datatime \nfor col in train.filter(regex='date', axis=1).columns:\n    train[col] = pd.to_datetime(train[col])\n    test[col] = pd.to_datetime(test[col])\n\n# Some feature engineering\ndef add_features(df):\n    for i in range(1, 11): # range from 1 to 10\n        \n    # Feat. difference of days\n        df[f'home_team_history_match_DIFF_day_{i}'] = (df['match_date'] - df[f'home_team_history_match_date_{i}']).dt.days\n        df[f'away_team_history_match_DIFF_days_{i}'] = (df['match_date'] - df[f'away_team_history_match_date_{i}']).dt.days\n        \n    # Feat. difference of scored goals\n        df[f'home_team_history_DIFF_goal_{i}'] = df[f'home_team_history_goal_{i}'] - df[f'home_team_history_opponent_goal_{i}']\n        df[f'away_team_history_DIFF_goal_{i}'] = df[f'away_team_history_goal_{i}'] - df[f'away_team_history_opponent_goal_{i}']\n        \n    # Feat dummy winner x equality x loser \n        df[f'home_winner_{i}'] = np.where(df[f'home_team_history_DIFF_goal_{i}'] > 0, 1., 0.) \n        df[f'home_equality_{i}'] = np.where(df[f'home_team_history_DIFF_goal_{i}'] == 0, 1., 0.) \n        df[f'home_loser_{i}'] = np.where(df[f'home_team_history_DIFF_goal_{i}'] < 0, 1., 0.)\n        df[f'away_winner_{i}'] = np.where(df[f'away_team_history_DIFF_goal_{i}'] > 0, 1., 0.)\n        df[f'away_equality_{i}'] = np.where(df[f'away_team_history_DIFF_goal_{i}'] == 0, 1., 0.) \n        df[f'away_loser_{i}'] = np.where(df[f'away_team_history_DIFF_goal_{i}'] < 0, 1., 0.)\n     \n    # Scores Classification \n        df[f'home_team_history_DIFF_goal_classification_{i}'] = pd.cut((df[f'home_team_history_goal_{i}'] - df[f'home_team_history_opponent_goal_{i}']).fillna(0), [-100, 0, 3, 100], labels = False)\n        df[f'away_team_history_DIFF_goal_classification_{i}'] = pd.cut((df[f'away_team_history_goal_{i}'] - df[f'away_team_history_opponent_goal_{i}']).fillna(0), [-100, 0, 3, 100], labels = False)\n        \n    # Results: multiple nested where # away:0, draw:1, home:2\n        df[f'home_team_result_{i}'] = np.where(df[f'home_team_history_DIFF_goal_{i}'] > 0., 2.,\n                         (np.where(df[f'home_team_history_DIFF_goal_{i}'] == 0., 1,\n                                   np.where(df[f'home_team_history_DIFF_goal_{i}'].isna(), np.nan, 0))))\n        df[f'away_team_result_{i}'] = np.where(df[f'away_team_history_DIFF_goal_{i}'] > 0., 2.,\n                         (np.where(df[f'away_team_history_DIFF_goal_{i}'] == 0., 1.,\n                                   np.where(df[f'away_team_history_DIFF_goal_{i}'].isna(), np.nan, 0.))))\n        \n    # Feat. difference of rating (\"modified\" ELO RATING)\n        df[f'home_team_history_ELO_rating_{i}'] = 1/(1+10**((df[f'home_team_history_opponent_rating_{i}']-df[f'home_team_history_rating_{i}'])/10))\n        df[f'away_team_history_ELO_rating_{i}'] = 1/(1+10**((df[f'away_team_history_opponent_rating_{i}']-df[f'away_team_history_rating_{i}'])/10))\n        df[f'home_away_team_history_ELO_rating_{i}'] = 1/(1+10**((df[f'away_team_history_rating_{i}']-df[f'home_team_history_rating_{i}'])/10))\n        \n    # Feat. same coach id\n        df[f'home_team_history_SAME_coaX_{i}'] = np.where(df['home_team_coach_id']==df[f'home_team_history_coach_{i}'],1,0)\n        df[f'away_team_history_SAME_coaX_{i}'] = np.where(df['away_team_coach_id']==df[f'away_team_history_coach_{i}'],1,0) \n        \n    # Feat. same league id\n        df[f'home_team_history_SAME_leaG_{i}'] = np.where(df['league_id']==df[f'home_team_history_league_id_{i}'],1,0)\n        df[f'away_team_history_SAME_leaG_{i}'] = np.where(df['league_id']==df[f'away_team_history_league_id_{i}'],1,0) \n\n    return df\n\ntrain = add_features(train)\ntest = add_features(test)","metadata":{"_uuid":"daed24ca-8f78-4419-b19f-3b97d78f29f7","_cell_guid":"fa41a07c-c823-4716-8666-21f3f8cc12ed","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-06T09:33:04.971018Z","iopub.execute_input":"2022-05-06T09:33:04.971477Z","iopub.status.idle":"2022-05-06T09:33:07.786481Z","shell.execute_reply.started":"2022-05-06T09:33:04.97144Z","shell.execute_reply":"2022-05-06T09:33:07.785767Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Scaling and Reshape\nThe input/output of the lstm is very trick. It is expected an array of dimensions (Matches/Batch, Time history, Features). I hope I did it right.","metadata":{"_uuid":"0fa67e85-50f7-43af-a9dc-b11c05bcbf8c","_cell_guid":"878d27a4-831a-4a9f-9c9b-275409afc69b","trusted":true}},{"cell_type":"code","source":"# save targets\ntrain_y = train['target'].copy()\n\n#keep only some features\ntrain_x = train.drop(['target', 'home_team_name', 'away_team_name'], axis=1) # is_cup EXCLUDED\n\n# Exclude all date, league, coach columns\ntrain_x.drop(train.filter(regex='date').columns, axis=1, inplace = True)\ntrain_x.drop(train.filter(regex='league').columns, axis=1, inplace = True)\ntrain_x.drop(train.filter(regex='coach').columns, axis=1, inplace = True)\n\n# Test set\n# test_id = test['id'].copy()\ntest_x = test.drop(['home_team_name', 'away_team_name'], axis=1) # is_cup EXCLUDED\n\n# Exclude all date, league, coach columns\ntest_x.drop(test.filter(regex='date').columns, axis=1, inplace = True)\ntest_x.drop(test.filter(regex='league').columns, axis=1, inplace = True)\ntest_x.drop(test.filter(regex='coach').columns, axis=1, inplace = True)","metadata":{"_uuid":"7b65ce25-5a33-4fb8-b04b-0f288ea3d9bb","_cell_guid":"fe6715ba-250e-4a67-bc76-f046ba57b793","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-06T09:54:25.279154Z","iopub.execute_input":"2022-05-06T09:54:25.279391Z","iopub.status.idle":"2022-05-06T09:54:26.281635Z","shell.execute_reply.started":"2022-05-06T09:54:25.279359Z","shell.execute_reply":"2022-05-06T09:54:26.280826Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Target, train and test shape\nprint(f\"Target: {train_y.shape} \\n Train shape: {train_x.shape} \\n Test: {test_x.shape}\")","metadata":{"_uuid":"9c748333-e838-48d8-88f0-33ef0051e57e","_cell_guid":"9ab58872-8c97-4c9a-a110-a55588e0f29f","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-06T09:54:26.283059Z","iopub.execute_input":"2022-05-06T09:54:26.283302Z","iopub.status.idle":"2022-05-06T09:54:26.288333Z","shell.execute_reply.started":"2022-05-06T09:54:26.283269Z","shell.execute_reply":"2022-05-06T09:54:26.287337Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Store feature names\n# feature_names = list(train.columns)\n# Pivot dataframe to create an input array for the LSTM network\nfeature_groups = [\"home_team_history_is_play_home\", \"home_team_history_is_cup\",\n    \"home_team_history_goal\", \"home_team_history_opponent_goal\",\n    \"home_team_history_rating\", \"home_team_history_opponent_rating\",  \n    \"away_team_history_is_play_home\", \"away_team_history_is_cup\",\n    \"away_team_history_goal\", \"away_team_history_opponent_goal\",\n    \"away_team_history_rating\", \"away_team_history_opponent_rating\",  \n    \"home_team_history_match_DIFF_day\", \"away_team_history_match_DIFF_days\",\n    \"home_team_history_DIFF_goal\",\"away_team_history_DIFF_goal\",\n    \"home_team_history_ELO_rating\",\"away_team_history_ELO_rating\",\n    \"home_away_team_history_ELO_rating\", \"home_team_history_DIFF_goal_classification\",\n    \"away_team_history_DIFF_goal_classification\",\n    \"home_team_history_SAME_coaX\", \"away_team_history_SAME_coaX\",\n    \"home_team_history_SAME_leaG\", \"away_team_history_SAME_leaG\",\n    \"home_team_result\", \"away_team_result\",\n    \"home_winner\",\"home_equality\", \"home_loser\", \"away_winner\",\"away_equality\", \"away_loser\"         \n                 ]    \n# Pivot dimension (id*features) x time_history\ntrain_x_pivot = pd.wide_to_long(train_x, stubnames=feature_groups, \n                i=['id','is_cup'], j='time', sep='_', suffix='\\d+')\ntest_x_pivot = pd.wide_to_long(test_x, stubnames=feature_groups, \n                i=['id','is_cup'], j='time', sep='_', suffix='\\d+')\n#\nprint(f\"Train pivot shape: {train_x_pivot.shape}\")  \nprint(f\"Test pivot shape: {test_x_pivot.shape}\") ","metadata":{"_uuid":"c316690b-dbb6-45f2-882c-18bcb932af61","_cell_guid":"46437c51-e209-4f27-8d53-1bf0e8547fc4","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-01T14:26:00.953574Z","iopub.execute_input":"2022-05-01T14:26:00.953907Z","iopub.status.idle":"2022-05-01T14:26:00.983117Z","shell.execute_reply.started":"2022-05-01T14:26:00.953873Z","shell.execute_reply":"2022-05-01T14:26:00.98231Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_x_pivot","metadata":{"execution":{"iopub.status.busy":"2022-05-01T14:26:04.923314Z","iopub.execute_input":"2022-05-01T14:26:04.924014Z","iopub.status.idle":"2022-05-01T14:26:04.945415Z","shell.execute_reply.started":"2022-05-01T14:26:04.923977Z","shell.execute_reply":"2022-05-01T14:26:04.944555Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# create columns based on index\ntrain_x_pivot = train_x_pivot.reset_index()\ntest_x_pivot = test_x_pivot.reset_index()\n# Deal with the is_cup feature\n# There are NA in 'is_cup'\ntrain_x_pivot=train_x_pivot.fillna({'is_cup':False})\ntrain_x_pivot['is_cup'] = pd.get_dummies(train_x_pivot['is_cup'], drop_first=True)\n#\ntest_x_pivot=test_x_pivot.fillna({'is_cup':False})\ntest_x_pivot['is_cup']= pd.get_dummies(test_x_pivot['is_cup'], drop_first=True)","metadata":{"execution":{"iopub.status.busy":"2022-05-01T14:11:16.718781Z","iopub.status.idle":"2022-05-01T14:11:16.719311Z","shell.execute_reply.started":"2022-05-01T14:11:16.71908Z","shell.execute_reply":"2022-05-01T14:11:16.719106Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Add more important features","metadata":{}},{"cell_type":"code","source":"# Feature engineering again!!! Group by id, stats over time\ndef add_features_II(df):\n    \n    # goals\n    df['home_team_history_DIFF_goal_csum'] = df.groupby('id')['home_team_history_DIFF_goal'].cumsum()\n    df['away_team_history_DIFF_goal_csum'] = df.groupby('id')['away_team_history_DIFF_goal'].cumsum()\n\n    # rating\n    df['home_team_hist_rat_mean'] = df.groupby('id')['home_team_history_rating'].transform('mean')\n    df['home_team_hist_rat_min'] = df.groupby('id')['home_team_history_rating'].transform('min')\n    df['home_team_hist_rat_max'] = df.groupby('id')['home_team_history_rating'].transform('max')\n    df['home_team_hist_rat_sum'] = df.groupby('id')['home_team_history_rating'].transform('sum')\n    df['home_team_hist_rat_std'] = df.groupby('id')['home_team_history_rating'].transform('std')\n    df['away_team_hist_rat_mean'] = df.groupby('id')['away_team_history_rating'].transform('mean')\n    df['away_team_hist_rat_min'] = df.groupby('id')['away_team_history_rating'].transform('min')\n    df['away_team_hist_rat_max'] = df.groupby('id')['away_team_history_rating'].transform('max')\n    df['home_team_hist_rat_sum'] = df.groupby('id')['home_team_history_rating'].transform('sum')\n    df['home_team_hist_rat_std'] = df.groupby('id')['home_team_history_rating'].transform('std')\n\n    df['home_away_rat_elo'] = 1/(1+10**((df['away_team_hist_rat_mean']-df['home_team_hist_rat_mean'])/10))\n    \n    # Result (%)\n    df['home_team_result_mean'] = df.groupby('id')['home_team_result'].transform('mean')\n    df['home_team_result_min'] = df.groupby('id')['home_team_result'].transform('min')\n    df['home_team_result_max'] = df.groupby('id')['home_team_result'].transform('max')\n    df['home_team_result_sum'] = df.groupby('id')['home_team_result'].transform('sum')\n    df['home_team_result_std'] = df.groupby('id')['home_team_result'].transform('std')\n    df['away_team_result_mean'] = df.groupby('id')['away_team_result'].transform('mean')\n    df['away_team_result_min'] = df.groupby('id')['away_team_result'].transform('min')\n    df['away_team_result_max'] = df.groupby('id')['away_team_result'].transform('max')\n    df['home_team_result_sum'] = df.groupby('id')['home_team_result'].transform('sum')\n    df['home_team_result_std'] = df.groupby('id')['home_team_result'].transform('std')\n\n    df['home_team_result_lag1'] = df.groupby('id')['home_team_result'].shift(-1)\n    df['away_team_result_lag1'] = df.groupby('id')['away_team_result'].shift(-1)\n    df['home_team_result_lag2'] = df.groupby('id')['home_team_result'].shift(-2)\n    df['away_team_result_lag2'] = df.groupby('id')['away_team_result'].shift(-2)\n    \n    return df\n\ntrain_x_pivot = add_features_II(train_x_pivot)\ntest_x_pivot = add_features_II(test_x_pivot)","metadata":{"execution":{"iopub.status.busy":"2022-05-01T14:11:16.720402Z","iopub.status.idle":"2022-05-01T14:11:16.720949Z","shell.execute_reply.started":"2022-05-01T14:11:16.720718Z","shell.execute_reply":"2022-05-01T14:11:16.720743Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# bidirectional LSTM is used\n\nINV = True\nif INV:\n    # Trying to keep the same id order\n    train_x_pivot.sort_values(by=['time'], inplace = True, ascending=False)\n    # Merge and drop columns\n    train_x_pivot = pd.merge(train_x['id'], train_x_pivot, on=\"id\").drop(['id', 'time'], axis = 1)\n    # Test\n    test_x_pivot.sort_values(by=['time'], inplace = True, ascending=False)\n    test_x_pivot = pd.merge(test_x['id'], test_x_pivot, on=\"id\").drop(['id', 'time'], axis = 1)","metadata":{"execution":{"iopub.status.busy":"2022-05-01T14:11:16.72199Z","iopub.status.idle":"2022-05-01T14:11:16.722535Z","shell.execute_reply.started":"2022-05-01T14:11:16.722281Z","shell.execute_reply":"2022-05-01T14:11:16.722306Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train = train_x_pivot.copy() \nx_test = test_x_pivot.copy() \n\n# Fill NA with median\nfill_median = True\nif fill_median:\n    x_train = np.where(np.isnan(x_train), np.nanmedian(x_train, axis=0), x_train)\n    x_test = np.where(np.isnan(x_test), np.nanmedian(x_test, axis=0), x_test)\n\n# Scale features using statistics that are robust to outliers\nRS = RobustScaler()\nx_train = RS.fit_transform(x_train)\nx_test = RS.transform(x_test)\n# Reshape \nx_train = x_train.reshape(-1, T_HIST, x_train.shape[-1])\nx_test = x_test.reshape(-1, T_HIST, x_test.shape[-1])\n\nif False:\n    # Fill NA with MASK\n    x_train = np.nan_to_num(x_train, nan=MASK)\n    x_test = np.nan_to_num(x_test, nan=MASK)","metadata":{"execution":{"iopub.status.busy":"2022-05-01T14:11:16.723588Z","iopub.status.idle":"2022-05-01T14:11:16.724351Z","shell.execute_reply.started":"2022-05-01T14:11:16.72399Z","shell.execute_reply":"2022-05-01T14:11:16.724017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Deal with targets\n# encode class values as integers\nencoder = LabelEncoder()\nencoder.fit(train_y)\nencoded_y = encoder.transform(train_y)\n\n# convert integers to dummy variables (i.e. one hot encoded)\ndummy_y = to_categorical(encoded_y)\n# \nprint(encoded_y.shape)\nprint(dummy_y.shape)","metadata":{"_uuid":"129f90f7-7744-488c-9e61-b49bb2c90992","_cell_guid":"40d047c0-ca6f-4bdc-af0f-17e0d1f843f5","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-01T14:11:16.728854Z","iopub.status.idle":"2022-05-01T14:11:16.72939Z","shell.execute_reply.started":"2022-05-01T14:11:16.729145Z","shell.execute_reply":"2022-05-01T14:11:16.72917Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Setup GPU\nBelow declare whether to use 1 GPU or multiple GPU. (Change CUDA_VISIBLE_DEVICES to use more GPUs). I am not aware of the impact on speed.","metadata":{}},{"cell_type":"code","source":"import os\nos.environ[\"CUDA_VISIBLE_DEVICES\"]=\"0\"\n\n# USE MULTIPLE GPUS\nif os.environ[\"CUDA_VISIBLE_DEVICES\"].count(',') == 0:\n    gpu_strategy = tf.distribute.get_strategy()\n    print('single strategy')\nelse:\n    gpu_strategy = tf.distribute.MirroredStrategy()\n    print('multiple strategy')","metadata":{"execution":{"iopub.status.busy":"2022-05-01T14:11:16.732095Z","iopub.status.idle":"2022-05-01T14:11:16.732632Z","shell.execute_reply.started":"2022-05-01T14:11:16.732395Z","shell.execute_reply":"2022-05-01T14:11:16.732434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Make a model\nThe model is LSTM.","metadata":{"_uuid":"f0fd77a2-0d9c-4fba-ac6d-f879a553bf4c","_cell_guid":"51235a13-fea9-47fd-a2b9-caeccbd0b67f","trusted":true}},{"cell_type":"code","source":"def model():\n    x_input = layers.Input(shape=x_train.shape[1:])\n\n    x = layers.Bidirectional(tf.compat.v1.keras.layers.CuDNNLSTM(16, return_sequences=True))(x_input) #(x)\n    x = layers.Dropout(0.5)(x)  \n    x = layers.Bidirectional(tf.compat.v1.keras.layers.CuDNNLSTM(8, return_sequences=True))(x)\n    x = layers.Dropout(0.5)(x)\n    x = layers.Flatten()(x)\n    \n    # output\n    output = layers.Dense(CLASS, activation='softmax')(x)\n    model = Model(inputs=[x_input],outputs=[output])\n\n    return model","metadata":{"_uuid":"8f733748-8539-4dff-9db7-88edd1e41bdf","_cell_guid":"da442908-1692-4121-b108-ebd4141c4d4f","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-01T14:11:16.735261Z","iopub.status.idle":"2022-05-01T14:11:16.735807Z","shell.execute_reply.started":"2022-05-01T14:11:16.735575Z","shell.execute_reply":"2022-05-01T14:11:16.735601Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Choose your model\nmodel = model()\nmodel.summary()","metadata":{"_uuid":"43445b36-d540-4621-b921-efbff25a5a48","_cell_guid":"d48d09c0-c867-4d6c-9edb-9174b243cf4f","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-01T14:11:16.744947Z","iopub.status.idle":"2022-05-01T14:11:16.745496Z","shell.execute_reply.started":"2022-05-01T14:11:16.745239Z","shell.execute_reply":"2022-05-01T14:11:16.745264Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_model(\n    model, \n    to_file='Football_Prob_Model.png', \n    show_shapes=True,\n    show_layer_names=True\n)","metadata":{"_uuid":"8a324a9c-628d-4173-b87f-c425a194d954","_cell_guid":"efb6e5f5-4590-4ea3-bf8b-afe761843ee4","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-01T14:11:16.746681Z","iopub.status.idle":"2022-05-01T14:11:16.747214Z","shell.execute_reply.started":"2022-05-01T14:11:16.746984Z","shell.execute_reply":"2022-05-01T14:11:16.747009Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Fit the model and a make submission\nOnce the model is fitted we make the **probabilities prediction**. Then we make the submission dataframe with **4 columns**. The columns home, away and draw contain probability while the column id contains the match id.","metadata":{"_uuid":"ea635cb3-5380-4259-ad5f-fd94e9606f26","_cell_guid":"0c123082-ce45-4f81-841d-eb90adea1783","trusted":true}},{"cell_type":"code","source":" # Just one fold, validation split = 20%\nif False:\n    EPOCH = 200\n    BATCH_SIZE = 512 \n    # N_SPLITS = 5\n    SEED = 123\n    VERBOSE = 1\n    PATIENCE = EPOCH // 10\n    VAL_SPLIT = 0.2\n    # Model\n    # It is a multi-class classification problem, categorical_crossentropy is used as the loss function.\n    model.compile(optimizer=\"adam\", loss=\"categorical_crossentropy\",\n                     metrics=[\"accuracy\"])\n    #\n    es = EarlyStopping(monitor='val_loss', patience=PATIENCE, verbose=0, mode='min',\n                           restore_best_weights=True)\n    lr = ReduceLROnPlateau(monitor=\"val_loss\", factor=0.5, patience=10, verbose=0)\n    #\n    model.fit(x_train, dummy_y, \n                  # validation_data=(x_train, y_train), \n                  validation_split=VAL_SPLIT,\n                  epochs=EPOCH,\n                  verbose=VERBOSE,\n                  batch_size=BATCH_SIZE,\n                  callbacks=[lr, es])\n","metadata":{"_uuid":"e20e5330-09de-4723-b0c4-6a1b07ab6927","_cell_guid":"19806374-e259-453a-b033-e80a15e0f03e","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-01T14:11:16.748269Z","iopub.status.idle":"2022-05-01T14:11:16.748829Z","shell.execute_reply.started":"2022-05-01T14:11:16.748596Z","shell.execute_reply":"2022-05-01T14:11:16.748621Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# N_SPLITS of the traning set for validation using KFold\n# Parameters\nEPOCH = 200\nBATCH_SIZE = 512\nN_SPLITS = 20\nSEED = 123\nVERBOSE = 1\nPATIENCE = EPOCH // 10\n\ntest_preds = []\n\nwith gpu_strategy.scope():\n    kf = KFold(n_splits=N_SPLITS, random_state=SEED) \n\n    for fold, (train_idx, test_idx) in enumerate(kf.split(x_train, dummy_y)):\n        print('-'*15, '>', f'Fold {fold+1}/{N_SPLITS}', '<', '-'*15)\n        X_train, X_valid = x_train[train_idx], x_train[test_idx]\n        Y_train, Y_valid = dummy_y[train_idx], dummy_y[test_idx]\n        \n        # It is a multi-class classification problem, categorical_crossentropy is used as the loss function.\n        model.compile(optimizer=\"adam\", loss=\"categorical_crossentropy\",\n                     metrics=[\"accuracy\"])\n        #\n        es = EarlyStopping(monitor='val_loss', patience=PATIENCE, verbose=0, mode='min',\n                           restore_best_weights=True)\n        lr = ReduceLROnPlateau(monitor=\"val_loss\", factor=0.5, patience=10, verbose=0)\n        #\n        model.fit(X_train, Y_train, \n                  validation_data=(X_valid, Y_valid), \n                  epochs=EPOCH,\n                  verbose=VERBOSE,\n                  batch_size=BATCH_SIZE,  \n                  callbacks=[lr, es])\n        # Model validation    \n        y_true = Y_valid.squeeze()\n        y_pred = model.predict(X_valid, batch_size=BATCH_SIZE).squeeze()\n        score1 = log_loss(y_true, y_pred)\n        print(f\"Fold-{fold+1} | OOF LogLoss Score: {score1}\")\n        \n        # Predictions\n        test_preds.append(model.predict(x_test).squeeze())\n\n","metadata":{"execution":{"iopub.status.busy":"2022-05-01T14:11:16.749898Z","iopub.status.idle":"2022-05-01T14:11:16.750448Z","shell.execute_reply.started":"2022-05-01T14:11:16.750196Z","shell.execute_reply":"2022-05-01T14:11:16.750223Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = sum(test_preds)/N_SPLITS \n\n# away, draw, home\nsubmission = pd.DataFrame(predictions,columns=['away', 'draw', 'home'])\n\n# Round\nround_num = False\nif round_num:\n    submission = submission.round(2)\n    submission['draw'] = 1 - (submission['home'] + submission['away'])  \n    \n#do not forget the id column\nsubmission['id'] = test[['id']]\n\n#submit!\nsubmission[['id', 'home', 'away', 'draw']].to_csv('submission.csv', index=False)","metadata":{"_uuid":"fbc22907-d44b-4d98-a63e-7308371f2575","_cell_guid":"daf73b19-9b2b-426f-a75a-eb1842f15261","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-01T14:11:16.753089Z","iopub.status.idle":"2022-05-01T14:11:16.753647Z","shell.execute_reply.started":"2022-05-01T14:11:16.753405Z","shell.execute_reply":"2022-05-01T14:11:16.753444Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission[['id', 'home', 'away', 'draw']].head()","metadata":{"_uuid":"a5aeb080-c652-4e2c-9476-e662c51ff731","_cell_guid":"a7b164c3-f7d6-47a8-b6a6-b84ebb382b4d","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2022-05-01T14:11:16.75468Z","iopub.status.idle":"2022-05-01T14:11:16.755203Z","shell.execute_reply.started":"2022-05-01T14:11:16.754972Z","shell.execute_reply":"2022-05-01T14:11:16.754997Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}