{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\n\nimport riiideducation\nfrom sklearn.metrics import roc_auc_score\nenv = riiideducation.make_env()\n\nfrom sklearn.feature_selection import RFE\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.model_selection import KFold\n\nimport tensorflow as tf\nimport tensorflow.keras.backend as K\nfrom tensorflow.keras.layers import Input, Dense","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\n    '/kaggle/input/riiid-test-answer-prediction/train.csv',\n    usecols=[1, 2, 3, 4, 5, 7, 8, 9],\n    dtype={\n        'timestamp': 'int64',\n        'user_id': 'int32',\n        'content_id': 'int16',\n        'content_type_id': 'int8',\n        'task_container_id': 'int16',\n        'answered_correctly':'int8',\n        'prior_question_elapsed_time': 'float32',\n        'prior_question_had_explanation': 'boolean'\n    }\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"questions_df = pd.read_csv(\n    '/kaggle/input/riiid-test-answer-prediction/questions.csv',                         \n    usecols=[0, 3],\n    dtype={\n        'question_id': 'int16',\n        'part': 'int8'}\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lectures_df = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/lectures.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Thanks https://www.kaggle.com/takamotoki/lgbm-iii-part3-adding-lecture-features for feature creation part"},{"metadata":{"trusted":true},"cell_type":"code","source":"lectures_df['type_of'] = lectures_df['type_of'].replace('solving question', 'solving_question')\nlectures_df = pd.get_dummies(lectures_df, columns=['part', 'type_of'])\npart_lectures_columns = [column for column in lectures_df.columns if column.startswith('part')]\ntypes_of_lectures_columns = [column for column in lectures_df.columns if column.startswith('type_of_')]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_lectures = train[train.content_type_id == True].merge(lectures_df, left_on='content_id', right_on='lecture_id', how='left')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"user_lecture_stats_part = train_lectures.groupby('user_id')[part_lectures_columns + types_of_lectures_columns].sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for column in user_lecture_stats_part.columns:\n    bool_column = column + '_boolean'\n    user_lecture_stats_part[bool_column] = (user_lecture_stats_part[column] > 0).astype(int)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import gc\n\ndel train_lectures\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = train[train.content_type_id == False].sort_values('timestamp').reset_index(drop = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"elapsed_mean = train.prior_question_elapsed_time.mean()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"group1 = train.loc[(train.content_type_id == False), ['task_container_id', 'user_id']].groupby(['task_container_id']).agg(['count'])\ngroup1.columns = ['avg_questions']\ngroup2 = train.loc[(train.content_type_id == False), ['task_container_id', 'user_id']].groupby(['task_container_id']).agg(['nunique'])\ngroup2.columns = ['avg_questions']\ngroup3 = group1 / group2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"group3['avg_questions_seen'] = group3.avg_questions.cumsum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results_u_final = train.loc[train.content_type_id == False, ['user_id','answered_correctly']].groupby(['user_id']).agg(['mean'])\nresults_u_final.columns = ['answered_correctly_user']\n\nresults_u2_final = train.loc[train.content_type_id == False, ['user_id','prior_question_had_explanation']].groupby(['user_id']).agg(['mean'])\nresults_u2_final.columns = ['explanation_mean_user']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prior_mean_user = results_u2_final.explanation_mean_user.mean()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.merge(train, questions_df, left_on = 'content_id', right_on = 'question_id', how = 'left')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results_q_final = train.loc[train.content_type_id == False, ['question_id','answered_correctly']].groupby(['question_id']).agg(['mean'])\nresults_q_final.columns = ['quest_pct']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results_q2_final = train.loc[train.content_type_id == False, ['question_id','part']].groupby(['question_id']).agg(['count'])\nresults_q2_final.columns = ['count']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"question2 = pd.merge(questions_df, results_q_final, left_on = 'question_id', right_on = 'question_id', how = 'left')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"question2 = pd.merge(question2, results_q2_final, left_on = 'question_id', right_on = 'question_id', how = 'left')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"question2.quest_pct = round(question2.quest_pct, 5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.drop(['timestamp', 'content_type_id', 'question_id', 'part'], axis=1, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"validation = train.groupby('user_id').tail(5)\ntrain = train[~train.index.isin(validation.index)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results_u_val = train[['user_id','answered_correctly']].groupby(['user_id']).agg(['mean'])\nresults_u_val.columns = ['answered_correctly_user']\n\nresults_u2_val = train[['user_id','prior_question_had_explanation']].groupby(['user_id']).agg(['mean'])\nresults_u2_val.columns = ['explanation_mean_user']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train.groupby('user_id').tail(18)\ntrain = train[~train.index.isin(X.index)]\nlen(X) + len(train) + len(validation)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results_u_X = train[['user_id','answered_correctly']].groupby(['user_id']).agg(['mean'])\nresults_u_X.columns = ['answered_correctly_user']\n\nresults_u2_X = train[['user_id','prior_question_had_explanation']].groupby(['user_id']).agg(['mean'])\nresults_u2_X.columns = ['explanation_mean_user']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del(train)\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = pd.merge(X, group3, left_on=['task_container_id'], right_index= True, how=\"left\")\nX = pd.merge(X, results_u_X, on=['user_id'], how=\"left\")\nX = pd.merge(X, results_u2_X, on=['user_id'], how=\"left\")\n\nX = pd.merge(X, user_lecture_stats_part, on=['user_id'], how=\"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"validation = pd.merge(validation, group3, left_on=['task_container_id'], right_index= True, how=\"left\")\nvalidation = pd.merge(validation, results_u_val, on=['user_id'], how=\"left\")\nvalidation = pd.merge(validation, results_u2_val, on=['user_id'], how=\"left\")\n\nvalidation = pd.merge(validation, user_lecture_stats_part, on=['user_id'], how=\"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\n\nlb_make = LabelEncoder()\n\nX.prior_question_had_explanation.fillna(False, inplace = True)\nvalidation.prior_question_had_explanation.fillna(False, inplace = True)\n\nvalidation[\"prior_question_had_explanation_enc\"] = lb_make.fit_transform(validation[\"prior_question_had_explanation\"])\nX[\"prior_question_had_explanation_enc\"] = lb_make.fit_transform(X[\"prior_question_had_explanation\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"content_mean = question2.quest_pct.mean()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"question2.quest_pct = question2.quest_pct.mask((question2['count'] < 3), .65)\n\nquestion2.quest_pct = question2.quest_pct.mask((question2.quest_pct < .2) & (question2['count'] < 21), .2)\n\nquestion2.quest_pct = question2.quest_pct.mask((question2.quest_pct > .95) & (question2['count'] < 21), .95)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = pd.merge(X, question2, left_on = 'content_id', right_on = 'question_id', how = 'left')\nvalidation = pd.merge(validation, question2, left_on = 'content_id', right_on = 'question_id', how = 'left')\nX.part = X.part - 1\nvalidation.part = validation.part - 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = X['answered_correctly']\nX = X.drop(['answered_correctly'], axis=1)\n\ny_val = validation['answered_correctly']\nX_val = validation.drop(['answered_correctly'], axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = X[['answered_correctly_user', 'explanation_mean_user', 'quest_pct', 'avg_questions_seen',\n       'prior_question_elapsed_time','prior_question_had_explanation_enc', 'part',\n       'part_1', 'part_2', 'part_3', 'part_4', 'part_5', 'part_6', 'part_7',\n       'type_of_concept', 'type_of_intention', 'type_of_solving_question', 'type_of_starter',\n       'part_1_boolean', 'part_2_boolean', 'part_3_boolean', 'part_4_boolean', 'part_5_boolean', 'part_6_boolean', 'part_7_boolean',\n       'type_of_concept_boolean', 'type_of_intention_boolean', 'type_of_solving_question_boolean', 'type_of_starter_boolean']]\n\nX_val = X_val[['answered_correctly_user', 'explanation_mean_user', 'quest_pct', 'avg_questions_seen',\n               'prior_question_elapsed_time','prior_question_had_explanation_enc', 'part',\n               'part_1', 'part_2', 'part_3', 'part_4', 'part_5', 'part_6', 'part_7',\n               'type_of_concept', 'type_of_intention', 'type_of_solving_question', 'type_of_starter',\n               'part_1_boolean', 'part_2_boolean', 'part_3_boolean', 'part_4_boolean', 'part_5_boolean', 'part_6_boolean', 'part_7_boolean',\n               'type_of_concept_boolean', 'type_of_intention_boolean', 'type_of_solving_question_boolean', 'type_of_starter_boolean']]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X['answered_correctly_user'].fillna(0.65,  inplace=True)\nX['explanation_mean_user'].fillna(prior_mean_user,  inplace=True)\nX['quest_pct'].fillna(content_mean, inplace=True)\n\nX['part'].fillna(4, inplace = True)\nX['avg_questions_seen'].fillna(1, inplace = True)\nX['prior_question_elapsed_time'].fillna(elapsed_mean, inplace = True)\nX['prior_question_had_explanation_enc'].fillna(0, inplace = True)\n\nX['part_1'].fillna(0, inplace = True)\nX['part_2'].fillna(0, inplace = True)\nX['part_3'].fillna(0, inplace = True)\nX['part_4'].fillna(0, inplace = True)\nX['part_5'].fillna(0, inplace = True)\nX['part_6'].fillna(0, inplace = True)\nX['part_7'].fillna(0, inplace = True)\nX['type_of_concept'].fillna(0, inplace = True)\nX['type_of_intention'].fillna(0, inplace = True)\nX['type_of_solving_question'].fillna(0, inplace = True)\nX['type_of_starter'].fillna(0, inplace = True)\nX['part_1_boolean'].fillna(0, inplace = True)\nX['part_2_boolean'].fillna(0, inplace = True)\nX['part_3_boolean'].fillna(0, inplace = True)\nX['part_4_boolean'].fillna(0, inplace = True)\nX['part_5_boolean'].fillna(0, inplace = True)\nX['part_6_boolean'].fillna(0, inplace = True)\nX['part_7_boolean'].fillna(0, inplace = True)\nX['type_of_concept_boolean'].fillna(0, inplace = True)\nX['type_of_intention_boolean'].fillna(0, inplace = True)\nX['type_of_solving_question_boolean'].fillna(0, inplace = True)\nX['type_of_starter_boolean'].fillna(0, inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_val['answered_correctly_user'].fillna(0.65,  inplace=True)\nX_val['explanation_mean_user'].fillna(prior_mean_user,  inplace=True)\nX_val['quest_pct'].fillna(content_mean,  inplace=True)\n\nX_val['part'].fillna(4, inplace = True)\nX_val['avg_questions_seen'].fillna(1, inplace = True)\nX_val['prior_question_elapsed_time'].fillna(elapsed_mean, inplace = True)\nX_val['prior_question_had_explanation_enc'].fillna(0, inplace = True)\n\nX_val['part_1'].fillna(0, inplace = True)\nX_val['part_2'].fillna(0, inplace = True)\nX_val['part_3'].fillna(0, inplace = True)\nX_val['part_4'].fillna(0, inplace = True)\nX_val['part_5'].fillna(0, inplace = True)\nX_val['part_6'].fillna(0, inplace = True)\nX_val['part_7'].fillna(0, inplace = True)\nX_val['type_of_concept'].fillna(0, inplace = True)\nX_val['type_of_intention'].fillna(0, inplace = True)\nX_val['type_of_solving_question'].fillna(0, inplace = True)\nX_val['type_of_starter'].fillna(0, inplace = True)\nX_val['part_1_boolean'].fillna(0, inplace = True)\nX_val['part_2_boolean'].fillna(0, inplace = True)\nX_val['part_3_boolean'].fillna(0, inplace = True)\nX_val['part_4_boolean'].fillna(0, inplace = True)\nX_val['part_5_boolean'].fillna(0, inplace = True)\nX_val['part_6_boolean'].fillna(0, inplace = True)\nX_val['part_7_boolean'].fillna(0, inplace = True)\nX_val['type_of_concept_boolean'].fillna(0, inplace = True)\nX_val['type_of_intention_boolean'].fillna(0, inplace = True)\nX_val['type_of_solving_question_boolean'].fillna(0, inplace = True)\nX_val['type_of_starter_boolean'].fillna(0, inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def create_model():\n    model = tf.keras.Sequential(\n        [\n            tf.keras.layers.Input(29),\n            tf.keras.layers.BatchNormalization(),\n            tf.keras.layers.Dense(200, activation=\"relu\"),\n            tf.keras.layers.BatchNormalization(),\n            tf.keras.layers.Dropout(0.5),\n            tf.keras.layers.Dense(30, activation=\"relu\"),\n            tf.keras.layers.BatchNormalization(),\n            tf.keras.layers.Dropout(0.2),\n            tf.keras.layers.Dense(1, activation=\"sigmoid\")\n        ]\n    )\n    model.compile(optimizer='adam', loss=\"binary_crossentropy\", metrics=['accuracy'])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"res = pd.DataFrame()\nres['row_id'] = [i for i in range(6611282)]\nres.loc[:, ['answered_correctly']] = 0\nmodels = []\n\nfor n, (tr, te) in enumerate(KFold(n_splits=3, random_state=666, shuffle=True).split(y)):\n    print(f'Fold {n}')\n    \n    model = create_model()\n    \n    model.fit(\n        X.values[tr],\n        y.values[tr],\n        validation_split=0.2,\n        epochs=13, \n        batch_size=3072\n    )\n\n    res.loc[te, ['answered_correctly']] = model.predict(X.values[te])\n    models.append(model)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('NN score: ', roc_auc_score(y.values, res['answered_correctly'].values))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"iter_test = env.iter_test()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for (test_df, sample_prediction_df) in iter_test:\n    test_df['task_container_id'] = test_df.task_container_id.mask(test_df.task_container_id > 9999, 9999)\n    test_df = pd.merge(test_df, group3, left_on=['task_container_id'], right_index= True, how=\"left\")\n    test_df = pd.merge(test_df, question2, left_on = 'content_id', right_on = 'question_id', how = 'left')\n    test_df = pd.merge(test_df, results_u_final, on=['user_id'],  how=\"left\")\n    test_df = pd.merge(test_df, results_u2_final, on=['user_id'],  how=\"left\")\n    \n    test_df = pd.merge(test_df, user_lecture_stats_part, on=['user_id'], how=\"left\")\n    test_df['part_1'].fillna(0, inplace = True)\n    test_df['part_2'].fillna(0, inplace = True)\n    test_df['part_3'].fillna(0, inplace = True)\n    test_df['part_4'].fillna(0, inplace = True)\n    test_df['part_5'].fillna(0, inplace = True)\n    test_df['part_6'].fillna(0, inplace = True)\n    test_df['part_7'].fillna(0, inplace = True)\n    test_df['type_of_concept'].fillna(0, inplace = True)\n    test_df['type_of_intention'].fillna(0, inplace = True)\n    test_df['type_of_solving_question'].fillna(0, inplace = True)\n    test_df['type_of_starter'].fillna(0, inplace = True)\n    test_df['part_1_boolean'].fillna(0, inplace = True)\n    test_df['part_2_boolean'].fillna(0, inplace = True)\n    test_df['part_3_boolean'].fillna(0, inplace = True)\n    test_df['part_4_boolean'].fillna(0, inplace = True)\n    test_df['part_5_boolean'].fillna(0, inplace = True)\n    test_df['part_6_boolean'].fillna(0, inplace = True)\n    test_df['part_7_boolean'].fillna(0, inplace = True)\n    test_df['type_of_concept_boolean'].fillna(0, inplace = True)\n    test_df['type_of_intention_boolean'].fillna(0, inplace = True)\n    test_df['type_of_solving_question_boolean'].fillna(0, inplace = True)\n    test_df['type_of_starter_boolean'].fillna(0, inplace = True)\n    \n    test_df['answered_correctly_user'].fillna(0.65,  inplace=True)\n    test_df['explanation_mean_user'].fillna(prior_mean_user,  inplace=True)\n    test_df['quest_pct'].fillna(content_mean,  inplace=True)\n    test_df['part'] = test_df.part - 1\n\n    test_df['part'].fillna(4, inplace = True)\n    test_df['avg_questions_seen'].fillna(1, inplace = True)\n    test_df['prior_question_elapsed_time'].fillna(elapsed_mean, inplace = True)\n    test_df['prior_question_had_explanation'].fillna(False, inplace=True)\n    test_df[\"prior_question_had_explanation_enc\"] = lb_make.fit_transform(test_df[\"prior_question_had_explanation\"])\n    \n    X_test = test_df[['answered_correctly_user', 'explanation_mean_user', 'quest_pct', 'avg_questions_seen',\n                      'prior_question_elapsed_time','prior_question_had_explanation_enc', 'part',\n                      'part_1', 'part_2', 'part_3', 'part_4', 'part_5', 'part_6', 'part_7',\n                      'type_of_concept', 'type_of_intention', 'type_of_solving_question', 'type_of_starter',\n                      'part_1_boolean', 'part_2_boolean', 'part_3_boolean', 'part_4_boolean', 'part_5_boolean', 'part_6_boolean', 'part_7_boolean',\n                      'type_of_concept_boolean', 'type_of_intention_boolean', 'type_of_solving_question_boolean', 'type_of_starter_boolean']]\n    \n    preds = [model.predict(X_test) for model in models]\n    \n    predictions = preds[0]\n    for i in range(1, 3):\n        predictions += preds[i]\n    predictions /= 3\n    \n    test_df['answered_correctly'] =  predictions\n    env.predict(test_df.loc[test_df['content_type_id'] == 0, ['row_id', 'answered_correctly']])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}