{"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":"code","source":"import pandas as pd, numpy as np\nfrom catboost import CatBoostClassifier\nfrom sklearn.model_selection import GridSearchCV\nimport pickle\nimport sys","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:44.083092Z","iopub.execute_input":"2023-06-17T14:21:44.083847Z","iopub.status.idle":"2023-06-17T14:21:45.900043Z","shell.execute_reply.started":"2023-06-17T14:21:44.083801Z","shell.execute_reply":"2023-06-17T14:21:45.898878Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load Train Data and Labels","metadata":{"papermill":{"duration":0.004542,"end_time":"2023-02-07T00:59:59.189777","exception":false,"start_time":"2023-02-07T00:59:59.185235","status":"completed"},"tags":[]}},{"cell_type":"code","source":"dtypes = {\"session_id\": 'int64',\n          \"index\": np.int16,\n          \"elapsed_time\": np.int32,\n          \"event_name\": 'category',\n          \"name\": 'category',\n          \"level\": np.int8,\n          \"page\": np.float16,\n          \"room_coor_x\": np.float16,\n          \"room_coor_y\": np.float16,\n          \"screen_coor_x\": np.float16,\n          \"screen_coor_y\": np.float16,\n          \"hover_duration\": np.float32,\n          \"text\": 'category',\n          \"fqid\": 'category',\n          \"room_fqid\": 'category',\n          \"text_fqid\": 'category',\n          \"fullscreen\": np.int8,\n          \"hq\": np.int8,\n          \"music\": np.int8,\n          \"level_group\": 'category'\n          }\nuse_col = ['session_id', 'index', 'elapsed_time', 'event_name', 'name', 'level', 'page',\n           'room_coor_x', 'room_coor_y', 'hover_duration', 'text', 'fqid', 'room_fqid', 'text_fqid', 'level_group']","metadata":{"papermill":{"duration":59.284316,"end_time":"2023-02-07T01:00:58.478743","exception":false,"start_time":"2023-02-07T00:59:59.194427","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-06-17T14:21:45.903439Z","iopub.execute_input":"2023-06-17T14:21:45.903861Z","iopub.status.idle":"2023-06-17T14:21:45.913954Z","shell.execute_reply.started":"2023-06-17T14:21:45.903821Z","shell.execute_reply":"2023-06-17T14:21:45.912608Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"targets = pd.read_csv('/kaggle/input/predict-student-performance-from-game-play/train_labels.csv')\ntargets['session'] = targets.session_id.apply(lambda x: int(x.split('_')[0]) )\ntargets['q'] = targets.session_id.apply(lambda x: int(x.split('_')[-1][1:]) )\n# print( targets.shape )\n# targets.head()","metadata":{"papermill":{"duration":0.598155,"end_time":"2023-02-07T01:00:59.082015","exception":false,"start_time":"2023-02-07T01:00:58.48386","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-06-17T14:21:45.915853Z","iopub.execute_input":"2023-06-17T14:21:45.916536Z","iopub.status.idle":"2023-06-17T14:21:47.549187Z","shell.execute_reply.started":"2023-06-17T14:21:45.916485Z","shell.execute_reply":"2023-06-17T14:21:47.547672Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"feature_df = pd.read_csv('/kaggle/input/featur/feature_sort.csv')","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.555020Z","iopub.execute_input":"2023-06-17T14:21:47.555419Z","iopub.status.idle":"2023-06-17T14:21:47.729726Z","shell.execute_reply.started":"2023-06-17T14:21:47.555381Z","shell.execute_reply":"2023-06-17T14:21:47.728395Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature Engineer","metadata":{"papermill":{"duration":0.005196,"end_time":"2023-02-07T01:00:59.092865","exception":false,"start_time":"2023-02-07T01:00:59.087669","status":"completed"},"tags":[]}},{"cell_type":"code","source":"def delt_time_def(df):\n    df.sort_values(by=['session_id', 'elapsed_time'], inplace=True)\n    df['d_time'] = df['elapsed_time'].diff(1)\n    df['d_time'].fillna(0, inplace=True)\n    df['delt_time'] = df['d_time'].clip(0, 103000)\n    df['delt_time_next'] = df['delt_time'].shift(-1)\n    return df","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.731221Z","iopub.execute_input":"2023-06-17T14:21:47.731658Z","iopub.status.idle":"2023-06-17T14:21:47.742997Z","shell.execute_reply.started":"2023-06-17T14:21:47.731620Z","shell.execute_reply":"2023-06-17T14:21:47.738524Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def feature_engineer(train, kol_f):\n    global kol_col, kol_col_max\n    kol_col = 9\n    kol_col_max = 11+kol_f*2\n    col = [i for i in range(0,kol_col_max)]\n    new_train = pd.DataFrame(index=train['session_id'].unique(), columns=col, dtype=np.float16)  \n    new_train[10] = new_train.index # \"session_id\"    \n\n    new_train[0] = train.groupby(['session_id'])['d_time'].quantile(q=0.3)\n    new_train[1] = train.groupby(['session_id'])['d_time'].quantile(q=0.8)\n    new_train[2] = train.groupby(['session_id'])['d_time'].quantile(q=0.5)\n    new_train[3] = train.groupby(['session_id'])['d_time'].quantile(q=0.65)\n    new_train[4] = train.groupby(['session_id'])['hover_duration'].agg('mean')\n    new_train[5] = train.groupby(['session_id'])['hover_duration'].agg('std')    \n    new_train[6] = new_train[10].apply(lambda x: int(str(x)[:2])).astype(np.uint8) # \"year\"\n    new_train[7] = new_train[10].apply(lambda x: int(str(x)[2:4])+1).astype(np.uint8) # \"month\"\n    new_train[8] = new_train[10].apply(lambda x: int(str(x)[4:6])).astype(np.uint8) # \"day\"\n    new_train[9] = new_train[10].apply(lambda x: int(str(x)[6:8])).astype(np.uint8) + new_train[10].apply(lambda x: int(str(x)[8:10])).astype(np.uint8)/60\n    new_train[10] = 0\n    new_train = new_train.fillna(-1)\n    \n    return new_train","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.744917Z","iopub.execute_input":"2023-06-17T14:21:47.745313Z","iopub.status.idle":"2023-06-17T14:21:47.765266Z","shell.execute_reply.started":"2023-06-17T14:21:47.745261Z","shell.execute_reply":"2023-06-17T14:21:47.764063Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def feature_next_t(row_f, new_train, train, gran_1, gran_2, i):\n    global kol_col\n    kol_col +=1\n    col1 = row_f['col1']\n    val1 = row_f['val1']\n    maska = (train[col1] == val1)\n    if row_f['kol_col'] == 1:       \n        new_train[kol_col] = train[maska].groupby(['session_id'])['delt_time_next'].sum()\n        if gran_1:\n            kol_col +=1\n            new_train[kol_col] = train[maska].groupby(['session_id'])['delt_time'].mean()\n        if gran_2:\n            kol_col +=1\n            new_train[kol_col] = train[maska].groupby(['session_id'])['index'].count()          \n    elif row_f['kol_col'] == 2: \n        col2 = row_f['col2']\n        val2 = row_f['val2']\n        maska = maska & (train[col2] == val2)        \n        new_train[kol_col] = train[maska].groupby(['session_id'])['delt_time_next'].sum()\n        if gran_1:\n            kol_col +=1\n            new_train[kol_col] = train[maska].groupby(['session_id'])['delt_time'].mean()\n        if gran_2:\n            kol_col +=1\n            new_train[kol_col] = train[maska].groupby(['session_id'])['index'].count()\n    return new_train","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.767175Z","iopub.execute_input":"2023-06-17T14:21:47.767568Z","iopub.status.idle":"2023-06-17T14:21:47.786872Z","shell.execute_reply.started":"2023-06-17T14:21:47.767532Z","shell.execute_reply":"2023-06-17T14:21:47.785308Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def feature_next_t_otvet(row_f, new_train, train, gran_1, gran_2, i):\n    global kol_col\n    kol_col +=1\n    col1 = row_f['col1']\n    val1 = row_f['val1']\n    maska = (train[col1] == val1)\n    if row_f['kol_col'] == 1:      \n        new_train[kol_col] = train[maska]['delt_time_next'].sum()\n        if gran_1:\n            kol_col +=1\n            new_train[kol_col] = train[maska]['delt_time'].mean()\n        if gran_2:\n            kol_col +=1\n            new_train[kol_col] = train[maska]['index'].count()          \n    elif row_f['kol_col'] == 2: \n        col2 = row_f['col2']\n        val2 = row_f['val2']\n        maska = maska & (train[col2] == val2)        \n        new_train[kol_col] = train[maska]['delt_time_next'].sum()\n        if gran_1:\n            kol_col +=1\n            new_train[kol_col] = train[maska]['delt_time'].mean()\n        if gran_2:\n            kol_col +=1\n            new_train[kol_col] = train[maska]['index'].count()\n    return new_train","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.788902Z","iopub.execute_input":"2023-06-17T14:21:47.789307Z","iopub.status.idle":"2023-06-17T14:21:47.802758Z","shell.execute_reply.started":"2023-06-17T14:21:47.789268Z","shell.execute_reply":"2023-06-17T14:21:47.801569Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def experiment_feature_next_t_otvet(row_f, new_train, train, gran_1, gran_2, i):\n    global kol_col\n    kol_col +=1\n    if row_f['kol_col'] == 1: \n        maska = train[row_f['col1']] == row_f['val1']\n        new_train[kol_col] = train[maska]['delt_time_next'].sum()\n        if gran_1:\n            kol_col +=1\n            new_train[kol_col] = train[maska]['delt_time'].mean()\n        if gran_2:\n            kol_col +=1\n            new_train[kol_col] = train[maska]['index'].count()          \n    elif row_f['kol_col'] == 2: \n        col2 = row_f['col2']\n        val2 = row_f['val2']\n        maska = (train[col1] == val1) & (train[col2] == val2)        \n        new_train[kol_col] = train[maska]['delt_time_next'].sum()\n        if gran_1:\n            kol_col +=1\n            new_train[kol_col] = train[maska]['delt_time'].mean()\n        if gran_2:\n            kol_col +=1\n            new_train[kol_col] = train[maska]['index'].count()\n    return new_train","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.804616Z","iopub.execute_input":"2023-06-17T14:21:47.804987Z","iopub.status.idle":"2023-06-17T14:21:47.821323Z","shell.execute_reply.started":"2023-06-17T14:21:47.804954Z","shell.execute_reply":"2023-06-17T14:21:47.819635Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def feature_quest_otvet(new_train, train, quest, kol_f):\n    global kol_col\n    kol_col = 9\n    g1 = 0.7 \n    g2 = 0.3 \n\n    feature_q = feature_df[feature_df['quest'] == quest].copy()\n    feature_q.reset_index(drop=True, inplace=True)\n    \n    gran1 = round(kol_f * g1)\n    gran2 = round(kol_f * g2)    \n    for i in range(0, kol_f):         \n        row_f = feature_q.loc[i]\n        new_train = feature_next_t_otvet(row_f, new_train, train, i < gran1, i <  gran2, i) \n    col = [i for i in range(0,kol_col+1)]\n    return new_train[col]","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.825521Z","iopub.execute_input":"2023-06-17T14:21:47.825952Z","iopub.status.idle":"2023-06-17T14:21:47.835924Z","shell.execute_reply.started":"2023-06-17T14:21:47.825903Z","shell.execute_reply":"2023-06-17T14:21:47.834618Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def feature_engineer_new(new_train, train, feature_q, kol_f):\n    g1 = 0.7 \n    g2 = 0.3 \n    gran1 = round(kol_f * g1)\n    gran2 = round(kol_f * g2)    \n    for i in range(0, kol_f): \n        row_f = feature_q.loc[i]       \n        new_train = feature_next_t(row_f, new_train, train, i < gran1, i <  gran2, i)         \n    return new_train","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.837625Z","iopub.execute_input":"2023-06-17T14:21:47.838051Z","iopub.status.idle":"2023-06-17T14:21:47.852839Z","shell.execute_reply.started":"2023-06-17T14:21:47.838012Z","shell.execute_reply":"2023-06-17T14:21:47.851434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def feature_quest(new_train, train, quest, kol_f):\n    global kol_col\n    kol_col = 9\n    feature_q = feature_df[feature_df['quest'] == quest].copy()\n    feature_q.reset_index(drop=True, inplace=True)\n    new_train = feature_engineer_new(new_train, train, feature_q, kol_f)\n    col = [i for i in range(0,kol_col+1)]\n    return new_train[col]","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.854921Z","iopub.execute_input":"2023-06-17T14:21:47.855310Z","iopub.status.idle":"2023-06-17T14:21:47.866799Z","shell.execute_reply.started":"2023-06-17T14:21:47.855271Z","shell.execute_reply":"2023-06-17T14:21:47.865359Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"models = {}\nbest_threshold = 0.63","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.871568Z","iopub.execute_input":"2023-06-17T14:21:47.872025Z","iopub.status.idle":"2023-06-17T14:21:47.881198Z","shell.execute_reply.started":"2023-06-17T14:21:47.871979Z","shell.execute_reply":"2023-06-17T14:21:47.879649Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"list_kol_f = {\n    1:140,3:110,\n    4:110, 5:220, 6:120, 7:110, 8:110, 9:100, 10:120, 11:120,\n    14: 110, 15:160, 16:105, 17:140             \n             }","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:21:47.883270Z","iopub.execute_input":"2023-06-17T14:21:47.884120Z","iopub.status.idle":"2023-06-17T14:21:47.893311Z","shell.execute_reply.started":"2023-06-17T14:21:47.884070Z","shell.execute_reply":"2023-06-17T14:21:47.891974Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Searching for Best Parameters","metadata":{}},{"cell_type":"code","source":"# df0_4 = pd.read_csv('/kaggle/input/featur/train_0_4t.csv', dtype=dtypes) \n# kol_lvl = (df0_4 .groupby(['session_id'])['level'].agg('nunique') < 5)\n# list_session = kol_lvl[kol_lvl].index\n# df0_4  = df0_4 [~df0_4 ['session_id'].isin(list_session)]\n# df0_4 = delt_time_def(df0_4)\n\n# quests_0_4 = [1, 3] \n# # list_kol_f = {1:140,3:110}\n\n# kol_quest = len(quests_0_4)\n# # ITERATE THRU QUESTIONS\n# for q in quests_0_4:\n#     print('### quest ', q, end='')\n#     new_train = feature_engineer(df0_4, list_kol_f[q])\n#     train_x = feature_quest(new_train, df0_4, q, list_kol_f[q])\n#     print (' ---- ', 'train_q.shape = ', train_x.shape)\n\n#     # TRAIN DATA\n#     train_users = train_x.index.values\n#     train_y = targets.loc[targets.q==q].set_index('session').loc[train_users]\n\n#     # TRAIN MODEL \n\n#     CBC = CatBoostClassifier()\n#     parameters = {'depth'        : [4,5,6,7,8],\n#                   'learning_rate': [0.03,0.04,0.05],\n#                   'iterations'   : [10,20,30,40,50,60]}\n#     model = GridSearchCV(estimator=CBC, param_grid = parameters, cv = 2, n_jobs=-1)\n\n#     model.fit(train_x.astype('float32'), train_y['correct'], verbose=False)\n# del df0_4","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:22:00.080063Z","iopub.execute_input":"2023-06-17T14:22:00.080481Z","iopub.status.idle":"2023-06-17T14:22:00.086440Z","shell.execute_reply.started":"2023-06-17T14:22:00.080443Z","shell.execute_reply":"2023-06-17T14:22:00.085492Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# print(\" Results from Grid Search \" )\n# print(\"\\n The best estimator across ALL searched params:\\n\",model.best_estimator_)\n# print(\"\\n The best score across ALL searched params:\\n\",model.best_score_)\n# print(\"\\n The best parameters across ALL searched params:\\n\",model.best_params_)","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:22:00.885551Z","iopub.execute_input":"2023-06-17T14:22:00.886302Z","iopub.status.idle":"2023-06-17T14:22:00.891012Z","shell.execute_reply.started":"2023-06-17T14:22:00.886257Z","shell.execute_reply":"2023-06-17T14:22:00.889831Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df5_12 = pd.read_csv('/kaggle/input/featur/train_5_12t.csv', dtype=dtypes)\n# kol_lvl = (df5_12.groupby(['session_id'])['level'].agg('nunique') < 8)\n# list_session = kol_lvl[kol_lvl].index\n# df5_12 = df5_12[~df5_12['session_id'].isin(list_session)]\n# df5_12 = delt_time_def(df5_12)\n# quests_5_12 = [4, 5, 6, 7, 8, 9, 10, 11] \n\n# # list_kol_f = {4:110, 5:220, 6:120, 7:110, 8:110, 9:100, 10:120, 11:120}\n\n# kol_quest = len(quests_5_12)\n# # ITERATE THRU QUESTIONS\n# for q in quests_5_12:\n#     print('### quest ', q, end='')\n#     new_train = feature_engineer(df5_12, list_kol_f[q])\n#     train_x = feature_quest(new_train, df5_12, q, list_kol_f[q])\n#     print (' ---- ', 'train_q.shape = ', train_x.shape)\n\n#     # TRAIN DATA\n#     train_users = train_x.index.values\n#     train_y = targets.loc[targets.q==q].set_index('session').loc[train_users]\n\n#     # TRAIN MODEL \n\n#     CBC = CatBoostClassifier()\n#     parameters = {'depth'        : [4,5,6,7,8],\n#                   'learning_rate': [0.03,0.04,0.05],\n#                   'iterations'   : [10,20,30,40,50,60]}\n#     model = GridSearchCV(estimator=CBC, param_grid = parameters, cv = 2, n_jobs=-1)\n\n#     model.fit(train_x.astype('float32'), train_y['correct'], verbose=False)\n# del df5_12","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:22:01.256591Z","iopub.execute_input":"2023-06-17T14:22:01.257277Z","iopub.status.idle":"2023-06-17T14:22:01.262926Z","shell.execute_reply.started":"2023-06-17T14:22:01.257238Z","shell.execute_reply":"2023-06-17T14:22:01.261888Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# print(\" Results from Grid Search \" )\n# print(\"\\n The best estimator across ALL searched params:\\n\",model.best_estimator_)\n# print(\"\\n The best score across ALL searched params:\\n\",model.best_score_)\n# print(\"\\n The best parameters across ALL searched params:\\n\",model.best_params_)","metadata":{"execution":{"iopub.status.busy":"2023-06-17T10:52:42.119920Z","iopub.execute_input":"2023-06-17T10:52:42.120266Z","iopub.status.idle":"2023-06-17T10:52:42.127904Z","shell.execute_reply.started":"2023-06-17T10:52:42.120216Z","shell.execute_reply":"2023-06-17T10:52:42.126293Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df13_22 = pd.read_csv('/kaggle/input/featur/train_13_22t.csv', dtype=dtypes) \n# kol_lvl = (df13_22 .groupby(['session_id'])['level'].agg('nunique') < 10)\n# list_session = kol_lvl[kol_lvl].index\n# df13_22  = df13_22 [~df13_22 ['session_id'].isin(list_session)]\n# df13_22 = delt_time_def(df13_22)\n\n# quests_13_22 = [14, 15, 16, 17] \n# # list_kol_f = {14: 110, 15:160, 16:105, 17:140}\n\n# kol_quest = len(quests_13_22)\n# # ITERATE THRU QUESTIONS\n# for q in quests_13_22:\n#     print('### quest ', q, end='')\n#     new_train = feature_engineer(df13_22, list_kol_f[q])\n#     train_x = feature_quest(new_train, df13_22, q, list_kol_f[q])\n#     print (' ---- ', 'train_q.shape = ', train_x.shape)\n\n#     # TRAIN DATA\n#     train_users = train_x.index.values\n#     train_y = targets.loc[targets.q==q].set_index('session').loc[train_users]\n\n#     # TRAIN MODEL \n\n#     CBC = CatBoostClassifier()\n#     parameters = {'depth'        : [4,5,6,7,8],\n#                   'learning_rate': [0.03,0.04,0.05],\n#                   'iterations'   : [10,20,30,40,50,60]}\n#     model = GridSearchCV(estimator=CBC, param_grid = parameters, cv = 2, n_jobs=-1)\n\n#     model.fit(train_x.astype('float32'), train_y['correct'], verbose=False)\n# del df13_22","metadata":{"execution":{"iopub.status.busy":"2023-06-17T10:52:42.129123Z","iopub.execute_input":"2023-06-17T10:52:42.129658Z","iopub.status.idle":"2023-06-17T11:31:56.621067Z","shell.execute_reply.started":"2023-06-17T10:52:42.129625Z","shell.execute_reply":"2023-06-17T11:31:56.619837Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Overall Best Parameters","metadata":{}},{"cell_type":"markdown","source":" Results from Grid Search \n\n The best estimator across ALL searched params:\n <catboost.core.CatBoostClassifier object at 0x7ceba810ec10>\n\n The best score across ALL searched params:\n 0.6887235708692248\n\n The best parameters across ALL searched params:\n {'depth': 7, 'iterations': 60, 'learning_rate': 0.05}","metadata":{}},{"cell_type":"code","source":"# print(\" Results from Grid Search \" )\n# print(\"\\n The best estimator across ALL searched params:\\n\",model.best_estimator_)\n# print(\"\\n The best score across ALL searched params:\\n\",model.best_score_)\n# print(\"\\n The best parameters across ALL searched params:\\n\",model.best_params_)","metadata":{"execution":{"iopub.status.busy":"2023-06-17T11:31:56.623786Z","iopub.execute_input":"2023-06-17T11:31:56.624193Z","iopub.status.idle":"2023-06-17T11:31:56.635315Z","shell.execute_reply.started":"2023-06-17T11:31:56.624157Z","shell.execute_reply":"2023-06-17T11:31:56.630600Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Create model with best parameters","metadata":{}},{"cell_type":"code","source":"Depth = 7\nlr = 0.05\nIter = 60\ndef create_model(old_train, quests, models, list_kol_f):\n    \n    kol_quest = len(quests)\n    # ITERATE THRU QUESTIONS\n    for q in quests:\n        print('### quest ', q, end='')\n        new_train = feature_engineer(old_train, list_kol_f[q])\n        train_x = feature_quest(new_train, old_train, q, list_kol_f[q])\n        print (' ---- ', 'train_q.shape = ', train_x.shape)\n           \n        # TRAIN DATA\n        train_users = train_x.index.values\n        train_y = targets.loc[targets.q==q].set_index('session').loc[train_users]\n\n        # TRAIN MODEL \n\n        #model = CatBoostClassifier(\n        #    n_estimators = 300,\n        #    learning_rate= 0.045,\n        #    depth = 6\n        #)\n        \n#         model = CatBoostClassifier(\n#             n_estimators = 300,\n#             learning_rate= 0.045,\n#             depth = 5\n#         )\n        model = CatBoostClassifier(depth=Depth, learning_rate=lr, iterations=Iter)\n        \n        model.fit(train_x.astype('float32'), train_y['correct'], verbose=False)\n\n        # SAVE MODEL, PREDICT VALID OOF\n        models[f'{q}'] = model\n    print('***')\n    \n    return models","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:22:08.879178Z","iopub.execute_input":"2023-06-17T14:22:08.879885Z","iopub.status.idle":"2023-06-17T14:22:08.890469Z","shell.execute_reply.started":"2023-06-17T14:22:08.879831Z","shell.execute_reply":"2023-06-17T14:22:08.889439Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"models = {}\nbest_threshold = 0.63\n\n#score0.7\nlist_kol_f = {\n    1:140,3:110,\n    4:120, 5:220, 6:130, 7:110, 8:110, 9:100, 10:140, 11:120,\n    14: 160, 15:160, 16:130, 17:140             \n             }","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:22:09.789078Z","iopub.execute_input":"2023-06-17T14:22:09.789857Z","iopub.status.idle":"2023-06-17T14:22:09.798003Z","shell.execute_reply.started":"2023-06-17T14:22:09.789810Z","shell.execute_reply":"2023-06-17T14:22:09.796322Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df0_4 = pd.read_csv('/kaggle/input/featur/train_0_4t.csv', dtype=dtypes) \nkol_lvl = (df0_4 .groupby(['session_id'])['level'].agg('nunique') < 5)\nlist_session = kol_lvl[kol_lvl].index\ndf0_4  = df0_4 [~df0_4 ['session_id'].isin(list_session)]\ndf0_4 = delt_time_def(df0_4)\n\nquests_0_4 = [1, 3] \n# list_kol_f = {1:140,3:110}\n\nmodels = create_model(df0_4, quests_0_4, models, list_kol_f)\ndel df0_4","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:22:10.385565Z","iopub.execute_input":"2023-06-17T14:22:10.385988Z","iopub.status.idle":"2023-06-17T14:23:07.305414Z","shell.execute_reply.started":"2023-06-17T14:22:10.385948Z","shell.execute_reply":"2023-06-17T14:23:07.304182Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df5_12 = pd.read_csv('/kaggle/input/featur/train_5_12t.csv', dtype=dtypes)\nkol_lvl = (df5_12.groupby(['session_id'])['level'].agg('nunique') < 8)\nlist_session = kol_lvl[kol_lvl].index\ndf5_12 = df5_12[~df5_12['session_id'].isin(list_session)]\ndf5_12 = delt_time_def(df5_12)\nquests_5_12 = [4, 5, 6, 7, 8, 9, 10, 11] \n\n# list_kol_f = {4:110, 5:220, 6:120, 7:110, 8:110, 9:100, 10:120, 11:120}\n\nmodels = create_model(df5_12, quests_5_12, models, list_kol_f)\ndel df5_12","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:23:07.307283Z","iopub.execute_input":"2023-06-17T14:23:07.307638Z","iopub.status.idle":"2023-06-17T14:28:50.423384Z","shell.execute_reply.started":"2023-06-17T14:23:07.307604Z","shell.execute_reply":"2023-06-17T14:28:50.422103Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df13_22 = pd.read_csv('/kaggle/input/featur/train_13_22t.csv', dtype=dtypes) \nkol_lvl = (df13_22 .groupby(['session_id'])['level'].agg('nunique') < 10)\nlist_session = kol_lvl[kol_lvl].index\ndf13_22  = df13_22 [~df13_22 ['session_id'].isin(list_session)]\ndf13_22 = delt_time_def(df13_22)\n\nquests_13_22 = [14, 15, 16, 17] \n# list_kol_f = {14: 110, 15:160, 16:105, 17:140}\n\nmodels = create_model(df13_22, quests_13_22, models, list_kol_f)\ndel df13_22 ","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:28:50.424897Z","iopub.execute_input":"2023-06-17T14:28:50.425244Z","iopub.status.idle":"2023-06-17T14:32:55.123050Z","shell.execute_reply.started":"2023-06-17T14:28:50.425211Z","shell.execute_reply":"2023-06-17T14:32:55.121782Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Infer Test Data**","metadata":{}},{"cell_type":"code","source":"import jo_wilder\n\ntry:\n    jo_wilder.make_env.__called__ = False\n    env.__called__ = False\n    type(env)._state = type(type(env)._state).__dict__['INIT']\nexcept:\n    pass\n\nenv = jo_wilder.make_env()\niter_test = env.iter_test()    ","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:40:45.371930Z","iopub.execute_input":"2023-06-17T14:40:45.374978Z","iopub.status.idle":"2023-06-17T14:40:45.387795Z","shell.execute_reply.started":"2023-06-17T14:40:45.374889Z","shell.execute_reply":"2023-06-17T14:40:45.386022Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import time","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:40:46.214867Z","iopub.execute_input":"2023-06-17T14:40:46.215297Z","iopub.status.idle":"2023-06-17T14:40:46.221254Z","shell.execute_reply.started":"2023-06-17T14:40:46.215258Z","shell.execute_reply":"2023-06-17T14:40:46.219974Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"g_end4 = 0\ng_end5 = 0\n\nlist_q = {'0-4':quests_0_4, '5-12':quests_5_12, '13-22':quests_13_22}\nfor (test, sam_sub) in iter_test:\n    sam_sub['question'] = [int(label.split('_')[1][1:]) for label in sam_sub['session_id']]    \n    grp = test.level_group.values[0]   \n    sam_sub['correct'] = 1\n    sam_sub.loc[sam_sub.question.isin([5, 8, 10, 13, 15]), 'correct'] = 0  \n    old_train = delt_time_def(test[test.level_group == grp])\n       \n    for q in list_q[grp]:\n        \n        start4 = time.time()\n        new_train = feature_engineer(old_train, list_kol_f[q])\n        new_train = feature_quest_otvet(new_train, old_train, q, list_kol_f[q])\n#       new_train = feature_quest(new_train, old_train, q, kol_f)\n        \n        end4 = time.time() - start4\n        g_end4 += end4\n        \n        start5 = time.time()        \n        \n        clf = models[f'{q}']\n        p = clf.predict_proba(new_train.astype('float32'))[:,1]        \n        \n        end5 = time.time() - start5\n        g_end5 += end5\n             \n        \n        mask = sam_sub.question == q \n        x = int(p[0]>best_threshold)\n        sam_sub.loc[mask,'correct'] = x      \n        \n        \n    sam_sub = sam_sub[['session_id', 'correct']]      \n    env.predict(sam_sub)","metadata":{"execution":{"iopub.status.busy":"2023-06-17T14:40:46.582653Z","iopub.execute_input":"2023-06-17T14:40:46.583465Z","iopub.status.idle":"2023-06-17T14:40:59.445011Z","shell.execute_reply.started":"2023-06-17T14:40:46.583415Z","shell.execute_reply":"2023-06-17T14:40:59.443530Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# EDA submission.csv","metadata":{"papermill":{"duration":0.011427,"end_time":"2023-02-07T01:02:45.502331","exception":false,"start_time":"2023-02-07T01:02:45.490904","status":"completed"},"tags":[]}},{"cell_type":"code","source":"df = pd.read_csv('submission.csv')\nprint( df.shape )\ndf.head(60)","metadata":{"papermill":{"duration":0.027432,"end_time":"2023-02-07T01:02:45.541022","exception":false,"start_time":"2023-02-07T01:02:45.51359","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-06-17T14:40:59.450350Z","iopub.execute_input":"2023-06-17T14:40:59.450775Z","iopub.status.idle":"2023-06-17T14:40:59.488739Z","shell.execute_reply.started":"2023-06-17T14:40:59.450735Z","shell.execute_reply":"2023-06-17T14:40:59.487592Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}