{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30635,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import polars as pl\nimport numpy as np\nimport pandas as pd\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_auc_score \nfrom datetime import datetime\n\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:56:21.825044Z","iopub.execute_input":"2024-03-15T13:56:21.825457Z","iopub.status.idle":"2024-03-15T13:56:21.830764Z","shell.execute_reply.started":"2024-03-15T13:56:21.825425Z","shell.execute_reply":"2024-03-15T13:56:21.829581Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def set_table_dtypes(df: pl.DataFrame) -> pl.DataFrame:\n    # implement here all desired dtypes for tables\n    # the following is just an example\n    for col in df.columns:\n        # last letter of column name will help you determine the type\n        if col[-1] in (\"P\", \"A\"):\n            df = df.with_columns(pl.col(col).cast(pl.Float64).alias(col))\n\n    return df\n\ndef convert_strings(df: pd.DataFrame) -> pd.DataFrame:\n    for col in df.columns:  \n        if df[col].dtype.name in ['object', 'string']:\n            df[col] = df[col].astype(\"string\").astype('category')\n            current_categories = df[col].cat.categories\n            new_categories = current_categories.to_list() + [\"Unknown\"]\n            new_dtype = pd.CategoricalDtype(categories=new_categories, ordered=True)\n            df[col] = df[col].astype(new_dtype)\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:30:43.838988Z","iopub.execute_input":"2024-03-15T13:30:43.839414Z","iopub.status.idle":"2024-03-15T13:30:43.848649Z","shell.execute_reply.started":"2024-03-15T13:30:43.839374Z","shell.execute_reply":"2024-03-15T13:30:43.846607Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_basetable = pl.read_csv(dataPath + \"csv_files/train/train_base.csv\")\ntrain_static = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/train/train_static_0_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/train/train_static_0_1.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntrain_static_cb = pl.read_csv(dataPath + \"csv_files/train/train_static_cb_0.csv\").pipe(set_table_dtypes)\ntrain_person_1 = pl.read_csv(dataPath + \"csv_files/train/train_person_1.csv\").pipe(set_table_dtypes) \ntrain_person_2 = pl.read_csv(dataPath + \"csv_files/train/train_person_2.csv\").pipe(set_table_dtypes) \ntrain_other = pl.read_csv(dataPath + \"csv_files/train/train_other_1.csv\").pipe(set_table_dtypes) \ntrain_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/train/train_credit_bureau_b_2.csv\").pipe(set_table_dtypes) ","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:30:43.850372Z","iopub.execute_input":"2024-03-15T13:30:43.851143Z","iopub.status.idle":"2024-03-15T13:31:01.468640Z","shell.execute_reply.started":"2024-03-15T13:30:43.851100Z","shell.execute_reply":"2024-03-15T13:31:01.467742Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_basetable = pl.read_csv(dataPath + \"csv_files/test/test_base.csv\")\ntest_static = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_1.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_2.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntest_static_cb = pl.read_csv(dataPath + \"csv_files/test/test_static_cb_0.csv\").pipe(set_table_dtypes)\ntest_person_1 = pl.read_csv(dataPath + \"csv_files/test/test_person_1.csv\").pipe(set_table_dtypes) \ntest_person_2 = pl.read_csv(dataPath + \"csv_files/test/test_person_2.csv\").pipe(set_table_dtypes) \ntest_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/test/test_credit_bureau_b_2.csv\").pipe(set_table_dtypes) ","metadata":{"execution":{"iopub.status.busy":"2024-03-15T15:05:38.506818Z","iopub.execute_input":"2024-03-15T15:05:38.507293Z","iopub.status.idle":"2024-03-15T15:05:38.561486Z","shell.execute_reply.started":"2024-03-15T15:05:38.507256Z","shell.execute_reply":"2024-03-15T15:05:38.560333Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Feature engineering\n\nIn this part, we can see a simple example of joining tables via `case_id`. Here the loading and joining is done with polars library. Polars library is blazingly fast and has much smaller memory footprint than pandas. ","metadata":{}},{"cell_type":"markdown","source":"**добавила еще несколько признаков:**\n- age,\n- education\n- cnt_days_employed_from_date (from employed_from_date)\n- empl_industry\n- familystate\n- language\n- sex\n- empl_economical_stat\n- addres_district","metadata":{}},{"cell_type":"code","source":"# We need to use aggregation functions in tables with depth > 1, so tables that contain num_group1 column or \n# also num_group2 column.\ntrain_person_1_feats_1 = train_person_1.group_by(\"case_id\").agg(\n    pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n    (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\n# Here num_group1=0 has special meaning, it is the person who applied for the loan.\ntrain_person_1_feats_2 = (\n    train_person_1\n    .select([\"case_id\", \"num_group1\", \"housetype_905L\", 'birth_259D', 'education_927M', 'empl_employedfrom_271D', 'empl_industry_691L', 'familystate_447L', 'incometype_1044T', 'language1_981M', 'sex_738L'])\n    .filter(pl.col(\"num_group1\") == 0)\n    .drop(\"num_group1\")\n    .rename({\"housetype_905L\": \"person_housetype\", 'birth_259D': 'birth_date', 'education_927M': 'education', 'empl_employedfrom_271D': 'employed_from_date', 'empl_industry_691L': 'empl_industry', 'familystate_447L': 'familystate', 'incometype_1044T': 'incometype', 'language1_981M': 'language', 'sex_738L': 'sex'})\n)\n\ntrain_person_2_feats = (\n    train_person_2\n    .select([\"case_id\", \"num_group1\", \"empls_economicalst_849M\", \"addres_district_368M\"])\n    .filter(pl.col(\"num_group1\") == 0)\n    .drop(\"num_group1\")\n    .rename({'empls_economicalst_849M': 'empl_economical_stat', 'addres_district_368M': 'addres_district'})\n)\n\n# Here we have num_goup1 and num_group2, so we need to aggregate again.\ntrain_credit_bureau_b_2_feats = train_credit_bureau_b_2.group_by(\"case_id\").agg(\n    pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n    (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\")\n)\n\n# We will process in this examples only A-type and M-type columns, so we need to select them.\nselected_static_cols = []\nfor col in train_static.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cols.append(col)\nprint(selected_static_cols)\n\nselected_static_cb_cols = []\nfor col in train_static_cb.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cb_cols.append(col)\nprint(selected_static_cb_cols)\n\n# Join all tables together.\ndata = train_basetable.join(\n    train_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_2, how=\"left\", on=\"case_id\"\n).join(\n    train_person_2_feats, how=\"left\", on=\"case_id\"\n).join(\n    train_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:37:49.593241Z","iopub.execute_input":"2024-03-15T13:37:49.593714Z","iopub.status.idle":"2024-03-15T13:37:52.939564Z","shell.execute_reply.started":"2024-03-15T13:37:49.593673Z","shell.execute_reply":"2024-03-15T13:37:52.938474Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_person_1_feats_1 = test_person_1.group_by(\"case_id\").agg(\n    pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n    (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\ntest_person_1_feats_2 = (\n    test_person_1\n    .select([\"case_id\", \"num_group1\", \"housetype_905L\", 'birth_259D', 'education_927M', 'empl_employedfrom_271D', 'empl_industry_691L', 'familystate_447L', 'incometype_1044T', 'language1_981M', 'sex_738L'])\n    .filter(pl.col(\"num_group1\") == 0)\n    .drop(\"num_group1\")\n    .rename({\"housetype_905L\": \"person_housetype\", 'birth_259D': 'birth_date', 'education_927M': 'education', 'empl_employedfrom_271D': 'employed_from_date', 'empl_industry_691L': 'empl_industry', 'familystate_447L': 'familystate', 'incometype_1044T': 'incometype', 'language1_981M': 'language', 'sex_738L': 'sex'})\n)\n\ntest_person_2_feats = (\n    test_person_2\n    .select([\"case_id\", \"num_group1\", \"empls_economicalst_849M\", \"addres_district_368M\"])\n    .filter(pl.col(\"num_group1\") == 0)\n    .drop(\"num_group1\")\n    .rename({'empls_economicalst_849M': 'empl_economical_stat', 'addres_district_368M': 'addres_district'})\n)\n\ntest_credit_bureau_b_2_feats = test_credit_bureau_b_2.group_by(\"case_id\").agg(\n    pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n    (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\")\n)\n\ndata_submission = test_basetable.join(\n    test_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    test_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_2, how=\"left\", on=\"case_id\"\n).join(\n    test_person_2_feats, how=\"left\", on=\"case_id\"\n).join(\n    test_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)\n","metadata":{"execution":{"iopub.status.busy":"2024-03-15T15:13:26.449983Z","iopub.execute_input":"2024-03-15T15:13:26.450398Z","iopub.status.idle":"2024-03-15T15:13:26.468632Z","shell.execute_reply.started":"2024-03-15T15:13:26.450360Z","shell.execute_reply":"2024-03-15T15:13:26.467550Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = data.unique(subset='case_id', keep='last')\ndata_submission = data_submission.unique(subset='case_id', keep='last')","metadata":{"execution":{"iopub.status.busy":"2024-03-15T15:16:56.009600Z","iopub.execute_input":"2024-03-15T15:16:56.010014Z","iopub.status.idle":"2024-03-15T15:16:58.837138Z","shell.execute_reply.started":"2024-03-15T15:16:56.009981Z","shell.execute_reply":"2024-03-15T15:16:58.836168Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**удалила признаки, где меньше 100000 non-null**","metadata":{}},{"cell_type":"code","source":"case_ids = data[\"case_id\"].unique().shuffle(seed=1)\ncase_ids_train, case_ids_test = train_test_split(case_ids, train_size=0.6, random_state=1)\ncase_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.5, random_state=1)\n\n# cols_pred = []\n# for col in data.columns:\n#     if col[-1].isupper() and col[:-1].islower():\n#         cols_pred.append(col)\n\ndrop_cols = [\n    'case_id', 'MONTH', 'WEEK_NUM', 'target', \n    # удаляю колонки где меньше 100000 non-null\n    'avglnamtstart24m_4525187A', 'lastotherinc_902A',\n    'lastotherlnsexpense_631A', 'maxannuity_4075009A', 'pmtaverage_3A', 'pmtaverage_4955615A',\n    'person_housetype', 'pmts_pmtsoverdue_635A_max', 'pmts_dpdvalue_108P_over31'\n]\ncols_pred = data.drop(columns=drop_cols).columns\n\nprint(cols_pred)\n\ndef from_polars_to_pandas(case_ids: pl.DataFrame) -> pl.DataFrame:\n    base = data.filter(pl.col(\"case_id\").is_in(case_ids))[[\"case_id\", \"WEEK_NUM\", \"target\"]].to_pandas()\n    X = data.filter(pl.col(\"case_id\").is_in(case_ids))[cols_pred].to_pandas()\n    y = data.filter(pl.col(\"case_id\").is_in(case_ids))[\"target\"].to_pandas()\n    \n    X['cnt_days_decision'] = (datetime.now() - pd.to_datetime(X['date_decision'])).dt.days\n    X['age'] = (datetime.now() - pd.to_datetime(X['birth_date'])).dt.days\n    X['cnt_days_employed'] = (datetime.now() - pd.to_datetime(X['employed_from_date'])).dt.days\n    \n    return (\n        base, \n#         X,\n        X.drop(columns=['date_decision', 'birth_date', 'employed_from_date']),\n        y\n    )\n    \n    \n\nbase_train, X_train, y_train = from_polars_to_pandas(case_ids_train)\nbase_valid, X_valid, y_valid = from_polars_to_pandas(case_ids_valid)\nbase_test, X_test, y_test = from_polars_to_pandas(case_ids_test)\n\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T14:07:29.540455Z","iopub.execute_input":"2024-03-15T14:07:29.540982Z","iopub.status.idle":"2024-03-15T14:07:42.595833Z","shell.execute_reply.started":"2024-03-15T14:07:29.540939Z","shell.execute_reply":"2024-03-15T14:07:42.594895Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f\"Train: {X_train.shape}\")\nprint(f\"Valid: {X_valid.shape}\")\nprint(f\"Test: {X_test.shape}\")","metadata":{"execution":{"iopub.status.busy":"2024-03-15T14:08:54.976411Z","iopub.execute_input":"2024-03-15T14:08:54.976874Z","iopub.status.idle":"2024-03-15T14:08:54.983192Z","shell.execute_reply.started":"2024-03-15T14:08:54.976834Z","shell.execute_reply":"2024-03-15T14:08:54.982060Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training LightGBM","metadata":{}},{"cell_type":"markdown","source":"**перебор гиперпараметров**","metadata":{}},{"cell_type":"code","source":"learning_rates = [0.001, 0.01, 0.05]\nnum_leaves = [10, 15, 45]\nmax_depths = [3, 5]","metadata":{"execution":{"iopub.status.busy":"2024-03-15T14:29:50.087294Z","iopub.execute_input":"2024-03-15T14:29:50.087695Z","iopub.status.idle":"2024-03-15T14:29:50.092643Z","shell.execute_reply.started":"2024-03-15T14:29:50.087665Z","shell.execute_reply":"2024-03-15T14:29:50.091303Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# lgb_train = lgb.Dataset(X_train, label=y_train)\n# lgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\n# best_score = 0\n# best_params = None\n# best_model = None\n\n# for lr in learning_rates:\n#     for n_leaves in num_leaves:\n#         for max_depth in max_depths:\n\n#             params = {\n#                 \"boosting_type\": \"gbdt\",\n#                 \"objective\": \"binary\",\n#                 \"metric\": \"auc\",\n#                 \"max_depth\": max_depth,\n#                 \"num_leaves\": n_leaves,\n#                 \"learning_rate\": lr,\n#                 \"feature_fraction\": 0.9,\n#                 \"bagging_fraction\": 0.8,\n#                 \"bagging_freq\": 5,\n#                 \"n_estimators\": 1000,\n#                 \"verbose\": -1,\n#             }\n\n#             gbm = lgb.train(\n#                 params,\n#                 lgb_train,\n#                 valid_sets=lgb_valid,\n#                 callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)]\n#             )\n\n#             y_valid_pred = gbm.predict(X_valid, num_iteration=gbm.best_iteration)\n#             valid_score = roc_auc_score(base_valid[\"target\"], y_valid_pred)\n\n#             print(f'params:\\tlr={lr}\\tmax_depth={max_depth}\\tnum_leaves={n_leaves}\\nvalid score={round(valid_score, 4)}\\n')\n\n#             if valid_score > best_score:\n#                 best_score = valid_score\n#                 best_params = params\n#                 best_model = gbm","metadata":{"execution":{"iopub.status.busy":"2024-03-15T14:30:37.534954Z","iopub.execute_input":"2024-03-15T14:30:37.535394Z","iopub.status.idle":"2024-03-15T14:57:03.390621Z","shell.execute_reply.started":"2024-03-15T14:30:37.535359Z","shell.execute_reply":"2024-03-15T14:57:03.389784Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Evaluation with AUC and then comparison with the stability metric is shown below.","metadata":{}},{"cell_type":"code","source":"# print(f'best score = {best_score}\\nbest params = {best_params}')","metadata":{"execution":{"iopub.status.busy":"2024-03-15T14:59:57.404488Z","iopub.execute_input":"2024-03-15T14:59:57.404997Z","iopub.status.idle":"2024-03-15T14:59:57.411413Z","shell.execute_reply.started":"2024-03-15T14:59:57.404961Z","shell.execute_reply":"2024-03-15T14:59:57.409883Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lgb_train = lgb.Dataset(X_train, label=y_train)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"max_depth\": 5,\n    \"num_leaves\": 45,\n    \"learning_rate\": 0.05,\n    \"feature_fraction\": 0.9,\n    \"bagging_fraction\": 0.8,\n    \"bagging_freq\": 5,\n    \"n_estimators\": 1000,\n    \"verbose\": -1,\n}\n\nbest_model = lgb.train(\n    params,\n    lgb_train,\n    valid_sets=lgb_valid,\n    callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)]\n)\n\ny_valid_pred = best_model.predict(X_valid, num_iteration=best_model.best_iteration)\nvalid_score = roc_auc_score(base_valid[\"target\"], y_valid_pred)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T15:42:28.032606Z","iopub.execute_input":"2024-03-15T15:42:28.033088Z","iopub.status.idle":"2024-03-15T15:43:59.771819Z","shell.execute_reply.started":"2024-03-15T15:42:28.033046Z","shell.execute_reply":"2024-03-15T15:43:59.770568Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred = best_model.predict(X, num_iteration=best_model.best_iteration)\n    base[\"score\"] = y_pred\n\nprint(f'The AUC score on the train set is: {roc_auc_score(base_train[\"target\"], base_train[\"score\"])}') \nprint(f'The AUC score on the valid set is: {roc_auc_score(base_valid[\"target\"], base_valid[\"score\"])}') \nprint(f'The AUC score on the test set is: {roc_auc_score(base_test[\"target\"], base_test[\"score\"])}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-15T15:44:22.581567Z","iopub.execute_input":"2024-03-15T15:44:22.582030Z","iopub.status.idle":"2024-03-15T15:44:55.617816Z","shell.execute_reply.started":"2024-03-15T15:44:22.581990Z","shell.execute_reply":"2024-03-15T15:44:55.616701Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def gini_stability(base, w_fallingrate=88.0, w_resstd=-0.5):\n    gini_in_time = base.loc[:, [\"WEEK_NUM\", \"target\", \"score\"]]\\\n        .sort_values(\"WEEK_NUM\")\\\n        .groupby(\"WEEK_NUM\")[[\"target\", \"score\"]]\\\n        .apply(lambda x: 2*roc_auc_score(x[\"target\"], x[\"score\"])-1).tolist()\n    \n    x = np.arange(len(gini_in_time))\n    y = gini_in_time\n    a, b = np.polyfit(x, y, 1)\n    y_hat = a*x + b\n    residuals = y - y_hat\n    res_std = np.std(residuals)\n    avg_gini = np.mean(gini_in_time)\n    return avg_gini + w_fallingrate * min(0, a) + w_resstd * res_std\n\nstability_score_train = gini_stability(base_train)\nstability_score_valid = gini_stability(base_valid)\nstability_score_test = gini_stability(base_test)\n\nprint(f'The stability score on the train set is: {stability_score_train}') \nprint(f'The stability score on the valid set is: {stability_score_valid}') \nprint(f'The stability score on the test set is: {stability_score_test}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-15T15:45:01.282175Z","iopub.execute_input":"2024-03-15T15:45:01.282691Z","iopub.status.idle":"2024-03-15T15:45:02.439653Z","shell.execute_reply.started":"2024-03-15T15:45:01.282648Z","shell.execute_reply":"2024-03-15T15:45:02.438637Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Submission","metadata":{}},{"cell_type":"code","source":"X_submission = data_submission[cols_pred].to_pandas()\nX_submission['cnt_days_decision'] = (datetime.now() - pd.to_datetime(X_submission['date_decision'])).dt.days\nX_submission['age'] = (datetime.now() - pd.to_datetime(X_submission['birth_date'])).dt.days\nX_submission['cnt_days_employed'] = (datetime.now() - pd.to_datetime(X_submission['employed_from_date'])).dt.days\nX_submission.drop(columns=['date_decision', 'birth_date', 'employed_from_date'], inplace=True)\n\nbool_col = 'mainoccupationinc_384A_any_selfemployed'\nX_submission[bool_col].fillna(bool(int(X_train[bool_col].mean())), inplace=True)\n\nX_submission = convert_strings(X_submission)\ncategorical_cols = X_train.select_dtypes(include=['category']).columns\n\nfor col in categorical_cols:\n    train_categories = set(X_train[col].cat.categories)\n    submission_categories = set(X_submission[col].cat.categories)\n    new_categories = submission_categories - train_categories\n    X_submission.loc[X_submission[col].isin(new_categories), col] = \"Unknown\"\n    new_dtype = pd.CategoricalDtype(categories=train_categories, ordered=True)\n    X_train[col] = X_train[col].astype(new_dtype)\n    X_submission[col] = X_submission[col].astype(new_dtype)\n    \n    \nother_cols = X_train.select_dtypes(include=['float64', 'int64']).columns\nfor col in other_cols:\n    new_dtype = X_train[col].dtype\n    X_submission[col].fillna(X_train[col].mean(), inplace=True)\n    X_submission[col] = X_submission[col].astype(new_dtype)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T16:06:34.708090Z","iopub.execute_input":"2024-03-15T16:06:34.708493Z","iopub.status.idle":"2024-03-15T16:06:35.308790Z","shell.execute_reply.started":"2024-03-15T16:06:34.708461Z","shell.execute_reply":"2024-03-15T16:06:35.307616Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_submission_pred = best_model.predict(X_submission, num_iteration=best_model.best_iteration)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T16:06:44.560914Z","iopub.execute_input":"2024-03-15T16:06:44.561322Z","iopub.status.idle":"2024-03-15T16:06:44.592166Z","shell.execute_reply.started":"2024-03-15T16:06:44.561288Z","shell.execute_reply":"2024-03-15T16:06:44.591064Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.DataFrame({\n    \"case_id\": data_submission[\"case_id\"].to_numpy(),\n    \"score\": y_submission_pred\n}).set_index('case_id')\nsubmission.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-15T16:06:45.563228Z","iopub.execute_input":"2024-03-15T16:06:45.563661Z","iopub.status.idle":"2024-03-15T16:06:45.573446Z","shell.execute_reply.started":"2024-03-15T16:06:45.563625Z","shell.execute_reply":"2024-03-15T16:06:45.572253Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}