{"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":7602123,"sourceType":"competition"}],"dockerImageVersionId":30635,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Example Notebook\n\nWelcome to the example notebook for the Home Credit Kaggle competition. The goal of this competition is to determine how likely a customer is going to default on an issued loan. The main difference between the [first](https://www.kaggle.com/c/home-credit-default-risk) and this competition is that now your submission will be scored with a custom metric that will take into account how well the model performs in future. A decline in performance will be penalized. The goal is to create a model that is stable and performs well in the future.\n\nIn this notebook you will see how to:\n* Load the data\n* Join tables with Polars - a DataFrame library implemented in Rust language, designed to be blazingy fast and memory efficient.  \n* Create simple aggregation features\n* Train a LightGBM model\n* Create a submission table\n\n## Load the data","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"code","source":"# !pip install --upgrade pandas","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:19.066515Z","iopub.execute_input":"2024-03-08T06:51:19.066935Z","iopub.status.idle":"2024-03-08T06:51:19.098801Z","shell.execute_reply.started":"2024-03-08T06:51:19.066887Z","shell.execute_reply":"2024-03-08T06:51:19.097431Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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 sklearn.preprocessing import LabelEncoder\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:19.101269Z","iopub.execute_input":"2024-03-08T06:51:19.101722Z","iopub.status.idle":"2024-03-08T06:51:23.193333Z","shell.execute_reply.started":"2024-03-08T06:51:19.101676Z","shell.execute_reply":"2024-03-08T06:51:23.192028Z"},"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":"2024-03-08T06:51:23.195033Z","iopub.execute_input":"2024-03-08T06:51:23.196196Z","iopub.status.idle":"2024-03-08T06:51:23.208737Z","shell.execute_reply.started":"2024-03-08T06:51:23.196146Z","shell.execute_reply":"2024-03-08T06:51:23.207272Z"},"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_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":"2024-03-08T06:51:23.212903Z","iopub.execute_input":"2024-03-08T06:51:23.214146Z","iopub.status.idle":"2024-03-08T06:51:41.812278Z","shell.execute_reply.started":"2024-03-08T06:51:23.214088Z","shell.execute_reply":"2024-03-08T06:51:41.811287Z"},"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_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":"2024-03-08T06:51:41.813962Z","iopub.execute_input":"2024-03-08T06:51:41.814426Z","iopub.status.idle":"2024-03-08T06:51:41.878721Z","shell.execute_reply.started":"2024-03-08T06:51:41.814390Z","shell.execute_reply":"2024-03-08T06:51:41.877816Z"},"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":"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 = train_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\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_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:41.879973Z","iopub.execute_input":"2024-03-08T06:51:41.880835Z","iopub.status.idle":"2024-03-08T06:51:43.611869Z","shell.execute_reply.started":"2024-03-08T06:51:41.880803Z","shell.execute_reply":"2024-03-08T06:51:43.610994Z"},"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 = test_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\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_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:43.612797Z","iopub.execute_input":"2024-03-08T06:51:43.613169Z","iopub.status.idle":"2024-03-08T06:51:43.631390Z","shell.execute_reply.started":"2024-03-08T06:51:43.613125Z","shell.execute_reply":"2024-03-08T06:51:43.630059Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# data = data.with_columns(\n#     pl.col(\"description_5085714M\").fill_null(\"unknown\"),\n#     pl.col(\"education_1103M\").fill_null(\"unknown\"),\n#     pl.col(\"education_88M\").fill_null(\"unknown\"),\n#     pl.col(\"maritalst_385M\").fill_null(\"unknown\"),\n#     pl.col(\"maritalst_893M\").fill_null(\"unknown\"),\n#     pl.col(\"person_housetype\").fill_null(\"unknown\")\n# )","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:43.635097Z","iopub.execute_input":"2024-03-08T06:51:43.635785Z","iopub.status.idle":"2024-03-08T06:51:43.644201Z","shell.execute_reply.started":"2024-03-08T06:51:43.635746Z","shell.execute_reply":"2024-03-08T06:51:43.642970Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\ncols_pred = []\nfor col in data.columns:\n    if col[-1].isupper() and col[:-1].islower():\n        cols_pred.append(col)\n\nprint(cols_pred)\n\ndef from_polars_to_pandas(case_ids: pl.DataFrame) -> pl.DataFrame:\n    return (\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[[\"case_id\", \"WEEK_NUM\", \"target\"]].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[cols_pred].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[\"target\"].to_pandas()\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":"2024-03-08T06:51:43.646450Z","iopub.execute_input":"2024-03-08T06:51:43.647361Z","iopub.status.idle":"2024-03-08T06:51:53.099588Z","shell.execute_reply.started":"2024-03-08T06:51:43.647320Z","shell.execute_reply":"2024-03-08T06:51:53.098210Z"},"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":"2024-03-08T06:51:53.104331Z","iopub.execute_input":"2024-03-08T06:51:53.104735Z","iopub.status.idle":"2024-03-08T06:51:53.111259Z","shell.execute_reply.started":"2024-03-08T06:51:53.104699Z","shell.execute_reply":"2024-03-08T06:51:53.110193Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.loc[0].values","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:53.112763Z","iopub.execute_input":"2024-03-08T06:51:53.113503Z","iopub.status.idle":"2024-03-08T06:51:53.132515Z","shell.execute_reply.started":"2024-03-08T06:51:53.113466Z","shell.execute_reply":"2024-03-08T06:51:53.130957Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# category_1 = []\n# category_1.extend(All_X_train[\"lastapprcommoditycat_1041M\"].unique())\n# category_1.extend(All_X_train[\"lastapprcommoditytypec_5251766M\"].unique())\n# category_1.extend(All_X_train[\"lastcancelreason_561M\"].unique())\n# category_1.extend(All_X_train[\"lastrejectcommoditycat_161M\"].unique())\n# category_1.extend(All_X_train[\"lastrejectcommodtypec_5251769M\"].unique())\n# category_1.extend(All_X_train[\"lastrejectreason_759M\"].unique())\n# category_1.extend(All_X_train[\"lastrejectreasonclient_4145040M\"].unique())\n# category_1.extend(All_X_train[\"previouscontdistrict_112M\"].unique())\n# category_1.extend(All_X_train[\"description_5085714M\"].unique())\n# category_1.extend(All_X_train[\"education_1103M\"].unique())\n# category_1.extend(All_X_train[\"education_88M\"].unique())\n# category_1.extend(All_X_train[\"maritalst_385M\"].unique())\n# category_1.extend(All_X_train[\"maritalst_893M\"].unique())\n\n# category_1 = set(category_1)\n# len(category_1)","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:53.134789Z","iopub.execute_input":"2024-03-08T06:51:53.135192Z","iopub.status.idle":"2024-03-08T06:51:53.144949Z","shell.execute_reply.started":"2024-03-08T06:51:53.135158Z","shell.execute_reply":"2024-03-08T06:51:53.143660Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# category_2 = []\n# category_2.extend(All_X_train[\"person_housetype\"].unique())","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:53.146262Z","iopub.execute_input":"2024-03-08T06:51:53.146608Z","iopub.status.idle":"2024-03-08T06:51:53.159632Z","shell.execute_reply.started":"2024-03-08T06:51:53.146578Z","shell.execute_reply":"2024-03-08T06:51:53.158472Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# le_1 = LabelEncoder()\n# le_1.fit(list(category_1))\n# # le.classes_\n\n# All_X_train[\"lastapprcommoditycat_1041M\"] = le_1.transform(All_X_train[\"lastapprcommoditycat_1041M\"].values)\n# All_X_train[\"lastapprcommoditytypec_5251766M\"] = le_1.transform(All_X_train[\"lastapprcommoditytypec_5251766M\"].values)\n# All_X_train[\"lastcancelreason_561M\"] = le_1.transform(All_X_train[\"lastcancelreason_561M\"].values)\n# All_X_train[\"lastrejectcommoditycat_161M\"] = le_1.transform(All_X_train[\"lastrejectcommoditycat_161M\"].values)\n# All_X_train[\"lastrejectcommodtypec_5251769M\"] = le_1.transform(All_X_train[\"lastrejectcommodtypec_5251769M\"].values)\n# All_X_train[\"lastrejectreason_759M\"] = le_1.transform(All_X_train[\"lastrejectreason_759M\"].values)\n# All_X_train[\"lastrejectreasonclient_4145040M\"] = le_1.transform(All_X_train[\"lastrejectreasonclient_4145040M\"].values)\n# All_X_train[\"previouscontdistrict_112M\"] = le_1.transform(All_X_train[\"previouscontdistrict_112M\"].values)\n# All_X_train[\"description_5085714M\"] = le_1.transform(All_X_train[\"description_5085714M\"].values)\n# All_X_train[\"education_1103M\"] = le_1.transform(All_X_train[\"education_1103M\"].values)\n# All_X_train[\"education_88M\"] = le_1.transform(All_X_train[\"education_88M\"].values)\n# All_X_train[\"maritalst_385M\"] = le_1.transform(All_X_train[\"maritalst_385M\"].values)\n# All_X_train[\"maritalst_893M\"] = le_1.transform(All_X_train[\"maritalst_893M\"].values)","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:53.161046Z","iopub.execute_input":"2024-03-08T06:51:53.161508Z","iopub.status.idle":"2024-03-08T06:51:53.172319Z","shell.execute_reply.started":"2024-03-08T06:51:53.161477Z","shell.execute_reply":"2024-03-08T06:51:53.171119Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# le_2 = LabelEncoder()\n# le_2.fit(list(category_2))\n\n# All_X_train[\"person_housetype\"] = le_2.transform(All_X_train[\"person_housetype\"].values)","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:53.173859Z","iopub.execute_input":"2024-03-08T06:51:53.174464Z","iopub.status.idle":"2024-03-08T06:51:53.187161Z","shell.execute_reply.started":"2024-03-08T06:51:53.174392Z","shell.execute_reply":"2024-03-08T06:51:53.186084Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# All_X_train.head()","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:53.188316Z","iopub.execute_input":"2024-03-08T06:51:53.188852Z","iopub.status.idle":"2024-03-08T06:51:53.197789Z","shell.execute_reply.started":"2024-03-08T06:51:53.188820Z","shell.execute_reply":"2024-03-08T06:51:53.196690Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.to_parquet('train.parquet', index=False)\nX_valid.to_parquet('valid.parquet', index=False)\nX_test.to_parquet('test.parquet', index=False)\n\n# X_valid.to_csv('train.csv', index=False)\n# X_valid.to_parquet('valid.parquet')\n# X_test.to_parquet('test.parquet')","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:53.199805Z","iopub.execute_input":"2024-03-08T06:51:53.200212Z","iopub.status.idle":"2024-03-08T06:51:57.435195Z","shell.execute_reply.started":"2024-03-08T06:51:53.200180Z","shell.execute_reply":"2024-03-08T06:51:57.433942Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training LightGBM\n\nMinimal example of LightGBM training is shown below.","metadata":{}},{"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# params = {\n#     \"boosting_type\": \"gbdt\",\n#     \"objective\": \"binary\",\n#     \"metric\": \"auc\",\n#     \"max_depth\": 3,\n#     \"num_leaves\": 31,\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\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# # )","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:57.437095Z","iopub.execute_input":"2024-03-08T06:51:57.437686Z","iopub.status.idle":"2024-03-08T06:51:57.444717Z","shell.execute_reply.started":"2024-03-08T06:51:57.437625Z","shell.execute_reply":"2024-03-08T06:51:57.443400Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# lgb_train","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:57.446641Z","iopub.execute_input":"2024-03-08T06:51:57.447242Z","iopub.status.idle":"2024-03-08T06:51:57.462003Z","shell.execute_reply.started":"2024-03-08T06:51:57.447191Z","shell.execute_reply":"2024-03-08T06:51:57.461056Z"},"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":"# for base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n#     y_pred = gbm.predict(X, num_iteration=gbm.best_iteration)\n#     base[\"score\"] = y_pred\n\n# print(f'The AUC score on the train set is: {roc_auc_score(base_train[\"target\"], base_train[\"score\"])}') \n# print(f'The AUC score on the valid set is: {roc_auc_score(base_valid[\"target\"], base_valid[\"score\"])}') \n# print(f'The AUC score on the test set is: {roc_auc_score(base_test[\"target\"], base_test[\"score\"])}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:57.463958Z","iopub.execute_input":"2024-03-08T06:51:57.464500Z","iopub.status.idle":"2024-03-08T06:51:57.477024Z","shell.execute_reply.started":"2024-03-08T06:51:57.464418Z","shell.execute_reply":"2024-03-08T06:51:57.475507Z"},"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\n# stability_score_train = gini_stability(base_train)\n# stability_score_valid = gini_stability(base_valid)\n# stability_score_test = gini_stability(base_test)\n\n# print(f'The stability score on the train set is: {stability_score_train}') \n# print(f'The stability score on the valid set is: {stability_score_valid}') \n# print(f'The stability score on the test set is: {stability_score_test}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:57.478119Z","iopub.execute_input":"2024-03-08T06:51:57.478479Z","iopub.status.idle":"2024-03-08T06:51:57.490016Z","shell.execute_reply.started":"2024-03-08T06:51:57.478449Z","shell.execute_reply":"2024-03-08T06:51:57.489081Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Submission\n\nScoring the submission dataset is below, we need to take care of new categories. Then we save the score as a last step. ","metadata":{}},{"cell_type":"code","source":"# X_submission = data_submission[cols_pred].to_pandas()\n# X_submission = convert_strings(X_submission)\n# categorical_cols = X_train.select_dtypes(include=['category']).columns\n\n# for 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# y_submission_pred = gbm.predict(X_submission, num_iteration=gbm.best_iteration)","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:57.491282Z","iopub.execute_input":"2024-03-08T06:51:57.491620Z","iopub.status.idle":"2024-03-08T06:51:57.507026Z","shell.execute_reply.started":"2024-03-08T06:51:57.491591Z","shell.execute_reply":"2024-03-08T06:51:57.506068Z"},"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')\n# submission.to_csv(\"./submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-08T06:51:57.508096Z","iopub.execute_input":"2024-03-08T06:51:57.508452Z","iopub.status.idle":"2024-03-08T06:51:57.517990Z","shell.execute_reply.started":"2024-03-08T06:51:57.508420Z","shell.execute_reply":"2024-03-08T06:51:57.517031Z"},"trusted":true},"execution_count":null,"outputs":[]}]}