{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","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":30673,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"### Decription\n\nThe goal of this competition is to predict which clients are more likely to default on their loans. The evaluation will favor solutions that are stable over time.","metadata":{}},{"cell_type":"markdown","source":"#### Special columns\n\ncase_id - This is the unique identifier for each credit case. You'll need this ID to join relevant tables to the base table.\n\ndate_decision - This refers to the date when a decision was made regarding the approval of the loan.\n\nWEEK_NUM - This is the week number used for aggregation. In the test sample, WEEK_NUM continues sequentially from the last training value of WEEK_NUM.\n\nMONTH - This column represents the month and is intended for aggregation purposes.\n\ntarget - This is the target value, determined after a certain period based on whether or not the client defaulted on the specific credit case (loan).\n\nnum_group1 - This is an indexing column used for the historical records of case_id in both depth=1 and depth=2 tables.\n\nnum_group2 - This is the second indexing column for depth=2 tables' historical records of case_id. The order of num_group1 and num_group2 is important and will be clarified in feature definitions.","metadata":{}},{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\n# for dirname, _, filenames in os.walk('/kaggle/input'):\n#     for filename in filenames:\n#         print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-03-31T18:12:16.619155Z","iopub.execute_input":"2024-03-31T18:12:16.619687Z","iopub.status.idle":"2024-03-31T18:12:17.925979Z","shell.execute_reply.started":"2024-03-31T18:12:16.619644Z","shell.execute_reply":"2024-03-31T18:12:17.924484Z"},"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","metadata":{"execution":{"iopub.status.busy":"2024-03-31T18:12:17.928790Z","iopub.execute_input":"2024-03-31T18:12:17.929398Z","iopub.status.idle":"2024-03-31T18:12:21.308395Z","shell.execute_reply.started":"2024-03-31T18:12:17.929352Z","shell.execute_reply":"2024-03-31T18:12:21.307433Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-03-31T18:12:21.309885Z","iopub.execute_input":"2024-03-31T18:12:21.310634Z","iopub.status.idle":"2024-03-31T18:12:21.315280Z","shell.execute_reply.started":"2024-03-31T18:12:21.310602Z","shell.execute_reply":"2024-03-31T18:12:21.314092Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def set_table_dtypes(df: pl.DataFrame) -> pl.DataFrame:\n    for col in df.columns:\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":"2024-03-31T18:12:21.317110Z","iopub.execute_input":"2024-03-31T18:12:21.317541Z","iopub.status.idle":"2024-03-31T18:12:21.331075Z","shell.execute_reply.started":"2024-03-31T18:12:21.317500Z","shell.execute_reply":"2024-03-31T18:12:21.329944Z"},"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":"2024-03-31T18:12:21.335162Z","iopub.execute_input":"2024-03-31T18:12:21.336637Z","iopub.status.idle":"2024-03-31T18:12:40.723334Z","shell.execute_reply.started":"2024-03-31T18:12:21.336560Z","shell.execute_reply":"2024-03-31T18:12:40.722134Z"},"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":"2024-03-31T18:12:40.724895Z","iopub.execute_input":"2024-03-31T18:12:40.725536Z","iopub.status.idle":"2024-03-31T18:12:40.803528Z","shell.execute_reply.started":"2024-03-31T18:12:40.725490Z","shell.execute_reply":"2024-03-31T18:12:40.802397Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_static_cb","metadata":{"execution":{"iopub.status.busy":"2024-03-31T18:12:40.805035Z","iopub.execute_input":"2024-03-31T18:12:40.805714Z","iopub.status.idle":"2024-03-31T18:12:40.842091Z","shell.execute_reply.started":"2024-03-31T18:12:40.805677Z","shell.execute_reply":"2024-03-31T18:12:40.841004Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_person_1","metadata":{"execution":{"iopub.status.busy":"2024-03-31T18:12:40.843546Z","iopub.execute_input":"2024-03-31T18:12:40.844600Z","iopub.status.idle":"2024-03-31T18:12:40.866250Z","shell.execute_reply.started":"2024-03-31T18:12:40.844558Z","shell.execute_reply":"2024-03-31T18:12:40.864738Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_credit_bureau_b_2","metadata":{"execution":{"iopub.status.busy":"2024-03-31T18:12:40.868265Z","iopub.execute_input":"2024-03-31T18:12:40.868768Z","iopub.status.idle":"2024-03-31T18:12:40.881626Z","shell.execute_reply.started":"2024-03-31T18:12:40.868726Z","shell.execute_reply":"2024-03-31T18:12:40.880509Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_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\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\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\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":"2024-03-31T18:12:40.883219Z","iopub.execute_input":"2024-03-31T18:12:40.884712Z","iopub.status.idle":"2024-03-31T18:12:43.935066Z","shell.execute_reply.started":"2024-03-31T18:12:40.884671Z","shell.execute_reply":"2024-03-31T18:12:43.934030Z"},"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":"2024-03-31T18:12:43.936255Z","iopub.execute_input":"2024-03-31T18:12:43.936592Z","iopub.status.idle":"2024-03-31T18:12:43.955815Z","shell.execute_reply.started":"2024-03-31T18:12:43.936566Z","shell.execute_reply":"2024-03-31T18:12:43.954047Z"},"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":"2024-03-31T18:12:43.959209Z","iopub.execute_input":"2024-03-31T18:12:43.960464Z","iopub.status.idle":"2024-03-31T18:12:52.839295Z","shell.execute_reply.started":"2024-03-31T18:12:43.960395Z","shell.execute_reply":"2024-03-31T18:12:52.838018Z"},"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":"2024-03-31T18:12:52.841028Z","iopub.execute_input":"2024-03-31T18:12:52.841527Z","iopub.status.idle":"2024-03-31T18:12:52.848973Z","shell.execute_reply.started":"2024-03-31T18:12:52.841484Z","shell.execute_reply":"2024-03-31T18:12:52.847295Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"selected_vars =    [ 'lastrejectreason_759M',\n                     'pmtssum_45A',\n                     'amtinstpaidbefduel24m_4187115A',\n                     'disbursedcredamount_1113A',\n                     'price_1097A',\n                     'credamount_770A',\n                     'maxdebt4_972A',\n                     'sumoutstandtotal_3546847A',\n                     'currdebt_22A',\n                     'totalsettled_863A',\n                     'lastcancelreason_561M',\n                     'lastrejectcommoditycat_161M',\n                     'currdebtcredtyperange_828A',\n                     'annuity_780A',\n                     'maxannuity_159A']\nX_train = X_train[selected_vars]\nX_valid = X_valid[selected_vars]\nX_test = X_test[selected_vars]","metadata":{"execution":{"iopub.status.busy":"2024-03-31T18:12:52.855312Z","iopub.execute_input":"2024-03-31T18:12:52.856269Z","iopub.status.idle":"2024-03-31T18:12:52.922529Z","shell.execute_reply.started":"2024-03-31T18:12:52.856218Z","shell.execute_reply":"2024-03-31T18:12:52.921426Z"},"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\": 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\ngbm = 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":"2024-03-31T18:12:52.923799Z","iopub.execute_input":"2024-03-31T18:12:52.924932Z","iopub.status.idle":"2024-03-31T18:13:33.033983Z","shell.execute_reply.started":"2024-03-31T18:12:52.924898Z","shell.execute_reply":"2024-03-31T18:13:33.032725Z"},"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 = gbm.predict(X, num_iteration=gbm.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":"2024-03-31T18:13:33.035598Z","iopub.execute_input":"2024-03-31T18:13:33.036806Z","iopub.status.idle":"2024-03-31T18:13:42.706635Z","shell.execute_reply.started":"2024-03-31T18:13:33.036765Z","shell.execute_reply":"2024-03-31T18:13:42.705011Z"},"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}')  \n","metadata":{"execution":{"iopub.status.busy":"2024-03-31T18:13:42.708054Z","iopub.execute_input":"2024-03-31T18:13:42.708374Z","iopub.status.idle":"2024-03-31T18:13:43.853009Z","shell.execute_reply.started":"2024-03-31T18:13:42.708348Z","shell.execute_reply":"2024-03-31T18:13:43.851778Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_submission = data_submission[cols_pred].to_pandas()\nX_submission = X_submission[selected_vars]\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\ny_submission_pred = gbm.predict(X_submission, num_iteration=gbm.best_iteration)","metadata":{"execution":{"iopub.status.busy":"2024-03-31T18:16:01.705119Z","iopub.execute_input":"2024-03-31T18:16:01.705679Z","iopub.status.idle":"2024-03-31T18:16:01.751051Z","shell.execute_reply.started":"2024-03-31T18:16:01.705639Z","shell.execute_reply":"2024-03-31T18:16:01.749457Z"},"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":"2024-03-31T18:16:06.560296Z","iopub.execute_input":"2024-03-31T18:16:06.560747Z","iopub.status.idle":"2024-03-31T18:16:06.574641Z","shell.execute_reply.started":"2024-03-31T18:16:06.560717Z","shell.execute_reply":"2024-03-31T18:16:06.573721Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}