{"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":30664,"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, RandomizedSearchCV\nfrom sklearn.metrics import roc_auc_score\n\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:31:15.152214Z","iopub.execute_input":"2024-03-17T19:31:15.153351Z","iopub.status.idle":"2024-03-17T19:31:19.730587Z","shell.execute_reply.started":"2024-03-17T19:31:15.153281Z","shell.execute_reply":"2024-03-17T19:31:19.729036Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"What I did: enriched dataset, created new features, hyperparameters tuning. Baseline - https://www.kaggle.com/code/jetakow/home-credit-2024-starter-notebook","metadata":{}},{"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":"2024-03-17T19:31:23.752109Z","iopub.execute_input":"2024-03-17T19:31:23.753767Z","iopub.status.idle":"2024-03-17T19:31:23.764547Z","shell.execute_reply.started":"2024-03-17T19:31:23.753711Z","shell.execute_reply":"2024-03-17T19:31:23.762854Z"},"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":"2024-03-17T19:31:29.244358Z","iopub.execute_input":"2024-03-17T19:31:29.244851Z","iopub.status.idle":"2024-03-17T19:31:49.448168Z","shell.execute_reply.started":"2024-03-17T19:31:29.244813Z","shell.execute_reply":"2024-03-17T19:31:49.447163Z"},"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":"2024-03-17T19:31:52.785626Z","iopub.execute_input":"2024-03-17T19:31:52.786191Z","iopub.status.idle":"2024-03-17T19:31:52.855577Z","shell.execute_reply.started":"2024-03-17T19:31:52.786143Z","shell.execute_reply":"2024-03-17T19:31:52.854304Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"enriching the data","metadata":{}},{"cell_type":"code","source":"train_debitcard_1 = pl.read_csv(dataPath + \"csv_files/train/train_debitcard_1.csv\").pipe(set_table_dtypes)\ntrain_deposit_1 = pl.read_csv(dataPath + \"csv_files/train/train_deposit_1.csv\").pipe(set_table_dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:31:57.837604Z","iopub.execute_input":"2024-03-17T19:31:57.838036Z","iopub.status.idle":"2024-03-17T19:31:57.948389Z","shell.execute_reply.started":"2024-03-17T19:31:57.838004Z","shell.execute_reply":"2024-03-17T19:31:57.947404Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_debitcard_1 = pl.read_csv(dataPath + \"csv_files/test/test_debitcard_1.csv\").pipe(set_table_dtypes)\ntest_deposit_1 = pl.read_csv(dataPath + \"csv_files/test/test_deposit_1.csv\").pipe(set_table_dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:32:02.912330Z","iopub.execute_input":"2024-03-17T19:32:02.913973Z","iopub.status.idle":"2024-03-17T19:32:02.943847Z","shell.execute_reply.started":"2024-03-17T19:32:02.913924Z","shell.execute_reply":"2024-03-17T19:32:02.942489Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\ntrain_debitcard_1_feats = train_debitcard_1.group_by(\"case_id\").agg(\n    pl.col(\"last180dayaveragebalance_704A\").mean().alias(\"last180dayaveragebalance_704A_mean\"),\n    pl.col(\"last30dayturnover_651A\").max().alias(\"maxlast30dayturnover_651A\"),\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).join(\n    train_debitcard_1_feats, how=\"left\", on=\"case_id\" \n)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:36:11.628331Z","iopub.execute_input":"2024-03-17T20:36:11.630051Z","iopub.status.idle":"2024-03-17T20:36:15.993932Z","shell.execute_reply.started":"2024-03-17T20:36:11.630000Z","shell.execute_reply":"2024-03-17T20:36:15.992697Z"},"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\ntest_debitcard_1_feats = test_debitcard_1.group_by(\"case_id\").agg(\n    pl.col(\"last180dayaveragebalance_704A\").mean().alias(\"last180dayaveragebalance_704A_mean\"),\n    pl.col(\"last30dayturnover_651A\").max().alias(\"maxlast30dayturnover_651A\"),\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).join(\n    test_debitcard_1_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:36:20.270028Z","iopub.execute_input":"2024-03-17T20:36:20.270526Z","iopub.status.idle":"2024-03-17T20:36:20.293681Z","shell.execute_reply.started":"2024-03-17T20:36:20.270481Z","shell.execute_reply":"2024-03-17T20:36:20.291742Z"},"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)\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":"2024-03-17T20:36:24.739890Z","iopub.execute_input":"2024-03-17T20:36:24.740437Z","iopub.status.idle":"2024-03-17T20:36:33.923881Z","shell.execute_reply.started":"2024-03-17T20:36:24.740398Z","shell.execute_reply":"2024-03-17T20:36:33.922136Z"},"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":"2024-03-17T20:36:38.384121Z","iopub.execute_input":"2024-03-17T20:36:38.384940Z","iopub.status.idle":"2024-03-17T20:36:38.394540Z","shell.execute_reply.started":"2024-03-17T20:36:38.384890Z","shell.execute_reply":"2024-03-17T20:36:38.392380Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"##baseline model","metadata":{}},{"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":"2024-03-17T19:55:23.195330Z","iopub.execute_input":"2024-03-17T19:55:23.195915Z","iopub.status.idle":"2024-03-17T19:56:34.339338Z","shell.execute_reply.started":"2024-03-17T19:55:23.195876Z","shell.execute_reply":"2024-03-17T19:56:34.337716Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"searching the best parameters with the help of optuna library","metadata":{}},{"cell_type":"code","source":"import optuna\n\nlgb_train = lgb.Dataset(X_train, label=y_train)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\n\ndef objective(trial):\n    params = {\n        \"objective\": \"binary\",\n        \"metric\": \"auc\",\n        \"verbosity\": -1,\n        \"boosting_type\": \"gbdt\",\n        \"num_leaves\": trial.suggest_int(\"num_leaves\", 2, 128),\n        \"max_depth\": trial.suggest_int(\"max_depth\", -1, 32),\n        \"learning_rate\": trial.suggest_float(\"learning_rate\", 0.001, 0.3),\n        \"n_estimators\": trial.suggest_int(\"n_estimators\", 100, 1000),\n        \"feature_fraction\": trial.suggest_float(\"feature_fraction\", 0.4, 1.0),\n        \"bagging_fraction\": trial.suggest_float(\"bagging_fraction\", 0.4, 1.0),\n        \"bagging_freq\": trial.suggest_int(\"bagging_freq\", 1, 7)\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    auc = gbm.best_score[\"valid_0\"][\"auc\"]\n    return auc\n\nstudy = optuna.create_study(direction=\"maximize\")\nstudy.optimize(objective, n_trials=10)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:36:42.924716Z","iopub.execute_input":"2024-03-17T20:36:42.925238Z","iopub.status.idle":"2024-03-17T20:40:38.916742Z","shell.execute_reply.started":"2024-03-17T20:36:42.925203Z","shell.execute_reply":"2024-03-17T20:40:38.915188Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"best_params = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"num_leaves\": 103,\n    \"max_depth\": 27,\n    \"learning_rate\": 0.03706734823469604,\n    \"n_estimators\": 348,\n    \"feature_fraction\": 0.6955121541431746,\n    \"bagging_fraction\": 0.812202334368307,\n    \"bagging_freq\": 1,\n    \"verbose\": -1\n}\n##from trial 6 above\n\nlgb_train = lgb.Dataset(X_train, label=y_train)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\ngbm = lgb.train(\nbest_params,\nlgb_train,\nvalid_sets=lgb_valid,\ncallbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)])","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:42:38.544693Z","iopub.execute_input":"2024-03-17T20:42:38.545293Z","iopub.status.idle":"2024-03-17T20:43:35.730152Z","shell.execute_reply.started":"2024-03-17T20:42:38.545227Z","shell.execute_reply":"2024-03-17T20:43:35.728555Z"},"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":"2024-03-17T20:44:10.096989Z","iopub.execute_input":"2024-03-17T20:44:10.097581Z","iopub.status.idle":"2024-03-17T20:44:29.106319Z","shell.execute_reply.started":"2024-03-17T20:44:10.097539Z","shell.execute_reply":"2024-03-17T20:44:29.104733Z"},"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":"2024-03-17T20:44:32.737178Z","iopub.execute_input":"2024-03-17T20:44:32.737707Z","iopub.status.idle":"2024-03-17T20:44:34.000721Z","shell.execute_reply.started":"2024-03-17T20:44:32.737670Z","shell.execute_reply":"2024-03-17T20:44:33.998984Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#submission \nX_submission = data_submission[cols_pred].to_pandas()\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":"2024-03-17T20:44:36.937509Z","iopub.execute_input":"2024-03-17T20:44:36.938050Z","iopub.status.idle":"2024-03-17T20:44:37.107717Z","shell.execute_reply.started":"2024-03-17T20:44:36.938013Z","shell.execute_reply":"2024-03-17T20:44:37.106086Z"},"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":"2024-03-17T20:44:54.739069Z","iopub.execute_input":"2024-03-17T20:44:54.739750Z","iopub.status.idle":"2024-03-17T20:44:54.765289Z","shell.execute_reply.started":"2024-03-17T20:44:54.739702Z","shell.execute_reply":"2024-03-17T20:44:54.763660Z"},"trusted":true},"execution_count":null,"outputs":[]}]}