{"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":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30636,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"In 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":"import polars as pl\nimport numpy as np\nimport pandas as pd\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split, StratifiedGroupKFold\nfrom sklearn.metrics import roc_auc_score \n\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-05-05T10:08:34.726668Z","iopub.execute_input":"2024-05-05T10:08:34.727043Z","iopub.status.idle":"2024-05-05T10:08:34.732216Z","shell.execute_reply.started":"2024-05-05T10:08:34.727017Z","shell.execute_reply":"2024-05-05T10:08:34.731242Z"},"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":"2024-05-05T10:08:34.734032Z","iopub.execute_input":"2024-05-05T10:08:34.73432Z","iopub.status.idle":"2024-05-05T10:08:34.74499Z","shell.execute_reply.started":"2024-05-05T10:08:34.734296Z","shell.execute_reply":"2024-05-05T10:08:34.744188Z"},"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":"2024-05-05T10:08:34.745987Z","iopub.execute_input":"2024-05-05T10:08:34.746248Z","iopub.status.idle":"2024-05-05T10:08:46.733736Z","shell.execute_reply.started":"2024-05-05T10:08:34.746216Z","shell.execute_reply":"2024-05-05T10:08:46.732716Z"},"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":"2024-05-05T10:08:46.73599Z","iopub.execute_input":"2024-05-05T10:08:46.736307Z","iopub.status.idle":"2024-05-05T10:08:46.788344Z","shell.execute_reply.started":"2024-05-05T10:08:46.736282Z","shell.execute_reply":"2024-05-05T10:08:46.787422Z"},"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\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":"2024-05-05T10:08:46.790996Z","iopub.execute_input":"2024-05-05T10:08:46.79154Z","iopub.status.idle":"2024-05-05T10:08:48.340084Z","shell.execute_reply.started":"2024-05-05T10:08:46.791509Z","shell.execute_reply":"2024-05-05T10:08:48.339074Z"},"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":"2024-05-05T10:08:48.341326Z","iopub.execute_input":"2024-05-05T10:08:48.341625Z","iopub.status.idle":"2024-05-05T10:08:48.35325Z","shell.execute_reply.started":"2024-05-05T10:08:48.3416Z","shell.execute_reply":"2024-05-05T10:08:48.352458Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data","metadata":{"execution":{"iopub.status.busy":"2024-05-05T10:08:48.354306Z","iopub.execute_input":"2024-05-05T10:08:48.355019Z","iopub.status.idle":"2024-05-05T10:08:48.393255Z","shell.execute_reply.started":"2024-05-05T10:08:48.354994Z","shell.execute_reply":"2024-05-05T10:08:48.392409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"case_ids = data[\"case_id\"].unique().shuffle(seed=2)\ncase_ids_train, case_ids_test = train_test_split(case_ids, train_size=0.9, random_state=11)\ncase_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.5, random_state=11)\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)","metadata":{"execution":{"iopub.status.busy":"2024-05-05T10:08:48.394504Z","iopub.execute_input":"2024-05-05T10:08:48.39483Z","iopub.status.idle":"2024-05-05T10:08:48.530303Z","shell.execute_reply.started":"2024-05-05T10:08:48.394798Z","shell.execute_reply":"2024-05-05T10:08:48.52934Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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":"2024-05-05T10:08:48.53204Z","iopub.execute_input":"2024-05-05T10:08:48.532841Z","iopub.status.idle":"2024-05-05T10:08:55.534128Z","shell.execute_reply.started":"2024-05-05T10:08:48.532804Z","shell.execute_reply":"2024-05-05T10:08:55.533273Z"},"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":"2024-05-05T10:08:55.535249Z","iopub.execute_input":"2024-05-05T10:08:55.535568Z","iopub.status.idle":"2024-05-05T10:08:55.540564Z","shell.execute_reply.started":"2024-05-05T10:08:55.535541Z","shell.execute_reply":"2024-05-05T10:08:55.539691Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#X = data.drop(columns=[\"target\", \"case_id\",\"WEEK_NUM\"])\n#y = data[\"target\"]\n#weeks = data[\"WEEK_NUM\"]\n\n#cv = StratifiedGroupKFold(n_splits=5, shuffle=False)\n\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"max_depth\": 10,\n    \"learning_rate\": 0.05,\n    \"max_bin\": 255,\n    \"n_estimators\": 1200,\n    \"colsample_bytree\": 0.8,\n    \"colsample_bynode\": 0.8,\n    \"verbose\": -1,\n    \"random_state\": 42,\n    \"reg_alpha\": 0.1,\n    \"reg_lambda\": 10,\n    \"extra_trees\":True,\n    'num_leaves':64,\n    \"device\": \"gpu\",\n}","metadata":{"execution":{"iopub.status.busy":"2024-05-05T10:08:55.542227Z","iopub.execute_input":"2024-05-05T10:08:55.542664Z","iopub.status.idle":"2024-05-05T10:08:55.553136Z","shell.execute_reply.started":"2024-05-05T10:08:55.542632Z","shell.execute_reply":"2024-05-05T10:08:55.55232Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"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)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\ngbm = lgb.train(\n    params,\n    lgb_train,\n    valid_sets=lgb_valid,\n    callbacks=[lgb.log_evaluation(250), lgb.early_stopping(50)]\n)","metadata":{"execution":{"iopub.status.busy":"2024-05-05T10:08:55.554223Z","iopub.execute_input":"2024-05-05T10:08:55.554497Z","iopub.status.idle":"2024-05-05T10:10:16.858241Z","shell.execute_reply.started":"2024-05-05T10:08:55.554474Z","shell.execute_reply":"2024-05-05T10:10:16.85719Z"},"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\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":"2024-05-05T10:10:16.861462Z","iopub.execute_input":"2024-05-05T10:10:16.861755Z","iopub.status.idle":"2024-05-05T10:11:37.79094Z","shell.execute_reply.started":"2024-05-05T10:10:16.86173Z","shell.execute_reply":"2024-05-05T10:11:37.78925Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import roc_auc_score","metadata":{"execution":{"iopub.status.busy":"2024-05-05T10:11:37.792104Z","iopub.execute_input":"2024-05-05T10:11:37.792424Z","iopub.status.idle":"2024-05-05T10:11:37.796929Z","shell.execute_reply.started":"2024-05-05T10:11:37.792398Z","shell.execute_reply":"2024-05-05T10:11:37.795973Z"},"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()\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":"2024-05-05T10:11:37.798245Z","iopub.execute_input":"2024-05-05T10:11:37.79871Z","iopub.status.idle":"2024-05-05T10:11:37.899925Z","shell.execute_reply.started":"2024-05-05T10:11:37.798667Z","shell.execute_reply":"2024-05-05T10:11:37.899083Z"},"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')","metadata":{"execution":{"iopub.status.busy":"2024-05-05T10:11:37.901306Z","iopub.execute_input":"2024-05-05T10:11:37.902247Z","iopub.status.idle":"2024-05-05T10:11:37.90804Z","shell.execute_reply.started":"2024-05-05T10:11:37.902198Z","shell.execute_reply":"2024-05-05T10:11:37.90706Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission","metadata":{"execution":{"iopub.status.busy":"2024-05-05T10:11:37.909236Z","iopub.execute_input":"2024-05-05T10:11:37.910084Z","iopub.status.idle":"2024-05-05T10:11:37.924139Z","shell.execute_reply.started":"2024-05-05T10:11:37.910052Z","shell.execute_reply":"2024-05-05T10:11:37.923265Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.to_csv(\"./submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-05-05T10:11:37.92536Z","iopub.execute_input":"2024-05-05T10:11:37.925664Z","iopub.status.idle":"2024-05-05T10:11:37.937086Z","shell.execute_reply.started":"2024-05-05T10:11:37.925638Z","shell.execute_reply":"2024-05-05T10:11:37.936249Z"},"trusted":true},"execution_count":null,"outputs":[]}]}