{"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":7602123,"sourceType":"competition"}],"dockerImageVersionId":30646,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"raw","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\nfor 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"}},{"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 \n\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-02-07T00:30:43.117132Z","iopub.execute_input":"2024-02-07T00:30:43.117509Z","iopub.status.idle":"2024-02-07T00:30:45.567040Z","shell.execute_reply.started":"2024-02-07T00:30:43.117482Z","shell.execute_reply":"2024-02-07T00:30:45.565614Z"},"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":"2024-02-07T00:31:01.551531Z","iopub.execute_input":"2024-02-07T00:31:01.551888Z","iopub.status.idle":"2024-02-07T00:31:01.559414Z","shell.execute_reply.started":"2024-02-07T00:31:01.551858Z","shell.execute_reply":"2024-02-07T00:31:01.558310Z"},"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":"2024-02-07T00:31:12.373046Z","iopub.execute_input":"2024-02-07T00:31:12.373378Z","iopub.status.idle":"2024-02-07T00:31:22.888075Z","shell.execute_reply.started":"2024-02-07T00:31:12.373351Z","shell.execute_reply":"2024-02-07T00:31:22.887072Z"},"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":"2024-02-07T00:31:33.353175Z","iopub.execute_input":"2024-02-07T00:31:33.353498Z","iopub.status.idle":"2024-02-07T00:31:33.417948Z","shell.execute_reply.started":"2024-02-07T00:31:33.353472Z","shell.execute_reply":"2024-02-07T00:31:33.417072Z"},"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\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":"2024-02-07T00:31:57.114538Z","iopub.execute_input":"2024-02-07T00:31:57.114843Z","iopub.status.idle":"2024-02-07T00:31:58.824506Z","shell.execute_reply.started":"2024-02-07T00:31:57.114821Z","shell.execute_reply":"2024-02-07T00:31:58.823816Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_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\ntest_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\ntest_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\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":"2024-02-07T00:32:12.781517Z","iopub.execute_input":"2024-02-07T00:32:12.781832Z","iopub.status.idle":"2024-02-07T00:32:13.561692Z","shell.execute_reply.started":"2024-02-07T00:32:12.781808Z","shell.execute_reply":"2024-02-07T00:32:13.560627Z"},"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":"2024-02-07T00:32:26.942028Z","iopub.execute_input":"2024-02-07T00:32:26.942348Z","iopub.status.idle":"2024-02-07T00:32:31.647485Z","shell.execute_reply.started":"2024-02-07T00:32:26.942324Z","shell.execute_reply":"2024-02-07T00:32:31.646484Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import lightgbm as lgb\n\nlgb_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\": 0.01,\n    \"feature_fraction\": 0.9,\n    \"bagging_fraction\": 0.8,\n    \"bagging_freq\": 5,\n    \"n_estimators\": 1500,\n    \"verbose\": -1,\n}\n\nlgb_model = lgb.train(\n    params,\n    lgb_train,\n    valid_sets=lgb_valid,  \n    callbacks=[lgb.log_evaluation(50), lgb.early_stopping(100)]\n)","metadata":{"execution":{"iopub.status.busy":"2024-02-07T00:32:43.782036Z","iopub.execute_input":"2024-02-07T00:32:43.782350Z","iopub.status.idle":"2024-02-07T00:34:59.579240Z","shell.execute_reply.started":"2024-02-07T00:32:43.782326Z","shell.execute_reply":"2024-02-07T00:34:59.578404Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import xgboost as xgb\n\nxgb_model = xgb.XGBClassifier(\n    #device=\"cuda\",\n    objective='binary:logistic',\n    tree_method=\"hist\",\n    enable_categorical=True,\n    eval_metric='auc',\n    #gamma=0.7,\n    #reg_alpha=0.7,\n    max_depth=10,\n    n_estimators=1200,\n    random_state=42,\n)\n\n# Training the model on the training data\nxgb_model.fit(\n    X_train, y_train,\n    eval_set=[(X_valid, y_valid)],\n    early_stopping_rounds=100,\n    verbose=True,\n)","metadata":{"execution":{"iopub.status.busy":"2024-02-07T00:35:31.965414Z","iopub.execute_input":"2024-02-07T00:35:31.965804Z","iopub.status.idle":"2024-02-07T00:45:30.992157Z","shell.execute_reply.started":"2024-02-07T00:35:31.965773Z","shell.execute_reply":"2024-02-07T00:45:30.990891Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nfrom catboost import CatBoostClassifier\ncat_features = [col for col in X_train.columns if X_train[col].dtype.name == 'category' or X_train[col].dtype.name == 'object']\n\nfor col in cat_features:\n    X_train[col] = X_train[col].cat.add_categories('Missing').fillna('Missing')\n    X_valid[col] = X_valid[col].cat.add_categories('Missing').fillna('Missing')\n\ncat_model = CatBoostClassifier(\n    iterations=1000,                 \n    depth=10,                        \n    learning_rate=0.1,               \n    eval_metric='AUC',               \n    random_seed=42,                  \n    bootstrap_type='Bayesian',       \n    bagging_temperature=1,           \n    od_type='Iter',                  \n    od_wait=50                      \n)\n\n\ncat_model.fit(\n    X_train, y_train,\n    eval_set=(X_valid, y_valid),\n    cat_features=cat_features,  \n    use_best_model=True,\n    verbose=True\n)","metadata":{"execution":{"iopub.status.busy":"2024-02-07T00:46:32.764755Z","iopub.execute_input":"2024-02-07T00:46:32.765092Z","iopub.status.idle":"2024-02-07T01:23:13.638504Z","shell.execute_reply.started":"2024-02-07T00:46:32.765068Z","shell.execute_reply":"2024-02-07T01:23:13.637279Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_submission = data_submission[cols_pred].to_pandas()\nX_submission = convert_strings(X_submission)\nX_submission_processed = X_submission.copy()\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\nfor col in cat_features:\n    X_submission_processed[col] = X_submission_processed[col].cat.add_categories('Missing').fillna('Missing')\n\nlgb_pred = lgb_model.predict(X_submission)\nxgb_pred = xgb_model.predict(X_submission)\ncat_pred = cat_model.predict(X_submission_processed)\n\ny_submission_pred = np.mean([lgb_pred, xgb_pred, cat_pred], axis=0)\nsubmission = 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\")\nsubmission","metadata":{"execution":{"iopub.status.busy":"2024-02-07T01:27:43.172671Z","iopub.execute_input":"2024-02-07T01:27:43.172978Z","iopub.status.idle":"2024-02-07T01:27:43.272807Z","shell.execute_reply.started":"2024-02-07T01:27:43.172953Z","shell.execute_reply":"2024-02-07T01:27:43.271847Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}