{"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":30684,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false},"colab":{"provenance":[]}},"nbformat_minor":4,"nbformat":4,"cells":[{"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#感覺可參考https://www.kaggle.com/code/adityashukla1/home-credit-risk-xgboost\n#↑(home-credit-risk-xgboost)\n#缺失看這個https://www.kaggle.com/code/cwhybe/eda-for-static-0-cols-end-with-a-d-p\n#↑(EDA for static_0 - cols end with A, D, P)\nimport os\nimport gc\nfrom glob import glob\nfrom pathlib import Path\nfrom datetime import datetime\n\n\n\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nimport polars.selectors as cs\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nfrom sklearn.model_selection import train_test_split,StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, ClassifierMixin\nfrom sklearn.ensemble import RandomForestClassifier\nfrom xgboost import XGBClassifier\nimport xgboost as xgb\n\nimport lightgbm as lgb\n\nimport warnings\nwarnings.simplefilter(action='ignore', category=FutureWarning)#cost7s\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_auc_score","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","id":"UrBU5GAWMG6a","execution":{"iopub.status.busy":"2024-05-02T02:48:15.144621Z","iopub.execute_input":"2024-05-02T02:48:15.145177Z","iopub.status.idle":"2024-05-02T02:48:20.939650Z","shell.execute_reply.started":"2024-05-02T02:48:15.145129Z","shell.execute_reply":"2024-05-02T02:48:20.938688Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"id":"GtXVCxFTMG6b","execution":{"iopub.status.busy":"2024-05-02T02:48:20.942154Z","iopub.execute_input":"2024-05-02T02:48:20.943037Z","iopub.status.idle":"2024-05-02T02:48:20.949575Z","shell.execute_reply.started":"2024-05-02T02:48:20.942983Z","shell.execute_reply":"2024-05-02T02:48:20.948230Z"},"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))#這邊會只指\"P\",\"A\"的欄位嗎?\n        if col[-1] in (\"D\"):\n            df = df.with_columns(pl.col(col).cast(pl.Date).alias(col))\n\n    return df\n#把浮點數的col存進dataframe中，data也是\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\n#cost1s","metadata":{"id":"QKAhydKpMG6b","execution":{"iopub.status.busy":"2024-05-02T02:48:20.953535Z","iopub.execute_input":"2024-05-02T02:48:20.953978Z","iopub.status.idle":"2024-05-02T02:48:20.968688Z","shell.execute_reply.started":"2024-05-02T02:48:20.953945Z","shell.execute_reply":"2024-05-02T02:48:20.966836Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"用這篇當範例https://www.kaggle.com/code/cwhybe/team9-baseline-v4/notebook#Submission</br>","metadata":{"id":"dpPhJTdQMG6c"}},{"cell_type":"markdown","source":"# Load Basetable","metadata":{"id":"Hp1V6WgyMG6c"}},{"cell_type":"code","source":"#cost2s\n# train\ntra_base_p = pl.read_csv(dataPath + \"csv_files/train/train_base.csv\")\ntra_base_p = tra_base_p.with_columns(pl.col('date_decision').str.to_date())\n\n# test\ntest_base_p = pl.read_csv(dataPath + \"csv_files/test/test_base.csv\")\ntest_base_p = test_base_p.with_columns(pl.col('date_decision').str.to_date())","metadata":{"id":"jckAARN8MG6d","execution":{"iopub.status.busy":"2024-05-02T02:48:20.971664Z","iopub.execute_input":"2024-05-02T02:48:20.972291Z","iopub.status.idle":"2024-05-02T02:48:21.950631Z","shell.execute_reply.started":"2024-05-02T02:48:20.972258Z","shell.execute_reply":"2024-05-02T02:48:21.949163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#cost15s\n# train\ntra_sta_p = 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)\n#tra_sta_cb_p= pl.read_csv(dataPath + \"csv_files/train/train_static_cb_0.csv\").pipe(set_table_dtypes)\n\n# test\ntest_sta_p = 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)\n#test_static_cb = pl.read_csv(dataPath + \"csv_files/test/test_static_cb_0.csv\").pipe(set_table_dtypes)\n#cost14s","metadata":{"id":"WSTabwBOMG6d","execution":{"iopub.status.busy":"2024-05-02T02:48:21.952414Z","iopub.execute_input":"2024-05-02T02:48:21.953132Z","iopub.status.idle":"2024-05-02T02:48:37.054887Z","shell.execute_reply.started":"2024-05-02T02:48:21.953071Z","shell.execute_reply":"2024-05-02T02:48:37.053572Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#cost1s\nselected_sta_p_cols = []\nfor col in tra_sta_p.columns:\n    if col[-1] in (\"A\", \"D\", \"M\", 'P', 'T', \"L\"):\n        selected_sta_p_cols.append(col)\nprint(selected_sta_p_cols)","metadata":{"id":"SA3RDrn0MG6d","outputId":"21c8bfa1-92d0-4506-ee7d-411105be7709","execution":{"iopub.status.busy":"2024-05-02T02:48:37.056670Z","iopub.execute_input":"2024-05-02T02:48:37.057058Z","iopub.status.idle":"2024-05-02T02:48:37.067664Z","shell.execute_reply.started":"2024-05-02T02:48:37.057025Z","shell.execute_reply":"2024-05-02T02:48:37.065980Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 合併tarin set的base層+0層","metadata":{"id":"uzAHPq2PMG6e"}},{"cell_type":"code","source":"#cost2s\ndata_p = tra_base_p.join(\n    tra_sta_p.select([\"case_id\"]+selected_sta_p_cols), how=\"left\", on=\"case_id\"\n)\n#cost3s","metadata":{"id":"89V7pUTEMG6e","execution":{"iopub.status.busy":"2024-05-02T02:48:37.069750Z","iopub.execute_input":"2024-05-02T02:48:37.070341Z","iopub.status.idle":"2024-05-02T02:48:38.376712Z","shell.execute_reply.started":"2024-05-02T02:48:37.070249Z","shell.execute_reply":"2024-05-02T02:48:38.375746Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#cost2s\ndata_p","metadata":{"id":"_2rP-8puMG6e","outputId":"612d4fcf-1926-43d1-b53a-48752e239eb7","execution":{"iopub.status.busy":"2024-05-02T02:48:38.377680Z","iopub.execute_input":"2024-05-02T02:48:38.377989Z","iopub.status.idle":"2024-05-02T02:48:38.422710Z","shell.execute_reply.started":"2024-05-02T02:48:38.377964Z","shell.execute_reply":"2024-05-02T02:48:38.421484Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def calculate_date_difference(df):\n    for col in df.columns:\n        if col[-1] == \"D\":\n            df = df.with_columns(\n                (pl.col('date_decision') - pl.col(col)).cast(pl.Int64).alias(col)#計算日期差異，可能以秒計算\n            )\n    return df","metadata":{"id":"fKFkjoBXMG6e","execution":{"iopub.status.busy":"2024-05-02T02:48:38.424257Z","iopub.execute_input":"2024-05-02T02:48:38.424701Z","iopub.status.idle":"2024-05-02T02:48:38.432300Z","shell.execute_reply.started":"2024-05-02T02:48:38.424660Z","shell.execute_reply":"2024-05-02T02:48:38.430691Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_p = calculate_date_difference(data_p)\ndata_p","metadata":{"id":"rK_wc-MXMG6f","outputId":"a452261f-d050-4f14-ae4c-e051cf4a7527","execution":{"iopub.status.busy":"2024-05-02T02:48:38.436499Z","iopub.execute_input":"2024-05-02T02:48:38.437054Z","iopub.status.idle":"2024-05-02T02:48:39.106755Z","shell.execute_reply.started":"2024-05-02T02:48:38.437020Z","shell.execute_reply":"2024-05-02T02:48:39.105315Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_submission_p = test_base_p.join(\n    test_sta_p.select([\"case_id\"]+selected_sta_p_cols), how=\"left\", on=\"case_id\"\n)","metadata":{"id":"RDAJxbbwMG6f","execution":{"iopub.status.busy":"2024-05-02T02:48:39.109055Z","iopub.execute_input":"2024-05-02T02:48:39.109578Z","iopub.status.idle":"2024-05-02T02:48:39.118465Z","shell.execute_reply.started":"2024-05-02T02:48:39.109536Z","shell.execute_reply":"2024-05-02T02:48:39.116845Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_submission_p = calculate_date_difference(data_submission_p)","metadata":{"id":"91o8BzDzMG6f","execution":{"iopub.status.busy":"2024-05-02T02:48:39.120572Z","iopub.execute_input":"2024-05-02T02:48:39.121557Z","iopub.status.idle":"2024-05-02T02:48:39.135309Z","shell.execute_reply.started":"2024-05-02T02:48:39.121518Z","shell.execute_reply":"2024-05-02T02:48:39.133805Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_submission_p","metadata":{"id":"1zqgY0JXMG6f","outputId":"739038be-b250-469b-fe61-1fe24b9f9010","execution":{"iopub.status.busy":"2024-05-02T02:48:39.137537Z","iopub.execute_input":"2024-05-02T02:48:39.138082Z","iopub.status.idle":"2024-05-02T02:48:39.165911Z","shell.execute_reply.started":"2024-05-02T02:48:39.138039Z","shell.execute_reply":"2024-05-02T02:48:39.164598Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 交叉驗證","metadata":{"id":"_pbpZragMG6g"}},{"cell_type":"code","source":"#cost27s\ncase_ids = data_p[\"case_id\"].unique().shuffle(seed=1)#cost29s\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_p.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_p.filter(pl.col(\"case_id\").is_in(case_ids))[[\"case_id\", \"WEEK_NUM\", \"target\"]].to_pandas(),\n        data_p.filter(pl.col(\"case_id\").is_in(case_ids))[cols_pred].to_pandas(),\n        data_p.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)\n\nprint('\\n')\nprint(f\"Train: {X_train.shape}\")\nprint(f\"Valid: {X_valid.shape}\")\nprint(f\"Test: {X_test.shape}\")","metadata":{"id":"QyHqTyjtMG6g","outputId":"ba29694c-026b-4654-951f-bf8a644d9385","execution":{"iopub.status.busy":"2024-05-02T02:48:39.167875Z","iopub.execute_input":"2024-05-02T02:48:39.168282Z","iopub.status.idle":"2024-05-02T02:49:24.701646Z","shell.execute_reply.started":"2024-05-02T02:48:39.168249Z","shell.execute_reply":"2024-05-02T02:49:24.699383Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# LGBM","metadata":{"id":"UUpds2KhMG6g"}},{"cell_type":"code","source":"#cos155s\nlgb_train = lgb.Dataset(X_train, label=y_train)#cost174s\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\": 4,\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":{"id":"ozeSW9lMMG6g","outputId":"a6b76572-e43c-4328-be38-abd8245b45da","execution":{"iopub.status.busy":"2024-05-02T02:49:24.704915Z","iopub.execute_input":"2024-05-02T02:49:24.705792Z","iopub.status.idle":"2024-05-02T02:51:51.370617Z","shell.execute_reply.started":"2024-05-02T02:49:24.705729Z","shell.execute_reply":"2024-05-02T02:51:51.369038Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# GINI & AUC","metadata":{"id":"26Lu4FW9MG6g"}},{"cell_type":"code","source":"#cost26s\nfor 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\"])}')\n\n\ndef 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('\\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":{"id":"D0YtUfKzMG6g","outputId":"88265f08-923d-4f6a-c091-3d582d7fec44","execution":{"iopub.status.busy":"2024-05-02T02:51:51.372685Z","iopub.execute_input":"2024-05-02T02:51:51.373057Z","iopub.status.idle":"2024-05-02T02:52:13.853008Z","shell.execute_reply.started":"2024-05-02T02:51:51.373027Z","shell.execute_reply":"2024-05-02T02:52:13.851604Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# CATBOOST","metadata":{"id":"2id7MMZvMG6h"}},{"cell_type":"code","source":"#cost8908s(i.e. 2.47hrs)\nimport 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":{"id":"PNcLD1UFMG6h","outputId":"5c112f2a-a4e3-47b7-ab24-22f0f612da02","execution":{"iopub.status.busy":"2024-05-02T02:52:13.855368Z","iopub.execute_input":"2024-05-02T02:52:13.855906Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# catboost主要是高效合理地处理类别型特征","metadata":{"id":"coQ9T6d4MG6h"}},{"cell_type":"markdown","source":"# XGBOOST model","metadata":{"id":"HMGkkVeIMG6h"}},{"cell_type":"code","source":"#cost344s\nimport 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":{"id":"7MitvnJjMG6h","outputId":"38b01a4a-2a0c-4a18-dd63-bf4044a770b9","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submission","metadata":{"id":"KIMsJqE3MG6i"}},{"cell_type":"markdown","source":"submission","metadata":{"id":"lB8JlkrcMG6i"}},{"cell_type":"code","source":"X_submission = data_submission_p[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\n#for col in cat_features:\n#    X_submission_processed[col] = X_submission_processed[col].cat.add_categories('Missing').fillna('Missing')\n\n#lgb_pred = lgb_model.predict(X_submission)\nxgb_pred = xgb_model.predict(X_submission)\n#cat_pred = cat_model.predict(X_submission_processed)\n\ny_submission_pred = np.mean([xgb_pred], axis=0)\nsubmission = pd.DataFrame({\n    \"case_id\": data_submission_p[\"case_id\"].to_numpy(),\n    \"score\": y_submission_pred\n}).set_index('case_id')\nsubmission.to_csv(\"./submission.csv\")\nsubmission","metadata":{"id":"HgsQnIQfMG6i","outputId":"ccfabfa0-2c0f-405a-ef1c-19361365e261","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.DataFrame({\n    \"case_id\": data_submission_p[\"case_id\"].to_numpy(),\n    \"score\": y_submission_pred\n}).set_index('case_id')\nsubmission.to_csv(\"./submission.csv\")","metadata":{"id":"k7sXqosPMG6i","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 以上完成</br>\n並完成lgbm的建模與交叉驗證</br>\n是參考這個程式碼：https://www.kaggle.com/code/cwhybe/team9-baseline-v4/notebook#Submission</br>\n-----------------------------------</br>\n","metadata":{"id":"Uy-BP1keMG6i"}}]}