{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","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":30786,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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\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","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np \nimport sklearn\nimport os \nimport time\nimport datetime\nimport lightgbm as lgb\nfrom lightgbm import LGBMRegressor\nimport polars as pl\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_auc_score ","metadata":{"execution":{"iopub.status.busy":"2024-10-06T07:46:24.369422Z","iopub.execute_input":"2024-10-06T07:46:24.370098Z","iopub.status.idle":"2024-10-06T07:46:29.765785Z","shell.execute_reply.started":"2024-10-06T07:46:24.370044Z","shell.execute_reply":"2024-10-06T07:46:29.764258Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-10-06T07:46:36.571699Z","iopub.execute_input":"2024-10-06T07:46:36.572466Z","iopub.status.idle":"2024-10-06T07:46:36.578679Z","shell.execute_reply.started":"2024-10-06T07:46:36.572418Z","shell.execute_reply":"2024-10-06T07:46:36.577141Z"},"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    return df","metadata":{"execution":{"iopub.status.busy":"2024-10-06T07:46:38.762574Z","iopub.execute_input":"2024-10-06T07:46:38.763077Z","iopub.status.idle":"2024-10-06T07:46:38.770897Z","shell.execute_reply.started":"2024-10-06T07:46:38.763032Z","shell.execute_reply":"2024-10-06T07:46:38.769340Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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":"2024-10-06T07:46:40.854351Z","iopub.execute_input":"2024-10-06T07:46:40.854811Z","iopub.status.idle":"2024-10-06T07:46:40.865384Z","shell.execute_reply.started":"2024-10-06T07:46:40.854767Z","shell.execute_reply":"2024-10-06T07:46:40.864030Z"},"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":"2024-10-06T07:46:43.959515Z","iopub.execute_input":"2024-10-06T07:46:43.960022Z","iopub.status.idle":"2024-10-06T07:47:02.234657Z","shell.execute_reply.started":"2024-10-06T07:46:43.959974Z","shell.execute_reply":"2024-10-06T07:47:02.233125Z"},"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":"2024-10-06T07:47:14.379476Z","iopub.execute_input":"2024-10-06T07:47:14.380062Z","iopub.status.idle":"2024-10-06T07:47:14.474196Z","shell.execute_reply.started":"2024-10-06T07:47:14.380008Z","shell.execute_reply":"2024-10-06T07:47:14.472917Z"},"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)\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\"})\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)\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)\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":"2024-10-06T07:47:17.936766Z","iopub.execute_input":"2024-10-06T07:47:17.937221Z","iopub.status.idle":"2024-10-06T07:47:21.213401Z","shell.execute_reply.started":"2024-10-06T07:47:17.937180Z","shell.execute_reply":"2024-10-06T07:47:21.212207Z"},"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)\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":"2024-10-06T07:47:21.215466Z","iopub.execute_input":"2024-10-06T07:47:21.215889Z","iopub.status.idle":"2024-10-06T07:47:21.236619Z","shell.execute_reply.started":"2024-10-06T07:47:21.215846Z","shell.execute_reply":"2024-10-06T07:47:21.235056Z"},"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=0.8, random_state=1)\ncase_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.8, 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":"2024-10-06T07:47:27.754557Z","iopub.execute_input":"2024-10-06T07:47:27.755982Z","iopub.status.idle":"2024-10-06T07:47:36.622026Z","shell.execute_reply.started":"2024-10-06T07:47:27.755917Z","shell.execute_reply":"2024-10-06T07:47:36.620901Z"},"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":"2024-10-06T07:47:36.624074Z","iopub.execute_input":"2024-10-06T07:47:36.624587Z","iopub.status.idle":"2024-10-06T07:47:36.631546Z","shell.execute_reply.started":"2024-10-06T07:47:36.624532Z","shell.execute_reply":"2024-10-06T07:47:36.630269Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.head()","metadata":{"execution":{"iopub.status.busy":"2024-10-06T07:52:19.698317Z","iopub.execute_input":"2024-10-06T07:52:19.699493Z","iopub.status.idle":"2024-10-06T07:52:19.745185Z","shell.execute_reply.started":"2024-10-06T07:52:19.699429Z","shell.execute_reply":"2024-10-06T07:52:19.743899Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"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\": 6,\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":"2024-10-06T07:58:13.797135Z","iopub.execute_input":"2024-10-06T07:58:13.798157Z","iopub.status.idle":"2024-10-06T07:59:25.777702Z","shell.execute_reply.started":"2024-10-06T07:58:13.798082Z","shell.execute_reply":"2024-10-06T07:59:25.775930Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import xgboost as xgb\nparams_xgb = {\n    'objective': 'reg:squarederror',  # 使用回归任务\n    'eval_metric': 'rmse',  # 评估指标，均方根误差\n    'eta': 0.1,  # 学习率\n    'max_depth': 6,  # 树的深度\n    'tree_method': 'hist',  # 使用 hist 方法以支持类别型特征\n    'enable_categorical': True  # 启用类别特征\n}\nxgb_train = xgb.DMatrix(X_train, label=y_train,enable_categorical=True)\nxgb_valid = xgb.DMatrix(X_valid, label=y_valid,enable_categorical=True)\nevals = [(xgb_train, 'train'), (xgb_valid, 'eval')]\nxgb_model=xgb.train(\n    params_xgb,\n    xgb_train,\n    num_boost_round=500, evals=evals, early_stopping_rounds=10\n)\n","metadata":{"execution":{"iopub.status.busy":"2024-10-06T08:09:17.507705Z","iopub.execute_input":"2024-10-06T08:09:17.508260Z","iopub.status.idle":"2024-10-06T08:09:53.066105Z","shell.execute_reply.started":"2024-10-06T08:09:17.508211Z","shell.execute_reply":"2024-10-06T08:09:53.064842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-06T08:10:59.694321Z","iopub.execute_input":"2024-10-06T08:10:59.694886Z","iopub.status.idle":"2024-10-06T08:10:59.834957Z","shell.execute_reply.started":"2024-10-06T08:10:59.694835Z","shell.execute_reply":"2024-10-06T08:10:59.833787Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"xgb_submission = xgb.DMatrix(X_submission, enable_categorical=True)\n\n# 使用训练好的模型进行预测\ny_submission_pred_1 = xgb_model.predict(xgb_submission)","metadata":{"execution":{"iopub.status.busy":"2024-10-06T08:13:01.365061Z","iopub.execute_input":"2024-10-06T08:13:01.365545Z","iopub.status.idle":"2024-10-06T08:13:01.392845Z","shell.execute_reply.started":"2024-10-06T08:13:01.365502Z","shell.execute_reply":"2024-10-06T08:13:01.391524Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_submission_2=np.mean([y_submission_pred,y_submission_pred_1],axis=0)","metadata":{"execution":{"iopub.status.busy":"2024-10-06T08:14:15.877942Z","iopub.execute_input":"2024-10-06T08:14:15.878362Z","iopub.status.idle":"2024-10-06T08:14:15.884355Z","shell.execute_reply.started":"2024-10-06T08:14:15.878323Z","shell.execute_reply":"2024-10-06T08:14:15.883057Z"},"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_2\n}).set_index('case_id')\nsubmission.to_csv(\"./submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-10-06T08:14:37.260542Z","iopub.execute_input":"2024-10-06T08:14:37.261052Z","iopub.status.idle":"2024-10-06T08:14:37.270517Z","shell.execute_reply.started":"2024-10-06T08:14:37.260998Z","shell.execute_reply":"2024-10-06T08:14:37.269197Z"},"trusted":true},"execution_count":null,"outputs":[]}]}