{"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":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"},{"sourceId":8410063,"sourceType":"datasetVersion","datasetId":5005254},{"sourceId":33095,"sourceType":"modelInstanceVersion","modelInstanceId":27710},{"sourceId":33096,"sourceType":"modelInstanceVersion","modelInstanceId":27711}],"dockerImageVersionId":30683,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## Training Notebooks\n- lgb https://www.kaggle.com/code/sunghoshim/home-credit-lgb-train-copy\n- cat https://www.kaggle.com/sunghoshim/home-credit-cat-train-copy\n\n## Reference\n- https://www.kaggle.com/code/xiaoleilian/home-credit-ensemble-infer-lgb-cat\n","metadata":{}},{"cell_type":"code","source":"import joblib\nfrom pathlib import Path\nimport gc\nfrom glob import glob\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nfrom sklearn.base import BaseEstimator, RegressorMixin\nfrom sklearn.metrics import roc_auc_score\nimport lightgbm as lgb\n\nimport warnings\nwarnings.filterwarnings('ignore')\n\nROOT = '/kaggle/input/home-credit-credit-risk-model-stability'","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-05-14T11:17:25.042876Z","iopub.execute_input":"2024-05-14T11:17:25.043281Z","iopub.status.idle":"2024-05-14T11:17:30.243829Z","shell.execute_reply.started":"2024-05-14T11:17:25.043236Z","shell.execute_reply":"2024-05-14T11:17:30.242737Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Pipeline:\n\n    def set_table_dtypes(df):\n        for col in df.columns:\n            if col in [\"case_id\", \"WEEK_NUM\", \"num_group1\", \"num_group2\"]:\n                df = df.with_columns(pl.col(col).cast(pl.Int64))\n            elif col in [\"date_decision\"]:\n                df = df.with_columns(pl.col(col).cast(pl.Date))\n            elif col[-1] in (\"P\", \"A\"):\n                df = df.with_columns(pl.col(col).cast(pl.Float64))\n            elif col[-1] in (\"M\",):\n                df = df.with_columns(pl.col(col).cast(pl.String))\n            elif col[-1] in (\"D\",):\n                df = df.with_columns(pl.col(col).cast(pl.Date))\n        return df\n\n    def handle_dates(df):\n        for col in df.columns:\n            if col[-1] in (\"D\",):\n                df = df.with_columns(pl.col(col) - pl.col(\"date_decision\"))  #!!?\n                df = df.with_columns(pl.col(col).dt.total_days()) # t - t-1\n        df = df.drop(\"date_decision\", \"MONTH\")\n        return df\n\n    def filter_cols(df):\n        for col in df.columns:\n            if col not in [\"target\", \"case_id\", \"WEEK_NUM\"]:\n                isnull = df[col].is_null().mean()\n                if isnull > 0.7:\n                    df = df.drop(col)\n        \n        for col in df.columns:\n            if (col not in [\"target\", \"case_id\", \"WEEK_NUM\"]) & (df[col].dtype == pl.String):\n                freq = df[col].n_unique()\n                if (freq == 1) | (freq > 200):\n                    df = df.drop(col)\n        \n        return df\n\n\n\nclass Aggregator:\n    # Please add or subtract features yourself, be aware that too many features will take up too much space.\n    def num_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"P\", \"A\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        # expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n        expr_median = [pl.median(col).alias(f\"median_{col}\") for col in cols]\n        expr_var = [pl.var(col).alias(f\"var_{col}\") for col in cols]\n\n        return expr_max + expr_last + expr_mean \n\n    def date_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"D\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        # expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        # expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n        expr_median = [pl.median(col).alias(f\"median_{col}\") for col in cols]\n\n        return expr_max + expr_last + expr_mean \n\n    def str_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"M\",)]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        # expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        # expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        # expr_count = [pl.count(col).alias(f\"count_{col}\") for col in cols]\n        return expr_max + expr_last  # +expr_count\n\n    def other_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"T\", \"L\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        # expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        # expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        return expr_max + expr_last\n\n    def count_expr(df):\n        cols = [col for col in df.columns if \"num_group\" in col]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        # expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        # expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        return expr_max + expr_last\n\n    def get_exprs(df):\n        exprs = Aggregator.num_expr(df) + \\\n                Aggregator.date_expr(df) + \\\n                Aggregator.str_expr(df) + \\\n                Aggregator.other_expr(df) + \\\n                Aggregator.count_expr(df)\n\n        return exprs","metadata":{"execution":{"iopub.status.busy":"2024-05-14T11:17:30.245789Z","iopub.execute_input":"2024-05-14T11:17:30.246095Z","iopub.status.idle":"2024-05-14T11:17:30.269106Z","shell.execute_reply.started":"2024-05-14T11:17:30.246070Z","shell.execute_reply":"2024-05-14T11:17:30.268251Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def read_file(path, depth=None):\n    df = pl.read_parquet(path)\n    df = df.pipe(Pipeline.set_table_dtypes)\n    if depth in [1,2]:\n        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df)) \n    return df\n\ndef read_files(regex_path, depth=None):\n    chunks = []\n    \n    for path in glob(str(regex_path)):\n        df = pl.read_parquet(path)\n        df = df.pipe(Pipeline.set_table_dtypes)\n        if depth in [1, 2]:\n            df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n        chunks.append(df)\n    \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    df = df.unique(subset=[\"case_id\"])\n    return df\n\n\ndef feature_eng(df_base, depth_0, depth_1, depth_2):\n    df_base = (\n        df_base\n        .with_columns(\n            month_decision = pl.col(\"date_decision\").dt.month(),\n            weekday_decision = pl.col(\"date_decision\").dt.weekday(),\n        )\n    )\n    for i, df in enumerate(depth_0 + depth_1 + depth_2):\n        df_base = df_base.join(df, how=\"left\", on=\"case_id\", suffix=f\"_{i}\")\n    df_base = df_base.pipe(Pipeline.handle_dates)\n    return df_base\n\n\ndef to_pandas(df_data, cat_cols=None):\n    df_data = df_data.to_pandas()\n    if cat_cols is None:\n        cat_cols = list(df_data.select_dtypes(\"object\").columns)\n    df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n    return df_data, cat_cols\n\n\ndef reduce_mem_usage(df):\n    \"\"\" iterate through all the columns of a dataframe and modify the data type\n        to reduce memory usage.        \n    \"\"\"\n    start_mem = df.memory_usage().sum() / 1024**2\n    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n    \n    for col in df.columns:\n        col_type = df[col].dtype\n        if str(col_type)==\"category\":\n            continue\n        \n        if col_type != object:\n            c_min = df[col].min()\n            c_max = df[col].max()\n            if str(col_type)[:3] == 'int':\n                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n                    df[col] = df[col].astype(np.int8)\n                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n                    df[col] = df[col].astype(np.int16)\n                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n                    df[col] = df[col].astype(np.int32)\n                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n                    df[col] = df[col].astype(np.int64)  \n            else:\n                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n                    df[col] = df[col].astype(np.float16)\n                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n                    df[col] = df[col].astype(np.float32)\n                else:\n                    df[col] = df[col].astype(np.float64)\n        else:\n            continue\n    end_mem = df.memory_usage().sum() / 1024**2\n    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))\n    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))\n    \n    return df","metadata":{"execution":{"iopub.status.busy":"2024-05-14T11:17:30.270304Z","iopub.execute_input":"2024-05-14T11:17:30.270594Z","iopub.status.idle":"2024-05-14T11:17:30.291555Z","shell.execute_reply.started":"2024-05-14T11:17:30.270571Z","shell.execute_reply":"2024-05-14T11:17:30.290824Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Load Models","metadata":{}},{"cell_type":"code","source":"lgb_notebook_info = joblib.load('/kaggle/input/lisa-hc/notebook_info.joblib')\n\ncols = lgb_notebook_info['cols']\ncat_cols = lgb_notebook_info['cat_cols']\nprint(f\"- [lgb] len(cols): {len(cols)}\")\nprint(f\"- [lgb] len(cat_cols): {len(cat_cols)}\")\n\nlgb_models = joblib.load('/kaggle/input/lisa-hc/lgb_models.joblib')\nlgb_models","metadata":{"execution":{"iopub.status.busy":"2024-05-14T11:17:30.293390Z","iopub.execute_input":"2024-05-14T11:17:30.293657Z","iopub.status.idle":"2024-05-14T11:17:30.909859Z","shell.execute_reply.started":"2024-05-14T11:17:30.293635Z","shell.execute_reply":"2024-05-14T11:17:30.908989Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat_notebook_info = joblib.load('/kaggle/input/lisa-hc/notebook_info.joblib')\n\n\ncat_models = joblib.load('/kaggle/input/lisa-hc/cat_models.joblib')\ncat_models","metadata":{"execution":{"iopub.status.busy":"2024-05-14T11:17:30.910882Z","iopub.execute_input":"2024-05-14T11:17:30.911161Z","iopub.status.idle":"2024-05-14T11:17:35.243264Z","shell.execute_reply.started":"2024-05-14T11:17:30.911139Z","shell.execute_reply":"2024-05-14T11:17:35.242384Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Prepare df_test","metadata":{}},{"cell_type":"code","source":"ROOT            = Path(\"/kaggle/input/home-credit-credit-risk-model-stability\")\n\nTEST_DIR        = ROOT / \"parquet_files\" / \"test\"\n\ndata_store = {\n    \"df_base\": read_file(TEST_DIR / \"test_base.parquet\"),\n    \"depth_0\": [\n        read_file(TEST_DIR / \"test_static_cb_0.parquet\"),\n        read_files(TEST_DIR / \"test_static_0_*.parquet\"),\n    ],\n    \"depth_1\": [\n        read_files(TEST_DIR / \"test_applprev_1_*.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_a_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_b_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_c_1.parquet\", 1),\n        read_files(TEST_DIR / \"test_credit_bureau_a_1_*.parquet\", 1),\n        read_file(TEST_DIR / \"test_credit_bureau_b_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_other_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_person_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_deposit_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_debitcard_1.parquet\", 1),\n    ],\n    \"depth_2\": [\n        read_file(TEST_DIR / \"test_credit_bureau_b_2.parquet\", 2),\n        read_files(TEST_DIR / \"test_credit_bureau_a_2_*.parquet\", 2),\n        read_file(TEST_DIR / \"test_applprev_2.parquet\", 2),\n        read_file(TEST_DIR / \"test_person_2.parquet\", 2)\n    ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-05-14T11:17:35.244369Z","iopub.execute_input":"2024-05-14T11:17:35.244651Z","iopub.status.idle":"2024-05-14T11:17:35.697751Z","shell.execute_reply.started":"2024-05-14T11:17:35.244627Z","shell.execute_reply":"2024-05-14T11:17:35.696727Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = feature_eng(**data_store)\nprint(\"test data shape:\\t\", df_test.shape)\ndel data_store\ngc.collect()\n\ndf_test = df_test.select(['case_id'] + cols)\n\ndf_test, cat_cols = to_pandas(df_test, cat_cols)\ndf_test = reduce_mem_usage(df_test)\ndf_test = df_test.set_index('case_id')\nprint(\"test data shape:\\t\", df_test.shape)\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-14T11:17:35.699061Z","iopub.execute_input":"2024-05-14T11:17:35.699352Z","iopub.status.idle":"2024-05-14T11:17:36.269516Z","shell.execute_reply.started":"2024-05-14T11:17:35.699327Z","shell.execute_reply":"2024-05-14T11:17:36.268495Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test","metadata":{"execution":{"iopub.status.busy":"2024-05-14T11:17:36.270842Z","iopub.execute_input":"2024-05-14T11:17:36.271211Z","iopub.status.idle":"2024-05-14T11:17:36.311520Z","shell.execute_reply.started":"2024-05-14T11:17:36.271179Z","shell.execute_reply":"2024-05-14T11:17:36.310591Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Voting Model","metadata":{}},{"cell_type":"code","source":"class VotingModel(BaseEstimator, RegressorMixin):\n    def __init__(self, estimators):\n        super().__init__()\n        self.estimators = estimators\n        \n    def fit(self, X, y=None):\n        return self\n    \n    def predict(self, X):\n        y_preds = [estimator.predict(X) for estimator in self.estimators]\n        return np.mean(y_preds, axis=0)\n     \n    def predict_proba(self, X):      \n        # lgb\n        y_preds = [estimator.predict_proba(X) for estimator in self.estimators[:5]]\n        \n        # cat        \n        X[cat_cols] = X[cat_cols].astype(str)\n        y_preds += [estimator.predict_proba(X) for estimator in self.estimators[-5:]]\n        \n        return np.mean(y_preds, axis=0)","metadata":{"execution":{"iopub.status.busy":"2024-05-14T11:17:36.312703Z","iopub.execute_input":"2024-05-14T11:17:36.313056Z","iopub.status.idle":"2024-05-14T11:17:36.322469Z","shell.execute_reply.started":"2024-05-14T11:17:36.313016Z","shell.execute_reply":"2024-05-14T11:17:36.321614Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = VotingModel(lgb_models + cat_models)\nlen(model.estimators)","metadata":{"execution":{"iopub.status.busy":"2024-05-14T11:17:36.326975Z","iopub.execute_input":"2024-05-14T11:17:36.327247Z","iopub.status.idle":"2024-05-14T11:17:36.333728Z","shell.execute_reply.started":"2024-05-14T11:17:36.327226Z","shell.execute_reply":"2024-05-14T11:17:36.332786Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred = pd.Series(model.predict_proba(df_test)[:, 1], index=df_test.index)\ndf_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\ndf_subm = df_subm.set_index(\"case_id\")\n\ndf_subm[\"score\"] = y_pred\ndf_subm.to_csv(\"submission.csv\")\ndf_subm","metadata":{"execution":{"iopub.status.busy":"2024-05-14T11:17:36.335021Z","iopub.execute_input":"2024-05-14T11:17:36.335694Z","iopub.status.idle":"2024-05-14T11:17:36.911138Z","shell.execute_reply.started":"2024-05-14T11:17:36.335660Z","shell.execute_reply":"2024-05-14T11:17:36.910170Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}