{"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":7602123,"sourceType":"competition"},{"sourceId":7584174,"sourceType":"datasetVersion","datasetId":4414761}],"dockerImageVersionId":30648,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Reference \nreference notebook: [here](https://www.kaggle.com/code/greysky/home-credit-baseline)\n\n**Thank you for viewing, your upvotes!!**","metadata":{}},{"cell_type":"code","source":"import os\nimport gc\nfrom glob import glob\nfrom pathlib import Path\nfrom datetime import datetime\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.model_selection import StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, RegressorMixin\nimport joblib\nimport lightgbm as lgb\nimport warnings\nwarnings.simplefilter(action='ignore', category=FutureWarning)","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:41:49.243781Z","iopub.execute_input":"2024-02-09T13:41:49.244133Z","iopub.status.idle":"2024-02-09T13:41:55.957739Z","shell.execute_reply.started":"2024-02-09T13:41:49.244104Z","shell.execute_reply":"2024-02-09T13:41:55.956735Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pre-Fitted 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        y_preds = [estimator.predict_proba(X) for estimator in self.estimators]\n        return np.mean(y_preds, axis=0)","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:41:55.959635Z","iopub.execute_input":"2024-02-09T13:41:55.959972Z","iopub.status.idle":"2024-02-09T13:41:55.967821Z","shell.execute_reply.started":"2024-02-09T13:41:55.959940Z","shell.execute_reply":"2024-02-09T13:41:55.966933Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pipeline","metadata":{}},{"cell_type":"code","source":"class Pipeline:\n    @staticmethod\n    def set_table_dtypes(df): #Standardize the dtype.\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\n        return df\n    \n    @staticmethod\n    def handle_dates(df): #Change the feature for D to the difference in days from date_decision.\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())\n                \n        df = df.drop(\"date_decision\", \"MONTH\")\n\n        return df\n    \n    @staticmethod\n    def filter_cols(df): #Remove those with an average is_null exceeding 0.95 and those that do not fall within the range 1 < nunique < 200.\n        for col in df.columns:\n            if col not in [\"target\", \"case_id\", \"WEEK_NUM\"]:\n                isnull = df[col].is_null().mean()\n\n                if isnull > 0.95:\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\n                if (freq == 1) | (freq > 200):\n                    df = df.drop(col)\n\n        return df","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:41:55.969084Z","iopub.execute_input":"2024-02-09T13:41:55.969465Z","iopub.status.idle":"2024-02-09T13:41:55.984113Z","shell.execute_reply.started":"2024-02-09T13:41:55.969432Z","shell.execute_reply":"2024-02-09T13:41:55.983255Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Automatic Aggregation","metadata":{}},{"cell_type":"code","source":"class Aggregator:\n    @staticmethod\n    def num_expr(df): #Extract the maximum and minimum values for features P and A, and add them as additional features.\n        cols = [col for col in df.columns if col[-1] in (\"P\", \"A\")]\n\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\n        return expr_max, expr_min\n\n    @staticmethod\n    def date_expr(df): #Extract the maximum and minimum values for features D, and add them as additional features.\n        cols = [col for col in df.columns if col[-1] in (\"D\",)]\n\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\n        return expr_max, expr_min\n\n    @staticmethod\n    def str_expr(df): #Extract the maximum and minimum values for features M, and add them as additional features.\n        cols = [col for col in df.columns if col[-1] in (\"M\",)]\n        \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\n        return expr_max, expr_min\n\n    @staticmethod\n    def other_expr(df): #Extract the maximum and minimum values for features T and L, and add them as additional features.\n        cols = [col for col in df.columns if col[-1] in (\"T\", \"L\")]\n        \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\n        return expr_max, expr_min\n    \n    @staticmethod\n    def count_expr(df): #Extract the maximum and minimum values for each num_group and add them as additional features.\n        cols = [col for col in df.columns if \"num_group\" in col]\n\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\n        return expr_max, expr_min\n\n    @staticmethod\n    def get_exprs(df): #Execute the above function and return the result.\n        maxexprs = Aggregator.num_expr(df)[0] + \\\n                Aggregator.date_expr(df)[0] + \\\n                Aggregator.str_expr(df)[0] + \\\n                Aggregator.other_expr(df)[0] + \\\n                Aggregator.count_expr(df)[0]\n        \n        minexprs = Aggregator.num_expr(df)[1] + \\\n                Aggregator.date_expr(df)[1] + \\\n                Aggregator.str_expr(df)[1] + \\\n                Aggregator.other_expr(df)[1] + \\\n                Aggregator.count_expr(df)[1]\n\n        return maxexprs, minexprs","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:41:55.985628Z","iopub.execute_input":"2024-02-09T13:41:55.985952Z","iopub.status.idle":"2024-02-09T13:41:56.004393Z","shell.execute_reply.started":"2024-02-09T13:41:55.985928Z","shell.execute_reply":"2024-02-09T13:41:56.003386Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### File I/O","metadata":{}},{"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    \n    if depth in [1, 2]:\n        maxexprs, minexprs = Aggregator.get_exprs(df)\n        df = df.group_by(\"case_id\").agg(*maxexprs, *minexprs)\n    \n    return df\n\ndef read_files(regex_path, depth=None):\n    chunks = []\n    for path in glob(str(regex_path)):\n        chunks.append(pl.read_parquet(path).pipe(Pipeline.set_table_dtypes))\n        \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    if depth in [1, 2]:\n        maxexprs, minexprs = Aggregator.get_exprs(df)\n        df = df.group_by(\"case_id\").agg(*maxexprs, *minexprs)\n    \n    return df","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:41:56.007173Z","iopub.execute_input":"2024-02-09T13:41:56.007487Z","iopub.status.idle":"2024-02-09T13:41:56.018229Z","shell.execute_reply.started":"2024-02-09T13:41:56.007464Z","shell.execute_reply":"2024-02-09T13:41:56.017346Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Engineering","metadata":{}},{"cell_type":"code","source":"def 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        \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        \n    df_base = df_base.pipe(Pipeline.handle_dates)\n    \n    return df_base","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:41:56.019228Z","iopub.execute_input":"2024-02-09T13:41:56.019493Z","iopub.status.idle":"2024-02-09T13:41:56.028567Z","shell.execute_reply.started":"2024-02-09T13:41:56.019470Z","shell.execute_reply":"2024-02-09T13:41:56.027593Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def to_pandas(df_data, cat_cols=None):\n    df_data = df_data.to_pandas()\n    \n    if cat_cols is None:\n        cat_cols = list(df_data.select_dtypes(\"object\").columns)\n    \n    df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n    \n    return df_data, cat_cols","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:41:56.029609Z","iopub.execute_input":"2024-02-09T13:41:56.029901Z","iopub.status.idle":"2024-02-09T13:41:56.038913Z","shell.execute_reply.started":"2024-02-09T13:41:56.029877Z","shell.execute_reply":"2024-02-09T13:41:56.037882Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Configuration","metadata":{}},{"cell_type":"code","source":"ROOT            = Path(\"/kaggle/input/home-credit-credit-risk-model-stability\")\nTRAIN_DIR       = ROOT / \"parquet_files\" / \"train\"\nTEST_DIR        = ROOT / \"parquet_files\" / \"test\"","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:41:56.040329Z","iopub.execute_input":"2024-02-09T13:41:56.040587Z","iopub.status.idle":"2024-02-09T13:41:56.048276Z","shell.execute_reply.started":"2024-02-09T13:41:56.040566Z","shell.execute_reply":"2024-02-09T13:41:56.047396Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Train Files Read & Feature Engineering","metadata":{}},{"cell_type":"code","source":"data_store = {\n    \"df_base\": read_file(TRAIN_DIR / \"train_base.parquet\"),\n    \"depth_0\": [\n        read_file(TRAIN_DIR / \"train_static_cb_0.parquet\"),\n        read_files(TRAIN_DIR / \"train_static_0_*.parquet\"),\n    ],\n    \"depth_1\": [\n        read_files(TRAIN_DIR / \"train_applprev_1_*.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_a_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_c_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_other_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_person_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_deposit_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_debitcard_1.parquet\", 1),\n    ],\n    \"depth_2\": [\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_2.parquet\", 2),\n    ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:41:56.051796Z","iopub.execute_input":"2024-02-09T13:41:56.052246Z","iopub.status.idle":"2024-02-09T13:42:30.670357Z","shell.execute_reply.started":"2024-02-09T13:41:56.052210Z","shell.execute_reply":"2024-02-09T13:42:30.669547Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = feature_eng(**data_store)\n\nprint(\"train data shape:\\t\", df_train.shape)","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:42:30.671525Z","iopub.execute_input":"2024-02-09T13:42:30.671875Z","iopub.status.idle":"2024-02-09T13:42:41.542274Z","shell.execute_reply.started":"2024-02-09T13:42:30.671843Z","shell.execute_reply":"2024-02-09T13:42:41.541380Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Test Files Read & Feature Engineering","metadata":{}},{"cell_type":"code","source":"data_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_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    ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:42:41.543699Z","iopub.execute_input":"2024-02-09T13:42:41.544034Z","iopub.status.idle":"2024-02-09T13:42:42.019628Z","shell.execute_reply.started":"2024-02-09T13:42:41.544007Z","shell.execute_reply":"2024-02-09T13:42:42.018576Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = feature_eng(**data_store)\n\nprint(\"test data shape:\\t\", df_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:42:42.020937Z","iopub.execute_input":"2024-02-09T13:42:42.021262Z","iopub.status.idle":"2024-02-09T13:42:42.059946Z","shell.execute_reply.started":"2024-02-09T13:42:42.021236Z","shell.execute_reply":"2024-02-09T13:42:42.059017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Elimination","metadata":{}},{"cell_type":"code","source":"df_train = df_train.pipe(Pipeline.filter_cols)\ndf_test = df_test.select([col for col in df_train.columns if col != \"target\"])\n\nprint(\"train data shape:\\t\", df_train.shape)\nprint(\"test data shape:\\t\", df_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:42:42.060968Z","iopub.execute_input":"2024-02-09T13:42:42.061253Z","iopub.status.idle":"2024-02-09T13:42:45.428011Z","shell.execute_reply.started":"2024-02-09T13:42:42.061230Z","shell.execute_reply":"2024-02-09T13:42:45.427136Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pandas Conversion","metadata":{}},{"cell_type":"code","source":"df_train, cat_cols = to_pandas(df_train)\ndf_test, cat_cols = to_pandas(df_test, cat_cols)","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:42:45.431516Z","iopub.execute_input":"2024-02-09T13:42:45.431790Z","iopub.status.idle":"2024-02-09T13:43:05.688335Z","shell.execute_reply.started":"2024-02-09T13:42:45.431767Z","shell.execute_reply":"2024-02-09T13:43:05.687474Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(df_train.shape)\ndf_train.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:43:05.689542Z","iopub.execute_input":"2024-02-09T13:43:05.689891Z","iopub.status.idle":"2024-02-09T13:43:05.719179Z","shell.execute_reply.started":"2024-02-09T13:43:05.689861Z","shell.execute_reply":"2024-02-09T13:43:05.718316Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(df_test.shape)\ndf_test.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:43:05.721743Z","iopub.execute_input":"2024-02-09T13:43:05.722012Z","iopub.status.idle":"2024-02-09T13:43:05.743942Z","shell.execute_reply.started":"2024-02-09T13:43:05.721989Z","shell.execute_reply":"2024-02-09T13:43:05.743031Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Garbage Collection","metadata":{}},{"cell_type":"code","source":"del data_store\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:43:05.745181Z","iopub.execute_input":"2024-02-09T13:43:05.745507Z","iopub.status.idle":"2024-02-09T13:43:05.880069Z","shell.execute_reply.started":"2024-02-09T13:43:05.745475Z","shell.execute_reply":"2024-02-09T13:43:05.879114Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Training","metadata":{}},{"cell_type":"code","source":"X = df_train.drop(columns=[\"target\", \"case_id\", \"WEEK_NUM\"])\ny = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\n\ncv = StratifiedGroupKFold(n_splits=5, shuffle=False)\n\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"max_depth\": 8,\n    \"learning_rate\": 0.05,\n    \"n_estimators\": 1000,\n    \"colsample_bytree\": 0.8, \n    \"colsample_bynode\": 0.8,\n    \"verbose\": -1,\n    \"random_state\": 42,\n    \"device\": \"gpu\",\n}\n\nfitted_models = []\n\nfor idx_train, idx_valid in cv.split(X, y, groups=weeks):\n    X_train, y_train = X.iloc[idx_train], y.iloc[idx_train]\n    X_valid, y_valid = X.iloc[idx_valid], y.iloc[idx_valid]\n\n    model = lgb.LGBMClassifier(**params)\n    model.fit(\n        X_train, y_train,\n        eval_set=[(X_valid, y_valid)],\n        callbacks=[lgb.log_evaluation(100), lgb.early_stopping(100)]\n    )\n\n    fitted_models.append(model)\n\nmodel = VotingModel(fitted_models)","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:43:05.881178Z","iopub.execute_input":"2024-02-09T13:43:05.881474Z","iopub.status.idle":"2024-02-09T13:59:08.815924Z","shell.execute_reply.started":"2024-02-09T13:43:05.881450Z","shell.execute_reply":"2024-02-09T13:59:08.814924Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Prediction","metadata":{}},{"cell_type":"code","source":"X_test = df_test.drop(columns=[\"WEEK_NUM\"])\nX_test = X_test.set_index(\"case_id\")\n\ny_pred = pd.Series(model.predict_proba(X_test)[:, 1], index=X_test.index)","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:59:08.817415Z","iopub.execute_input":"2024-02-09T13:59:08.817748Z","iopub.status.idle":"2024-02-09T13:59:09.133937Z","shell.execute_reply.started":"2024-02-09T13:59:08.817720Z","shell.execute_reply":"2024-02-09T13:59:09.132923Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Submission","metadata":{}},{"cell_type":"code","source":"df_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\ndf_subm = df_subm.set_index(\"case_id\")\n\ndf_subm[\"score\"] = y_pred","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:59:09.135248Z","iopub.execute_input":"2024-02-09T13:59:09.135550Z","iopub.status.idle":"2024-02-09T13:59:09.149406Z","shell.execute_reply.started":"2024-02-09T13:59:09.135525Z","shell.execute_reply":"2024-02-09T13:59:09.148508Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Check null: \", df_subm[\"score\"].isnull().any())\n\ndf_subm.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:59:09.150408Z","iopub.execute_input":"2024-02-09T13:59:09.150691Z","iopub.status.idle":"2024-02-09T13:59:09.160757Z","shell.execute_reply.started":"2024-02-09T13:59:09.150666Z","shell.execute_reply":"2024-02-09T13:59:09.159788Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-02-09T13:59:09.161944Z","iopub.execute_input":"2024-02-09T13:59:09.162248Z","iopub.status.idle":"2024-02-09T13:59:09.174736Z","shell.execute_reply.started":"2024-02-09T13:59:09.162222Z","shell.execute_reply":"2024-02-09T13:59:09.173876Z"},"trusted":true},"execution_count":null,"outputs":[]}]}