{"metadata":{"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30674,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true},"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.10.13"},"papermill":{"default_parameters":{},"duration":1221.035913,"end_time":"2024-03-11T20:40:31.474791","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2024-03-11T20:20:10.438878","version":"2.5.0"},"colab":{"provenance":[],"gpuType":"T4"},"accelerator":"GPU"},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# from google.colab import drive\n# drive.mount('/content/drive')","metadata":{"id":"D8YOHKE4XlD6","outputId":"a4418ec8-1481-4cb4-bcf5-0a9c074e920f"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# import os\n# os.chdir('/content/drive/MyDrive/home-credit')\n# !pwd","metadata":{"id":"lG-5HiXYf7mP","outputId":"b49bbf7a-9bf4-4a78-b5e5-16b21af36349"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport gc\nfrom glob import glob\nfrom pathlib import Path\nfrom datetime import datetime\n\nimport numpy as np\nimport pandas as pd\nimport polars as pl\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nfrom sklearn.model_selection import StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, ClassifierMixin\n\nimport lightgbm as lgb\n\nimport warnings\nwarnings.simplefilter(action='ignore', category=FutureWarning)","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","papermill":{"duration":6.175783,"end_time":"2024-03-11T20:20:19.343026","exception":false,"start_time":"2024-03-11T20:20:13.167243","status":"completed"},"tags":[],"id":"b9b059db","execution":{"iopub.status.busy":"2024-03-28T00:58:46.331956Z","iopub.execute_input":"2024-03-28T00:58:46.332681Z","iopub.status.idle":"2024-03-28T00:58:52.123452Z","shell.execute_reply.started":"2024-03-28T00:58:46.332649Z","shell.execute_reply":"2024-03-28T00:58:52.122458Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pre-Fitted Voting Model","metadata":{"papermill":{"duration":0.008777,"end_time":"2024-03-11T20:20:19.361579","exception":false,"start_time":"2024-03-11T20:20:19.352802","status":"completed"},"tags":[],"id":"0e7fb251"}},{"cell_type":"code","source":"class VotingModel(BaseEstimator, ClassifierMixin):\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":{"papermill":{"duration":0.018278,"end_time":"2024-03-11T20:20:19.389382","exception":false,"start_time":"2024-03-11T20:20:19.371104","status":"completed"},"tags":[],"id":"db0720f2","execution":{"iopub.status.busy":"2024-03-28T00:58:52.125200Z","iopub.execute_input":"2024-03-28T00:58:52.125480Z","iopub.status.idle":"2024-03-28T00:58:52.132554Z","shell.execute_reply.started":"2024-03-28T00:58:52.125456Z","shell.execute_reply":"2024-03-28T00:58:52.131708Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pipeline","metadata":{"papermill":{"duration":0.008615,"end_time":"2024-03-11T20:20:19.406942","exception":false,"start_time":"2024-03-11T20:20:19.398327","status":"completed"},"tags":[],"id":"619c2a3a"}},{"cell_type":"code","source":"\nclass Pipeline:\n    @staticmethod\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.Int32))\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.Utf8))\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):\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                df = df.with_columns(pl.col(col).cast(pl.Float32))\n\n        df = df.drop(\"date_decision\", \"MONTH\")\n\n        return df\n\n    @staticmethod\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\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.Utf8):\n                freq = df[col].n_unique()\n\n                if (freq == 1) | (freq > 200):\n                    df = df.drop(col)\n\n        return df","metadata":{"papermill":{"duration":0.023479,"end_time":"2024-03-11T20:20:19.439407","exception":false,"start_time":"2024-03-11T20:20:19.415928","status":"completed"},"tags":[],"id":"569dbecf","execution":{"iopub.status.busy":"2024-03-28T00:58:52.137507Z","iopub.execute_input":"2024-03-28T00:58:52.138167Z","iopub.status.idle":"2024-03-28T00:58:52.154377Z","shell.execute_reply.started":"2024-03-28T00:58:52.138136Z","shell.execute_reply":"2024-03-28T00:58:52.153451Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Automatic Aggregation","metadata":{"papermill":{"duration":0.008664,"end_time":"2024-03-11T20:20:19.457100","exception":false,"start_time":"2024-03-11T20:20:19.448436","status":"completed"},"tags":[],"id":"c49e3f30"}},{"cell_type":"code","source":"class Aggregator:\n    @staticmethod\n    def num_expr(df):\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\n        return expr_max\n\n    @staticmethod\n    def date_expr(df):\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\n        return expr_max\n\n    @staticmethod\n    def str_expr(df):\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\n        return expr_max\n\n    @staticmethod\n    def other_expr(df):\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\n        return expr_max\n\n    @staticmethod\n    def count_expr(df):\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\n        return expr_max\n\n    @staticmethod\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":{"papermill":{"duration":0.021569,"end_time":"2024-03-11T20:20:19.488325","exception":false,"start_time":"2024-03-11T20:20:19.466756","status":"completed"},"tags":[],"id":"842a310a","execution":{"iopub.status.busy":"2024-03-28T00:59:18.870560Z","iopub.execute_input":"2024-03-28T00:59:18.871400Z","iopub.status.idle":"2024-03-28T00:59:18.882720Z","shell.execute_reply.started":"2024-03-28T00:59:18.871369Z","shell.execute_reply":"2024-03-28T00:59:18.881762Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### File I/O","metadata":{"papermill":{"duration":0.009719,"end_time":"2024-03-11T20:20:19.506836","exception":false,"start_time":"2024-03-11T20:20:19.497117","status":"completed"},"tags":[],"id":"918fb453"}},{"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        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n\n    return df\n\ndef read_files(regex_path, depth=None):\n    chunks = []\n    for path in glob(str(regex_path)):\n        df = pl.read_parquet(path)\n        df = df.pipe(Pipeline.set_table_dtypes)\n\n        if depth in [1, 2]:\n            df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n\n        chunks.append(df)\n\n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    df = df.unique(subset=[\"case_id\"])\n\n    return df","metadata":{"papermill":{"duration":0.018108,"end_time":"2024-03-11T20:20:19.533703","exception":false,"start_time":"2024-03-11T20:20:19.515595","status":"completed"},"tags":[],"id":"c2520a18","execution":{"iopub.status.busy":"2024-03-28T00:59:19.992722Z","iopub.execute_input":"2024-03-28T00:59:19.993540Z","iopub.status.idle":"2024-03-28T00:59:20.000828Z","shell.execute_reply.started":"2024-03-28T00:59:19.993508Z","shell.execute_reply":"2024-03-28T00:59:19.999834Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Engineering","metadata":{"papermill":{"duration":0.00854,"end_time":"2024-03-11T20:20:19.550995","exception":false,"start_time":"2024-03-11T20:20:19.542455","status":"completed"},"tags":[],"id":"5751113b"}},{"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":{"papermill":{"duration":0.01688,"end_time":"2024-03-11T20:20:19.576796","exception":false,"start_time":"2024-03-11T20:20:19.559916","status":"completed"},"tags":[],"id":"92e9745b","execution":{"iopub.status.busy":"2024-03-28T00:59:24.337133Z","iopub.execute_input":"2024-03-28T00:59:24.338036Z","iopub.status.idle":"2024-03-28T00:59:24.345316Z","shell.execute_reply.started":"2024-03-28T00:59:24.337996Z","shell.execute_reply":"2024-03-28T00:59:24.344160Z"},"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":{"papermill":{"duration":0.015752,"end_time":"2024-03-11T20:20:19.601370","exception":false,"start_time":"2024-03-11T20:20:19.585618","status":"completed"},"tags":[],"id":"79001ea6","execution":{"iopub.status.busy":"2024-03-28T00:59:24.632033Z","iopub.execute_input":"2024-03-28T00:59:24.632412Z","iopub.status.idle":"2024-03-28T00:59:24.637600Z","shell.execute_reply.started":"2024-03-28T00:59:24.632383Z","shell.execute_reply":"2024-03-28T00:59:24.636673Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Configuration","metadata":{"papermill":{"duration":0.00861,"end_time":"2024-03-11T20:20:19.619092","exception":false,"start_time":"2024-03-11T20:20:19.610482","status":"completed"},"tags":[],"id":"53397d0f"}},{"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":{"papermill":{"duration":0.015255,"end_time":"2024-03-11T20:20:19.643247","exception":false,"start_time":"2024-03-11T20:20:19.627992","status":"completed"},"tags":[],"id":"543fc1a9","execution":{"iopub.status.busy":"2024-03-28T01:00:03.662629Z","iopub.execute_input":"2024-03-28T01:00:03.663341Z","iopub.status.idle":"2024-03-28T01:00:03.670284Z","shell.execute_reply.started":"2024-03-28T01:00:03.663304Z","shell.execute_reply":"2024-03-28T01:00:03.668991Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Train Files Read & Feature Engineering","metadata":{"papermill":{"duration":0.008715,"end_time":"2024-03-11T20:20:19.660605","exception":false,"start_time":"2024-03-11T20:20:19.651890","status":"completed"},"tags":[],"id":"1d35d110"}},{"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_file(TRAIN_DIR / \"train_credit_bureau_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_person_1.parquet\", 1),\n    ],\n    \"depth_2\": [\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_2.parquet\", 2),\n    ]\n}","metadata":{"papermill":{"duration":126.876005,"end_time":"2024-03-11T20:22:26.545249","exception":false,"start_time":"2024-03-11T20:20:19.669244","status":"completed"},"tags":[],"id":"03c8f51a","execution":{"iopub.status.busy":"2024-03-28T01:00:04.763545Z","iopub.execute_input":"2024-03-28T01:00:04.764233Z","iopub.status.idle":"2024-03-28T01:00:20.228451Z","shell.execute_reply.started":"2024-03-28T01:00:04.764203Z","shell.execute_reply":"2024-03-28T01:00:20.227649Z"},"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":{"papermill":{"duration":11.999532,"end_time":"2024-03-11T20:22:38.554478","exception":false,"start_time":"2024-03-11T20:22:26.554946","status":"completed"},"tags":[],"id":"7ca62eeb","outputId":"871ed716-9c9c-46a8-c144-7cf591fc582b","execution":{"iopub.status.busy":"2024-03-28T01:00:20.230082Z","iopub.execute_input":"2024-03-28T01:00:20.230379Z","iopub.status.idle":"2024-03-28T01:00:25.377540Z","shell.execute_reply.started":"2024-03-28T01:00:20.230355Z","shell.execute_reply":"2024-03-28T01:00:25.376582Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Test Files Read & Feature Engineering","metadata":{"papermill":{"duration":0.009104,"end_time":"2024-03-11T20:22:38.572989","exception":false,"start_time":"2024-03-11T20:22:38.563885","status":"completed"},"tags":[],"id":"6589dd41"}},{"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_file(TEST_DIR / \"test_credit_bureau_b_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_person_1.parquet\", 1),\n    ],\n    \"depth_2\": [\n        read_file(TEST_DIR / \"test_credit_bureau_b_2.parquet\", 2),\n    ]\n}","metadata":{"papermill":{"duration":0.589237,"end_time":"2024-03-11T20:22:39.171145","exception":false,"start_time":"2024-03-11T20:22:38.581908","status":"completed"},"tags":[],"id":"914207b2","execution":{"iopub.status.busy":"2024-03-28T01:00:25.378723Z","iopub.execute_input":"2024-03-28T01:00:25.379013Z","iopub.status.idle":"2024-03-28T01:00:25.697321Z","shell.execute_reply.started":"2024-03-28T01:00:25.378989Z","shell.execute_reply":"2024-03-28T01:00:25.696540Z"},"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":{"papermill":{"duration":0.051709,"end_time":"2024-03-11T20:22:39.232155","exception":false,"start_time":"2024-03-11T20:22:39.180446","status":"completed"},"tags":[],"id":"ff11469b","outputId":"994e2c0b-2b55-41f8-e2bc-c4e6838dc0ba","execution":{"iopub.status.busy":"2024-03-28T01:00:25.699094Z","iopub.execute_input":"2024-03-28T01:00:25.699392Z","iopub.status.idle":"2024-03-28T01:00:25.722185Z","shell.execute_reply.started":"2024-03-28T01:00:25.699368Z","shell.execute_reply":"2024-03-28T01:00:25.721163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Elimination","metadata":{"papermill":{"duration":0.008776,"end_time":"2024-03-11T20:22:39.250093","exception":false,"start_time":"2024-03-11T20:22:39.241317","status":"completed"},"tags":[],"id":"de51c4ea"}},{"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":{"papermill":{"duration":2.758307,"end_time":"2024-03-11T20:22:42.017667","exception":false,"start_time":"2024-03-11T20:22:39.259360","status":"completed"},"tags":[],"id":"b4053b07","outputId":"109cd1a9-093c-4761-b59f-b2579b4c0f64","execution":{"iopub.status.busy":"2024-03-28T01:00:25.723251Z","iopub.execute_input":"2024-03-28T01:00:25.723491Z","iopub.status.idle":"2024-03-28T01:00:27.515253Z","shell.execute_reply.started":"2024-03-28T01:00:25.723470Z","shell.execute_reply":"2024-03-28T01:00:27.514243Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pandas Conversion","metadata":{"papermill":{"duration":0.009039,"end_time":"2024-03-11T20:22:42.036115","exception":false,"start_time":"2024-03-11T20:22:42.027076","status":"completed"},"tags":[],"id":"96e47fd9"}},{"cell_type":"code","source":"df_train, cat_cols = to_pandas(df_train)\ndf_test, cat_cols = to_pandas(df_test, cat_cols)","metadata":{"papermill":{"duration":18.703961,"end_time":"2024-03-11T20:23:00.749238","exception":false,"start_time":"2024-03-11T20:22:42.045277","status":"completed"},"tags":[],"id":"37d2be78","execution":{"iopub.status.busy":"2024-03-28T01:00:41.078233Z","iopub.execute_input":"2024-03-28T01:00:41.079197Z","iopub.status.idle":"2024-03-28T01:00:52.694016Z","shell.execute_reply.started":"2024-03-28T01:00:41.079162Z","shell.execute_reply":"2024-03-28T01:00:52.693013Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Garbage Collection","metadata":{"papermill":{"duration":0.00925,"end_time":"2024-03-11T20:23:00.767926","exception":false,"start_time":"2024-03-11T20:23:00.758676","status":"completed"},"tags":[],"id":"dce4218d"}},{"cell_type":"code","source":"del data_store\n\ngc.collect()\ngc.collect()","metadata":{"papermill":{"duration":0.137016,"end_time":"2024-03-11T20:23:00.913914","exception":false,"start_time":"2024-03-11T20:23:00.776898","status":"completed"},"tags":[],"id":"16e8b237","outputId":"13f81e8d-b2b9-4046-e636-10bbead53370","execution":{"iopub.status.busy":"2024-03-28T01:00:52.695837Z","iopub.execute_input":"2024-03-28T01:00:52.696473Z","iopub.status.idle":"2024-03-28T01:00:52.931956Z","shell.execute_reply.started":"2024-03-28T01:00:52.696439Z","shell.execute_reply":"2024-03-28T01:00:52.930976Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### EDA","metadata":{"papermill":{"duration":0.009084,"end_time":"2024-03-11T20:23:00.932380","exception":false,"start_time":"2024-03-11T20:23:00.923296","status":"completed"},"tags":[],"id":"0f2c782c"}},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\ndf_train, _ = train_test_split(df_train, test_size=0.3, stratify=df_train[['target']])","metadata":{"id":"Kr4VDB_LzVYC","execution":{"iopub.status.busy":"2024-03-28T01:00:55.758306Z","iopub.execute_input":"2024-03-28T01:00:55.758985Z","iopub.status.idle":"2024-03-28T01:01:06.864388Z","shell.execute_reply.started":"2024-03-28T01:00:55.758954Z","shell.execute_reply":"2024-03-28T01:01:06.863537Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train['target'].value_counts()","metadata":{"id":"fR2t3pOjt_An","outputId":"78e8aba2-99d8-41b5-dd4e-d831169216ca","execution":{"iopub.status.busy":"2024-03-28T01:01:06.866385Z","iopub.execute_input":"2024-03-28T01:01:06.867145Z","iopub.status.idle":"2024-03-28T01:01:06.886877Z","shell.execute_reply.started":"2024-03-28T01:01:06.867103Z","shell.execute_reply":"2024-03-28T01:01:06.885888Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Train is duplicated:\\t\", df_train[\"case_id\"].duplicated().any())\nprint(\"Train Week Range:\\t\", (df_train[\"WEEK_NUM\"].min(), df_train[\"WEEK_NUM\"].max()))\n\nprint()\n\nprint(\"Test is duplicated:\\t\", df_test[\"case_id\"].duplicated().any())\nprint(\"Test Week Range:\\t\", (df_test[\"WEEK_NUM\"].min(), df_test[\"WEEK_NUM\"].max()))","metadata":{"papermill":{"duration":0.038139,"end_time":"2024-03-11T20:23:00.979829","exception":false,"start_time":"2024-03-11T20:23:00.941690","status":"completed"},"tags":[],"id":"9a87b1ad","outputId":"ed2d3744-fbf7-459c-889f-32c128479eb6","execution":{"iopub.status.busy":"2024-03-28T01:01:06.888002Z","iopub.execute_input":"2024-03-28T01:01:06.888299Z","iopub.status.idle":"2024-03-28T01:01:06.921725Z","shell.execute_reply.started":"2024-03-28T01:01:06.888264Z","shell.execute_reply":"2024-03-28T01:01:06.920838Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.lineplot(\n    data=df_train,\n    x=\"WEEK_NUM\",\n    y=\"target\",\n)\nplt.show()","metadata":{"papermill":{"duration":16.554713,"end_time":"2024-03-11T20:23:17.543990","exception":false,"start_time":"2024-03-11T20:23:00.989277","status":"completed"},"tags":[],"id":"890cf105","outputId":"4df63480-da4d-40a2-9407-b588063f8f0d","execution":{"iopub.status.busy":"2024-03-28T01:01:06.923461Z","iopub.execute_input":"2024-03-28T01:01:06.923753Z","iopub.status.idle":"2024-03-28T01:01:16.943541Z","shell.execute_reply.started":"2024-03-28T01:01:06.923729Z","shell.execute_reply":"2024-03-28T01:01:16.942600Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Training","metadata":{"papermill":{"duration":0.01291,"end_time":"2024-03-11T20:23:17.567408","exception":false,"start_time":"2024-03-11T20:23:17.554498","status":"completed"},"tags":[],"id":"3c6f07d8"}},{"cell_type":"code","source":"# !sudo apt install nvidia-driver-460 nvidia-cuda-toolkit clinfo\n# !apt-get update --fix-missing","metadata":{"id":"89N3TACg0jGd","outputId":"a675742c-f0b5-448e-b6fb-77738621f299"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# !mkdir -p /etc/OpenCL/vendors && echo \"libnvidia-opencl.so.1\" > /etc/OpenCL/vendors/nvidia.icd\n","metadata":{"id":"kVVzsKnw2TiH"},"execution_count":null,"outputs":[]},{"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":{"papermill":{"duration":1032.311042,"end_time":"2024-03-11T20:40:29.890585","exception":false,"start_time":"2024-03-11T20:23:17.579543","status":"completed"},"tags":[],"id":"ee57fad5","outputId":"bbddb66f-b881-419f-b4a4-d10acb8f7475","execution":{"iopub.status.busy":"2024-03-28T01:01:23.382372Z","iopub.execute_input":"2024-03-28T01:01:23.382846Z","iopub.status.idle":"2024-03-28T01:09:13.808270Z","shell.execute_reply.started":"2024-03-28T01:01:23.382813Z","shell.execute_reply":"2024-03-28T01:09:13.807209Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Prediction","metadata":{"papermill":{"duration":0.015335,"end_time":"2024-03-11T20:40:29.921663","exception":false,"start_time":"2024-03-11T20:40:29.906328","status":"completed"},"tags":[],"id":"a2764c7f"}},{"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":{"papermill":{"duration":0.29704,"end_time":"2024-03-11T20:40:30.234187","exception":false,"start_time":"2024-03-11T20:40:29.937147","status":"completed"},"tags":[],"id":"37fc8919","execution":{"iopub.status.busy":"2024-03-28T01:09:47.360380Z","iopub.execute_input":"2024-03-28T01:09:47.361270Z","iopub.status.idle":"2024-03-28T01:09:47.542254Z","shell.execute_reply.started":"2024-03-28T01:09:47.361238Z","shell.execute_reply":"2024-03-28T01:09:47.541221Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Submission","metadata":{"papermill":{"duration":0.015506,"end_time":"2024-03-11T20:40:30.266313","exception":false,"start_time":"2024-03-11T20:40:30.250807","status":"completed"},"tags":[],"id":"22d542aa"}},{"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":{"papermill":{"duration":0.035461,"end_time":"2024-03-11T20:40:30.317145","exception":false,"start_time":"2024-03-11T20:40:30.281684","status":"completed"},"tags":[],"id":"64927164","execution":{"iopub.status.busy":"2024-03-28T01:09:48.382647Z","iopub.execute_input":"2024-03-28T01:09:48.383328Z","iopub.status.idle":"2024-03-28T01:09:48.401818Z","shell.execute_reply.started":"2024-03-28T01:09:48.383297Z","shell.execute_reply":"2024-03-28T01:09:48.400783Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Check null: \", df_subm[\"score\"].isnull().any())\n\ndf_subm.head()","metadata":{"papermill":{"duration":0.031645,"end_time":"2024-03-11T20:40:30.364269","exception":false,"start_time":"2024-03-11T20:40:30.332624","status":"completed"},"tags":[],"id":"4611b0c3","outputId":"79390953-2aee-46ce-bf9f-86a3fb619042","execution":{"iopub.status.busy":"2024-03-28T01:09:50.183392Z","iopub.execute_input":"2024-03-28T01:09:50.183787Z","iopub.status.idle":"2024-03-28T01:09:50.197793Z","shell.execute_reply.started":"2024-03-28T01:09:50.183758Z","shell.execute_reply":"2024-03-28T01:09:50.197081Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.to_csv(\"submission.csv\")","metadata":{"papermill":{"duration":0.024175,"end_time":"2024-03-11T20:40:30.404950","exception":false,"start_time":"2024-03-11T20:40:30.380775","status":"completed"},"tags":[],"id":"f0b40346","execution":{"iopub.status.busy":"2024-03-28T01:09:52.442738Z","iopub.execute_input":"2024-03-28T01:09:52.443375Z","iopub.status.idle":"2024-03-28T01:09:52.450481Z","shell.execute_reply.started":"2024-03-28T01:09:52.443345Z","shell.execute_reply":"2024-03-28T01:09:52.449552Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"papermill":{"duration":0.015608,"end_time":"2024-03-11T20:40:30.436155","exception":false,"start_time":"2024-03-11T20:40:30.420547","status":"completed"},"tags":[],"id":"215ee20c"},"execution_count":null,"outputs":[]}]}