{"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":"gpu","dataSources":[{"sourceId":84493,"databundleVersionId":9871156,"sourceType":"competition"},{"sourceId":9677479,"sourceType":"datasetVersion","datasetId":5903334},{"sourceId":202003795,"sourceType":"kernelVersion"},{"sourceId":202123051,"sourceType":"kernelVersion"}],"dockerImageVersionId":30787,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"%%time\n\nimport pickle \nimport os\nimport polars as pl\nimport numpy as np\nimport pandas as pd\nfrom tqdm import tqdm\nimport kaggle_evaluation.jane_street_inference_server","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-10-20T19:30:07.905284Z","iopub.execute_input":"2024-10-20T19:30:07.905702Z","iopub.status.idle":"2024-10-20T19:30:09.042029Z","shell.execute_reply.started":"2024-10-20T19:30:07.905658Z","shell.execute_reply":"2024-10-20T19:30:09.041052Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\nwith open('/kaggle/input/js-models/trained_models.pkl', 'rb') as f:\n    LightModels = pickle.load(f)","metadata":{"execution":{"iopub.status.busy":"2024-10-20T19:30:09.043793Z","iopub.execute_input":"2024-10-20T19:30:09.044208Z","iopub.status.idle":"2024-10-20T19:30:14.524662Z","shell.execute_reply.started":"2024-10-20T19:30:09.044175Z","shell.execute_reply":"2024-10-20T19:30:14.523823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%time \n\nlags_ : pl.DataFrame | None = None\n\ndef predict(test: pl.DataFrame, lags: pl.DataFrame | None) -> pl.DataFrame | pd.DataFrame:\n    \n    fe = [f'feature_0{i}' if i<10 else f'feature_{i}' for i in range(79)]\n\n    global lags_, LightModels\n    \n    if lags is not None:\n        lags_ = lags\n        \n    test_preds = np.zeros(len(test))\n    \n    for model in tqdm(LightModels):\n        test_preds += model.predict(test.select(pl.col(fe)).to_pandas())\n        \n    test_preds /= len(LightModels)\n    \n    predictions = test.select('row_id').with_columns(pl.Series(\n            name   = 'responder_6', \n            values = np.clip(test_preds, a_min = -5, a_max = 5),\n            dtype  = pl.Float64,\n        )\n    )  \n            \n    assert isinstance(predictions, (pl.DataFrame, pd.DataFrame))\n    assert predictions.columns == ['row_id', 'responder_6']\n    assert len(predictions) == len(test)\n    \n    return predictions\n\ninference_server = kaggle_evaluation.jane_street_inference_server.JSInferenceServer(predict)\n\nif os.getenv('KAGGLE_IS_COMPETITION_RERUN'):\n    inference_server.serve()\nelse:\n    inference_server.run_local_gateway(\n        (\n            '/kaggle/input/jane-street-real-time-market-data-forecasting/test.parquet',\n            '/kaggle/input/jane-street-real-time-market-data-forecasting/lags.parquet',\n        )\n    )","metadata":{"execution":{"iopub.status.busy":"2024-10-20T19:30:14.525834Z","iopub.execute_input":"2024-10-20T19:30:14.526774Z","iopub.status.idle":"2024-10-20T19:30:15.072984Z","shell.execute_reply.started":"2024-10-20T19:30:14.526729Z","shell.execute_reply":"2024-10-20T19:30:15.071312Z"},"trusted":true},"execution_count":null,"outputs":[]}]}