{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":96164,"databundleVersionId":11418275,"sourceType":"competition"}],"dockerImageVersionId":31041,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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":{"iopub.status.busy":"2025-06-24T06:35:15.745402Z","iopub.execute_input":"2025-06-24T06:35:15.746191Z","iopub.status.idle":"2025-06-24T06:35:15.753387Z","shell.execute_reply.started":"2025-06-24T06:35:15.746158Z","shell.execute_reply":"2025-06-24T06:35:15.752637Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.model_selection import train_test_split\nfrom lightgbm import LGBMRegressor, early_stopping, log_evaluation\nfrom sklearn.metrics import mean_squared_error\n\ntrain = pd.read_parquet('/kaggle/input/drw-crypto-market-prediction/train.parquet')\ntest = pd.read_parquet('/kaggle/input/drw-crypto-market-prediction/test.parquet')\n\nX = train.drop(columns=['label'])\ny = train['label']\nX_test = test.drop(columns=['label'])\n\nfrom sklearn.model_selection import train_test_split\nX_train, X_val, y_train, y_val = train_test_split(\n    X, y, test_size=0.2, random_state=42\n)\n\nimport lightgbm as lgb\nfrom lightgbm import early_stopping, log_evaluation\n\nmodel = lgb.LGBMRegressor(\n    n_estimators=1000,\n    learning_rate=0.05,\n    max_depth=-1,\n    random_state=42\n)\n\nmodel.fit(\n    X_train, y_train,\n    eval_set=[(X_val, y_val)],\n    eval_metric='rmse',\n    callbacks=[\n        early_stopping(stopping_rounds=50),\n        log_evaluation(period=100)  # Log every 100 rounds\n    ]\n)\n\npreds = model.predict(X_test)\n\nsubmission = pd.DataFrame({\n    'ID': range(1, len(preds)+1),\n    'prediction': preds\n})\n\nsubmission.to_csv('submission.csv', index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-24T06:35:15.754583Z","iopub.execute_input":"2025-06-24T06:35:15.754801Z"}},"outputs":[],"execution_count":null}]}