{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# G-Research Crypto - Starter Random Forest Pipeline\n\nimport pandas as pd\nimport numpy as np\nimport gresearch_crypto\nimport traceback\n\nfrom sklearn.model_selection import train_test_split\n\nimport cudf\nimport cupy as cp\nfrom cuml.ensemble import RandomForestRegressor\nfrom sklearn.model_selection import KFold\n\nSEED = 1111\n\nnp.random.seed(SEED)\n\n\nTRAIN_CSV = '/kaggle/input/g-research-crypto-forecasting/train.csv'\nASSET_DETAILS_CSV = '/kaggle/input/g-research-crypto-forecasting/asset_details.csv'","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = pd.read_csv(TRAIN_CSV)\ndf_train.head()\n\ndf_train.replace([np.inf, -np.inf], np.nan)\ndf_train = df_train.dropna(how=\"any\")\n\ndf_train=df_train.astype('float32')\n\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_asset_details = pd.read_csv(ASSET_DETAILS_CSV).sort_values(\"Asset_ID\")\ndf_asset_details","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def upper_shadow(df):\n    return df['High'] - np.maximum(df['Close'], df['Open'])\n\ndef lower_shadow(df):\n    return np.minimum(df['Close'], df['Open']) - df['Low']\n\n# A utility function to build features from the original df\n# It works for rows to, so we can reutilize it.\ndef get_features(df):\n    df_feat = df[['Count', 'Open', 'High', 'Low', 'Close', 'Volume', 'VWAP']].copy()\n    df_feat['Upper_Shadow'] = upper_shadow(df_feat)\n    df_feat['Lower_Shadow'] = lower_shadow(df_feat)\n    return df_feat\n\ndef get_Xy_and_model_for_asset(df_train, asset_id):\n    df = df_train[df_train[\"Asset_ID\"] == asset_id]\n    \n    # TODO: Try different features here!\n    df_proc = get_features(df)\n    df_proc['y'] = df['Target']\n    #df_proc = df_proc.dropna(how=\"any\")\n    \n    X = df_proc.drop(\"y\", axis=1)\n    y = df_proc[\"y\"]\n    \n    # TODO: Try different features here!\n    model = RandomForestRegressor(n_estimators = 50, max_depth=9,random_state=1111 )\n    model.fit(cudf.from_pandas(X), cudf.from_pandas(y))\n    \n    return X, y, model","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Xs = {}\nys = {}\nmodels = {}\n\nfor asset_id, asset_name in zip(df_asset_details['Asset_ID'], df_asset_details['Asset_Name']):\n    print(f\"Training model for {asset_name:<16} (ID={asset_id:<2})\")\n    try:\n        X, y, model = get_Xy_and_model_for_asset(df_train, asset_id)    \n        Xs[asset_id], ys[asset_id], models[asset_id] = X, y, model\n    except: \n        traceback.print_exc()\n        Xs[asset_id], ys[asset_id], models[asset_id] = None, None, None ","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"env = gresearch_crypto.make_env()\niter_test = env.iter_test()\n\nfor i, (df_test, df_pred) in enumerate(iter_test):\n    for j , row in df_test.iterrows():\n        \n        if models[row['Asset_ID']] is not None:\n            try:\n                model = models[row['Asset_ID']]\n                x_test = get_features(row)\n                #y_pred = model.predict(pd.DataFrame([x_test]))[0]\n                #y_pred = model.predict(pd.DataFrame([x_test]))\n                y_pred = model.predict(cudf.from_pandas(pd.DataFrame([x_test])).astype('float32'))\n                df_pred.loc[df_pred['row_id'] == row['row_id'], 'Target'] = y_pred.to_array()\n            except:\n                df_pred.loc[df_pred['row_id'] == row['row_id'], 'Target'] = 0\n                traceback.print_exc()\n        else: \n            df_pred.loc[df_pred['row_id'] == row['row_id'], 'Target'] = 0\n        \n    env.predict(df_pred)","metadata":{},"execution_count":null,"outputs":[]}]}