{"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":"markdown","source":"# Random predictions\n\nThis dummy submission presents random predictions based on a fitted Gaussian on the target distribution across all assets.","metadata":{}},{"cell_type":"code","source":"from scipy.stats import norm\nimport numpy as np\nimport gresearch_crypto\n\ntarget_mean, target_std = (2.40946942906261e-06, 0.004333437997098369)\n\ndef random_prediction(size: int) -> np.array:\n    return norm.rvs(\n        loc = target_mean,\n        scale = target_std,\n        size = size\n    )\n\nenv = gresearch_crypto.make_env()\niter_test = env.iter_test()\n\nfor i, (df_test, df_pred) in enumerate(iter_test):\n    df_pred['Target'] = random_prediction(size = df_pred.shape[0])\n    env.predict(df_pred)","metadata":{"execution":{"iopub.status.busy":"2022-01-20T19:23:32.071271Z","iopub.execute_input":"2022-01-20T19:23:32.072383Z","iopub.status.idle":"2022-01-20T19:23:33.078221Z","shell.execute_reply.started":"2022-01-20T19:23:32.072238Z","shell.execute_reply":"2022-01-20T19:23:33.077288Z"},"trusted":true},"execution_count":null,"outputs":[]}]}