{"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":"# Libraries\nimport datatable as dt\nimport pandas as pd\nimport numpy as np","metadata":{"execution":{"iopub.status.busy":"2022-10-02T15:38:33.164170Z","iopub.execute_input":"2022-10-02T15:38:33.165472Z","iopub.status.idle":"2022-10-02T15:38:33.170457Z","shell.execute_reply.started":"2022-10-02T15:38:33.165431Z","shell.execute_reply":"2022-10-02T15:38:33.169431Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load data\ntrain = dt.fread('../input/tabular-playground-series-oct-2022/train_0.csv').to_pandas()\ndtypes_dict_train = dict(pd.read_csv('../input/tps2022octparquet/dtypes_train.csv').values)\n\n# Reduce memory usage by 70%.\ntrain = train.astype(dtypes_dict_train)\ntrain.head(3)","metadata":{"execution":{"iopub.status.busy":"2022-10-02T15:38:33.172749Z","iopub.execute_input":"2022-10-02T15:38:33.173111Z","iopub.status.idle":"2022-10-02T15:38:37.045079Z","shell.execute_reply.started":"2022-10-02T15:38:33.173079Z","shell.execute_reply":"2022-10-02T15:38:37.043848Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['team_A_scoring_within_10sec'].mean()","metadata":{"execution":{"iopub.status.busy":"2022-10-02T15:38:37.046398Z","iopub.execute_input":"2022-10-02T15:38:37.046766Z","iopub.status.idle":"2022-10-02T15:38:37.199016Z","shell.execute_reply.started":"2022-10-02T15:38:37.046731Z","shell.execute_reply":"2022-10-02T15:38:37.197678Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['team_B_scoring_within_10sec'].mean()","metadata":{"execution":{"iopub.status.busy":"2022-10-02T15:38:37.201261Z","iopub.execute_input":"2022-10-02T15:38:37.201637Z","iopub.status.idle":"2022-10-02T15:38:37.357791Z","shell.execute_reply.started":"2022-10-02T15:38:37.201604Z","shell.execute_reply":"2022-10-02T15:38:37.356542Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Sample submission\nsub = pd.read_csv('../input/tabular-playground-series-oct-2022/sample_submission.csv')\n\n# Optimal constant predictions (for log-loss metric)\nsub['team_A_scoring_within_10sec'] = 0.058310741557685675\nsub['team_B_scoring_within_10sec'] = 0.05575279580493175\n\n# Submit\nsub.to_csv('submission.csv', index=False)\nsub.head(3)","metadata":{"execution":{"iopub.status.busy":"2022-10-02T15:38:37.359180Z","iopub.execute_input":"2022-10-02T15:38:37.359594Z","iopub.status.idle":"2022-10-02T15:38:40.009126Z","shell.execute_reply.started":"2022-10-02T15:38:37.359561Z","shell.execute_reply":"2022-10-02T15:38:40.007817Z"},"trusted":true},"execution_count":null,"outputs":[]}]}