{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":59093,"databundleVersionId":7469972,"sourceType":"competition"}],"dockerImageVersionId":30635,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\ntest_df = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/test.csv\")\nsample_df = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/sample_submission.csv\")\n\nsubmission_df = pd.DataFrame(columns=sample_df.columns.values)\nsubmission_df['eeg_id'] = test_df['eeg_id']","metadata":{"execution":{"iopub.status.busy":"2024-01-23T05:26:44.102338Z","iopub.execute_input":"2024-01-23T05:26:44.102780Z","iopub.status.idle":"2024-01-23T05:26:44.675567Z","shell.execute_reply.started":"2024-01-23T05:26:44.102747Z","shell.execute_reply":"2024-01-23T05:26:44.674617Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Copied from Chris Deotte's notebook\ndf = pd.read_csv('/kaggle/input/hms-harmful-brain-activity-classification/train.csv')\nTARGETS = df.columns[-6:]\nTARS = {'Seizure':0, 'LPD':1, 'GPD':2, 'LRDA':3, 'GRDA':4, 'Other':5}\nTARS2 = {x:y for y,x in TARS.items()}\n\ntrain = df.groupby('eeg_id')[['patient_id']].agg('first')\n\ntmp = df.groupby('eeg_id')[TARGETS].agg('sum')\nfor t in TARGETS:\n    train[t] = tmp[t].values\n    \ny_data = train[TARGETS].values\ny_data = y_data / y_data.sum(axis=1,keepdims=True)\ntrain[TARGETS] = y_data\n\ntmp = df.groupby('eeg_id')[['expert_consensus']].agg('first')\ntrain['target'] = tmp\ntrain_mean = train[TARGETS].mean()\n\ntrain_mean","metadata":{"execution":{"iopub.status.busy":"2024-01-23T05:26:57.680661Z","iopub.execute_input":"2024-01-23T05:26:57.681066Z","iopub.status.idle":"2024-01-23T05:26:58.063684Z","shell.execute_reply.started":"2024-01-23T05:26:57.681032Z","shell.execute_reply":"2024-01-23T05:26:58.062551Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for col in TARGETS:\n    submission_df[col] = train_mean[col]\n    \nsubmission_df.to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2024-01-23T05:27:05.920807Z","iopub.execute_input":"2024-01-23T05:27:05.921327Z","iopub.status.idle":"2024-01-23T05:27:05.935387Z","shell.execute_reply.started":"2024-01-23T05:27:05.921282Z","shell.execute_reply":"2024-01-23T05:27:05.933836Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%cat submission.csv","metadata":{"execution":{"iopub.status.busy":"2024-01-23T05:27:12.170514Z","iopub.execute_input":"2024-01-23T05:27:12.171000Z","iopub.status.idle":"2024-01-23T05:27:13.284767Z","shell.execute_reply.started":"2024-01-23T05:27:12.170960Z","shell.execute_reply":"2024-01-23T05:27:13.283652Z"},"trusted":true},"execution_count":null,"outputs":[]}]}