{"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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-01-18T16:37:27.913268Z","iopub.execute_input":"2024-01-18T16:37:27.913649Z","iopub.status.idle":"2024-01-18T16:37:27.929214Z","shell.execute_reply.started":"2024-01-18T16:37:27.913619Z","shell.execute_reply":"2024-01-18T16:37:27.928129Z"},"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":"2024-01-18T16:37:30.529912Z","iopub.execute_input":"2024-01-18T16:37:30.530290Z","iopub.status.idle":"2024-01-18T16:37:30.710619Z","shell.execute_reply.started":"2024-01-18T16:37:30.530262Z","shell.execute_reply":"2024-01-18T16:37:30.709538Z"},"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":"2024-01-18T16:37:32.858371Z","iopub.execute_input":"2024-01-18T16:37:32.858783Z","iopub.status.idle":"2024-01-18T16:37:32.869479Z","shell.execute_reply.started":"2024-01-18T16:37:32.858745Z","shell.execute_reply":"2024-01-18T16:37:32.867977Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%cat submission.csv","metadata":{"execution":{"iopub.status.busy":"2024-01-18T16:37:34.482726Z","iopub.execute_input":"2024-01-18T16:37:34.483078Z","iopub.status.idle":"2024-01-18T16:37:35.511041Z","shell.execute_reply.started":"2024-01-18T16:37:34.483051Z","shell.execute_reply":"2024-01-18T16:37:35.509962Z"},"trusted":true},"execution_count":null,"outputs":[]}]}