{"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":"gpu","dataSources":[{"sourceId":59093,"databundleVersionId":7457433,"sourceType":"competition"}],"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Brain Activity Data View and Features","metadata":{"papermill":{"duration":0.009232,"end_time":"2023-04-04T16:08:25.219577","exception":false,"start_time":"2023-04-04T16:08:25.210345","status":"completed"},"tags":[]}},{"cell_type":"code","source":"import os\nimport math\nimport random\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport pyarrow.parquet as pq","metadata":{"papermill":{"duration":13.400642,"end_time":"2023-04-04T16:08:38.628644","exception":false,"start_time":"2023-04-04T16:08:25.228002","status":"completed"},"tags":[],"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train0 = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/train.csv\")\ndisplay(train0[0:3])\nprint(train0.columns.tolist())","metadata":{"_kg_hide-output":false,"papermill":{"duration":0.058938,"end_time":"2023-04-04T16:08:38.71259","exception":false,"start_time":"2023-04-04T16:08:38.653652","status":"completed"},"tags":[],"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test0 = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/test.csv\")\ndisplay(test0)\nprint(test0.columns.tolist())","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submit=pd.read_csv('/kaggle/input/hms-harmful-brain-activity-classification/sample_submission.csv')\ndisplay(submit)\nprint(submit.columns.tolist())","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# train_eegs","metadata":{}},{"cell_type":"code","source":"path = '/kaggle/input/hms-harmful-brain-activity-classification/train_eegs/1000913311.parquet'\ntable = pq.read_table(path)\ndf = table.to_pandas()\ndisplay(df)\ncolumns_eegs=df.columns","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for column in df.columns:\n    plt.figure(figsize=(12,4))\n    plt.plot(df.index, df[column], label=column)\n    plt.title(column)\n    plt.xlabel('Index')\n    plt.ylabel('Value')\n    plt.legend()\n    plt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# train_spectrograms","metadata":{}},{"cell_type":"code","source":"path = '/kaggle/input/hms-harmful-brain-activity-classification/train_spectrograms/1000086677.parquet'\ntable = pq.read_table(path)\ndf = table.to_pandas()\ndisplay(df)\ncolumns_spec=df.columns","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for column in df.columns:\n    plt.figure(figsize=(12,4))\n    plt.plot(df.index, df[column], label=column)\n    plt.title(column)\n    plt.xlabel('Index')\n    plt.ylabel('Value')\n    plt.legend()\n    plt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# create features from eegs","metadata":{}},{"cell_type":"code","source":"paths=[]\nids=[]\nfor dirname, _, filenames in os.walk('/kaggle/input/hms-harmful-brain-activity-classification/train_eegs'):\n    for filename in filenames:\n        path=os.path.join(dirname, filename)\n        ids+=[filename.split('.')[0]]\n        paths+=[path]\n        \ntrain_eggs=pd.DataFrame(columns=['eeg_id','path'])\ntrain_eggs['path']=paths\ntrain_eggs['eeg_id']=ids\n\nfor i in range(len(paths)):\n    path=paths[i]\n    table = pq.read_table(path)\n    df = table.to_pandas()\n    for column in columns_eegs:\n        train_eggs.loc[i,column+'_min']=df[column].min()\n        train_eggs.loc[i,column+'_max']=df[column].max()\n#display(train_eggs)\ntrain_eggs.to_csv('train_eggs.csv',index=False)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"paths=[]\nids=[]\nfor dirname, _, filenames in os.walk('/kaggle/input/hms-harmful-brain-activity-classification/test_eegs'):\n    for filename in filenames:\n        path=os.path.join(dirname, filename)\n        ids+=[filename.split('.')[0]]\n        paths+=[path]\n        \ntest_eggs=pd.DataFrame(columns=['eeg_id','path'])\ntest_eggs['path']=paths\ntest_eggs['eeg_id']=ids\n\nfor i in range(len(paths)):\n    path=paths[i]\n    table = pq.read_table(path)\n    df = table.to_pandas()\n    for column in columns_eegs:\n        test_eggs.loc[i,column+'_min']=df[column].min()\n        test_eggs.loc[i,column+'_max']=df[column].max()\n#display(test_eggs)\ntest_eggs.to_csv('test_eggs.csv',index=False)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# create features from spectograms","metadata":{}},{"cell_type":"code","source":"paths=[]\nids=[]\nfor dirname, _, filenames in os.walk('/kaggle/input/hms-harmful-brain-activity-classification/train_spectrograms'):\n    for filename in filenames:\n        path=os.path.join(dirname, filename)\n        ids+=[filename.split('.')[0]]\n        paths+=[path]\n        \ntrain_spectrograms=pd.DataFrame(columns=['spectrogram_id','path'])\ntrain_spectrograms['path']=paths\ntrain_spectrograms['spectrogram_id']=ids\n\nfor i in range(len(paths)):\n    path=paths[i]\n    table = pq.read_table(path)\n    df = table.to_pandas()\n    for column in columns_spec:\n        train_spectrograms.loc[i,column+'_max']=df[column].max()\n#display(train_spectrograms)\ntrain_spectrograms.to_csv('train_spectrograms.csv',index=False)","metadata":{"_kg_hide-output":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"paths=[]\nids=[]\nfor dirname, _, filenames in os.walk('/kaggle/input/hms-harmful-brain-activity-classification/test_spectrograms'):\n    for filename in filenames:\n        path=os.path.join(dirname, filename)\n        ids+=[filename.split('.')[0]]\n        paths+=[path]\n        \ntest_spectrograms=pd.DataFrame(columns=['spectrogram_id','path'])\ntest_spectrograms['path']=paths\ntest_spectrograms['spectrogram_id']=ids\n\nfor i in range(len(paths)):\n    path=paths[i]\n    table = pq.read_table(path)\n    df = table.to_pandas()\n    for column in columns_spec:\n        test_spectrograms.loc[i,column+'_max']=df[column].max()\n#display(test_spectrograms)\ntest_spectrograms.to_csv('test_spectrograms.csv',index=False)","metadata":{"_kg_hide-output":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}