{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\nimport pydicom","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_dir = \"../input/osic-pulmonary-fibrosis-progression/train\"\ntest_dir = \"../input/osic-pulmonary-fibrosis-progression/test\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ID_dir_list = os.listdir(train_dir)\nlen(ID_dir_list)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"eliminated_ID_list = []\ndf_list=[]\n\nfor ID_dir in ID_dir_list:\n    df_base = pd.DataFrame(columns=[\"name\",\"value\"])\n    files = os.listdir(os.path.join(train_dir,ID_dir))\n    for f in files:\n        ds = pydicom.dcmread(os.path.join(train_dir,os.path.join(ID_dir,f)))\n        df_temp = pd.DataFrame(ds.values())\n        if df_temp.shape[1] >1:\n            print(ID_dir+\" is eliminated.\")\n            eliminated_ID_list.append(ID_dir)\n            break\n        df_temp[0] = df_temp[0].apply(lambda x: pydicom.dataelem.DataElement_from_raw(x) \n                                if isinstance(x, pydicom.dataelem.RawDataElement) else x)\n        df_temp['name'] = df_temp[0].apply(lambda x: x.name)\n        df_temp['value'] = df_temp[0].apply(lambda x: x.value)\n        df_temp = df_temp.drop(df_temp.index[df_temp[\"name\"].str.contains(\"Pixel Data\")])\n        df_val = df_temp.drop(0,axis=1)\n        df_ID_dcmnum = pd.DataFrame([[\"ID\",ID_dir],[\"dcm_num\",f]],columns= ['name','value'])\n        df_add = df_ID_dcmnum.append(df_val)\n        df_base = pd.merge(df_base,df_add,on=\"name\",how=\"outer\")\n    df_base=df_base.T\n    df_fix = df_base[2:]\n    df_fix.columns = df_base.iloc[1].to_list()\n    df_list.append(df_fix)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_final = pd.concat(df_list)\ndf_final = df_final.reset_index()\ndf_final = df_final.drop(\"index\",axis=1)\ndf_final.to_csv(\"dcm_info_train.csv\",index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"eliminated_df_list=[]\n\nfor ID_dir in eliminated_ID_list:\n    df_base = pd.DataFrame(columns=[\"name\",\"value\"])\n    files = os.listdir(os.path.join(train_dir,ID_dir))\n    for f in files:\n        ds = pydicom.dcmread(os.path.join(train_dir,os.path.join(ID_dir,f)))\n        print(ds)\n        df_temp = pd.DataFrame(ds.values())\n        if df_temp.shape[1] >1:\n            print(ID_dir+\" is eliminated.\")\n            break\n        df_temp[0] = df_temp[0].apply(lambda x: pydicom.dataelem.DataElement_from_raw(x) \n                                if isinstance(x, pydicom.dataelem.RawDataElement) else x)\n        df_temp['name'] = df_temp[0].apply(lambda x: x.name)\n        df_temp['value'] = df_temp[0].apply(lambda x: x.value)\n        df_temp = df_temp.drop(df_temp.index[df_temp[\"name\"].str.contains(\"Pixel Data\")])\n        df_val = df_temp.drop(0,axis=1)\n        df_ID_dcmnum = pd.DataFrame([[\"ID\",ID_dir],[\"dcm_num\",f]],columns= ['name','value'])\n        df_add = df_ID_dcmnum.append(df_val)\n        df_base = pd.merge(df_base,df_add,on=\"name\",how=\"outer\")\n    print(ID_dir+\" is passed.\")\n    df_base=df_base.T\n    df_fix = df_base[2:]\n    df_fix.columns = df_base.iloc[1].to_list()\n    eliminated_df_list.append(df_fix)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_final_2 = pd.concat(eliminated_df_list)\ndf_final_2 = df_final_2.reset_index()\ndf_final_2 = df_final_2.drop(\"index\",axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train_dcm_info  = pd.concat([df_final,df_final_2],axis=0)\ndf_train_dcm_info.to_csv(\"dcm_info_train.csv\",index=False)","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}