{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nimport time\n\n# Read the test.csv and get the unique StudyInstanceUID\n\n# root = '/kaggle/input/rsna-str-pulmonary-embolism-detection'\n\nstart_time = time.time()\n\ndef elapsed_time():\n    t = str(round((time.time() - start_time) / 60, 2))\n    print(f'{t} minutes')\n\n\n\n\ntest_csv_path = '/kaggle/input/rsna-str-pulmonary-embolism-detection/test.csv'\n\ntest = pd.read_csv(test_csv_path)\n\nprint(test.shape)\ntest.head()\n\n\n\nsuffix_list = ['negative_exam_for_pe', 'rv_lv_ratio_gte_1', 'rv_lv_ratio_lt_1', 'leftsided_pe',\n                     'chronic_pe', 'rightsided_pe', 'acute_and_chronic_pe', 'central_pe', 'indeterminate']\n\n\nstudy_exam_id_list = []\nfor v in test.StudyInstanceUID:\n    if v not in study_exam_id_list:\n        study_exam_id_list.append(v)\n\ncount = 1\n\nimage_id_list = []\nfor v in test.SOPInstanceUID:\n    if v not in image_id_list:\n        elapsed_time()\n        print(f'{count} {v}')\n        count = count + 1\n        image_id_list.append(v)\n\nprint(f'len(image_id_list) = {len(image_id_list)}')\n\n\nstr_temp =''\n\nrows_list = []\n\n\nfor suffix in suffix_list:\n    for study_exam_id in study_exam_id_list:\n        str_temp = study_exam_id +'_'+ suffix\n        rows_list.append(str_temp)\n        elapsed_time()\n\n\nfor i in image_id_list:\n    rows_list.append(i)\n\n\nscore = []\nfor i in range(len(rows_list)):\n    score.append(0.095) # Hard coded value \n\n\nprint(len(score))\nelapsed_time()\n\nsub_temp = pd.DataFrame({'id':rows_list, 'label':score})\n\nsub_temp.to_csv('submission.csv', index=False)\n\n\n\n# SOPInstanceUID\n\n# for dirname, _, filenames in os.walk('/kaggle/input'):\n#     for filename in filenames:\n#         print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"","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}