{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport os\nprint(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.diagnosis.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv('../input/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tqdm import tqdm\nfrom PIL import Image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#the func is from https://www.kaggle.com/toshik/image-size-and-rate-of-new-whale\ndef get_size_list(targets, dir_target):\n\n    result = list()\n\n    for target in tqdm(targets):\n\n        img = np.array(Image.open(os.path.join(dir_target, target+'.png')))\n        result.append(str(img.shape))\n\n    return result","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['size_info'] = get_size_list(train.id_code.tolist(), dir_target='../input/train_images')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.size_info.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test['size_info'] = get_size_list(test.id_code.tolist(), dir_target='../input/test_images')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.size_info.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_size_info = train.size_info.value_counts().to_frame().reset_index()\ntest_size_info = test.size_info.value_counts().to_frame().reset_index()\nsize_info = train_size_info.merge(test_size_info,on='index',how='outer').fillna(0)\nsize_info.columns = ['size','size_train','size_test']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"size_info","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tmp = train.groupby(['size_info','diagnosis']).size().unstack().fillna(0).reset_index()\ntrain_size_info.columns = ['size_info','size']\ntmp = tmp.merge(train_size_info,on='size_info',how='left')\ntmp\n# it seem that the size contain some information","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in range(5):\n    tmp.iloc[:,i+1] = tmp.iloc[:,i+1]/tmp['size']\ntmp","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.diagnosis.value_counts().sort_index()/3662","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}