{"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","collapsed":true,"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":false},"cell_type":"markdown","source":"**分析目标：**\n\n1.测试数据集多大，训练数据集多大，各多少张图片？\n\n2.眼底病变的分类。每个类别的图片数量？用图表分析一下这个数量分布\n\n3.展示每个分类的4个图片\n\n4.是否图片存不正确的标签？"},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nimport matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data=pd.read_csv('../input/train.csv')\ntest_data = pd.read_csv(\"../input/test.csv\")\ntrain_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#1.测试数据集多大，训练数据集多大，各多少张图片？\nprint('train_data size:',train_data.id_code.count())\nprint('test_data size:',test_data.id_code.count())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#2.眼底病变的分类。每个类别的图片数量？用图表分析一下这个数量分布\ndiagnosis_counts = train_data.diagnosis.value_counts()\nprint(diagnosis_counts)\ndiagnosis_counts.plot(kind = 'pie',autopct='%.2f')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#3.展示每个分类的4个图片\nimport matplotlib.image as pli\nimport cv2\na = 0\nfig=plt.figure(figsize=(10,12))\nplt.suptitle('diagnosis pic', fontsize=16, fontweight='bold')\nplt.subplots_adjust(left=0.2, wspace=0.2, top=0.8)  #位置调整\nfor dia in range(0,5):\n    for i in train_data[train_data.diagnosis == dia].iloc[:4].id_code:\n        add = '../input/train_images/'+i+'.png'\n        a += 1\n        plt.subplot(5,4,a) \n        image = pli.imread(add)\n#         resized = cv2.resize(image,(277,277))\n        plt.imshow(image)\n        plt.title(dia, color='b')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#4.是否图片存不正确的标签？\n#啥意思","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}