{"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","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport matplotlib.pyplot as plt\nimport cv2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv')\ntrain.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train['id_code']\ny = train['diagnosis']\nprint(y.value_counts())\n\ny.hist()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.iloc[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img = plt.imread(\"../input/train_images/\"+X.iloc[0]+\".png\")\nplt.imshow(img)\nprint(img.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(y.unique()))\nprint(len(y))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"SEED = 77\nIMG_SIZE = 512\nfig = plt.figure(figsize=(25, 16))\n# display 10 images from each class\nfor class_id in sorted(y.unique()):\n    for i, (idx, row) in enumerate(train.loc[train['diagnosis'] == class_id].sample(5, random_state=SEED).iterrows()):\n        ax = fig.add_subplot(5, 5, class_id * 5 + i + 1, xticks=[], yticks=[])\n        path = f\"../input/train_images/{row['id_code']}.png\"\n        image = cv2.imread(path)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        image = cv2.resize(image, (IMG_SIZE, IMG_SIZE))\n\n        plt.imshow(image)\n        ax.set_title('Label: %d-%d-%s' % (class_id, idx, row['id_code']) )\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.loc[train['diagnosis'] == 0].sample(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}