{"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)\nfrom PIL import Image\nimport matplotlib.pyplot as plt\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":"train_data = pd.read_csv('../input/train_ship_segmentations_v2.csv')\ntrain_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9afa05eae97da18079201b97ab947b4e701cfd86"},"cell_type":"code","source":"train_samples = train_data.loc[train_data['EncodedPixels'].notnull(),:].sample(10)\ntrain_samples","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2434803c5856452e00485314b67ebdf48b0b3f37"},"cell_type":"code","source":"train_images = os.listdir(\"../input/train_v2\")\nlen(train_images)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ad85e2465440584689941380b75e76362982481e"},"cell_type":"code","source":"n_images = 10\ncont = 0\nfig, axs = plt.subplots(n_images,2,figsize=(15,15/2*n_images))\n\ntrain_samples = train_data.loc[train_data['EncodedPixels'].notnull(),:].sample(n_images)\nfor ind, row_sample in train_samples.iterrows():\n    #Load Image\n    im = Image.open(\"../input/train_v2/{}\".format(row_sample['ImageId']))\n    px = im.load()\n    print(np.asarray(im).shape)\n    #Show image\n    ax = axs[cont,0]\n    ax.imshow(np.asarray(im))\n    ax.axis('off')\n    \n    #Load Pixels\n    pixels_array = row_sample['EncodedPixels'].split(' ')\n    \n    #Edit Pixels of image\n    for i in np.arange(0,len(pixels_array),2):\n        for pixel in range(int(pixels_array[i]), int(pixels_array[i])+int(pixels_array[i+1])):\n            numpy_row = np.floor(int(pixel)/np.asarray(im).shape[0])\n            numpy_column = int(pixel)-np.asarray(im).shape[0]*numpy_row\n            px[numpy_row,numpy_column] = (250,0,0) \n    \n    #Show image\n    ax = axs[cont,1]\n    ax.imshow(np.asarray(im))\n    ax.axis('off')\n    \n    cont += 1\n    \nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"12e8799d0b1680ca0e6abd4927913369f8194b81"},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}