{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"0c7c49f0-fe74-6762-f303-b6bca6b43fd4"},"outputs":[],"source":"from PIL import ImageFilter, ImageStat, Image, ImageDraw\nfrom multiprocessing import Pool, cpu_count\nfrom sklearn.preprocessing import LabelEncoder\nimport pandas as pd\nimport numpy as np\nimport glob\nimport cv2\n\ndef im_multi(path):\n    try:\n        im_stats_im_ = Image.open(path)\n        return [path, {'size': im_stats_im_.size}]\n    except:\n        print(path)\n        return [path, {'size': [0,0]}]\n\ndef im_stats(im_stats_df):\n    im_stats_d = {}\n    p = Pool(cpu_count())\n    ret = p.map(im_multi, im_stats_df['path'])\n    for i in range(len(ret)):\n        im_stats_d[ret[i][0]] = ret[i][1]\n    im_stats_df['size'] = im_stats_df['path'].map(lambda x: ' '.join(str(s) for s in im_stats_d[x]['size']))\n    return im_stats_df\n\ndef get_im_cv2(path):\n    img = cv2.imread(path)\n    resized = cv2.resize(img, (32, 32), cv2.INTER_LINEAR) #use cv2.resize(img, (64, 64), cv2.INTER_LINEAR)\n    return [path, resized]\n\ndef normalize_image_features(paths):\n    imf_d = {}\n    p = Pool(cpu_count())\n    ret = p.map(get_im_cv2, paths)\n    for i in range(len(ret)):\n        imf_d[ret[i][0]] = ret[i][1]\n    ret = []\n    fdata = [imf_d[f] for f in paths]\n    fdata = np.array(fdata, dtype=np.uint8)\n    fdata = fdata.transpose((0, 3, 1, 2))\n    fdata = fdata.astype('float32')\n    fdata = fdata / 255\n    return fdata"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"03c54fb5-f374-92a5-f196-9c0d428b3117"},"outputs":[],"source":"train = glob.glob('../input/train/**/*.jpg') + glob.glob('../input/additional/**/*.jpg')\ntrain=train[:10]\nprint(train)\ntrain = pd.DataFrame([[p.split('/')[3],p.split('/')[4],p] for p in train], columns = ['type','image','path'])[::2] #limit for Kaggle Demo\ntrain = im_stats(train)\ntrain = train[train['size'] != '0 0'].reset_index(drop=True) #remove bad images\ntrain=train[0]\ntrain_data = normalize_image_features(train['path'])\nprint(train_data)\n\nnp.save('train.npy', train_data, allow_pickle=True, fix_imports=True)\n\nle = LabelEncoder()\ntrain_target = le.fit_transform(train['type'].values)\nprint(le.classes_) #in case not 1 to 3 order\nnp.save('train_target.npy', train_target, allow_pickle=True, fix_imports=True)\n\ntest = glob.glob('../input/test/*.jpg')\ntest = pd.DataFrame([[p.split('/')[3],p] for p in test], columns = ['image','path']) [::2] #limit for Kaggle Demo\ntest_data = normalize_image_features(test['path'])\nnp.save('test.npy', test_data, allow_pickle=True, fix_imports=True)\n\ntest_id = test.image.values\nnp.save('test_id.npy', test_id, allow_pickle=True, fix_imports=True)\n\n\n"}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.0"}},"nbformat":4,"nbformat_minor":0}