{"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)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport cv2\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.csv')\ntrain_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(train_data.category_id)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data['category_id'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"empty_img = train_data[train_data.category_id == 0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(empty_img.shape)\nempty_img.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"reduced_empty_img = empty_img.sample(15000)\nprint(reduced_empty_img.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"non_empty_img = train_data[train_data.category_id !=0]\nprint(non_empty_img.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"reduced_data = pd.concat((reduced_empty_img,non_empty_img))\nprint(reduced_data.shape)\nreduced_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(reduced_data.category_id)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data = pd.read_csv('../input/test.csv')\ntest_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_files = reduced_data['file_name'].values\ntest_files = test_data['file_name'].values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_files.shape)\nprint(test_files.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_files[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_images = list()\nfor i in range(len(train_files)):\n    if i % 1000 == 0:\n        print(i)\n    img = plt.imread(os.path.join('../input/train_images/', train_files[i]))\n    if len(img.shape) != 3:\n        img = cv2.cvtColor(img,cv2.COLOR_GRAY2RGB)\n    train_images.append(cv2.resize(img,(32,32)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_images = list()\nfor i in range(len(test_files)):\n    if i % 1000 == 0:\n        print(i)\n    img = plt.imread(os.path.join('../input/test_images/', test_files[i]))\n    if len(img.shape) != 3:\n        img = cv2.cvtColor(img,cv2.COLOR_GRAY2RGB)\n    test_images.append(cv2.resize(img,(32,32)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils.np_utils import to_categorical\n\nX_train = np.array(train_images)\nX_test = np.array(test_images)\n\ntarget_dummies = reduced_data['category_id'].values\nY_train = to_categorical(target_dummies)\n\nprint(X_train.shape)\nprint(X_test.shape)\nprint(Y_train.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.save('X_train.npy', X_train)\nnp.save('X_test.npy', X_test)\nnp.save('Y_train.npy', Y_train)","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}