{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nfrom glob import glob\nimport random\nimport time\nimport tensorflow\nimport datetime\nos.environ['KERAS_BACKEND'] = 'tensorflow'\nos.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' # 3 = INFO, WARNING, and ERROR messages are not printed\n\nfrom tqdm import tqdm\n\nimport numpy as np\nimport pandas as pd\nfrom IPython.display import FileLink\nimport matplotlib.pyplot as plt\nimport warnings\nwarnings.filterwarnings('ignore')\nimport seaborn as sns \n%matplotlib inline\nfrom IPython.display import display, Image\nimport matplotlib.image as mpimg\nimport cv2\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.datasets import load_files       \nfrom keras.utils import np_utils\nfrom sklearn.utils import shuffle\nfrom sklearn.metrics import log_loss\n\nfrom keras.models import Sequential, Model\nfrom keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization, GlobalAveragePooling2D\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.preprocessing import image\nfrom keras.callbacks import ModelCheckpoint, EarlyStopping\nfrom keras.applications.vgg16 import VGG16","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"dataset = pd.read_csv('../input/state-farm-distracted-driver-detection/driver_imgs_list.csv')\ndataset.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"by_drivers = dataset.groupby('subject')\nunique_drivers = by_drivers.groups.keys()\nprint(unique_drivers)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Load the dataset previously downloaded from Kaggle\nNUMBER_CLASSES = 10\n# Color type: 1 - grey, 3 - rgb\n\ndef get_cv2_image(path, img_rows, img_cols, color_type=3):\n    # Loading as Grayscale image\n    if color_type == 1:\n        img = cv2.imread(path, cv2.IMREAD_GRAYSCALE)\n    elif color_type == 3:\n        img = cv2.imread(path, cv2.IMREAD_COLOR)\n    # Reduce size\n    img = cv2.resize(img, (img_rows, img_cols)) \n    return img\n\n# Training\ndef load_train(img_rows, img_cols, color_type=3):\n    start_time = time.time()\n    train_images = [] \n    train_labels = []\n    # Loop over the training folder \n    for classed in tqdm(range(NUMBER_CLASSES)):\n        print('Loading directory c{}'.format(classed))\n        files = glob(os.path.join('../input/state-farm-distracted-driver-detection/imgs/train' , 'c' + str(classed), '*.jpg'))\n        for file in files:\n            img = get_cv2_image(file, img_rows, img_cols, color_type)\n            train_images.append(img)\n            train_labels.append(classed)\n    print(\"Data Loaded in {} second\".format(time.time() - start_time))\n    return train_images, train_labels \n\ndef read_and_normalize_train_data(img_rows, img_cols, color_type):\n    X, labels = load_train(img_rows, img_cols, color_type)\n    y = np_utils.to_categorical(labels, 10)\n    x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n    \n    x_train = np.array(x_train, dtype=np.uint8).reshape(-1,img_rows,img_cols,color_type)\n    x_test = np.array(x_test, dtype=np.uint8).reshape(-1,img_rows,img_cols,color_type)\n    \n    return x_train, x_test, y_train, y_test\n\n# Validation\ndef load_test(size=200000, img_rows=64, img_cols=64, color_type=3):\n    path = os.path.join('../input/state-farm-distracted-driver-detection/imgs/test' ,'c' + str(classed), '*.jpg')\n    files = sorted(glob(path))\n    X_test, X_test_id = [], []\n    total = 0\n    files_size = len(files)\n    for file in tqdm(files):\n        if total >= size or total >= files_size:\n            break\n        file_base = os.path.basename(file)\n        img = get_cv2_image(file, img_rows, img_cols, color_type)\n        X_test.append(img)\n        X_test_id.append(file_base)\n        total += 1\n    return X_test, X_test_id\n\ndef read_and_normalize_sampled_test_data(size, img_rows, img_cols, color_type=3):\n    test_data, test_ids = load_test(size, img_rows, img_cols, color_type)\n    \n    test_data = np.array(test_data, dtype=np.uint8)\n    test_data = test_data.reshape(-1,img_rows,img_cols,color_type)\n    \n    return test_data, test_ids","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_rows = 224\nimg_cols = 224\ncolor_type = 3","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_test, y_train, y_test = read_and_normalize_train_data(img_rows, img_cols, color_type)\nprint('Train shape:', x_train.shape)\nprint(x_train.shape[0], 'train samples')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Statistics\n# Load the list of names\nnames = [item[17:19] for item in sorted(glob(\"../input/state-farm-distracted-driver-detection/imgs/train/*/\"))]\ntest_files_size = len(np.array(glob(os.path.join('../input/state-farm-distracted-driver-detection/imgs', 'test', '*.jpg'))))\nx_train_size = len(x_train)\ncategories_size = len(names)\nx_test_size = len(x_test)\nprint('There are %s total images.\\n' % (test_files_size + x_train_size + x_test_size))\nprint('There are %d training images.' % x_train_size)\nprint('There are %d total training categories.' % categories_size)\nprint('There are %d validation images.' % x_test_size)\nprint('There are %d test images.'% test_files_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Plot figure size\nplt.figure(figsize = (10,10))\n# Count the number of images per category\nsns.countplot(x = 'classname', data = dataset)\n# Change the Axis names\nplt.ylabel('Count')\nplt.title('Categories Distribution')\n# Show plot\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Find the frequency of images per driver\ndrivers_id = pd.DataFrame((dataset['subject'].value_counts()).reset_index())\ndrivers_id.columns = ['driver_id', 'Counts']\ndrivers_id","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Plotting class distribution\ndataset['class_type'] = dataset['classname'].str.extract('(\\d)',expand=False).astype(np.float)\nplt.figure(figsize = (20,20))\ndataset.hist('class_type', alpha=0.5, layout=(1,1), bins=10)\nplt.title('Class distribution')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"activity_map = {'c0': 'Safe driving', \n                'c1': 'Texting - right', \n                'c2': 'Talking on the phone - right', \n                'c3': 'Texting - left', \n                'c4': 'Talking on the phone - left', \n                'c5': 'Operating the radio', \n                'c6': 'Drinking', \n                'c7': 'Reaching behind', \n                'c8': 'Hair and makeup', \n                'c9': 'Talking to passenger'}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize = (12, 20))\nimage_count = 1\nBASE_URL = '../input/state-farm-distracted-driver-detection/imgs/train/'\nfor directory in os.listdir(BASE_URL):\n    if directory[0] != '.':\n        for i, file in enumerate(os.listdir(BASE_URL + directory)):\n            if i == 1:\n                break\n            else:\n                fig = plt.subplot(5, 2, image_count)\n                image_count += 1\n                image = mpimg.imread(BASE_URL + directory + '/' + file)\n                plt.imshow(image)\n                plt.title(activity_map[directory])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}