{"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\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\n#for dirname, _, filenames in os.walk('../input/haarcascadefrontalfaces/'):\n    #for filename in filenames:\n        #print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Loading Data"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_dir = '/kaggle/input/deepfake-detection-challenge/train_sample_videos/'\ntrain_video_files = [train_dir + x for x in os.listdir(train_dir)]\ntest_dir = '/kaggle/input/deepfake-detection-challenge/test_videos/'\ntest_video_files = [test_dir + x for x in os.listdir(test_dir)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train = pd.read_json('/kaggle/input/deepfake-detection-challenge/train_sample_videos/metadata.json').transpose()\ndf_train.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Count The Real and Fake Videos"},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.label.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.label.value_counts().plot(kind='pie')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Analyzing Training Videos By Face Detection"},{"metadata":{"trusted":true},"cell_type":"code","source":"import cv2\n# Load the cascade\nface_cascade = cv2.CascadeClassifier('../input/haarcascadefrontalfaces/haarcascade_frontalface_default.xml')\ncolumns = 1\nrows = 10\nplt.figure(figsize=(100, 100))\n# To capture video from webcam. \n#cap = cv2.VideoCapture(0)\n# To use a video file as input \n#_,img = cap.read()\nfor i in range(1, columns*rows+1):\n    cap = cv2.VideoCapture(train_video_files[i])\n    _,img = cap.read()\n    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n    # Detect the faces\n    faces = face_cascade.detectMultiScale(gray,1.1, 5)\n    # Draw the rectangle around each face\n    for (x, y, w, h) in faces:\n        cv2.rectangle(img, (x, y), (x+w, y+h), (255, 0, 0), 5)\n    # Display\n    name_video = train_video_files[i].split('/', 5)[5]\n    df=df_train[df_train.index == name_video] \n    label=df['label'].values[0]\n    #ax.set_title(label)\n    plt.subplot(rows, columns, i)\n    plt.imshow(img)\n    #x=img.shape[1]\n    plt.text(1000,1000, str(label),\n             fontsize=18, ha='center',backgroundcolor='black', color='white', weight='bold')\n    cap.release()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Analyzing Testing Videos By Face Detection and Finding The Video Name"},{"metadata":{"trusted":true},"cell_type":"code","source":"import cv2\n# Load the cascade\nface_cascade = cv2.CascadeClassifier('../input/haarcascadefrontalfaces/haarcascade_frontalface_default.xml')\ncolumns = 1\nrows = 5\nplt.figure(figsize=(100, 100))\n# To capture video from webcam. \n#cap = cv2.VideoCapture(0)\n# To use a video file as input \n#_,img = cap.read()\nfor i in range(1, 5):\n    cap = cv2.VideoCapture(test_video_files[i])\n    _,img = cap.read()\n    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n    # Detect the faces\n    faces = face_cascade.detectMultiScale(gray,1.1, 5)\n    # Draw the rectangle around each face\n    for (x, y, w, h) in faces:\n        cv2.rectangle(img, (x, y), (x+w, y+h), (255, 0, 0), 5)\n    # Display\n    name_video = train_video_files[i].split('/', 5)[5]\n    #df=df_train[df_train.index == name_video] \n    #label=df['label'].values[0]\n    #ax.set_title(label)\n    plt.subplot(rows, columns, i)\n    plt.imshow(img)\n    #x=img.shape[1]\n    plt.text(1000,1000, str(name_video),\n             fontsize=18, ha='center',backgroundcolor='black', color='white', weight='bold')\n    cap.release()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Manual Detection From Testing Videos"},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv(\"/kaggle/input/deepfake-detection-challenge/sample_submission.csv\")\ndf['label'] = 0.5 #maximum are fake\ndf.loc[df['filename'] == 'aassnaulhq.mp4', 'label'] = 0 # Guess the true value\ndf.loc[df['filename'] == 'aayfryxljh.mp4', 'label'] = 0\ndf.loc[df['filename'] == 'alrtntfxtd.mp4', 'label'] = 0\ndf.loc[df['filename'] == 'ayipraspbn.mp4', 'label'] = 0\ndf.to_csv('submission.csv', index=False)","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":1}