{"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)\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 all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\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.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import os\nfile = []\nfile = os.listdir('/kaggle/input/deepfake-detection-challenge/train_sample_videos/')\n#file = os.listdir('/kaggle/input/deepfake-detection-challenge/test_videos/')\n#file.remove[\"metadata.json\"]\nsimilar = []\nframe1 = []\ndissimilar = []\nfor i in file:\n    if (i =='metadata.json'):\n              file.remove('metadata.json')\n#print(file)\nfor i in file:\n        file2 = []\n        file1 = '/kaggle/input/deepfake-detection-challenge/train_sample_videos/'+i;\n        #file1 = '/kaggle/input/deepfake-detection-challenge/test_videos/'+i;\n        file2.append(file1)\n#         /*print(file2)*/ \n        import cv2\n        j=0;\n        for j in file2:\n                    cap = cv2.VideoCapture(j)\n                    #print(cap)\n                    #frame=[]\n                    _, frame = cap.read()\n                    frame1.append(frame)\n                    \n#print(frame1)\n#                     ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#print(file)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\n\ndata1 = pd.DataFrame(frame1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#print(data1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data1.columns = ['col']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#print(data1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#data1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rowvalues =[]\nsimilar=[]\ndissimilar=[]\nx =-1\ny=1\nfor y in range(400):\n    #if x<400:\n    #print(data1)\n                        x =x+1;\n                        y = y+1;\n                        #print(x,y)\n                        z = data1.col[x:y]\n                        #dupes = [a for n, a in enumerate(z) if a in z[:n]]\n                        #no_dupes = [a for n, a in enumerate(z) if a not in z[:n]]\n                        #print(z)\n                        for i in z:\n                            #print(k)\n                            #dupes = [a for n, a in enumerate(i) if a in i[:n]]\n                            #no_dupes = [a for n, a in enumerate(i) if a not in i[:n]]\n                            if (i == i+1).any():\n                            \n                                        #print(i)\n                                        similar.append(i)\n                                        #print(\"Similar\"+i)\n                                        #print(i)\n                                        #print(similar)\n                                        #print(similar.append(i))\n                                        #print(similar.append(i), file=open('/Users/debopriyosanyal/Desktop/16071982/op.log', 'w'))\n                                        #print(similar)\n                            else:\n                                    \n                                        dissimilar.append(i)\n                                        #print(\"dissimilar\"+i,file=open('/Users/debopriyosanyal/Desktop/16071982/op1.log', 'w'))\n                                        #print(\"dissimilar\")\n                                        #fileOut.write()\n                                        #print(dissimilar.append(i))\n                                        #print(dissimilar.append(i), file=open('/Users/debopriyosanyal/Desktop/16071982/op1.log', 'w'))\n                                        #print(dissimilar)\n                                    \n                                    \n                            #print(similar)\n                            #print(dissimilar)\n                        if similar:\n                                rowvalues.append(x,y)\n                        #x = x+1\n                        #print(x)\n                        #y = y+2\n                        #print(y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(rowvalues)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"duplicate = []\nif not rowvalues:\n    df = pd.DataFrame({'filename':file})\n    #print (df)\n    df['label'] = df.apply(lambda x: 0, axis=1)\n    print (df)\n    df = df.sort_values('filename')\n    print(df)\n    df = df[df.filename != 'metadata.json']\n    print(df)\n    df.to_csv(\"submission.csv\", encoding='utf-8', index=False)\n    \nelse:\n\n    df1 = pd.DataFrame(rowvalues)\n    df1.columns = ['X','Y']\n    A= df1.col['Y']\n    for i in A:\n       G= df.iloc[i,'filename']\n       duplicate.append(G)\n    dffake = pd.DataFrame(G)\n    dffake.columns = ['filename']\n    dffake['label'] = dffake.apply(lambda x: 1, axis=1)\n    dffake = dffake.sort_values('filename')\n    dffake.to_csv(\"submission.csv\", encoding='utf-8', index =False)\n    ","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}