{"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\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 read-only \"../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# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import zipfile\ntrain_zip = '/kaggle/input/dogs-vs-cats/train.zip'\ntest_zip = '/kaggle/input/dogs-vs-cats/test1.zip'\ntrain_ref = zipfile.ZipFile(train_zip,'r')\ntest_ref = zipfile.ZipFile(test_zip,'r')\ntrain_ref.extractall('/kaggle/temp/')\ntrain_ref.close()\ntest_ref.extractall('/kaggle/temp/')\ntest_ref.close()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for dirname, _, filenames in os.walk('/kaggle/temp/'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.mkdir('/kaggle/temp/Processed/')\nos.mkdir('/kaggle/temp/Processed/train')\nos.mkdir('/kaggle/temp/Processed/train/dogs')\nos.mkdir('/kaggle/temp/Processed/train/cats')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import shutil","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames = os.listdir('/kaggle/temp/train/')\nfor filename in filenames:\n    category = filename.split('.')[0]\n    if category == 'dog':\n        shutil.move('/kaggle/temp/train/'+filename,'/kaggle/temp/Processed/train/dogs')\n    else:\n        shutil.move('/kaggle/temp/train/'+filename,'/kaggle/temp/Processed/train/cats')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(os.listdir('/kaggle/temp/Processed/train/dogs'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(os.listdir('/kaggle/temp/Processed/train/cats'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.mkdir('/kaggle/temp/Processed/validation')\nos.mkdir('/kaggle/temp/Processed/validation/dogs')\nos.mkdir('/kaggle/temp/Processed/validation/cats')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dog_filenames = os.listdir('/kaggle/temp/Processed/train/dogs')[:2500]\ncat_filenames = os.listdir('/kaggle/temp/Processed/train/cats')[:2500]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for filename_d in dog_filenames:\n    shutil.move('/kaggle/temp/Processed/train/dogs/'+filename_d,'/kaggle/temp/Processed/validation/dogs')\nfor filename_c in cat_filenames:\n    shutil.move('/kaggle/temp/Processed/train/cats/'+filename_c,'/kaggle/temp/Processed/validation/cats')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(os.listdir('/kaggle/temp/Processed/train/dogs'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(os.listdir('/kaggle/temp/Processed/train/cats'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(os.listdir('/kaggle/temp/Processed/validation/dogs'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(os.listdir('/kaggle/temp/Processed/validation/cats'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.layers import Dense,Conv2D, MaxPooling2D, Flatten\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.optimizers import RMSprop\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential([Conv2D(16,kernel_size=(3,3),activation='relu',input_shape=(150,150,3)),\n                   MaxPooling2D(2,2),\n                   Conv2D(32,kernel_size=(3,3),activation='relu'),\n                   MaxPooling2D(2,2),\n                   Conv2D(64,kernel_size=(3,3),activation='relu'),\n                   MaxPooling2D(2,2),\n                   Flatten(),\n                   Dense(512,activation='relu'),\n                   Dense(1,activation='sigmoid')\n                   ])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=RMSprop(lr=0.001),loss='binary_crossentropy',metrics=['acc'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dir = '/kaggle/temp/Processed/train/'\ntest_dir = '/kaggle/temp/test1/'\nval_dir = '/kaggle/temp/Processed/validation/'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale = 1.0/255)\ntest_datagen  = ImageDataGenerator(rescale = 1.0/255)\n\ntrain_generator = train_datagen.flow_from_directory(train_dir,batch_size=25,class_mode='binary',target_size=(150,150))\nvalidation_generator = test_datagen.flow_from_directory(val_dir,batch_size=25,class_mode='binary',target_size=(150,150))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(train_generator,\n                   validation_data = validation_generator,\n                   steps_per_epoch=100,\n                   epochs=30,\n                   validation_steps=50,\n                   verbose=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_files = {}\nfor dirname, _, filenames in os.walk('/kaggle/temp/test1/'):\n    for filename in filenames:\n        test_files[int(filename.split('.')[0])]=filename","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sorted_test_files= {}\nfor i in sorted(test_files):\n    sorted_test_files[i] = test_files[i]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sorted_test_files","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.preprocessing import image\npredictions = []\nfor i in range(len(sorted_test_files)):\n    test_img = '/kaggle/temp/test1/'+ sorted_test_files[i+1]\n    test_img = image.load_img(test_img,target_size=(150,150))\n    test_img = image.img_to_array(test_img)\n    test_img = np.vstack([[test_img]])\n    pred = model.predict(test_img)\n    predictions.append(int(pred[0][0]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(predictions)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_img1 = '/kaggle/temp/test1/'+ sorted_test_files[8]\ntest_img1 = image.load_img(test_img1,target_size=(150,150))\ntest_img1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ids = [*range(1,12501)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(predictions)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = {'id':ids,'label':predictions}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame(sub)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pwd","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv('submission.csv')","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}