{"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":"\n\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nimport os, zipfile, random\n\n# Import the backend\nimport tensorflow as tf\n\n# Data preprocessing\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator, load_img\nfrom tensorflow.keras.preprocessing import image\nfrom tensorflow.keras.utils import to_categorical\n\n# Model architecture\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D, BatchNormalization\nfrom tensorflow.keras.callbacks import LearningRateScheduler, EarlyStopping, ReduceLROnPlateau\n\n# Model evaluation\nfrom sklearn.metrics import accuracy_score\nimport os, cv2, re, random\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_size = (150, 150)\ninput_dim = (150, 150, 3)\nepochs = 30\nbatch_size = 16","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"local_zip_train = '/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip'\nlocal_zip_test = '/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip'\nzip_ref = zipfile.ZipFile(local_zip_train, 'r')\nzip_ref.extractall('/kaggle/working')\nzip_ref.close()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames = os.listdir(\"/kaggle/working/train\")\ncategories = []\nfor filename in filenames:\n    category = filename.split('.')[0]\n    if category == 'dog':\n        categories.append(1)\n    else:\n        categories.append(0)\n\ndf = pd.DataFrame({\n    'filename': filenames,\n    'category': categories\n})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images_list = []\nfor i in df['filename']:\n    i='/kaggle/working/train/'+i\n    images_list.append(i)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_width = 150\nimg_height = 150\ndef prepare_data(list_of_images):\n    \"\"\"\n    Returns two arrays: \n        x is an array of resized images\n        y is an array of labels\n    \"\"\"\n    x = [] # images as arrays\n    y = [] # labels\n    \n    for image in list_of_images:\n        x.append(cv2.resize(cv2.imread(image), (img_width,img_height), interpolation=cv2.INTER_CUBIC))\n    \n    for i in list_of_images:\n        if 'dog' in i:\n            y.append(1)\n        elif 'cat' in i:\n            y.append(0)\n        #else:\n            #print('neither cat nor dog name present in images')\n            \n    return x, y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X,Y = prepare_data(images_list) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import random as rn\n\nfig,ax=plt.subplots(5,2)\nfig.set_size_inches(15,15)\nfor i in range(5):\n    for j in range (2):\n        l=rn.randint(0,len(Y))\n        ax[i,j].imshow(X[l])\n       # ax[i,j].set_title('Dog: '+Y[l])\n        \nplt.tight_layout()\n        \n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_val, Y_train, Y_val = train_test_split(X,Y, test_size=0.2, random_state=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.applications.vgg16 import decode_predictions\nfrom keras.applications.vgg16 import VGG16\nfrom keras.models import Model\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras import layers, models, optimizers\nmodel=models.Sequential()\n\nmodel.add(layers.Conv2D(32, (3, 3), input_shape=(150, 150, 3)))\nmodel.add(layers.Activation('relu'))\nmodel.add(layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(layers.Conv2D(32, (3, 3)))\nmodel.add(layers.Activation('relu'))\nmodel.add(layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(layers.Conv2D(64, (3, 3)))\nmodel.add(layers.Activation('relu'))\nmodel.add(layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(64))\nmodel.add(layers.Activation('relu'))\nmodel.add(layers.Dropout(0.5))\nmodel.add(layers.Dense(1))\nmodel.add(layers.Activation('sigmoid'))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\nmodel.compile(loss='binary_crossentropy',\n              optimizer='rmsprop',\n              metrics=['accuracy'])\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\ntrain_datagen = ImageDataGenerator(\n    rescale=1. / 255,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True)\n\nval_datagen = ImageDataGenerator(\n    rescale=1. / 255,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\ntrain_generator = train_datagen.flow(np.array(X_train), Y_train, batch_size=batch_size)\nvalidation_generator = val_datagen.flow(np.array(X_val), Y_val, batch_size=batch_size)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"nb_train_samples = len(X_train)\nnb_validation_samples = len(X_val)\nbatch_size = 16","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\nvisualize_acc_loss = model.fit_generator(\n    train_generator, \n    steps_per_epoch=nb_train_samples // batch_size,\n    epochs=40,\n    validation_data=validation_generator,\n    validation_steps=nb_validation_samples // batch_size\n)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\nfig, ax = plt.subplots(2,1)\nax[0].plot(visualize_acc_loss.history['loss'], color='b', label=\"Training loss\")\nax[0].plot(visualize_acc_loss.history['val_loss'], color='r', label=\"validation loss\",axes =ax[0])\nlegend = ax[0].legend(loc='best', shadow=True)\n\nax[1].plot(visualize_acc_loss.history['accuracy'], color='b', label=\"Training accuracy\")\nax[1].plot(visualize_acc_loss.history['val_accuracy'], color='r',label=\"Validation accuracy\")\nlegend = ax[1].legend(loc='best', shadow=True)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def plot_confusion_matrix(cm, classes,\n                          normalize=False,\n                          title='Confusion matrix',\n                          cmap=plt.cm.Blues):\n    \"\"\"\n    This function prints and plots the confusion matrix.\n    Normalization can be applied by setting `normalize=True`.\n    \"\"\"\n    plt.imshow(cm, interpolation='nearest', cmap=cmap)\n    plt.title(title)\n    plt.colorbar()\n    tick_marks = np.arange(len(classes))\n    plt.xticks(tick_marks, classes, rotation=45)\n    plt.yticks(tick_marks, classes)\n    \n    if normalize:\n        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n\n    thresh = cm.max() / 2.\n    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n        plt.text(j, i, cm[i, j],\n                 horizontalalignment=\"center\",\n                 color=\"white\" if cm[i, j] > thresh else \"black\")\n\n    plt.tight_layout()\n    plt.ylabel('True label')\n    plt.xlabel('Predicted label')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import confusion_matrix\nimport itertools\n\nY_pred = model.predict(np.array(X_val))\n\nY_pred_labels = [] # labels    \n    \nfor i in range(0,len(Y_pred)):\n    if Y_pred[i, 0] >= 0.5: \n        Y_pred_labels.append(1)\n    else:\n        Y_pred_labels.append(0)\n\n# Convert predictions classes to one hot vectors \nY_pred_classes = np.argmax(Y_pred) \n\n# compute the confusion matrix\nconfusion_mtx = confusion_matrix(Y_val, Y_pred_labels) \n\n# plot the confusion matrix\nplot_confusion_matrix(confusion_mtx, classes = range(1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_pred = model.predict(np.array(X_val))\n\n#####predict cat | predict dog\nfor i in range(0,5):\n    if Y_pred[i, 0] >= 0.5: \n        print('I am {:.2%} sure this is a Dog'.format(Y_pred[i][0]))\n    else: \n        print('I am {:.2%} sure this is a Cat'.format(1-Y_pred[i][0]))\n        \n    plt.imshow(X_val[i])    \n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def prepare_data_test(list_of_images):\n\n    x = [] # images as arrays\n    for image in list_of_images:\n        x.append(cv2.resize(cv2.imread(image), (150,150), interpolation=cv2.INTER_CUBIC))\n        return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"local_zip_test = '/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip'\nzip_ref = zipfile.ZipFile(local_zip_test, 'r')\nzip_ref.extractall('/kaggle/working')\nzip_ref.close()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames = os.listdir(\"/kaggle/working/test\")\ncategories = []\nfor filename in filenames:\n    categories.append(filename)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images_list = []\nfor i in categories:\n    i='/kaggle/working/test/'+i\n    images_list.append(i)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images_list","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_image=prepare_data_test(images_list)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_datagen = ImageDataGenerator(\n    rescale=1. / 255,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_generator = test_datagen.flow(np.array(test_image), batch_size=batch_size)\nprediction_probabilities = model.predict_generator(test_generator, verbose=1,steps = len(test_generator))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"counter = range(1, len(images_list) + 1)\nsolution = pd.DataFrame({\"id\": counter, \"label\":list(prediction_probabilities)})\ncols =solution.columns\n\nfor col in cols:\n    solution[col] = solution[col].map(lambda x: str(x).lstrip('[').rstrip(']')).astype(float)\n\nsolution.to_csv(\"dogsVScats.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":4}