{"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)\nfrom sklearn.model_selection import train_test_split\nimport zipfile\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\n\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense\nfrom tensorflow.keras.layers import Dropout\nfrom tensorflow.keras.layers import Flatten\nfrom tensorflow.keras.layers import Conv2D\nfrom tensorflow.keras.layers import MaxPooling2D\nfrom tensorflow.keras.layers import BatchNormalization\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.callbacks import TensorBoard,EarlyStopping","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"class LoadData():\n    def __init__(self):\n        self.train_file = None\n        self.test_file = None\n        self.submisson_File = None\n        self.submisson_File = os.path.join('/kaggle/input/dogs-vs-cats',\"Submission.csv\")\n        self.data_frame = None\n        self.train_df = None\n        self.validation_df = None\n        \n        zip_ref = zipfile.ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r')\n        zip_ref.extractall('/tmp/train')\n        zip_ref.close()\n        \n    def prepare_data(self):\n        filenames = os.listdir(\"/tmp/train/train\")\n        categories = []\n        for filename in filenames:\n            category = filename.split('.')[0]\n            if category == 'dog':\n                categories.append(1)\n            else:\n                categories.append(0)\n\n        self.data_frame = pd.DataFrame({'filename': filenames,'category': categories})\n        self.data_frame[\"category\"] = self.data_frame[\"category\"].replace({0: 'cat', 1: 'dog'}) \n        self.train_df, self.validation_df = train_test_split(self.data_frame, test_size=0.20, random_state=42)\n        self.train_df = self.train_df.reset_index(drop=True)\n        self.validation_df = self.validation_df.reset_index(drop=True)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ld_obj = LoadData()\nld_obj.prepare_data()\nld_obj.data_frame.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ld_obj.train_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ld_obj.validation_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class PreProcessing():\n    def __init__(self):\n        self.train_data_gen = None\n        self.valid_data_gen = None\n        self.FAST_RUN = False\n        self.image_width=128\n        self.image_height=128\n        self.image_size=(self.image_width, self.image_height)\n        self.image_channels=3\n        self.batch_size = 15\n        self.train_data_length = ld_obj.train_df.shape[0]\n        self.validation_data_length = ld_obj.validation_df.shape[0]\n        self.train_generator = None\n        self.validation_generator = None\n        \n    def data_genrator(self):\n        train_datagen = ImageDataGenerator(\n        rotation_range=15,\n        rescale=1./255,\n        shear_range=0.1,\n        zoom_range=0.2,\n        horizontal_flip=True,\n        width_shift_range=0.1,\n        height_shift_range=0.1\n        )\n\n        self.train_generator = train_datagen.flow_from_dataframe(\n            ld_obj.train_df, \n            \"/tmp/train/train/\", \n            x_col='filename',\n            y_col='category',\n            target_size=self.image_size,\n            class_mode='categorical',\n            batch_size=self.batch_size\n        )\n        \n        validation_datagen = ImageDataGenerator(rescale=1./255)\n        self.validation_generator = validation_datagen.flow_from_dataframe(\n            ld_obj.validation_df, \n            \"/tmp/train/train/\", \n            x_col='filename',\n            y_col='category',\n            target_size=self.image_size,\n            class_mode='categorical',\n            batch_size=self.batch_size\n        )\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pre_process_obj = PreProcessing()\npre_process_obj.data_genrator()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class DesignModel():\n    def __init__(self):\n        self.model = None\n        \n    def create_model(self):\n        model = Sequential()\n\n        model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(pre_process_obj.image_width, pre_process_obj.image_height, pre_process_obj.image_channels)))\n        model.add(BatchNormalization())\n        model.add(MaxPooling2D(pool_size=(2, 2)))\n        model.add(Dropout(0.25))\n\n        model.add(Conv2D(64, (3, 3), activation='relu'))\n        model.add(BatchNormalization())\n        model.add(MaxPooling2D(pool_size=(2, 2)))\n        model.add(Dropout(0.25))\n\n        model.add(Conv2D(128, (3, 3), activation='relu'))\n        model.add(BatchNormalization())\n        model.add(MaxPooling2D(pool_size=(2, 2)))\n        model.add(Dropout(0.25))\n\n        model.add(Flatten())\n        model.add(Dense(512, activation='relu'))\n        model.add(BatchNormalization())\n        model.add(Dropout(0.5))\n        \n        model.add(Dense(2, activation='softmax'))\n        self.model = model\n    \n    def compile_model(self):\n        self.model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\n\n        self.model.summary()\n    def train_model(self):\n        \n        self.model.fit(pre_process_obj.train_generator,\n                              validation_data=pre_process_obj.validation_generator,\n                              steps_per_epoch=pre_process_obj.train_data_length//pre_process_obj.batch_size,\n                              epochs=15,\n                              validation_steps=pre_process_obj.validation_data_length//pre_process_obj.batch_size,\n                              verbose=2)\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_obj = DesignModel()\nmodel_obj.create_model()\nmodel_obj.compile_model()\nmodel_obj.train_model()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class Prediction():\n    def __init__(self,model):\n        self.model = model\n        \n    def prediction(self):\n        zip_ref = zipfile.ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r')\n        zip_ref.extractall('/tmp/test1')\n        zip_ref.close()\n        test_filenames = os.listdir(\"/tmp/test1/test1\")\n        test_df = pd.DataFrame({\n            'filename': test_filenames\n        })\n        nb_samples = test_df.shape[0]\n        \n        test_gen = ImageDataGenerator(rescale=1./255)\n        test_generator = test_gen.flow_from_dataframe(\n            test_df, \n            \"/tmp/test1/test1/\", \n            x_col='filename',\n            y_col=None,\n            class_mode=None,\n            target_size=pre_process_obj.image_size,\n            batch_size=pre_process_obj.batch_size,\n            shuffle=False\n        )\n        predict = self.model.predict_generator(test_generator, steps=np.ceil(nb_samples/pre_process_obj.batch_size))\n        test_df['category'] = np.argmax(predict, axis=-1)\n        label_map = dict((v,k) for k,v in pre_process_obj.train_generator.class_indices.items())\n        test_df['category'] = test_df['category'].replace(label_map)\n        test_df['category'] = test_df['category'].replace({ 'dog': 1, 'cat': 0 })\n\n        submission_df = test_df.copy()\n        submission_df['id'] = submission_df['filename'].str.split('.').str[0]\n        submission_df['label'] = submission_df['category']\n        submission_df.drop(['filename', 'category'], axis=1, inplace=True)\n        submission_df.to_csv('submission.csv', index=False)\n        \n    def predict(self,image):\n        print(image)\n        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_obj = Prediction(model_obj.model)\npred_obj.prediction()","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}