{"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 5GB 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":"print(os.listdir(\"../input/dogs-vs-cats/\"))\nimport zipfile\nimport tensorflow as tf\n\ndataset_train=\"train\"\ndataset_test=\"test1\"\nwith zipfile.ZipFile(\"../input/dogs-vs-cats/\"+dataset_train+\".zip\",\"r\") as z:\n    z.extractall(\".\")\n    \nwith zipfile.ZipFile(\"../input/dogs-vs-cats/\"+dataset_test+\".zip\",\"r\") as z:\n    z.extractall(\".\")\n\n#from subprocess import check_output\n#print(check_output([\"ls\", \"train\"]).decode(\"utf8\"))\n","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})\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df[\"category\"] = df[\"category\"].replace({0: 'cat', 1: 'dog'}) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\ntrain_df, validate_df = train_test_split(df, \n                                         test_size=0.20,                                         \n                                         random_state=0)\ntrain_df = train_df.reset_index(drop=True)\nvalidate_df = validate_df.reset_index(drop=True)\n\ntotal_train = train_df.shape[0]\ntotal_validate = validate_df.shape[0]\nbatch_size=15","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import Activation, Flatten, Dense\nfrom keras.utils import to_categorical\n#from keras import backend as K\n\nmodel = Sequential()\n#add model layers\nmodel.add(Conv2D(64, kernel_size=3, activation='relu', input_shape=(128,128,3)))\nmodel.add(Conv2D(64, kernel_size=3, activation='relu'))\nmodel.add(Conv2D(32, kernel_size=3, activation='relu'))\nmodel.add(Conv2D(32, kernel_size=3, activation='relu'))\nmodel.add(Flatten())\nmodel.add(Dense(2, activation='softmax'))\nmodel.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n\ntrain_datagen = ImageDataGenerator(\n    rescale=1. / 255,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True)\n\nvalidation_datagen = ImageDataGenerator(rescale=1. / 255)\n\ntrain_generator = train_datagen.flow_from_dataframe(\n    train_df,\n    \"/kaggle/working/train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=(128,128),\n    batch_size=15,\n    class_mode='categorical')\n\nvalidation_generator = validation_datagen.flow_from_dataframe(\n    validate_df,\n    \"/kaggle/working/train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=(128,128),\n    batch_size=15,\n    class_mode='categorical')\n\nmodel.fit_generator(\n    train_generator,\n    validation_data=validation_generator,epochs=3)\n\n\n\nmodel.save_weights(\"model.h5\")\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_filenames = os.listdir(\"/kaggle/working/test1\")\ntest_df = pd.DataFrame({\n    'filename': test_filenames\n})\n\nnb_samples = test_df.shape[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_gen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_gen.flow_from_dataframe(\n    test_df, \n    \"/kaggle/working/test1\", \n    x_col='filename',\n    y_col=None,\n    class_mode=None,\n    target_size=(128,128),\n    batch_size=15,\n    shuffle=False\n)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict = model.predict_generator(test_generator)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['category'] = np.argmax(predict, axis=-1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label_map = dict((v,k) for k,v in train_generator.class_indices.items())\ntest_df['category'] = test_df['category'].replace(label_map)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['category'] = test_df['category'].replace({ 'dog': 1, 'cat': 0 })\ntest_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df = test_df.copy()\nsubmission_df['id'] = submission_df['filename'].str.split('.').str[0]\nsubmission_df['label'] = submission_df['category']\nsubmission_df.drop(['filename', 'category'], axis=1, inplace=True)\nsubmission_df.to_csv('submission.csv', index=False)","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}