{"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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nimport seaborn as sns\n\nnp.random.seed(1)","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"df_train = pd.read_csv('../input/train.csv')\ndf_test = pd.read_csv('../input/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = df_train['label']\nx_train = df_train.drop(labels = ['label'] , axis=1)\ndel df_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"g = sns.countplot(y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train/255.0\ndf_test = df_test/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.isnull().any().describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test.isnull().any().describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train.values.reshape(-1 , 28 , 28 ,1)\ndf_test = df_test.values.reshape(-1 , 28 ,28 ,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils.np_utils import to_categorical\ny_train = to_categorical(y_train , num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_train  , x_val , y_train , y_val = train_test_split(x_train , y_train , test_size = .1 , random_state = 0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.image as mpimg\ng = plt.imshow(x_train[0][: , : , 0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\n\nclassifier = Sequential()\n\nclassifier.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\nclassifier.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nclassifier.add(MaxPool2D(pool_size=(2,2)))\nclassifier.add(Dropout(0.25))\n\n\n\nclassifier.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nclassifier.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nclassifier.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nclassifier.add(Dropout(0.25))\n\n\n\nclassifier.add(Flatten())\nclassifier.add(Dense(256, activation = \"relu\"))\nclassifier.add(Dropout(0.5))\nclassifier.add(Dense(10, activation = \"softmax\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"classifier.compile(optimizer = 'adam' , loss = \"categorical_crossentropy\", metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = 30 \nbatch_size = 126","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\n\ndatagen = ImageDataGenerator(\n        featurewise_center=False,  # set input mean to 0 over the dataset\n        samplewise_center=False,  # set each sample mean to 0\n        featurewise_std_normalization=False,  # divide inputs by std of the dataset\n        samplewise_std_normalization=False,  # divide each input by its std\n        zca_whitening=False,  # apply ZCA whitening\n        rotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)\n        zoom_range = 0.1, # Randomly zoom image \n        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)\n        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)\n        horizontal_flip=False,  # randomly flip images\n        vertical_flip=False)  # randomly flip images\n\n\ndatagen.fit(x_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = classifier.fit_generator(datagen.flow(x_train,y_train, batch_size=batch_size),\n                              epochs = epochs, validation_data = (x_val,y_val),\n                              verbose = 2, steps_per_epoch=x_train.shape[0] // batch_size\n                              )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = classifier.predict(df_test)\n\n\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"cnn_mnist_datagen.csv\",index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}