{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport pandas as pd\n\nimport os\nprint(os.listdir('../input'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_folder = \"../input\"\n\ntest = pd.read_csv(data_folder + \"/test.csv\")\ntrain = pd.read_csv(data_folder + \"/train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = (train.iloc[:,1:].values).astype('float32')\nx_test = test.values.astype('float32')\n\nx_train /= 255.0\nx_test /= 255.0\n\ny_train = train.iloc[:,0].values.astype('int32')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('X_TRAIN SHAPE:      ', x_train.shape)\nprint('X_TEST SHAPE:       ', x_test.shape)\nprint('SAMPLES IN X_TRAIN: ', x_train.shape[0])\nprint('SAMPLES IN X_TEST:  ', x_test.shape[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train.reshape(42000, 28, 28,1) # 28 x 28 = 784\nx_test = x_test.reshape(28000, 28, 28,1)\n\nprint(x_train.shape)\nprint(x_test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(12,10))\n\nfor img in range(10):  \n    plt.subplot(5, 5, img+1)\n    plt.imshow(x_train[img].reshape((28, 28)), cmap='binary_r')\n    plt.axis('off')\n    \n    plt.title('Label: ' + y_train[img].astype('str'))\n    \nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras \nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.utils import to_categorical\n\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = to_categorical(y_train, 10)\nx_train, x_test, y_train, y_test = train_test_split(x_train, y_train, test_size = 0.1, random_state=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28,28,1)))\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\n\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(Conv2D(128, (3, 3), activation='relu'))\n\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer='Adadelta', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x_train, y_train, batch_size=128, epochs=10, verbose=1,\n          validation_data=(x_test, y_test))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss, accuracy = model.evaluate(x_test, y_test, verbose=0)\n\nprint('Test Loss:', loss)\nprint('Test Accuracy:', accuracy%100)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.4"}},"nbformat":4,"nbformat_minor":1}