{"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\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport seaborn as sns\nimport tensorflow as tf","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = train['label'].astype('float32')\nX_train = train.drop(['label'], axis=1).astype('int32')\nX_test = test.astype('float32')\n\nX_train = X_train/255\nX_test = X_test/255\n\nX_train = X_train.values.reshape(-1,28,28,1)\nX_test = X_test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# one-hot encoding\nfrom keras.utils.np_utils import to_categorical\ny_train = to_categorical(y_train, num_classes = 10)\ny_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train['label'].head())\ny_train[0:5,:]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_cv, y_train, y_cv = train_test_split(X_train, y_train, test_size = 0.1, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.layers import Input,InputLayer, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D\nfrom keras.layers import AveragePooling2D, MaxPooling2D, Dropout\nfrom keras.models import Sequential,Model\nfrom keras.optimizers import SGD\nfrom keras.callbacks import ModelCheckpoint,LearningRateScheduler\nimport keras\nfrom keras import backend as K","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"input_shape = (28,28,1)\nX_input = Input(input_shape)\n\n# layer 1\nx = Conv2D(64,(3,3),strides=(1,1),name='layer_conv1',padding='same')(X_input)\nx = BatchNormalization()(x)\nx = Activation('relu')(x)\nx = MaxPooling2D((2,2),name='maxPool1')(x)\n# layer 2\nx = Conv2D(32,(3,3),strides=(1,1),name='layer_conv2',padding='same')(x)\nx = BatchNormalization()(x)\nx = Activation('relu')(x)\nx = MaxPooling2D((2,2),name='maxPool2')(x)\n# layer 3\nx = Conv2D(32,(3,3),strides=(1,1),name='conv3',padding='same')(x)\nx = BatchNormalization()(x)\nx = Activation('relu')(x)\nx = MaxPooling2D((2,2), name='maxPool3')(x)\n# fc\nx = Flatten()(x)\nx = Dense(64,activation ='relu',name='fc0')(x)\nx = Dropout(0.25)(x)\nx = Dense(32,activation ='relu',name='fc1')(x)\nx = Dropout(0.25)(x)\nx = Dense(10,activation ='softmax',name='fc2')(x)\n\nconv_model = Model(inputs=X_input, outputs=x, name='Predict')\nconv_model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Adam optimizer\nconv_model.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['accuracy'])\nconv_model.fit(X_train, y_train, epochs=10, batch_size=100, validation_data=(X_cv,y_cv))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ny_pred = conv_model.predict(X_test)\ny_pred = np.argmax(y_pred,axis=1)\nmy_submission = pd.DataFrame({'ImageId': list(range(1, len(y_pred)+1)), 'Label': y_pred})\nmy_submission.to_csv('submission.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}