{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"from __future__ import print_function,division\nfrom builtins import range\n\n# 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)\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D, Dense, Activation, BatchNormalization, MaxPool2D, Flatten, Dropout\nfrom keras.utils import to_categorical\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.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"data = pd.read_csv('../input/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = data.as_matrix()\nnp.random.shuffle(data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x = data[:, 1:].reshape(-1,28,28,1)/255.0\ny = data[:, 0].astype(np.int32)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#get shape\nN  = len(y)\nk = len(set(y))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = to_categorical(y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.add(Conv2D(input_shape=(28,28,1), filters = 32, kernel_size=(3,3)))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\nmodel.add(MaxPool2D())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.add(Conv2D(filters = 64, kernel_size=(3,3)))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\nmodel.add(MaxPool2D())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.add(Flatten())\nmodel.add(Dense(units=300))\nmodel.add(Activation('relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(units=k))\nmodel.add(Activation('softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss= 'categorical_crossentropy', optimizer='adam', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"r = model.fit(x,y, validation_split=0.33, epochs=8, batch_size=32)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_test = pd.read_csv('../input/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_test = x_test.as_matrix()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_test = x_test[:,:].reshape(-1,28,28,1)/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"result = model.predict(x_test)\n\nresult = np.argmax(result, axis = 1)\n\nresult = pd.Series(result, name = 'Label')\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(r.history['loss'], label = 'loss')\nplt.plot(r.history['val_loss'], label = 'val_loss')\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(r.history['acc'], label = 'accuracy')\nplt.plot(r.history['val_acc'], label = 'Validation_accuracy')\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),result],axis = 1)\n\nexport_csv = submission.to_csv(\"cnn_keras_mnist.csv\",index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}