{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.python import keras\nfrom tensorflow.python.keras.models import Sequential\nfrom tensorflow.python.keras.layers import Dense, Flatten, Conv2D, Dropout\n\n#define image size and num classes\nimg_rows, img_cols = 28, 28\nnum_classes = 10\n\ndef data_prep(raw):\n    out_y = keras.utils.to_categorical(raw.label, num_classes)\n\n    num_images = raw.shape[0]\n    x_as_array = raw.values[:,1:]\n    x_shaped_array = x_as_array.reshape(num_images, img_rows, img_cols, 1)\n    out_x = x_shaped_array / 255\n    return out_x, out_y\n\ntrain_file = \"../input/digit-recognizer/train.csv\"\nraw_data = pd.read_csv(train_file)\n\nx, y = data_prep(raw_data)\n\nmodel = Sequential()\nmodel.add(Conv2D(20, kernel_size=(3, 3),\n                 activation='relu',\n                 input_shape=(img_rows, img_cols, 1)))\nmodel.add(Conv2D(20, kernel_size=(3, 3), activation='relu'))\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dense(num_classes, activation='softmax'))\n\nmodel.compile(loss=keras.losses.categorical_crossentropy,\n              optimizer='adam',\n              metrics=['accuracy'])\nmodel.fit(x, y,\n          batch_size=128,\n          epochs=2,\n          validation_split = 0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport matplotlib.image as mpimg","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"plt.imshow(x[100][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test=pd.read_csv('../input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = test / 255.0\ntest = test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# predict results\nresults= model.predict(test)\n\n# select the indix with the maximum probability\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")\n","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":{"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":1}