{"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 20GB 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras\nfrom keras.datasets import mnist\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D , MaxPooling2D\nfrom keras.layers import Dense, Dropout , Flatten\nfrom keras import backend as K","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# Load the data\ntrain = pd.read_csv(\"../input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"../input/digit-recognizer/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = train[\"label\"]\n\n# Drop 'label' column\nX_train = train.drop(labels = [\"label\"],axis = 1) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(X_train.shape)\nprint(Y_train.shape)\nprint(test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Normalize the data\nX_train = X_train / 255.0\ntest = test / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.values.reshape(42000,28,28,1)\ntest = test.values.reshape(28000,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(X_train.shape)\nprint(test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(Y_train.shape)\nprint(Y_train[1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = keras.utils.to_categorical(Y_train, num_classes = 10)\nprint(Y_train[1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nx = X_train[5]\nx = x.reshape(28,28)\nplt.imshow(x , cmap='gray')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\n#First Conv2D layer\nmodel.add(Conv2D(filters=32 , kernel_size=(3,3) , activation = 'relu' , input_shape = (28,28,1) ))\nmodel.add(MaxPooling2D(pool_size= (2,2) ))\n\nmodel.add(Conv2D(64, kernel_size = (3,3) , activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size= (2,2)))\n\nmodel.add(Conv2D(64 , kernel_size = (3,3) , activation = 'relu'))\n\nmodel.add(Flatten())\nmodel.add(Dense(64 , activation = 'relu'))\n\nmodel.add(Dense(10 , activation = 'softmax'))\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer='rmsprop',\n             loss='categorical_crossentropy',\n             metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X_train,Y_train, epochs=10 , batch_size=64)","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\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(results[1])","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":{"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}