{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import tensorflow.keras as keras\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten\nfrom tensorflow.keras.layers import Conv2D, MaxPool2D\n\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Setup dataset","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"training_data = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest_data = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"training_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = training_data.drop('label', axis=1).values\ny_train = training_data[['label']].values\n\nX_test = test_data.values\ntest_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 128\nnum_classes = 10\nepochs = 12\n\nimg_rows, img_cols = 28, 28\ninput_shape = (1, img_rows, img_cols)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Preprocessing","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.reshape(-1,28,28,1)\nX_test = X_test.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.astype('float32')\nX_test = X_test.astype('float32')\n\nX_train /= 255\nX_test /= 255\nprint('x_train shape:', X_train.shape)\nprint(X_train.shape[0], 'train samples')\nprint(X_test.shape[0], 'test samples')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Split into train and validation set","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nX_train, X_val, y_train, y_val = train_test_split(X_train, y_train, stratify=y_train, \n                                                 test_size=0.15, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# One-hot encode targets","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# convert class vectors to binary class matrices\n\ny_train = keras.utils.to_categorical(y_train, num_classes)\ny_val = keras.utils.to_categorical(y_val, num_classes)\ny_train.shape, y_val.shape ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Model ","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation = \"softmax\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = keras.optimizers.RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)\n\nmodel.compile(loss='categorical_crossentropy',\n              optimizer=optimizer,\n              metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X_train, y_train,\n          batch_size=batch_size,\n          epochs=epochs,\n          verbose=1,\n          validation_data=(X_val, y_val))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"score = model.evaluate(X_val, y_val, verbose=0)\nscore","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Prediction","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# predict results\nresults = model.predict(X_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":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"), results],axis = 1)\nsubmission.to_csv(\"cnn_mnist.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":4}