{"cells":[{"metadata":{},"cell_type":"markdown","source":"# MNIST"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom numpy import mean\nfrom numpy import std\nfrom matplotlib import pyplot\nfrom sklearn.model_selection import KFold\nfrom keras.datasets import mnist\nfrom keras.utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv('../input/digit-recognizer/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels = df['label'].values\nfeatures = df[list(df.columns)[1:]].values.astype('float32') / 255.\nfeatures = features.reshape(-1, 28, 28, 1)\nlabels = np.eye(10)[labels]\nprint(labels.shape, features.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=0.33, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def define_model():\n    model = Sequential()\n    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', input_shape=(28, 28, 1)))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Flatten())\n    model.add(Dense(100, activation='relu', kernel_initializer='he_uniform'))\n    model.add(Dense(10, activation='softmax'))\n    opt = SGD(lr=0.01, momentum=0.9)\n    model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def evaluate_model(dataX, dataY, n_folds=5):\n    scores, histories = list(), list()\n    kfold = KFold(n_folds, shuffle=True, random_state=1)\n\n    for train_ix, test_ix in kfold.split(dataX):\n        model = define_model()\n\n        trainX, trainY, testX, testY = dataX[train_ix], dataY[train_ix], dataX[test_ix], dataY[test_ix]\n        history = model.fit(trainX, trainY, epochs=10, batch_size=32, validation_data=(testX, testY), verbose=0)\n        \n        _, acc = model.evaluate(testX, testY, verbose=0)\n        print('> %.3f' % (acc * 100.0))\n\n        scores.append(acc)\n        histories.append(history)\n    return scores, histories","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"scores, histories = evaluate_model(X_train, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def summarize_diagnostics(histories):\n    for i in range(len(histories)):\n        # plot loss\n        pyplot.subplot(2, 1, 1)\n        pyplot.title('Cross Entropy Loss')\n        pyplot.plot(histories[i].history['loss'], color='blue', label='train')\n        pyplot.plot(histories[i].history['val_loss'], color='orange', label='test')\n        # plot accuracy\n        pyplot.subplot(2, 1, 2)\n        pyplot.title('Classification Accuracy')\n        pyplot.plot(histories[i].history['accuracy'], color='blue', label='train')\n        pyplot.plot(histories[i].history['val_accuracy'], color='orange', label='test')\n    pyplot.show()\n\ndef summarize_performance(scores):\n    print('Accuracy: mean=%.3f std=%.3f, n=%d' % (mean(scores)*100, std(scores)*100, len(scores)))\n    pyplot.boxplot(scores)\n    pyplot.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"summarize_diagnostics(histories)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"summarize_performance(scores)","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}