{"cells":[{"metadata":{"_uuid":"baa906a034ce54c720c1eef76d1219f4fd274607"},"cell_type":"markdown","source":"# Digit Recognizer - Keras - CNN (Convolutional Neural Network)","execution_count":null},{"metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nimport seaborn as sns\n%matplotlib inline\n\nnp.random.seed(2)\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\nimport itertools\n\nfrom keras.utils.np_utils import to_categorical # convert to one-hot-encoding\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D, BatchNormalization\nfrom keras.optimizers import RMSprop\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau\nfrom keras.datasets import mnist\n\nsns.set(style='white', context='notebook', palette='deep')","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"# Load Data\ntrain=pd.read_csv(\"../input/digit-recognizer/train.csv\")\ntest=pd.read_csv(\"../input/digit-recognizer/test.csv\")\n\nY_train = train[\"label\"]\nX_train = train.drop(labels = [\"label\"], axis = 1) ","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"22c0b3a1fbc8246a25fc82698fee940f750286ca","trusted":true},"cell_type":"code","source":"# Histogram of data\ng = sns.countplot(Y_train)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"15ba2b09f4e13d802d0251e22a2f2926f91c051f","trusted":true},"cell_type":"code","source":"# Normalize data to make CNN faster\nX_train = X_train / 255.0\ntest = test / 255.0","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"1fbda439ba2cda5750a39d8a0052d7fa36f75712","trusted":true},"cell_type":"code","source":"# Reshape 3D array (height = 28px, width = 28px , canal = 1)\nX_train = X_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"bcfa0e540a8168ed6aa45102eb165a2c1c1b1414","trusted":true},"cell_type":"code","source":"# Convert label to one hot vectors (ex : 2 -> [0,0,1,0,0,0,0,0,0,0])\nY_train = to_categorical(Y_train, num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"6dd248708c7f4f8954b7224b48e3223938c43495","trusted":true},"cell_type":"code","source":"# Split datasets into training and validation sets\nX_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1, random_state=2)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"c7866d3f98ebe3a24e98fe5616aaa63261745500","trusted":true},"cell_type":"code","source":"# Draw an example of a data set\ng = plt.imshow(X_train[0][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"6e2e5990ea804642d89167c422ba4c0c6de12391","trusted":true},"cell_type":"code","source":"# Create a CNN model\n# model：\n\"\"\"\n  [[Conv2D->relu]*2 -> BatchNormalization -> MaxPool2D -> Dropout]*2 -> \n  [Conv2D->relu]*2 -> BatchNormalization -> Dropout -> \n  Flatten -> Dense -> BatchNormalization -> Dropout -> Out\n\"\"\"\nmodel = Sequential()\n\nmodel.add(Conv2D(filters = 64, kernel_size = (5,5),padding = 'Same', activation ='relu', input_shape = (28,28,1)))\nmodel.add(BatchNormalization())\n\nmodel.add(Conv2D(filters = 64, kernel_size = (5,5),padding = 'Same', activation ='relu'))\nmodel.add(BatchNormalization())\n\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', activation ='relu'))\nmodel.add(BatchNormalization())\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3), padding = 'Same',  activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.25))\n\nmodel.add(Dense(10, activation = \"softmax\"))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"cedc2d384512ea3b12c0d46f652198f03bf5bd55","trusted":true},"cell_type":"code","source":"# Print out the model\nfrom keras.utils import plot_model\nplot_model(model, to_file='model.png', show_shapes=True, show_layer_names=True)\nfrom IPython.display import Image\nImage(\"model.png\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"037ca9731e61537769531376e3c02ab5ce6a8c18","trusted":true},"cell_type":"code","source":"# Define Optimizer\noptimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"807ec021c1ab973a0506d14caf66b5d8777490a7","trusted":true},"cell_type":"code","source":"# Compile model\nmodel.compile(optimizer = optimizer , loss = \"categorical_crossentropy\", metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"7bab2f865ea70bcccb6ec181369db75ddcf13110","trusted":true},"cell_type":"code","source":"# Set dynamic adjustment of learning rate\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_accuracy', \n                                            patience=3, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"cc78b198d12ff5cd785f200fbb11f154dc7dfafe","trusted":true},"cell_type":"code","source":"epochs = 10\nbatch_size = 64","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"931940a6c0eb999aa2eef607ec5688989891c514","trusted":true},"cell_type":"code","source":"# Prevent overfitting by data enhancement\ndatagen = ImageDataGenerator(\n        featurewise_center=False, # set input mean to 0 over the dataset\n        samplewise_center=False,  # set each sample mean to 0\n        featurewise_std_normalization=False,  # divide inputs by std of the dataset\n        samplewise_std_normalization=False,  # divide each input by its std\n        zca_whitening=False,  # apply ZCA whitening\n        rotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)\n        zoom_range = 0.1, # Randomly zoom image \n        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)\n        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)\n        horizontal_flip=False,  # randomly flip images\n        vertical_flip=False)  # randomly flip images\ndatagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8d4946afedc9e577f07ea023624a336e336470c5","trusted":true},"cell_type":"code","source":"# Training model\nhistory = model.fit_generator(datagen.flow(X_train,Y_train, batch_size=batch_size),\n                              epochs = epochs, validation_data = (X_val,Y_val),\n                              verbose = 1, steps_per_epoch=X_train.shape[0] // batch_size\n                              , callbacks=[learning_rate_reduction])","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3e03c94fda973c4b8c91b96b019356a4d62ee999","trusted":true},"cell_type":"code","source":"# Draw the loss and accuracy curves of the training set and the validation set. \n# Can judge whether it is under-fitting or over-fitting\nfig, ax = plt.subplots(2,1)\nax[0].plot(history.history['loss'], color='b', label=\"Training loss\")\nax[0].plot(history.history['val_loss'], color='r', label=\"validation loss\",axes =ax[0])\nlegend = ax[0].legend(loc='best', shadow=True)\n\nax[1].plot(history.history['accuracy'], color='b', label=\"Training accuracy\")\nax[1].plot(history.history['val_accuracy'], color='r',label=\"Validation accuracy\")\nlegend = ax[1].legend(loc='best', shadow=True)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"c690e863d42af0c72a31dab0aa008c5e85973643","trusted":true},"cell_type":"code","source":"# Draw a confusion matrix that can be used to observe high false positives\n\ndef plot_confusion_matrix(cm, classes,\n                          normalize=False,\n                          title='Confusion matrix',\n                          cmap=plt.cm.Blues):\n    \"\"\"\n    This function prints and plots the confusion matrix.\n    Normalization can be applied by setting `normalize=True`.\n    \"\"\"\n    plt.imshow(cm, interpolation='nearest', cmap=cmap)\n    plt.title(title)\n    plt.colorbar()\n    tick_marks = np.arange(len(classes))\n    plt.xticks(tick_marks, classes, rotation=45)\n    plt.yticks(tick_marks, classes)\n\n    if normalize:\n        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n\n    thresh = cm.max() / 2.\n    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n        plt.text(j, i, cm[i, j],\n                 horizontalalignment=\"center\",\n                 color=\"white\" if cm[i, j] > thresh else \"black\")\n\n    plt.tight_layout()\n    plt.ylabel('True label')\n    plt.xlabel('Predicted label')\n\n# Predict the values from the validation dataset\nY_pred = model.predict(X_val)\n# Convert predictions classes to one hot vectors \nY_pred_classes = np.argmax(Y_pred,axis = 1) \n# Convert validation observations to one hot vectors\nY_true = np.argmax(Y_val,axis = 1) \n# compute the confusion matrix\nconfusion_mtx = confusion_matrix(Y_true, Y_pred_classes) \n# plot the confusion matrix\nplot_confusion_matrix(confusion_mtx, classes = range(10)) ","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"86708a448631dade2fdf0a7584a38c4c22260e6f","trusted":true},"cell_type":"code","source":"# Make predictions about test sets\nresults = model.predict(test)\n\n# Convert one-hot vector to number\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b5ed81e948596d3135ffef4a4210c20421cbf4cc","trusted":true},"cell_type":"code","source":"# Save the final result\nfinal_result = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nfinal_result.to_csv(\"cnn_mnist_submission.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}