{"cells":[{"metadata":{},"cell_type":"markdown","source":"## *Author: Akshay Vyas*\n> **Table of Contents**\n1. Introduction\n2. Data Acquisiton and Data Preprocessing\n3. Model Development\n4. Model Evaluation\n5. Prediction and Submission\n"},{"metadata":{},"cell_type":"markdown","source":"# 1. Introduction"},{"metadata":{},"cell_type":"markdown","source":"Using Convolutional Neural Networks (CNN) for solving the multi-class classification problem of Digit Recognition."},{"metadata":{},"cell_type":"markdown","source":"# 2. Data Acquistion and Data Preprocessing"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nimport seaborn as sns\nsns.set(style='white', context='notebook', palette='deep')\n\nnp.random.seed(2)\n\nimport warnings\nwarnings.filterwarnings(\"ignore\")\nimport os\nprint(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Obtaining train data\ntrain = pd.read_csv(\"../input/train.csv\")\ntrain.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Obtaining test data\ntest = pd.read_csv(\"../input/test.csv\")\ntest.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = train[\"label\"]\n\n#Now dropping the label column from the dataset\nX_train = train.drop(labels = [\"label\"], axis = 1)\n\n#Free memory space\ndel train\n\nX_train.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Creating a count plot for all the labels\nsns.countplot(Y_train)\nY_train.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#check missing values in train dataset\nX_train.isnull().any().describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.isnull().any().describe()","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":"#Reshape the image in 3 dimensions (height = 28px, width = 28px, canal = 1))\n# from 784 values in 1 Dimensional vector\nX_train = X_train.values.reshape(-1, 28, 28, 1)\ntest = test.values.reshape(-1, 28, 28, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Encoding labels to one hot vectors\n# Example: 3 = [0, 0, 0, 1, 0, 0, 0, 0, 0, 0]\nfrom keras.utils.np_utils import to_categorical # convert-to-one-hot-encoding\n\nY_train = to_categorical(Y_train, num_classes = 10)\nY_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Spliting data into training and validation set\nfrom sklearn.model_selection import train_test_split\n\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":{"trusted":true},"cell_type":"code","source":"plt.imshow(X_train[0][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 3. Model Development"},{"metadata":{"trusted":true},"cell_type":"code","source":"#Convolutional Neural Network Architecture\n#CNN Model\n#Input -> [[Conv2D->relu]*2 -> MaxPool2D -> Dropout]*2 -> \n#         Flatten -> Dense -> Dropout -> Output\n\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\n\ndef get_cnn_model():\n    model = Sequential([\n        Conv2D(filters = 32, kernel_size = (5,5), padding='Same',\n              activation = 'relu', input_shape = (28, 28, 1)),\n        Conv2D(filters = 32, kernel_size = (5,5), padding='Same',\n              activation = 'relu'),\n        MaxPool2D(pool_size = (2,2)),\n        Dropout(0.25),\n        Conv2D(filters = 32, kernel_size = (5,5), padding='Same',\n              activation = 'relu'),\n        Conv2D(filters = 32, kernel_size = (5,5), padding='Same',\n              activation = 'relu'),\n        MaxPool2D(pool_size = (2,2)),\n        Dropout(0.25),\n        Flatten(),\n        Dense(256, activation = 'relu'),\n        Dropout(0.5),\n        Dense(10, activation = 'softmax')\n    ])\n    return model\n\nmodel = get_cnn_model()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Defining the Optimizer\nfrom keras.optimizers import RMSprop\n\noptimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Compiling the model\nmodel.compile(optimizer = optimizer, loss = \"categorical_crossentropy\", \n             metrics = [\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Setting a learning rate annealer\nfrom keras.callbacks import ReduceLROnPlateau\n\nlearning_rate_reduction = ReduceLROnPlateau(monitor = 'val_acc',\n                                           patience = 3, \n                                           verbose = 1,\n                                           factor = 0.5, \n                                           min_lr = 0.00001)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = 3\nbatch_size = 86","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Calculation Validation accuracy\nhistory = model.fit(X_train, Y_train, batch_size = batch_size,\n                   epochs = epochs,\n                   validation_data = (X_val, Y_val), \n                   verbose = 2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Now performing Data Augmentation to improve Accuracy\nfrom keras.preprocessing.image import ImageDataGenerator\n\ndatagen = ImageDataGenerator(\n            featurewise_center = False,\n            samplewise_center= False,\n            featurewise_std_normalization= False,\n            samplewise_std_normalization= False,\n            zca_whitening= False,\n            rotation_range= 10,\n            zoom_range= 0.1,\n            width_shift_range=0.1,\n            height_shift_range=0.1,\n            horizontal_flip=False,\n            vertical_flip=False)\n\ndatagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(datagen.flow(X_train, Y_train, \n                                          batch_size=batch_size),\n                             epochs = epochs,\n                             validation_data = (X_val, Y_val),\n                             verbose =2, \n                             steps_per_epoch=X_train.shape[0] // batch_size,\n                             callbacks = [learning_rate_reduction])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 4. Model Evaluation"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Plot the loss and accuracy curves for training and validation \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['acc'], color='b', label=\"Training accuracy\")\nax[1].plot(history.history['val_acc'], color='r',label=\"Validation accuracy\")\nlegend = ax[1].legend(loc='best', shadow=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Look at confusion matrix \nfrom sklearn.metrics import confusion_matrix\nimport itertools\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":{"trusted":true},"cell_type":"code","source":"# Display some error results \n\n# Errors are difference between predicted labels and true labels\nerrors = (Y_pred_classes - Y_true != 0)\n\nY_pred_classes_errors = Y_pred_classes[errors]\nY_pred_errors = Y_pred[errors]\nY_true_errors = Y_true[errors]\nX_val_errors = X_val[errors]\n\ndef display_errors(errors_index,img_errors,pred_errors, obs_errors):\n    \"\"\" This function shows 6 images with their predicted and real labels\"\"\"\n    n = 0\n    nrows = 2\n    ncols = 3\n    fig, ax = plt.subplots(nrows,ncols,sharex=True,sharey=True)\n    for row in range(nrows):\n        for col in range(ncols):\n            error = errors_index[n]\n            ax[row,col].imshow((img_errors[error]).reshape((28,28)))\n            ax[row,col].set_title(\"Predicted label :{}\\nTrue label :{}\".format(pred_errors[error],obs_errors[error]))\n            n += 1\n\n# Probabilities of the wrong predicted numbers\nY_pred_errors_prob = np.max(Y_pred_errors,axis = 1)\n\n# Predicted probabilities of the true values in the error set\ntrue_prob_errors = np.diagonal(np.take(Y_pred_errors, Y_true_errors, axis=1))\n\n# Difference between the probability of the predicted label and the true label\ndelta_pred_true_errors = Y_pred_errors_prob - true_prob_errors\n\n# Sorted list of the delta prob errors\nsorted_dela_errors = np.argsort(delta_pred_true_errors)\n\n# Top 6 errors \nmost_important_errors = sorted_dela_errors[-6:]\n\n# Show the top 6 errors\ndisplay_errors(most_important_errors, X_val_errors, Y_pred_classes_errors, Y_true_errors)\n","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":"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":{},"cell_type":"markdown","source":"Thank you for reading the kernel. \nHope you it helped you understand the basics of Deep Neural Networks."}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}