{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Welcome to digital recognizer with using CNN"},{"metadata":{},"cell_type":"markdown","source":"**I would really appreciate your votes if you liked this notebook!**"},{"metadata":{},"cell_type":"markdown","source":"*First we need import all required libraries*"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import math\nimport pandas as pd\nimport numpy as np\nimport tensorflow as tf\nimport h5py\nimport itertools\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.model_selection import train_test_split\n\nfrom keras.datasets import mnist\nfrom tensorflow.keras.models import Sequential, load_model\nfrom tensorflow.keras.optimizers import Adam, RMSprop\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D, BatchNormalization\nfrom keras.callbacks import ReduceLROnPlateau, ModelCheckpoint, EarlyStopping\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.utils.np_utils import to_categorical\nfrom keras.utils.vis_utils import plot_model\n\n%matplotlib inline\nnp.random.seed(2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Load the data"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# train = pd.read_csv('../input/digit-recognizer/train.csv')\ntest = pd.read_csv('../input/digit-recognizer/test.csv')\n\n# train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"*Here we load and split mnist dataset*"},{"metadata":{"trusted":true},"cell_type":"code","source":"(X_train, Y_train), (X_val, Y_val) = mnist.load_data()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"*Here we look at the examples of inputs*"},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(X_train[1])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Processing the data"},{"metadata":{},"cell_type":"markdown","source":"## Data separation"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Y_train = train[\"label\"]\n# X_train = train.drop(labels=[\"label\"], axis=1)\n\nprint(X_train.shape, ', ', Y_train.shape)\n\ng = sns.countplot(Y_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data normalization"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train/255\ntest = test/255\n\nprint(X_train.shape, ', ', test.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data reshaping"},{"metadata":{},"cell_type":"markdown","source":"*To process the data we need to reshape 784 pixels of each entry into (28, 28, 1)*"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.reshape(-1, 28, 28, 1)\nX_val = X_val.reshape(-1, 28, 28, 1)\n\nX_train = X_train.astype('float32')\nX_val = X_val.astype('float32')\ntest = test.values.reshape(-1, 28, 28, 1)\n\nprint(X_train.shape,', ',X_val.shape,', ', test.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data splitting"},{"metadata":{"trusted":true},"cell_type":"code","source":"#random_seed = 2\nY_train = to_categorical(Y_train, num_classes = 10)\n\n#X_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1, \n#                                                  random_state = random_seed)\nY_val = to_categorical(Y_val, num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Initial model"},{"metadata":{},"cell_type":"markdown","source":"*This is a model with 11 layers such as convolutional layer, pooling layer, flatten layer and fully-connected(dense) layer. Final layer will make a predictions*"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters = 32, kernel_size = (5, 5), padding = \"Same\", activation = \"relu\",\n                 kernel_initializer = 'he_uniform', input_shape = (28, 28, 1)))\nmodel.add(Conv2D(filters = 32, kernel_size = (5, 5), padding = \"Same\", activation = \"relu\",\n                kernel_initializer = 'he_uniform'))\nmodel.add(MaxPooling2D(pool_size = (2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3, 3), padding = \"Same\", activation = \"relu\",\n                kernel_initializer = 'he_uniform'))\nmodel.add(Conv2D(filters = 64, kernel_size = (3, 3), padding = \"Same\", activation = \"relu\",\n                kernel_initializer = 'he_uniform'))\nmodel.add(MaxPooling2D(pool_size = (2, 2), strides = (2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation=\"relu\", kernel_initializer = 'he_uniform'))\nmodel.add(Dropout(0.5))\n\nmodel.add(Dense(units = 10, activation=\"softmax\", kernel_initializer = 'he_uniform'))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Compile the model"},{"metadata":{},"cell_type":"markdown","source":"*We can use different optimizers such as Adam, SGD, RMSprop, Adadelta, Adagrad, Adamax, Nadam, Ftrl. In this model we use RMSprop optimizer*\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = RMSprop(lr = 0.001, rho = 0.9, epsilon = 1e-08, decay = 0.0)\nmodel.compile(optimizer = optimizer , loss = 'categorical_crossentropy', metrics = ['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"*Using the method ```summary()``` we can see layers' types, output shape and amount of parameters*"},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Set callbacks"},{"metadata":{"trusted":true},"cell_type":"code","source":"# ModelCheckpoint\ncheckpoint = ModelCheckpoint('./mod_best.hdf5',monitor = 'val_loss', mode = \"min\", verbose = 1, save_best_model = True)\n\n# EarlyStopping\nearlystop = EarlyStopping(monitor = 'val_loss', patience = 3, min_delta = 0,verbose =1, restore_best_weights = True)\n\n# ReduceLROnPlateau\nreduce_lr = ReduceLROnPlateau(monitor='val_loss', patience=3, verbose=1, factor=0.5, min_lr=0.00001)\n\ncallbacks = [reduce_lr,checkpoint]","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data augmentation"},{"metadata":{},"cell_type":"markdown","source":"*We use data augmentation to prevent overfitting*"},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = 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\n\ndatagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Fit the model"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = load_model(\"./mod_best.hdf5\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 128\nepochs = 30\nhistory = model.fit_generator(datagen.flow(X_train,Y_train, batch_size = batch_size),\n                              epochs = epochs, validation_data = datagen.flow(X_val,Y_val, batch_size = batch_size),\n                              steps_per_epoch = X_train.shape[0] // batch_size,\n                              callbacks = callbacks)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Evaluate the model"},{"metadata":{},"cell_type":"markdown","source":"## Plot the loss and accuracy curves for training and validation"},{"metadata":{"trusted":true},"cell_type":"code","source":"score = model.evaluate(X_val, Y_val, verbose=0)\nprint(\"Val_Loss :\",score[0])\nprint(\"Val_Acc :\",score[1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(2, 1)\nax[0].plot(history.history[\"loss\"], color=\"b\", label=\"Training loss\")\nax[0].plot(history.history[\"val_loss\"], color=\"g\", label=\"validation loss\", axes=ax[0])\nax[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=\"g\", label=\"Validation accuracy\")\nax[1].legend(loc=\"best\", shadow=True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Confusion matrix"},{"metadata":{},"cell_type":"markdown","source":"*The function `plot_confusion_matrix()` prints and plots the confusion matrix.\n    Normalization can be applied by setting `normalize=True`*"},{"metadata":{"trusted":true},"cell_type":"code","source":"def plot_confusion_matrix(cm, classes, normalize = False, title = \"Confusion matrix\", cmap = plt.cm.Blues):\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 = 0)\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() / 2.0\n    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n        plt.text(\n            j,\n            i,\n            cm[i, j],\n            horizontalalignment = \"center\",\n            color=\"white\" if cm[i, j] > thresh else \"black\",\n        )\n\n    plt.tight_layout()\n    plt.ylabel(\"True label\")\n    plt.xlabel(\"Predicted label\")\n    \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\nCM = confusion_matrix(Y_true, Y_pred_classes)\n# plot the confusion matrix\nplt.figure(figsize = (15,10))\nsns.heatmap(CM,annot = True,cmap = \"viridis\")\nplt.tight_layout()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Display some error results"},{"metadata":{"trusted":true},"cell_type":"code","source":"\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\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(\n                \"Predicted label :{}\\nTrue label :{}\".format(\n                    pred_errors[error], obs_errors[error]\n                )\n            )\n            n += 1\n\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)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Model plotting"},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_model(model, to_file = \"../working/plot.png\", show_shapes = True, show_layer_names = True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Predictions and accuracy"},{"metadata":{},"cell_type":"markdown","source":"*Generate predictions on the test data using `predict()`*"},{"metadata":{"trusted":true},"cell_type":"code","source":"probabilities = model.predict(test)\ny_pred = np.argmax(probabilities, axis=1)\nprint(y_pred.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"*We evaluate the model on the train data via evaluate()*"},{"metadata":{},"cell_type":"markdown","source":"# Initial submission"},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame({'ImageId': np.arange(1, 28001), 'Label': y_pred})\nsubmission.to_csv(\"submission.csv\", index = False)\nprint(\"Your submission was successfully saved!\")","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}