{"cells":[{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":false},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport seaborn as sns\nfrom matplotlib import pyplot as plt\nimport matplotlib.image as mpimg\n\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras.layers import Dense,Conv2D,Flatten,MaxPool2D,Dropout,BatchNormalization\nfrom keras.optimizers import Adam\nfrom keras.callbacks import ReduceLROnPlateau\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Define required constants\nImage size is `28*28` as per the MNIST standards and images are grayscale, so number of channels is `1`."},{"metadata":{"trusted":false},"cell_type":"code","source":"# constants\nIMG_SIZE = 28\nN_CHANNELS = 1 # because gray scale images","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"train_df = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')\ntest_df = pd.read_csv('/kaggle/input/Kannada-MNIST/Dig-MNIST.csv')\npred_df = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"train_df = train_df.append(test_df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"train_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"print (f'Training set: {train_df.shape}')\nprint (f'To be Predicted: {pred_df.shape}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"X_train = train_df.drop(['label'], axis = 1)\nY_train = train_df['label']\nX_pred = pred_df.drop(['id'], axis = 1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Split the given dataset into training and testing dataset"},{"metadata":{"trusted":false},"cell_type":"code","source":"X_train, X_test, Y_train, Y_test = train_test_split(X_train, Y_train, test_size=0.05)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Normalize the images "},{"metadata":{"trusted":false},"cell_type":"code","source":"X_train, X_test, X_pred = X_train.apply(lambda x: x/255), X_test.apply(lambda x: x/255), X_pred.apply(lambda x: x/255)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Convert training and testing labels (Ys) to one hot encoding"},{"metadata":{"trusted":false},"cell_type":"code","source":"Y_train, Y_test = pd.get_dummies(Y_train), pd.get_dummies(Y_test)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### CNN takes images in shape `(batch_size, h, w, channels)`, so reshape the images"},{"metadata":{"trusted":false},"cell_type":"code","source":"X_train = X_train.values.reshape(-1, IMG_SIZE, IMG_SIZE, N_CHANNELS)\nX_test = X_test.values.reshape(-1, IMG_SIZE, IMG_SIZE, N_CHANNELS)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"print (f'Training images: {X_train.shape}')\nprint (f'Testing images: {X_test.shape}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"Y_train = Y_train.to_numpy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"fig, ax = plt.subplots(nrows=3, ncols=4)\ncount=0\nfor row in ax:\n    for col in row:\n        col.set_title(np.argmax(Y_train[count, :]))\n        col.imshow(X_train[count, :, :, 0])\n        count += 1\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Apply data augmentation:\nTo get more training data, to avoid overfitting, data augmentation is used. Data augmentation is the creation of altered copies of each training instance (image) within a training dataset. \nI've used following data augmentation for this problem:\n* Ramdomly rotate the images by 8 degrees\n* Randomly zoom the images by 15%\n* Randomly shift its height and width by 15%"},{"metadata":{"trusted":false},"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=8,  # randomly rotate images in the range (degrees, 0 to 180)\n        zoom_range = 0.15, # Randomly zoom image \n        width_shift_range=0.15,  # randomly shift images horizontally (fraction of total width)\n        height_shift_range=0.15,  # randomly shift images vertically (fraction of total height)\n        horizontal_flip=False,  # randomly flip images\n        vertical_flip=False)  # randomly flip images\n\n\n# This will just calculate parameters required to augment the given data. This won't perform any augmentations\ndatagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Create CNN model using Keras"},{"metadata":{"trusted":false},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters=32, kernel_size=(3, 3), padding='SAME', activation='relu', input_shape=(28, 28, 1)))\nmodel.add(Conv2D(filters=32, kernel_size=(3, 3), padding='SAME', activation='relu'))\nmodel.add(BatchNormalization(momentum=0.15))\nmodel.add(MaxPool2D(pool_size=(2, 2)))\nmodel.add(Conv2D(filters=32, kernel_size=(5, 5), padding='SAME', activation='relu'))\nmodel.add(Dropout(rate=0.3))\n\nmodel.add(Conv2D(filters=64, kernel_size=(3, 3), padding='SAME', activation='relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3, 3), padding='SAME', activation='relu'))\nmodel.add(BatchNormalization(momentum=0.15))\nmodel.add(MaxPool2D(pool_size=(2, 2)))\nmodel.add(Conv2D(filters=64, kernel_size=(5, 5), padding='SAME', activation='relu'))\nmodel.add(Dropout(rate=0.3))\n\nmodel.add(Flatten())\nmodel.add(Dense(128, activation = \"relu\"))\nmodel.add(Dropout(0.40))\nmodel.add(Dense(64, activation = \"relu\"))\nmodel.add(Dropout(0.40))\nmodel.add(Dense(10, activation = \"softmax\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"model.compile(optimizer=\"adam\", loss=['categorical_crossentropy'], metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"# Set a learning rate annealer. Learning rate will be half after 3 epochs if accuracy is not increased\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":{"trusted":false},"cell_type":"code","source":"batch_size=32\nepochs = 25","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"# Fit the model\nhistory = model.fit_generator(datagen.flow(X_train, Y_train, batch_size=batch_size),\n                              epochs = epochs, validation_data = (X_test,Y_test),\n                              steps_per_epoch=X_train.shape[0] // batch_size, \n                              callbacks=[learning_rate_reduction])\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Ploting loss and accuracy"},{"metadata":{"trusted":false},"cell_type":"code","source":"%matplotlib inline\ndef PlotLoss(his, epoch):\n    plt.style.use(\"ggplot\")\n    plt.figure()\n    plt.plot(np.arange(0, epoch), his.history[\"loss\"], label=\"train_loss\")\n    plt.plot(np.arange(0, epoch), his.history[\"val_loss\"], label=\"val_loss\")\n    plt.title(\"Training Loss\")\n    plt.xlabel(\"Epoch #\")\n    plt.ylabel(\"Loss\")\n    plt.legend(loc=\"upper right\")\n    plt.show()\n\ndef PlotAcc(his, epoch):\n    plt.style.use(\"ggplot\")\n    plt.figure()\n    plt.plot(np.arange(0, epoch), his.history[\"accuracy\"], label=\"train_acc\")\n    plt.plot(np.arange(0, epoch), his.history[\"val_accuracy\"], label=\"val_accuracy\")\n    plt.title(\"Training Accuracy\")\n    plt.xlabel(\"Epoch #\")\n    plt.ylabel(\"Accuracy\")\n    plt.legend(loc=\"upper right\")\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"PlotLoss(history, epochs)\nPlotAcc(history, epochs)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Confusion matrix "},{"metadata":{"trusted":false},"cell_type":"code","source":"cfm = confusion_matrix(np.argmax(Y_test.to_numpy(), axis=1), np.argmax(model.predict(X_test), axis=1))\ncfm = pd.DataFrame(cfm,index=range(0,10),columns=range(0,10))\ncfm","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Make predictions using trained model"},{"metadata":{"trusted":false},"cell_type":"code","source":"preds = model.predict(X_pred.values.reshape(-1, IMG_SIZE, IMG_SIZE, N_CHANNELS))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Predictions will be in one hot encoding, take `argmax` to make the predictions submission ready"},{"metadata":{"trusted":false},"cell_type":"code","source":"pred_df['label'] = np.argmax(preds, axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"preds = pred_df[['id', 'label']]","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Finally create submission file"},{"metadata":{"trusted":true},"cell_type":"code","source":"preds.to_csv('sub.csv', index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.6"}},"nbformat":4,"nbformat_minor":1}