{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\n\nY_train = train[\"label\"]\nX_train = train.drop(labels = [\"label\"], axis = 1) \n\n# Load more data sets, if there is no such data, validation accuracy = 0.9964\n# With this batch of data, the validation accuracy can reach 0.9985\n(x_train1, y_train1), (x_test1, y_test1) = mnist.load_data()\n\ntrain1 = np.concatenate([x_train1, x_test1], axis=0)\ny_train1 = np.concatenate([y_train1, y_test1], axis=0)\n\nY_train1 = y_train1\nX_train1 = train1.reshape(-1, 28*28)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train / 255.0\ntest = test / 255.0\n\nX_train1 = X_train1 / 255.0\n\n# Reshape Picture is 3D array (height = 28px, width = 28px , canal = 1)\nX_train = np.concatenate((X_train.values, X_train1))\nY_train = np.concatenate((Y_train, Y_train1))\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)\n\n# 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)\n\n# Split dataset into training set and validation set\nX_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1, random_state=2)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Creating CNN 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 = 32, kernel_size = (5,5),padding = 'Same', activation ='relu', input_shape = (28,28,1)))\nmodel.add(Conv2D(filters = 32 ,kernel_size=(5,5) , padding='Same' ,activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.2))\n\nmodel.add(Conv2D(filters = 64, kernel_size = (5,5),padding = 'Same', activation ='relu'))\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 = 128, kernel_size = (3,3),padding = 'Same', activation ='relu'))\nmodel.add(Conv2D(filters = 128, kernel_size = (3,3),padding = 'Same', activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\n\nmodel.add(Conv2D(filters = 256, kernel_size = (3,3),padding = 'Same', activation ='relu'))\nmodel.add(Conv2D(filters = 256, kernel_size = (3,3),padding = 'Same', activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.2))\n\nmodel.add(Conv2D(filters = 512, kernel_size = (5,5),padding = 'Same', activation ='relu'))\nmodel.add(Conv2D(filters = 512, kernel_size = (5,5),padding = 'Same', activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.3))\n\n\n#model.add(Conv2D(filters = 64, kernel_size = (3,3), padding = 'Same',  activation ='relu'))\n#model.add(BatchNormalization())\n#model.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(BatchNormalization())\nmodel.add(Dense(128, activation = \"relu\"))\nmodel.add(Dropout(0.25))\nmodel.add(Dense(10, activation = \"softmax\"))\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)\n\n# Compile model\nmodel.compile(optimizer = optimizer , loss = \"categorical_crossentropy\", metrics=[\"accuracy\"])\n\n# Audjusting learning rate\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n                                            patience=3, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)\n\n#Adjusting epochs and batch_size\nepochs = 50\nbatch_size = 128\n\n#Data Augmentation \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)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(datagen.flow(X_train,Y_train, batch_size=batch_size),\n                              epochs = epochs, validation_data = (X_val,Y_val),\n                              verbose = 2, steps_per_epoch=X_train.shape[0] // batch_size\n                              , callbacks=[learning_rate_reduction])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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":"results = model.predict(test)\n\n# Convert one-hot vector to number\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")\n\n# Save the final result in cnn_mnist_submission.csv\nsubmission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"cnn_mnist_submission.csv\",index=False)\n\n","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}