{"cells":[{"metadata":{},"cell_type":"markdown","source":"**This notebook is created thanks to DATAI Team Deep Learning Course. The purpose of this notebook is just learning Convolutional Neural Networks' basics with Keras Library.**"},{"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)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\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\nimport warnings\nwarnings.filterwarnings('ignore')\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":{},"cell_type":"markdown","source":"# Loading Dataset"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"#Train Dataset\n\ntrain = pd.read_csv('../input/digit-recognizer/train.csv')\nprint(train.shape)\ntrain.head(15)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Test Dataset\n\ntest = pd.read_csv('../input/digit-recognizer/test.csv')\nprint(test.shape)\ntest.head(15)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Seperating labels\ny_train_first = train[\"label\"]\n\n#Dropping label to the main dataset\nx_train_first = train.drop(labels = [\"label\"], axis = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(x_train_first.shape)\nx_train_first","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Visualizing numbers\nplt.figure(figsize = (15,7))\ng = sns.countplot(y_train_first, palette = \"icefire\")\nplt.title(\"Number of digits\")\ny_train_first.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img = x_train_first.iloc[0].to_numpy() #as_matrix() method is deprecated !!\nimg = img.reshape((28,28))\nplt.imshow(img, cmap = 'gray')\nplt.title(train.iloc[0,0])\nplt.axis('off')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img = x_train_first.iloc[70].to_numpy() #as_matrix() method is deprecated !!\nimg = img.reshape((28,28))\nplt.imshow(img, cmap = 'gray')\nplt.title(train.iloc[70,0])\nplt.axis('off')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Normalization\n\n* Normalization provides to work CNN faster\n* Normalization is converting colorful images to grayscale "},{"metadata":{"trusted":true},"cell_type":"code","source":"#Normalize the data\nx_train_first = x_train_first / 255.0 #colors can take 255 numbers (max: 255)\ntest = test / 255.0\nprint(\"x_train shape: \",x_train_first.shape)\nprint(\"test shape: \",test.shape)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Reshape\n\n* Our dataset's shape is (28 x 28)\n* We have to reshape our data as (28 x 28 x 1) 3D matrices. ('1' means that this data is grayscaled)\n* Keras wants to know extra dimension in the end which correspond to channels.\n* Grayscale => 1 Channel"},{"metadata":{"trusted":true},"cell_type":"code","source":"#Reshaping\nx_train_first = x_train_first.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)\nprint(\"x_train shape: \",x_train_first.shape)\nprint(\"test shape: \",test.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Label Encoding\n\n* We have to encode the labels as binary like:\n    * 3 => [0,0,0,1,0,0,0,0,0,0]\n    * 9 => [0,0,0,0,0,0,0,0,0,1]"},{"metadata":{"trusted":true},"cell_type":"code","source":"#Encoding labels\nfrom keras.utils.np_utils import to_categorical #Converts to one-hot-encoding\ny_train_first = to_categorical(y_train_first, num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train_first","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Train Test Split\n\n* We seperate the data for training and testing (validation)."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_val, Y_train, Y_val = train_test_split(x_train_first, y_train_first, test_size = 0.1, random_state = 42)\nprint(\"x_train shape: \",X_train.shape)\nprint(\"x_test shape: \",X_val.shape)\nprint(\"y_train shape: \",Y_train.shape)\nprint(\"y_test shape: \",Y_val.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Convolutional Neural Networks (CNN)"},{"metadata":{},"cell_type":"markdown","source":"## Create Model\n\n* conv => max pool => dropout => conv => max pool => dropout => fully connected (2 layer)\n* Dropout: Dropout is a technique where randomly selected neurons are ignored during training."},{"metadata":{"trusted":true},"cell_type":"code","source":"from 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\nfrom keras.optimizers import RMSprop,Adam\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau\n\nmodel = Sequential() #Add Layers to the model\n#***************\n\nmodel.add(Conv2D(filters = 8, kernel_size= (5,5), padding = 'Same',\n                activation = 'relu', input_shape=(28,28,1)))\nmodel.add(MaxPool2D(pool_size = (2,2)))\nmodel.add(Dropout(0.25)) #Yüzde 25 node u active et ya da etme\n#***************\n\nmodel.add(Conv2D(filters = 16, kernel_size = (3,3), padding = 'Same',\n                activation = 'relu'))\nmodel.add(MaxPool2D(pool_size = (2,2), strides = (2,2))) #Strides, 2 adım atlayarak gez pixellerde\nmodel.add(Dropout(0.25))\n#Fully Connected\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = \"relu\")) #Hidden Layere\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation = \"softmax\")) #Hidden Layer\n\n#Softmax function is generilazed version of sigmoid function.\n#Softmax is generally used for multiple classifications instead of binary classification\n\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Define Optimizer\n\n* Adaptive Momentum will be used (ADAM), this updates the learning rate instead of constant learning rate which is seen in Gradient Descent."},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = Adam(lr= 0.001, beta_1 = 0.9, beta_2 = 0.999) #Beta parameters are determines the learning rate's variability'","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Compile Model\n\n* Categorical cross-entropy\n* Binary Cross entropy is for describing 2 features (1 or 0)\n* Categorical cross-entropy is for multiple features.\n* If prediction is true CCE is 0, if not, CCE is infinite."},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer = optimizer, loss = \"categorical_crossentropy\", metrics = [\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Epochs and Batch Size"},{"metadata":{},"cell_type":"markdown","source":"* Say you have a dataset of 10 examples (or samples). You have a **batch size** of 2, and you've specified you want the algorithm to run for 3 **epochs**. Therefore, in each epoch, you have 5 **batches** (10/2 = 5). Each batch gets passed through the algorithm, therefore you have 5 iterations **per epoch**."},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = 10 # for better result increase the epochs\nbatch_size = 250","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data Augmentation"},{"metadata":{},"cell_type":"markdown","source":"* To avoid overfitting problem, we need to expand artificially our handwritten digit dataset\n\n* Alter the training data with small transformations to reproduce the variations of digit.\n* For example, the number is not centered The scale is not the same (some who write with big/small numbers) The image is rotated."},{"metadata":{"trusted":true},"cell_type":"code","source":"# Data augmentation\ndatagen = ImageDataGenerator(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,  # dimesion reduction\n        rotation_range=0.5,  # randomly rotate images in the range 5 degrees\n        zoom_range = 0.5, # Randomly zoom image 5%\n        width_shift_range=0.5,  # randomly shift images horizontally 5%\n        height_shift_range=0.5,  # randomly shift images vertically 5%\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":"history = model.fit_generator(datagen.flow(X_train,Y_train, batch_size = batch_size),\n                             epochs = epochs, validation_data = (X_val, Y_val), steps_per_epoch=X_train.shape[0] // batch_size)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Evaluating the Model\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['val_loss'], color = 'b', label = \"validation loss\")\nplt.title(\"Test Loss\")\nplt.xlabel(\"Number of Epochs\")\nplt.ylabel(\"Loss\")\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# confusion matrix\nimport seaborn as sns\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\nf,ax = plt.subplots(figsize=(8, 8))\nsns.heatmap(confusion_mtx, annot=True, linewidths=0.01,cmap=\"Greens\",linecolor=\"gray\", fmt= '.1f',ax=ax)\nplt.xlabel(\"Predicted Label\")\nplt.ylabel(\"True Label\")\nplt.title(\"Confusion Matrix\")\nplt.show()","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}