{"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":{},"cell_type":"markdown","source":"# Importing Library","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nimport keras\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D, BatchNormalization\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom keras.optimizers import RMSprop","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Load Data","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"../input/digit-recognizer/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train.shape)\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(test.shape)\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Keeping dependent variable in y_train and independent variable in x_train","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = train[\"label\"].astype('float32')\nx_train = train.drop(labels = [\"label\"],axis = 1).astype('float32')\n\ny_train.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.shape, y_train.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Missing Value","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.isnull().any().describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.isnull().any().describe()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"\nThere is no missing values in the train and test dataset. So we can safely go ahead.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"# Normalization","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"We can divide each pixel with 255.0 to get NORMALIZATION","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train / 255.0\ntest = test / 255.0","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Reshaping","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"Input data are in 1-D, we re- shape into 3-D matrix. \nFor RGB images, there is 3 channels, we would have reshaped 784px vectors to 28x28x3 3D matrices.\nFor Black and White image we re-shape into 28x28x1","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"#Reshaping the data for 2D CNN input into (-1,28,28,1) size\nx_train = np.array(x_train).reshape(-1,28,28,1)\ntest = np.array(test).reshape(-1,28,28,1)\nprint(x_train.shape)\nprint(test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Some examples\ng = plt.imshow(x_train[8][:,:,0])\nprint(y_train[8])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Label Encoding","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# Encode labels to one hot vectors (ex : 2 -> [0,0,1,0,0,0,0,0,0,0])\ny_train = keras.utils.to_categorical(y_train, 10)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# CNN Model","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"Forming Model","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Flatten())\nmodel.add(Dense(512, activation = \"relu\"))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation = \"softmax\"))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Compile Model","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)","execution_count":null,"outputs":[]},{"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":"Getting the summary of Model","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Data Augmentation","execution_count":null},{"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\n\ndatagen.fit(x_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Fit the Model","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit_generator(datagen.flow(x_train,y_train, batch_size = 86),epochs = 30, steps_per_epoch = x_train.shape[0]//64)\n                            ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Prediction based on test data.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = model.predict(test)\n\n# Convert predictions classes to one hot vectors \nfinal_pred = np.argmax(pred,axis = 1) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"final_pred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub = pd.read_csv('../input/digit-recognizer/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub = pd.DataFrame({\"ImageId\": list(range(1,len(final_pred)+1)),\n                         \"Label\": final_pred})\nsample_sub.to_csv('CNN_submission1.csv', index=False)\nsample_sub.head()","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}