{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Import Libraries"},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np \nimport pandas as pd \nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Lambda, Flatten\nfrom keras.optimizers import Adam ,RMSprop\nfrom sklearn.model_selection import train_test_split\nfrom keras import  backend as K\nfrom keras.preprocessing.image import ImageDataGenerator","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Load data"},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(r\"../input/Kannada-MNIST/train.csv\")\nprint(train.shape)\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv(r\"../input/Kannada-MNIST/test.csv\")\nprint(test.shape)\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"X_train = (train.iloc[:,1:].values).astype('float32')\ny_train = train.iloc[:,0].values.astype('int32')\nX_test = (test.iloc[:,1:].values).astype('float32')","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"X_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"y_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"X_test","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data Visulaization"},{"metadata":{"trusted":false},"cell_type":"code","source":"X_train = X_train.reshape(X_train.shape[0],28,28)\n\nfor i in range(1,4):\n    plt.subplot(329+(i+1))\n    plt.imshow(X_train[i],cmap=plt.get_cmap('gray'))\n    plt.title(y_train[i])","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"X_train = X_train.reshape(X_train.shape[0],28,28,1) \nX_test = X_test.reshape(X_test.shape[0],28,28,1) \nprint(X_train.shape) \nprint(X_test.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Preprocessing data images"},{"metadata":{},"cell_type":"markdown","source":"# Feature Standardization"},{"metadata":{"trusted":false},"cell_type":"code","source":"meanpx = X_train.mean().astype(np.float32)\nstdpx = X_train.std().astype(np.float32)\n\ndef standardize(x):\n    return (x-meanpx)/stdpx","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# One-hot encoding of labels"},{"metadata":{"trusted":false},"cell_type":"code","source":"from keras.utils.np_utils import to_categorical\ny_train = to_categorical(y_train)\nnum_classes = y_train.shape[1]\nnum_classes","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"plt.title(y_train[7])\nplt.plot(y_train[7])\nplt.xticks(range(10));","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Designing Neural Net Architecture"},{"metadata":{},"cell_type":"markdown","source":"# Linear Model"},{"metadata":{"trusted":false},"cell_type":"code","source":"from keras.models import Sequential \nfrom keras.layers.core import Lambda, Dense, Flatten, Dropout\nfrom keras.callbacks import EarlyStopping\nfrom keras.layers import BatchNormalization, Convolution2D , MaxPooling2D","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"model = Sequential()\nmodel.add(Lambda(standardize,input_shape=(28,28,1)))\nmodel.add(Flatten())\nmodel.add(Dense(10,activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"from keras.optimizers import RMSprop\nmodel.compile(optimizer=RMSprop(lr=0.001),loss='categorical_crossentropy',metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"from keras.preprocessing import image\ngen = image.ImageDataGenerator()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX = X_train\ny = y_train\nX_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.10, random_state=42)\nbatches = gen.flow(X_train, y_train, batch_size=64)\nval_batches=gen.flow(X_val, y_val, batch_size=64)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"history=model.fit_generator(generator=batches, steps_per_epoch=X_train.shape[0]//64, epochs=30, \n                    validation_data=val_batches, validation_steps=val_batches.n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"model.evaluate(X_train,y_train) #train loss and train accuracy","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Fully Connected Layer"},{"metadata":{"trusted":false},"cell_type":"code","source":"def fully_connected_layer():\n    model=Sequential([\n        Lambda(standardize,input_shape=(28,28,1)),\n        Flatten(),\n        Dense(512,activation='relu'),\n        Dense(10,activation='softmax')\n    ])\n    model.compile(optimizer='Adam', loss='categorical_crossentropy', metrics=['accuracy'])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"fc = fully_connected_layer()\nfc.optimizer.lr=0.01","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"history=model.fit_generator(generator=batches, steps_per_epoch=X_train.shape[0]//64, epochs=10, \n                    validation_data=val_batches, validation_steps=val_batches.n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Convolution Neural Network"},{"metadata":{"trusted":false},"cell_type":"code","source":"from keras.layers import Convolution2D, MaxPooling2D\n\ndef get_cnn_model():\n    model = Sequential([\n        Lambda(standardize, input_shape=(28,28,1)),\n        Convolution2D(32,(3,3), activation='relu'),\n        Convolution2D(32,(3,3), activation='relu'),\n        MaxPooling2D(),\n        Convolution2D(64,(3,3), activation='relu'),\n        Convolution2D(64,(3,3), activation='relu'),\n        MaxPooling2D(),\n        Flatten(),\n        Dense(512, activation='relu'),\n        Dense(10, activation='softmax')\n        ])\n    model.compile(Adam(), loss='categorical_crossentropy',\n                  metrics=['accuracy'])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"model= get_cnn_model()\nmodel.optimizer.lr=0.01","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"history=model.fit_generator(generator=batches, steps_per_epoch=X_train.shape[0]//64, epochs=10, \n                    validation_data=val_batches, validation_steps=val_batches.n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data Augmentation"},{"metadata":{"trusted":false},"cell_type":"code","source":"gen =ImageDataGenerator(rotation_range=8, width_shift_range=0.08, shear_range=0.3,\n                               height_shift_range=0.08, zoom_range=0.08)\nbatches = gen.flow(X_train, y_train, batch_size=64)\nval_batches = gen.flow(X_val, y_val, batch_size=64)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"model.optimizer.lr=0.001\nhistory=model.fit_generator(generator=batches, steps_per_epoch=X_train.shape[0]//64, epochs=3, \n                    validation_data=val_batches, validation_steps=val_batches.n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Adding Batch Normalization"},{"metadata":{"trusted":false},"cell_type":"code","source":"from keras.layers import BatchNormalization\n\ndef get_bn_model():\n    model = Sequential([\n        Lambda(standardize,input_shape=(28,28,1)),\n        Convolution2D(32,(3,3), activation='relu'),\n        BatchNormalization(axis=1),\n        Convolution2D(32,(3,3), activation='relu'),\n        MaxPooling2D(),\n        BatchNormalization(axis=1),\n        Convolution2D(64,(3,3), activation='relu'),\n        BatchNormalization(axis=1),\n        Convolution2D(64,(3,3), activation='relu'),\n        MaxPooling2D(),\n        Flatten(),\n        BatchNormalization(),\n        Dense(512,activation='relu'),\n        BatchNormalization(),\n        Dense(10,activation='softmax')\n    ])\n    model.compile(Adam(), loss='categorical_crossentropy', metrics=['accuracy'])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"model= get_bn_model()\nmodel.optimizer.lr=0.01\nhistory=model.fit_generator(generator=batches, steps_per_epoch=X_train.shape[0]//64, epochs=5, \n                    validation_data=val_batches, validation_steps=val_batches.n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Submission to Kaggle"},{"metadata":{"trusted":false},"cell_type":"code","source":"predictions = model.predict_classes(X_test, verbose=0)\nsubmissions=pd.DataFrame({\"ImageId\": list(range(1,len(predictions)+1)),\n                         \"Label\": predictions})\nsubmissions.to_csv(\"DR.csv\", index=False, header=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"submissions.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"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}