import pandas as pd
import numpy as np
# The competition datafiles are in the directory ../input
# Read competition data files:
train = pd.read_csv("../input/train.csv")

test_images = (pd.read_csv("../input/test.csv").values).astype('float32')




train_images = (train.ix[:,1:].values).astype('float32')
train_labels = train.ix[:,0].values.astype('int32')

train_images = train_images / 255
test_images = test_images / 255

from keras.utils.np_utils import to_categorical
train_labels = to_categorical(train_labels)

seed = 43
np.random.seed(seed)

from keras.models import Sequential
from keras.layers import Dense , Dropout
from keras.optimizers import RMSprop

            
            
model = Sequential()
model.add(Dense(64, activation='relu',input_dim=(28 * 28)))
model.add(Dense(128, activation='relu'))
#model.add(Dropout(0.15))
model.add(Dense(64, activation='relu'))
#model.add(Dropout(0.15))
model.add(Dense(10, activation='softmax'))


model.compile(optimizer=RMSprop(lr=0.0001), loss='categorical_crossentropy',
 metrics=['accuracy'])

history=model.fit(train_images, train_labels, 
            nb_epoch=15, batch_size=64)
            
predictions = model.predict_classes(test_images, verbose=0)

submissions=pd.DataFrame({"ImageId": list(range(1,len(predictions)+1)),
                         "Label": predictions})
submissions.to_csv("DR.csv", index=False, header=True)