from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

batch_size = 64
num_classes = 10
epochs = 10
img_rows, img_cols = 28, 28

(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

model = Sequential([
  Flatten(),
  Dense(512, activation='relu'),
  Dense(512, activation='relu'),
  Dropout(0.2),
  Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
model.fit(x_train, y_train, epochs=epochs, batch_size=batch_size)
model.evaluate(x_test, y_test)

model1 = Sequential()
model1.add(Conv2D(6, (3, 3), padding='same', activation='relu',input_shape=input_shape))
model1.add(MaxPooling2D(pool_size=(2, 2)))
model1.add(Dropout(0.2))
model1.add(Conv2D(8, (3, 3), padding='same', activation='relu'))
model1.add(MaxPooling2D(pool_size=(2, 2)))
model1.add(Dropout(0.2))
model1.add(Flatten())
model1.add(Dense(30, activation='relu'))
model1.add(Dropout(0.2))
model1.add(Dense(10, activation='softmax'))

model1.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
model1.fit(x_train, y_train, epochs=10)
model1.evaluate(x_test, y_test)


from sklearn.ensemble import RandomForestClassifier

x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)

model.rf =  RandomForestClassifier(n_estimators=1000,n_jobs=-1,
                                   oob_score=True,max_features="sqrt")
model.rf.fit(x_train, y_train)
print(model.rf.score(x_test,y_test))