import keras
import numpy as np
from keras.datasets import mnist
import matplotlib.pyplot as plt
from sklearn.metrics import accuracy_score

(X_train, y_train), (X_test, y_test) = mnist.load_data()

print("Datasets size")
print("Train data:", X_train.shape)
print("Test data:", X_test.shape)

print("Samples from training data:")
for i in range(0,10):
    plt.subplot(1,10,i+1)
    plt.imshow(X_train[i], cmap=plt.get_cmap("gray"))
    plt.title(y_train[i]);
    plt.axis('off');
plt.show()

images_train =  []
for image_train in X_train:
    images_train.append(image_train.flatten())

images_test = []

for image_test in X_test:
    images_test.append(image_test.flatten())

images_train = np.array(images_train)
images_test = np.array(images_test)

from sklearn.neural_network import MLPClassifier

neural_network = MLPClassifier(hidden_layer_sizes=(30,20,10),random_state=1)

neural_network.fit(images_train, y_train)



acc = accuracy_score(y_test, neural_network.predict(images_test))
print("Neural network model accuracy is {0:0.2f}".format(acc))
print("Number of connection between input and first hidden layer:")
print(np.size(neural_network.coefs_[0]))

print("Number of connection between first and second hidden layer:")
print(np.size(neural_network.coefs_[1]))