def mnist_digit_recognition():
train_set, test_set = load_mnist_dataset()
n_labels = 10 # 1,2,3,4,5,6,7,9,0
n_features = 28 * 28
draw_ex_images(5, 4, train_set[0].shape[0], train_set[0])
mnist_model = GaussianNaiveBayes(n_labels, n_features)
start = time.time()
mnist_model.train(train_set[0], train_set[1])
end = time.time()
print(end - start)
mnist_model.save_model()
mean, var, pi = mnist_model.get_parameters()
print(f"Model parameters: mean {mean}, var {var}, pi {pi}")
test_data, labels = test_set
limit = 150
test_data, labels = test_data[:limit], labels[:limit]
results = np.arange(limit, dtype=np.int)
for n in range(limit):
results[n] = mnist_model.classify(test_data[n])
print(f"{n} : predicted {results[n]}, correct {labels[n]}")
print("recognition rate: ", (results == labels).mean())
def naive_bayes_test():
n_labels, n_features = 2, 2
nb = GaussianNaiveBayes(n_labels, n_features)
# prepare sample training data
data1 = np.random.multivariate_normal([1,4], [[2,0],[0,2]], size=100)
data2 = np.random.multivariate_normal([5,7], [[3,0],[0,1]], size=100)
data = np.concatenate((data1, data2), axis=0)
# prepare training label data
labels = np.concatenate((np.array([0]*100), np.array([1]*100)), axis=0)
print "correct labels"
print labels
# nb.load()
nb.train(data, labels)
# nb.save()
results = nb.classify(data)
print "predicted labels"
print results
print "recognition rate: ", (results == labels).mean()
def mnist_digit_recognition():
train_set, valid_set, test_set = load_mnist_dataset("mnist.pkl.gz")
n_labels = 10 # 1,2,3,4,5,6,7,9,0
n_features = 28*28
mnist_model = GaussianNaiveBayes(n_labels, n_features)
mnist_model.train(train_set[0], train_set[1])
[mean, var], pi = mnist_model.get_parameters()
# visualization of learned means
create_2D_images_horizontal(mean, w=28, h=28)
show()
test_data, labels = test_set
# slice
#limit = len(test_data)
limit = 50
test_data, labels = test_data[:limit], labels[:limit]
results = np.arange(limit, dtype=np.int)
for n in range(limit):
results[n] = mnist_model.classify(test_data[n])
print "%d : predicted %s, correct %s" % (n, results[n], labels[n])
# results = mnist_model.classify(test_data)
print "recognition rate: ", (results == labels).mean()
def mnist_digit_recognition():
train_set, valid_set, test_set = load_mnist_dataset("mnist.pkl.gz")
n_labels = 10 # 1,2,3,4,5,6,7,9,0
n_features = 28 * 28
mnist_model = GaussianNaiveBayes(n_labels, n_features)
mnist_model.train(train_set[0], train_set[1])
[mean, var], pi = mnist_model.get_parameters()
# visualization of learned means
create_2D_images_horizontal(mean, w=28, h=28)
show()
test_data, labels = test_set
# slice
#limit = len(test_data)
limit = 50
test_data, labels = test_data[:limit], labels[:limit]
results = np.arange(limit, dtype=np.int)
for n in range(limit):
results[n] = mnist_model.classify(test_data[n])
print "%d : predicted %s, correct %s" % (n, results[n], labels[n])
# results = mnist_model.classify(test_data)
print "recognition rate: ", (results == labels).mean()