def main():
X, Y = util.get_mnist()
Ntrain = len(Y) // 2
Xtrain, Ytrain = X[:Ntrain], Y[:Ntrain]
Xtest, Ytest = X[Ntrain:], Y[Ntrain:]
model = get_model()
t0 = datetime.now()
model.fit(Xtrain, Ytrain)
print("Training time:", (datetime.now() - t0))
t0 = datetime.now()
print("Train accuracy:", model.score(Xtrain, Ytrain))
print("Time to compute train accuracy:", (datetime.now() - t0),
"Train size:", len(Ytrain))
t0 = datetime.now()
print("Test accuracy:", model.score(Xtest, Ytest))
print("Time to compute test accuracy:", (datetime.now() - t0),
"Test size:", len(Ytest))
# Plot the mean of each class
# for c, g in iteritems(model.gaussians):
# plt.imshow(g['mean'].reshape(28, 28))
# plt.title(c)
# plt.show()
util.save_model(model, 'model_bayes')
def test_image_conversion(self):
# Arrange
from PIL import Image
X, y = util.get_mnist(1)
X = X.astype('float32')
# image_arr = X[0].reshape(1,-1)
image_arr = X[0]
logging.info(f'Shape: {image_arr.shape}')
# im = Image.fromarray(np.uint8(X[0]))
measurement_in_pixels = 28
image_arr = image_arr.reshape(measurement_in_pixels,
measurement_in_pixels)
logging.info(f'Type: {type(image_arr)}')
# image_path = os.path.join(config.DATA_FOLDER_PATH, 'sample.PNG')
# im = Image.open(image_path)
# image_arr = np.asarray(im)
logging.info(f'a shape:{image_arr.shape}')
image = Image.fromarray(np.uint8(image_arr), mode='L')
def get_data(limit=None):
X, Y = util.get_mnist(limit=limit, otherize_digits=[])
X_train, X_test, Y_train, Y_test = train_test_split(X,
Y,
shuffle=True,
train_size=0.6)
return X, Y, X_train, X_test, Y_train, Y_test
def get_data(limit=None):
if RUNNING_LOCAL is True:
from app import util
X, Y = util.get_mnist(limit=limit, otherize_digits=[])
else:
X, Y = get_train(limit)
X_train, X_test, Y_train, Y_test = train_test_split(
X, Y, shuffle=shuffle_sample_data, train_size=0.7)
return X, Y, X_train, X_test, Y_train, Y_test
def get_data(limit=None):
if RUNNING_LOCAL is True:
from app import util
X, y = util.get_mnist(limit=limit)
else:
X, y = get_train(limit)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
shuffle=False,
train_size=0.7)
return X, y, X_train, X_test, y_train, y_test
def main():
X, Y = get_mnist()
Ntrain = len(Y) // 2
Xtrain, Ytrain = X[:Ntrain], Y[:Ntrain]
Xtest, Ytest = X[Ntrain:], Y[Ntrain:]
model = get_model()
t0 = datetime.now()
model.fit(Xtrain, Ytrain)
print("Training time:", (datetime.now() - t0))
t0 = datetime.now()
print("Train accuracy:", model.score(Xtrain, Ytrain))
print("Time to compute train accuracy:", (datetime.now() - t0),
"Train size:", len(Ytrain))
t0 = datetime.now()
print("Test accuracy:", model.score(Xtest, Ytest))
print("Time to compute test accuracy:", (datetime.now() - t0),
"Test size:", len(Ytest))