def main():
Dataset = namedtuple('Dataset', ['inputs', 'labels'])
# Reading in data. You do not need to touch this.
with open("data/train-images-idx3-ubyte.gz",
'rb') as f1, open("data/train-labels-idx1-ubyte.gz", 'rb') as f2:
buf1 = gzip.GzipFile(fileobj=f1).read(16 + 60000 * 28 * 28)
buf2 = gzip.GzipFile(fileobj=f2).read(8 + 60000)
inputs = np.frombuffer(buf1, dtype='uint8',
offset=16).reshape(60000, 28 * 28)
inputs = np.where(inputs > 99, 1, 0)
labels = np.frombuffer(buf2, dtype='uint8', offset=8)
data_train = Dataset(inputs, labels)
with open("data/t10k-images-idx3-ubyte.gz",
'rb') as f1, open("data/t10k-labels-idx1-ubyte.gz", 'rb') as f2:
buf1 = gzip.GzipFile(fileobj=f1).read(16 + 10000 * 28 * 28)
buf2 = gzip.GzipFile(fileobj=f2).read(8 + 10000)
inputs = np.frombuffer(buf1, dtype='uint8',
offset=16).reshape(10000, 28 * 28)
inputs = np.where(inputs > 99, 1, 0)
labels = np.frombuffer(buf2, dtype='uint8', offset=8)
data_test = Dataset(inputs, labels)
# run naive bayes
model = NaiveBayes(10)
model.train(data_train)
print("{:.1f}%".format(model.accuracy(data_test) * 100))
# run logistic regression
model = LogisticRegression(784, 10)
model.train(data_train)
print("{:.1f}%".format(model.accuracy(data_test) * 100))
def main():
np.random.seed(0)
X_train, X_val, y_train, y_val, x_sex, x_age, x_sex_age = get_credit()
model = NaiveBayes(2)
model.train(X_train, y_train)
model.accuracy(X_train, y_train)
model.accuracy(X_val, y_val)
print("------------------------------------------------------------")
print("Train accuracy:")
print(model.accuracy(X_train, y_train))
print("------------------------------------------------------------")
print("Test accuracy:")
print(model.accuracy(X_val, y_val))
print("------------------------------------------------------------")
print("Fairness measures:")
model.print_fairness(X_val, y_val, x_sex_age)