xs, ys = DataUtil.get_dataset("mushroom", "../../_Data/mushroom.txt", tar_idx=0)
nb = MultinomialNB()
nb.feed_data(xs, ys)
xs, ys = nb["x"].tolist(), nb["y"].tolist()
train_num = 6000
x_train, x_test = xs[:train_num], xs[train_num:]
y_train, y_test = ys[:train_num], ys[train_num:]
learning_time = time.time()
nb = GaussianNB()
nb.fit(x_train, y_train)
learning_time = time.time() - learning_time
estimation_time = time.time()
nb.estimate(x_train, y_train)
nb.estimate(x_test, y_test)
estimation_time = time.time() - estimation_time
print(
"Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(
learning_time, estimation_time,
learning_time + estimation_time
)
)
nb.show_timing_log()
nb.visualize()
np.random.shuffle(_data)
train_num = 6000
xs = _data
ys = [xx.pop(0) for xx in xs]
nb = MultinomialNB()
nb.feed_data(xs, ys)
xs, ys = nb["x"].tolist(), nb["y"].tolist()
train_x, test_x = xs[:train_num], xs[train_num:]
train_y, test_y = ys[:train_num], ys[train_num:]
train_num = 6000
train_data = _data[:train_num]
test_data = _data[train_num:]
learning_time = time.time()
nb = GaussianNB()
nb.fit(train_x, train_y)
learning_time = time.time() - learning_time
estimation_time = time.time()
nb.estimate(train_x, train_y)
nb.estimate(test_x, test_y)
estimation_time = time.time() - estimation_time
print("Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(
learning_time, estimation_time, learning_time + estimation_time))
