import numpy as np from sklearn.datasets import make_classification from sklearn.model_selection import train_test_split def generate_dataset(): x, y = make_classification(n_samples=500, n_features=2, n_redundant=0, n_informative=2, random_state=0, n_clusters_per_class=1) random = np.random.RandomState(2) x += 2.5 * random.uniform(size=x.shape) return x, y def split_dataset(x, y): return train_test_split( x, y, test_size=.05, random_state=42)