machine_learn/util/sample.py

from sklearn.datasets import make_classification
from collections import Counter
from imblearn.over_sampling import RandomOverSampler

X, y = make_classification(n_samples=5000, n_features=2, n_informative=2,
                           n_redundant=0, n_repeated=0, n_classes=3,
                           n_clusters_per_class=1,
                           weights=[0.01, 0.05, 0.94],
                           class_sep=0.8, random_state=0)
# Counter(y)
print(X)
print(y)
ros = RandomOverSampler(random_state=0)
X_resampled, y_resampled = ros.fit_sample(X, y)
print(X_resampled)
# sorted(Counter(y_resampled).items())