Sharedimblearn-test.ipynbOpen in CoCalc

imblearn on cocalc

kernel: python 3 ubuntu linux

import imblearn
imblearn.__version__
'0.4.3'
from collections import Counter
from sklearn.datasets import make_classification
from imblearn.over_sampling import SMOTE  # doctest: +NORMALIZE_WHITESPACE
# implementation of SMOTE - Synthetic Minority Over-sampling Technique
X, y = make_classification(
    n_classes=2,
    class_sep=2,
    weights=[0.1, 0.9],
    n_informative=3,
    n_redundant=1,
    flip_y=0,
    n_features=20,
    n_clusters_per_class=1,
    n_samples=1000,
    random_state=10)
print('Original dataset shape %s' % Counter(y))
Original dataset shape Counter({1: 900, 0: 100})
sm = SMOTE(random_state=42)
sm
SMOTE(k_neighbors=5, kind='deprecated', m_neighbors='deprecated', n_jobs=1, out_step='deprecated', random_state=42, ratio=None, sampling_strategy='auto', svm_estimator='deprecated')
X_res, y_res = sm.fit_resample(X, y)
print('Resampled dataset shape %s' % Counter(y_res))
Resampled dataset shape Counter({0: 900, 1: 900})