Python【图解】样本不均衡问题及采样策略

样本不均衡的影响

from sklearn.datasets import make_blobs
import numpy as np, matplotlib.pyplot as mp
from sklearn.linear_model import LogisticRegression

# 负样本:正样本 = 1:1
X, Y = make_blobs(centers=2, cluster_std=2, random_state=0)
# 负样本:正样本 = 5:1
X0 = np.concatenate([X if i < 1 else X[Y == 0] for i in range(5)])
Y0 = np.concatenate((Y, np.zeros(200, np.int32)))
# 负样本:正样本 = 1:5
X1 = np.concatenate([X if i < 1 else X[Y == 1] for i in range(5)])
Y1 = np.concatenate((Y, np.ones(200, np.int32)))

for i, (Xi