上采样+下采样+分层抽样

数据生成

import pandas as pd
import numpy as np

data = pd.DataFrame(np.random.random((50, 3)), columns=['a', 'b', 'c'])
data['y'] = np.vstack((np.zeros((6, 1)), np.ones((44, 1))))

过采样/上采样

# 朴素随机过采样 过采样后样本类别的比列为1:1
from imblearn.over_sampling import RandomOverSampler

ros = RandomOverSampler(random_state=0)
x, y = ros.fit_sample(data[['a', 'b', 'c']], data['y'])

ros = RandomOverSampler(random_state=0)

x, y = ros.fit_sample(data[['a', 'b', 'c']], data['y'])

# SMOTE过采样
# SMOTE：对于少数类的样本a，随机选择一个最近邻的样本b，
# 然后从a到b的连线上随机选取一个点c作为新的少数类样本
from imblearn.over_sampling import SMOTE

x, y = SMOTE(k_neighbors=5).fit_sample(data[['a', 'b', 'c']], data['y'])  # 少数类别的样本数不能少于k_neighbors

# ADASYN
# 关注的是在那些基于K近邻分类器被错误分类的原始样本附近生成新的少数类样本
from imblearn.over_sampling import ADASYN

x, y = ADASYN().fit_sample(data[['a', 'b', 'c']], data['y'])

下采样

from imblearn.under_sampling import ClusterCentroids
 
cc = ClusterCentroids(random_state=0)
x, y = cc.fit_sample(data[['a', 'b', 'c']], data['y'])

from imblearn.under_sampling import RandomUnderSampler

rus = RandomUnderSampler(random_state=0)

x, y = rus.fit_sample(data[['a', 'b', 'c']], data['y'])

分层抽样

typical = {0: 1, 1: 0.2}  # 抽样比例

def function(group, typical):
    name = group.name
    frac = typical[name]
    return group.sample(frac=frac)

result = data.groupby('y', group_keys=False).apply(function, typical)

过采样和下采样结合

在之前的SMOTE方法中, 当由边界的样本与其他样本进行过采样差值时, 很容易生成一些噪音数据. 因此, 在过采样之后需要对样本进行清洗. 这样, 第三节中涉及到的TomekLink 与 EditedNearestNeighbours方法就能实现上述的要求. 所以就有了两种结合过采样与下采样的方法:
(i) SMOTETomek

from imblearn.combine import SMOTEENN

smote_enn = SMOTEENN(random_state=0)

x, y = smote_enn.fit_sample(data[['a', 'b', 'c']], data['y'])

(ii) SMOTEENN

from imblearn.combine import SMOTETomek

smote_tomek = SMOTETomek(random_state=0)

x, y = smote_tomek.fit_sample(data[['a', 'b', 'c']], data['y'])