# 数据源生成
import pandas as pd
import numpy as np
x = np.random.randint(0,100,size=(100,3))
y = pd.Series(data=np.random.randint(0,1,size=(95,)))
y = y.append(pd.Series(data=[1,1,1,1,1]),ignore_index=False).values
y = y.reshape((-1,1))
all_data_np = np.concatenate((x,y),axis=1)
np.random.shuffle(all_data_np)
df = pd.DataFrame(all_data_np)
df.head()

df.shape  # (100, 4)

df[3].value_counts()  # 样本分类不均衡
0    95
1     5
Name: 3, dtype: int64

X = df[[0,1,2]]
y = df[3]

from imblearn.over_sampling import SMOTE
s = SMOTE(k_neighbors=3)
feature,target = s.fit_sample(X,y)  # 返回一个元组

feature.shape  # 原来100行增加到190  # (190, 3)
target.shape  # (190,)

target.value_counts()
1    95
0    95
Name: 3, dtype: int64

from imblearn.under_sampling import RandomUnderSampler
r = RandomUnderSampler()  # 没有那个n_neighbors参数

a,b = r.fit_sample(X,y)

a.shape  # (10, 3)
b.shape  # (10,)

b.value_counts()
1    5
0    5
Name: 3, dtype: int64