-
Notifications
You must be signed in to change notification settings - Fork 4
/
smote-output.py
55 lines (48 loc) · 2.24 KB
/
smote-output.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
# -*- coding: utf-8 -*-
"""
This program is used to generate datasets after SMOTE operation.
Date: 2019-03-03
"""
# import os
import time
from argparse import ArgumentParser, ArgumentDefaultsHelpFormatter
__author__ = 'Min'
if __name__ == "__main__":
start_time = time.time()
parser = ArgumentParser(description='This program is used to generate datasets after SMOTE operation.',
formatter_class=ArgumentDefaultsHelpFormatter)
parser.add_argument('--input', type=str, help='The path of input dataset.', required=True)
parser.add_argument('--output', type=str, help='The path of output dataset.', required=True)
args = parser.parse_args()
# 导入相关库
import numpy as np
import pandas as pd
from imblearn.over_sampling import SMOTE
# 读取数据
df = pd.read_csv(args.input)
# 设定分类信息和特征矩阵
X = df.iloc[:, 1:].values
y = df.iloc[:, 0].values
# f_names = df.columns[1:].values
# 不同 Class 统计 (根据 Target 列)
print('\nInput Dataset shape: ', X.shape, ' Number of features: ', X.shape[1])
num_categories = np.unique(y).size
sum_y = np.asarray(np.unique(y.astype(int), return_counts=True))
df_sum_y = pd.DataFrame(sum_y.T, columns=['Class', 'Sum'], index=None)
print('\n', df_sum_y)
# Apply SMOTE 生成 fake data
sm = SMOTE(k_neighbors=2)
x_resampled, y_resampled = sm.fit_sample(X, y)
# after over sampleing 读取分类信息并返回数量
np_resampled_y = np.asarray(np.unique(y_resampled.astype(int), return_counts=True))
df_resampled_y = pd.DataFrame(np_resampled_y.T, columns=['Class', 'Sum'])
print("\nNumber of samples after SMOTE over sampleing:\n{0}".format(df_resampled_y))
# 合并新的特征矩阵
resampled_data = np.column_stack((y_resampled, x_resampled))
resampled_df = pd.DataFrame(index=None, data=resampled_data, columns=df.columns.values)
# 输出SMOTE后的特征集
resampled_df.to_csv('{0}'.format(args.output), index=None)
print('\nNew datasets saved to:`{0}`'.format(args.output))
end_time = time.time() # 程序结束时间
print('\n[Finished in: {0:.6f} mins = {1:.6f} seconds]'.format(
((end_time - start_time) / 60), (end_time - start_time)))