预处理算法_9_数据标准化

 

#!/usr/bin/env python
# -*- coding:utf-8 -*-

# <editable>


def execute():
    # <editable>
    '''
    载入模块
    '''
    from sklearn import preprocessing
    import pandas as pd
    from sqlalchemy import create_engine
    '''
    连接数据库
    '''
    engine = create_engine('mysql+pymysql://root:123123qwe@127.0.0.1:3306/analysis')
    '''
    选择目标数据
    '''
    params = {
        "columns": "score",
        "method": "0_scale",

    }
    inputs = {"table": 'test'}
    sql = 'select ' + params['columns'] + ' from ' + inputs['table']
    data_in = pd.read_sql_query(sql, engine)
    print(data_in)
    '''
    标准化
    '''
    data_in = data_in.select_dtypes(include=['number'])  # 筛选数值型数据
    data_out = data_in
    if (params['method'] == '0_scale'):
        data_out = preprocessing.scale(data_in)
    else:
        data_out = preprocessing.minmax_scale(data_in)

    data_out = pd.DataFrame(data_out, columns=data_in.columns)

    '''
    将结果写出
    '''
    print(data_out)
    '''
    数据示例
       score
    0   80.0
    1   20.0
    2    NaN
    3    5.0
    4    4.0
    5   20.0
          score
    0  1.937494
    1 -0.207333
    2       NaN
    3 -0.743540
    4 -0.779287
    5 -0.207333
    '''


# </editable>


if __name__ == '__main__':
    execute()