python统计分析-相关性分析

 

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

# <editable>
def execute():
    # <editable>
    '''
    载入模块
    '''
    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": "SUNACTIVITY",
        "method": "pearson",
    }
    inputs = {"table": '纯随机性检验'}    # 利用了这个表的数据而已
    data_sql = 'select ' + params['columns'] + ' from ' + inputs['table']
    data_in = pd.read_sql_query(data_sql, engine)
    print(data_in)
    '''
    相关性分析
    
    method:
        * pearson : standard correlation coefficient
        * kendall : Kendall Tau correlation coefficient
        * spearman : Spearman rank correlation
    '''
    data_out = data_in.corr(method=params['method'])
    ind = pd.DataFrame({'ind': data_out.index})
    ind.index = data_out.index
    data_out = pd.concat([ind, data_out], axis=1)
    data_out = data_out.round(3)
    '''
    将结果写出
    '''

    print(data_out)
    '''
    数据示例
        SUNACTIVITY
    0           5.0
    1          11.0
    2          16.0
    3          23.0
    4          36.0
    5          40.4
    6          29.8
    7          15.2
    8           7.5
    9           2.9
    10         83.4
    11         47.7
    12         47.8
    13         30.7
    14         12.2
    15         40.4
    16         29.8
    17         15.2
    18          7.5
    19          2.9
    20         12.6
                         ind  SUNACTIVITY
    SUNACTIVITY  SUNACTIVITY          1.0

    '''
# </editable>


if __name__ == '__main__':
    execute()