皮尔森相关性系数的计算python代码

Posted 2022-05-02 时光-ing

import os
import pandas as pd
import numpy as np
from scipy.stats import pearsonr

def Pearson(data):
    selected = []
    for i in range(len(data.columns) - 1):
        coor, p = pearsonr(list(data.iloc[:, i]), list(data.iloc[:, -1]))
        if p < 0.05 or len(selected) < 0.8 * (len(data.columns) - 1):
            selected.append(data.columns[i])
        print("0与Result的corr为: 1".format(data.columns[i], coor))

if __name__ == "__main__":
    path = os.path.join(os.getcwd(), 'XXX.xls')
    # 读取数据
    data = pd.read_excel(path, skiprows=0)
    data.head()
    X = np.array(data.iloc[:, :-1])
    y = np.array(data.iloc[:, -1:])
    # 3. 皮尔逊分析
    remaining = Pearson(data)
    data = data.loc[:, remaining + ['Result']]
    print(data.head())