皮尔森相关性系数的计算python代码

Posted 2022-03-30 时光-ing

from math import sqrt
import numpy as np
import pandas as pd

def excel_one_line_to_list():
    def multipl(a, b):
        sumofab = 0.0
        for i in range(len(a)):
            temp = a[i] * b[i]
            sumofab += temp
        return sumofab

    def corrcoef(x, y):
        n = len(x)
        # 求和
        sum1 = sum(x)
        sum2 = sum(y)
        # 求乘积之和
        sumofxy = multipl(x, y)
        # 求平方和
        sumofx2 = sum([pow(i, 2) for i in x])
        sumofy2 = sum([pow(j, 2) for j in y])
        num = sumofxy - (float(sum1) * float(sum2) / n)
        # 计算皮尔逊相关系数
        den = sqrt((sumofx2 - float(sum1 ** 2) / n) * (sumofy2 - float(sum2 ** 2) / n))
        return num / den

    df = pd.read_excel("G:\\文件夹1\\文件夹2\\文件夹3\\data.xls", usecols=[0], names=None)  # 读取项目名称列,不要列名
    df = np.array(df)

    df2 = pd.read_excel("G:\\文件夹1\\文件夹2\\文件夹3\\data.xls", usecols=[1], names=None)  # 读取项目名称列,不要列名
    df2 = np.array(df2)
    print(corrcoef(df, df2))
if __name__ == '__main__':
    excel_one_line_to_list()