1、公式如下:
2、通常情况下通过以下取值范围判断变量的相关强度:
相关系数 0.8-1.0 极强相关
0.6-0.8 强相关
0.4-0.6 中等程度相关
0.2-0.4 弱相关
0.0-0.2 极弱相关或无相关
3、python实现
import math
#计算特征和类的平均值
def calcMean(x,y):
sum_x = sum(x)
sum_y = sum(y)
n = len(x)
x_mean = float(sum_x+0.0)/n
y_mean = float(sum_y+0.0)/n
return x_mean,y_mean
#计算Pearson系数
def calcPearson(x,y):
x_mean,y_mean = calcMean(x,y) #计算x,y向量平均值
n = len(x)
sumTop = 0.0
sumBottom = 0.0
x_pow = 0.0
y_pow = 0.0
for i in range(n):
sumTop += (x[i]-x_mean)*(y[i]-y_mean)
for i in range(n):
x_pow += math.pow(x[i]-x_mean,2)
for i in range(n):
y_pow += math.pow(y[i]-y_mean,2)
sumBottom = math.sqrt(x_pow*y_pow)
p = sumTop/sumBottom
return p
x = [1.0,2.0]
y = [5.0,4.0]
p = calcPearson(x,y)
print(p)
参考文章:
1、百度百科
2、https://blog.csdn.net/niuwei22007/article/details/52334544
3、https://blog.csdn.net/xzfreewind/article/details/73550856