Python--计算相关系数

计算两个列表变量的相关系数

#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)
   if n==0:
	   return 0,0
   else:
	   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)
        x_pow += (x[i] - x_mean)*(x[i]-x_mean)
    for i in range(n):
        # y_pow += math.pow(y[i]-y_mean,2)
        y_pow += (y[i] - y_mean) * (y[i] - y_mean)
    sumBottom = sqrt(x_pow*y_pow)
    p = sumTop/sumBottom
    return p