python计算股价与前一天股价关联(皮尔逊系数)

import pandas as pd
a = pd.read_csv("a.csv",names=["ha"])
b = a.iloc[1:,:]

row = pd.DataFrame({"ha":range(1)},index=range(a.index.size,a.index.size+1))
c = pd.concat([b,row]).rename(columns={"ha":"he"})
c.index=a.index
d = pd.concat([a,c],axis=1)
print(calcAttribute(d))
#%%
import math
#皮尔逊相关系数
#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)  
   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  

#计算每个特征的spearman系数，返回数组  
def calcAttribute(dataSet):  
    prr = []  
    n,m = dataSet.shape    #获取数据集行数和列数
    print(n,m)
    x = [0] * n             #初始化特征x和类别y向量  
    y = [0] * n  
    for i in range(n):      #得到类向量  
        y[i] = dataSet.iat[i,m-1]  
    for j in range(m-1):    #获取每个特征的向量，并计算Pearson系数，存入到列表中  
        for k in range(n):  
            x[k] = dataSet.iat[k,j]  
        prr.append(calcPearson(x,y))  
    return prr  
#%%

结果为0.1119,关系的确不强

#后面又测试了某股票一年来的数据与深圳成指之间的关联性，为0.5259

相比起来就显得关联性强的多了