person系数计算python源码

 """
    pearson系数计算
    请先安装xlrd模块读取excel
    数据放置在sheet的前两列，第一行是标题，不要放数据   
 """
    import xlrd
    
    def re_excel_col(filename, sheet_index):
        '''读取表格中的某些列'''
        print("开始读取文件")
        # 需要读取表格的文件名 ：filename
        # 默认sheet_index = 0 ：sheet_index
        data = xlrd.open_workbook(filename)
        # 读取制定表格的sheet，一般第一个是0
        sheet = data.sheet_by_index(sheet_index)
        
        # 获取x和y的值，首行需要放置标签，x第一列，y第二列
        col_read_x_value = sheet.col_values(0, start_rowx = 1, end_rowx = None)
        col_read_y_value = sheet.col_values(1, start_rowx = 1, end_rowx = None)
        print("已经读取完毕"+ filename , end = '\n')
        pearson(col_read_x_value, col_read_y_value)
    
    def pearson(x_value, y_value):
        """计算Pearson系数"""
        print("\n开始处理数据")
        # 计算X的平均值
        average_x = 0
        for i in x_value:
        average_x += i
        average_x = average_x  len(x_value)
           
        # 计算Y的平均值
        average_y = 0
        for j in y_value:
        average_y += j
        average_y = average_y / len(y_value)
        
        # 计算三个系数
        L_XY = 0
        L_XX = 0
        L_YY = 0
        
        for m,n in zip(x_value, y_value):
        L_XY += (average_x - m) * (average_y - n)
        L_XX += abs(average_x - m)**(2)
        L_YY += abs(average_y - n)**(2)
        
        r = L_XY / (L_XX * L_YY)**(1/2)
        r = format(r, '.8f')
        print("pearson系数为：", r)
        
 # 主程序(第一个元素选择excel表格的位置，第二个元素是第几个sheet，0是默认第一个sheet)  
    re_excel_col(r'd:\Desktop\小程序\1.xlsx', 0)