统计算法_数值/线性关系度量

继续统计算法，这次也没什么特别的，还没到那么深入，也是比较基础的
1、方差-样本
2、协方差(标准差)-样本
3、变异系数
4、相关系数

依然是先造个list，这次把这个功能写个函数，方便以后调用，另外上一篇写过的函数这次也会继承
def create_rand_list(min_num,max_num,count_list):
  case_list = []
  while len(case_list) < 10:
    rand_float = random.uniform(1,30)
    if rand_float in case_list:
      continue
    case_list.append(rand_float)
  case_list = [round(case,2) for case in case_list]
  return case_list

下面是历史函数
sum_fun() #
len_fun() #
multiply_fun() #
sum_mean_fun() #
sum_mean_rate() #
median_fun() #
modes_fun() #
ext_minus_fun() #
geom_mean_fun() #
geom_mean_rate() #

新函数代码

import random

# 先生成一个随机list，已有函数，不赘述
rand_list = [15.79, 6.83, 12.83, 22.32, 17.92, 6.29, 10.19, 10.13, 24.23, 25.56]

# 1、方差-样本S^2，list中的每个元素减整个list的平均数的平方累加，结果比个数-1，方差总量不-1
def var_fun(rand_list):
  mean_num = sum_mean_fun(rand_list) #计算平均数
  len_num = len_fun(rand_list) #计算总量
  var_list = [(x-mean_num)**2 for x in rand_list]
  var_sum = sum_fun(var_list)
  var_num = var_sum/(len_num - 1)
  return var_num

# 2、协方差(标准差)-样本S，这个简单，用方差开平方就可以了
def covar_fun(rand_list):
  var_num = var_fun(rand_list)
  covar_num = var_num ** 0.5
  return covar_num

# 3、变异系数CV，变异程度度量，协方差/算数平均数*100%
# 说明(百度百科)：在进行数据统计分析时，如果变异系数大于15%，则要考虑该数据可能不正常，应该剔除
def  trans_coef_fun(rand_list):
  covar_num = covar_fun(rand_list)
  mean_num = sum_mean_fun(rand_list)
  trans_coef_num = covar_num / mean_num
  return trans_coef_num

# 4、相关系数-样本r，表示两个维之间的线性关系，-1 < r < 1，越接近1关系维间的关系越强
#    因为是两个维，因此需要输入两维的list，算法比较麻烦
'''
((x1-mean(x))(y1-mean(y))+(x2-mean(x))(y2-mean(y))+...(xn-mean(x))(yn-mean(y)))
/((x1-mean(x))^2+(x2-mean(x))^2+...(xn-mean(x))^2)^0.5*((y1-mean(y))^2+(y2-mean(y))^2+...(yn-mean(y))^2)^0.5
'''
x_list = rand_list
y_list = [4.39, 13.84, 9.21, 9.91, 15.69, 14.92, 25.77, 23.99, 8.15, 25.07]
def pearson_fun(x_list,y_list):
  x_mean = sum_mean_fun(x_list)
  y_mean = sum_mean_fun(y_list)
  len_num = len_fun(x_list)
  if len_num == len_fun(y_list)
    xy_multiply_list = [(x_list[i]-x_mean)*(y_list[i]-y_mean) for i in range(len_num)]
    xy_multiply_num = sum_fun(xy_multiply_list)
  else:
    print 'input list wrong,another input try'
    return 1
  x_covar_son_list = [(x-sum_mean_fun)**2 for x in x_list]
  y_covar_son_list = [(y-sum_mean_fun)**2 for y in y_list]
  x_covar_son_num = sum_fun(x_covar_son_list)
  y_covar_son_num = sum_fun(y_covar_son_list)
  xy_covar_son_multiply_num = (x_covar_son_num ** 0.5) * (y_covar_son_num ** 0.5)
  pearson_num = xy_multiply_num / xy_covar_son_multiply_num
  return pearson_num