Python基于皮尔逊系数实现股票预测

 # -*- coding: utf-8 -*-
 """
 Created on Mon Dec  2 14:49:59 2018

 @author: zhen
 """

 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
 from datetime import datetime

 def normal(a):  #最大值最小值归一化
     return (a - np.min(a)) / (np.max(a) - np.min(a)+0.000001)

 def normalization(x): # np.std:计算矩阵的标准差（方差的算术平方根）
     return (x - np.mean(x)) / np.std(x)

 def corrcoef(a,b):
     corrc = np.corrcoef(a,b) # 计算皮尔逊相关系数，用于度量两个变量之间的相关性，其值介于-1到1之间
     corrc = corrc[0,1]
     return (16 * ((1 - corrc) / (1 + corrc)) ** 1) # ** 表示乘方

 startTimeStamp = datetime.now() # 获取当前时间
 # 加载数据
 filename = 'C:/Users/zhen/.spyder-py3/sh000300_2017.csv'
 # 获取第一，二列的数据
 all_date = pd.read_csv(filename,usecols=[0, 1, 3], dtype = 'str')
 all_date = np.array(all_date)
 data = all_date[:, 0]
 times = all_date[:, 1]

 data_points = pd.read_csv(filename,usecols=[3])
 data_points = np.array(data_points)
 data_points = data_points[:,0] #数据

 topk = 10 #只显示top-10
 baselen = 100
 basebegin = 361
 basedata = data[basebegin]+' '+times[basebegin]+'~'+data[basebegin+baselen-1]+' '+times[basebegin+baselen-1]
 base = data_points[basebegin:basebegin+baselen]#一天的数据是240个点
 length = len(data_points) #数据长度

 # 分割片段
 subseries = []
 dateseries = []
 for j in range(0,length):
     if (j < (basebegin - baselen) or j > (basebegin + baselen - 1)) and j <length - baselen:
         subseries.append(data_points[j:j+baselen])
         dateseries.append(j) #开始位置

 # 片段搜索
 listdistance = []
 for i in range(0, len(subseries)):
     tt = np.array(subseries[i])
     distance = corrcoef(base, tt)
     listdistance.append(distance)

 # 排序
 index = np.argsort(listdistance,kind='quicksort') #排序，返回排序后的索引序列

 # 显示，要匹配的数据
 plt.figure(0)
 plt.plot((base),label = basedata, linewidth='')
 plt.legend(loc='upper left')
 plt.title('Base data')

 # 原始数据
 plt.figure(1)
 num = index[0]
 length = len(subseries[num])
 begin = data[dateseries[num]]+' '+times[dateseries[num]]
 end = data[dateseries[num]+length-1]+' '+times[dateseries[num]+length-1]
 label = begin+'~'+end
 plt.plot((subseries[num]), label=label, linewidth='')
 plt.legend(loc='upper left')
 plt.title('Similarity data')

 # 结果集对比
 plt.figure(2)
 plt.plot(normalization(base),label= basedata,linewidth='')
 length = len(subseries[num])
 begin = data[dateseries[num]] + ' ' + times[dateseries[num]]
 end = data[dateseries[num] + length - 1] + ' ' + times[dateseries[num] + length - 1]
 label = begin + '~' + end
 plt.plot(normalization(subseries[num]), label=label, linewidth='')
 plt.legend(loc='lower right')
 plt.title('normal similarity search')
 plt.show()

 endTimeStamp=datetime.now()
 print('run time', (endTimeStamp-startTimeStamp).seconds, "s")

结果：