沪深300配对交易

获取数据

通过pandas_datareader来获取沪深300的股票数据，为此，先从网上爬虫得到沪深300的股票名单

import os
import pandas as pd
import pandas_datareader as web
import pickle
import requests
import bs4 as bs
import matplotlib.pyplot as plt
import numpy as np
# import tushare


def save_hs300_tickers():
    # resp = requests.get('https://en.wikipedia.org/wiki/List_of_S%26P_500_companies')
    resp = requests.get(
        'https://zh.wikipedia.org/wiki/%E6%B2%AA%E6%B7%B1300#%E6%88%90%E4%BB%BD%E8%82%A1%E5%88%97%E8%A1%A8')
    soup =bs.BeautifulSoup(resp.text, "lxml")
    table = soup.find('table', {
   'class':"wikitable collapsible sortable"})
    tickers = []
    for row in table.find_all('tr')[1:]:
        ticker = row.find('td').text
        if ticker[0] == "6" :
            ticker = ticker + ".SS"
        else :
            ticker = ticker + ".SZ"
        tickers.append(ticker)


    with open("hs300tickers.pickle","wb") as f:
        pickle.dump(tickers,f)

    print(tickers)
    return tickers

之后下载数据

def get_data_from_yahoo(reload_hs300=False):
    if reload_hs300:
        tickers = save_hs300_tickers()
    else:
        with open("hs300tickers.pickle", "rb") as f:
            tickers = pickle.load(f)
    if not os.path.exists('stock_dfs'):
        os.makedirs('stock_dfs')

    start_date = dt.datetime(2010, 1, 1)
    end_date = dt.datetime(