单因子——数据Wind

读取数据

import time
date = time.strftime("%Y-%m-%d") 
date = date.replace("'", "")
from WindPy import *
import pandas as pd
import numpy as np
from pymongo import MongoClient
w.start()
w.isconnected()
import time
from concurrent.futures import ProcessPoolExecutor,ThreadPoolExecutor, as_completed
import json

连接数据库

host ='xxx.xxx.x.xx'
port='27017'
user='xxxx'
code='utf8utf8'
uri= "mongodb://"+user+":"+code+"@"+host+":"+port+"/"+"?authMechanism=SCRAM-SHA-1"
client=MongoClient(uri)
db = client['CN_Stock']
collection = db['Wind_Close_Price']

获取Wind中A股公司列表

A_list = w.wset("sectorconstituent","date=2019-07-30;sectorid=a001010100000000",usedf=True)
A_list = A_list[1]#取dataframe部分

多线程

df = pd.DataFrame(columns = ['wind_code','close','volume','amt','total_shares'] )
df['wind_code'] = A_list['wind_code']
df_list = A_list.copy()
#定义多线程函数
def applyParallel(dfGrouped, func):
        ppe = ThreadPoolExecutor(10)#设置线程池中最多能同时运行的线程数目
        futures = []
        results = []
        for name, group in dfGrouped:
            p = ppe.submit(func, group)#提交函数和变量，立即返回
            futures.append(p)
        for future in as_completed(futures):
            r = future.result()
            results.append(r)
        return pd.concat(results)#合