tushare股票数据下载分享

1.tushare介绍

        tushare数据内容包含股票、基金、期货、债券、外汇、行业大数据，同时包括了数字货币行情等区块链数据，为各类金融投资和研究人员提供适用的数据和工具。我也用tushare的数据，完成了大作业、毕业论文等文章的数据收集工作，在工作过程中也常用tushare进行股票等资产筛选工作。

2.tushare官网链接：

Tushare数据

3.数据获取代码演示

        可以非常方便地通过api获取交易日列表、指数成分股和指数日度收益率数据，可以在此数据基础上进行指数增强、趋势择时等量化策略的设计。输入参数，返回的数据是DataFrame，数据整理很便捷，下载后可以保存到本地，读取更加快速。

import pandas as pd
import numpy as np
from datetime import datetime
import os
from sklearn.model_selection import cross_val_score
import statsmodels.api as sm
import xgboost as xgb
import matplotlib.pyplot as plt
from sklearn.metrics import roc_auc_score
import tushare as ts
# 设置中文编码和负号的正常显示
plt.rcParams.update({"font.family": "STIXGeneral",
                     "font.size": 10,
                      "mathtext.fontset": "cm"})
plt.rcParams['font.family'] = 'Heiti TC'
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

def data_download():
    print('————————————sample choose————————————')
    # 股票池
    start_time = "2010-01-01"
    end_time = "2022-12-31"#tushare接口返回的最后日期是2021-12-31

    # 登录tushare接口和choice接口
    ts.set_token('你的token')
    pro = ts.pro_api('账号')


    print('————————————pre_setting————————————')
    # 筛选出样本区间的每月最后一个交易日
    list_trade = pro.trade_cal(exchange='', is_open='1', 
                            start_date=start_time, 
                            end_date=end_time, 
                            fields='cal_date')
    list_trade.sort_values(by="cal_date" , inplace=True, ascending=True) 
    list_trade.reset_index(drop=True,inplace=True)
    df_time = list_trade
    df_time = df_time.rename(columns={'cal_date':'Date'})
    df_time['Date'] = df_time['Date'].astype('datetime64[ns]')
    df_time['Year'] = df_time['Date'].map(lambda x: x.year)
    df_time['Month'] = df_time['Date'].map(lambda x: x.month)
    df_time['Day'] = df_time['Date'].map(lambda x: x.day)
    df_time['Date_0'] = df_time['Date'].astype('str')
    df_first = df_time.sort_values(by=['Date'], ascending=True)
    df_first = df_first.drop_duplicates(subset=['Year', 'Month']).sort_values(by=['Date'], ascending=True)
    first_time = list(df_first['Date'].astype('str'))
    df_last = df_time.sort_values(by=['Date'], ascending=False)
    df_last = df_last.drop_duplicates(subset=['Year', 'Month']).sort_values(by=['Date'], ascending=True)
    last_time = list(df_last['Date'].astype('str'))

    # 样本筛选
    # 沪深300指数成分股code列表
    hs300 = pro.index_weight(index_code='000300.SH', start_date='20230201',end_date='20230201')#沪深300成分股
    hs300.to_csv('hs300_data.csv')
    hs300_code = list(hs300['con_code'])

    # 获得沪深三百指数的股票收益率作为参照
    hs_return = pro.index_daily(**{"ts_code": "000300.SH","trade_date": "","start_date": start_time,"end_date": end_time,"limit": "","offset": ""}, fields=["ts_code","trade_date","close"])
    hs_return.sort_values(by="trade_date" , inplace=True, ascending=True) 
    hs_return.reset_index(drop=True,inplace=True)
    hs_return['Date'] = hs_return['trade_date'].astype('datetime64[ns]').astype('str')
    hs_return = hs_return[hs_return['Date'].isin(first_time[1:])][['close', 'Date']]
    hs_return['HS_INDEX'] = (-hs_return['close'].diff(-1)) / (hs_return['close'])