【Time Series】【专题系列】一、时序预测股票数据获取

【Time Series】【专题系列】一、时序预测股票数据获取

目录

一、简介

二、代码

---

一、简介

        "时间序列+金融"是一个很有"钱"景的话题，若想开始DeepLearning+TimeSeries+Stock，首先得拿到数据。本文提供了一种股票数据获取的源代码。

二、代码

        1、首先，将要获取数据的股票按照图中xlsx的格式整理，sheet名设置为"stock_names"。如下图：

        2、然后直接运行下列代码，配置好输入(stock_names.xlsx)和输出路径，就可以实现数据获取。

import os
import baostock as bs
import pandas as pd
from datetime import datetime
from datetime import timedelta

# 自定义的日期解析函数，仅保留日期部分
def custom_date_parser(x):
    return datetime.strptime(x, '%Y-%m-%d %H:%M:%S').date()

class stock_data():
    def __init__(self):
        self.params = self.init_baostock()

    def init_baostock(self):
        # 计算MACD / KDJ / RSI 的params 参数设置
        # 12,26,9
        # 6,12,24
        # 9,3,3
        # params = []
        # with open('configs/input_params.txt', 'r') as f:
        #     code_list = f.readlines()
        #     for index, item in enumerate(code_list):
        #         item = item.strip()
        #         item = item.split(',')
        #         params += [int(i) for i in item]
        #     return params
        params = [12,26,9,
                  6,12,24,
                  9,3,3]
        return params

    def get_stock_basedata(self,code,start_date,end_date):
        """open/high/low/close/volume/MACD/KDJ"""
        lg = bs.login()
        #将时间去除时分秒
        start_date = (pd.to_datetime(start_date) + timedelta(days=1)).strftime("%Y-%m-%d")
        end_date = (pd.to_datetime(end_date) + timedelta(days=1)).strftime("%Y-%m-%d")
        rs = bs.query_history_k_data_plus(code,
                                          "date,code,open,high,low,close,preclose,volume,amount,turn",
                                          start_date=start_date, end_date=end_date, frequency="d",
                                          adjustflag='2')  # 注意adjustflag取前复权
        data_list = []
        while (rs.error_code == '0') & rs.next():
            data_list.append(rs.get_row_data())
        self.stock_pd = pd.DataFrame(data_list, columns=rs.fields)
        self.stock_pd[['open', 'high', 'low', 'close', 'volume']] = self.stock_pd[['open', 'high', 'low', 'close', 'volume']].astype(
            'float64')
        self.stock_pd = self.stock_pd.rename(columns={'date': 'datetime'})
        self.stock_pd.index = pd.DatetimeIndex(self.stock_pd['datetime'])
        # Step2： 利用Pandas 计算MACD / KDJ / RSI
        short_ema = self.stock_pd['close'].ewm(span=self.params[0]).mean()
        long_ema = self.stock_pd['close'].ewm(span=self.params[1]).mean()
        self.stock_pd.loc[:, 'DIFF'] = short_ema - long_ema
        self.stock_pd.loc[:, 'DEA'] = self.stock_pd['DIFF'].ewm(span=self.params[2]).mean()
        self.stock_pd.loc[:, 'MACD'] = 2 * (self.stock_pd['DIFF'] - self.stock_pd['DEA'])
        low_list = self.stock_pd['low'].rolling(9, min_periods=9).min()
        low_list.fillna(value=self.stock_pd['low'].expanding().min(), inplace=True)
        high_list = self.stock_pd['high'].rolling(9, min_periods=9).max()
        high_list.fillna(value=self.stock_pd['high'].expanding().max(), inplace=True)
        rsv = (self.stock_pd['close'] - low_list) / (high_list - low_list) * 100
        self.stock_pd['k'] = pd.DataFrame(rsv).ewm(com=2).mean()
        self.stock_pd['d'] = self.stock_pd['k'].ewm(com=2).mean()
        self.stock_pd['j'] = 3 * self.stock_pd['k'] - 2 * self.stock_pd['d']

        return self.stock_pd

def get_data_workflow(input_stock_names,output_stock_datas):
    #1.获取csv下所有股票的数据并保留在文件夹下
    stock_class = stock_data()
    stocks_df = pd.read_excel(input_stock_names,
                              sheet_name='stock_names',
                              parse_dates=['起始时间','终止时间'],
                              date_parser=custom_date_parser)

    #2.获取数据
    for _,code,start_date,end_date,stock_name in stocks_df.itertuples():
        tmp_stock_pds = stock_class.get_stock_basedata(code,start_date,end_date)
        # 3.保存写入数据
        tmp_stock_pds.to_excel(os.path.join(output_stock_datas, stock_name + '.xlsx'), index=False)

if __name__ == '__main__':
    get_data_workflow(input_stock_names='input_datas/stock_names.xlsx',
                                  output_stock_datas='output_datas/stock_datas')