Python 股市预测工具

最新推荐文章于 2025-03-04 17:08:03 发布

原创最新推荐文章于 2025-03-04 17:08:03 发布 · 506 阅读

8 ·

CC 4.0 BY-SA版权

文章标签：

#python #开发语言 #web安全 #安全 #网络 #运维 #wireshark

程序员同时被 3 个专栏收录

3074 篇文章

订阅专栏

计算机工具

1670 篇文章

订阅专栏

原创

53 篇文章

订阅专栏

大家好！今天给你们带来了简单Python股市预测工具，仅供学习，请勿实用！

在这里插入图片描述

安装：

pip install baostock``pip install numpy``pip install statsmodels

完整实例：

import baostock as bs``import numpy as np``from statsmodels.tsa.statespace.sarimax import SARIMAX``from statsmodels.tsa.seasonal import seasonal_decompose``from datetime import datetime, timedelta``   ``def stock_price_prediction(stock_code, predict_days):`    `#登录baostock`    `lg = bs.login()``   `    `#设置日期范围`    `end_date = datetime.now().strftime("%Y-%m-%d")`    `start_date = (datetime.now() - timedelta(days=60)).strftime("%Y-%m-%d")#分析天数``   `    `#查询股票数据`    `rs = bs.query_history_k_data(stock_code,`                                 `"date,open,close",`                                 `start_date=start_date,`                                 `end_date=end_date,`                                 `frequency="d",`                                 `adjustflag="3")`    `data_list = []`    `while rs.next():`        `data_list.append(rs.get_row_data())`    `data = np.array(data_list)``   `    `#数据处理`    `close_prices = data[:, 2].astype(float)  #仅使用收盘价`    `close_prices_diff = np.diff(close_prices)  #计算价格差分``   `    `#季节性分解`    `result = seasonal_decompose(close_prices_diff, model='additive', period=7)`    `trend = result.trend`    `seasonal = result.seasonal`    `residual = result.resid``   `    `#根据季节性分解结果设置SARIMAX参数`    `#这里假设季节性周期为7天，根据实际情况调整`    `seasonal_order = (1, 1, 1, 7)`    `#根据残差选择ARIMA参数`    `#这里假设ARIMA参数为(1, 1, 1)，根据实际情况调整`    `order = (1, 1, 1)``   `    `# 建立SARIMAX模型`    `model = SARIMAX(trend, order=order, seasonal_order=seasonal_order)`    `model_fit = model.fit(disp=False)``   `    `#预测未来价格变动`    `forecast = model_fit.forecast(steps=predict_days)``   `    `#将预测的价格变动转换为未来的收盘价`    `future_close_prices = close_prices[-1] + forecast.cumsum()``   `    `#打印预测结果`    `print("\n未来%d天的股票价格预测：" % predict_days)`    `print("==============================")`    `print("|{:^14s}|{:^14s}|".format("日期", "收盘价"))`    `print("|" + "-" * 14 + "|" + "-" * 14 + "|")`    `for i in range(predict_days):`        `date_str = (np.datetime64(end_date) + np.timedelta64(i+1, 'D')).astype(str)`        `close_price_str = "%.2f" % future_close_prices[i]`        `print("|{:^14s}|{:^14s}|".format(date_str, close_price_str))`    `print("==============================")``   `    `#显示历史数据`    `display_data(data)``   `    `#退出baostock`    `bs.logout()``   ``def display_data(data):`    `print("\n获取到的历史股票价格数据：")`    `print("=" * 50)`    `print("|{:^14s}|{:^14s}|{:^14s}|".format("日期", "开盘价", "收盘价"))`    `print("|" + "-" * 14 + "|" + "-" * 14 + "|" + "-" * 14 + "|")`    `for row in data:`        `print("|{:^14s}|{:^14s}|{:^14s}|".format(row[0], row[1], row[2]))`    `print("=" * 50)``   ``#预测的股票代码和天数``stock_code = "sh.600519"  # 贵州茅台``predict_days = 5  # 预测天数``stock_price_prediction(stock_code, predict_days)

输出：

login success!``   ``未来5天的股票价格预测：``==============================``|      日期      |     收盘价      |``|--------------|--------------|``|  2024-04-15  |   1624.04    |``|  2024-04-16  |   1614.54    |``|  2024-04-17  |   1604.57    |``|  2024-04-18  |   1595.40    |``|  2024-04-19  |   1586.41    |``==============================``   ``获取到的历史股票价格数据：``==================================================``|      日期      |     开盘价      |     收盘价      |``|--------------|--------------|--------------|``|  2024-02-19  |  1737.8700   |  1695.4300   |``|  2024-02-20  |  1697.3600   |  1670.0000   |``|  2024-02-21  |  1666.0200   |  1717.6600   |``|  2024-02-22  |  1707.5000   |  1718.3800   |``|  2024-02-23  |  1711.1100   |  1714.0900   |``|  2024-02-26  |  1708.0000   |  1694.9800   |``|  2024-02-27  |  1683.0000   |  1689.5000   |``|  2024-02-28  |  1688.9200   |  1681.5500   |``|  2024-02-29  |  1681.5500   |  1695.0000   |``|  2024-03-01  |  1690.0000   |  1685.0600   |``|  2024-03-04  |  1679.0000   |  1676.3000   |``|  2024-03-05  |  1670.8100   |  1695.1000   |``|  2024-03-06  |  1691.0000   |  1680.5500   |``|  2024-03-07  |  1680.0000   |  1683.6300   |``|  2024-03-08  |  1680.5600   |  1671.4300   |``|  2024-03-11  |  1675.0000   |  1694.4900   |``|  2024-03-12  |  1693.9400   |  1745.0000   |``|  2024-03-13  |  1739.9700   |  1727.4500   |``|  2024-03-14  |  1719.0000   |  1716.6300   |``|  2024-03-15  |  1712.5000   |  1717.4900   |``|  2024-03-18  |  1715.0000   |  1708.2600   |``|  2024-03-19  |  1703.0000   |  1708.0200   |``|  2024-03-20  |  1703.3600   |  1709.6000   |``|  2024-03-21  |  1708.1000   |  1709.0000   |``|  2024-03-22  |  1705.0300   |  1701.3500   |``|  2024-03-25  |  1698.5400   |  1689.0100   |``|  2024-03-26  |  1687.4600   |  1709.2900   |``|  2024-03-27  |  1705.0000   |  1701.0000   |``|  2024-03-28  |  1695.0000   |  1701.6400   |``|  2024-03-29  |  1701.6400   |  1702.9000   |``|  2024-04-01  |  1709.9900   |  1721.3300   |``|  2024-04-02  |  1722.0000   |  1713.9900   |``|  2024-04-03  |  1734.0000   |  1715.1100   |``|  2024-04-08  |  1695.0000   |  1666.6600   |``|  2024-04-09  |  1660.6700   |  1662.2200   |``|  2024-04-10  |  1662.2700   |  1647.9800   |``|  2024-04-11  |  1640.1100   |  1648.0000   |``|  2024-04-12  |  1651.0000   |  1634.0300   |``==================================================``logout success!