Python实现股票涨跌预测——随机森林模型

威少的书童

已于 2023-03-22 09:27:27 修改

阅读量1.5w

点赞数 22

分类专栏：金融大数据文章标签： python 机器学习算法数据分析

于 2021-03-18 18:00:17 首次发布

本文链接：https://blog.csdn.net/weixin_44436319/article/details/114986896

版权

B站账号@狼群里的小杨，记得点赞收藏加关注，一键三连哦！

废话不多说，干货全在代码里面了。各位自行学习！

'''
python3.7
-*- coding: UTF-8 -*-
@Project -> File   ：Code -> Stock
@IDE    ：PyCharm
@Author ：YangShouWei
@USER: 296714435
@Date   ：2021/3/18 15:52:15
@LastEditor:
'''


import tushare  as ts # 引入股票基本数据相关库
import numpy as np
import pandas as pd
import talib # 引入股票衍生变量数据相关库
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score # 引入预测准确度评分函数
from sklearn.model_selection import GridSearchCV # 网格搜索参数调优函数

# #获取数据
# 1. 获取股票基本数据
df = ts.get_k_data('000002', start='2016-01-01',end='2020-12-31')
df = df.set_index('date') # 将日期作为索引值

# 2.简单衍生变量数据构造
df['close-open'] = (df['close']-df['open'])/df['open']
df['high-low'] = (df['high']-df['low'])/df['low']
df['pre_close'] = df['close'].shift(1)
df['price_change'] = df['close']-df['pre_close']
df['p_change'] = (df['close']-