根据股票当日涨幅和换手率预测其下一交易日的涨跌情况[Python实现]

        前些天在某网站看到了一个比较有意思的股票交易策略，即在尾盘[02:30~03:00]挑选出当日换手率3%~5%，涨幅5%左右的股票买入，下一交易日伺机卖出。因为股票涨跌存在一定的延续性，个人感觉该策略似乎有一点道理，后经过连续几天的测试，认为该策略有进一步研究和验证的价值。于是打算通过python对其进行一个初步的验证，思路大概如下：

1、获取沪深A股部分股票(60XXXX和00XXXX)过去一个月(2022-06-01~2022-07-01)涨幅和换手率的历史数据

2、以连续两个交易日的数据构建数据集，其中前一日的涨幅和换手率取整后作为X，后一日的涨跌作为y

3、各种机器学习模型对数据进行拟合，这里主要基于sklearn并且不考虑堆叠

数据获取部分

        要获取沪深股票历史数据，首先需要获取股票代码部分，然后根据股票代码再到相应接口获取历史数据，这两部分均可通过网易财经获得

import urllib.request
import re
import time
from random import random

def CodeGet():
    '''
    在http://quotes.money.163.com/old/#query=EQA_EXCHANGE_CNSESH&DataType=HS_RANK&sort=PERCENT&order=desc&count=24&page=0
    通过点击翻页查看开发者工具(F12)→Network找到了沪深A股的代码接口,分别是:
    沪:http://quotes.money.163.com/hs/service/diyrank.php?host=http%3A%2F%2Fquotes.money.163.com%2Fhs%2Fservice%2Fdiyrank.php&page=0&query=STYPE%3AEQA%3BEXCHANGE%3ACNSESH&fields=NO%2CSYMBOL%2CNAME%2CPRICE%2CPERCENT%2CUPDOWN%2CFIVE_MINUTE%2COPEN%2CYESTCLOSE%2CHIGH%2CLOW%2CVOLUME%2CTURNOVER%2CHS%2CLB%2CWB%2CZF%2CPE%2CMCAP%2CTCAP%2CMFSUM%2CMFRATIO.MFRATIO2%2CMFRATIO.MFRATIO10%2CSNAME%2CCODE%2CANNOUNMT%2CUVSNEWS&sort=PERCENT&order=desc&count=24&type=query
    深:http://quotes.money.163.com/hs/service/diyrank.php?host=http%3A%2F%2Fquotes.money.163.com%2Fhs%2Fservice%2Fdiyrank.php&page=0&query=STYPE%3AEQA%3BEXCHANGE%3ACNSESZ&fields=NO%2CSYMBOL%2CNAME%2CPRICE%2CPERCENT%2CUPDOWN%2CFIVE_MINUTE%2COPEN%2CYESTCLOSE%2CHIGH%2CLOW%2CVOLUME%2CTURNOVER%2CHS%2CLB%2CWB%2CZF%2CPE%2CMCAP%2CTCAP%2CMFSUM%2CMFRATIO.MFRATIO2%2CMFRATIO.MFRATIO10%2CSNAME%2CCODE%2CANNOUNMT%2CUVSNEWS&sort=PERCENT&order=desc&count=24&type=query
    其中沪88页,深110页,提取出其中符合条件的股票代码
    '''
    p = re.compile('"CODE":"[0-9]*"')
    code_lst = []
    # 沪代码提取
    for i in range(88):
        print('CodeGet-', i)
        try:
            req = urllib.request.urlopen(f'http://quotes.money.163.com/hs/service/diyrank.php?host=http%3A%2F%2Fquotes.money.163.com%2Fhs%2Fservice%2Fdiyrank.php&page={i}&query=STYPE%3AEQA%3BEXCHANGE%3ACNSESH&fields=NO%2CSYMBOL%2CNAME%2CPRICE%2CPERCENT%2CUPDOWN%2CFIVE_MINUTE%2COPEN%2CYESTCLOSE%2CHIGH%2CLOW%2CVOLUME%2CTURNOVER%2CHS%2CLB%2CWB%2CZF%2CPE%2CMCAP%2CTCAP%2CMFSUM%2CMFRATIO.MFRATIO2%2CMFRATIO.MFRATIO10%2CSNAME%2CCODE%2CANNOUNMT%2CUVSNEWS&sort=PERCENT&order=desc&count=24&type=query').read().decode()
        except:
            print('failure-', i)
            continue
        for j in p.findall(req):
            t = j[-7:-1]
            if t.startswith('60'):
                code_lst.append(t)  # 毕竟68XXXX也买不了
        if random() < .7:
            time.sleep(5)
    # 深代码提取
    for i in range(110):
        print('CodeGet--', i)
        try:
            req = urllib.request.urlopen(f'http://quotes.money.163.com/hs/service/diyrank.php?host=http%3A%2F%2Fquotes.money.163.com%2Fhs%2Fservice%2Fdiyrank.php&page={i}&query=STYPE%3AEQA%3BEXCHANGE%3ACNSESZ&fields=NO%2CSYMBOL%2CNAME%2CPRICE%2CPERCENT%2CUPDOWN%2CFIVE_MINUTE%2COPEN%2CYESTCLOSE%2CHIGH%2CLOW%2CVOLUME%2CTURNOVER%2CHS%2CLB%2CWB%2CZF%2CPE%2CMCAP%2CTCAP%2CMFSUM%2CMFRATIO.MFRATIO2%2CMFRATIO.MFRATIO10%2CSNAME%2CCODE%2CANNOUNMT%2CUVSNEWS&sort=PERCENT&order=desc&count=24&type=query').read().decode()
        except:
            print('failure--', i)
            continue
        for j in p.findall(req):
            t = j[-7:-1]
            if t.startswith('00'):
                code_lst.append(t)
        if random() < .7:
            time.sleep(5)
    return code_lst

def DataGet(code: list):
    '''
    这里还是用网易财经的接口
    http://quotes.money.163.com/service/chddata.html?code={}&start=20220601&end=20220702&fields=TCLOSE;HIGH;LOW;TOPEN;LCLOSE;CHG;PCHG;TURNOVER;VOTURNOVER;TCAP;MCAP
    因为只需要涨跌幅和换手率,所以只查询PCHG和TURNOVER两个字段就行
    通过urllib.request.urlretrieve将数据保存于本地data文件夹
    '''
    for i in code:
        print(i)
        try:
            if i[0] == '0':
                urllib.request.urlretrieve(f'http://quotes.money.163.com/service/chddata.html?code=1{i}&start=20220601&end=20220702&fields=PCHG;TURNOVER', f'data\\{i}.csv')
            elif i[0] == '6':
                urllib.request.urlretrieve(f'http://quotes.money.163.com/service/chddata.html?code=0{i}&start=20220601&end=20220702&fields=PCHG;TURNOVER', f'data\\{i}.csv')                
        except:
            pass

if __name__ == '__main__':
    DataGet(CodeGet())

        写到这里先运行一下，发现请求频率有点过快，加个睡眠随机时间，再次运行共获得3015个文件

数据分析部分

        首先看一下，换手率3%~5%且涨幅3%~7%的股票下一个交易日的涨跌幅情况，单个数据形式是这样的

import matplotlib.pyplot as plt
import pandas as pd
import os

lst = []

for i in os.listdir('data'):
    try:
        data = pd.read_csv(f'data\\{i}', encoding = 'utf-8').values
    except UnicodeDecodeError:
        try:
            data = pd.read_csv(f'data\\{i}', encoding = 'gbk').values
        except:
            continue
    for j in range(len(data) - 1, 0, -1):
        try:
            if (3 <= data[j, 3] <= 7) and (3 <= data[j, 4] <= 5):
                lst.append(data[j - 1, 3])
        except:
            pass

print(sum(lst) / len(lst))  # -0.011

plt.hist(lst, bins = 50)

plt.show()

        emmmmm，基本上是正态的，但可以看到涨停的数量有些异常，再看下细分的统计情况

from collections import defaultdict
import matplotlib.pyplot as plt
import pandas as pd
import os

# 这里打算把当日涨跌幅分为5类[-10, -6, -2, 2, 6, 10] → [-2, -1, 0, 1, 2]
# 当日换手率分为5类[0, 1, 3, 5, 10] → [0, 1, 2, 3, 4]
def cal(pchg, turnover):
    '''
    接收涨跌幅和换手率返回相应类别
    '''
    if pchg <= -6:
        p = -2
    elif pchg <= -2:
        p = -1
    elif pchg <= 2:
        p = 0
    elif pchg <= 6:
        p = 1
    else:
        p = 2
    if turnover <= 1:
        t = 0
    elif turnover <= 3:
        t = 1
    elif turnover <= 5:
        t = 2
    elif turnover <= 10:
        t = 3
    else:
        t = 4
    return (p, t)

dic = defaultdict(list)

for i in os.listdir('data'):
    try:
        data = pd.read_csv(f'data\\{i}', encoding = 'utf-8').values
    except UnicodeDecodeError:
        try:
            data = pd.read_csv(f'data\\{i}', encoding = 'gbk').values
        except:
            continue
    for j in range(len(data) - 1, 0, -1):
        try:
            key = cal(data[j, 3], data[j, 4])
            if data[j - 1, 3].__class__.__name__ == 'float':
                dic[key].append(data[j - 1, 3])
        except:
            pass

for k, v in dic.items():
    print(f'{k}:{sum(v) / len(v):.2f}')

'''
(0, 0):0.33
(-1, 0):0.76
(1, 1):0.26
(1, 0):0.27
(-1, 1):0.79
(0, 1):0.29
(2, 1):1.66
(1, 3):-0.33
(1, 2):-0.00
(-1, 2):0.49
(2, 3):0.80
(0, 2):0.24
(-1, 3):0.31
(0, 3):-0.08
(2, 2):0.61
(-2, 2):0.84
(2, 4):0.06
(0, 4):-0.20
(-1, 4):-0.32
(1, 4):-0.85
(-2, 3):-0.35
(-2, 1):0.58
(-2, 4):-1.35
(2, 0):4.25
(-2, 0):-4.44
'''

fig = plt.figure()

n = 1

for i in (-2, -1, 0, 1, 2):
    for j in range(5):
        ax = fig.add_subplot(5, 5, n)
        if (i, j) in dic:
            ax.hist(dic[(i, j)], label = f'pchg({i})-turnover({j})')
            ax.legend()
        n += 1

plt.show()

        至此可以对策略进行些许修正：当日涨幅在6%以上，并且换手率小于3%时，下一交易日的期望涨幅较高

模型拟合部分

        通过一系列机器学习模型对数据进行拟合，保留表现最好的模型，并根据期预测结果作图

import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from random import random
from sklearn.linear_model import SGDRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.ensemble import RandomForestRegressor, BaggingRegressor, ExtraTreesRegressor, AdaBoostRegressor, GradientBoostingRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.metrics import mean_squared_error

X_train, y_train, X_test, y_test = [], [], [], []

for i in os.listdir('data'):
    try:
        data = pd.read_csv(f'data\\{i}', encoding = 'utf-8').values
    except UnicodeDecodeError:
        try:
            data = pd.read_csv(f'data\\{i}', encoding = 'gbk').values
        except:
            pass
    for j in range(len(data) - 1, 0, -1):
        try:
            if data[j, 3].__class__.__name__ == 'float' and data[j, 4].__class__.__name__ == 'float' and data[j - 1, 3].__class__.__name__ == 'float':
                if random() < 0.7:
                    X_train.append([data[j, 3], data[j, 4]])
                    y_train.append(data[j - 1, 3])
                else:
                    X_test.append([data[j, 3], data[j, 4]])
                    y_test.append(data[j - 1, 3])
        except:
            pass

X = X_train + X_test
y = y_train + y_test

model, mse = None, np.inf

for mod in (SGDRegressor, KNeighborsRegressor, RandomForestRegressor, BaggingRegressor, ExtraTreesRegressor, AdaBoostRegressor, GradientBoostingRegressor, DecisionTreeRegressor):
    model_tmp = mod()
    model_tmp.fit(X_train, y_train)
    mse_tmp = mean_squared_error(model_tmp.predict(X_test), y_test)
    if mse_tmp < mse:
        mse = mse_tmp
        model = model_tmp

pchg = np.arange(-10, 10, 0.2)
turnover = np.arange(0, 10, 0.1)
z = np.array([[model.predict(np.array([pchg[i], turnover[j]]).reshape(1, -1))[0] for i in range(100)] for j in range(100)])

pchg_, turnover_, z_ = [], [], []

for p in pchg:
    for t in turnover:
        pchg_.append(p)
        turnover_.append(t)
        z_.append(model.predict(np.array([p, t]).reshape(1, -1))[0])

scatter_data = pd.DataFrame({'pchg': pchg_, 'turnover': turnover_, 'z': z_})
scatter_data.plot.scatter('pchg', 'turnover', c = 'z', colormap = 'jet')
plt.show()  # 散点图

pchg, turnover = np.meshgrid(pchg, turnover)

# 表面图
fig = plt.figure()
ax = fig.gca(projection = '3d')
ax.plot_surface(pchg, turnover, z, alpha = 0.3)
plt.show()

        效果一般，但仍不难看出高涨幅和低换手率带来的下一交易日的期望涨幅较大

最后

        本文仅为过去一月的历史数据分析，无法明确已有规律能否在未来数据上生效(机器学习难以回答的问题)，因此并不构成投资建议。