通过聚类算法分析股票，选股的策略代码如下（一）！

主要是用于分类选股，没有太多特别

1、这里用的是涨跌幅做聚类，特征并不多！
2、时间只是分析了2023年至今的分类情况！
3、这里博主K-mean选了10类，可以根据自己需求更改！

这个有什么用呢？
1、对冲关系的股票必定是存在两种不同聚类之中！
2、K-mean选2类，大家可是看看是不是大市值和小市值这两类！
3、热门股票们（龙头们）是会有聚类现象的，可以辅助分析！

from jqdata import *
from jqfactor import *
import jqdata
from jqfactor import *
import pandas as pd

import numpy as np
from sklearn.model_selection import train_test_split
from xgboost import XGBClassifier
import matplotlib.pyplot as plt
import jqdata
from jqfactor import *
from tqdm import tqdm
import warnings
warnings.filterwarnings("ignore")
import numpy as np
import pandas as pd
from pandas.tseries.offsets import CustomBusinessDay
# from datetime import datetime
import datetime
import xgboost as xgb
import talib
from sklearn.preprocessing import StandardScaler         

current_date = datetime.datetime.now()
current_time = current_date.strftime("%Y-%m-%d")

#去除上市距beginDate不足3个月的股票
def delect_stop(stocks,beginDate,n=365):
    stockList=[]
    beginDate = datetime.datetime.strptime(beginDate, "%Y-%m-%d")
    for stock in stocks:
        start_date=get_security_info(stock).start_date
        if start_date<(beginDate-datetime.timedelta(days=n)).date():
            stockList.append(stock)
    return stockList
#获取股票池
def get_stock(stockPool,begin_date):
    if stockPool=='HS300':
        stockList=get_index_stocks('000300.XSHG',begin_date)
    elif stockPool=='ZZ500':
        stockList=get_index_stocks('399905.XSHE',begin_date)
    elif stockPool=='ZZ800':
        stockList=get_index_stocks('399906.XSHE',begin_date)   
    elif stockPool=='CYBZ':
        stockList=get_index_stocks('399006.XSHE',begin_date)
    elif stockPool=='ZXBZ':
        stockList=get_index_stocks('399005.XSHE',begin_date)
    elif stockPool=='A':
        stockList=get_index_stocks('000002.XSHG',begin_date)+get_index_stocks('399107.XSHE',begin_date)
        stockList = [stock for stock in stockList if not stock.startswith(('3', '68', '4', '8'))]
    elif stockPool=='AA':
        stockList=get_index_stocks('000985.XSHG',begin_date)
        stockList = [stock for stock in stockList if not stock.startswith(('3', '68', '4', '8'))]

    #剔除ST股
    st_data=get_extras('is_st',stockList, count = 1,end_date=begin_date)
    stockList = [stock for stock in stockList if not st_data[stock][0]]
    #剔除停牌、新股及退市股票
    stockList=delect_stop(stockList,begin_date)
    return stockList

stockList=get_stock('AA',current_time)


_end_date = current_date + datetime.timedelta(-2)
_end_date = _end_date.strftime("%Y-%m-%d")
print(_end_date)

DATA = []
for i in stockList:
    df = get_price(i,  frequency='1d', 
                   start_date='2023-01-01',
                   end_date=_end_date,
    #                fields=['open','close','high','low']
                   fields=['close']
                  )

    df['returns'] = df['close'].pct_change() * 100
    df = df.dropna()
#     print(df)
    # 将收益率转换为 NumPy 数组
    returns_array = df['returns'].values
    DATA.append(returns_array)

DATA = np.array(DATA)
print(DATA.shape)
max_value = np.max(DATA)
min_value = np.min(DATA)
nan_count = np.isnan(DATA).sum()

print("数组中包含 NaN 的数量:", nan_count)
print("最大值:", max_value)
print("最小值:", min_value)

2023-12-12
(3032, 228)
数组中包含 NaN 的数量: 0
最大值: 10.465116279069765
最小值: -10.416666666666663

import numpy as np
import matplotlib.pyplot as plt
from sklearn.manifold import TSNE

# 使用 t-SNE 进行降维
tsne = TSNE(n_components=2, random_state=42)
embedded_data = tsne.fit_transform(DATA)
print(embedded_data.shape)

# 创建一个散点图进行可视化
plt.scatter(embedded_data[:, 0], embedded_data[:, 1], marker='.', alpha=0.5)
plt.title('t-SNE Visualization')
plt.show()

未完，详见下一篇

...