Python 股票量化学习（未完）

目录

一、读取某列数据

二、获取数据

三、区分数据集

四、归一化

---

一、读取某列数据

import numpy as np
import tushare as ts
import pandas as pd
import matplotlib.pyplot as plt
df_base = ts.get_stock_basics()
df_base[['pe','pb']]

二、获取数据

https://www.joinquant.com/help/api/help?name=Stock#%E8%B4%A2%E5%8A%A1%E6%8C%87%E6%A0%87%E6%95%B0%E6%8D%AE

import numpy as np
import tushare as ts
import pandas as pd
from pandas import Series, DataFrame
from sklearn.model_selection import train_test_split
from IPython.core.interactiveshell import InteractiveShell 
InteractiveShell.ast_node_interactivity = 'all' #默认为'last'

#换手率、市盈率、市净率、市销率、市现率、销售净利率、ROE、ROA、营业收入同比增长率
q = query(
      valuation,indicator
  )
ret = get_fundamentals(q,statDate='2015')
#ret
data=ret[['code','turnover_ratio','pe_ratio','pb_ratio','ps_ratio','pcf_ratio','net_profit_margin','roe','roa','inc_revenue_year_on_year']]

ret
#数据处理
leng=len(data['code'])


#获取价格、成交量、计算收益率
price_rate=pd.DataFrame()
for i in range(leng):
    price_open=get_price(data.iloc[i,0], start_date='2015-12-01', end_date='2015-12-31', frequency='31d',fields='open')
    price_close=get_price(data.iloc[i,0], start_date='2015-12-01', end_date='2015-12-31', frequency='31d',fields='close')
    volume=get_price(data.iloc[i,0], start_date='2015-12-01', end_date='2015-12-31', frequency='31d',fields='volume')
    rate=(price_close.iloc[0,0]-price_open.iloc[0,0])/price_open.iloc[0,0]
    rate=pd.DataFrame({'code':[data.iloc[i,0]],'volume':[volume.iloc[0,0]],'rate':[rate]})
    rate.index = Series([i])
    price_rate=pd.concat([price_rate,rate])
price_rate.loc[price_rate.rate > 0.2, 'rate'] = 1
price_rate.loc[price_rate.rate < 0.2, 'rate'] = 0
#price_rate

#整合数据、删除代码、删除缺失值
final_date=pd.merge(data,price_rate)
final_date1=final_date.dropna()
del final_date1['code']
final_date1

三、区分数据集

final_date1 -= final_date1.min()
final_date1 /= final_date1.max()
final_date2=final_date1.values
X=final_date2[:,:-1]
y=final_date2[:,-1]
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

四、归一化

#0-1（X为array）
X-= X.min()
X/= X.max()

#Z-score标准化(X为array)
mu=np.average(X)
sigma=np.std(X)
X= (X- mu) / sigma;