对股票历史数据OHCLV转换为金融技术指标

显然，股票的OHCL为高相关性的数据（Open,High,Close,Low），喂给神经网络时会带来较少的信息，本文介绍了两种将OHCLV转化为金融技术指标的办法，从而减少相关性，更好的描述动态，复杂的，非线性的，充满噪音的股票市场。

首先本文使用调用tushare库提取股票历史数据。

pip  install tushare

#获取使用接口
def get_token():
    ts.set_token("xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")
    pro=ts.pro_api()
    return pro

##获取数据列表
def get_data_list(cursor,sql,conn):
    cursor.execute(sql)
    res=cursor.fetchall()
    conn.commit()
    ts_codes_list=list(res)
    ts_codes_list=[",".join(list(x)) for x in ts_codes_list]
    return ts_codes_list
##获取数据
def get_data(ts_codes_list,pro):
    daily=pd.DataFrame(columns=["ts_code","trade_date","open","close","high","low","volume"]) ##获取相应的列信息
    for i in range(0,len(ts_codes_list),100):  
        j=i+100
        if(j>=len(ts_codes_list)):
            j=len(ts_codes_list)
        name=",".join(ts_codes_list[i:j])
        part= pro.daily(ts_code=name, trade_date=get_date())[["ts_code","trade_date","open","close","high","low","volume"]]
        daily=pd.concat([daily,part],ignore_index=True) 
    daily["trade_date"]=daily["trade_date"].apply(get_date_format)
    return daily

其次，第一种办法是使用TA库

pip  install TA

data = add_all_ta_features(df, "open", "high", "low", "close", "volume", fillna=True) 
        print("Added TA Features...")
        data = data.reset_index(drop=True)

data.columns

Index(['date', 'open', 'high', 'low', 'close', 'volume', 'tic', 'day',
       'volume_adi', 'volume_obv', 'volume_cmf', 'volume_fi', 'volume_mfi',
       'volume_em', 'volume_sma_em', 'volume_vpt', 'volume_nvi', 'volume_vwap',
       'volatility_atr', 'volatility_bbm', 'volatility_bbh', 'volatility_bbl',
       'volatility_bbw', 'volatility_bbp', 'volatility_bbhi',
       'volatility_bbli', 'volatility_kcc', 'volatility_kch', 'volatility_kcl',
       'volatility_kcw', 'volatility_kcp', 'volatility_kchi',
       'volatility_kcli', 'volatility_dcl', 'volatility_dch', 'volatility_dcm',
       'volatility_dcw', 'volatility_dcp', 'volatility_ui', 'trend_macd',
       'trend_macd_signal', 'trend_macd_diff', 'trend_sma_fast',
       'trend_sma_slow', 'trend_ema_fast', 'trend_ema_slow', 'trend_adx',
       'trend_adx_pos', 'trend_adx_neg', 'trend_vortex_ind_pos',
       'trend_vortex_ind_neg', 'trend_vortex_ind_diff', 'trend_trix',
       'trend_mass_index', 'trend_cci', 'trend_dpo', 'trend_kst',
       'trend_kst_sig', 'trend_kst_diff', 'trend_ichimoku_conv',
       'trend_ichimoku_base', 'trend_ichimoku_a', 'trend_ichimoku_b',
       'trend_visual_ichimoku_a', 'trend_visual_ichimoku_b', 'trend_aroon_up',
       'trend_aroon_down', 'trend_aroon_ind', 'trend_psar_up',
       'trend_psar_down', 'trend_psar_up_indicator',
       'trend_psar_down_indicator', 'trend_stc', 'momentum_rsi',
       'momentum_stoch_rsi', 'momentum_stoch_rsi_k', 'momentum_stoch_rsi_d',
       'momentum_tsi', 'momentum_uo', 'momentum_stoch',
       'momentum_stoch_signal', 'momentum_wr', 'momentum_ao', 'momentum_kama',
       'momentum_roc', 'momentum_ppo', 'momentum_ppo_signal',
       'momentum_ppo_hist', 'others_dr', 'others_dlr', 'others_cr'],
      dtype='object')

第二种使用stockstats库进行对OHCLV的转换。

from stockstats import StockDataFrame as Sdf

df = data.copy()
df = df.sort_values(by=['tic','date'])
stock = Sdf.retype(df.copy())
unique_ticker = stock.tic.unique()
for indicator in self.tech_indicator_list:
       indicator_df = pd.DataFrame()
       for i in range(len(unique_ticker)):
                try:
                    temp_indicator = stock[stock.tic == unique_ticker[i]][indicator]
                    temp_indicator = pd.DataFrame(temp_indicator)
                    temp_indicator['tic'] = unique_ticker[i]
                    temp_indicator['date'] = df[df.tic == unique_ticker[i]]['date'].to_list()
                    indicator_df = indicator_df.append(
                        temp_indicator, ignore_index=True
                    )
                except Exception as e:
                    print(e)
        df =df.merge(indicator_df[['tic','date',indicator]],on=['tic','date'],how='left')
df = df.sort_values(by=['date','tic'])