def get_stock_returns(stocks, start_date, end_date, freq):
close_price = Parallel(n_jobs=10, backend='threading', verbose=5)(
delayed(csf.get_stock_hist_bar)(code, freq,
start_date=start_date,
end_date=end_date,
field=['date', 'close'])
for code in stocks)
for start_date, p in zip(stocks, close_price):
p['tick'] = start_date
close_price = pd.concat(close_price)
close_price = close_price.dropna()
# index.name原来为空
close_price.index.name = 'dt'
# 转成一个frame, index:dt, columns:tick
close_price = (close_price.set_index('tick', append=True)
.to_panel()['close']
.sort_index()
.fillna(method='ffill')
)
# 取每个周期末
group_key = {'M': [close_price.index.year, close_price.index.month],
'W': [close_price.index.year, close_price.index.week],
'Q': [close_price.index.year, close_price.index.quarter]
}
close_price = close_price.groupby(group_key[freq]).tail(1)
returns = close_price.pct_change().shift(-1).dropna(axis=1, how='all')
returns.index = returns.index.map(lambda dt: str(dt.date()))
returns.index.name = 'date'
returns = returns.unstack().to_frame()
returns.columns = ['ret']
returns = returns.swaplevel(0, 1).sort_index()
returns.index.names = ['date', 'code']
return returns
