def cal_factor_return(self, sf_ids):
sfs = []
for sf_id in sf_ids:
sfs.append(
StockFactor.subclass(sf_id, StockFactor.stock_factors[sf_id]))
close = StockAsset.all_stock_nav()
ret = close.pct_change()
ret = ret[StockAsset.all_stock_info().index]
dates = ret.index
dates = dates[dates > '2000-01-01']
df_ret = pd.DataFrame(columns=sf_ids)
df_sret = pd.DataFrame(columns=StockAsset.all_stock_info().index)
for date, next_date in zip(dates[:-1], dates[1:]):
print 'cal_factor_return:', date
tmp_exposure = {}
tmp_ret = ret.loc[next_date].values
for sf in sfs:
tmp_exposure[sf.factor_id] = sf.exposure.loc[date]
tmp_exposure_df = pd.DataFrame(tmp_exposure)
tmp_exposure_df = tmp_exposure_df[sf_ids].fillna(0.0)
tmp_exposure_df = tmp_exposure_df.loc[
StockAsset.all_stock_info().index]
mod = sm.OLS(tmp_ret, tmp_exposure_df.values, missing='drop').fit()
df_ret.loc[next_date] = mod.params
df_sret.loc[next_date] = tmp_ret - np.dot(tmp_exposure_df.values,
mod.params)
return df_ret, df_sret
def cal_earning(self, stock_id):
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
stock_quote = StockAsset.get_stock(stock_id).quote
p = stock_quote.tclose
pe = stock_fdmt.pettm
eps = p / pe
return eps
def cal_indexposure(self, stock_id):
stock_quote = StockAsset.get_stock(stock_id).quote
stock_info = StockAsset.all_stock_info()
sf = pd.DataFrame(index=stock_quote.index)
sf_ind = stock_info.loc[stock_id].sk_swlevel1code
if sf_ind == self.sf_ind:
sf_exposure = 1
else:
sf_exposure = 0
sf['exposure'] = sf_exposure
return sf.exposure
def cal_halpha(self, stock_id):
stock_quote = StockAsset.get_stock(stock_id).quote
close = stock_quote.tcloseaf
close = close.replace(0.0, method='pad')
ret = close.pct_change()
sz = Asset.load_nav_series('120000016')
bret = sz.pct_change()
ret = ret.resample('m').sum().iloc[:-1]
bret = bret.resample('m').sum().iloc[:-1]
common_index = ret.index.intersection(bret.index)
ret = ret.loc[common_index]
bret = bret.loc[common_index]
ser = pd.Series()
if len(common_index) < 60:
return ser
for i in range(60, len(common_index)):
tmp_dates = common_index[i - 59:i + 1]
y = ret.loc[tmp_dates].values
x = bret.loc[tmp_dates].values.reshape(-1, 1)
mod = LinearRegression().fit(x, y)
ser.loc[tmp_dates[-1]] = mod.intercept_
today = get_today()
ser.loc[today] = np.nan
ser = ser.resample('d').last().fillna(method='pad')
return ser
def cal_dastd(self, stock_id, period=23):
stock_quote = StockAsset.get_stock(stock_id).quote
close = stock_quote.tclose
close = close.replace(0.0, method='pad')
ret = close.pct_change()
ret = ret.rolling(period).apply(lambda x: pow(pow(x, 2).mean(), 0.5))
return ret
def cal_factor_return(self, sf_ids):
period = 21
sfs = []
for sf_id in sf_ids:
sfs.append(
StockFactor.subclass(sf_id, StockFactor.stock_factors[sf_id]))
close = StockAsset.all_stock_nav()
ret = close.pct_change(period).iloc[period:]
ret = ret[StockAsset.all_stock_info().index]
dates = ret.index
dates = dates[dates >= '2005-01-01']
df_ret = pd.DataFrame(columns=sf_ids)
df_sret = pd.DataFrame(columns=StockAsset.all_stock_info().index)
pool = Pool(len(sfs))
sfs = pool.map(multiprocess_load_factor_exposure, sfs)
pool.close()
pool.join()
for date, next_date in zip(dates[:-period], dates[period:]):
tmp_exposure = {}
tmp_ret = ret.loc[next_date].values
for sf in sfs:
tmp_exposure[sf.factor_id] = sf.exposure.loc[date]
#tmp_exposure[sf.factor_id] = fed[sf.factor_id].loc[date]
tmp_exposure_df = pd.DataFrame(tmp_exposure)
tmp_exposure_df = tmp_exposure_df[sf_ids].fillna(0.0)
tmp_exposure_df = tmp_exposure_df.loc[
StockAsset.all_stock_info().index]
mod = sm.OLS(tmp_ret, tmp_exposure_df.values, missing='drop').fit()
# mod = sm.WLS(tmp_ret, tmp_exposure_df.values, weights = tmp_amount, missing = 'drop').fit()
# print(mod.summary())
df_ret.loc[next_date] = mod.params
df_sret.loc[next_date] = tmp_ret - np.dot(tmp_exposure_df.values,
mod.params)
return df_ret, df_sret
def cal_mom(self, stock_id, period=23):
stock_quote = StockAsset.get_stock(stock_id).quote
close = stock_quote.tclose
close = close.replace(0.0, method='pad')
ret = close.pct_change()
tr = stock_quote.turnrate
ret_tr = (ret * tr).rolling(period).sum()
weight = tr.rolling(period).sum()
# mom = ret.rolling(period).mean()
mom = ret_tr / weight
return mom
def cal_hilo(self, stock_id, period=23):
stock_quote = StockAsset.get_stock(stock_id).quote
high = stock_quote.thigh
high = high.replace(0.0, method='pad')
hi = high.rolling(period).max()
low = stock_quote.tlow
low = low.replace(0.0, method='pad')
lo = low.rolling(period).min()
hilo = np.log(hi / low)
return hilo
def cal_egro(self, stock_id):
def cal_egro_single(x):
mod = LinearRegression().fit(np.arange(5).reshape(-1, 1), x)
return mod.coef_[0] / np.mean(x)
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
stock_quote = StockAsset.get_stock(stock_id).quote
p = stock_quote.tclose
pe = stock_fdmt.pettm
eps = p / pe
eps = eps[eps.diff() > 0.001]
eps_y = pd.Series()
for k, v in eps.groupby(eps.index.strftime('%Y')):
eps_y.loc[v.index[-1]] = v.values[-1]
eps_y = eps_y.rolling(5).apply(cal_egro_single)
today = datetime.now()
today_idx = pd.tslib.Timestamp(today.year, today.month, today.day)
eps_y.loc[today_idx] = np.nan
eps_y = eps_y.resample('d').last().fillna(method='pad').dropna()
return eps_y
def cal_cmra(self, stock_id):
stock_quote = StockAsset.get_stock(stock_id).quote
close = stock_quote.tcloseaf
close = close.replace(0.0, method='pad')
nav = close / close.iloc[0]
zt = np.log(nav)
zt_max = zt.rolling(window=252 * 5).max()
zt_min = zt.rolling(window=252 * 5).min()
cmra = np.log((1 + zt_max) / (1 + zt_min))
cmra = cmra.fillna(method='pad')
cmra = cmra.dropna()
return cmra
def cal_factor_exposure(self):
all_stocks = StockAsset.all_stock_info()
factor_exposure = []
for desc_method in self.desc_methods:
stock_exposure = {}
for stock_id in all_stocks.index:
stock_exposure[stock_id] = desc_method(stock_id)
stock_exposure_df = pd.DataFrame(stock_exposure)
stock_exposure_df = StockFactor.stock_factor_filter(
stock_exposure_df)
stock_exposure_df = StockFactor.normalized(stock_exposure_df)
factor_exposure.append(stock_exposure_df)
factor_exposure_df = reduce(lambda x, y: x + y,
factor_exposure) / len(factor_exposure)
factor_exposure_df = factor_exposure_df[all_stocks.index]
self.exposure = factor_exposure_df
return factor_exposure_df
def cal_btsg(self, stock_id):
stock_quote = StockAsset.get_stock(stock_id).quote
close = stock_quote.tcloseaf
close = close.replace(0.0, method='pad')
ret = close.pct_change()
sz = Asset.load_nav_series('120000016')
bret = sz.pct_change()
ret = ret.resample('m').sum().iloc[:-1]
bret = bret.resample('m').sum().iloc[:-1]
common_index = ret.index.intersection(bret.index)
ret = ret.loc[common_index]
bret = bret.loc[common_index]
ser = pd.Series()
if len(common_index) < 60:
return ser
for i in range(60, len(common_index)):
tmp_dates = common_index[:i + 1]
y = ret.loc[tmp_dates].values
x = bret.loc[tmp_dates].values.reshape(-1, 1)
x = sm.add_constant(x)
mod = sm.OLS(y, x).fit()
beta = mod.params[1]
sigma = mod.resid.std()
btsg = pow(beta * sigma, 0.5)
ser.loc[tmp_dates[-1]] = btsg
today = get_today()
ser.loc[today] = np.nan
ser = ser.resample('d').last().fillna(method='pad')
return ser
def cal_equtotliab(self, stock_id):
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
equtotliab = stock_fdmt.equtotliab
return equtotliab
def cal_ltmliabtota(self, stock_id):
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
ltmliabtota = stock_fdmt.ltmliabtota
return ltmliabtota
def cal_cashrt(self, stock_id):
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
cashrt = stock_fdmt.cashrt
return cashrt
def cal_currentrt(self, stock_id):
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
currentrt = stock_fdmt.currentrt
return currentrt
def cal_sgpmargin(self, stock_id):
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
sgpmargin = stock_fdmt.sgpmargin
return sgpmargin
def cal_roa(self, stock_id):
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
roa = stock_fdmt.roa
return roa
def cal_bp(self, stock_id):
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
bp = 1 / stock_fdmt.pb
return bp
def cal_turnover(self, stock_id, period=23):
stock_quote = StockAsset.get_stock(stock_id).quote
tr = stock_quote.turnrate
tr = tr.rolling(period).mean()
return tr
def cal_size(self, stock_id):
stock_quote = StockAsset.get_stock(stock_id).quote
totmktcap = stock_quote.totmktcap
return totmktcap
def cal_roe(self, stock_id):
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
roe = stock_fdmt.roedilutedcut
return roe
def cal_ep(self, stock_id):
stock_fdmt = StockAsset.get_stock(stock_id).fdmt
ep = 1 / stock_fdmt.pettm
return ep
def valid_stock_table():
all_stocks = StockAsset.all_stock_info()
all_stocks = all_stocks.reset_index()
all_stocks = all_stocks.set_index(['sk_secode'])
st_stocks = StockAsset.stock_st()
all_stocks.sk_listdate = all_stocks.sk_listdate + timedelta(365)
engine = database.connection('caihui')
Session = sessionmaker(bind=engine)
session = Session()
sql = session.query(asset_stock.tq_qt_skdailyprice.tradedate,
asset_stock.tq_qt_skdailyprice.secode,
asset_stock.tq_qt_skdailyprice.tclose,
asset_stock.tq_qt_skdailyprice.amount).filter(
asset_stock.tq_qt_skdailyprice.secode.in_(
all_stocks.index)).statement
#过滤停牌股票
quotation_amount = pd.read_sql(sql,
session.bind,
index_col=['tradedate', 'secode'],
parse_dates=['tradedate'])
quotation = quotation_amount[['tclose']]
quotation = quotation.replace(0.0, np.nan)
quotation = quotation.unstack()
quotation.columns = quotation.columns.droplevel(0)
#60个交易日内需要有25个交易日未停牌
quotation_count = quotation.rolling(60).count()
quotation[quotation_count < 25] = np.nan
#过滤掉过去一年日均成交额排名后20%的股票
amount = quotation_amount[['amount']]
amount = amount.unstack()
amount.columns = amount.columns.droplevel(0)
year_amount = amount.rolling(252, min_periods=100).mean()
def percentile20nan(x):
x[x <= np.percentile(x, 20)] = np.nan
return x
year_amount = year_amount.apply(percentile20nan, axis=1)
quotation[year_amount.isnull()] = np.nan
session.commit()
session.close()
#过滤st股票
for i in range(0, len(st_stocks)):
secode = st_stocks.index[i]
record = st_stocks.iloc[i]
selecteddate = record.selecteddate
outdate = record.outdate
if secode in set(quotation.columns):
#print secode, selecteddate, outdate
quotation.loc[selecteddate:outdate, secode] = np.nan
#过滤上市未满一年股票
for secode in all_stocks.index:
if secode in set(quotation.columns):
quotation.loc[:all_stocks.loc[secode, 'sk_listdate'],
secode] = np.nan
quotation = quotation.rename(
columns=dict(zip(all_stocks.index, all_stocks.globalid)))
asset_stock_factor.update_valid_stock_table(quotation)