def default_china_equity_universe_mask(unmask, asset_finder=None):
#a_stocks = []
info = load_tushare_df("basic")
sme = load_tushare_df("sme")
gem = load_tushare_df("gem")
st = load_tushare_df("st")
uset = pd.concat([sme, gem, st])
try:
maskdf = info.drop([y for y in uset['code']],
axis=0) # st,sme,gem 的都不要，稳健型只要主板股票
maskdf = maskdf.drop(unmask, axis=0)
except:
pass
#Returns a factor indicating membership (=1) in the given iterable of securities
#print("==enter IsInSymbolsList==")
def _sid(sid):
return asset_finder.retrieve_asset(sid)
class IsInDefaultChinaUniverse(CustomFilter):
inputs = []
window_length = 1
def compute(self, today, asset_ids, out, *inputs):
#print asset_ids
#print maskset
if asset_finder != None:
assets = [_sid(id).symbol for id in asset_ids]
else:
assets = [sid(id).symbol for id in asset_ids]
#print "--------------"
#print pd.Series(assets)
out[:] = pd.Series(assets).isin(maskdf.index)
#print out
return IsInDefaultChinaUniverse()
def get_sector(sector_dict=None):
if sector_dict is None:
sector_dict = get_sector_class()
#print("++enter getSector++",len(sector_dict))
basic = load_tushare_df("basic")
class Sector(CustomClassifier): #CustomClassifier 是int , factor 是float
inputs = []
window_length = 1
dtype = np.int64
missing_value = 0
#result[isnan(result)] = self.missing_value
#params = ('universes',)
def findSector(self, assets):
sector_list = []
for msid in assets:
stock = sid(msid).symbol
try:
industry = basic.loc[stock].industry
sector_no = sector_dict[industry]
sector_list.append(sector_no)
except:
#print "stock %s in industry %s not find in default sector set, set zero" % (stock,industry)
sector_list.append(self.missing_value)
else:
pass
return sector_list
def compute(self, today, assets, out, *inputs):
out[:] = self.findSector(assets)
return Sector()
def get_sector_class(limit_size=Sector_TOPN, umask=Sector_Umask):
df = load_tushare_df("basic")
df = df[-df['industry'].isin(umask)] # 排除给定行
industryClass = {}
no = Sector_StartNo
#for industry,_ in load_tushare_df("industry").groupby('c_name'):
for industry, _ in df.groupby('industry').industry.value_counts().nlargest(
limit_size).iteritems():
industryClass[industry[0]] = no
no = no + 1
return industryClass
def get_sectors_no(mids):
basic = load_tushare_df("basic")
_class, _ = get_sector_class()
no_ = []
missing_value = 0
for msid in mids:
stock = sid(msid).symbol
try:
industry = basic.loc[stock].industry
sector_no = _class[industry]
no_.append(sector_no)
except:
# print "stock %s in industry %s not find in default sector set, set zero" % (stock,industry)
no_.append(missing_value)
return no_
def get_sector_by_onehot(sector_dict=None, mask=None, asset_finder=None):
if sector_dict is None:
sector_dict, _ = get_sector_class()
basic = load_tushare_df("basic")
def _sid(sid):
return asset_finder.retrieve_asset(sid)
def _onehot_sectors(sector_keys):
##- Convert the Sectors column into binary labels
sector_binarizer = preprocessing.LabelBinarizer()
strlbls = map(
str, sector_keys
) # LabelBinarizer didn't like float values, so convert to strings
sector_binarizer.fit(strlbls)
sector_labels_bin = sector_binarizer.transform(
strlbls) # this is now 12 binary columns from 1 categorical
##- Create a pandas dataFrame from the new binary labels
#print(sector_labels_bin)
colNames = []
for i in range(len(sector_labels_bin[0])):
colNames.append("S_L_" + strlbls[i]) # TODO
sLabels = pd.DataFrame(data=sector_labels_bin,
index=strlbls,
columns=colNames)
return sLabels
sector_indict, sector_rindict = get_sector_class() #TODO ORDERDICT????
sector_indict_keys = sector_indict.keys()
sector_indict_keys.sort()
onehot_sector = _onehot_sectors(sector_indict_keys)
#print sector_indict
#print sector_inddict
#print onehot_sector
class OneHotSector(CustomFactor): #CustomClassifier 是int , factor 是float
inputs = []
window_length = 1
outputs = sector_indict_keys
def _find_sector(self, asset):
sector_no = 0
sector_name = ""
if asset_finder != None:
stock = _sid(asset).symbol
else:
stock = sid(asset).symbol
try:
industry = basic.loc[stock].industry
sector_no = sector_dict[industry]
sector_name = industry
except:
#print "stock %s in not find in default sector set, set zero" % (stock)
pass
else:
pass
return sector_no, sector_name
def compute(self, today, assets, out):
idx = 0
for asset in assets:
sno, sname = self._find_sector(asset)
if sno != 0:
onehots = onehot_sector.loc[sname]
#print onehots
i = 0
for output in self.outputs:
if sno != 0:
#print ("++++",idx,output,onehots.values[i])
out[idx][output] = int(onehots.values[i])
else:
out[idx][output] = 0
i += 1
idx += 1
#print out
if mask != None:
return OneHotSector(mask=mask), sector_indict_keys
else:
return OneHotSector(), sector_indict_keys
def Fundamental(asset_finder = None):
def _sid(sid):
return asset_finder.retrieve_asset(sid)
columns = ['pe', # 市盈率
'outstanding', # 流通股本(亿)
'totals', # 总股本(亿)
'totalAssets', # 总资产(万)
'liquidAssets', # 流动资产
'fixedAssets', # 固定资产
'reserved', # 公积金
'reservedPerShare', # 每股公积金
'esp', # 每股收益
'bvps', # 每股净资
'pb', # 市净率
'timeToMarket', # 上市日期 0：未上市
'undp', # 未分利润
'perundp', # 每股未分配
'rev', # 收入同比(%)
'profit', # 利润同比(%)
'gpr', # 毛利率(%)
'npr', # 净利润率
'holders', # 股东人数
]
info=load_tushare_df("basic")
class Fundamental(CustomFactor):
outputs = columns
inputs = [USEquityPricing.close]
window_length = 1
window_safe = True
def handle(self, assets):
if asset_finder != None:
stocks = [_sid(msid).symbol for msid in assets]
else:
stocks = [sid(msid).symbol for msid in assets]
#print stocks
#print info.ix[stocks][columns]
return info.ix[stocks][columns]
def compute(self, today, assets, out,close):
df = self.handle(assets)
out.pe[:] = df.pe
out.outstanding[:] = close[-1] * df.outstanding * 1.0e+8
out.totals[:] = close[-1] * df.totals * 1.0e+8
out.totalAssets[:] = df.totalAssets * 1.0e+4
out.liquidAssets[:] = df.liquidAssets
out.fixedAssets[:] = df.fixedAssets
out.reserved[:] =df.reserved
out.reservedPerShare[:] = df.reservedPerShare
out.esp[:] = df.esp
out.bvps[:] = df.bvps
out.pb[:] = df.pb
out.timeToMarket[:] = df.timeToMarket
out.undp[:] = df.undp
out.perundp[:] = df.perundp
out.rev[:] = df.rev
out.profit[:] = df.profit
out.gpr[:] = df.gpr
out.npr[:] = df.npr
out.holders[:] = df.holders
return Fundamental()
