class IndustryNeutOperation(GroupNeutOperation):
"""Class to neutralize alpha by industry classifications.
:param str standard: Industry classification standard, currently only supports: ('SW2014', 'ZX'). Default: 'SW2014'
"""
def __init__(self, standard='SW2014', **kwargs):
super(IndustryNeutOperation, self).__init__(**kwargs)
self.standard = standard
self.industry = IndustryFetcher(datetime_index=True)
self.group = None
def operate(self, alpha, group='sector', simple=False, date=None):
alpha = alpha[np.isfinite(alpha)]
if isinstance(alpha, pd.Series):
group = self.industry.fetch_daily(group, date).dropna()
nalpha = alpha.ix[group.index]
nalpha = nalpha.groupby(group).transform(lambda x: x-x.mean())
return nalpha.reindex(index=alpha.index)
window = np.unique(dateutil.to_datestr(alpha.index))
if simple:
self.group = self.industry.fetch_daily(group, window[-1])
else:
self.group = self.industry.fetch_window(group, window)
return super(IndustryNeutOperation, self).operate(alpha)
class IndustryNeutOperation(GroupNeutOperation):
"""Class to neutralize alpha by industry classifications.
:param str standard: Industry classification standard, currently only supports: ('SW2014', 'ZX'). Default: 'SW2014'
"""
def __init__(self, standard='SW2014', **kwargs):
super(IndustryNeutOperation, self).__init__(**kwargs)
self.standard = standard
self.industry = IndustryFetcher(datetime_index=True)
self.group = None
def operate(self, alpha, group='sector', simple=False, date=None):
alpha = alpha[np.isfinite(alpha)]
if isinstance(alpha, pd.Series):
group = self.industry.fetch_daily(group, date).dropna()
nalpha = alpha.ix[group.index]
nalpha = nalpha.groupby(group).transform(lambda x: x - x.mean())
return nalpha.reindex(index=alpha.index)
window = np.unique(dateutil.to_datestr(alpha.index))
if simple:
self.group = self.industry.fetch_daily(group, window[-1])
else:
self.group = self.industry.fetch_window(group, window)
return super(IndustryNeutOperation, self).operate(alpha)
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.dates import DateFormatter
datefmt = DateFormatter('%Y%m%d')
from matplotlib.backends.backend_pdf import PdfPages
import magic
from orca.mongo.industry import IndustryFetcher
from orca.mongo.index import IndexQuoteFetcher
from orca.mongo.components import ComponentsFetcher
from orca.mongo.sywgquote import SYWGQuoteFetcher
from orca.mongo.kday import UnivFetcher
industry_fetcher = IndustryFetcher(datetime_index=True, reindex=True)
indexquote_fetcher = IndexQuoteFetcher(datetime_index=True)
components_fetcher = ComponentsFetcher(datetime_index=True)
sywgquote_fetcher = SYWGQuoteFetcher(datetime_index=True, use_industry=True)
univ_fetcher = UnivFetcher(datetime_index=True, reindex=True)
from orca.utils import dateutil
from orca.utils.io import read_frame
from orca.operation import api
class Weight(object):
"""Class to analyse portfolio weight decomposition through time."""
def __init__(self, alpha, n, rank=None):
self.alpha = api.format(alpha)
self.rank_alpha = self.alpha.rank(axis=1, ascending=False)
def __init__(self, standard='SW2014', **kwargs):
super(IndustryRankOperation, self).__init__(**kwargs)
self.standard = standard
self.industry = IndustryFetcher(datetime_index=True)
self.group = None
def __init__(self, standard='SW2014', **kwargs):
super(IndustryNeutOperation, self).__init__(**kwargs)
self.standard = standard
self.industry = IndustryFetcher(datetime_index=True)
self.group = None
"""
.. moduleauthor:: Li, Wang <*****@*****.**>
"""
import os
from string import Template
import pandas as pd
import logbook
logbook.set_datetime_format('local')
logger = logbook.Logger('assets')
from orca.mongo.barra import BarraFetcher
barra_fetcher = BarraFetcher('short')
from orca.mongo.industry import IndustryFetcher
industry_fetcher = IndustryFetcher()
from orca.mongo.components import ComponentsFetcher
components_fetcher = ComponentsFetcher()
def get_board(sid):
if sid[:2] == '60':
return 'SH'
elif sid[:2] == '30':
return 'CYB'
elif sid[:3] == '002':
return 'ZXB'
else:
return 'SZ'
def generate_path(path_pattern, date):
return Template(path_pattern).substitute(YYYYMMDD=date, YYYYMM=date[:6], YYYY=date[:4], MM=date[4:6], DD=date[6:8])
TradingDaysFilter,
ActiveFilter,
ComponentsFilter,
IndustryFilter,
)
from orca.universe.rules import (
startswith,
count_gt,
)
window = dateutil.get_startfrom(DATES, '20140104', 50)
close = QuoteFetcher(datetime_index=True,
reindex=True).fetch_window('close', window)
hs300 = ComponentsFetcher(datetime_index=True,
reindex=True).fetch_window('HS300', window)
sector = IndustryFetcher(datetime_index=True,
reindex=True).fetch_window('sector', window)
class SpecialTestCase(unittest.TestCase):
def test_ticker_filter(self):
sh = TickerFilter(startswith('60')).filter_daily(window[0])
dct = {sid: sid[:2] == '60' for sid in SIDS}
self.assertEqual(sh.to_dict(), dct)
def test_trading_days_filter(self):
trd_filter = TradingDaysFilter(50, count_gt(40), delay=0)
trd1 = trd_filter.filter_daily(window[-1])
trd2 = close.count() > 40
self.assertTrue(series_equal(trd1, trd2))
def test_active_filter(self):
"""
.. moduleauthor:: Li, Wang <*****@*****.**>
"""
import os
from string import Template
import pandas as pd
import logbook
logbook.set_datetime_format('local')
logger = logbook.Logger('assets')
from orca.mongo.barra import BarraFetcher
barra_fetcher = BarraFetcher('short')
from orca.mongo.industry import IndustryFetcher
industry_fetcher = IndustryFetcher()
from orca.mongo.components import ComponentsFetcher
components_fetcher = ComponentsFetcher()
def get_board(sid):
if sid[:2] == '60':
return 'SH'
elif sid[:2] == '30':
return 'CYB'
elif sid[:3] == '002':
return 'ZXB'
else:
return 'SZ'
"""
.. moduleauthor:: Li, Wang <*****@*****.**>
"""
from orca.mongo.industry import IndustryFetcher
industry_fetcher = IndustryFetcher()
def industry2name(pdobj):
pdobj = pdobj.copy()
ind_name = industry_fetcher.fetch_info()
pdobj.index = [ind_name[ind] for ind in pdobj.index]
return pdobj
def name2industry(pdobj):
pdobj = pdobj.copy()
name_ind = {v: k for k, v in industry_fetcher.fetch_info().iteritems()}
pdobj.index = [name_ind[name] for name in pdobj.index]
return pdobj
import pandas as pd
from orca import DATES
from orca.mongo.quote import QuoteFetcher
quote_fetcher = QuoteFetcher(datetime_index=True)
import dateutil
def setUp(self):
self.fetcher = IndustryFetcher()
self.dates = dateutil.get_startfrom(DATES, '20140101', 20)
class IndustryFetcherTestCase(unittest.TestCase):
def setUp(self):
self.fetcher = IndustryFetcher()
self.dates = dateutil.get_startfrom(DATES, '20140101', 20)
def tearDown(self):
self.fetcher = None
def test_fetch_window1(self):
df1_1 = self.fetcher.fetch_window('level1', self.dates)
df1_2 = self.fetcher.fetch_window('sector', self.dates)
df2_1 = self.fetcher.fetch_window('level2', self.dates)
df2_2 = self.fetcher.fetch_window('industry', self.dates)
df3_1 = self.fetcher.fetch_window('level3', self.dates)
df3_2 = self.fetcher.fetch_window('subindustry', self.dates)
self.assertTrue(frames_equal(df1_1, df1_2)
& frames_equal(df2_1, df2_2)
& frames_equal(df3_1, df3_2))
def test_fetch_window2(self):
df1 = self.fetcher.fetch_window('level1', self.dates)
df2 = self.fetcher.fetch_window('level1', self.dates, standard='ZX')
self.assertFalse(frames_equal(df1, df2))
def test_fetch_info1(self):
d0 = self.fetcher.fetch_info('name', level=0)
d1 = self.fetcher.fetch_info('name', level=1)
d2 = self.fetcher.fetch_info('name', level=2)
d3 = self.fetcher.fetch_info('name', level=3)
self.assertEqual(len(d0), len(d1)+len(d2)+len(d3))
def test_fetch_info2(self):
d0 = self.fetcher.fetch_info('index', level=0)
d1 = self.fetcher.fetch_info('index', level=1)
d2 = self.fetcher.fetch_info('index', level=2)
d3 = self.fetcher.fetch_info('index', level=3)
self.assertEqual(len(d0), len(d1)+len(d2)+len(d3))
"""
.. moduleauthor:: Li, Wang <*****@*****.**>
"""
import pandas as pd
from orca import SIDS
from orca.mongo.industry import IndustryFetcher
FETCHER = IndustryFetcher()
def get_board(sid):
if sid[:2] == '60':
return 'SH'
elif sid[:2] == '30':
return 'CYB'
elif sid[:3] == '002':
return 'ZXB'
return 'SZ'
BOARD = pd.Series({sid: get_board(sid) for sid in SIDS})
def group_by_board(df):
if isinstance(df, pd.Series):
group = BOARD.ix[df.index]
return df.groupby(group)
group = BOARD.ix[df.columns]
return df.groupby(group, axis=1)