def random_intalpha(startdate='20140103', freq='30min', n=None):
if not n >= 0:
n = np.random.randint(10, 20)
dates = dateutil.get_startfrom(DATES,
dateutil.compliment_datestring(str(startdate), -1, True),
n)
times = dateutil.generate_intervals(int(freq[:-3])*60)
dts = pd.to_datetime([d+' '+t for d in dates for t in times])
df = pd.DataFrame(np.random.randn(len(dts), len(SIDS)), index=dts, columns=SIDS)
return df
def random_alpha(startdate='20140103', n=None, datetime_index=True):
"""Generate a random alpha(i.e. a DataFrame of random floats with DatetimeINdex and full sids columns).
:param startdate: Starting point. Default: '20140103'
:type startdate: int, str
:param int n: Length of the returned DataFrame; when None, it will be a random number between 50 and 100. Default: None
:param boolean datetime_index: Whether to format the DataFrame with DatetimeIndex. Default: True
"""
if not n >= 0:
n = np.random.randint(50, 100)
dates = dateutil.get_startfrom(DATES,
dateutil.compliment_datestring(str(startdate), -1, True),
n)
df = pd.DataFrame(np.random.randn(n, len(SIDS)), index=dates, columns=SIDS)
if datetime_index:
df.index = pd.to_datetime(df.index)
return df
frames_equal,
)
from orca.utils import dateutil
from orca.universe.special import (
TickerFilter,
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):
def setUp(self):
self.fetcher = IndexQuoteFetcher()
self.dates = dateutil.get_startfrom(DATES, '20140101', 20)
def setUp(self):
self.fetcher = KDayFetcherDummy()
self.dates_str = dateutil.get_startfrom(DATES, '20140101', 50)
self.dates_pddt = pd.to_datetime(self.dates_str)
def setUp(self):
self.fetcher = KMinFetcherDummy()
self.dates_str = dateutil.get_startfrom(DATES, '20140101', 50)
self.times = list(
dateutil.generate_timestamps('100000', '113000', 30 * 60))
self.dates_pddt = pd.to_datetime(self.dates_str)
def setUp(self):
self.filter = SimpleDataFilterDummy()
self.fetcher = QuoteFetcher(datetime_index=True, reindex=True)
self.dates = dateutil.get_startfrom(DATES, '20140801', 20)
self.startdate, self.enddate = self.dates[0], self.dates[-1]
self.si, self.ei = map(DATES.index, [self.startdate, self.enddate])
def setUp(self):
self.fetcher = ComponentsFetcher()
self.dates = dateutil.get_startfrom(DATES, '20140101', 10)
def setUp(self):
self.adjfetcher = AdjQuoteFetcher()
self.fetcher = QuoteFetcher()
self.dates = get_startfrom(DATES, '20140101', 50)
def setUp(self):
self.fetcher = KDayFetcherDummy()
self.dates_str = dateutil.get_startfrom(DATES, '20140101', 50)
self.dates_pddt = pd.to_datetime(self.dates_str)
def setUp(self):
self.fetcher = KMinFetcherDummy()
self.dates_str = dateutil.get_startfrom(DATES, '20140101', 50)
self.times = list(dateutil.generate_timestamps('100000', '113000', 30*60))
self.dates_pddt = pd.to_datetime(self.dates_str)
import numpy as np
import pandas as pd
from orca import (
DATES,
SIDS,
)
from orca.utils.testing import (
series_equal,
frames_equal,
)
from orca.utils import dateutil
from orca.perf.analyser import Analyser
from orca.perf.performance import Performance
dates = pd.to_datetime(dateutil.get_startfrom(DATES, '20140101', 120))
alpha1 = pd.DataFrame(np.random.randn(len(dates), len(SIDS)), index=dates, columns=SIDS)
valid = pd.DataFrame(np.random.randint(3, size=alpha1.shape), index=dates, columns=SIDS).astype(bool)
alpha1[~valid] = np.nan
# long-short alpha
alpha1 = alpha1.subtract(alpha1.mean(axis=1), axis=0)
valid = pd.DataFrame(np.random.randint(4, size=alpha1.shape), index=dates, columns=SIDS).astype(bool)
data = pd.DataFrame(np.random.randn(*alpha1.shape), index=dates, columns=SIDS)
data[~valid] = np.nan
# long part
alpha2 = alpha1[alpha1>0]
# short part
alpha3 = -alpha1[alpha1<0]
def setUp(self):
self.filter = SimpleDataFilterDummy()
self.fetcher = QuoteFetcher(datetime_index=True, reindex=True)
self.dates = dateutil.get_startfrom(DATES, '20140801', 20)
self.startdate, self.enddate = self.dates[0], self.dates[-1]
self.si, self.ei = map(DATES.index, [self.startdate, self.enddate])
frames_equal,
)
from orca.utils import dateutil
from orca.universe.special import (
TickerFilter,
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])
import numpy as np
import pandas as pd
from orca import (
DATES,
SIDS,
)
from orca.utils.testing import (
series_equal,
frames_equal,
)
from orca.utils import dateutil
from orca.perf.analyser import Analyser
from orca.perf.performance import Performance
dates = pd.to_datetime(dateutil.get_startfrom(DATES, '20140101', 120))
alpha1 = pd.DataFrame(np.random.randn(len(dates), len(SIDS)),
index=dates,
columns=SIDS)
valid = pd.DataFrame(np.random.randint(3, size=alpha1.shape),
index=dates,
columns=SIDS).astype(bool)
alpha1[~valid] = np.nan
# long-short alpha
alpha1 = alpha1.subtract(alpha1.mean(axis=1), axis=0)
valid = pd.DataFrame(np.random.randint(4, size=alpha1.shape),
index=dates,
columns=SIDS).astype(bool)
data = pd.DataFrame(np.random.randn(*alpha1.shape), index=dates, columns=SIDS)
data[~valid] = np.nan
def setUp(self):
self.fetcher = QuoteFetcher()
self.dates = get_startfrom(DATES, '2014010', 50)
def setUp(self):
self.fetcher = ComponentsFetcher()
self.dates = dateutil.get_startfrom(DATES, '20140101', 10)
