def make_equity_info(cls):
out = pd.concat(
[
# 15 assets on each exchange. Each asset lives for 5 days.
# A new asset starts each day.
make_rotating_equity_info(
num_assets=20,
first_start=cls.START_DATE,
frequency=get_calendar(exchange).day,
periods_between_starts=1,
# NOTE: The asset_lifetime parameter name is a bit
# misleading. It determines the number of trading
# days between each asset's start_date and end_date,
# so assets created with this method actual "live"
# for (asset_lifetime + 1) days. But, since pipeline
# doesn't show you an asset the day it IPOs, this
# number matches the number of days that each asset
# should appear in a pipeline output.
asset_lifetime=5,
exchange=exchange,
)
for exchange in cls.EXCHANGE_INFO.exchange
],
ignore_index=True,
)
assert_equal(out.end_date.max(), cls.END_DATE)
return out
def make_equity_info(cls):
out = pd.concat(
[
# 15 assets on each exchange. Each asset lives for 5 days.
# A new asset starts each day.
make_rotating_equity_info(
num_assets=20,
first_start=cls.START_DATE,
frequency=get_calendar(exchange).day,
periods_between_starts=1,
# NOTE: The asset_lifetime parameter name is a bit
# misleading. It determines the number of trading
# days between each asset's start_date and end_date,
# so assets created with this method actual "live"
# for (asset_lifetime + 1) days. But, since pipeline
# doesn't show you an asset the day it IPOs, this
# number matches the number of days that each asset
# should appear in a pipeline output.
asset_lifetime=5,
exchange=exchange,
) for exchange in cls.EXCHANGE_INFO.exchange
],
ignore_index=True,
)
assert_equal(out.end_date.max(), cls.END_DATE)
return out
def test_compute_lifetimes(self):
num_assets = 4
trading_day = self.trading_schedule.day
first_start = pd.Timestamp('2015-04-01', tz='UTC')
frame = make_rotating_equity_info(
num_assets=num_assets,
first_start=first_start,
frequency=trading_day,
periods_between_starts=3,
asset_lifetime=5
)
self.write_assets(equities=frame)
finder = self.asset_finder
all_dates = pd.date_range(
start=first_start,
end=frame.end_date.max(),
freq=trading_day,
)
for dates in all_subindices(all_dates):
expected_with_start_raw = full(
shape=(len(dates), num_assets),
fill_value=False,
dtype=bool,
)
expected_no_start_raw = full(
shape=(len(dates), num_assets),
fill_value=False,
dtype=bool,
)
for i, date in enumerate(dates):
it = frame[['start_date', 'end_date']].itertuples()
for j, start, end in it:
# This way of doing the checks is redundant, but very
# clear.
if start <= date <= end:
expected_with_start_raw[i, j] = True
if start < date:
expected_no_start_raw[i, j] = True
expected_with_start = pd.DataFrame(
data=expected_with_start_raw,
index=dates,
columns=frame.index.values,
)
result = finder.lifetimes(dates, include_start_date=True)
assert_frame_equal(result, expected_with_start)
expected_no_start = pd.DataFrame(
data=expected_no_start_raw,
index=dates,
columns=frame.index.values,
)
result = finder.lifetimes(dates, include_start_date=False)
assert_frame_equal(result, expected_no_start)
def test_compute_lifetimes(self):
num_assets = 4
trading_day = self.trading_calendar.day
first_start = pd.Timestamp('2015-04-01', tz='UTC')
frame = make_rotating_equity_info(
num_assets=num_assets,
first_start=first_start,
frequency=trading_day,
periods_between_starts=3,
asset_lifetime=5
)
self.write_assets(equities=frame)
finder = self.asset_finder
all_dates = pd.date_range(
start=first_start,
end=frame.end_date.max(),
freq=trading_day,
)
for dates in all_subindices(all_dates):
expected_with_start_raw = full(
shape=(len(dates), num_assets),
fill_value=False,
dtype=bool,
)
expected_no_start_raw = full(
shape=(len(dates), num_assets),
fill_value=False,
dtype=bool,
)
for i, date in enumerate(dates):
it = frame[['start_date', 'end_date']].itertuples()
for j, start, end in it:
# This way of doing the checks is redundant, but very
# clear.
if start <= date <= end:
expected_with_start_raw[i, j] = True
if start < date:
expected_no_start_raw[i, j] = True
expected_with_start = pd.DataFrame(
data=expected_with_start_raw,
index=dates,
columns=frame.index.values,
)
result = finder.lifetimes(dates, include_start_date=True)
assert_frame_equal(result, expected_with_start)
expected_no_start = pd.DataFrame(
data=expected_no_start_raw,
index=dates,
columns=frame.index.values,
)
result = finder.lifetimes(dates, include_start_date=False)
assert_frame_equal(result, expected_no_start)
def make_equity_info(cls):
cls.equity_info = ret = make_rotating_equity_info(
num_assets=6,
first_start=cls.first_asset_start,
frequency=cls.trading_calendar.day,
periods_between_starts=4,
asset_lifetime=8,
)
return ret
def make_equity_info(cls):
cls.equity_info = ret = make_rotating_equity_info(
num_assets=6,
first_start=cls.first_asset_start,
frequency=cls.TRADING_ENV_TRADING_CALENDAR.trading_day,
periods_between_starts=4,
asset_lifetime=8,
)
return ret
def make_equity_info(cls):
cls.equity_info = ret = make_rotating_equity_info(
num_assets=6,
first_start=cls.first_asset_start,
frequency=cls.trading_calendar.day,
periods_between_starts=4,
asset_lifetime=8,
)
return ret
def make_equity_info(cls):
cls.equity_info = ret = make_rotating_equity_info(
num_assets=6,
first_start=cls.first_asset_start,
frequency=cls.TRADING_ENV_TRADING_CALENDAR.trading_day,
periods_between_starts=4,
asset_lifetime=8,
)
return ret
def test_compute_lifetimes(self):
assets_per_exchange = 4
trading_day = self.trading_calendar.day
first_start = pd.Timestamp('2015-04-01', tz='UTC')
equities = pd.concat(
[
make_rotating_equity_info(
num_assets=assets_per_exchange,
first_start=first_start,
frequency=trading_day,
periods_between_starts=3,
asset_lifetime=5,
exchange=exchange,
) for exchange in (
'US_EXCHANGE_1',
'US_EXCHANGE_2',
'CA_EXCHANGE',
'JP_EXCHANGE',
)
],
ignore_index=True,
)
# make every symbol unique
equities['symbol'] = list(string.ascii_uppercase[:len(equities)])
equities['real_sid'] = equities['symbol']
# shuffle up the sids so they are not contiguous per exchange
sids = np.arange(len(equities))
np.random.RandomState(1337).shuffle(sids)
equities.index = sids
permute_sid = dict(zip(sids, range(len(sids)))).__getitem__
exchanges = pd.DataFrame.from_records([
{
'exchange': 'US_EXCHANGE_1',
'country_code': 'US'
},
{
'exchange': 'US_EXCHANGE_2',
'country_code': 'US'
},
{
'exchange': 'CA_EXCHANGE',
'country_code': 'CA'
},
{
'exchange': 'JP_EXCHANGE',
'country_code': 'JP'
},
])
sids_by_country = {
'US': equities.index[:2 * assets_per_exchange],
'CA':
equities.index[2 * assets_per_exchange:3 * assets_per_exchange],
'JP': equities.index[3 * assets_per_exchange:],
}
self.write_assets(equities=equities, exchanges=exchanges)
finder = self.asset_finder
all_dates = pd.date_range(
start=first_start,
end=equities.end_date.max(),
freq=trading_day,
)
for dates in all_subindices(all_dates):
expected_with_start_raw = full(
shape=(len(dates), assets_per_exchange),
fill_value=False,
dtype=bool,
)
expected_no_start_raw = full(
shape=(len(dates), assets_per_exchange),
fill_value=False,
dtype=bool,
)
for i, date in enumerate(dates):
it = equities.iloc[:4][['start_date',
'end_date']].itertuples(index=False, )
for j, (start, end) in enumerate(it):
# This way of doing the checks is redundant, but very
# clear.
if start <= date <= end:
expected_with_start_raw[i, j] = True
if start < date:
expected_no_start_raw[i, j] = True
for country_codes in powerset(exchanges.country_code.unique()):
expected_sids = pd.Int64Index(
sorted(
concat(sids_by_country[country_code]
for country_code in country_codes)))
permuted_sids = [
sid for sid in sorted(expected_sids, key=permute_sid)
]
tile_count = len(country_codes) + ('US' in country_codes)
expected_with_start = pd.DataFrame(
data=np.tile(
expected_with_start_raw,
tile_count,
),
index=dates,
columns=pd.Int64Index(permuted_sids),
)
result = finder.lifetimes(
dates,
include_start_date=True,
country_codes=country_codes,
)
assert_equal(result.columns, expected_sids)
result = result[permuted_sids]
assert_equal(result, expected_with_start)
expected_no_start = pd.DataFrame(
data=np.tile(
expected_no_start_raw,
tile_count,
),
index=dates,
columns=pd.Int64Index(permuted_sids),
)
result = finder.lifetimes(
dates,
include_start_date=False,
country_codes=country_codes,
)
assert_equal(result.columns, expected_sids)
result = result[permuted_sids]
assert_equal(result, expected_no_start)
