def setUp(self):
self.asset_info = EQUITY_INFO
self.writer = SyntheticDailyBarWriter(
self.asset_info,
self.trading_days,
)
self.dir_ = TempDirectory()
self.dir_.create()
self.dest = self.dir_.getpath('daily_equity_pricing.bcolz')
def test_write_ohlcv_content(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
for column in SyntheticDailyBarWriter.OHLCV:
idx = 0
data = result[column][:]
multiplier = 1 if column == 'volume' else 1000
for asset_id in self.assets:
for date in self.dates_for_asset(asset_id):
self.assertEqual(
SyntheticDailyBarWriter.expected_value(
asset_id, date, column) * multiplier,
data[idx],
)
idx += 1
self.assertEqual(idx, len(data))
def test_write_ohlcv_content(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
for column in SyntheticDailyBarWriter.OHLCV:
idx = 0
data = result[column][:]
multiplier = 1 if column == 'volume' else 1000
for asset_id in self.assets:
for date in self.dates_for_asset(asset_id):
self.assertEqual(
SyntheticDailyBarWriter.expected_value(
asset_id,
date,
column
) * multiplier,
data[idx],
)
idx += 1
self.assertEqual(idx, len(data))
def setUpClass(cls):
cls.test_data_dir = TempDirectory()
cls.db_path = cls.test_data_dir.getpath('adjustments.db')
writer = SQLiteAdjustmentWriter(cls.db_path)
writer.write(SPLITS, MERGERS, DIVIDENDS)
cls.assets = TEST_QUERY_ASSETS
all_days = TradingEnvironment().trading_days
cls.calendar_days = all_days[all_days.slice_indexer(
TEST_CALENDAR_START, TEST_CALENDAR_STOP)]
cls.asset_info = EQUITY_INFO
cls.bcolz_writer = SyntheticDailyBarWriter(
cls.asset_info,
cls.calendar_days,
)
cls.bcolz_path = cls.test_data_dir.getpath('equity_pricing.bcolz')
cls.bcolz_writer.write(cls.bcolz_path, cls.calendar_days, cls.assets)
def setUpClass(cls):
cls.first_asset_start = Timestamp('2015-04-01', tz='UTC')
cls.env = TradingEnvironment()
cls.trading_day = day = cls.env.trading_day
cls.calendar = date_range('2015', '2015-08', tz='UTC', freq=day)
cls.asset_info = make_rotating_asset_info(
num_assets=6,
first_start=cls.first_asset_start,
frequency=day,
periods_between_starts=4,
asset_lifetime=8,
)
cls.last_asset_end = cls.asset_info['end_date'].max()
cls.all_assets = cls.asset_info.index
cls.env.write_data(equities_df=cls.asset_info)
cls.finder = cls.env.asset_finder
cls.temp_dir = TempDirectory()
cls.temp_dir.create()
try:
cls.writer = SyntheticDailyBarWriter(
asset_info=cls.asset_info[['start_date', 'end_date']],
calendar=cls.calendar,
)
table = cls.writer.write(
cls.temp_dir.getpath('testdata.bcolz'),
cls.calendar,
cls.all_assets,
)
cls.pipeline_loader = USEquityPricingLoader(
BcolzDailyBarReader(table),
NullAdjustmentReader(),
)
except:
cls.temp_dir.cleanup()
raise
class BcolzDailyBarTestCase(TestCase):
@classmethod
def setUpClass(cls):
all_trading_days = TradingEnvironment().trading_days
cls.trading_days = all_trading_days[
all_trading_days.get_loc(TEST_CALENDAR_START):
all_trading_days.get_loc(TEST_CALENDAR_STOP) + 1
]
def setUp(self):
self.asset_info = EQUITY_INFO
self.writer = SyntheticDailyBarWriter(
self.asset_info,
self.trading_days,
)
self.dir_ = TempDirectory()
self.dir_.create()
self.dest = self.dir_.getpath('daily_equity_pricing.bcolz')
def tearDown(self):
self.dir_.cleanup()
@property
def assets(self):
return self.asset_info.index
def trading_days_between(self, start, end):
return self.trading_days[self.trading_days.slice_indexer(start, end)]
def asset_start(self, asset_id):
return self.writer.asset_start(asset_id)
def asset_end(self, asset_id):
return self.writer.asset_end(asset_id)
def dates_for_asset(self, asset_id):
start, end = self.asset_start(asset_id), self.asset_end(asset_id)
return self.trading_days_between(start, end)
def test_write_ohlcv_content(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
for column in SyntheticDailyBarWriter.OHLCV:
idx = 0
data = result[column][:]
multiplier = 1 if column == 'volume' else 1000
for asset_id in self.assets:
for date in self.dates_for_asset(asset_id):
self.assertEqual(
SyntheticDailyBarWriter.expected_value(
asset_id,
date,
column
) * multiplier,
data[idx],
)
idx += 1
self.assertEqual(idx, len(data))
def test_write_day_and_id(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
idx = 0
ids = result['id']
days = result['day']
for asset_id in self.assets:
for date in self.dates_for_asset(asset_id):
self.assertEqual(ids[idx], asset_id)
self.assertEqual(date, seconds_to_timestamp(days[idx]))
idx += 1
def test_write_attrs(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
expected_first_row = {
'1': 0,
'2': 5, # Asset 1 has 5 trading days.
'3': 12, # Asset 2 has 7 trading days.
'4': 33, # Asset 3 has 21 trading days.
'5': 44, # Asset 4 has 11 trading days.
'6': 49, # Asset 5 has 5 trading days.
}
expected_last_row = {
'1': 4,
'2': 11,
'3': 32,
'4': 43,
'5': 48,
'6': 57, # Asset 6 has 9 trading days.
}
expected_calendar_offset = {
'1': 0, # Starts on 6-01, 1st trading day of month.
'2': 15, # Starts on 6-22, 16th trading day of month.
'3': 1, # Starts on 6-02, 2nd trading day of month.
'4': 0, # Starts on 6-01, 1st trading day of month.
'5': 9, # Starts on 6-12, 10th trading day of month.
'6': 10, # Starts on 6-15, 11th trading day of month.
}
self.assertEqual(result.attrs['first_row'], expected_first_row)
self.assertEqual(result.attrs['last_row'], expected_last_row)
self.assertEqual(
result.attrs['calendar_offset'],
expected_calendar_offset,
)
assert_index_equal(
self.trading_days,
DatetimeIndex(result.attrs['calendar'], tz='UTC'),
)
def _check_read_results(self, columns, assets, start_date, end_date):
table = self.writer.write(self.dest, self.trading_days, self.assets)
reader = BcolzDailyBarReader(table)
results = reader.load_raw_arrays(columns, start_date, end_date, assets)
dates = self.trading_days_between(start_date, end_date)
for column, result in zip(columns, results):
assert_array_equal(
result,
self.writer.expected_values_2d(
dates,
assets,
column.name,
)
)
@parameterized.expand([
([USEquityPricing.open],),
([USEquityPricing.close, USEquityPricing.volume],),
([USEquityPricing.volume, USEquityPricing.high, USEquityPricing.low],),
(USEquityPricing.columns,),
])
def test_read(self, columns):
self._check_read_results(
columns,
self.assets,
TEST_QUERY_START,
TEST_QUERY_STOP,
)
def test_start_on_asset_start(self):
"""
Test loading with queries that starts on the first day of each asset's
lifetime.
"""
columns = [USEquityPricing.high, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.asset_start(asset),
end_date=self.trading_days[-1],
)
def test_start_on_asset_end(self):
"""
Test loading with queries that start on the last day of each asset's
lifetime.
"""
columns = [USEquityPricing.close, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.asset_end(asset),
end_date=self.trading_days[-1],
)
def test_end_on_asset_start(self):
"""
Test loading with queries that end on the first day of each asset's
lifetime.
"""
columns = [USEquityPricing.close, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.trading_days[0],
end_date=self.asset_start(asset),
)
def test_end_on_asset_end(self):
"""
Test loading with queries that end on the last day of each asset's
lifetime.
"""
columns = [USEquityPricing.close, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.trading_days[0],
end_date=self.asset_end(asset),
)
class BcolzDailyBarTestCase(TestCase):
@classmethod
def setUpClass(cls):
all_trading_days = TradingEnvironment().trading_days
cls.trading_days = all_trading_days[all_trading_days.get_loc(
TEST_CALENDAR_START):all_trading_days.get_loc(TEST_CALENDAR_STOP) +
1]
def setUp(self):
self.asset_info = EQUITY_INFO
self.writer = SyntheticDailyBarWriter(
self.asset_info,
self.trading_days,
)
self.dir_ = TempDirectory()
self.dir_.create()
self.dest = self.dir_.getpath('daily_equity_pricing.bcolz')
def tearDown(self):
self.dir_.cleanup()
@property
def assets(self):
return self.asset_info.index
def trading_days_between(self, start, end):
return self.trading_days[self.trading_days.slice_indexer(start, end)]
def asset_start(self, asset_id):
return self.writer.asset_start(asset_id)
def asset_end(self, asset_id):
return self.writer.asset_end(asset_id)
def dates_for_asset(self, asset_id):
start, end = self.asset_start(asset_id), self.asset_end(asset_id)
return self.trading_days_between(start, end)
def test_write_ohlcv_content(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
for column in SyntheticDailyBarWriter.OHLCV:
idx = 0
data = result[column][:]
multiplier = 1 if column == 'volume' else 1000
for asset_id in self.assets:
for date in self.dates_for_asset(asset_id):
self.assertEqual(
SyntheticDailyBarWriter.expected_value(
asset_id, date, column) * multiplier,
data[idx],
)
idx += 1
self.assertEqual(idx, len(data))
def test_write_day_and_id(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
idx = 0
ids = result['id']
days = result['day']
for asset_id in self.assets:
for date in self.dates_for_asset(asset_id):
self.assertEqual(ids[idx], asset_id)
self.assertEqual(date, seconds_to_timestamp(days[idx]))
idx += 1
def test_write_attrs(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
expected_first_row = {
'1': 0,
'2': 5, # Asset 1 has 5 trading days.
'3': 12, # Asset 2 has 7 trading days.
'4': 33, # Asset 3 has 21 trading days.
'5': 44, # Asset 4 has 11 trading days.
'6': 49, # Asset 5 has 5 trading days.
}
expected_last_row = {
'1': 4,
'2': 11,
'3': 32,
'4': 43,
'5': 48,
'6': 57, # Asset 6 has 9 trading days.
}
expected_calendar_offset = {
'1': 0, # Starts on 6-01, 1st trading day of month.
'2': 15, # Starts on 6-22, 16th trading day of month.
'3': 1, # Starts on 6-02, 2nd trading day of month.
'4': 0, # Starts on 6-01, 1st trading day of month.
'5': 9, # Starts on 6-12, 10th trading day of month.
'6': 10, # Starts on 6-15, 11th trading day of month.
}
self.assertEqual(result.attrs['first_row'], expected_first_row)
self.assertEqual(result.attrs['last_row'], expected_last_row)
self.assertEqual(
result.attrs['calendar_offset'],
expected_calendar_offset,
)
assert_index_equal(
self.trading_days,
DatetimeIndex(result.attrs['calendar'], tz='UTC'),
)
def _check_read_results(self, columns, assets, start_date, end_date):
table = self.writer.write(self.dest, self.trading_days, self.assets)
reader = BcolzDailyBarReader(table)
results = reader.load_raw_arrays(columns, start_date, end_date, assets)
dates = self.trading_days_between(start_date, end_date)
for column, result in zip(columns, results):
assert_array_equal(
result,
self.writer.expected_values_2d(
dates,
assets,
column.name,
))
@parameterized.expand([
([USEquityPricing.open], ),
([USEquityPricing.close, USEquityPricing.volume], ),
([USEquityPricing.volume, USEquityPricing.high,
USEquityPricing.low], ),
(USEquityPricing.columns, ),
])
def test_read(self, columns):
self._check_read_results(
columns,
self.assets,
TEST_QUERY_START,
TEST_QUERY_STOP,
)
def test_start_on_asset_start(self):
"""
Test loading with queries that starts on the first day of each asset's
lifetime.
"""
columns = [USEquityPricing.high, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.asset_start(asset),
end_date=self.trading_days[-1],
)
def test_start_on_asset_end(self):
"""
Test loading with queries that start on the last day of each asset's
lifetime.
"""
columns = [USEquityPricing.close, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.asset_end(asset),
end_date=self.trading_days[-1],
)
def test_end_on_asset_start(self):
"""
Test loading with queries that end on the first day of each asset's
lifetime.
"""
columns = [USEquityPricing.close, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.trading_days[0],
end_date=self.asset_start(asset),
)
def test_end_on_asset_end(self):
"""
Test loading with queries that end on the last day of each asset's
lifetime.
"""
columns = [USEquityPricing.close, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.trading_days[0],
end_date=self.asset_end(asset),
)
def test_unadjusted_spot_price(self):
table = self.writer.write(self.dest, self.trading_days, self.assets)
reader = BcolzDailyBarReader(table)
# At beginning
price = reader.spot_price(1, Timestamp('2015-06-01', tz='UTC'),
'close')
# Synthetic writes price for date.
self.assertEqual(135630.0, price)
# Middle
price = reader.spot_price(1, Timestamp('2015-06-02', tz='UTC'),
'close')
self.assertEqual(135631.0, price)
# End
price = reader.spot_price(1, Timestamp('2015-06-05', tz='UTC'),
'close')
self.assertEqual(135634.0, price)
# Another sid at beginning.
price = reader.spot_price(2, Timestamp('2015-06-22', tz='UTC'),
'close')
self.assertEqual(235651.0, price)
# Ensure that volume does not have float adjustment applied.
volume = reader.spot_price(1, Timestamp('2015-06-02', tz='UTC'),
'volume')
self.assertEqual(145631, volume)
def test_unadjusted_spot_price_no_data(self):
table = self.writer.write(self.dest, self.trading_days, self.assets)
reader = BcolzDailyBarReader(table)
# before
with self.assertRaises(NoDataOnDate):
reader.spot_price(2, Timestamp('2015-06-08', tz='UTC'), 'close')
# after
with self.assertRaises(NoDataOnDate):
reader.spot_price(4, Timestamp('2015-06-16', tz='UTC'), 'close')
def test_unadjusted_spot_price_empty_value(self):
table = self.writer.write(self.dest, self.trading_days, self.assets)
reader = BcolzDailyBarReader(table)
# A sid, day and corresponding index into which to overwrite a zero.
zero_sid = 1
zero_day = Timestamp('2015-06-02', tz='UTC')
zero_ix = reader.sid_day_index(zero_sid, zero_day)
# Write a zero into the synthetic pricing data at the day and sid,
# so that a read should now return -1.
# This a little hacky, in lieu of changing the synthetic data set.
reader._spot_col('close')[zero_ix] = 0
close = reader.spot_price(zero_sid, zero_day, 'close')
self.assertEqual(-1, close)
class BcolzDailyBarTestCase(TestCase):
@classmethod
def setUpClass(cls):
all_trading_days = TradingEnvironment().trading_days
cls.trading_days = all_trading_days[
all_trading_days.get_loc(TEST_CALENDAR_START):
all_trading_days.get_loc(TEST_CALENDAR_STOP) + 1
]
def setUp(self):
self.asset_info = EQUITY_INFO
self.writer = SyntheticDailyBarWriter(
self.asset_info,
self.trading_days,
)
self.dir_ = TempDirectory()
self.dir_.create()
self.dest = self.dir_.getpath('daily_equity_pricing.bcolz')
def tearDown(self):
self.dir_.cleanup()
@property
def assets(self):
return self.asset_info.index
def trading_days_between(self, start, end):
return self.trading_days[self.trading_days.slice_indexer(start, end)]
def asset_start(self, asset_id):
return self.writer.asset_start(asset_id)
def asset_end(self, asset_id):
return self.writer.asset_end(asset_id)
def dates_for_asset(self, asset_id):
start, end = self.asset_start(asset_id), self.asset_end(asset_id)
return self.trading_days_between(start, end)
def test_write_ohlcv_content(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
for column in SyntheticDailyBarWriter.OHLCV:
idx = 0
data = result[column][:]
multiplier = 1 if column == 'volume' else 1000
for asset_id in self.assets:
for date in self.dates_for_asset(asset_id):
self.assertEqual(
SyntheticDailyBarWriter.expected_value(
asset_id,
date,
column
) * multiplier,
data[idx],
)
idx += 1
self.assertEqual(idx, len(data))
def test_write_day_and_id(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
idx = 0
ids = result['id']
days = result['day']
for asset_id in self.assets:
for date in self.dates_for_asset(asset_id):
self.assertEqual(ids[idx], asset_id)
self.assertEqual(date, seconds_to_timestamp(days[idx]))
idx += 1
def test_write_attrs(self):
result = self.writer.write(self.dest, self.trading_days, self.assets)
expected_first_row = {
'1': 0,
'2': 5, # Asset 1 has 5 trading days.
'3': 12, # Asset 2 has 7 trading days.
'4': 33, # Asset 3 has 21 trading days.
'5': 44, # Asset 4 has 11 trading days.
'6': 49, # Asset 5 has 5 trading days.
}
expected_last_row = {
'1': 4,
'2': 11,
'3': 32,
'4': 43,
'5': 48,
'6': 57, # Asset 6 has 9 trading days.
}
expected_calendar_offset = {
'1': 0, # Starts on 6-01, 1st trading day of month.
'2': 15, # Starts on 6-22, 16th trading day of month.
'3': 1, # Starts on 6-02, 2nd trading day of month.
'4': 0, # Starts on 6-01, 1st trading day of month.
'5': 9, # Starts on 6-12, 10th trading day of month.
'6': 10, # Starts on 6-15, 11th trading day of month.
}
self.assertEqual(result.attrs['first_row'], expected_first_row)
self.assertEqual(result.attrs['last_row'], expected_last_row)
self.assertEqual(
result.attrs['calendar_offset'],
expected_calendar_offset,
)
assert_index_equal(
self.trading_days,
DatetimeIndex(result.attrs['calendar'], tz='UTC'),
)
def _check_read_results(self, columns, assets, start_date, end_date):
table = self.writer.write(self.dest, self.trading_days, self.assets)
reader = BcolzDailyBarReader(table)
results = reader.load_raw_arrays(columns, start_date, end_date, assets)
dates = self.trading_days_between(start_date, end_date)
for column, result in zip(columns, results):
assert_array_equal(
result,
self.writer.expected_values_2d(
dates,
assets,
column.name,
)
)
@parameterized.expand([
([USEquityPricing.open],),
([USEquityPricing.close, USEquityPricing.volume],),
([USEquityPricing.volume, USEquityPricing.high, USEquityPricing.low],),
(USEquityPricing.columns,),
])
def test_read(self, columns):
self._check_read_results(
columns,
self.assets,
TEST_QUERY_START,
TEST_QUERY_STOP,
)
def test_start_on_asset_start(self):
"""
Test loading with queries that starts on the first day of each asset's
lifetime.
"""
columns = [USEquityPricing.high, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.asset_start(asset),
end_date=self.trading_days[-1],
)
def test_start_on_asset_end(self):
"""
Test loading with queries that start on the last day of each asset's
lifetime.
"""
columns = [USEquityPricing.close, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.asset_end(asset),
end_date=self.trading_days[-1],
)
def test_end_on_asset_start(self):
"""
Test loading with queries that end on the first day of each asset's
lifetime.
"""
columns = [USEquityPricing.close, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.trading_days[0],
end_date=self.asset_start(asset),
)
def test_end_on_asset_end(self):
"""
Test loading with queries that end on the last day of each asset's
lifetime.
"""
columns = [USEquityPricing.close, USEquityPricing.volume]
for asset in self.assets:
self._check_read_results(
columns,
self.assets,
start_date=self.trading_days[0],
end_date=self.asset_end(asset),
)
def test_unadjusted_spot_price(self):
table = self.writer.write(self.dest, self.trading_days, self.assets)
reader = BcolzDailyBarReader(table)
# At beginning
price = reader.spot_price(1, Timestamp('2015-06-01', tz='UTC'),
'close')
# Synthetic writes price for date.
self.assertEqual(135630.0, price)
# Middle
price = reader.spot_price(1, Timestamp('2015-06-02', tz='UTC'),
'close')
self.assertEqual(135631.0, price)
# End
price = reader.spot_price(1, Timestamp('2015-06-05', tz='UTC'),
'close')
self.assertEqual(135634.0, price)
# Another sid at beginning.
price = reader.spot_price(2, Timestamp('2015-06-22', tz='UTC'),
'close')
self.assertEqual(235651.0, price)
# Ensure that volume does not have float adjustment applied.
volume = reader.spot_price(1, Timestamp('2015-06-02', tz='UTC'),
'volume')
self.assertEqual(145631, volume)
def test_unadjusted_spot_price_no_data(self):
table = self.writer.write(self.dest, self.trading_days, self.assets)
reader = BcolzDailyBarReader(table)
# before
with self.assertRaises(NoDataOnDate):
reader.spot_price(2, Timestamp('2015-06-08', tz='UTC'), 'close')
# after
with self.assertRaises(NoDataOnDate):
reader.spot_price(4, Timestamp('2015-06-16', tz='UTC'), 'close')
def test_unadjusted_spot_price_empty_value(self):
table = self.writer.write(self.dest, self.trading_days, self.assets)
reader = BcolzDailyBarReader(table)
# A sid, day and corresponding index into which to overwrite a zero.
zero_sid = 1
zero_day = Timestamp('2015-06-02', tz='UTC')
zero_ix = reader.sid_day_index(zero_sid, zero_day)
# Write a zero into the synthetic pricing data at the day and sid,
# so that a read should now return -1.
# This a little hacky, in lieu of changing the synthetic data set.
reader._spot_col('close')[zero_ix] = 0
close = reader.spot_price(zero_sid, zero_day, 'close')
self.assertEqual(-1, close)
