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))
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)
dates = self.trading_days_between(start_date, end_date)
results = reader.load_raw_arrays(columns, dates, assets)
for column, result in zip(columns, results):
assert_array_equal(
result,
self.writer.expected_values_2d(
dates,
assets,
column.name,
))
def test_read_no_adjustments(self):
adjustment_reader = NullAdjustmentReader()
columns = [USEquityPricing.close, USEquityPricing.volume]
query_days = self.calendar_days_between(TEST_QUERY_START,
TEST_QUERY_STOP)
adjustments = adjustment_reader.load_adjustments(
columns,
query_days,
self.assets,
)
self.assertEqual(adjustments, [{}, {}])
baseline_reader = BcolzDailyBarReader(self.bcolz_path)
pricing_loader = USEquityPricingLoader(
baseline_reader,
adjustment_reader,
)
closes, volumes = pricing_loader.load_adjusted_array(
columns,
DataFrame(True, index=query_days, columns=self.assets),
)
expected_baseline_closes = self.bcolz_writer.expected_values_2d(
query_days,
self.assets,
'close',
)
expected_baseline_volumes = self.bcolz_writer.expected_values_2d(
query_days,
self.assets,
'volume',
)
# AdjustedArrays should yield the same data as the expected baseline.
for windowlen in range(1, len(query_days) + 1):
for offset, window in enumerate(closes.traverse(windowlen)):
assert_array_equal(
expected_baseline_closes[offset:offset + windowlen],
window,
)
for offset, window in enumerate(volumes.traverse(windowlen)):
assert_array_equal(
expected_baseline_volumes[offset:offset + windowlen],
window,
)
# Verify that we checked up to the longest possible window.
with self.assertRaises(WindowLengthTooLong):
closes.traverse(windowlen + 1)
with self.assertRaises(WindowLengthTooLong):
volumes.traverse(windowlen + 1)
def create_bar_reader(cls, tempdir):
resources = {
cls.AAPL: join(TEST_RESOURCE_PATH, 'AAPL.csv'),
cls.MSFT: join(TEST_RESOURCE_PATH, 'MSFT.csv'),
cls.BRK_A: join(TEST_RESOURCE_PATH, 'BRK-A.csv'),
}
raw_data = {
asset: read_csv(path, parse_dates=['day']).set_index('day')
for asset, path in iteritems(resources)
}
# Add 'price' column as an alias because all kinds of stuff in zipline
# depends on it being present. :/
for frame in raw_data.values():
frame['price'] = frame['close']
writer = DailyBarWriterFromCSVs(resources)
data_path = tempdir.getpath('testdata.bcolz')
table = writer.write(data_path, trading_days, cls.assets)
return raw_data, BcolzDailyBarReader(table)
def setUpClass(cls):
cls.first_asset_start = Timestamp('2015-04-01', tz='UTC')
cls.env = TradingEnvironment()
cls.trading_day = cls.env.trading_day
cls.asset_info = make_rotating_asset_info(
num_assets=6,
first_start=cls.first_asset_start,
frequency=cls.trading_day,
periods_between_starts=4,
asset_lifetime=8,
)
cls.all_assets = cls.asset_info.index
cls.all_dates = date_range(
start=cls.first_asset_start,
end=cls.asset_info['end_date'].max(),
freq=cls.trading_day,
)
cls.env.write_data(equities_df=cls.asset_info)
cls.finder = cls.env.asset_finder
cls.temp_dir = TempDirectory()
cls.temp_dir.create()
cls.writer = SyntheticDailyBarWriter(
asset_info=cls.asset_info[['start_date', 'end_date']],
calendar=cls.all_dates,
)
table = cls.writer.write(
cls.temp_dir.getpath('testdata.bcolz'),
cls.all_dates,
cls.all_assets,
)
cls.ffc_loader = USEquityPricingLoader(
BcolzDailyBarReader(table),
NullAdjustmentReader(),
)
def test_read_with_adjustments(self):
columns = [USEquityPricing.high, USEquityPricing.volume]
query_days = self.calendar_days_between(TEST_QUERY_START,
TEST_QUERY_STOP)
baseline_reader = BcolzDailyBarReader(self.bcolz_path)
adjustment_reader = SQLiteAdjustmentReader(self.db_path)
pricing_loader = USEquityPricingLoader(
baseline_reader,
adjustment_reader,
)
closes, volumes = pricing_loader.load_adjusted_array(
columns,
DataFrame(True, index=query_days, columns=arange(1, 7)),
)
expected_baseline_highs = self.bcolz_writer.expected_values_2d(
query_days,
self.assets,
'high',
)
expected_baseline_volumes = self.bcolz_writer.expected_values_2d(
query_days,
self.assets,
'volume',
)
# At each point in time, the AdjustedArrays should yield the baseline
# with all adjustments up to that date applied.
for windowlen in range(1, len(query_days) + 1):
for offset, window in enumerate(closes.traverse(windowlen)):
baseline = expected_baseline_highs[offset:offset + windowlen]
baseline_dates = query_days[offset:offset + windowlen]
expected_adjusted_highs = self.apply_adjustments(
baseline_dates,
self.assets,
baseline,
# Apply all adjustments.
concat([SPLITS, MERGERS, DIVIDENDS], ignore_index=True),
)
assert_allclose(expected_adjusted_highs, window)
for offset, window in enumerate(volumes.traverse(windowlen)):
baseline = expected_baseline_volumes[offset:offset + windowlen]
baseline_dates = query_days[offset:offset + windowlen]
# Apply only splits and invert the ratio.
adjustments = SPLITS.copy()
adjustments.ratio = 1 / adjustments.ratio
expected_adjusted_volumes = self.apply_adjustments(
baseline_dates,
self.assets,
baseline,
adjustments,
)
# FIXME: Make AdjustedArray properly support integral types.
assert_array_equal(
expected_adjusted_volumes,
window.astype(uint32),
)
# Verify that we checked up to the longest possible window.
with self.assertRaises(WindowLengthTooLong):
closes.traverse(windowlen + 1)
with self.assertRaises(WindowLengthTooLong):
volumes.traverse(windowlen + 1)