def test_bundle(self):
# # 耗时3秒以内
ingest(TEST_BUNDLE_NAME)
bundle = load(TEST_BUNDLE_NAME)
sids = TEST_SIDS
assert_equal(set(bundle.asset_finder.sids), set(sids))
sessions = self.calendar.all_sessions
actual = bundle.equity_daily_bar_reader.load_raw_arrays(
self.columns,
sessions[sessions.get_loc(self.start_date, 'bfill')],
sessions[sessions.get_loc(self.end_date, 'ffill')],
sids,
)
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder, )
assert_equal(actual, expected_pricing, array_decimal=2)
adjustments_for_cols = bundle.adjustment_reader.load_adjustments(
self.columns,
sessions,
pd.Index(sids),
)
for column, adjustments, expected in zip(self.columns,
adjustments_for_cols,
expected_adjustments):
assert_equal(
adjustments,
expected,
msg=column,
)
def load_data():
print('Loading data...')
from zipline.data.bundles import register
from estimize.zipline.data.bundles.yahoo import yahoo_bundle
tickers = {
'SPY',
}
register(
'yahoo',
yahoo_bundle(tickers),
)
bundles_module.ingest(
'yahoo',
os.environ,
pd.Timestamp.utcnow(),
[],
True,
)
bundles_module.ingest(
'quantopian-quandl',
os.environ,
pd.Timestamp.utcnow(),
[],
True,
)
def ingest_data(bundle_name):
ingest_start_time = time.time()
log.info('prepare "{}" dataset ......'.format(bundle_name))
bundles_module.ingest(bundle_name, show_progress=True)
duration = format(time.time() - ingest_start_time, '0.2f')
log.info('{} was done. duration is {} seconds'.format(
bundle_name, duration))
def test_bundle(self):
environ = {
'CSVDIR': test_resource_path('csvdir_samples', 'csvdir')
}
ingest('csvdir', environ=environ)
bundle = load('csvdir', environ=environ)
sids = 0, 1, 2, 3
assert_equal(set(bundle.asset_finder.sids), set(sids))
for equity in bundle.asset_finder.retrieve_all(sids):
assert_equal(equity.start_date, self.asset_start, msg=equity)
assert_equal(equity.end_date, self.asset_end, msg=equity)
sessions = self.calendar.all_sessions
actual = bundle.equity_daily_bar_reader.load_raw_arrays(
self.columns,
sessions[sessions.get_loc(self.asset_start, 'bfill')],
sessions[sessions.get_loc(self.asset_end, 'ffill')],
sids,
)
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder,
)
assert_equal(actual, expected_pricing, array_decimal=2)
adjs_for_cols = bundle.adjustment_reader.load_pricing_adjustments(
self.columns,
sessions,
pd.Index(sids),
)
assert_equal([sorted(adj.keys()) for adj in adjs_for_cols],
expected_adjustments)
def test_bundle(self):
with open(test_resource_path(
'quandl_samples',
'QUANDL_ARCHIVE.zip'), 'rb') as quandl_response:
self.responses.add(
self.responses.GET,
'https://file_url.mock.quandl',
body=quandl_response.read(),
content_type='application/zip',
status=200,
)
url_map = {
format_metadata_url(self.api_key): test_resource_path(
'quandl_samples',
'metadata.csv.gz',
)
}
zipline_root = self.enter_instance_context(tmp_dir()).path
environ = {
'ZIPLINE_ROOT': zipline_root,
'QUANDL_API_KEY': self.api_key,
}
with patch_read_csv(url_map):
ingest('quandl', environ=environ)
bundle = load('quandl', environ=environ)
sids = 0, 1, 2, 3
assert_equal(set(bundle.asset_finder.sids), set(sids))
sessions = self.calendar.all_sessions
actual = bundle.equity_daily_bar_reader.load_raw_arrays(
self.columns,
sessions[sessions.get_loc(self.start_date, 'bfill')],
sessions[sessions.get_loc(self.end_date, 'ffill')],
sids,
)
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder,
)
assert_equal(actual, expected_pricing, array_decimal=2)
adjs_for_cols = bundle.adjustment_reader.load_pricing_adjustments(
self.columns,
sessions,
pd.Index(sids),
)
for column, adjustments, expected in zip(self.columns,
adjs_for_cols,
expected_adjustments):
assert_equal(
adjustments,
expected,
msg=column,
)
def test_bundle(self):
with open(test_resource_path(
'quandl_samples',
'QUANDL_ARCHIVE.zip'), 'rb') as quandl_response:
self.responses.add(
self.responses.GET,
'https://file_url.mock.quandl',
body=quandl_response.read(),
content_type='application/zip',
status=200,
)
url_map = {
format_metadata_url(self.api_key): test_resource_path(
'quandl_samples',
'metadata.csv.gz',
)
}
zipline_root = self.enter_instance_context(tmp_dir()).path
environ = {
'ZIPLINE_ROOT': zipline_root,
'QUANDL_API_KEY': self.api_key,
}
with patch_read_csv(url_map):
ingest('quandl', environ=environ)
bundle = load('quandl', environ=environ)
sids = 0, 1, 2, 3
assert_equal(set(bundle.asset_finder.sids), set(sids))
sessions = self.calendar.all_sessions
actual = bundle.equity_daily_bar_reader.load_raw_arrays(
self.columns,
sessions[sessions.get_loc(self.start_date, 'bfill')],
sessions[sessions.get_loc(self.end_date, 'ffill')],
sids,
)
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder,
)
assert_equal(actual, expected_pricing, array_decimal=2)
adjs_for_cols = bundle.adjustment_reader.load_pricing_adjustments(
self.columns,
sessions,
pd.Index(sids),
)
for column, adjustments, expected in zip(self.columns,
adjs_for_cols,
expected_adjustments):
assert_equal(
adjustments,
expected,
msg=column,
)
def test_bundle(self):
with open(
join(TEST_RESOURCE_PATH, "quandl_samples",
"QUANDL_ARCHIVE.zip"),
"rb",
) as quandl_response:
self.responses.add(
self.responses.GET,
"https://file_url.mock.quandl",
body=quandl_response.read(),
content_type="application/zip",
status=200,
)
url_map = {
format_metadata_url(self.api_key):
join(
TEST_RESOURCE_PATH,
"quandl_samples",
"metadata.csv.gz",
)
}
zipline_root = self.enter_instance_context(tmp_dir()).path
environ = {
"ZIPLINE_ROOT": zipline_root,
"QUANDL_API_KEY": self.api_key,
}
with patch_read_csv(url_map):
ingest("quandl", environ=environ)
bundle = load("quandl", environ=environ)
sids = 0, 1, 2, 3
assert set(bundle.asset_finder.sids) == set(sids)
sessions = self.calendar.all_sessions
actual = bundle.equity_daily_bar_reader.load_raw_arrays(
self.columns,
sessions[sessions.get_loc(self.start_date, "bfill")],
sessions[sessions.get_loc(self.end_date, "ffill")],
sids,
)
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder, )
np.testing.assert_array_almost_equal(actual,
expected_pricing,
decimal=2)
adjs_for_cols = bundle.adjustment_reader.load_pricing_adjustments(
self.columns,
sessions,
pd.Index(sids),
)
for column, adjustments, expected in zip(self.columns, adjs_for_cols,
expected_adjustments):
assert adjustments == expected, column
def __register_bundle__(self):
from zipline.data.bundles import register
from zipline.data.bundles import ingest
register(
self.bundle_name, # name this whatever you like
self.tradea_bundle(self.symbol_list),
)
ingest(self.bundle_name)
def ingest(bundle, show_progress):
"""Ingest the data for the given bundle.
"""
bundles_module.ingest(
bundle,
os.environ,
pd.Timestamp.utcnow(),
show_progress,
)
def ingest(bundle, show_progress):
"""Ingest the data for the given bundle.
"""
bundles_module.ingest(
bundle,
os.environ,
pd.Timestamp.utcnow(),
show_progress,
)
def ingest(bundle, assets_version, show_progress):
if bundle == 'tdx':
register('tdx', tdx_bundle, 'SHSZ')
bundles_module.ingest(bundle,
os.environ,
pd.Timestamp.utcnow(),
assets_version,
show_progress,
)
def test_bundle(self):
zipline_root = self.enter_instance_context(tmp_dir()).path
environ = {
'ZIPLINE_ROOT': zipline_root,
'QUANDL_API_KEY': self.api_key,
}
# custom bundles need to be registered before use or they will not
# be recognized
register(
'ZacksQuandl',
from_zacks_dump(
test_resource_path('zacks_samples', 'fictitious.csv')))
ingest('ZacksQuandl', environ=environ)
# load bundle now that it has been ingested
bundle = load('ZacksQuandl', environ=environ)
sids = 0, 1, 2
# check sids match
assert_equal(set(bundle.asset_finder.sids), set(sids))
# check asset_{start, end} is the same as {start, end}_date
for equity in bundle.asset_finder.retrieve_all(sids):
assert_equal(equity.start_date, self.asset_start, msg=equity)
assert_equal(equity.end_date, self.asset_end, msg=equity)
# get daily OHLCV data from bundle
sessions = self.calendar.all_sessions
actual = bundle.equity_daily_bar_reader.load_raw_arrays(
self.columns,
sessions[sessions.get_loc(self.asset_start, 'bfill')],
sessions[sessions.get_loc(self.asset_end, 'ffill')],
sids,
)
# get expected data from csv
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder, )
# check OHLCV data matches
assert_equal(actual, expected_pricing, array_decimal=2)
adjustments_for_cols = bundle.adjustment_reader.load_adjustments(
self.columns,
sessions,
pd.Index(sids),
)
for column, adjustments, expected in zip(self.columns,
adjustments_for_cols,
expected_adjustments):
assert_equal(
adjustments,
expected,
msg=column,
)
def ingest(bundle_name, show_progress):
"""Ingest the data for the given bundle.
"""
bundles.ingest(
bundle_name,
os.environ,
datetime.date.today(),
show_progress,
)
def ingest(bundle, assets_version, show_progress):
"""提取指定包的数据
"""
bundles_module.ingest(
bundle,
os.environ,
pd.Timestamp.utcnow(),
assets_version,
show_progress,
)
def ingest(bundle, assets, minute, start, fundamental, assets_version, show_progress):
if bundle == 'tdx':
if assets:
if not os.path.exists(assets):
raise FileNotFoundError
df = pd.read_csv(assets, names=['symbol', 'name'], dtype=str, encoding='utf8')
register_tdx(df,minute,start,fundamental)
else:
register_tdx(None,minute,start,fundamental)
bundles_module.ingest(bundle,
os.environ,
pd.Timestamp.utcnow(),
assets_version,
show_progress,
)
def ingest(bundle, assets, minute, start, fundamental, assets_version, show_progress, writer):
if bundle == 'tdx':
if assets:
if not os.path.exists(assets):
raise FileNotFoundError
df = pd.read_csv(assets, names=['symbol', 'name'], dtype=str, encoding='utf8')
register_tdx(df,minute,start,fundamental)
else:
register_tdx(None,minute,start,fundamental)
bundles_module.ingest(bundle,
os.environ,
pd.Timestamp.utcnow(),
assets_version,
show_progress,
writer=writer
)
def ingest(bundle, assets, minute, start=None, show_progress=True):
if bundle == 'tdx':
if assets:
if not os.path.exists(assets):
raise FileNotFoundError
df = pd.read_csv(assets, names=['symbol', 'name'], dtype=str, encoding='utf8')
register_tdx(df[:1], minute, start)
else:
df = pd.DataFrame({
'symbol': ['000001'],
'name': ['平安银行']
})
register_tdx(df, minute, start)
bundles_module.ingest(bundle,
os.environ,
pd.Timestamp.utcnow(),
show_progress=show_progress,
)
def target_ingest(assets, ingest_minute=False):
if assets:
if not os.path.exists(assets):
raise FileNotFoundError
df = pd.read_csv(assets,
names=['symbol', 'name'],
dtype=str,
encoding='utf8')
register_tdx(df[:1], ingest_minute)
else:
df = pd.DataFrame({'symbol': ['000001'], 'name': ['平安银行']})
register_tdx(df, ingest_minute)
bundles_module.ingest(
'tdx',
os.environ,
pd.Timestamp.utcnow(),
show_progress=True,
)
def target_ingest(assets, ingest_minute=False):
import cn_stock_holidays.zipline.default_calendar
if assets:
if not os.path.exists(assets):
raise FileNotFoundError
df = pd.read_csv(assets,
names=['symbol', 'name'],
dtype=str,
encoding='utf8')
register('tdx', partial(tdx_bundle, df[:1], ingest_minute), 'SHSZ')
else:
df = pd.DataFrame({'symbol': ['000001'], 'name': ['平安银行']})
register('tdx', partial(tdx_bundle, df, ingest_minute), 'SHSZ')
bundles_module.ingest(
'tdx',
os.environ,
pd.Timestamp.utcnow(),
show_progress=True,
)
def test_bundle(self):
environ = {
"CSVDIR": join(
TEST_RESOURCE_PATH,
"csvdir_samples",
"csvdir",
),
}
ingest("csvdir", environ=environ)
bundle = load("csvdir", environ=environ)
sids = 0, 1, 2, 3
assert set(bundle.asset_finder.sids) == set(sids)
for equity in bundle.asset_finder.retrieve_all(sids):
assert equity.start_date == self.asset_start, equity
assert equity.end_date == self.asset_end, equity
sessions = self.calendar.all_sessions
actual = bundle.equity_daily_bar_reader.load_raw_arrays(
self.columns,
sessions[sessions.get_loc(self.asset_start, "bfill")],
sessions[sessions.get_loc(self.asset_end, "ffill")],
sids,
)
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder, )
np.testing.assert_array_almost_equal(actual,
expected_pricing,
decimal=2)
adjs_for_cols = bundle.adjustment_reader.load_pricing_adjustments(
self.columns,
sessions,
pd.Index(sids),
)
assert [sorted(adj.keys())
for adj in adjs_for_cols] == expected_adjustments
def ingest(bundle, assets, minute, start, overwrite, assets_version,
show_progress):
logger.warning(
"this project is no longer maintained, please go to https://github.com/JaysonAlbert/zipline for the new project."
)
if bundle == 'tdx':
if assets:
if not os.path.exists(assets):
raise FileNotFoundError
df = pd.read_csv(assets,
names=['symbol', 'name'],
dtype=str,
encoding='utf8')
register_tdx(df, minute, start, overwrite)
else:
register_tdx(None, minute, start, overwrite)
bundles_module.ingest(
bundle,
os.environ,
pd.Timestamp.utcnow(),
assets_version,
show_progress,
)
bundle,
os.environ,
pd.Timestamp.utcnow(),
assets_version,
show_progress,
)
if __name__ == '__main__':
import sys
start_session = pd.to_datetime('20000124', utc=True)
if len(sys.argv) >= 2:
assets = sys.argv[1]
if not os.path.exists(assets):
raise FileNotFoundError
df = pd.read_csv(assets,
names=['symbol', 'name'],
dtype=str,
encoding='utf8')
register_tdx(df, start=start_session)
else:
register_tdx(minute=True, start=start_session)
bundles_module.ingest(
'tdx',
os.environ,
pd.Timestamp.utcnow(),
show_progress=True,
)
# main()
def test_bundle(self):
url_map = merge(
{
format_wiki_url(
self.api_key,
symbol,
self.start_date,
self.end_date,
): test_resource_path('quandl_samples', symbol + '.csv.gz')
for symbol in self.symbols
},
{
format_metadata_url(self.api_key, n): test_resource_path(
'quandl_samples',
'metadata-%d.csv.gz' % n,
)
for n in (1, 2)
},
)
zipline_root = self.enter_instance_context(tmp_dir()).path
environ = {
'ZIPLINE_ROOT': zipline_root,
'QUANDL_API_KEY': self.api_key,
}
with patch_read_csv(url_map, strict=True):
ingest('quandl', environ=environ)
bundle = load('quandl', environ=environ)
sids = 0, 1, 2, 3
assert_equal(set(bundle.asset_finder.sids), set(sids))
for equity in bundle.asset_finder.retrieve_all(sids):
assert_equal(equity.start_date, self.asset_start, msg=equity)
assert_equal(equity.end_date, self.asset_end, msg=equity)
cal = self.calendar
actual = bundle.daily_bar_reader.load_raw_arrays(
self.columns,
cal[cal.get_loc(self.asset_start, 'bfill')],
cal[cal.get_loc(self.asset_end, 'ffill')],
sids,
)
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder,
)
assert_equal(actual, expected_pricing, array_decimal=2)
adjustments_for_cols = bundle.adjustment_reader.load_adjustments(
self.columns,
cal,
pd.Index(sids),
)
for column, adjustments, expected in zip(self.columns,
adjustments_for_cols,
expected_adjustments):
assert_equal(
adjustments,
expected,
msg=column,
)
# start_date += timedelta(days=1)
start_date = end_date - timedelta(days=365)
while not cal.is_session(start_date):
start_date -= timedelta(days=1)
initialize_client()
import time
start_time = time.time()
register(
'alpaca_api',
# api_to_bundle(interval=['1d', '1m']),
# api_to_bundle(interval=['1m']),
api_to_bundle(interval=['1d']),
calendar_name='NYSE',
start_session=start_date,
end_session=end_date)
assets_version = ((), )[0] # just a weird way to create an empty tuple
bundles_module.ingest(
"alpaca_api",
os.environ,
assets_versions=assets_version,
show_progress=True,
)
print(f"--- It took {timedelta(seconds=time.time() - start_time)} ---")
if __name__ == '__main__':
cal: TradingCalendar = trading_calendars.get_calendar('NYSE')
start_date = pd.Timestamp('1999-11-1', tz='utc')
end_date = pd.Timestamp(date.today() - timedelta(days=1), tz='utc')
while not cal.is_session(end_date):
end_date -= timedelta(days=1)
print('ingesting tiingo-data from: ' + str(start_date) + ' to: ' +
str(end_date))
start_time = time.time()
register('tiingo',
tiingo_bundle,
calendar_name='NYSE',
start_session=start_date,
end_session=end_date)
assets_version = ((), )[0] # just a weird way to create an empty tuple
bundles_module.ingest(
"tiingo",
os.environ,
assets_versions=assets_version,
show_progress=True,
)
print("--- %s seconds ---" % (time.time() - start_time))
def init():
print('Initializing...')
from zipline.data.bundles import register
from estimize.zipline.data.bundles.yahoo import yahoo_bundle
tickers = {
'SPY',
}
register(
'yahoo',
yahoo_bundle(tickers),
)
bundles_module.ingest(
'yahoo',
os.environ,
pd.Timestamp.utcnow(),
[],
True,
)
bundles_module.ingest(
'quantopian-quandl',
os.environ,
pd.Timestamp.utcnow(),
[],
True,
)
injector = Injector([DefaultModule])
asset_info_service = injector.get(AssetInfoService)
estimates_service = injector.get(EstimatesService)
estimize_consensus_service = injector.get(EstimizeConsensusService)
estimize_signal_service = injector.get(EstimizeSignalService)
factor_serivce = injector.get(FactorService)
market_cap_service = injector.get(MarketCapService)
releases_service = injector.get(ReleasesService)
missing_csv_warning = 'Make sure you have added {} to your ./data directory.'
remote_csv_warning = 'There was an issue downloading {}, make sure you are connected to the internet.'
actions = [
('instruments.csv', asset_info_service.get_asset_info, missing_csv_warning),
('estimates.csv', estimates_service.get_estimates, missing_csv_warning),
('consensus.csv', estimize_consensus_service.get_final_consensuses, missing_csv_warning),
('signal_time_series.csv', estimize_signal_service.get_signals, missing_csv_warning),
('market_factors.csv', factor_serivce.get_market_factors, remote_csv_warning),
('market_caps.csv', market_cap_service.get_market_caps, remote_csv_warning),
('releases.csv', releases_service.get_releases, missing_csv_warning),
]
def item_show_func(item):
if item is not None:
return 'Caching {}'.format(item[0])
with click.progressbar(actions, label='Caching Estimize Data', item_show_func=item_show_func) as items:
for item in items:
try:
item[1]()
except:
print('\nERROR: {}'.format(item[2].format(item[0])))
print("calling asset_db_writer")
print("metadata", type(metadata))
# drop metadata nan val which exists in any items first
metadata = metadata.dropna(axis=0, how="any")
# Not sure why symbol_map is needed
symbol_map = pd.Series(metadata.symbol.index, metadata.symbol)
if traceDebug:
print("symbol_map", type(symbol_map))
print(symbol_map)
# 写入基础信息
asset_db_writer.write(equities=metadata)
adjustment_writer.write()
return
bundle_name = 'spy-quotemedia-bundle'
register(
bundle_name,
squant_bundle,
calendar_name='NYSE' # US equities
)
ingest(bundle_name)
__all__ = ['squant_bundle']
# alpha-vantage has a fixed time-window, no point in changing these
start_date = pd.Timestamp('1999-11-1', tz='utc')
end_date = pd.Timestamp(date.today() - timedelta(days=1), tz='utc')
while not cal.is_session(end_date):
end_date -= timedelta(days=1)
print('ingesting alpha_vantage-data from: ' + str(start_date) + ' to: ' +
str(end_date))
start_time = time.time()
register(
'alpha_vantage',
# api_to_bundle(interval=['1d', '1m']),
# api_to_bundle(interval=['1m']),
api_to_bundle(interval=['1d']),
calendar_name='NYSE',
start_session=start_date,
end_session=end_date)
assets_version = ((), )[0] # just a weird way to create an empty tuple
bundles_module.ingest(
"alpha_vantage",
os.environ,
assets_versions=assets_version,
show_progress=True,
)
print("--- %s seconds ---" % (time.time() - start_time))
def test_bundle(self):
url_map = merge(
{
format_wiki_url(
self.api_key,
symbol,
self.start_date,
self.end_date,
): test_resource_path('quandl_samples', symbol + '.csv.gz')
for symbol in self.symbols
},
{
format_metadata_url(self.api_key, n): test_resource_path(
'quandl_samples',
'metadata-%d.csv.gz' % n,
)
for n in (1, 2)
},
)
zipline_root = self.enter_instance_context(tmp_dir()).path
environ = {
'ZIPLINE_ROOT': zipline_root,
'QUANDL_API_KEY': self.api_key,
}
with patch_read_csv(url_map, strict=True):
ingest('quandl', environ=environ)
bundle = load('quandl', environ=environ)
sids = 0, 1, 2, 3
assert_equal(set(bundle.asset_finder.sids), set(sids))
for equity in bundle.asset_finder.retrieve_all(sids):
assert_equal(equity.start_date, self.asset_start, msg=equity)
assert_equal(equity.end_date, self.asset_end, msg=equity)
sessions = self.calendar.all_sessions
actual = bundle.equity_daily_bar_reader.load_raw_arrays(
self.columns,
sessions[sessions.get_loc(self.asset_start, 'bfill')],
sessions[sessions.get_loc(self.asset_end, 'ffill')],
sids,
)
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder,
)
assert_equal(actual, expected_pricing, array_decimal=2)
adjustments_for_cols = bundle.adjustment_reader.load_adjustments(
self.columns,
sessions,
pd.Index(sids),
)
for column, adjustments, expected in zip(self.columns,
adjustments_for_cols,
expected_adjustments):
assert_equal(
adjustments,
expected,
msg=column,
)
while not cal.is_session(start_date):
start_date -= timedelta(days=1)
print(f'Ingest between {start_date} and {end_date}')
# initialize_client()
import time
start_time = time.time()
register(
'custom_csv',
# api_to_bundle(interval=['1d', '1m']),
# api_to_bundle(interval=['1m']),
api_to_bundle(interval=['1d']),
calendar_name='NYSE',
start_session=start_date,
end_session=end_date
)
assets_version = ((),)[0] # just a weird way to create an empty tuple
bundles_module.ingest(
"custom_csv",
os.environ,
assets_versions=assets_version,
show_progress=True,
)
print(f"--- It took {timedelta(seconds=time.time() - start_time)} ---")
