def _list_bundle(self):
return {
os.path.join(pth.data_path(['bundle', d], environ=self.environ))
for d in os.listdir(
pth.data_path(['bundle'], environ=self.environ),
)
}
def find_most_recent_time(bundle_name):
"""
Find most recent "time folder" for a given bundle.
:param bundle_name:
The name of the targeted bundle.
:return folder:
The name of the time folder.
"""
try:
bundle_folders = os.listdir(data_path([bundle_name]), )
except OSError:
return None
most_recent_bundle = dict()
for folder in bundle_folders:
date = from_bundle_ingest_dirname(folder)
if not most_recent_bundle or date > \
most_recent_bundle[list(most_recent_bundle.keys())[0]]:
most_recent_bundle = dict()
most_recent_bundle[folder] = date
if most_recent_bundle:
return list(most_recent_bundle.keys())[0]
else:
return None
def ingestions_for_bundle(bundle, environ=None):
return sorted(
(from_bundle_ingest_dirname(ing)
for ing in os.listdir(pth.data_path([bundle], environ))
if not pth.hidden(ing)),
reverse=True,
)
def ingestions_for_bundle(bundle, environ=None):
return sorted(
(from_bundle_ingest_dirname(ing)
for ing in os.listdir(pth.data_path([bundle], environ))
if not pth.hidden(ing)),
reverse=True,
)
def most_recent_data(bundle_name, timestamp, environ=None):
"""Get the path to the most recent data after ``date``for the
given bundle.
Parameters
----------
bundle_name : str
The name of the bundle to lookup.
timestamp : datetime
The timestamp to begin searching on or before.
environ : dict, optional
An environment dict to forward to catalyst_root.
"""
if bundle_name not in bundles:
raise UnknownBundle(bundle_name)
try:
candidates = os.listdir(
pth.data_path([bundle_name], environ=environ),
)
return pth.data_path(
[bundle_name,
max(
filter(complement(pth.hidden), candidates),
key=from_bundle_ingest_dirname,
)],
environ=environ,
)
except (ValueError, OSError) as e:
if getattr(e, 'errno', errno.ENOENT) != errno.ENOENT:
raise
raise ValueError(
'no data for bundle {bundle!r} on or before {timestamp}\n'
'maybe you need to run: $ catalyst ingest -b {bundle}'.format(
bundle=bundle_name,
timestamp=timestamp,
),
)
def most_recent_data(bundle_name, timestamp, environ=None):
"""Get the path to the most recent data after ``date``for the
given bundle.
Parameters
----------
bundle_name : str
The name of the bundle to lookup.
timestamp : datetime
The timestamp to begin searching on or before.
environ : dict, optional
An environment dict to forward to catalyst_root.
"""
if bundle_name not in bundles:
raise UnknownBundle(bundle_name)
try:
candidates = os.listdir(
pth.data_path([bundle_name], environ=environ),
)
return pth.data_path(
[bundle_name,
max(
filter(complement(pth.hidden), candidates),
key=from_bundle_ingest_dirname,
)],
environ=environ,
)
except (ValueError, OSError) as e:
if getattr(e, 'errno', errno.ENOENT) != errno.ENOENT:
raise
raise ValueError(
'no data for bundle {bundle!r} on or before {timestamp}\n'
'maybe you need to run: $ catalyst ingest -b {bundle}'.format(
bundle=bundle_name,
timestamp=timestamp,
),
)
def adjustment_db_path(bundle_name, timestr, environ=None):
return pth.data_path(
adjustment_db_relative(bundle_name, timestr, environ),
environ=environ,
)
def clean(name,
before=None,
after=None,
keep_last=None,
environ=os.environ):
"""Clean up data that was created with ``ingest`` or
``$ python -m catalyst ingest``
Parameters
----------
name : str
The name of the bundle to remove data for.
before : datetime, optional
Remove data ingested before this date.
This argument is mutually exclusive with: keep_last
after : datetime, optional
Remove data ingested after this date.
This argument is mutually exclusive with: keep_last
keep_last : int, optional
Remove all but the last ``keep_last`` ingestions.
This argument is mutually exclusive with:
before
after
environ : mapping, optional
The environment variables. Defaults of os.environ.
Returns
-------
cleaned : set[str]
The names of the runs that were removed.
Raises
------
BadClean
Raised when ``before`` and or ``after`` are passed with
``keep_last``. This is a subclass of ``ValueError``.
"""
try:
all_runs = sorted(
filter(
complement(pth.hidden),
os.listdir(pth.data_path([name], environ=environ)),
),
key=from_bundle_ingest_dirname,
)
except OSError as e:
if e.errno != errno.ENOENT:
raise
raise UnknownBundle(name)
if ((before is not None or after is not None) and
keep_last is not None):
raise BadClean(before, after, keep_last)
if keep_last is None:
def should_clean(name):
dt = from_bundle_ingest_dirname(name)
return (
(before is not None and dt < before) or
(after is not None and dt > after)
)
elif keep_last >= 0:
last_n_dts = set(take(keep_last, reversed(all_runs)))
def should_clean(name):
return name not in last_n_dts
else:
raise BadClean(before, after, keep_last)
cleaned = set()
for run in all_runs:
if should_clean(run):
path = pth.data_path([name, run], environ=environ)
shutil.rmtree(path)
cleaned.add(path)
return cleaned
def daily_path(bundle_name, timestr, environ=None):
return pth.data_path(
daily_relative(bundle_name, timestr, environ),
environ=environ,
)
def five_minute_path(bundle_name, timestr, environ=None):
return pth.data_path(
five_minute_relative(bundle_name, timestr, environ),
environ=environ,
)
def asset_db_path(bundle_name, timestr, environ=None, db_version=None):
return pth.data_path(
asset_db_relative(bundle_name, timestr, environ, db_version),
environ=environ,
)
def ingest(name,
environ=os.environ,
timestamp=None,
assets_versions=(),
show_progress=False,
is_compile=False):
"""Ingest data for a given bundle.
Parameters
----------
name : str
The name of the bundle.
environ : mapping, optional
The environment variables. By default this is os.environ.
timestamp : datetime, optional
The timestamp to use for the load.
By default this is the current time.
assets_versions : Iterable[int], optional
Versions of the assets db to which to downgrade.
show_progress : bool, optional
Tell the ingest function to display the progress where possible.
"""
try:
bundle = bundles[name]
except KeyError:
raise UnknownBundle(name)
calendar = get_calendar(bundle.calendar_name)
start_session = bundle.start_session
end_session = bundle.end_session
if start_session is None or start_session < calendar.first_session:
start_session = calendar.first_session
if end_session is None or end_session > calendar.last_session:
end_session = calendar.last_session
if timestamp is None:
timestamp = pd.Timestamp.utcnow()
timestamp = timestamp.tz_convert('utc').tz_localize(None)
timestr = to_bundle_ingest_dirname(timestamp)
cachepath = cache_path(name, environ=environ)
pth.ensure_directory(pth.data_path([name, timestr], environ=environ))
pth.ensure_directory(cachepath)
with dataframe_cache(cachepath, clean_on_failure=False) as cache, \
ExitStack() as stack:
# we use `cleanup_on_failure=False` so that we don't purge the
# cache directory if the load fails in the middle
if bundle.create_writers:
wd = stack.enter_context(working_dir(
pth.data_path([], environ=environ))
)
daily_bars_path = wd.ensure_dir(
*daily_relative(
name, timestr, environ=environ,
)
)
daily_bar_writer = BcolzDailyBarWriter(
daily_bars_path,
calendar,
start_session,
end_session,
)
# Do an empty write to ensure that the daily ctables exist
# when we create the SQLiteAdjustmentWriter below. The
# SQLiteAdjustmentWriter needs to open the daily ctables so
# that it can compute the adjustment ratios for the dividends.
daily_bar_writer.write(())
five_minute_bar_writer = BcolzFiveMinuteBarWriter(
wd.ensure_dir(*five_minute_relative(
name, timestr, environ=environ)
),
calendar,
start_session,
end_session,
five_minutes_per_day=bundle.five_minutes_per_day,
)
minute_bar_writer = BcolzMinuteBarWriter(
wd.ensure_dir(*minute_relative(
name, timestr, environ=environ)
),
calendar,
start_session,
end_session,
minutes_per_day=bundle.minutes_per_day,
)
assets_db_path = wd.getpath(*asset_db_relative(
name, timestr, environ=environ,
))
asset_db_writer = AssetDBWriter(assets_db_path)
adjustment_db_writer = stack.enter_context(
SQLiteAdjustmentWriter(
wd.getpath(*adjustment_db_relative(
name, timestr, environ=environ)),
BcolzDailyBarReader(daily_bars_path),
calendar.all_sessions,
overwrite=True,
)
)
else:
daily_bar_writer = None
five_minute_bar_writer = None
minute_bar_writer = None
asset_db_writer = None
adjustment_db_writer = None
if assets_versions:
raise ValueError('Need to ingest a bundle that creates '
'writers in order to downgrade the assets'
' db.')
bundle.ingest(
environ,
asset_db_writer,
minute_bar_writer,
five_minute_bar_writer,
daily_bar_writer,
adjustment_db_writer,
calendar,
start_session,
end_session,
cache,
show_progress,
is_compile,
pth.data_path([name, timestr], environ=environ),
)
for version in sorted(set(assets_versions), reverse=True):
version_path = wd.getpath(*asset_db_relative(
name, timestr, environ=environ, db_version=version,
))
with working_file(version_path) as wf:
shutil.copy2(assets_db_path, wf.path)
downgrade(wf.path, version)
def ingest(name,
environ=os.environ,
timestamp=None,
assets_versions=(),
show_progress=False,
is_compile=False):
"""Ingest data for a given bundle.
Parameters
----------
name : str
The name of the bundle.
environ : mapping, optional
The environment variables. By default this is os.environ.
timestamp : datetime, optional
The timestamp to use for the load.
By default this is the current time.
assets_versions : Iterable[int], optional
Versions of the assets db to which to downgrade.
show_progress : bool, optional
Tell the ingest function to display the progress where possible.
"""
try:
bundle = bundles[name]
except KeyError:
raise UnknownBundle(name)
calendar = get_calendar(bundle.calendar_name)
start_session = bundle.start_session
end_session = bundle.end_session
if start_session is None or start_session < calendar.first_session:
start_session = calendar.first_session
if end_session is None or end_session > calendar.last_session:
end_session = calendar.last_session
if timestamp is None:
timestamp = pd.Timestamp.utcnow()
timestamp = timestamp.tz_convert('utc').tz_localize(None)
timestr = to_bundle_ingest_dirname(timestamp)
cachepath = cache_path(name, environ=environ)
pth.ensure_directory(pth.data_path([name, timestr], environ=environ))
pth.ensure_directory(cachepath)
with dataframe_cache(cachepath, clean_on_failure=False) as cache, \
ExitStack() as stack:
# we use `cleanup_on_failure=False` so that we don't purge the
# cache directory if the load fails in the middle
if bundle.create_writers:
wd = stack.enter_context(working_dir(
pth.data_path([], environ=environ))
)
daily_bars_path = wd.ensure_dir(
*daily_relative(
name, timestr, environ=environ,
)
)
daily_bar_writer = BcolzDailyBarWriter(
daily_bars_path,
calendar,
start_session,
end_session,
)
# Do an empty write to ensure that the daily ctables exist
# when we create the SQLiteAdjustmentWriter below. The
# SQLiteAdjustmentWriter needs to open the daily ctables so
# that it can compute the adjustment ratios for the dividends.
daily_bar_writer.write(())
minute_bar_writer = BcolzMinuteBarWriter(
wd.ensure_dir(*minute_relative(
name, timestr, environ=environ)
),
calendar,
start_session,
end_session,
minutes_per_day=bundle.minutes_per_day,
)
assets_db_path = wd.getpath(*asset_db_relative(
name, timestr, environ=environ,
))
asset_db_writer = AssetDBWriter(assets_db_path)
adjustment_db_writer = stack.enter_context(
SQLiteAdjustmentWriter(
wd.getpath(*adjustment_db_relative(
name, timestr, environ=environ)),
BcolzDailyBarReader(daily_bars_path),
calendar.all_sessions,
overwrite=True,
)
)
else:
daily_bar_writer = None
minute_bar_writer = None
asset_db_writer = None
adjustment_db_writer = None
if assets_versions:
raise ValueError('Need to ingest a bundle that creates '
'writers in order to downgrade the assets'
' db.')
bundle.ingest(
environ,
asset_db_writer,
minute_bar_writer,
daily_bar_writer,
adjustment_db_writer,
calendar,
start_session,
end_session,
cache,
show_progress,
is_compile,
pth.data_path([name, timestr], environ=environ),
)
for version in sorted(set(assets_versions), reverse=True):
version_path = wd.getpath(*asset_db_relative(
name, timestr, environ=environ, db_version=version,
))
with working_file(version_path) as wf:
shutil.copy2(assets_db_path, wf.path)
downgrade(wf.path, version)
def cache_path(bundle_name, environ=None):
return pth.data_path(
cache_relative(bundle_name, environ),
environ=environ,
)
def _list_bundle(self):
return {
os.path.join(pth.data_path(['bundle', d], environ=self.environ))
for d in os.listdir(
pth.data_path(['bundle'], environ=self.environ), )
}
def cache_path(bundle_name, environ=None):
return pth.data_path(
cache_relative(bundle_name, environ),
environ=environ,
)
def clean(name,
before=None,
after=None,
keep_last=None,
environ=os.environ):
"""Clean up data that was created with ``ingest`` or
``$ python -m catalyst ingest``
Parameters
----------
name : str
The name of the bundle to remove data for.
before : datetime, optional
Remove data ingested before this date.
This argument is mutually exclusive with: keep_last
after : datetime, optional
Remove data ingested after this date.
This argument is mutually exclusive with: keep_last
keep_last : int, optional
Remove all but the last ``keep_last`` ingestions.
This argument is mutually exclusive with:
before
after
environ : mapping, optional
The environment variables. Defaults of os.environ.
Returns
-------
cleaned : set[str]
The names of the runs that were removed.
Raises
------
BadClean
Raised when ``before`` and or ``after`` are passed with
``keep_last``. This is a subclass of ``ValueError``.
"""
try:
all_runs = sorted(
filter(
complement(pth.hidden),
os.listdir(pth.data_path([name], environ=environ)),
),
key=from_bundle_ingest_dirname,
)
except OSError as e:
if e.errno != errno.ENOENT:
raise
raise UnknownBundle(name)
if ((before is not None or after is not None) and
keep_last is not None):
raise BadClean(before, after, keep_last)
if keep_last is None:
def should_clean(name):
dt = from_bundle_ingest_dirname(name)
return (
(before is not None and dt < before) or
(after is not None and dt > after)
)
elif keep_last >= 0:
last_n_dts = set(take(keep_last, reversed(all_runs)))
def should_clean(name):
return name not in last_n_dts
else:
raise BadClean(before, after, keep_last)
cleaned = set()
for run in all_runs:
if should_clean(run):
path = pth.data_path([name, run], environ=environ)
shutil.rmtree(path)
cleaned.add(path)
return cleaned
def adjustment_db_path(bundle_name, timestr, environ=None):
return pth.data_path(
adjustment_db_relative(bundle_name, timestr, environ),
environ=environ,
)
def daily_path(bundle_name, timestr, environ=None):
return pth.data_path(
daily_relative(bundle_name, timestr, environ),
environ=environ,
)
def minute_path(bundle_name, timestr, environ=None):
return pth.data_path(
minute_relative(bundle_name, timestr, environ),
environ=environ,
)
def minute_equity_path(bundle_name, timestr, environ=None):
return pth.data_path(
minute_equity_relative(bundle_name, timestr, environ),
environ=environ,
)
def asset_db_path(bundle_name, timestr, environ=None, db_version=None):
return pth.data_path(
asset_db_relative(bundle_name, timestr, environ, db_version),
environ=environ,
)
