def test_optionally(self):
error = TypeError('arg must be int')
def preprocessor(func, argname, arg):
if not isinstance(arg, int):
raise error
return arg
@preprocess(a=optionally(preprocessor))
def f(a):
return a
self.assertIs(f(1), 1)
self.assertIsNone(f(None))
with self.assertRaises(TypeError) as e:
f('a')
self.assertIs(e.exception, error)
def test_optionally(self):
error = TypeError('arg must be int')
def preprocessor(func, argname, arg):
if not isinstance(arg, int):
raise error
return arg
@preprocess(a=optionally(preprocessor))
def f(a):
return a
self.assertIs(f(1), 1)
self.assertIsNone(f(None))
with self.assertRaises(TypeError) as e:
f('a')
self.assertIs(e.exception, error)
def _make_bundle_core():
"""Create a family of data bundle functions that read from the same
bundle mapping.
Returns
-------
bundles : mappingproxy
The mapping of bundles to bundle payloads.
register_bundle : Bundle
A bundle instance to add to the ``bundles`` mapping.
register : callable
The function which registers new bundles in the ``bundles`` mapping.
unregister : callable
The function which deregisters bundles from the ``bundles`` mapping.
ingest : callable
The function which downloads and write data for a given data bundle.
load : callable
The function which loads the ingested bundles back into memory.
clean : callable
The function which cleans up data written with ``ingest``.
"""
_bundles = {} # the registered bundles
# Expose _bundles through a proxy so that users cannot mutate this
# accidentally. Users may go through `register` to update this which will
# warn when trampling another bundle.
bundles = mappingproxy(_bundles)
def register_bundle(bundle_cls,
asset_filter=None,
start_session=None,
end_session=None,
create_writers=True):
bundle = bundle_cls(asset_filter=asset_filter)
return register(
bundle.name,
bundle.ingest,
calendar_name=bundle.calendar_name,
minutes_per_day=bundle.minutes_per_day,
five_minutes_per_day=bundle.five_minutes_per_day,
start_session=start_session,
end_session=end_session,
create_writers=create_writers,
)
@curry
def register(name,
f,
calendar_name='OPEN',
start_session=None,
end_session=None,
minutes_per_day=1440,
five_minutes_per_day=288,
create_writers=True):
"""Register a data bundle ingest function.
Parameters
----------
name : str
The name of the bundle.
f : callable
The ingest function. This function will be passed:
environ : mapping
The environment this is being run with.
asset_db_writer : AssetDBWriter
The asset db writer to write into.
minute_bar_writer : BcolzMinuteBarWriter
The minute bar writer to write into.
daily_bar_writer : BcolzDailyBarWriter
The daily bar writer to write into.
adjustment_writer : SQLiteAdjustmentWriter
The adjustment db writer to write into.
calendar : catalyst.utils.calendars.TradingCalendar
The trading calendar to ingest for.
start_session : pd.Timestamp
The first session of data to ingest.
end_session : pd.Timestamp
The last session of data to ingest.
cache : DataFrameCache
A mapping object to temporarily store dataframes.
This should be used to cache intermediates in case the load
fails. This will be automatically cleaned up after a
successful load.
show_progress : bool
Show the progress for the current load where possible.
calendar_name : str, optional
The name of a calendar used to align bundle data.
Default is 'NYSE'.
start_session : pd.Timestamp, optional
The first session for which we want data. If not provided,
or if the date lies outside the range supported by the
calendar, the first_session of the calendar is used.
end_session : pd.Timestamp, optional
The last session for which we want data. If not provided,
or if the date lies outside the range supported by the
calendar, the last_session of the calendar is used.
minutes_per_day : int, optional
The number of minutes in each normal trading day.
create_writers : bool, optional
Should the ingest machinery create the writers for the ingest
function. This can be disabled as an optimization for cases where
they are not needed, like the ``quantopian-quandl`` bundle.
Notes
-----
This function my be used as a decorator, for example:
.. code-block:: python
@register('quandl')
def quandl_ingest_function(...):
...
See Also
--------
catalyst.data.bundles.bundles
"""
if name in bundles:
warnings.warn(
'Overwriting bundle with name %r' % name,
stacklevel=3,
)
# NOTE: We don't eagerly compute calendar values here because
# `register` is called at module scope in catalyst, and creating a
# calendar currently takes between 0.5 and 1 seconds, which causes a
# noticeable delay on the catalyst CLI.
_bundles[name] = RegisteredBundle(
calendar_name=calendar_name,
start_session=start_session,
end_session=end_session,
minutes_per_day=minutes_per_day,
five_minutes_per_day=five_minutes_per_day,
ingest=f,
create_writers=create_writers,
)
return f
def unregister(name):
"""Unregister a bundle.
Parameters
----------
name : str
The name of the bundle to unregister.
Raises
------
UnknownBundle
Raised when no bundle has been registered with the given name.
See Also
--------
catalyst.data.bundles.bundles
"""
try:
del _bundles[name]
except KeyError:
raise UnknownBundle(name)
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 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 load(name, environ=os.environ, timestamp=None):
"""Loads a previously ingested bundle.
Parameters
----------
name : str
The name of the bundle.
environ : mapping, optional
The environment variables. Defaults of os.environ.
timestamp : datetime, optional
The timestamp of the data to lookup.
Defaults to the current time.
Returns
-------
bundle_data : BundleData
The raw data readers for this bundle.
"""
if timestamp is None:
timestamp = pd.Timestamp.utcnow()
timestr = most_recent_data(name, timestamp, environ=environ)
return BundleData(
asset_finder=AssetFinder(
asset_db_path(name, timestr, environ=environ),
),
minute_bar_reader=BcolzMinuteBarReader(
minute_path(name, timestr, environ=environ),
),
five_minute_bar_reader=BcolzFiveMinuteBarReader(
five_minute_path(name, timestr, environ=environ),
),
daily_bar_reader=BcolzDailyBarReader(
daily_path(name, timestr, environ=environ),
),
adjustment_reader=SQLiteAdjustmentReader(
adjustment_db_path(name, timestr, environ=environ),
),
)
@preprocess(
before=optionally(ensure_timestamp),
after=optionally(ensure_timestamp),
)
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
return BundleCore(
bundles,
register_bundle,
register,
unregister,
ingest,
load,
clean,
)
class BlazeEstimatesLoader(PipelineLoader):
"""An abstract pipeline loader for the estimates datasets that loads
data from a blaze expression.
Parameters
----------
expr : Expr
The expression representing the data to load.
columns : dict[str -> str]
A dict mapping BoundColumn names to the associated names in `expr`.
resources : dict, optional
Mapping from the loadable terms of ``expr`` to actual data resources.
odo_kwargs : dict, optional
Extra keyword arguments to pass to odo when executing the expression.
data_query_time : time, optional
The time to use for the data query cutoff.
data_query_tz : tzinfo or str
The timezeone to use for the data query cutoff.
checkpoints : Expr, optional
The expression representing checkpointed data to be used for faster
forward-filling of data from `expr`.
Notes
-----
The expression should have a tabular dshape of::
Dim * {{
{SID_FIELD_NAME}: int64,
{TS_FIELD_NAME}: datetime,
{FISCAL_YEAR_FIELD_NAME}: float64,
{FISCAL_QUARTER_FIELD_NAME}: float64,
{EVENT_DATE_FIELD_NAME}: datetime,
}}
And other dataset-specific fields, where each row of the table is a
record including the sid to identify the company, the timestamp where we
learned about the announcement, and the date of the event.
If the '{TS_FIELD_NAME}' field is not included it is assumed that we
start the backtest with knowledge of all announcements.
"""
__doc__ = __doc__.format(
SID_FIELD_NAME=SID_FIELD_NAME,
TS_FIELD_NAME=TS_FIELD_NAME,
FISCAL_YEAR_FIELD_NAME=FISCAL_YEAR_FIELD_NAME,
FISCAL_QUARTER_FIELD_NAME=FISCAL_QUARTER_FIELD_NAME,
EVENT_DATE_FIELD_NAME=EVENT_DATE_FIELD_NAME,
)
@preprocess(data_query_tz=optionally(ensure_timezone))
def __init__(self,
expr,
columns,
resources=None,
odo_kwargs=None,
data_query_time=None,
data_query_tz=None,
checkpoints=None):
dshape = expr.dshape
if not istabular(dshape):
raise ValueError(
'expression dshape must be tabular, got: %s' % dshape,
)
required_cols = list(
required_estimates_fields(columns)
)
self._expr = bind_expression_to_resources(
expr[required_cols],
resources,
)
self._columns = columns
self._odo_kwargs = odo_kwargs if odo_kwargs is not None else {}
check_data_query_args(data_query_time, data_query_tz)
self._data_query_time = data_query_time
self._data_query_tz = data_query_tz
self._checkpoints = checkpoints
def load_adjusted_array(self, columns, dates, assets, mask):
# Only load requested columns.
requested_column_names = [self._columns[column.name]
for column in columns]
raw = load_raw_data(
assets,
dates,
self._data_query_time,
self._data_query_tz,
self._expr[sorted(metadata_columns.union(requested_column_names))],
self._odo_kwargs,
checkpoints=self._checkpoints,
)
return self.loader(
raw,
{column.name: self._columns[column.name] for column in columns},
).load_adjusted_array(
columns,
dates,
assets,
mask,
)
@property
def columns(self):
return self._columns
class BlazeLoader(dict):
"""A PipelineLoader for datasets constructed with ``from_blaze``.
Parameters
----------
dsmap : mapping, optional
An initial mapping of datasets to ``ExprData`` objects.
NOTE: Further mutations to this map will not be reflected by this
object.
data_query_time : time, optional
The time to use for the data query cutoff.
data_query_tz : tzinfo or str, optional
The timezeone to use for the data query cutoff.
pool : Pool, optional
The pool to use to run blaze queries concurrently. This object must
support ``imap_unordered``, ``apply`` and ``apply_async`` methods.
Attributes
----------
pool : Pool
The pool to use to run blaze queries concurrently. This object must
support ``imap_unordered``, ``apply`` and ``apply_async`` methods.
It is possible to change the pool after the loader has been
constructed. This allows us to set a new pool for the ``global_loader``
like: ``global_loader.pool = multiprocessing.Pool(4)``.
See Also
--------
:class:`catalyst.utils.pool.SequentialPool`
:class:`multiprocessing.Pool`
"""
@preprocess(data_query_tz=optionally(ensure_timezone))
def __init__(self,
dsmap=None,
data_query_time=None,
data_query_tz=None,
pool=SequentialPool()):
self.update(dsmap or {})
check_data_query_args(data_query_time, data_query_tz)
self._data_query_time = data_query_time
self._data_query_tz = data_query_tz
# explicitly public
self.pool = pool
@classmethod
@memoize(cache=WeakKeyDictionary())
def global_instance(cls):
return cls()
def __hash__(self):
return id(self)
def __call__(self, column):
if column.dataset in self:
return self
raise KeyError(column)
def __repr__(self):
return '<%s: %s>' % (
type(self).__name__,
super(BlazeLoader, self).__repr__(),
)
def load_adjusted_array(self, columns, dates, assets, mask):
return merge(
self.pool.imap_unordered(
partial(self._load_dataset, dates, assets, mask),
itervalues(groupby(getdataset, columns)),
), )
def _load_dataset(self, dates, assets, mask, columns):
try:
(dataset, ) = set(map(getdataset, columns))
except ValueError:
raise AssertionError('all columns must come from the same dataset')
expr, deltas, checkpoints, odo_kwargs, apply_deltas_adjustments = self[
dataset]
have_sids = (dataset.ndim == 2)
asset_idx = pd.Series(index=assets, data=np.arange(len(assets)))
assets = list(map(int, assets)) # coerce from numpy.int64
added_query_fields = {AD_FIELD_NAME, TS_FIELD_NAME
} | ({SID_FIELD_NAME} if have_sids else set())
requested_columns = set(map(getname, columns))
colnames = sorted(added_query_fields | requested_columns)
data_query_time = self._data_query_time
data_query_tz = self._data_query_tz
lower_dt, upper_dt = normalize_data_query_bounds(
dates[0],
dates[-1],
data_query_time,
data_query_tz,
)
def collect_expr(e, lower):
"""Materialize the expression as a dataframe.
Parameters
----------
e : Expr
The baseline or deltas expression.
lower : datetime
The lower time bound to query.
Returns
-------
result : pd.DataFrame
The resulting dataframe.
Notes
-----
This can return more data than needed. The in memory reindex will
handle this.
"""
predicate = e[TS_FIELD_NAME] <= upper_dt
if lower is not None:
predicate &= e[TS_FIELD_NAME] >= lower
return odo(e[predicate][colnames], pd.DataFrame, **odo_kwargs)
lower, materialized_checkpoints = get_materialized_checkpoints(
checkpoints, colnames, lower_dt, odo_kwargs)
materialized_expr = self.pool.apply_async(collect_expr, (expr, lower))
materialized_deltas = (self.pool.apply(collect_expr,
(deltas, lower)) if deltas
is not None else pd.DataFrame(columns=colnames))
if materialized_checkpoints is not None:
materialized_expr = pd.concat(
(
materialized_checkpoints,
materialized_expr.get(),
),
ignore_index=True,
copy=False,
)
# It's not guaranteed that assets returned by the engine will contain
# all sids from the deltas table; filter out such mismatches here.
if not materialized_deltas.empty and have_sids:
materialized_deltas = materialized_deltas[
materialized_deltas[SID_FIELD_NAME].isin(assets)]
if data_query_time is not None:
for m in (materialized_expr, materialized_deltas):
m.loc[:, TS_FIELD_NAME] = m.loc[:, TS_FIELD_NAME].astype(
'datetime64[ns]')
normalize_timestamp_to_query_time(
m,
data_query_time,
data_query_tz,
inplace=True,
ts_field=TS_FIELD_NAME,
)
# Inline the deltas that changed our most recently known value.
# Also, we reindex by the dates to create a dense representation of
# the data.
sparse_output, non_novel_deltas = overwrite_novel_deltas(
materialized_expr,
materialized_deltas,
dates,
)
# If we ever have cases where we find out about multiple asof_dates'
# data on the same TS, we want to make sure that last_in_date_group
# selects the correct last asof_date's value.
sparse_output.sort_values(AD_FIELD_NAME, inplace=True)
non_novel_deltas.sort_values(AD_FIELD_NAME, inplace=True)
if AD_FIELD_NAME not in requested_columns:
sparse_output.drop(AD_FIELD_NAME, axis=1, inplace=True)
sparse_deltas = last_in_date_group(non_novel_deltas,
dates,
assets,
reindex=False,
have_sids=have_sids)
dense_output = last_in_date_group(sparse_output,
dates,
assets,
reindex=True,
have_sids=have_sids)
ffill_across_cols(dense_output, columns,
{c.name: c.name
for c in columns})
# By default, no non-novel deltas are applied.
def no_adjustments_from_deltas(*args):
return {}
adjustments_from_deltas = no_adjustments_from_deltas
if have_sids:
if apply_deltas_adjustments:
adjustments_from_deltas = adjustments_from_deltas_with_sids
column_view = identity
else:
# If we do not have sids, use the column view to make a single
# column vector which is unassociated with any assets.
column_view = op.itemgetter(np.s_[:, np.newaxis])
if apply_deltas_adjustments:
adjustments_from_deltas = adjustments_from_deltas_no_sids
mask = np.full(
shape=(len(mask), 1),
fill_value=True,
dtype=bool_dtype,
)
return {
column: AdjustedArray(
column_view(
dense_output[column.name].values.astype(column.dtype), ),
mask,
adjustments_from_deltas(
dates,
sparse_output[TS_FIELD_NAME].values,
column_idx,
column.name,
asset_idx,
sparse_deltas,
),
column.missing_value,
)
for column_idx, column in enumerate(columns)
}
def _make_bundle_core():
"""Create a family of data bundle functions that read from the same
bundle mapping.
Returns
-------
bundles : mappingproxy
The mapping of bundles to bundle payloads.
register_bundle : Bundle
A bundle instance to add to the ``bundles`` mapping.
register : callable
The function which registers new bundles in the ``bundles`` mapping.
unregister : callable
The function which deregisters bundles from the ``bundles`` mapping.
ingest : callable
The function which downloads and write data for a given data bundle.
load : callable
The function which loads the ingested bundles back into memory.
clean : callable
The function which cleans up data written with ``ingest``.
"""
_bundles = {} # the registered bundles
# Expose _bundles through a proxy so that users cannot mutate this
# accidentally. Users may go through `register` to update this which will
# warn when trampling another bundle.
bundles = mappingproxy(_bundles)
def register_bundle(bundle_cls,
asset_filter=None,
start_session=None,
end_session=None,
create_writers=True):
bundle = bundle_cls(asset_filter=asset_filter)
return register(
bundle.name,
bundle.ingest,
calendar_name=bundle.calendar_name,
minutes_per_day=bundle.minutes_per_day,
start_session=start_session,
end_session=end_session,
create_writers=create_writers,
)
@curry
def register(name,
f,
calendar_name='OPEN',
start_session=None,
end_session=None,
minutes_per_day=1440,
create_writers=True):
"""Register a data bundle ingest function.
Parameters
----------
name : str
The name of the bundle.
f : callable
The ingest function. This function will be passed:
environ : mapping
The environment this is being run with.
asset_db_writer : AssetDBWriter
The asset db writer to write into.
minute_bar_writer : BcolzMinuteBarWriter
The minute bar writer to write into.
daily_bar_writer : BcolzDailyBarWriter
The daily bar writer to write into.
adjustment_writer : SQLiteAdjustmentWriter
The adjustment db writer to write into.
calendar : catalyst.utils.calendars.TradingCalendar
The trading calendar to ingest for.
start_session : pd.Timestamp
The first session of data to ingest.
end_session : pd.Timestamp
The last session of data to ingest.
cache : DataFrameCache
A mapping object to temporarily store dataframes.
This should be used to cache intermediates in case the load
fails. This will be automatically cleaned up after a
successful load.
show_progress : bool
Show the progress for the current load where possible.
calendar_name : str, optional
The name of a calendar used to align bundle data.
Default is 'NYSE'.
start_session : pd.Timestamp, optional
The first session for which we want data. If not provided,
or if the date lies outside the range supported by the
calendar, the first_session of the calendar is used.
end_session : pd.Timestamp, optional
The last session for which we want data. If not provided,
or if the date lies outside the range supported by the
calendar, the last_session of the calendar is used.
minutes_per_day : int, optional
The number of minutes in each normal trading day.
create_writers : bool, optional
Should the ingest machinery create the writers for the ingest
function. This can be disabled as an optimization for cases where
they are not needed, like the ``quantopian-quandl`` bundle.
Notes
-----
This function my be used as a decorator, for example:
.. code-block:: python
@register('quandl')
def quandl_ingest_function(...):
...
See Also
--------
catalyst.data.bundles.bundles
"""
if name in bundles:
warnings.warn(
'Overwriting bundle with name %r' % name,
stacklevel=3,
)
# NOTE: We don't eagerly compute calendar values here because
# `register` is called at module scope in catalyst, and creating a
# calendar currently takes between 0.5 and 1 seconds, which causes a
# noticeable delay on the catalyst CLI.
_bundles[name] = RegisteredBundle(
calendar_name=calendar_name,
start_session=start_session,
end_session=end_session,
minutes_per_day=minutes_per_day,
ingest=f,
create_writers=create_writers,
)
return f
def unregister(name):
"""Unregister a bundle.
Parameters
----------
name : str
The name of the bundle to unregister.
Raises
------
UnknownBundle
Raised when no bundle has been registered with the given name.
See Also
--------
catalyst.data.bundles.bundles
"""
try:
del _bundles[name]
except KeyError:
raise UnknownBundle(name)
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 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 load(name, environ=os.environ, timestamp=None):
"""Loads a previously ingested bundle.
Parameters
----------
name : str
The name of the bundle.
environ : mapping, optional
The environment variables. Defaults of os.environ.
timestamp : datetime, optional
The timestamp of the data to lookup.
Defaults to the current time.
Returns
-------
bundle_data : BundleData
The raw data readers for this bundle.
"""
if timestamp is None:
timestamp = pd.Timestamp.utcnow()
timestr = most_recent_data(name, timestamp, environ=environ)
return BundleData(
asset_finder=AssetFinder(
asset_db_path(name, timestr, environ=environ),
),
minute_bar_reader=BcolzMinuteBarReader(
minute_path(name, timestr, environ=environ),
),
daily_bar_reader=BcolzDailyBarReader(
daily_path(name, timestr, environ=environ),
),
adjustment_reader=SQLiteAdjustmentReader(
adjustment_db_path(name, timestr, environ=environ),
),
)
@preprocess(
before=optionally(ensure_timestamp),
after=optionally(ensure_timestamp),
)
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
return BundleCore(
bundles,
register_bundle,
register,
unregister,
ingest,
load,
clean,
)