mirror of
https://github.com/wassname/catalyst.git
synced 2026-07-13 17:42:42 +08:00
Scott Sanderson
a8b67d352e
- Split out extra_rows handling into an `ExecutionPlan` subclass.
`ExecutionPlan` now requires the dates and calendar against which a
set of terms will be computed, and now defers to a term's
`compute_extra_rows` method when deciding how many extra rows are
required to compute for that term. This will allow downsampled terms
to request enough extra rows to guarantee that we can maintain consistent
calculation dates.
As a consequence of the above, `TermGraph` now only deals with logical
dependencies, not with metadata surrounding extra row calculations.
This means that TermGraph can be used to generate dependency
visualizations in interactive contexts where we don't yet have a
calendar or start/end dates.
- Refactored test_{filter,factor,classifier} to use check_terms instead
of run_graph. This makes it easier to make changes to TermGraph,
since the testing interface is now to simply provide a dict of terms.
- Refactored BasePipelineTestCase to use fixtures to create an asset
finder. This fixes a potential leak of the test's asset db, which was
not being explicitly cleaned up.
- Refactored test_technical to use BasePipelineTestCase.
- Added a new special term, `InputDates()`, which can be used to request
date labels for inputs. Like `AssetExists`, `InputDates` is provided
in the initial workspace by default.
- Added a default (failing) `_compute` method to `AssetExists` which
provides a more useful error than AttributeError.
67 lines
1.9 KiB
Python
67 lines
1.9 KiB
Python
from __future__ import print_function
|
|
from zipline.assets import AssetFinder
|
|
|
|
from .classifiers import Classifier, CustomClassifier
|
|
from .engine import SimplePipelineEngine
|
|
from .factors import Factor, CustomFactor
|
|
from .filters import Filter, CustomFilter
|
|
from .term import Term
|
|
from .graph import ExecutionPlan, TermGraph
|
|
from .pipeline import Pipeline
|
|
from .loaders import USEquityPricingLoader
|
|
|
|
|
|
def engine_from_files(daily_bar_path,
|
|
adjustments_path,
|
|
asset_db_path,
|
|
calendar,
|
|
warmup_assets=False):
|
|
"""
|
|
Construct a SimplePipelineEngine from local filesystem resources.
|
|
|
|
Parameters
|
|
----------
|
|
daily_bar_path : str
|
|
Path to pass to `BcolzDailyBarReader`.
|
|
adjustments_path : str
|
|
Path to pass to SQLiteAdjustmentReader.
|
|
asset_db_path : str
|
|
Path to pass to `AssetFinder`.
|
|
calendar : pd.DatetimeIndex
|
|
Calendar to use for the loader.
|
|
warmup_assets : bool, optional
|
|
Whether or not to populate AssetFinder caches. This can speed up
|
|
initial latency on subsequent pipeline runs, at the cost of extra
|
|
memory consumption. Default is False
|
|
"""
|
|
loader = USEquityPricingLoader.from_files(daily_bar_path, adjustments_path)
|
|
|
|
if not asset_db_path.startswith("sqlite:"):
|
|
asset_db_path = "sqlite:///" + asset_db_path
|
|
asset_finder = AssetFinder(asset_db_path)
|
|
if warmup_assets:
|
|
results = asset_finder.retrieve_all(asset_finder.sids)
|
|
print("Warmed up %d assets." % len(results))
|
|
|
|
return SimplePipelineEngine(
|
|
lambda _: loader,
|
|
calendar,
|
|
asset_finder,
|
|
)
|
|
|
|
|
|
__all__ = (
|
|
'Classifier',
|
|
'CustomFactor',
|
|
'CustomFilter',
|
|
'CustomClassifier',
|
|
'engine_from_files',
|
|
'ExecutionPlan',
|
|
'Factor',
|
|
'Filter',
|
|
'Pipeline',
|
|
'SimplePipelineEngine',
|
|
'Term',
|
|
'TermGraph',
|
|
)
|