Coverage for python/lsst/pipe/base/pipeline.py: 19%
442 statements
« prev ^ index » next coverage.py v6.5.0, created at 2023-02-01 02:07 -0800
« prev ^ index » next coverage.py v6.5.0, created at 2023-02-01 02:07 -0800
1# This file is part of pipe_base.
2#
3# Developed for the LSST Data Management System.
4# This product includes software developed by the LSST Project
5# (http://www.lsst.org).
6# See the COPYRIGHT file at the top-level directory of this distribution
7# for details of code ownership.
8#
9# This program is free software: you can redistribute it and/or modify
10# it under the terms of the GNU General Public License as published by
11# the Free Software Foundation, either version 3 of the License, or
12# (at your option) any later version.
13#
14# This program is distributed in the hope that it will be useful,
15# but WITHOUT ANY WARRANTY; without even the implied warranty of
16# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17# GNU General Public License for more details.
18#
19# You should have received a copy of the GNU General Public License
20# along with this program. If not, see <http://www.gnu.org/licenses/>.
21from __future__ import annotations
23"""Module defining Pipeline class and related methods.
24"""
26__all__ = ["Pipeline", "TaskDef", "TaskDatasetTypes", "PipelineDatasetTypes", "LabelSpecifier"]
28import copy
29import logging
30import os
31import re
32import urllib.parse
33import warnings
35# -------------------------------
36# Imports of standard modules --
37# -------------------------------
38from dataclasses import dataclass
39from types import MappingProxyType
40from typing import (
41 TYPE_CHECKING,
42 AbstractSet,
43 Callable,
44 ClassVar,
45 Dict,
46 Generator,
47 Iterable,
48 Iterator,
49 Mapping,
50 Optional,
51 Set,
52 Tuple,
53 Type,
54 Union,
55 cast,
56)
58# -----------------------------
59# Imports for other modules --
60from lsst.daf.butler import DatasetType, NamedValueSet, Registry, SkyPixDimension
61from lsst.resources import ResourcePath, ResourcePathExpression
62from lsst.utils import doImportType
63from lsst.utils.introspection import get_full_type_name
65from . import pipelineIR, pipeTools
66from ._task_metadata import TaskMetadata
67from .config import PipelineTaskConfig
68from .configOverrides import ConfigOverrides
69from .connections import iterConnections
70from .pipelineTask import PipelineTask
71from .task import _TASK_METADATA_TYPE
73if TYPE_CHECKING: # Imports needed only for type annotations; may be circular. 73 ↛ 74line 73 didn't jump to line 74, because the condition on line 73 was never true
74 from lsst.obs.base import Instrument
75 from lsst.pex.config import Config
77# ----------------------------------
78# Local non-exported definitions --
79# ----------------------------------
81_LOG = logging.getLogger(__name__)
83# ------------------------
84# Exported definitions --
85# ------------------------
88@dataclass
89class LabelSpecifier:
90 """A structure to specify a subset of labels to load
92 This structure may contain a set of labels to be used in subsetting a
93 pipeline, or a beginning and end point. Beginning or end may be empty,
94 in which case the range will be a half open interval. Unlike python
95 iteration bounds, end bounds are *INCLUDED*. Note that range based
96 selection is not well defined for pipelines that are not linear in nature,
97 and correct behavior is not guaranteed, or may vary from run to run.
98 """
100 labels: Optional[Set[str]] = None
101 begin: Optional[str] = None
102 end: Optional[str] = None
104 def __post_init__(self) -> None:
105 if self.labels is not None and (self.begin or self.end):
106 raise ValueError(
107 "This struct can only be initialized with a labels set or a begin (and/or) end specifier"
108 )
111class TaskDef:
112 """TaskDef is a collection of information about task needed by Pipeline.
114 The information includes task name, configuration object and optional
115 task class. This class is just a collection of attributes and it exposes
116 all of them so that attributes could potentially be modified in place
117 (e.g. if configuration needs extra overrides).
119 Attributes
120 ----------
121 taskName : `str`, optional
122 The fully-qualified `PipelineTask` class name. If not provided,
123 ``taskClass`` must be.
124 config : `lsst.pipe.base.config.PipelineTaskConfig`, optional
125 Instance of the configuration class corresponding to this task class,
126 usually with all overrides applied. This config will be frozen. If
127 not provided, ``taskClass`` must be provided and
128 ``taskClass.ConfigClass()`` will be used.
129 taskClass : `type`, optional
130 `PipelineTask` class object; if provided and ``taskName`` is as well,
131 the caller guarantees that they are consistent. If not provided,
132 ``taskName`` is used to import the type.
133 label : `str`, optional
134 Task label, usually a short string unique in a pipeline. If not
135 provided, ``taskClass`` must be, and ``taskClass._DefaultName`` will
136 be used.
137 """
139 def __init__(
140 self,
141 taskName: Optional[str] = None,
142 config: Optional[PipelineTaskConfig] = None,
143 taskClass: Optional[Type[PipelineTask]] = None,
144 label: Optional[str] = None,
145 ):
146 if taskName is None:
147 if taskClass is None:
148 raise ValueError("At least one of `taskName` and `taskClass` must be provided.")
149 taskName = get_full_type_name(taskClass)
150 elif taskClass is None:
151 taskClass = doImportType(taskName)
152 if config is None:
153 if taskClass is None:
154 raise ValueError("`taskClass` must be provided if `config` is not.")
155 config = taskClass.ConfigClass()
156 if label is None:
157 if taskClass is None:
158 raise ValueError("`taskClass` must be provided if `label` is not.")
159 label = taskClass._DefaultName
160 self.taskName = taskName
161 try:
162 config.validate()
163 except Exception:
164 _LOG.error("Configuration validation failed for task %s (%s)", label, taskName)
165 raise
166 config.freeze()
167 self.config = config
168 self.taskClass = taskClass
169 self.label = label
170 self.connections = config.connections.ConnectionsClass(config=config)
172 @property
173 def configDatasetName(self) -> str:
174 """Name of a dataset type for configuration of this task (`str`)"""
175 return self.label + "_config"
177 @property
178 def metadataDatasetName(self) -> Optional[str]:
179 """Name of a dataset type for metadata of this task, `None` if
180 metadata is not to be saved (`str`)
181 """
182 if self.config.saveMetadata:
183 return self.makeMetadataDatasetName(self.label)
184 else:
185 return None
187 @classmethod
188 def makeMetadataDatasetName(cls, label: str) -> str:
189 """Construct the name of the dataset type for metadata for a task.
191 Parameters
192 ----------
193 label : `str`
194 Label for the task within its pipeline.
196 Returns
197 -------
198 name : `str`
199 Name of the task's metadata dataset type.
200 """
201 return f"{label}_metadata"
203 @property
204 def logOutputDatasetName(self) -> Optional[str]:
205 """Name of a dataset type for log output from this task, `None` if
206 logs are not to be saved (`str`)
207 """
208 if cast(PipelineTaskConfig, self.config).saveLogOutput:
209 return self.label + "_log"
210 else:
211 return None
213 def __str__(self) -> str:
214 rep = "TaskDef(" + self.taskName
215 if self.label:
216 rep += ", label=" + self.label
217 rep += ")"
218 return rep
220 def __eq__(self, other: object) -> bool:
221 if not isinstance(other, TaskDef):
222 return False
223 # This does not consider equality of configs when determining equality
224 # as config equality is a difficult thing to define. Should be updated
225 # after DM-27847
226 return self.taskClass == other.taskClass and self.label == other.label
228 def __hash__(self) -> int:
229 return hash((self.taskClass, self.label))
231 @classmethod
232 def _unreduce(cls, taskName: str, config: PipelineTaskConfig, label: str) -> TaskDef:
233 """Custom callable for unpickling.
235 All arguments are forwarded directly to the constructor; this
236 trampoline is only needed because ``__reduce__`` callables can't be
237 called with keyword arguments.
238 """
239 return cls(taskName=taskName, config=config, label=label)
241 def __reduce__(self) -> Tuple[Callable[[str, PipelineTaskConfig, str], TaskDef], Tuple[str, Config, str]]:
242 return (self._unreduce, (self.taskName, self.config, self.label))
245class Pipeline:
246 """A `Pipeline` is a representation of a series of tasks to run, and the
247 configuration for those tasks.
249 Parameters
250 ----------
251 description : `str`
252 A description of that this pipeline does.
253 """
255 def __init__(self, description: str):
256 pipeline_dict = {"description": description, "tasks": {}}
257 self._pipelineIR = pipelineIR.PipelineIR(pipeline_dict)
259 @classmethod
260 def fromFile(cls, filename: str) -> Pipeline:
261 """Load a pipeline defined in a pipeline yaml file.
263 Parameters
264 ----------
265 filename: `str`
266 A path that points to a pipeline defined in yaml format. This
267 filename may also supply additional labels to be used in
268 subsetting the loaded Pipeline. These labels are separated from
269 the path by a \\#, and may be specified as a comma separated
270 list, or a range denoted as beginning..end. Beginning or end may
271 be empty, in which case the range will be a half open interval.
272 Unlike python iteration bounds, end bounds are *INCLUDED*. Note
273 that range based selection is not well defined for pipelines that
274 are not linear in nature, and correct behavior is not guaranteed,
275 or may vary from run to run.
277 Returns
278 -------
279 pipeline: `Pipeline`
280 The pipeline loaded from specified location with appropriate (if
281 any) subsetting
283 Notes
284 -----
285 This method attempts to prune any contracts that contain labels which
286 are not in the declared subset of labels. This pruning is done using a
287 string based matching due to the nature of contracts and may prune more
288 than it should.
289 """
290 return cls.from_uri(filename)
292 @classmethod
293 def from_uri(cls, uri: ResourcePathExpression) -> Pipeline:
294 """Load a pipeline defined in a pipeline yaml file at a location
295 specified by a URI.
297 Parameters
298 ----------
299 uri: convertible to `ResourcePath`
300 If a string is supplied this should be a URI path that points to a
301 pipeline defined in yaml format, either as a direct path to the
302 yaml file, or as a directory containing a "pipeline.yaml" file (the
303 form used by `write_to_uri` with ``expand=True``). This uri may
304 also supply additional labels to be used in subsetting the loaded
305 Pipeline. These labels are separated from the path by a \\#, and
306 may be specified as a comma separated list, or a range denoted as
307 beginning..end. Beginning or end may be empty, in which case the
308 range will be a half open interval. Unlike python iteration bounds,
309 end bounds are *INCLUDED*. Note that range based selection is not
310 well defined for pipelines that are not linear in nature, and
311 correct behavior is not guaranteed, or may vary from run to run.
312 The same specifiers can be used with a `ResourcePath` object, by
313 being the sole contents in the fragments attribute.
315 Returns
316 -------
317 pipeline: `Pipeline`
318 The pipeline loaded from specified location with appropriate (if
319 any) subsetting
321 Notes
322 -----
323 This method attempts to prune any contracts that contain labels which
324 are not in the declared subset of labels. This pruning is done using a
325 string based matching due to the nature of contracts and may prune more
326 than it should.
327 """
328 # Split up the uri and any labels that were supplied
329 uri, label_specifier = cls._parse_file_specifier(uri)
330 pipeline: Pipeline = cls.fromIR(pipelineIR.PipelineIR.from_uri(uri))
332 # If there are labels supplied, only keep those
333 if label_specifier is not None:
334 pipeline = pipeline.subsetFromLabels(label_specifier)
335 return pipeline
337 def subsetFromLabels(self, labelSpecifier: LabelSpecifier) -> Pipeline:
338 """Subset a pipeline to contain only labels specified in labelSpecifier
340 Parameters
341 ----------
342 labelSpecifier : `labelSpecifier`
343 Object containing labels that describes how to subset a pipeline.
345 Returns
346 -------
347 pipeline : `Pipeline`
348 A new pipeline object that is a subset of the old pipeline
350 Raises
351 ------
352 ValueError
353 Raised if there is an issue with specified labels
355 Notes
356 -----
357 This method attempts to prune any contracts that contain labels which
358 are not in the declared subset of labels. This pruning is done using a
359 string based matching due to the nature of contracts and may prune more
360 than it should.
361 """
362 # Labels supplied as a set
363 if labelSpecifier.labels:
364 labelSet = labelSpecifier.labels
365 # Labels supplied as a range, first create a list of all the labels
366 # in the pipeline sorted according to task dependency. Then only
367 # keep labels that lie between the supplied bounds
368 else:
369 # Create a copy of the pipeline to use when assessing the label
370 # ordering. Use a dict for fast searching while preserving order.
371 # Remove contracts so they do not fail in the expansion step. This
372 # is needed because a user may only configure the tasks they intend
373 # to run, which may cause some contracts to fail if they will later
374 # be dropped
375 pipeline = copy.deepcopy(self)
376 pipeline._pipelineIR.contracts = []
377 labels = {taskdef.label: True for taskdef in pipeline.toExpandedPipeline()}
379 # Verify the bounds are in the labels
380 if labelSpecifier.begin is not None:
381 if labelSpecifier.begin not in labels:
382 raise ValueError(
383 f"Beginning of range subset, {labelSpecifier.begin}, not found in "
384 "pipeline definition"
385 )
386 if labelSpecifier.end is not None:
387 if labelSpecifier.end not in labels:
388 raise ValueError(
389 f"End of range subset, {labelSpecifier.end}, not found in pipeline definition"
390 )
392 labelSet = set()
393 for label in labels:
394 if labelSpecifier.begin is not None:
395 if label != labelSpecifier.begin:
396 continue
397 else:
398 labelSpecifier.begin = None
399 labelSet.add(label)
400 if labelSpecifier.end is not None and label == labelSpecifier.end:
401 break
402 return Pipeline.fromIR(self._pipelineIR.subset_from_labels(labelSet))
404 @staticmethod
405 def _parse_file_specifier(uri: ResourcePathExpression) -> Tuple[ResourcePath, Optional[LabelSpecifier]]:
406 """Split appart a uri and any possible label subsets"""
407 if isinstance(uri, str):
408 # This is to support legacy pipelines during transition
409 uri, num_replace = re.subn("[:](?!\\/\\/)", "#", uri)
410 if num_replace:
411 warnings.warn(
412 f"The pipeline file {uri} seems to use the legacy : to separate "
413 "labels, this is deprecated and will be removed after June 2021, please use "
414 "# instead.",
415 category=FutureWarning,
416 )
417 if uri.count("#") > 1:
418 raise ValueError("Only one set of labels is allowed when specifying a pipeline to load")
419 # Everything else can be converted directly to ResourcePath.
420 uri = ResourcePath(uri)
421 label_subset = uri.fragment or None
423 specifier: Optional[LabelSpecifier]
424 if label_subset is not None:
425 label_subset = urllib.parse.unquote(label_subset)
426 args: Dict[str, Union[Set[str], str, None]]
427 # labels supplied as a list
428 if "," in label_subset:
429 if ".." in label_subset:
430 raise ValueError(
431 "Can only specify a list of labels or a rangewhen loading a Pipline not both"
432 )
433 args = {"labels": set(label_subset.split(","))}
434 # labels supplied as a range
435 elif ".." in label_subset:
436 # Try to de-structure the labelSubset, this will fail if more
437 # than one range is specified
438 begin, end, *rest = label_subset.split("..")
439 if rest:
440 raise ValueError("Only one range can be specified when loading a pipeline")
441 args = {"begin": begin if begin else None, "end": end if end else None}
442 # Assume anything else is a single label
443 else:
444 args = {"labels": {label_subset}}
446 # MyPy doesn't like how cavalier kwarg construction is with types.
447 specifier = LabelSpecifier(**args) # type: ignore
448 else:
449 specifier = None
451 return uri, specifier
453 @classmethod
454 def fromString(cls, pipeline_string: str) -> Pipeline:
455 """Create a pipeline from string formatted as a pipeline document.
457 Parameters
458 ----------
459 pipeline_string : `str`
460 A string that is formatted according like a pipeline document
462 Returns
463 -------
464 pipeline: `Pipeline`
465 """
466 pipeline = cls.fromIR(pipelineIR.PipelineIR.from_string(pipeline_string))
467 return pipeline
469 @classmethod
470 def fromIR(cls, deserialized_pipeline: pipelineIR.PipelineIR) -> Pipeline:
471 """Create a pipeline from an already created `PipelineIR` object.
473 Parameters
474 ----------
475 deserialized_pipeline: `PipelineIR`
476 An already created pipeline intermediate representation object
478 Returns
479 -------
480 pipeline: `Pipeline`
481 """
482 pipeline = cls.__new__(cls)
483 pipeline._pipelineIR = deserialized_pipeline
484 return pipeline
486 @classmethod
487 def fromPipeline(cls, pipeline: Pipeline) -> Pipeline:
488 """Create a new pipeline by copying an already existing `Pipeline`.
490 Parameters
491 ----------
492 pipeline: `Pipeline`
493 An already created pipeline intermediate representation object
495 Returns
496 -------
497 pipeline: `Pipeline`
498 """
499 return cls.fromIR(copy.deepcopy(pipeline._pipelineIR))
501 def __str__(self) -> str:
502 return str(self._pipelineIR)
504 def mergePipeline(self, pipeline: Pipeline) -> None:
505 """Merge another in-memory `Pipeline` object into this one.
507 This merges another pipeline into this object, as if it were declared
508 in the import block of the yaml definition of this pipeline. This
509 modifies this pipeline in place.
511 Parameters
512 ----------
513 pipeline : `Pipeline`
514 The `Pipeline` object that is to be merged into this object.
515 """
516 self._pipelineIR.merge_pipelines((pipeline._pipelineIR,))
518 def addLabelToSubset(self, subset: str, label: str) -> None:
519 """Add a task label from the specified subset.
521 Parameters
522 ----------
523 subset : `str`
524 The labeled subset to modify
525 label : `str`
526 The task label to add to the specified subset.
528 Raises
529 ------
530 ValueError
531 Raised if the specified subset does not exist within the pipeline.
532 Raised if the specified label does not exist within the pipeline.
533 """
534 if label not in self._pipelineIR.tasks:
535 raise ValueError(f"Label {label} does not appear within the pipeline")
536 if subset not in self._pipelineIR.labeled_subsets:
537 raise ValueError(f"Subset {subset} does not appear within the pipeline")
538 self._pipelineIR.labeled_subsets[subset].subset.add(label)
540 def removeLabelFromSubset(self, subset: str, label: str) -> None:
541 """Remove a task label from the specified subset.
543 Parameters
544 ----------
545 subset : `str`
546 The labeled subset to modify
547 label : `str`
548 The task label to remove from the specified subset.
550 Raises
551 ------
552 ValueError
553 Raised if the specified subset does not exist in the pipeline.
554 Raised if the specified label does not exist within the specified
555 subset.
556 """
557 if subset not in self._pipelineIR.labeled_subsets:
558 raise ValueError(f"Subset {subset} does not appear within the pipeline")
559 if label not in self._pipelineIR.labeled_subsets[subset].subset:
560 raise ValueError(f"Label {label} does not appear within the pipeline")
561 self._pipelineIR.labeled_subsets[subset].subset.remove(label)
563 def findSubsetsWithLabel(self, label: str) -> set[str]:
564 """Find any subsets which may contain the specified label.
566 This function returns the name of subsets which return the specified
567 label. May return an empty set if there are no subsets, or no subsets
568 containing the specified label.
570 Parameters
571 ----------
572 label : `str`
573 The task label to use in membership check
575 Returns
576 -------
577 subsets : `set` of `str`
578 Returns a set (possibly empty) of subsets names which contain the
579 specified label.
581 Raises
582 ------
583 ValueError
584 Raised if the specified label does not exist within this pipeline.
585 """
586 results = set()
587 if label not in self._pipelineIR.tasks:
588 raise ValueError(f"Label {label} does not appear within the pipeline")
589 for subset in self._pipelineIR.labeled_subsets.values():
590 if label in subset.subset:
591 results.add(subset.label)
592 return results
594 def addInstrument(self, instrument: Union[Instrument, str]) -> None:
595 """Add an instrument to the pipeline, or replace an instrument that is
596 already defined.
598 Parameters
599 ----------
600 instrument : `~lsst.daf.butler.instrument.Instrument` or `str`
601 Either a derived class object of a `lsst.daf.butler.instrument` or
602 a string corresponding to a fully qualified
603 `lsst.daf.butler.instrument` name.
604 """
605 if isinstance(instrument, str):
606 pass
607 else:
608 # TODO: assume that this is a subclass of Instrument, no type
609 # checking
610 instrument = get_full_type_name(instrument)
611 self._pipelineIR.instrument = instrument
613 def getInstrument(self) -> Optional[str]:
614 """Get the instrument from the pipeline.
616 Returns
617 -------
618 instrument : `str`, or None
619 The fully qualified name of a `lsst.obs.base.Instrument` subclass,
620 name, or None if the pipeline does not have an instrument.
621 """
622 return self._pipelineIR.instrument
624 def addTask(self, task: Union[Type[PipelineTask], str], label: str) -> None:
625 """Add a new task to the pipeline, or replace a task that is already
626 associated with the supplied label.
628 Parameters
629 ----------
630 task: `PipelineTask` or `str`
631 Either a derived class object of a `PipelineTask` or a string
632 corresponding to a fully qualified `PipelineTask` name.
633 label: `str`
634 A label that is used to identify the `PipelineTask` being added
635 """
636 if isinstance(task, str):
637 taskName = task
638 elif issubclass(task, PipelineTask):
639 taskName = get_full_type_name(task)
640 else:
641 raise ValueError(
642 "task must be either a child class of PipelineTask or a string containing"
643 " a fully qualified name to one"
644 )
645 if not label:
646 # in some cases (with command line-generated pipeline) tasks can
647 # be defined without label which is not acceptable, use task
648 # _DefaultName in that case
649 if isinstance(task, str):
650 task_class = doImportType(task)
651 label = task_class._DefaultName
652 self._pipelineIR.tasks[label] = pipelineIR.TaskIR(label, taskName)
654 def removeTask(self, label: str) -> None:
655 """Remove a task from the pipeline.
657 Parameters
658 ----------
659 label : `str`
660 The label used to identify the task that is to be removed
662 Raises
663 ------
664 KeyError
665 If no task with that label exists in the pipeline
667 """
668 self._pipelineIR.tasks.pop(label)
670 def addConfigOverride(self, label: str, key: str, value: object) -> None:
671 """Apply single config override.
673 Parameters
674 ----------
675 label : `str`
676 Label of the task.
677 key: `str`
678 Fully-qualified field name.
679 value : object
680 Value to be given to a field.
681 """
682 self._addConfigImpl(label, pipelineIR.ConfigIR(rest={key: value}))
684 def addConfigFile(self, label: str, filename: str) -> None:
685 """Add overrides from a specified file.
687 Parameters
688 ----------
689 label : `str`
690 The label used to identify the task associated with config to
691 modify
692 filename : `str`
693 Path to the override file.
694 """
695 self._addConfigImpl(label, pipelineIR.ConfigIR(file=[filename]))
697 def addConfigPython(self, label: str, pythonString: str) -> None:
698 """Add Overrides by running a snippet of python code against a config.
700 Parameters
701 ----------
702 label : `str`
703 The label used to identity the task associated with config to
704 modify.
705 pythonString: `str`
706 A string which is valid python code to be executed. This is done
707 with config as the only local accessible value.
708 """
709 self._addConfigImpl(label, pipelineIR.ConfigIR(python=pythonString))
711 def _addConfigImpl(self, label: str, newConfig: pipelineIR.ConfigIR) -> None:
712 if label == "parameters":
713 if newConfig.rest.keys() - self._pipelineIR.parameters.mapping.keys():
714 raise ValueError("Cannot override parameters that are not defined in pipeline")
715 self._pipelineIR.parameters.mapping.update(newConfig.rest)
716 if newConfig.file:
717 raise ValueError("Setting parameters section with config file is not supported")
718 if newConfig.python:
719 raise ValueError("Setting parameters section using python block in unsupported")
720 return
721 if label not in self._pipelineIR.tasks:
722 raise LookupError(f"There are no tasks labeled '{label}' in the pipeline")
723 self._pipelineIR.tasks[label].add_or_update_config(newConfig)
725 def write_to_uri(self, uri: ResourcePathExpression) -> None:
726 """Write the pipeline to a file or directory.
728 Parameters
729 ----------
730 uri : convertible to `ResourcePath`
731 URI to write to; may have any scheme with `ResourcePath` write
732 support or no scheme for a local file/directory. Should have a
733 ``.yaml``.
734 """
735 self._pipelineIR.write_to_uri(uri)
737 def toExpandedPipeline(self) -> Generator[TaskDef, None, None]:
738 """Returns a generator of TaskDefs which can be used to create quantum
739 graphs.
741 Returns
742 -------
743 generator : generator of `TaskDef`
744 The generator returned will be the sorted iterator of tasks which
745 are to be used in constructing a quantum graph.
747 Raises
748 ------
749 NotImplementedError
750 If a dataId is supplied in a config block. This is in place for
751 future use
752 """
753 taskDefs = []
754 for label in self._pipelineIR.tasks:
755 taskDefs.append(self._buildTaskDef(label))
757 # lets evaluate the contracts
758 if self._pipelineIR.contracts is not None:
759 label_to_config = {x.label: x.config for x in taskDefs}
760 for contract in self._pipelineIR.contracts:
761 # execute this in its own line so it can raise a good error
762 # message if there was problems with the eval
763 success = eval(contract.contract, None, label_to_config)
764 if not success:
765 extra_info = f": {contract.msg}" if contract.msg is not None else ""
766 raise pipelineIR.ContractError(
767 f"Contract(s) '{contract.contract}' were not satisfied{extra_info}"
768 )
770 taskDefs = sorted(taskDefs, key=lambda x: x.label)
771 yield from pipeTools.orderPipeline(taskDefs)
773 def _buildTaskDef(self, label: str) -> TaskDef:
774 if (taskIR := self._pipelineIR.tasks.get(label)) is None:
775 raise NameError(f"Label {label} does not appear in this pipeline")
776 taskClass: Type[PipelineTask] = doImportType(taskIR.klass)
777 taskName = get_full_type_name(taskClass)
778 config = taskClass.ConfigClass()
779 overrides = ConfigOverrides()
780 if self._pipelineIR.instrument is not None:
781 overrides.addInstrumentOverride(self._pipelineIR.instrument, taskClass._DefaultName)
782 if taskIR.config is not None:
783 for configIR in (configIr.formatted(self._pipelineIR.parameters) for configIr in taskIR.config):
784 if configIR.dataId is not None:
785 raise NotImplementedError(
786 "Specializing a config on a partial data id is not yet "
787 "supported in Pipeline definition"
788 )
789 # only apply override if it applies to everything
790 if configIR.dataId is None:
791 if configIR.file:
792 for configFile in configIR.file:
793 overrides.addFileOverride(os.path.expandvars(configFile))
794 if configIR.python is not None:
795 overrides.addPythonOverride(configIR.python)
796 for key, value in configIR.rest.items():
797 overrides.addValueOverride(key, value)
798 overrides.applyTo(config)
799 return TaskDef(taskName=taskName, config=config, taskClass=taskClass, label=label)
801 def __iter__(self) -> Generator[TaskDef, None, None]:
802 return self.toExpandedPipeline()
804 def __getitem__(self, item: str) -> TaskDef:
805 return self._buildTaskDef(item)
807 def __len__(self) -> int:
808 return len(self._pipelineIR.tasks)
810 def __eq__(self, other: object) -> bool:
811 if not isinstance(other, Pipeline):
812 return False
813 elif self._pipelineIR == other._pipelineIR:
814 # Shortcut: if the IR is the same, the expanded pipeline must be
815 # the same as well. But the converse is not true.
816 return True
817 else:
818 self_expanded = {td.label: (td.taskClass,) for td in self}
819 other_expanded = {td.label: (td.taskClass,) for td in other}
820 if self_expanded != other_expanded:
821 return False
822 # After DM-27847, we should compare configuration here, or better,
823 # delegated to TaskDef.__eq__ after making that compare configurations.
824 raise NotImplementedError(
825 "Pipelines cannot be compared because config instances cannot be compared; see DM-27847."
826 )
829@dataclass(frozen=True)
830class TaskDatasetTypes:
831 """An immutable struct that extracts and classifies the dataset types used
832 by a `PipelineTask`
833 """
835 initInputs: NamedValueSet[DatasetType]
836 """Dataset types that are needed as inputs in order to construct this Task.
838 Task-level `initInputs` may be classified as either
839 `~PipelineDatasetTypes.initInputs` or
840 `~PipelineDatasetTypes.initIntermediates` at the Pipeline level.
841 """
843 initOutputs: NamedValueSet[DatasetType]
844 """Dataset types that may be written after constructing this Task.
846 Task-level `initOutputs` may be classified as either
847 `~PipelineDatasetTypes.initOutputs` or
848 `~PipelineDatasetTypes.initIntermediates` at the Pipeline level.
849 """
851 inputs: NamedValueSet[DatasetType]
852 """Dataset types that are regular inputs to this Task.
854 If an input dataset needed for a Quantum cannot be found in the input
855 collection(s) or produced by another Task in the Pipeline, that Quantum
856 (and all dependent Quanta) will not be produced.
858 Task-level `inputs` may be classified as either
859 `~PipelineDatasetTypes.inputs` or `~PipelineDatasetTypes.intermediates`
860 at the Pipeline level.
861 """
863 prerequisites: NamedValueSet[DatasetType]
864 """Dataset types that are prerequisite inputs to this Task.
866 Prerequisite inputs must exist in the input collection(s) before the
867 pipeline is run, but do not constrain the graph - if a prerequisite is
868 missing for a Quantum, `PrerequisiteMissingError` is raised.
870 Prerequisite inputs are not resolved until the second stage of
871 QuantumGraph generation.
872 """
874 outputs: NamedValueSet[DatasetType]
875 """Dataset types that are produced by this Task.
877 Task-level `outputs` may be classified as either
878 `~PipelineDatasetTypes.outputs` or `~PipelineDatasetTypes.intermediates`
879 at the Pipeline level.
880 """
882 @classmethod
883 def fromTaskDef(
884 cls,
885 taskDef: TaskDef,
886 *,
887 registry: Registry,
888 include_configs: bool = True,
889 storage_class_mapping: Optional[Mapping[str, str]] = None,
890 ) -> TaskDatasetTypes:
891 """Extract and classify the dataset types from a single `PipelineTask`.
893 Parameters
894 ----------
895 taskDef: `TaskDef`
896 An instance of a `TaskDef` class for a particular `PipelineTask`.
897 registry: `Registry`
898 Registry used to construct normalized `DatasetType` objects and
899 retrieve those that are incomplete.
900 include_configs : `bool`, optional
901 If `True` (default) include config dataset types as
902 ``initOutputs``.
903 storage_class_mapping : `Mapping` of `str` to `StorageClass`, optional
904 If a taskdef contains a component dataset type that is unknown
905 to the registry, its parent StorageClass will be looked up in this
906 mapping if it is supplied. If the mapping does not contain the
907 composite dataset type, or the mapping is not supplied an exception
908 will be raised.
910 Returns
911 -------
912 types: `TaskDatasetTypes`
913 The dataset types used by this task.
915 Raises
916 ------
917 ValueError
918 Raised if dataset type connection definition differs from
919 registry definition.
920 LookupError
921 Raised if component parent StorageClass could not be determined
922 and storage_class_mapping does not contain the composite type, or
923 is set to None.
924 """
926 def makeDatasetTypesSet(
927 connectionType: str,
928 is_input: bool,
929 freeze: bool = True,
930 ) -> NamedValueSet[DatasetType]:
931 """Constructs a set of true `DatasetType` objects
933 Parameters
934 ----------
935 connectionType : `str`
936 Name of the connection type to produce a set for, corresponds
937 to an attribute of type `list` on the connection class instance
938 is_input : `bool`
939 These are input dataset types, else they are output dataset
940 types.
941 freeze : `bool`, optional
942 If `True`, call `NamedValueSet.freeze` on the object returned.
944 Returns
945 -------
946 datasetTypes : `NamedValueSet`
947 A set of all datasetTypes which correspond to the input
948 connection type specified in the connection class of this
949 `PipelineTask`
951 Raises
952 ------
953 ValueError
954 Raised if dataset type connection definition differs from
955 registry definition.
956 LookupError
957 Raised if component parent StorageClass could not be determined
958 and storage_class_mapping does not contain the composite type,
959 or is set to None.
961 Notes
962 -----
963 This function is a closure over the variables ``registry`` and
964 ``taskDef``, and ``storage_class_mapping``.
965 """
966 datasetTypes = NamedValueSet[DatasetType]()
967 for c in iterConnections(taskDef.connections, connectionType):
968 dimensions = set(getattr(c, "dimensions", set()))
969 if "skypix" in dimensions:
970 try:
971 datasetType = registry.getDatasetType(c.name)
972 except LookupError as err:
973 raise LookupError(
974 f"DatasetType '{c.name}' referenced by "
975 f"{type(taskDef.connections).__name__} uses 'skypix' as a dimension "
976 f"placeholder, but does not already exist in the registry. "
977 f"Note that reference catalog names are now used as the dataset "
978 f"type name instead of 'ref_cat'."
979 ) from err
980 rest1 = set(registry.dimensions.extract(dimensions - set(["skypix"])).names)
981 rest2 = set(
982 dim.name for dim in datasetType.dimensions if not isinstance(dim, SkyPixDimension)
983 )
984 if rest1 != rest2:
985 raise ValueError(
986 f"Non-skypix dimensions for dataset type {c.name} declared in "
987 f"connections ({rest1}) are inconsistent with those in "
988 f"registry's version of this dataset ({rest2})."
989 )
990 else:
991 # Component dataset types are not explicitly in the
992 # registry. This complicates consistency checks with
993 # registry and requires we work out the composite storage
994 # class.
995 registryDatasetType = None
996 try:
997 registryDatasetType = registry.getDatasetType(c.name)
998 except KeyError:
999 compositeName, componentName = DatasetType.splitDatasetTypeName(c.name)
1000 if componentName:
1001 if storage_class_mapping is None or compositeName not in storage_class_mapping:
1002 raise LookupError(
1003 "Component parent class cannot be determined, and "
1004 "composite name was not in storage class mapping, or no "
1005 "storage_class_mapping was supplied"
1006 )
1007 else:
1008 parentStorageClass = storage_class_mapping[compositeName]
1009 else:
1010 parentStorageClass = None
1011 datasetType = c.makeDatasetType(
1012 registry.dimensions, parentStorageClass=parentStorageClass
1013 )
1014 registryDatasetType = datasetType
1015 else:
1016 datasetType = c.makeDatasetType(
1017 registry.dimensions, parentStorageClass=registryDatasetType.parentStorageClass
1018 )
1020 if registryDatasetType and datasetType != registryDatasetType:
1021 # The dataset types differ but first check to see if
1022 # they are compatible before raising.
1023 if is_input:
1024 # This DatasetType must be compatible on get.
1025 is_compatible = datasetType.is_compatible_with(registryDatasetType)
1026 else:
1027 # Has to be able to be converted to expect type
1028 # on put.
1029 is_compatible = registryDatasetType.is_compatible_with(datasetType)
1030 if is_compatible:
1031 # For inputs we want the pipeline to use the
1032 # pipeline definition, for outputs it should use
1033 # the registry definition.
1034 if not is_input:
1035 datasetType = registryDatasetType
1036 _LOG.debug(
1037 "Dataset types differ (task %s != registry %s) but are compatible"
1038 " for %s in %s.",
1039 datasetType,
1040 registryDatasetType,
1041 "input" if is_input else "output",
1042 taskDef.label,
1043 )
1044 else:
1045 try:
1046 # Explicitly check for storage class just to
1047 # make more specific message.
1048 _ = datasetType.storageClass
1049 except KeyError:
1050 raise ValueError(
1051 "Storage class does not exist for supplied dataset type "
1052 f"{datasetType} for {taskDef.label}."
1053 ) from None
1054 raise ValueError(
1055 f"Supplied dataset type ({datasetType}) inconsistent with "
1056 f"registry definition ({registryDatasetType}) "
1057 f"for {taskDef.label}."
1058 )
1059 datasetTypes.add(datasetType)
1060 if freeze:
1061 datasetTypes.freeze()
1062 return datasetTypes
1064 # optionally add initOutput dataset for config
1065 initOutputs = makeDatasetTypesSet("initOutputs", is_input=False, freeze=False)
1066 if include_configs:
1067 initOutputs.add(
1068 DatasetType(
1069 taskDef.configDatasetName,
1070 registry.dimensions.empty,
1071 storageClass="Config",
1072 )
1073 )
1074 initOutputs.freeze()
1076 # optionally add output dataset for metadata
1077 outputs = makeDatasetTypesSet("outputs", is_input=False, freeze=False)
1078 if taskDef.metadataDatasetName is not None:
1079 # Metadata is supposed to be of the TaskMetadata type, its
1080 # dimensions correspond to a task quantum.
1081 dimensions = registry.dimensions.extract(taskDef.connections.dimensions)
1083 # Allow the storage class definition to be read from the existing
1084 # dataset type definition if present.
1085 try:
1086 current = registry.getDatasetType(taskDef.metadataDatasetName)
1087 except KeyError:
1088 # No previous definition so use the default.
1089 storageClass = "TaskMetadata" if _TASK_METADATA_TYPE is TaskMetadata else "PropertySet"
1090 else:
1091 storageClass = current.storageClass.name
1093 outputs.update({DatasetType(taskDef.metadataDatasetName, dimensions, storageClass)})
1094 if taskDef.logOutputDatasetName is not None:
1095 # Log output dimensions correspond to a task quantum.
1096 dimensions = registry.dimensions.extract(taskDef.connections.dimensions)
1097 outputs.update({DatasetType(taskDef.logOutputDatasetName, dimensions, "ButlerLogRecords")})
1099 outputs.freeze()
1101 return cls(
1102 initInputs=makeDatasetTypesSet("initInputs", is_input=True),
1103 initOutputs=initOutputs,
1104 inputs=makeDatasetTypesSet("inputs", is_input=True),
1105 prerequisites=makeDatasetTypesSet("prerequisiteInputs", is_input=True),
1106 outputs=outputs,
1107 )
1110@dataclass(frozen=True)
1111class PipelineDatasetTypes:
1112 """An immutable struct that classifies the dataset types used in a
1113 `Pipeline`.
1114 """
1116 packagesDatasetName: ClassVar[str] = "packages"
1117 """Name of a dataset type used to save package versions.
1118 """
1120 initInputs: NamedValueSet[DatasetType]
1121 """Dataset types that are needed as inputs in order to construct the Tasks
1122 in this Pipeline.
1124 This does not include dataset types that are produced when constructing
1125 other Tasks in the Pipeline (these are classified as `initIntermediates`).
1126 """
1128 initOutputs: NamedValueSet[DatasetType]
1129 """Dataset types that may be written after constructing the Tasks in this
1130 Pipeline.
1132 This does not include dataset types that are also used as inputs when
1133 constructing other Tasks in the Pipeline (these are classified as
1134 `initIntermediates`).
1135 """
1137 initIntermediates: NamedValueSet[DatasetType]
1138 """Dataset types that are both used when constructing one or more Tasks
1139 in the Pipeline and produced as a side-effect of constructing another
1140 Task in the Pipeline.
1141 """
1143 inputs: NamedValueSet[DatasetType]
1144 """Dataset types that are regular inputs for the full pipeline.
1146 If an input dataset needed for a Quantum cannot be found in the input
1147 collection(s), that Quantum (and all dependent Quanta) will not be
1148 produced.
1149 """
1151 prerequisites: NamedValueSet[DatasetType]
1152 """Dataset types that are prerequisite inputs for the full Pipeline.
1154 Prerequisite inputs must exist in the input collection(s) before the
1155 pipeline is run, but do not constrain the graph - if a prerequisite is
1156 missing for a Quantum, `PrerequisiteMissingError` is raised.
1158 Prerequisite inputs are not resolved until the second stage of
1159 QuantumGraph generation.
1160 """
1162 intermediates: NamedValueSet[DatasetType]
1163 """Dataset types that are output by one Task in the Pipeline and consumed
1164 as inputs by one or more other Tasks in the Pipeline.
1165 """
1167 outputs: NamedValueSet[DatasetType]
1168 """Dataset types that are output by a Task in the Pipeline and not consumed
1169 by any other Task in the Pipeline.
1170 """
1172 byTask: Mapping[str, TaskDatasetTypes]
1173 """Per-Task dataset types, keyed by label in the `Pipeline`.
1175 This is guaranteed to be zip-iterable with the `Pipeline` itself (assuming
1176 neither has been modified since the dataset types were extracted, of
1177 course).
1178 """
1180 @classmethod
1181 def fromPipeline(
1182 cls,
1183 pipeline: Union[Pipeline, Iterable[TaskDef]],
1184 *,
1185 registry: Registry,
1186 include_configs: bool = True,
1187 include_packages: bool = True,
1188 ) -> PipelineDatasetTypes:
1189 """Extract and classify the dataset types from all tasks in a
1190 `Pipeline`.
1192 Parameters
1193 ----------
1194 pipeline: `Pipeline` or `Iterable` [ `TaskDef` ]
1195 A collection of tasks that can be run together.
1196 registry: `Registry`
1197 Registry used to construct normalized `DatasetType` objects and
1198 retrieve those that are incomplete.
1199 include_configs : `bool`, optional
1200 If `True` (default) include config dataset types as
1201 ``initOutputs``.
1202 include_packages : `bool`, optional
1203 If `True` (default) include the dataset type for software package
1204 versions in ``initOutputs``.
1206 Returns
1207 -------
1208 types: `PipelineDatasetTypes`
1209 The dataset types used by this `Pipeline`.
1211 Raises
1212 ------
1213 ValueError
1214 Raised if Tasks are inconsistent about which datasets are marked
1215 prerequisite. This indicates that the Tasks cannot be run as part
1216 of the same `Pipeline`.
1217 """
1218 allInputs = NamedValueSet[DatasetType]()
1219 allOutputs = NamedValueSet[DatasetType]()
1220 allInitInputs = NamedValueSet[DatasetType]()
1221 allInitOutputs = NamedValueSet[DatasetType]()
1222 prerequisites = NamedValueSet[DatasetType]()
1223 byTask = dict()
1224 if include_packages:
1225 allInitOutputs.add(
1226 DatasetType(
1227 cls.packagesDatasetName,
1228 registry.dimensions.empty,
1229 storageClass="Packages",
1230 )
1231 )
1232 # create a list of TaskDefs in case the input is a generator
1233 pipeline = list(pipeline)
1235 # collect all the output dataset types
1236 typeStorageclassMap: Dict[str, str] = {}
1237 for taskDef in pipeline:
1238 for outConnection in iterConnections(taskDef.connections, "outputs"):
1239 typeStorageclassMap[outConnection.name] = outConnection.storageClass
1241 for taskDef in pipeline:
1242 thisTask = TaskDatasetTypes.fromTaskDef(
1243 taskDef,
1244 registry=registry,
1245 include_configs=include_configs,
1246 storage_class_mapping=typeStorageclassMap,
1247 )
1248 allInitInputs.update(thisTask.initInputs)
1249 allInitOutputs.update(thisTask.initOutputs)
1250 allInputs.update(thisTask.inputs)
1251 prerequisites.update(thisTask.prerequisites)
1252 allOutputs.update(thisTask.outputs)
1253 byTask[taskDef.label] = thisTask
1254 if not prerequisites.isdisjoint(allInputs):
1255 raise ValueError(
1256 "{} marked as both prerequisites and regular inputs".format(
1257 {dt.name for dt in allInputs & prerequisites}
1258 )
1259 )
1260 if not prerequisites.isdisjoint(allOutputs):
1261 raise ValueError(
1262 "{} marked as both prerequisites and outputs".format(
1263 {dt.name for dt in allOutputs & prerequisites}
1264 )
1265 )
1266 # Make sure that components which are marked as inputs get treated as
1267 # intermediates if there is an output which produces the composite
1268 # containing the component
1269 intermediateComponents = NamedValueSet[DatasetType]()
1270 intermediateComposites = NamedValueSet[DatasetType]()
1271 outputNameMapping = {dsType.name: dsType for dsType in allOutputs}
1272 for dsType in allInputs:
1273 # get the name of a possible component
1274 name, component = dsType.nameAndComponent()
1275 # if there is a component name, that means this is a component
1276 # DatasetType, if there is an output which produces the parent of
1277 # this component, treat this input as an intermediate
1278 if component is not None:
1279 # This needs to be in this if block, because someone might have
1280 # a composite that is a pure input from existing data
1281 if name in outputNameMapping:
1282 intermediateComponents.add(dsType)
1283 intermediateComposites.add(outputNameMapping[name])
1285 def checkConsistency(a: NamedValueSet, b: NamedValueSet) -> None:
1286 common = a.names & b.names
1287 for name in common:
1288 # Any compatibility is allowed. This function does not know
1289 # if a dataset type is to be used for input or output.
1290 if not (a[name].is_compatible_with(b[name]) or b[name].is_compatible_with(a[name])):
1291 raise ValueError(f"Conflicting definitions for dataset type: {a[name]} != {b[name]}.")
1293 checkConsistency(allInitInputs, allInitOutputs)
1294 checkConsistency(allInputs, allOutputs)
1295 checkConsistency(allInputs, intermediateComposites)
1296 checkConsistency(allOutputs, intermediateComposites)
1298 def frozen(s: AbstractSet[DatasetType]) -> NamedValueSet[DatasetType]:
1299 assert isinstance(s, NamedValueSet)
1300 s.freeze()
1301 return s
1303 return cls(
1304 initInputs=frozen(allInitInputs - allInitOutputs),
1305 initIntermediates=frozen(allInitInputs & allInitOutputs),
1306 initOutputs=frozen(allInitOutputs - allInitInputs),
1307 inputs=frozen(allInputs - allOutputs - intermediateComponents),
1308 # If there are storage class differences in inputs and outputs
1309 # the intermediates have to choose priority. Here choose that
1310 # inputs to tasks much match the requested storage class by
1311 # applying the inputs over the top of the outputs.
1312 intermediates=frozen(allOutputs & allInputs | intermediateComponents),
1313 outputs=frozen(allOutputs - allInputs - intermediateComposites),
1314 prerequisites=frozen(prerequisites),
1315 byTask=MappingProxyType(byTask), # MappingProxyType -> frozen view of dict for immutability
1316 )
1318 @classmethod
1319 def initOutputNames(
1320 cls,
1321 pipeline: Union[Pipeline, Iterable[TaskDef]],
1322 *,
1323 include_configs: bool = True,
1324 include_packages: bool = True,
1325 ) -> Iterator[str]:
1326 """Return the names of dataset types ot task initOutputs, Configs,
1327 and package versions for a pipeline.
1329 Parameters
1330 ----------
1331 pipeline: `Pipeline` or `Iterable` [ `TaskDef` ]
1332 A `Pipeline` instance or collection of `TaskDef` instances.
1333 include_configs : `bool`, optional
1334 If `True` (default) include config dataset types.
1335 include_packages : `bool`, optional
1336 If `True` (default) include the dataset type for package versions.
1338 Yields
1339 ------
1340 datasetTypeName : `str`
1341 Name of the dataset type.
1342 """
1343 if include_packages:
1344 # Package versions dataset type
1345 yield cls.packagesDatasetName
1347 if isinstance(pipeline, Pipeline):
1348 pipeline = pipeline.toExpandedPipeline()
1350 for taskDef in pipeline:
1352 # all task InitOutputs
1353 for name in taskDef.connections.initOutputs:
1354 attribute = getattr(taskDef.connections, name)
1355 yield attribute.name
1357 # config dataset name
1358 if include_configs:
1359 yield taskDef.configDatasetName