aspect-data 0.0.4__tar.gz → 0.0.6__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (45) hide show
  1. {aspect_data-0.0.4 → aspect_data-0.0.6}/PKG-INFO +1 -1
  2. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/__init__.py +2 -0
  3. aspect_data-0.0.6/aspect/collate/__init__.py +2 -0
  4. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/collate/base.py +30 -1
  5. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/collate/chemprop.py +1 -1
  6. aspect_data-0.0.6/aspect/data.py +912 -0
  7. aspect_data-0.0.6/aspect/io.py +504 -0
  8. aspect_data-0.0.6/aspect/package_data.py +54 -0
  9. aspect_data-0.0.6/aspect/transform/__init__.py +15 -0
  10. aspect_data-0.0.6/aspect/transform/chemprop.py +85 -0
  11. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/transform/functions.py +0 -73
  12. aspect_data-0.0.6/aspect/transform/registry.py +23 -0
  13. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect_data.egg-info/PKG-INFO +1 -1
  14. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect_data.egg-info/SOURCES.txt +9 -1
  15. {aspect_data-0.0.4 → aspect_data-0.0.6}/pyproject.toml +1 -1
  16. aspect_data-0.0.6/test/test_checkpoint.py +242 -0
  17. aspect_data-0.0.6/test/test_checksum.py +101 -0
  18. {aspect_data-0.0.4 → aspect_data-0.0.6}/test/test_collate.py +56 -0
  19. {aspect_data-0.0.4 → aspect_data-0.0.6}/test/test_collate_chemprop.py +19 -8
  20. aspect_data-0.0.6/test/test_data_source.py +22 -0
  21. aspect_data-0.0.6/test/test_dataloader.py +79 -0
  22. aspect_data-0.0.6/test/test_empty_pipeline.py +33 -0
  23. aspect_data-0.0.6/test/test_io.py +128 -0
  24. aspect_data-0.0.6/test/test_transform_dict.py +48 -0
  25. aspect_data-0.0.4/aspect/collate/__init__.py +0 -7
  26. aspect_data-0.0.4/aspect/data.py +0 -581
  27. aspect_data-0.0.4/aspect/io.py +0 -189
  28. aspect_data-0.0.4/aspect/package_data.py +0 -35
  29. aspect_data-0.0.4/aspect/transform/__init__.py +0 -9
  30. aspect_data-0.0.4/aspect/transform/registry.py +0 -17
  31. {aspect_data-0.0.4 → aspect_data-0.0.6}/LICENSE +0 -0
  32. {aspect_data-0.0.4 → aspect_data-0.0.6}/README.md +0 -0
  33. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/checkpoint_utils.py +0 -0
  34. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/cli_module/__init__.py +0 -0
  35. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/cli_module/cli.py +0 -0
  36. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/cli_module/featurize.py +0 -0
  37. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/cli_module/io.py +0 -0
  38. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/transform/base.py +0 -0
  39. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/transform/deep_functions.py +0 -0
  40. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect/typing.py +0 -0
  41. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect_data.egg-info/dependency_links.txt +0 -0
  42. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect_data.egg-info/entry_points.txt +0 -0
  43. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect_data.egg-info/requires.txt +0 -0
  44. {aspect_data-0.0.4 → aspect_data-0.0.6}/aspect_data.egg-info/top_level.txt +0 -0
  45. {aspect_data-0.0.4 → aspect_data-0.0.6}/setup.cfg +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: aspect-data
3
- Version: 0.0.4
3
+ Version: 0.0.6
4
4
  Summary: General purpose, chemistry, and taxonomic featurization of tabular data with caching.
5
5
  Author-email: Eachan Johnson <eachan.johnson@crick.ac.uk>
6
6
  License: MIT License
@@ -3,3 +3,5 @@ from importlib.metadata import version
3
3
  app_name = "aspect-data"
4
4
  __author__ = "Eachan Johnson"
5
5
  __version__ = version(app_name)
6
+
7
+ from .data import DataPipeline
@@ -0,0 +1,2 @@
1
+ from .base import ColumnCollator, resolve_collator
2
+ from .chemprop import chemprop_collate
@@ -1,6 +1,7 @@
1
1
  """Specialised column collation."""
2
2
 
3
3
  from collections.abc import Callable, Mapping, Iterable
4
+ from importlib import import_module
4
5
  from typing import Any, TypeAlias
5
6
 
6
7
  from ..typing import Batch
@@ -9,6 +10,28 @@ from ..typing import Batch
9
10
  CollateFn: TypeAlias = Callable[[Iterable[Any]], Any]
10
11
 
11
12
 
13
+ def resolve_collator(path: str) -> CollateFn:
14
+ """Resolve ``module:attribute`` to a runtime collator."""
15
+
16
+ try:
17
+ module_name, attribute = path.split(":", 1)
18
+ except ValueError as error:
19
+ raise ValueError(
20
+ "Collator path must have form "
21
+ f"'module:attribute', but was {path!r}."
22
+ ) from error
23
+
24
+ module = import_module(module_name)
25
+ collator = getattr(module, attribute)
26
+
27
+ if not callable(collator):
28
+ raise TypeError(
29
+ f"Resolved collator {path!r} is not callable."
30
+ )
31
+
32
+ return collator
33
+
34
+
12
35
  class ColumnCollator:
13
36
  """Override collation for selected dataset columns."""
14
37
 
@@ -16,7 +39,13 @@ class ColumnCollator:
16
39
  self,
17
40
  collators: Mapping[str, CollateFn] | None = None,
18
41
  ):
19
- self.collators = collators or {}
42
+ collators = collators or {}
43
+ if not isinstance(collators, Mapping):
44
+ raise ValueError(
45
+ "If provided, `collators` must be a dict, "
46
+ f"but was {type(collators)}: {collators}"
47
+ )
48
+ self.collators = dict(collators)
20
49
 
21
50
  def __call__(
22
51
  self,
@@ -95,7 +95,7 @@ def chemprop_collate(
95
95
  raise ValueError("Cannot collate an empty Chemprop batch.")
96
96
 
97
97
  molgraphs = [
98
- _molgraph_from_mapping(value["bmg"])
98
+ _molgraph_from_mapping(value["mg"])
99
99
  for value in values
100
100
  ]
101
101
  bmg = BatchMolGraph(molgraphs)