datamaestro-text 2025.5.13__tar.gz → 2025.6.11__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 (123) hide show
  1. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/.gitignore +1 -0
  2. {datamaestro_text-2025.5.13/src/datamaestro_text.egg-info → datamaestro_text-2025.6.11}/PKG-INFO +1 -1
  3. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/com/github/prdwb/orconvqa.py +3 -3
  4. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/datasets/irds/datasets.py +4 -4
  5. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/version.py +2 -2
  6. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11/src/datamaestro_text.egg-info}/PKG-INFO +1 -1
  7. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/.circleci/config.yml +0 -0
  8. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/.flake8 +0 -0
  9. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/.github/workflows/pytest.yml +0 -0
  10. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/.github/workflows/python-publish.yml +0 -0
  11. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/.pre-commit-config.yaml +0 -0
  12. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/.readthedocs.yml +0 -0
  13. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/LICENSE +0 -0
  14. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/MANIFEST.in +0 -0
  15. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/Makefile +0 -0
  16. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/README.md +0 -0
  17. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/Makefile +0 -0
  18. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/make.bat +0 -0
  19. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/requirements.txt +0 -0
  20. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/api/conversation.rst +0 -0
  21. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/api/embeddings.rst +0 -0
  22. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/api/index.rst +0 -0
  23. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/api/ir.rst +0 -0
  24. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/api/nlp.rst +0 -0
  25. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/api/recommendation.rst +0 -0
  26. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/api/text.rst +0 -0
  27. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/conf.py +0 -0
  28. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/datasets/conversation.rst +0 -0
  29. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/datasets/embeddings.rst +0 -0
  30. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/datasets/index.rst +0 -0
  31. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/datasets/ir.rst +0 -0
  32. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/datasets/irds.rst +0 -0
  33. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/datasets/recommendation.rst +0 -0
  34. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/datasets/text.rst +0 -0
  35. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/docs/source/index.rst +0 -0
  36. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/mkdocs.yml +0 -0
  37. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/pyproject.toml +0 -0
  38. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/requirements-dev.txt +0 -0
  39. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/requirements.txt +0 -0
  40. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/setup.cfg +0 -0
  41. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/__init__.py +0 -0
  42. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/__init__.py +0 -0
  43. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/ai/quac.yaml +0 -0
  44. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/com/fastml/goodbooks-10k.yaml +0 -0
  45. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/com/github/aagohary/canard.py +0 -0
  46. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/com/github/apple/ml-qrecc.py +0 -0
  47. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/com/github/soskek/bookcorpus.yaml +0 -0
  48. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/com/microsoft/msmarco/passage.py +0 -0
  49. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/com/microsoft/wikiqa.yaml +0 -0
  50. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/com/oscar-corpus.py +0 -0
  51. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/com/sentiment140.py +0 -0
  52. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/com/smashwords/bookcorpus.py +0 -0
  53. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/edu/cornell/nlvr.yaml +0 -0
  54. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/edu/stanford/__init__.py +0 -0
  55. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/edu/stanford/aclimdb.py +0 -0
  56. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/edu/stanford/glove.py +0 -0
  57. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/edu/stanford/im2p.yaml +0 -0
  58. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/edu/upenn/__init__.py +0 -0
  59. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/edu/upenn/ldc/__init__.py +0 -0
  60. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/edu/upenn/ldc/aquaint.py +0 -0
  61. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/gov/__init__.py +0 -0
  62. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/gov/nist/__init__.py +0 -0
  63. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/gov/nist/ir/covid.py +0 -0
  64. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/gov/nist/trec/__init__.py +0 -0
  65. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/gov/nist/trec/adhoc.py +0 -0
  66. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/gov/nist/trec/clueweb.yaml +0 -0
  67. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/gov/nist/trec/deeplearning.yaml +0 -0
  68. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/gov/nist/trec/index.yaml +0 -0
  69. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/gov/nist/trec/tipster.py +0 -0
  70. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/gov/nist/trec/web.yaml +0 -0
  71. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/io/github/rajpurkar/squad.yaml +0 -0
  72. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/io/github/thunlp/fewrel.py +0 -0
  73. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/io/metamind/research/__init__.py +0 -0
  74. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/io/metamind/research/wikitext.py +0 -0
  75. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/net/mattmahoney/enwiki.yaml +0 -0
  76. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/org/acm/recsys/cb2014.yaml +0 -0
  77. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/org/cocodataset/index.yaml +0 -0
  78. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/org/grouplens/movielens.py +0 -0
  79. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/org/universaldependencies/french.py +0 -0
  80. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/config/uk/ac/ucl/cs/qangaroo.yaml +0 -0
  81. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/__init__.py +0 -0
  82. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/conversation/__init__.py +0 -0
  83. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/conversation/base.py +0 -0
  84. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/conversation/canard.py +0 -0
  85. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/conversation/orconvqa.py +0 -0
  86. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/conversation/qrecc.py +0 -0
  87. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/embeddings.py +0 -0
  88. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/ir/__init__.py +0 -0
  89. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/ir/base.py +0 -0
  90. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/ir/cord19.py +0 -0
  91. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/ir/csv.py +0 -0
  92. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/ir/data.py +0 -0
  93. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/ir/formats.py +0 -0
  94. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/ir/huggingface.py +0 -0
  95. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/ir/stores.py +0 -0
  96. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/ir/trec.py +0 -0
  97. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/ir/utils.py +0 -0
  98. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/recommendation.py +0 -0
  99. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/tagging.py +0 -0
  100. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/data/text.py +0 -0
  101. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/datasets/irds/__init__.py +0 -0
  102. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/datasets/irds/data.py +0 -0
  103. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/datasets/irds/helpers.py +0 -0
  104. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/datasets/irds/utils.py +0 -0
  105. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/download/tmdb.py +0 -0
  106. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/interfaces/plaintext.py +0 -0
  107. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/interfaces/trec.py +0 -0
  108. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/test/__init__.py +0 -0
  109. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/test/test_datasets.py +0 -0
  110. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/test/test_documented.py +0 -0
  111. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/transforms/__init__.py +0 -0
  112. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/transforms/ir/__init__.py +0 -0
  113. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/utils/__init__.py +0 -0
  114. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/utils/files.py +0 -0
  115. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/utils/iter.py +0 -0
  116. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/utils/randomstream.py +0 -0
  117. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text/utils/shuffle.py +0 -0
  118. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text.egg-info/SOURCES.txt +0 -0
  119. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text.egg-info/dependency_links.txt +0 -0
  120. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text.egg-info/entry_points.txt +0 -0
  121. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text.egg-info/requires.txt +0 -0
  122. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/src/datamaestro_text.egg-info/top_level.txt +0 -0
  123. {datamaestro_text-2025.5.13 → datamaestro_text-2025.6.11}/tox.ini +0 -0
@@ -1,4 +1,5 @@
1
1
  *.egg-info
2
+ .DS_Store
2
3
  .vscode
3
4
  __pycache__
4
5
  site
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: datamaestro-text
3
- Version: 2025.5.13
3
+ Version: 2025.6.11
4
4
  Summary: Datamaestro module for text-related datasets
5
5
  Author-email: Benjamin Piwowarski <benjamin@piwowarski.fr>
6
6
  License: GPL-3
@@ -49,9 +49,9 @@ def preprocessed(train, dev, test):
49
49
  Each dataset is an instance of :class:`datamaestro_text.data.conversation.OrConvQADataset`
50
50
  """
51
51
  return {
52
- "train": OrConvQADataset(path=train),
53
- "validation": OrConvQADataset(path=dev),
54
- "test": OrConvQADataset(path=test),
52
+ "train": OrConvQADataset.C(path=train),
53
+ "validation": OrConvQADataset.C(path=dev),
54
+ "test": OrConvQADataset.C(path=test),
55
55
  }
56
56
 
57
57
 
@@ -65,7 +65,7 @@ class QrelsDataset(Dataset):
65
65
  return True
66
66
 
67
67
  def _prepare(self, download=False) -> Documents:
68
- return AdhocAssessments(id=self.fullid)
68
+ return AdhocAssessments.C(id=self.fullid)
69
69
 
70
70
 
71
71
  class QueriesDataset(Dataset):
@@ -78,7 +78,7 @@ class QueriesDataset(Dataset):
78
78
  return True
79
79
 
80
80
  def _prepare(self, download=False) -> Documents:
81
- return Topics(id=self.fullid)
81
+ return Topics.C(id=self.fullid)
82
82
 
83
83
 
84
84
  # class ScoredDocuments(Dataset):
@@ -96,7 +96,7 @@ class DocumentsDataset(Dataset):
96
96
  return True
97
97
 
98
98
  def _prepare(self, download=False) -> Documents:
99
- return Documents(id=self.fullid)
99
+ return Documents.C(id=self.fullid)
100
100
 
101
101
 
102
102
  class TrainingTripletsDataset(Dataset):
@@ -123,7 +123,7 @@ class Collection(Dataset):
123
123
  topics: QueriesDataset
124
124
 
125
125
  def _prepare(self, download=False) -> Documents:
126
- return Adhoc(
126
+ return Adhoc.C(
127
127
  id=self.fullid,
128
128
  topics=self.topics.prepare(download),
129
129
  assessments=self.assessments.prepare(download),
@@ -17,5 +17,5 @@ __version__: str
17
17
  __version_tuple__: VERSION_TUPLE
18
18
  version_tuple: VERSION_TUPLE
19
19
 
20
- __version__ = version = '2025.5.13'
21
- __version_tuple__ = version_tuple = (2025, 5, 13)
20
+ __version__ = version = '2025.6.11'
21
+ __version_tuple__ = version_tuple = (2025, 6, 11)
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: datamaestro-text
3
- Version: 2025.5.13
3
+ Version: 2025.6.11
4
4
  Summary: Datamaestro module for text-related datasets
5
5
  Author-email: Benjamin Piwowarski <benjamin@piwowarski.fr>
6
6
  License: GPL-3