datamaestro-text 2023.12.12__tar.gz → 2024.1.5__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 (118) hide show
  1. {datamaestro-text-2023.12.12/src/datamaestro_text.egg-info → datamaestro-text-2024.1.5}/PKG-INFO +2 -1
  2. datamaestro-text-2024.1.5/docs/requirements.txt +5 -0
  3. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/requirements.txt +1 -0
  4. datamaestro-text-2024.1.5/src/datamaestro_text/data/conversation/__init__.py +1 -0
  5. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/__init__.py +2 -2
  6. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/version.py +2 -2
  7. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5/src/datamaestro_text.egg-info}/PKG-INFO +2 -1
  8. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text.egg-info/requires.txt +1 -0
  9. datamaestro-text-2023.12.12/docs/requirements.txt +0 -3
  10. datamaestro-text-2023.12.12/src/datamaestro_text/data/conversation/__init__.py +0 -1
  11. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/.circleci/config.yml +0 -0
  12. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/.flake8 +0 -0
  13. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/.github/workflows/pytest.yml +0 -0
  14. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/.github/workflows/python-publish.yml +0 -0
  15. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/.gitignore +0 -0
  16. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/.pre-commit-config.yaml +0 -0
  17. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/.readthedocs.yml +0 -0
  18. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/LICENSE +0 -0
  19. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/MANIFEST.in +0 -0
  20. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/Makefile +0 -0
  21. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/README.md +0 -0
  22. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/Makefile +0 -0
  23. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/make.bat +0 -0
  24. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/api/conversation.rst +0 -0
  25. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/api/index.rst +0 -0
  26. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/api/ir.rst +0 -0
  27. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/api/text.rst +0 -0
  28. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/conf.py +0 -0
  29. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/datasets/conversation.rst +0 -0
  30. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/datasets/embeddings.rst +0 -0
  31. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/datasets/index.rst +0 -0
  32. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/datasets/ir.rst +0 -0
  33. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/datasets/irds.rst +0 -0
  34. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/datasets/recommendation.rst +0 -0
  35. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/datasets/text.rst +0 -0
  36. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/docs/source/index.rst +0 -0
  37. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/mkdocs.yml +0 -0
  38. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/pyproject.toml +0 -0
  39. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/requirements-dev.txt +0 -0
  40. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/setup.cfg +0 -0
  41. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/__init__.py +0 -0
  42. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/__init__.py +0 -0
  43. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/ai/quac.yaml +0 -0
  44. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/com/fastml/goodbooks-10k.yaml +0 -0
  45. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/com/github/aagohary/canard.py +0 -0
  46. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/com/github/prdwb/orconvqa.py +0 -0
  47. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/com/github/soskek/bookcorpus.yaml +0 -0
  48. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/com/microsoft/msmarco/passage.py +0 -0
  49. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/com/microsoft/wikiqa.yaml +0 -0
  50. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/com/oscar-corpus.py +0 -0
  51. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/com/sentiment140.py +0 -0
  52. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/com/smashwords/bookcorpus.py +0 -0
  53. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/edu/cornell/nlvr.yaml +0 -0
  54. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/edu/stanford/__init__.py +0 -0
  55. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/edu/stanford/aclimdb.py +0 -0
  56. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/edu/stanford/glove.py +0 -0
  57. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/edu/stanford/im2p.yaml +0 -0
  58. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/edu/upenn/__init__.py +0 -0
  59. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/edu/upenn/ldc/__init__.py +0 -0
  60. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/edu/upenn/ldc/aquaint.py +0 -0
  61. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/gov/__init__.py +0 -0
  62. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/gov/nist/__init__.py +0 -0
  63. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/gov/nist/ir/covid.py +0 -0
  64. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/gov/nist/trec/__init__.py +0 -0
  65. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/gov/nist/trec/adhoc.py +0 -0
  66. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/gov/nist/trec/clueweb.yaml +0 -0
  67. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/gov/nist/trec/deeplearning.yaml +0 -0
  68. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/gov/nist/trec/index.yaml +0 -0
  69. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/gov/nist/trec/tipster.py +0 -0
  70. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/gov/nist/trec/web.yaml +0 -0
  71. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/io/github/rajpurkar/squad.yaml +0 -0
  72. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/io/github/thunlp/fewrel.py +0 -0
  73. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/io/metamind/research/__init__.py +0 -0
  74. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/io/metamind/research/wikitext.py +0 -0
  75. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/net/mattmahoney/enwiki.yaml +0 -0
  76. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/org/acm/recsys/cb2014.yaml +0 -0
  77. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/org/cocodataset/index.yaml +0 -0
  78. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/org/grouplens/movielens.py +0 -0
  79. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/org/universaldependencies/french.py +0 -0
  80. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/config/uk/ac/ucl/cs/qangaroo.yaml +0 -0
  81. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/conversation/base.py +0 -0
  82. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/conversation/canard.py +0 -0
  83. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/conversation/orconvqa.py +0 -0
  84. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/embeddings.py +0 -0
  85. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/base.py +0 -0
  86. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/cord19.py +0 -0
  87. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/csv.py +0 -0
  88. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/data.py +0 -0
  89. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/formats.py +0 -0
  90. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/huggingface.py +0 -0
  91. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/stores.py +0 -0
  92. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/trec.py +0 -0
  93. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/utils.py +0 -0
  94. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/recommendation.py +0 -0
  95. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/tagging.py +0 -0
  96. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/text.py +0 -0
  97. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/datasets/irds/__init__.py +0 -0
  98. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/datasets/irds/data.py +0 -0
  99. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/datasets/irds/datasets.py +0 -0
  100. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/datasets/irds/helpers.py +0 -0
  101. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/datasets/irds/utils.py +0 -0
  102. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/download/tmdb.py +0 -0
  103. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/interfaces/plaintext.py +0 -0
  104. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/interfaces/trec.py +0 -0
  105. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/test/__init__.py +0 -0
  106. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/test/test_datasets.py +0 -0
  107. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/transforms/__init__.py +0 -0
  108. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/transforms/ir/__init__.py +0 -0
  109. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/utils/__init__.py +0 -0
  110. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/utils/files.py +0 -0
  111. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/utils/iter.py +0 -0
  112. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/utils/randomstream.py +0 -0
  113. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/utils/shuffle.py +0 -0
  114. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text.egg-info/SOURCES.txt +0 -0
  115. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text.egg-info/dependency_links.txt +0 -0
  116. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text.egg-info/entry_points.txt +0 -0
  117. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text.egg-info/top_level.txt +0 -0
  118. {datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/tox.ini +0 -0
{datamaestro-text-2023.12.12/src/datamaestro_text.egg-info → datamaestro-text-2024.1.5}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: datamaestro-text
3
- Version: 2023.12.12
3
+ Version: 2024.1.5
4
4
  Summary: Datamaestro module for text-related datasets
5
5
  Author-email: Benjamin Piwowarski <benjamin@piwowarski.fr>
6
6
  License: GPL-3
@@ -19,6 +19,7 @@ Requires-Python: >=3.8
19
19
  Description-Content-Type: text/markdown
20
20
  License-File: LICENSE
21
21
  Requires-Dist: datamaestro>=0.8.16
22
+ Requires-Dist: ir_datasets
22
23
  Requires-Dist: attrs
23
24
 
24
25
  [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit) [![PyPI version](https://badge.fury.io/py/datamaestro-text.svg)](https://badge.fury.io/py/datamaestro-text)
datamaestro-text-2024.1.5/docs/requirements.txt ADDED
@@ -0,0 +1,5 @@
1
+ sphinx>=6
2
+ myst-parser>=0.18.0
3
+ datamaestro>=0.8.5
4
+ sphinx-toolbox
5
+ sphinx-rtd-theme==1.2.2
{datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/requirements.txt RENAMED
@@ -1,2 +1,3 @@
1
1
  datamaestro>=0.8.16
2
+ ir_datasets
2
3
  attrs
datamaestro-text-2024.1.5/src/datamaestro_text/data/conversation/__init__.py ADDED
@@ -0,0 +1 @@
1
+ from .base import Entry, ConversationDataset, Conversation, AnswerEntry, DecontextualizedEntry
{datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/data/ir/__init__.py RENAMED
@@ -261,8 +261,8 @@ class TrainingTripletsLines(TrainingTriplets):
261
261
  class PairwiseSample:
262
262
  """A a query with positive and negative samples"""
263
263
 
264
- topic: Topic
265
- """The topic"""
264
+ topics: List[Topic]
265
+ """The topic(s)"""
266
266
 
267
267
  positives: List[Document]
268
268
  """Relevant documents"""
{datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5}/src/datamaestro_text/version.py RENAMED
@@ -12,5 +12,5 @@ __version__: str
12
12
  __version_tuple__: VERSION_TUPLE
13
13
  version_tuple: VERSION_TUPLE
14
14
 
15
- __version__ = version = '2023.12.12'
16
- __version_tuple__ = version_tuple = (2023, 12, 12)
15
+ __version__ = version = '2024.1.5'
16
+ __version_tuple__ = version_tuple = (2024, 1, 5)
{datamaestro-text-2023.12.12 → datamaestro-text-2024.1.5/src/datamaestro_text.egg-info}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: datamaestro-text
3
- Version: 2023.12.12
3
+ Version: 2024.1.5
4
4
  Summary: Datamaestro module for text-related datasets
5
5
  Author-email: Benjamin Piwowarski <benjamin@piwowarski.fr>
6
6
  License: GPL-3
@@ -19,6 +19,7 @@ Requires-Python: >=3.8
19
19
  Description-Content-Type: text/markdown
20
20
  License-File: LICENSE
21
21
  Requires-Dist: datamaestro>=0.8.16
22
+ Requires-Dist: ir_datasets
22
23
  Requires-Dist: attrs
23
24
 
24
25
  [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit) [![PyPI version](https://badge.fury.io/py/datamaestro-text.svg)](https://badge.fury.io/py/datamaestro-text)
datamaestro-text-2023.12.12/docs/requirements.txt DELETED
@@ -1,3 +0,0 @@
1
- sphinx>=4.2
2
- myst-parser>=0.18.0
3
- datamaestro>=0.8.5
datamaestro-text-2023.12.12/src/datamaestro_text/data/conversation/__init__.py DELETED
@@ -1 +0,0 @@
1
- from .base import Entry, ConversationDataset