datamaestro-text 2025.5.13__py3-none-any.whl → 2025.6.11__py3-none-any.whl

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.
@@ -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
@@ -1,5 +1,5 @@
1
1
  datamaestro_text/__init__.py,sha256=hU8jZpkXl3F74qIfqnJl7v4nJ9YxfoR7IpJpUREFNRI,248
2
- datamaestro_text/version.py,sha256=EsLzhbhZSIiOqGSyEpMlneQnIpzB12JreUxG8EMn7EE,519
2
+ datamaestro_text/version.py,sha256=M2FaCl2nFdTTxwIhOsBo1SQ_3ytid7NHYp2QLIimPXY,519
3
3
  datamaestro_text/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
4
4
  datamaestro_text/config/ai/quac.yaml,sha256=h1D7UJo2z1nZ_9MXpDHuQNJG9Ma2oayUdJV6lyumAIg,1103
5
5
  datamaestro_text/config/com/oscar-corpus.py,sha256=dDfdy_uhG6esRQQzUOOORwK8KvEq4c4hZbWt22pv-zY,733
@@ -7,7 +7,7 @@ datamaestro_text/config/com/sentiment140.py,sha256=3cZfqs395gY14gGojRC_RTYEdG5l8
7
7
  datamaestro_text/config/com/fastml/goodbooks-10k.yaml,sha256=5ZABxUnBFs2ZnCXtBH8YoBiPb3SocRRdH1DLSfVWF-Y,1172
8
8
  datamaestro_text/config/com/github/aagohary/canard.py,sha256=DREIKU2FFrfwibjU48Y1AsKTUzhwxmD4Kuykd4bDIus,1762
9
9
  datamaestro_text/config/com/github/apple/ml-qrecc.py,sha256=-iHKJocWZ8N9N-P8E45y4ewg3OT_23XonlDh5-NcH2g,3055
10
- datamaestro_text/config/com/github/prdwb/orconvqa.py,sha256=Tg3hbnvilxW_Lwt7fpKvGMtu-6mc9oNIHM-LX6JTR1U,3026
10
+ datamaestro_text/config/com/github/prdwb/orconvqa.py,sha256=MFJYaxJoqJQ6kMDHa2PIE0zoxYTA8Kyl26-vzFoMML0,3032
11
11
  datamaestro_text/config/com/github/soskek/bookcorpus.yaml,sha256=qJKs35yeEIilEMgNvU3OEqMp1TSn7mDM2T-uYyA7kTU,1607
12
12
  datamaestro_text/config/com/microsoft/wikiqa.yaml,sha256=U7rU-W2Xz1MYv2YXT4jCTj5DsHyM0VssbQPNa3EISaM,540
13
13
  datamaestro_text/config/com/microsoft/msmarco/passage.py,sha256=tVldwVh0pQpXXifqcMNEN9cLO1HXkXoEhToSazSx5RE,11643
@@ -62,7 +62,7 @@ datamaestro_text/data/ir/trec.py,sha256=qDOzmgUn0hMqeP9KdI190-9IKsLl6yNRqIoBz6s-
62
62
  datamaestro_text/data/ir/utils.py,sha256=6-GhXVtgkBZGhIs2-ODZua_3DmKjSSVydStpHDqbAwE,833
63
63
  datamaestro_text/datasets/irds/__init__.py,sha256=Tq0HN1qojnZYLBumM59BuTkz7r0gcu-5OXmDDLgPpAc,707
64
64
  datamaestro_text/datasets/irds/data.py,sha256=0V5nPMQeh1I3Sp36x_NE7xrbC_vbZAKhU5NONj95aok,22058
65
- datamaestro_text/datasets/irds/datasets.py,sha256=yrJx3X7u7oYcHXsL8YmUrXsQhkiqkBC6LjeZA_Ldx5Q,5617
65
+ datamaestro_text/datasets/irds/datasets.py,sha256=n5mvD2omVI4PkeuJgX13Cio6gLrgYjxq8ZUKKyqocEs,5625
66
66
  datamaestro_text/datasets/irds/helpers.py,sha256=fGE-fbuJbXdTzl1qo55247jzn9cvApY-d82GJBgfY1E,3982
67
67
  datamaestro_text/datasets/irds/utils.py,sha256=m30JLIrV_HgilN11TvY9dGTyumES6LLzWZDUAMT915M,1425
68
68
  datamaestro_text/download/tmdb.py,sha256=kU_Vz9jhznlyeKMHziVu58IHoWv8zPu6CZTHVNQvmu4,4009
@@ -78,9 +78,9 @@ datamaestro_text/utils/files.py,sha256=n6ZGl5LNrZbHLcV9RFwd7cFT0vPUezit-2dsBzs1v
78
78
  datamaestro_text/utils/iter.py,sha256=uzBmavBeqVyEvYmi9Ds2dqh0ywhJE-1SBO5v8AoIKcc,2537
79
79
  datamaestro_text/utils/randomstream.py,sha256=_-boH4IIqN8qcl3IktjpNp9vmF4TWRzHUSNVwg7WAr8,973
80
80
  datamaestro_text/utils/shuffle.py,sha256=o8JTz3mr0lYWyv0zEh91jEK12ci1etMiUnzh5GkOHCM,3490
81
- datamaestro_text-2025.5.13.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
82
- datamaestro_text-2025.5.13.dist-info/METADATA,sha256=EYppi8IJMqWU3ObzwSvM_PuOkC_pgwGAxwvaFx2dG3A,1847
83
- datamaestro_text-2025.5.13.dist-info/WHEEL,sha256=DnLRTWE75wApRYVsjgc6wsVswC54sMSJhAEd4xhDpBk,91
84
- datamaestro_text-2025.5.13.dist-info/entry_points.txt,sha256=lO1P5hE183L5qEEVHlG8d_ik0HNXnX7Eo87cQLdcl-Y,111
85
- datamaestro_text-2025.5.13.dist-info/top_level.txt,sha256=gYSeqViE8r7eCxSdqFJL74OwljOwKsGPaIhEcCXqc-o,17
86
- datamaestro_text-2025.5.13.dist-info/RECORD,,
81
+ datamaestro_text-2025.6.11.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
82
+ datamaestro_text-2025.6.11.dist-info/METADATA,sha256=oMXEU9_JPRCrUCoSE6IGmmyLzfdpVQgKHAaaEbFXMXY,1847
83
+ datamaestro_text-2025.6.11.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
84
+ datamaestro_text-2025.6.11.dist-info/entry_points.txt,sha256=lO1P5hE183L5qEEVHlG8d_ik0HNXnX7Eo87cQLdcl-Y,111
85
+ datamaestro_text-2025.6.11.dist-info/top_level.txt,sha256=gYSeqViE8r7eCxSdqFJL74OwljOwKsGPaIhEcCXqc-o,17
86
+ datamaestro_text-2025.6.11.dist-info/RECORD,,
@@ -1,5 +1,5 @@
1
1
  Wheel-Version: 1.0
2
- Generator: setuptools (80.4.0)
2
+ Generator: setuptools (80.9.0)
3
3
  Root-Is-Purelib: true
4
4
  Tag: py3-none-any
5
5