structured-data-models 0.2.0__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.
Files changed (152) hide show
  1. sdm/__init__.py +58 -0
  2. sdm/_constants.py +6 -0
  3. sdm/_inference.py +42 -0
  4. sdm/_kernels/__init__.py +10 -0
  5. sdm/_kernels/rmsnorm_cast.py +92 -0
  6. sdm/_kernels/segment_multi_reduce.py +141 -0
  7. sdm/_kernels/triton/__init__.py +7 -0
  8. sdm/_kernels/triton/rmsnorm_cast.py +136 -0
  9. sdm/_kernels/triton/segment_multi_reduce.py +173 -0
  10. sdm/_memory.py +34 -0
  11. sdm/_warnings.py +29 -0
  12. sdm/cache.py +163 -0
  13. sdm/ensemble.py +501 -0
  14. sdm/evaluation/__init__.py +11 -0
  15. sdm/evaluation/classification.py +205 -0
  16. sdm/explain/__init__.py +12 -0
  17. sdm/explain/base.py +123 -0
  18. sdm/explain/gradient.py +112 -0
  19. sdm/models/__init__.py +20 -0
  20. sdm/models/_huggingface.py +58 -0
  21. sdm/models/base.py +966 -0
  22. sdm/models/callback.py +106 -0
  23. sdm/models/ecoc.py +197 -0
  24. sdm/models/kumo/__init__.py +13 -0
  25. sdm/models/kumo/relational/NOTICE +5 -0
  26. sdm/models/kumo/relational/__init__.py +11 -0
  27. sdm/models/kumo/relational/graph.py +101 -0
  28. sdm/models/kumo/relational/invariant_gnn.py +122 -0
  29. sdm/models/kumo/relational/model.py +602 -0
  30. sdm/models/kumo/relational/recipe.py +18 -0
  31. sdm/models/kumo/relational/task.py +113 -0
  32. sdm/models/kumo/tabular/__init__.py +17 -0
  33. sdm/models/kumo/tabular/batching.py +139 -0
  34. sdm/models/kumo/tabular/block.py +100 -0
  35. sdm/models/kumo/tabular/cell_embedding.py +85 -0
  36. sdm/models/kumo/tabular/icl.py +136 -0
  37. sdm/models/kumo/tabular/model.py +299 -0
  38. sdm/models/kumo/tabular/recipe.py +71 -0
  39. sdm/models/kumo/tabular/row_embedding.py +214 -0
  40. sdm/models/tabfm/LICENSE +209 -0
  41. sdm/models/tabfm/__init__.py +11 -0
  42. sdm/models/tabfm/block.py +94 -0
  43. sdm/models/tabfm/cell_embedding.py +219 -0
  44. sdm/models/tabfm/ckpt.py +242 -0
  45. sdm/models/tabfm/icl.py +107 -0
  46. sdm/models/tabfm/model.py +261 -0
  47. sdm/models/tabfm/recipe.py +46 -0
  48. sdm/models/tabfm/row_embedding.py +241 -0
  49. sdm/models/tabiclv2/LICENSE +33 -0
  50. sdm/models/tabiclv2/__init__.py +11 -0
  51. sdm/models/tabiclv2/block.py +81 -0
  52. sdm/models/tabiclv2/ckpt.py +134 -0
  53. sdm/models/tabiclv2/icl.py +420 -0
  54. sdm/models/tabiclv2/model.py +293 -0
  55. sdm/models/tabiclv2/recipe.py +46 -0
  56. sdm/models/tabiclv2/row_embedding.py +254 -0
  57. sdm/nn/__init__.py +28 -0
  58. sdm/nn/_buffer.py +91 -0
  59. sdm/nn/attention.py +825 -0
  60. sdm/nn/glu.py +78 -0
  61. sdm/nn/linear.py +46 -0
  62. sdm/nn/rms_norm.py +59 -0
  63. sdm/nn/rope.py +107 -0
  64. sdm/nn/scaling.py +240 -0
  65. sdm/nn/set_transformer.py +162 -0
  66. sdm/nn/softplus.py +65 -0
  67. sdm/processing/__init__.py +96 -0
  68. sdm/processing/base.py +254 -0
  69. sdm/processing/categorical/__init__.py +16 -0
  70. sdm/processing/categorical/_categorical.py +60 -0
  71. sdm/processing/categorical/align.py +540 -0
  72. sdm/processing/categorical/count.py +121 -0
  73. sdm/processing/categorical/impute.py +107 -0
  74. sdm/processing/categorical/shuffle.py +204 -0
  75. sdm/processing/common/__init__.py +32 -0
  76. sdm/processing/common/callable.py +29 -0
  77. sdm/processing/common/choice.py +185 -0
  78. sdm/processing/common/drop.py +28 -0
  79. sdm/processing/common/ensemble.py +187 -0
  80. sdm/processing/common/identity.py +18 -0
  81. sdm/processing/common/select.py +107 -0
  82. sdm/processing/common/sequential.py +158 -0
  83. sdm/processing/common/shuffle.py +195 -0
  84. sdm/processing/common/stype.py +199 -0
  85. sdm/processing/common/table.py +120 -0
  86. sdm/processing/common/task.py +135 -0
  87. sdm/processing/common/to_numerical.py +60 -0
  88. sdm/processing/datetime/__init__.py +8 -0
  89. sdm/processing/datetime/calendar.py +196 -0
  90. sdm/processing/ensemble.py +203 -0
  91. sdm/processing/execution.py +418 -0
  92. sdm/processing/numerical/__init__.py +38 -0
  93. sdm/processing/numerical/_stats.py +29 -0
  94. sdm/processing/numerical/cast.py +33 -0
  95. sdm/processing/numerical/clip.py +48 -0
  96. sdm/processing/numerical/clip_soft.py +54 -0
  97. sdm/processing/numerical/constant.py +235 -0
  98. sdm/processing/numerical/flip_sign.py +78 -0
  99. sdm/processing/numerical/impute.py +52 -0
  100. sdm/processing/numerical/pca.py +62 -0
  101. sdm/processing/numerical/power.py +325 -0
  102. sdm/processing/numerical/quantile.py +306 -0
  103. sdm/processing/numerical/quantile_clip.py +63 -0
  104. sdm/processing/numerical/random_projection.py +86 -0
  105. sdm/processing/numerical/rank_gaussian.py +168 -0
  106. sdm/processing/numerical/robust_scale.py +88 -0
  107. sdm/processing/numerical/sigma_clip.py +123 -0
  108. sdm/processing/numerical/standardize.py +71 -0
  109. sdm/processing/output/__init__.py +14 -0
  110. sdm/processing/output/reduce.py +86 -0
  111. sdm/processing/output/softmax.py +48 -0
  112. sdm/processing/output/sort.py +16 -0
  113. sdm/processing/recipe.py +154 -0
  114. sdm/processing/text/__init__.py +12 -0
  115. sdm/processing/text/sentence_transformer.py +451 -0
  116. sdm/processing/text/tfidf.py +478 -0
  117. sdm/relational/__init__.py +16 -0
  118. sdm/relational/backend/__init__.py +12 -0
  119. sdm/relational/backend/_cugraph.py +546 -0
  120. sdm/relational/backend/_pyg_lib.py +175 -0
  121. sdm/relational/data.py +393 -0
  122. sdm/relational/join.py +173 -0
  123. sdm/relational/sampler.py +259 -0
  124. sdm/relational/task.py +465 -0
  125. sdm/stype.py +396 -0
  126. sdm/task.py +53 -0
  127. sdm/tensor/__init__.py +20 -0
  128. sdm/tensor/categorical.py +953 -0
  129. sdm/tensor/columnar.py +1127 -0
  130. sdm/tensor/io/__init__.py +22 -0
  131. sdm/tensor/io/arrow.py +120 -0
  132. sdm/tensor/io/cudf.py +47 -0
  133. sdm/tensor/mixin.py +124 -0
  134. sdm/tensor/nullable.py +963 -0
  135. sdm/tensor/string.py +526 -0
  136. sdm/tensor/table.py +2035 -0
  137. sdm/tensor/var_len.py +1486 -0
  138. sdm/testing/__init__.py +14 -0
  139. sdm/testing/decorators.py +61 -0
  140. sdm/testing/memory.py +92 -0
  141. structured_data_models-0.2.0.dist-info/METADATA +142 -0
  142. structured_data_models-0.2.0.dist-info/RECORD +152 -0
  143. structured_data_models-0.2.0.dist-info/WHEEL +5 -0
  144. structured_data_models-0.2.0.dist-info/licenses/LICENSE +204 -0
  145. structured_data_models-0.2.0.dist-info/licenses/THIRD_PARTY_LICENSES.md +40 -0
  146. structured_data_models-0.2.0.dist-info/licenses/sdm/models/kumo/relational/NOTICE +5 -0
  147. structured_data_models-0.2.0.dist-info/licenses/sdm/models/tabfm/LICENSE +209 -0
  148. structured_data_models-0.2.0.dist-info/licenses/sdm/models/tabiclv2/LICENSE +33 -0
  149. structured_data_models-0.2.0.dist-info/licenses/third_party/contributor-covenant/LICENSE +20 -0
  150. structured_data_models-0.2.0.dist-info/licenses/third_party/pytorch/LICENSE +84 -0
  151. structured_data_models-0.2.0.dist-info/licenses/third_party/tabpfn-extensions/LICENSE +202 -0
  152. structured_data_models-0.2.0.dist-info/top_level.txt +1 -0
sdm/relational/join.py ADDED
@@ -0,0 +1,173 @@
1
+ # SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
+ # SPDX-License-Identifier: Apache-2.0
3
+
4
+ import importlib.util
5
+ import math
6
+ from collections.abc import Sequence
7
+ from typing import Literal
8
+
9
+ import pyarrow as pa
10
+ import pyarrow.compute as pc
11
+ import torch
12
+ from torch import Tensor
13
+
14
+ from sdm import TableTensor
15
+ from sdm._warnings import warn_once
16
+ from sdm.tensor.io import arrow_as_tensor, to_cudf
17
+
18
+ PREFIX = "sdm_internal"
19
+ LEFT_ROW_ID = f"__{PREFIX}_left_row_id__"
20
+ RIGHT_ROW_ID = f"__{PREFIX}_right_row_id__"
21
+
22
+
23
+ def join_index(
24
+ left_table: TableTensor,
25
+ right_table: TableTensor,
26
+ left_keys: Sequence[str],
27
+ right_keys: Sequence[str],
28
+ how: Literal["inner"] = "inner",
29
+ dtype: torch.dtype | None = None,
30
+ device: torch.device | str | None = None,
31
+ ) -> tuple[Tensor, Tensor]:
32
+ r"""Return row-index pairs for matching rows in two tables.
33
+
34
+ Args:
35
+ left_table: The left table.
36
+ right_table: The right table.
37
+ left_keys: Column names from ``left_table`` used as join keys.
38
+ right_keys: Column names from ``right_table`` used as join keys.
39
+ how: The join type.
40
+ dtype: The dtype.
41
+ device: The device.
42
+
43
+ Returns:
44
+ ``(left_index, right_index)`` pair with one entry per matched row.
45
+ """
46
+ assert how == "inner"
47
+
48
+ if left_table.device != right_table.device:
49
+ raise RuntimeError(
50
+ "Expected 'left_table' and 'right_table' to be on the same device "
51
+ f"(got '{left_table.device}' and '{right_table.device}')"
52
+ )
53
+
54
+ dtype = dtype or torch.long
55
+ device = device or left_table.device
56
+
57
+ left_table = left_table[list(left_keys)]
58
+ right_table = right_table[list(right_keys)]
59
+ left_rows = math.prod(left_table.size()[:-1])
60
+ right_rows = math.prod(right_table.size()[:-1])
61
+
62
+ if max(left_rows, right_rows) - 1 > torch.iinfo(dtype).max:
63
+ raise ValueError(
64
+ f"Creating row indices up to {max(left_rows, right_rows) - 1:,} "
65
+ f"in '{dtype}' would overflow"
66
+ )
67
+
68
+ backend: Literal["arrow", "cudf"] = "arrow"
69
+ if left_table.is_cuda:
70
+ if importlib.util.find_spec("cudf") is not None:
71
+ backend = "cudf"
72
+ else:
73
+ warn_once(
74
+ key="missing-cudf-join",
75
+ message=(
76
+ "Falling back to a CPU-based join because cuDF is not "
77
+ "installed. Install cuDF to enable faster CUDA-based "
78
+ "joins without device synchronization."
79
+ ),
80
+ )
81
+
82
+ if backend == "arrow":
83
+ left = left_table.to_arrow().append_column(
84
+ LEFT_ROW_ID,
85
+ pa.array(torch.arange(left_rows, dtype=dtype).numpy()),
86
+ )
87
+ right = right_table.to_arrow().append_column(
88
+ RIGHT_ROW_ID,
89
+ pa.array(torch.arange(right_rows, dtype=dtype).numpy()),
90
+ )
91
+
92
+ left = dropna(left, subset=left_keys)
93
+ right = dropna(right, subset=right_keys)
94
+
95
+ right_schema = right.schema
96
+ for left_key, right_key in zip(left_keys, right_keys):
97
+ left_type = left[left_key].type
98
+ if left_type != right[right_key].type:
99
+ index = right.schema.get_field_index(right_key)
100
+ field = right.schema.field(index).with_type(left_type)
101
+ right_schema = right_schema.set(index, field)
102
+ if right_schema != right.schema:
103
+ right = right.cast(right_schema, safe=True)
104
+
105
+ joined = left.join(
106
+ right,
107
+ keys=left_keys,
108
+ right_keys=right_keys,
109
+ join_type=how,
110
+ )
111
+
112
+ return (
113
+ arrow_as_tensor(joined[LEFT_ROW_ID], device=device),
114
+ arrow_as_tensor(joined[RIGHT_ROW_ID], device=device),
115
+ )
116
+
117
+ assert backend == "cudf"
118
+ with torch.cuda.device(left_table.device):
119
+ left = left_table.to_cudf()
120
+ left[LEFT_ROW_ID] = to_cudf(
121
+ torch.arange(left_rows, dtype=dtype, device=left_table.device)
122
+ )
123
+ right = right_table.to_cudf()
124
+ right[RIGHT_ROW_ID] = to_cudf(
125
+ torch.arange(right_rows, dtype=dtype, device=right_table.device)
126
+ )
127
+
128
+ joined = left.dropna(subset=list(left_keys)).merge(
129
+ right.dropna(subset=list(right_keys)),
130
+ left_on=left_keys,
131
+ right_on=right_keys,
132
+ how=how,
133
+ )
134
+
135
+ return (
136
+ torch.as_tensor(joined[LEFT_ROW_ID]).to(device),
137
+ torch.as_tensor(joined[RIGHT_ROW_ID]).to(device),
138
+ )
139
+
140
+
141
+ def dropna(
142
+ table: pa.Table,
143
+ subset: Sequence[str] | None = None,
144
+ ) -> pa.Table:
145
+ r"""Drop rows with null or NaN values in the given columns."""
146
+ columns = table.column_names if subset is None else subset
147
+
148
+ mask = None
149
+ for name in columns:
150
+ column = table[name]
151
+
152
+ _mask = None
153
+ if column.null_count > 0:
154
+ _mask = column.is_valid()
155
+
156
+ if pa.types.is_floating(column.type):
157
+ __mask = pc.call_function(
158
+ "invert", [pc.call_function("is_nan", [column])]
159
+ )
160
+ if _mask is not None:
161
+ _mask = pc.call_function("and_kleene", [_mask, __mask])
162
+ else:
163
+ _mask = __mask
164
+
165
+ if _mask is None:
166
+ continue
167
+
168
+ if mask is not None:
169
+ mask = pc.call_function("and_kleene", [mask, _mask])
170
+ else:
171
+ mask = _mask
172
+
173
+ return table if mask is None else table.filter(mask)
@@ -0,0 +1,259 @@
1
+ # SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
+ # SPDX-License-Identifier: Apache-2.0
3
+
4
+ from collections.abc import Callable, Iterator, Mapping, Sequence
5
+ from typing import Generic, Literal, NamedTuple, Self, TypeVar, cast
6
+
7
+ import torch
8
+ from torch import Tensor
9
+
10
+ from sdm import ColumnarTensor, EnsembleTable, Stype, TableTensor
11
+ from sdm.relational import (
12
+ RelatedTables,
13
+ RelationalData,
14
+ Relationship,
15
+ TaskLink,
16
+ )
17
+ from sdm.relational.backend import (
18
+ CuGraphRelationalSampler,
19
+ PyGLibRelationalSampler,
20
+ )
21
+ from sdm.tensor.mixin import DeviceMixin
22
+
23
+ T = TypeVar("T", bound=TableTensor | EnsembleTable)
24
+
25
+ EXAMPLE_ID = "__example__"
26
+
27
+
28
+ class _RelationalSamplerOutput(NamedTuple, Generic[T]):
29
+ task_table: TableTensor
30
+ related_tables: RelatedTables[T]
31
+
32
+
33
+ class RelationalSamplerOutput(
34
+ _RelationalSamplerOutput[T], DeviceMixin, Generic[T]
35
+ ):
36
+ r"""Relational sampler output.
37
+
38
+ Args:
39
+ task_table: The task table.
40
+ related_tables: The related tables for the task table.
41
+ """
42
+
43
+ def _tensors(self) -> Iterator[Tensor]:
44
+ yield self.task_table
45
+ yield from self.related_tables._tensors()
46
+
47
+ def _apply_tensor(self, fn: Callable[[Tensor], Tensor]) -> Self:
48
+ return self.__class__(
49
+ task_table=cast(TableTensor, fn(self.task_table)),
50
+ related_tables=self.related_tables._apply_tensor(fn),
51
+ )
52
+
53
+
54
+ class RelationalSampler:
55
+ r"""Subgraph sampler over relational data.
56
+
57
+ Args:
58
+ data: The collection of named tables and their relationships.
59
+ time_columns: Mapping from table name to the datetime column used for
60
+ temporal sampling. A row in a time-aware table can only be sampled
61
+ if its timestamp does not exceed the query timestamp.
62
+ """
63
+
64
+ def __init__(
65
+ self,
66
+ data: RelationalData,
67
+ time_columns: Mapping[str, str] | None = None,
68
+ ) -> None:
69
+ self.data = data
70
+ self.time_columns = time_columns or {}
71
+
72
+ for table_name, column_name in self.time_columns.items():
73
+ stype = data.tables[table_name].stype(column_name)
74
+ if stype != Stype.datetime:
75
+ raise ValueError(
76
+ f"Expected '{column_name}' in table '{table_name}' to "
77
+ f"have semantic type {str(Stype.datetime)!r} "
78
+ f"(got {str(stype)!r})"
79
+ )
80
+
81
+ if self.data.is_cuda:
82
+ self._sampler = CuGraphRelationalSampler(data, self.time_columns)
83
+ else:
84
+ self._sampler = PyGLibRelationalSampler(data, self.time_columns)
85
+
86
+ def __call__(
87
+ self,
88
+ task_table: TableTensor,
89
+ task_link: TaskLink | Mapping[str, str | Sequence[str]],
90
+ num_neighbors: Sequence[int],
91
+ task_time_column: str | None = None,
92
+ temporal_strategy: Literal["last", "uniform"] = "last",
93
+ ) -> RelationalSamplerOutput:
94
+ r"""Alias of :meth:`sample`."""
95
+ return self.sample(
96
+ task_table=task_table,
97
+ task_link=task_link,
98
+ num_neighbors=num_neighbors,
99
+ task_time_column=task_time_column,
100
+ temporal_strategy=temporal_strategy,
101
+ )
102
+
103
+ def sample(
104
+ self,
105
+ task_table: TableTensor,
106
+ task_link: TaskLink | Mapping[str, str | Sequence[str]],
107
+ num_neighbors: Sequence[int],
108
+ task_time_column: str | None = None,
109
+ temporal_strategy: Literal["last", "uniform"] = "last",
110
+ ) -> RelationalSamplerOutput:
111
+ r"""Sample :class:`RelatedTables` for task rows.
112
+
113
+ Args:
114
+ num_neighbors: Number of neighbors to sample per hop.
115
+ task_table: Task table whose rows define the sampling queries.
116
+ task_link: Link from ``task_table`` rows to a table in the
117
+ relational data.
118
+ task_time_column: Datetime column in ``task_table`` used as the
119
+ query timestamp for temporal sampling.
120
+ temporal_strategy: How temporal neighbors are selected. ``"last"``
121
+ selects the most recent neighbors before each seed timestamp.
122
+ ``"uniform"`` samples uniformly from neighbors before each seed
123
+ timestamp.
124
+ """
125
+ if not isinstance(task_link, TaskLink):
126
+ task_link = TaskLink.from_mapping(task_link)
127
+
128
+ for table, columns in (
129
+ (task_table, task_link.task_columns),
130
+ (self.data.tables[task_link.table], task_link.table_columns),
131
+ ):
132
+ for column in columns:
133
+ stype = table.stype(column)
134
+ if stype != Stype.id:
135
+ raise ValueError(
136
+ f"Expected column '{column}' to have semantic type "
137
+ f"{str(Stype.id)!r} (got {str(stype)!r})"
138
+ )
139
+
140
+ if task_time_column is not None:
141
+ stype = task_table.stype(task_time_column)
142
+ if stype != Stype.datetime:
143
+ raise ValueError(
144
+ f"Expected task time column to have semantic type "
145
+ f"{str(Stype.datetime)!r} (got {str(stype)!r})"
146
+ )
147
+
148
+ shared = False
149
+ if task_table.dim() not in (2, 3):
150
+ raise ValueError(
151
+ f"Task table needs to be either 2D or 3D "
152
+ f"(got {task_table.dim()})"
153
+ )
154
+ if task_table.dim() == 3:
155
+ num_members, num_rows = task_table.size()[:2]
156
+ shared = all(
157
+ all(column.stride(0) == 0 for column in block.unbind(-1))
158
+ if isinstance(block, ColumnarTensor)
159
+ else block.stride(0) == 0
160
+ for _, block in task_table.items()
161
+ if block.size(-1) > 0
162
+ )
163
+ if shared:
164
+ task_table = task_table[0]
165
+ else:
166
+ task_table = cast(TableTensor, task_table.flatten(0, 1))
167
+ else:
168
+ num_members, num_rows = None, task_table.size(0)
169
+
170
+ nodes = self._sampler.sample(
171
+ task_table=task_table,
172
+ task_link=task_link,
173
+ num_neighbors=num_neighbors,
174
+ task_time_column=task_time_column,
175
+ temporal_strategy=temporal_strategy,
176
+ )
177
+
178
+ tables: dict[str, TableTensor | EnsembleTable] = {}
179
+ for table_name, (example, index) in nodes.items():
180
+ table = torch.cat(
181
+ [
182
+ self.data.tables[table_name][index],
183
+ TableTensor(
184
+ columns={"id": (EXAMPLE_ID,)},
185
+ id=ColumnarTensor(
186
+ (
187
+ example
188
+ if num_members is None or shared
189
+ else example % num_rows,
190
+ )
191
+ ),
192
+ ),
193
+ ],
194
+ dim=-1,
195
+ )
196
+ table = cast(TableTensor, table)
197
+
198
+ if num_members is None:
199
+ tables[table_name] = table
200
+ continue
201
+
202
+ if shared:
203
+ tables[table_name] = EnsembleTable.from_tables(
204
+ tables=[table for _ in range(num_members)],
205
+ member_table_ids=range(num_members),
206
+ )
207
+ continue
208
+
209
+ member = example // num_rows
210
+ tables[table_name] = EnsembleTable.from_tables(
211
+ tables=[table[member == i] for i in range(num_members)],
212
+ member_table_ids=range(num_members),
213
+ )
214
+
215
+ # Build composite keys for disjoint linkage across examples:
216
+ relationships = tuple(
217
+ Relationship(
218
+ left_table=rel.left_table,
219
+ left_columns=(*rel.left_columns, EXAMPLE_ID),
220
+ right_table=rel.right_table,
221
+ right_columns=(*rel.right_columns, EXAMPLE_ID),
222
+ )
223
+ for rel in self.data.relationships
224
+ if rel.left_table in tables and rel.right_table in tables
225
+ )
226
+
227
+ task_link = TaskLink(
228
+ task_columns=(*task_link.task_columns, EXAMPLE_ID),
229
+ table=task_link.table,
230
+ table_columns=(*task_link.table_columns, EXAMPLE_ID),
231
+ )
232
+
233
+ arange = torch.arange(task_table.size(0), device=task_table.device)
234
+ if num_members is not None:
235
+ arange = arange % num_rows
236
+ task_table: Tensor = torch.cat(
237
+ [
238
+ task_table,
239
+ TableTensor(
240
+ columns={"id": (EXAMPLE_ID,)},
241
+ id=ColumnarTensor((arange,)),
242
+ ),
243
+ ],
244
+ dim=-1,
245
+ )
246
+ if num_members is not None:
247
+ if shared:
248
+ task_table = task_table.expand(num_members, *task_table.size())
249
+ else:
250
+ task_table = task_table.view(num_members, num_rows, -1)
251
+
252
+ return RelationalSamplerOutput(
253
+ task_table=cast(TableTensor, task_table),
254
+ related_tables=RelatedTables(
255
+ tables=tables,
256
+ relationships=relationships,
257
+ task_links=(task_link,),
258
+ ),
259
+ )