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
@@ -0,0 +1,199 @@
1
+ # SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
+ # SPDX-License-Identifier: Apache-2.0
3
+
4
+ from typing import cast
5
+
6
+ import torch
7
+ from torch.nn import ModuleDict
8
+
9
+ from sdm import EnsembleTable, Stype
10
+ from sdm.processing import (
11
+ EnsembleInvertibleMixin,
12
+ EnsembleProcessor,
13
+ Processor,
14
+ )
15
+
16
+
17
+ class StypeDispatch(EnsembleProcessor, EnsembleInvertibleMixin):
18
+ r"""Apply separate processor pipelines to columns grouped by semantic type.
19
+
20
+ For each configured route, matching columns from a
21
+ :class:`~sdm.tensor.TableTensor` or
22
+ :class:`~sdm.EnsembleTable` are passed to that processor. Ordinary
23
+ processors learn separate state for each compatible ensemble group, while
24
+ ensemble-aware processors operate on all groups directly. Compatible
25
+ members are processed together and route outputs are concatenated in
26
+ semantic type order while preserving logical member order. A route may
27
+ change column values, names, count, or order. With the default passthrough
28
+ behavior, unconfigured semantic types follow in input order.
29
+
30
+ Inverse transform supports routes that preserve their semantic type. Every
31
+ active route must be invertible, and routes must not share an output
32
+ semantic type. Passthrough columns are preserved.
33
+
34
+ Args:
35
+ numerical: Processor or stateless callable route for numerical
36
+ columns.
37
+ categorical: Processor or stateless callable route for categorical
38
+ columns.
39
+ datetime: Processor or stateless callable route for datetime columns.
40
+ text: Processor or stateless callable route for text columns.
41
+ id: Processor or stateless callable route for identifier columns.
42
+ """
43
+
44
+ def __init__(
45
+ self,
46
+ *,
47
+ numerical: object = None,
48
+ categorical: object = None,
49
+ datetime: object = None,
50
+ id: object = None,
51
+ text: object = None,
52
+ ) -> None:
53
+ super().__init__()
54
+ self.processors: ModuleDict[EnsembleProcessor] = ModuleDict()
55
+ for stype, processor in (
56
+ (Stype.numerical, numerical),
57
+ (Stype.categorical, categorical),
58
+ (Stype.datetime, datetime),
59
+ (Stype.text, text),
60
+ (Stype.id, id),
61
+ ):
62
+ if processor is None:
63
+ continue
64
+ processor = EnsembleProcessor.as_processor(processor)
65
+ self.processors[str(stype)] = processor
66
+
67
+ self.handles_stypes = frozenset(
68
+ Stype(stype) for stype in self.processors
69
+ )
70
+ self.requires_fit = any(
71
+ processor.requires_fit for processor in self.processors.values()
72
+ )
73
+ self._active_routes: tuple[str, ...] | None = None
74
+
75
+ def get_extra_state(
76
+ self,
77
+ ) -> tuple[str, ...] | None:
78
+ r""":meta private:""" # noqa: D415
79
+ return self._active_routes
80
+
81
+ def set_extra_state(self, state: object) -> None:
82
+ r""":meta private:""" # noqa: D415
83
+ self._active_routes = cast(tuple[str, ...] | None, state)
84
+
85
+ def _find_active_routes(
86
+ self,
87
+ ensemble_table: EnsembleTable,
88
+ ) -> tuple[str, ...]:
89
+ return tuple(
90
+ stype
91
+ for stype in self.processors
92
+ if any(
93
+ len(group.columns[Stype(stype)]) > 0
94
+ for group in ensemble_table._iter_groups()
95
+ )
96
+ )
97
+
98
+ def _fit_ensemble(
99
+ self,
100
+ ensemble_table: EnsembleTable,
101
+ *,
102
+ generator: torch.Generator | None = None,
103
+ ) -> None:
104
+ self._active_routes = self._find_active_routes(ensemble_table)
105
+ for stype in self._active_routes:
106
+ self.processors[stype].fit_ensemble(
107
+ ensemble_table.select_stypes(stype),
108
+ generator=generator,
109
+ )
110
+
111
+ def _fit_transform_ensemble(
112
+ self,
113
+ ensemble_table: EnsembleTable,
114
+ *,
115
+ generator: torch.Generator | None = None,
116
+ ) -> EnsembleTable:
117
+ self._active_routes = self._find_active_routes(ensemble_table)
118
+ outputs = [
119
+ self.processors[stype].fit_transform_ensemble(
120
+ ensemble_table.select_stypes(stype),
121
+ generator=generator,
122
+ )
123
+ for stype in self._active_routes
124
+ ]
125
+ outputs.append(self._remainder_ensemble(ensemble_table))
126
+ if len(outputs) == 0:
127
+ return ensemble_table.select_stypes(())
128
+ return EnsembleTable.concatenate_columns(outputs)
129
+
130
+ def _transform_ensemble(
131
+ self,
132
+ ensemble_table: EnsembleTable,
133
+ ) -> EnsembleTable:
134
+ active_routes = self._active_routes
135
+ if not self.requires_fit or active_routes is None:
136
+ active_routes = self._find_active_routes(ensemble_table)
137
+ self._active_routes = active_routes
138
+ outputs = [
139
+ self.processors[stype].transform_ensemble(
140
+ ensemble_table.select_stypes(stype)
141
+ )
142
+ for stype in active_routes
143
+ ]
144
+ outputs.append(self._remainder_ensemble(ensemble_table))
145
+ if len(outputs) == 0:
146
+ return ensemble_table.select_stypes(())
147
+ return EnsembleTable.concatenate_columns(outputs)
148
+
149
+ def _inverse_transform_ensemble(
150
+ self,
151
+ ensemble_table: EnsembleTable,
152
+ ) -> EnsembleTable:
153
+ active_routes = self._active_routes
154
+ if not self.requires_fit or active_routes is None:
155
+ active_routes = self._find_active_routes(ensemble_table)
156
+ self._active_routes = active_routes
157
+
158
+ outputs = []
159
+ for stype in active_routes:
160
+ processor = self.processors[stype]
161
+ if not isinstance(processor, EnsembleInvertibleMixin):
162
+ raise TypeError(
163
+ f"{processor.__class__.__name__!r} is not invertible."
164
+ )
165
+ # TODO This is wrong. A processor may not map to same stype back!
166
+ outputs.append(
167
+ processor.inverse_transform_ensemble(
168
+ ensemble_table.select_stypes(stype)
169
+ )
170
+ )
171
+
172
+ outputs.append(self._remainder_ensemble(ensemble_table))
173
+ return EnsembleTable.concatenate_columns(outputs)
174
+
175
+ def _remainder_ensemble(
176
+ self,
177
+ ensemble_table: EnsembleTable,
178
+ ) -> EnsembleTable:
179
+ return ensemble_table.select_stypes(
180
+ tuple(
181
+ stype for stype in Stype if str(stype) not in self.processors
182
+ )
183
+ )
184
+
185
+ def __repr__(self, *, indent: int = 0) -> str:
186
+ if len(self.processors) == 0:
187
+ return super().__repr__(indent=indent)
188
+
189
+ reprs = []
190
+ for stype, processor in self.processors.items():
191
+ processor = cast(Processor, processor)
192
+ processor_repr = processor.__repr__(indent=indent + 2)
193
+ processor_repr = processor_repr[indent + 2 :]
194
+ reprs.append(f"{' ' * (indent + 2)}{stype}={processor_repr}")
195
+ return (
196
+ f"{' ' * indent}{self.__class__.__name__}(\n"
197
+ + ",\n".join(reprs)
198
+ + f",\n{' ' * indent})"
199
+ )
@@ -0,0 +1,120 @@
1
+ # SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
+ # SPDX-License-Identifier: Apache-2.0
3
+
4
+ from typing import Literal, cast
5
+
6
+ import torch
7
+ from torch.nn import ModuleDict
8
+
9
+ from sdm import EnsembleTable, Stype
10
+ from sdm.processing import EnsembleProcessor, Processor
11
+
12
+
13
+ class TableDispatch(EnsembleProcessor):
14
+ """Apply separate feature processors to task and related tables.
15
+
16
+ :class:`TableDispatch` is resolved only during model execution.
17
+
18
+ Args:
19
+ task: Processor used for the task table.
20
+ related: Processor used for related tables.
21
+ """
22
+
23
+ def __init__(
24
+ self,
25
+ *,
26
+ task: object = None,
27
+ related: object = None,
28
+ ) -> None:
29
+ super().__init__()
30
+ self.processors: ModuleDict[EnsembleProcessor] = ModuleDict()
31
+ for route, processor in (("task", task), ("related", related)):
32
+ if processor is None:
33
+ continue
34
+ self.processors[route] = EnsembleProcessor.as_processor(processor)
35
+
36
+ self.requires_fit = any(
37
+ processor.requires_fit for processor in self.processors.values()
38
+ )
39
+ self._route: Literal["task", "related"] | None = None
40
+
41
+ @property
42
+ def handles_stypes(self) -> frozenset[Stype]:
43
+ r""":meta private:""" # noqa: D415
44
+ return frozenset(
45
+ stype
46
+ for processor in self.processors.values()
47
+ for stype in processor.handles_stypes
48
+ )
49
+
50
+ def _fit_ensemble(
51
+ self,
52
+ ensemble_table: EnsembleTable,
53
+ *,
54
+ generator: torch.Generator | None = None,
55
+ ) -> None:
56
+ if self._route is None:
57
+ raise RuntimeError(
58
+ f"{self.__class__.__name__!r} has no resolved table route; "
59
+ "use it in a 'Recipe' through model execution"
60
+ )
61
+ if self._route in self.processors:
62
+ self.processors[self._route].fit_ensemble(
63
+ ensemble_table,
64
+ generator=generator,
65
+ )
66
+
67
+ def _fit_transform_ensemble(
68
+ self,
69
+ ensemble_table: EnsembleTable,
70
+ *,
71
+ generator: torch.Generator | None = None,
72
+ ) -> EnsembleTable:
73
+ if self._route is None:
74
+ raise RuntimeError(
75
+ f"{self.__class__.__name__!r} has no resolved table route; "
76
+ "use it in a 'Recipe' through model execution"
77
+ )
78
+ if self._route not in self.processors:
79
+ return ensemble_table
80
+ return self.processors[self._route].fit_transform_ensemble(
81
+ ensemble_table,
82
+ generator=generator,
83
+ )
84
+
85
+ def _transform_ensemble(
86
+ self,
87
+ ensemble_table: EnsembleTable,
88
+ ) -> EnsembleTable:
89
+ if self._route is None:
90
+ raise RuntimeError(
91
+ f"{self.__class__.__name__!r} has no resolved table route; "
92
+ "use it in a 'Recipe' through model execution"
93
+ )
94
+ if self._route not in self.processors:
95
+ return ensemble_table
96
+ return self.processors[self._route].transform_ensemble(ensemble_table)
97
+
98
+ def get_extra_state(self) -> str | None:
99
+ r""":meta private:""" # noqa: D415
100
+ return self._route
101
+
102
+ def set_extra_state(self, state: object) -> None:
103
+ r""":meta private:""" # noqa: D415
104
+ self._route = cast(Literal["task", "related"] | None, state)
105
+
106
+ def __repr__(self, *, indent: int = 0) -> str:
107
+ if len(self.processors) == 0:
108
+ return super().__repr__(indent=indent)
109
+
110
+ reprs = []
111
+ for route, processor in self.processors.items():
112
+ processor = cast(Processor, processor)
113
+ processor_repr = processor.__repr__(indent=indent + 2)
114
+ processor_repr = processor_repr[indent + 2 :]
115
+ reprs.append(f"{' ' * (indent + 2)}{route}={processor_repr}")
116
+ return (
117
+ f"{' ' * indent}{self.__class__.__name__}(\n"
118
+ + ",\n".join(reprs)
119
+ + f",\n{' ' * indent})"
120
+ )
@@ -0,0 +1,135 @@
1
+ # SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
+ # SPDX-License-Identifier: Apache-2.0
3
+
4
+ from typing import Literal, cast
5
+
6
+ import torch
7
+ from torch.nn import ModuleDict
8
+
9
+ from sdm import EnsembleTable, Stype, TableTensor
10
+ from sdm.processing import EnsembleProcessor, Processor
11
+
12
+
13
+ class TaskDispatch(EnsembleProcessor):
14
+ """Apply separate processors based on the semantic type of the target.
15
+
16
+ :class:`TaskDispatch` is resolved only during model execution.
17
+
18
+ Args:
19
+ classification: Processor selected for a categorical target.
20
+ regression: Processor selected for a numerical target.
21
+ """
22
+
23
+ def __init__(
24
+ self,
25
+ *,
26
+ classification: object = None,
27
+ regression: object = None,
28
+ ) -> None:
29
+ super().__init__()
30
+ self.processors: ModuleDict[EnsembleProcessor] = ModuleDict()
31
+ for task, processor in (
32
+ ("classification", classification),
33
+ ("regression", regression),
34
+ ):
35
+ if processor is None:
36
+ continue
37
+ processor = EnsembleProcessor.as_processor(processor)
38
+ self.processors[task] = processor
39
+
40
+ self.requires_fit = any(
41
+ processor.requires_fit for processor in self.processors.values()
42
+ )
43
+ self._task: Literal["classification", "regression"] | None = None
44
+
45
+ @property
46
+ def handles_stypes(self) -> frozenset[Stype]:
47
+ r""":meta private:""" # noqa: D415
48
+ if self._task is None:
49
+ return frozenset(
50
+ stype
51
+ for processor in self.processors.values()
52
+ for stype in processor.handles_stypes
53
+ )
54
+ if self._task not in self.processors:
55
+ return frozenset()
56
+ return self.processors[self._task].handles_stypes
57
+
58
+ def _processor(self) -> EnsembleProcessor:
59
+ if self._task is None:
60
+ raise RuntimeError(
61
+ f"{self.__class__.__name__!r} has no resolved task; use it "
62
+ "in a 'Recipe' through model execution"
63
+ )
64
+ return self.processors[self._task]
65
+
66
+ def _fit(
67
+ self,
68
+ table: TableTensor,
69
+ *,
70
+ generator: torch.Generator | None = None,
71
+ ) -> None:
72
+ self._processor().fit(table, generator=generator)
73
+
74
+ def _fit_transform(
75
+ self,
76
+ table: TableTensor,
77
+ *,
78
+ generator: torch.Generator | None = None,
79
+ ) -> TableTensor:
80
+ return self._processor().fit_transform(table, generator=generator)
81
+
82
+ def _transform(self, table: TableTensor) -> TableTensor:
83
+ return self._processor().transform(table)
84
+
85
+ def _fit_ensemble(
86
+ self,
87
+ ensemble_table: EnsembleTable,
88
+ *,
89
+ generator: torch.Generator | None = None,
90
+ ) -> None:
91
+ self._processor().fit_ensemble(ensemble_table, generator=generator)
92
+
93
+ def _fit_transform_ensemble(
94
+ self,
95
+ ensemble_table: EnsembleTable,
96
+ *,
97
+ generator: torch.Generator | None = None,
98
+ ) -> EnsembleTable:
99
+ return self._processor().fit_transform_ensemble(
100
+ ensemble_table,
101
+ generator=generator,
102
+ )
103
+
104
+ def _transform_ensemble(
105
+ self,
106
+ ensemble_table: EnsembleTable,
107
+ ) -> EnsembleTable:
108
+ return self._processor().transform_ensemble(ensemble_table)
109
+
110
+ def get_extra_state(self) -> str | None:
111
+ r""":meta private:""" # noqa: D415
112
+ return self._task
113
+
114
+ def set_extra_state(self, state: object) -> None:
115
+ r""":meta private:""" # noqa: D415
116
+ self._task = cast(
117
+ Literal["classification", "regression"] | None,
118
+ state,
119
+ )
120
+
121
+ def __repr__(self, *, indent: int = 0) -> str:
122
+ if len(self.processors) == 0:
123
+ return super().__repr__(indent=indent)
124
+
125
+ reprs = []
126
+ for task, processor in self.processors.items():
127
+ processor = cast(Processor, processor)
128
+ processor_repr = processor.__repr__(indent=indent + 2)
129
+ processor_repr = processor_repr[indent + 2 :]
130
+ reprs.append(f"{' ' * (indent + 2)}{task}={processor_repr}")
131
+ return (
132
+ f"{' ' * indent}{self.__class__.__name__}(\n"
133
+ + ",\n".join(reprs)
134
+ + f",\n{' ' * indent})"
135
+ )
@@ -0,0 +1,60 @@
1
+ # SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
+ # SPDX-License-Identifier: Apache-2.0
3
+
4
+ from typing import cast
5
+
6
+ import torch
7
+
8
+ from sdm import Stype, TableTensor
9
+ from sdm.processing import Processor
10
+
11
+
12
+ class ToNumerical(Processor):
13
+ """Move categorical columns into the numerical block.
14
+
15
+ This is an stype conversion step:
16
+ :class:`~sdm.tensor.CategoricalTensor` already stores ordinal category ids
17
+ and the category vocabulary. ``ToNumerical`` reuses those existing ids,
18
+ casts them to the numerical dtype, and clears the categorical block so
19
+ numerical-only models can consume both original numerical and categorical
20
+ features. Missing categorical values remain ``-1``.
21
+
22
+ Unhandled semantic types are preserved unchanged.
23
+
24
+ """
25
+
26
+ requires_fit = False
27
+ handles_stypes = frozenset({Stype.numerical, Stype.categorical})
28
+
29
+ def _transform(self, table: TableTensor) -> TableTensor:
30
+ """Return ``table`` with categorical columns moved to ``numerical``."""
31
+ # Already numerical-only: nothing to move.
32
+ if all(
33
+ stype == Stype.numerical or block.size(-1) == 0
34
+ for stype, block in table.items()
35
+ ):
36
+ return table
37
+
38
+ # Casting to the (floating-point) numerical dtype also unwraps a
39
+ # CategoricalTensor to its raw ordinal ids as a plain tensor.
40
+ categorical = table.categorical.to(table.numerical.dtype)
41
+ columns = (
42
+ *table.columns[Stype.numerical],
43
+ *table.columns[Stype.categorical],
44
+ )
45
+ numerical = (
46
+ categorical
47
+ if table.numerical.size(-1) == 0
48
+ else torch.cat((table.numerical, categorical), dim=-1)
49
+ )
50
+ out = table.__class__(
51
+ columns={Stype.numerical: columns},
52
+ numerical=numerical,
53
+ )
54
+ return cast(
55
+ TableTensor,
56
+ torch.cat(
57
+ (table.drop_stypes((Stype.numerical, Stype.categorical)), out),
58
+ dim=-1,
59
+ ),
60
+ )
@@ -0,0 +1,8 @@
1
+ # SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
+ # SPDX-License-Identifier: Apache-2.0
3
+
4
+ """Datetime preprocessing transforms."""
5
+
6
+ from sdm.processing.datetime.calendar import AddCalendarFields
7
+
8
+ __all__ = ["AddCalendarFields"]