tablassert 19.6.0__tar.gz → 20.0.0__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.
- {tablassert-19.6.0 → tablassert-20.0.0}/PKG-INFO +3 -16
- {tablassert-19.6.0 → tablassert-20.0.0}/README.md +0 -6
- {tablassert-19.6.0 → tablassert-20.0.0}/pyproject.toml +3 -14
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/biolink.py +12 -7
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/cli.py +117 -686
- tablassert-20.0.0/src/tablassert/data/infores_catalog.yaml +6166 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/errors.py +14 -48
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/extras.py +7 -41
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/fullmap.py +1 -1
- tablassert-20.0.0/src/tablassert/infores_registry.py +318 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/lib.py +17 -3
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/models.py +1 -1
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/net.py +18 -41
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/qc.py +8 -6
- tablassert-19.6.0/src/tablassert/agent.py +0 -5691
- tablassert-19.6.0/src/tablassert/distill.py +0 -343
- tablassert-19.6.0/src/tablassert/distill_reward.py +0 -1417
- tablassert-19.6.0/src/tablassert/graph_target.py +0 -134
- {tablassert-19.6.0 → tablassert-20.0.0}/LICENSE +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/Cargo.lock +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/Cargo.toml +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/examples/count_tables.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/src/fullmap.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/src/json.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/src/lib.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/src/ndjson.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/src/nlp.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/src/uuid.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/tests/build_golden.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/tests/common/mod.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/tests/extract_prebuilt.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/tests/fixtures/nlp_golden.tsv +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/rust/tests/nlp_golden.rs +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/__init__.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/_lazy.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/cli_entry.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/coerce.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/data/experimental_taxa.yaml +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/enums.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/ingests.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/log.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/nlp.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/progress.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/rig.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/rs.pyi +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/runcache.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/study.py +0 -0
- {tablassert-19.6.0 → tablassert-20.0.0}/src/tablassert/utils.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: tablassert
|
|
3
|
-
Version:
|
|
3
|
+
Version: 20.0.0
|
|
4
4
|
Classifier: License :: OSI Approved :: Apache Software License
|
|
5
5
|
Classifier: Development Status :: 5 - Production/Stable
|
|
6
6
|
Classifier: Intended Audience :: Science/Research
|
|
@@ -22,35 +22,28 @@ Classifier: Framework :: Pydantic :: 2
|
|
|
22
22
|
Classifier: Operating System :: POSIX :: Linux
|
|
23
23
|
Classifier: Operating System :: MacOS :: MacOS X
|
|
24
24
|
Classifier: Environment :: Console
|
|
25
|
-
Requires-Dist: biolink-model>=4.4.
|
|
25
|
+
Requires-Dist: biolink-model>=4.4.6
|
|
26
26
|
Requires-Dist: polars>=2.0.0rc2
|
|
27
27
|
Requires-Dist: pyarrow>=21.0.0
|
|
28
28
|
Requires-Dist: rapidfuzz>=3.14.3
|
|
29
29
|
Requires-Dist: pydantic>=2.12.5
|
|
30
30
|
Requires-Dist: pyyaml>=6.0.3
|
|
31
31
|
Requires-Dist: fastexcel>=0.21.0
|
|
32
|
-
Requires-Dist: smolagents>=1.26.0 ; extra == 'agent'
|
|
33
|
-
Requires-Dist: litellm>=1.93.0 ; extra == 'agent'
|
|
34
32
|
Requires-Dist: aria2==0.0.1b0 ; extra == 'aria2'
|
|
35
33
|
Requires-Dist: cyclopts>=1.0.0 ; extra == 'cli'
|
|
36
34
|
Requires-Dist: rich>=13.0.0 ; extra == 'cli'
|
|
37
|
-
Requires-Dist: datasets>=3.0.0 ; extra == 'distill'
|
|
38
35
|
Requires-Dist: loguru>=0.7.3 ; extra == 'log'
|
|
39
|
-
Requires-Dist: dspy>=3.2.1 ; extra == 'optimize'
|
|
40
36
|
Requires-Dist: scikit-learn>=1.8.0 ; extra == 'qc'
|
|
41
37
|
Requires-Dist: sentence-transformers>=5.3.0 ; extra == 'qc'
|
|
42
38
|
Requires-Dist: polars[rtcompat]>=2.0.0rc2 ; extra == 'rt'
|
|
43
|
-
Provides-Extra: agent
|
|
44
39
|
Provides-Extra: aria2
|
|
45
40
|
Provides-Extra: cli
|
|
46
|
-
Provides-Extra: distill
|
|
47
41
|
Provides-Extra: log
|
|
48
|
-
Provides-Extra: optimize
|
|
49
42
|
Provides-Extra: qc
|
|
50
43
|
Provides-Extra: rt
|
|
51
44
|
License-File: LICENSE
|
|
52
45
|
Summary: Tablassert turns biomedical spreadsheets (Excel, CSV, TSV) into knowledge graphs ready for NCATS Translator. Declare how your columns map to subject–predicate–object statements in YAML; Tablassert resolves free text to standard CURIEs, attaches provenance and statistical annotations, and emits KGX-compliant nodes and edges.
|
|
53
|
-
Keywords: knowledge graph,kgx,ncats translator,biolink,bioinformatics,biomedical data,entity resolution,tabular data,yaml configuration,declarative pipeline,quality control
|
|
46
|
+
Keywords: knowledge graph,kgx,ncats translator,biolink,bioinformatics,biomedical data,entity resolution,tabular data,yaml configuration,declarative pipeline,quality control
|
|
54
47
|
Author-email: Skye Lane Goetz <sgoetz@isbscience.org>
|
|
55
48
|
License-Expression: Apache-2.0
|
|
56
49
|
Requires-Python: >=3.11
|
|
@@ -192,8 +185,6 @@ See the [Tutorial](https://skyeav.github.io/Tablassert/tutorial/) for the full w
|
|
|
192
185
|
low-confidence mappings
|
|
193
186
|
- **KGX compliance**: emits NCATS Translator-compatible node/edge NDJSON with Biolink categories
|
|
194
187
|
and predicates
|
|
195
|
-
- **Autonomous agent (experimental)**: `tablassert agent` derives, builds, and refines configs for
|
|
196
|
-
whole papers
|
|
197
188
|
- **Performance & reproducibility**: lazy Polars pipelines and a deterministic UV-based
|
|
198
189
|
development environment
|
|
199
190
|
|
|
@@ -212,9 +203,6 @@ provides the `tablassert` command. Other extras are opt-in:
|
|
|
212
203
|
| `rt` | CPU-compatible Polars runtime | `pip install "tablassert[rt]"` |
|
|
213
204
|
| `aria2` | bundled aria2c downloader, used automatically by `build-fullmap` when installed (Linux/Windows wheels only) | `pip install "tablassert[aria2]"` |
|
|
214
205
|
| `qc` | four-stage QC audit (exact -> fuzzy -> abbreviation -> SapBERT embeddings) | `pip install "tablassert[qc]"` |
|
|
215
|
-
| `agent` | autonomous agent (smolagents, litellm, article/table context) -- experimental, API may change | `pip install "tablassert[agent]"` |
|
|
216
|
-
| `optimize` | GEPA prompt optimization for `agent --optimize` (dspy) -- experimental, API may change | `pip install "tablassert[optimize]"` |
|
|
217
|
-
| `distill` | distillation dataset export (`tablassert distill-export`, HF `datasets`) -- experimental, API may change | `pip install "tablassert[distill]"` |
|
|
218
206
|
| `log` | loguru-backed file/progress logging (rotation, enqueue) | `pip install "tablassert[log]"` |
|
|
219
207
|
|
|
220
208
|
Reaching a feature whose extra is missing never produces a bare `ModuleNotFoundError`: the failure
|
|
@@ -250,7 +238,6 @@ no LazyFrame setup or NLP preprocessing required. See the
|
|
|
250
238
|
- **[Use Case Gallery](https://skyeav.github.io/Tablassert/examples/)**: real-world configuration patterns
|
|
251
239
|
- **[CLI Reference](https://skyeav.github.io/Tablassert/cli/)**: complete command-line flag reference
|
|
252
240
|
- **[Fullmap](https://skyeav.github.io/Tablassert/fullmap/)**: building and querying the entity-resolution database
|
|
253
|
-
- **[Agent](https://skyeav.github.io/Tablassert/agent/)**: the autonomous agent pipeline
|
|
254
241
|
- **[Configuration](https://skyeav.github.io/Tablassert/configuration/graph/)**: graph and table configuration reference
|
|
255
242
|
- **[API Reference](https://skyeav.github.io/Tablassert/api/fullmap/)**: core functions documentation
|
|
256
243
|
- **[Development](https://skyeav.github.io/Tablassert/development/)**: dev environment setup and contributor workflow
|
|
@@ -131,8 +131,6 @@ See the [Tutorial](https://skyeav.github.io/Tablassert/tutorial/) for the full w
|
|
|
131
131
|
low-confidence mappings
|
|
132
132
|
- **KGX compliance**: emits NCATS Translator-compatible node/edge NDJSON with Biolink categories
|
|
133
133
|
and predicates
|
|
134
|
-
- **Autonomous agent (experimental)**: `tablassert agent` derives, builds, and refines configs for
|
|
135
|
-
whole papers
|
|
136
134
|
- **Performance & reproducibility**: lazy Polars pipelines and a deterministic UV-based
|
|
137
135
|
development environment
|
|
138
136
|
|
|
@@ -151,9 +149,6 @@ provides the `tablassert` command. Other extras are opt-in:
|
|
|
151
149
|
| `rt` | CPU-compatible Polars runtime | `pip install "tablassert[rt]"` |
|
|
152
150
|
| `aria2` | bundled aria2c downloader, used automatically by `build-fullmap` when installed (Linux/Windows wheels only) | `pip install "tablassert[aria2]"` |
|
|
153
151
|
| `qc` | four-stage QC audit (exact -> fuzzy -> abbreviation -> SapBERT embeddings) | `pip install "tablassert[qc]"` |
|
|
154
|
-
| `agent` | autonomous agent (smolagents, litellm, article/table context) -- experimental, API may change | `pip install "tablassert[agent]"` |
|
|
155
|
-
| `optimize` | GEPA prompt optimization for `agent --optimize` (dspy) -- experimental, API may change | `pip install "tablassert[optimize]"` |
|
|
156
|
-
| `distill` | distillation dataset export (`tablassert distill-export`, HF `datasets`) -- experimental, API may change | `pip install "tablassert[distill]"` |
|
|
157
152
|
| `log` | loguru-backed file/progress logging (rotation, enqueue) | `pip install "tablassert[log]"` |
|
|
158
153
|
|
|
159
154
|
Reaching a feature whose extra is missing never produces a bare `ModuleNotFoundError`: the failure
|
|
@@ -189,7 +184,6 @@ no LazyFrame setup or NLP preprocessing required. See the
|
|
|
189
184
|
- **[Use Case Gallery](https://skyeav.github.io/Tablassert/examples/)**: real-world configuration patterns
|
|
190
185
|
- **[CLI Reference](https://skyeav.github.io/Tablassert/cli/)**: complete command-line flag reference
|
|
191
186
|
- **[Fullmap](https://skyeav.github.io/Tablassert/fullmap/)**: building and querying the entity-resolution database
|
|
192
|
-
- **[Agent](https://skyeav.github.io/Tablassert/agent/)**: the autonomous agent pipeline
|
|
193
187
|
- **[Configuration](https://skyeav.github.io/Tablassert/configuration/graph/)**: graph and table configuration reference
|
|
194
188
|
- **[API Reference](https://skyeav.github.io/Tablassert/api/fullmap/)**: core functions documentation
|
|
195
189
|
- **[Development](https://skyeav.github.io/Tablassert/development/)**: dev environment setup and contributor workflow
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[project]
|
|
2
2
|
name = "tablassert"
|
|
3
|
-
version = "
|
|
3
|
+
version = "20.0.0"
|
|
4
4
|
description = "Tablassert turns biomedical spreadsheets (Excel, CSV, TSV) into knowledge graphs ready for NCATS Translator. Declare how your columns map to subject–predicate–object statements in YAML; Tablassert resolves free text to standard CURIEs, attaches provenance and statistical annotations, and emits KGX-compliant nodes and edges."
|
|
5
5
|
authors = [
|
|
6
6
|
{ name = "Skye Lane Goetz", email = "sgoetz@isbscience.org" }
|
|
@@ -17,7 +17,6 @@ keywords = [
|
|
|
17
17
|
"yaml configuration",
|
|
18
18
|
"declarative pipeline",
|
|
19
19
|
"quality control",
|
|
20
|
-
"llm agent",
|
|
21
20
|
]
|
|
22
21
|
readme = "README.md"
|
|
23
22
|
license = "Apache-2.0"
|
|
@@ -47,7 +46,7 @@ classifiers = [
|
|
|
47
46
|
]
|
|
48
47
|
requires-python = ">=3.11"
|
|
49
48
|
dependencies = [
|
|
50
|
-
"biolink-model>=4.4.
|
|
49
|
+
"biolink-model>=4.4.6",
|
|
51
50
|
"polars>=2.0.0rc2",
|
|
52
51
|
"pyarrow>=21.0.0",
|
|
53
52
|
"rapidfuzz>=3.14.3",
|
|
@@ -71,7 +70,7 @@ module-name = "tablassert.rs"
|
|
|
71
70
|
bindings = "pyo3"
|
|
72
71
|
manifest-path = "rust/Cargo.toml"
|
|
73
72
|
features = ["extension-module"]
|
|
74
|
-
include = ["src/tablassert/data/experimental_taxa.yaml"]
|
|
73
|
+
include = ["src/tablassert/data/experimental_taxa.yaml", "src/tablassert/data/infores_catalog.yaml"]
|
|
75
74
|
|
|
76
75
|
[project.scripts]
|
|
77
76
|
tablassert = "tablassert.cli_entry:main"
|
|
@@ -92,16 +91,6 @@ qc = [
|
|
|
92
91
|
"scikit-learn>=1.8.0",
|
|
93
92
|
"sentence-transformers>=5.3.0",
|
|
94
93
|
]
|
|
95
|
-
agent = [
|
|
96
|
-
"smolagents>=1.26.0",
|
|
97
|
-
"litellm>=1.93.0",
|
|
98
|
-
]
|
|
99
|
-
optimize = [
|
|
100
|
-
"dspy>=3.2.1",
|
|
101
|
-
]
|
|
102
|
-
distill = [
|
|
103
|
-
"datasets>=3.0.0",
|
|
104
|
-
]
|
|
105
94
|
log = [
|
|
106
95
|
"loguru>=0.7.3",
|
|
107
96
|
]
|
|
@@ -593,8 +593,12 @@ release from making ``species_context_qualifier`` silently emittable again.
|
|
|
593
593
|
|
|
594
594
|
|
|
595
595
|
CLASS_FIELD_OVERRIDES: dict[str, frozenset[str]] = {
|
|
596
|
-
|
|
597
|
-
|
|
596
|
+
# Absorbed by biolink-model 4.4.6 (now declared natively on both pinned classes,
|
|
597
|
+
# removed by the tripwire; kept here commented as the pattern for future grants):
|
|
598
|
+
# "EntityToDiseaseAssociation": frozenset({"population_context_qualifier", "sex_qualifier", "temporal_context_qualifier"}),
|
|
599
|
+
# "EntityToPhenotypicFeatureAssociation": frozenset({"population_context_qualifier", "temporal_context_qualifier"}),
|
|
600
|
+
"EntityToDiseaseAssociation": frozenset({"sex_qualifier", "temporal_context_qualifier"}),
|
|
601
|
+
"EntityToPhenotypicFeatureAssociation": frozenset({"temporal_context_qualifier"}),
|
|
598
602
|
}
|
|
599
603
|
"""Per-class grants of edge fields the resolved association class does not declare.
|
|
600
604
|
|
|
@@ -612,11 +616,12 @@ mixin consolidation attached ``disease_context_qualifier``,
|
|
|
612
616
|
``anatomical_context_qualifier``, and ``frequency_qualifier`` to the whole
|
|
613
617
|
disease/phenotype family, renamed ``FDA_regulatory_approvals`` to the canonical
|
|
614
618
|
``regulatory_approvals`` on the pinned classes, and added ``sex_qualifier`` to
|
|
615
|
-
``EntityToPhenotypicFeatureAssociation
|
|
616
|
-
|
|
617
|
-
|
|
618
|
-
|
|
619
|
-
``
|
|
619
|
+
``EntityToPhenotypicFeatureAssociation``; biolink-model 4.4.6 then attached
|
|
620
|
+
``population_context_qualifier`` to both pinned classes, so the tripwire removed
|
|
621
|
+
those grants the day each release landed). The remaining ones stay deliberately
|
|
622
|
+
ahead of the model (pending an upstream Biolink widening).
|
|
623
|
+
``_validation_record`` strips granted fields before record validation so the
|
|
624
|
+
deliberate gap is not reported as ``extra_forbidden``.
|
|
620
625
|
|
|
621
626
|
A tripwire test asserts every granted field is still absent from its class: the moment
|
|
622
627
|
a biolink-model release attaches the slot, the suite fails and the stale grant is
|