tablassert 16.0.0__tar.gz → 16.1.1__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 (37) hide show
  1. {tablassert-16.0.0 → tablassert-16.1.1}/PKG-INFO +2 -1
  2. {tablassert-16.0.0 → tablassert-16.1.1}/README.md +1 -0
  3. {tablassert-16.0.0 → tablassert-16.1.1}/pyproject.toml +1 -1
  4. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/cli.py +13 -3
  5. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/lib.py +39 -2
  6. {tablassert-16.0.0 → tablassert-16.1.1}/LICENSE +0 -0
  7. {tablassert-16.0.0 → tablassert-16.1.1}/rust/Cargo.lock +0 -0
  8. {tablassert-16.0.0 → tablassert-16.1.1}/rust/Cargo.toml +0 -0
  9. {tablassert-16.0.0 → tablassert-16.1.1}/rust/examples/count_tables.rs +0 -0
  10. {tablassert-16.0.0 → tablassert-16.1.1}/rust/src/fullmap.rs +0 -0
  11. {tablassert-16.0.0 → tablassert-16.1.1}/rust/src/json.rs +0 -0
  12. {tablassert-16.0.0 → tablassert-16.1.1}/rust/src/lib.rs +0 -0
  13. {tablassert-16.0.0 → tablassert-16.1.1}/rust/src/ndjson.rs +0 -0
  14. {tablassert-16.0.0 → tablassert-16.1.1}/rust/src/uuid.rs +0 -0
  15. {tablassert-16.0.0 → tablassert-16.1.1}/rust/tests/build_golden.rs +0 -0
  16. {tablassert-16.0.0 → tablassert-16.1.1}/rust/tests/common/mod.rs +0 -0
  17. {tablassert-16.0.0 → tablassert-16.1.1}/rust/tests/extract_prebuilt.rs +0 -0
  18. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/__init__.py +0 -0
  19. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/_lazy.py +0 -0
  20. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/agent.py +0 -0
  21. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/biolink.py +0 -0
  22. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/coerce.py +0 -0
  23. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/enums.py +0 -0
  24. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/errors.py +0 -0
  25. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/extras.py +0 -0
  26. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/fullmap.py +0 -0
  27. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/graph_target.py +0 -0
  28. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/ingests.py +0 -0
  29. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/log.py +0 -0
  30. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/models.py +0 -0
  31. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/nlp.py +0 -0
  32. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/progress.py +0 -0
  33. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/qc.py +0 -0
  34. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/rig.py +0 -0
  35. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/rs.pyi +0 -0
  36. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/study.py +0 -0
  37. {tablassert-16.0.0 → tablassert-16.1.1}/src/tablassert/utils.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: tablassert
3
- Version: 16.0.0
3
+ Version: 16.1.1
4
4
  Classifier: License :: OSI Approved :: Apache Software License
5
5
  Classifier: Development Status :: 5 - Production/Stable
6
6
  Classifier: Intended Audience :: Science/Research
@@ -60,6 +60,7 @@ Project-URL: Source, https://github.com/SkyeAv/Tablassert
60
60
  [![CI](https://github.com/SkyeAv/Tablassert/actions/workflows/ci.yml/badge.svg)](https://github.com/SkyeAv/Tablassert/actions/workflows/ci.yml)
61
61
  [![License](https://img.shields.io/pypi/l/tablassert.svg)](https://github.com/SkyeAv/Tablassert/blob/main/LICENSE)
62
62
  [![Docs](https://img.shields.io/github/deployments/SkyeAv/Tablassert/github-pages?label=docs)](https://skyeav.github.io/Tablassert/)
63
+ [![GitHub stars](https://img.shields.io/github/stars/SkyeAv/Tablassert.svg)](https://github.com/SkyeAv/Tablassert/stargazers)
63
64
 
64
65
  > Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON,
65
66
  > declaratively, with entity resolution built in and optional quality control.
@@ -5,6 +5,7 @@
5
5
  [![CI](https://github.com/SkyeAv/Tablassert/actions/workflows/ci.yml/badge.svg)](https://github.com/SkyeAv/Tablassert/actions/workflows/ci.yml)
6
6
  [![License](https://img.shields.io/pypi/l/tablassert.svg)](https://github.com/SkyeAv/Tablassert/blob/main/LICENSE)
7
7
  [![Docs](https://img.shields.io/github/deployments/SkyeAv/Tablassert/github-pages?label=docs)](https://skyeav.github.io/Tablassert/)
8
+ [![GitHub stars](https://img.shields.io/github/stars/SkyeAv/Tablassert.svg)](https://github.com/SkyeAv/Tablassert/stargazers)
8
9
 
9
10
  > Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON,
10
11
  > declaratively, with entity resolution built in and optional quality control.
@@ -1,6 +1,6 @@
1
1
  [project]
2
2
  name = "tablassert"
3
- version = "16.0.0"
3
+ version = "16.1.1"
4
4
  description = "Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution and quality control built in."
5
5
  authors = [
6
6
  { name = "Skye Lane Goetz", email = "sgoetz@isbscience.org" }
@@ -119,11 +119,12 @@ def build_pipeline(
119
119
  qc: bool = False,
120
120
  log: bool = False,
121
121
  head: bool = False,
122
+ no_original: bool = False,
122
123
  threads: int | None = None,
123
124
  ) -> None:
124
125
  """Load a graph YAML and build it through the shared in-process core."""
125
126
  graph: Graph = _load_graph(configuration_file)
126
- build_graph_pipeline(graph, configuration_file, progress, release=release, qc=qc, log=log, head=head, threads=threads)
127
+ build_graph_pipeline(graph, configuration_file, progress, release=release, qc=qc, log=log, head=head, no_original=no_original, threads=threads)
127
128
 
128
129
 
129
130
  def build_graph_pipeline(
@@ -134,6 +135,7 @@ def build_graph_pipeline(
134
135
  qc: bool = False,
135
136
  log: bool = False,
136
137
  head: bool = False,
138
+ no_original: bool = False,
137
139
  threads: int | None = None,
138
140
  audit_sources: bool = True,
139
141
  ) -> None:
@@ -152,6 +154,8 @@ def build_graph_pipeline(
152
154
  qc: When ``True``, run quality-control audits and final study assertions.
153
155
  log: When ``True``, enable per-section verbose logging.
154
156
  head: When ``True``, build a random sample of up to five rows per section.
157
+ no_original: When ``True``, omit the verbatim ``original_*`` source-cell
158
+ copies from the final edge NDJSON.
155
159
  threads: Optional worker thread count for the parallel fullmap reads behind
156
160
  entity resolution (auto when unset).
157
161
  """
@@ -258,6 +262,7 @@ def build_graph_pipeline(
258
262
  section_sources if audit_sources else None,
259
263
  on_phase=sub_step,
260
264
  on_subgraph=advance,
265
+ no_original=no_original,
261
266
  uuid_fields=g.uuid_fields,
262
267
  uuid_domain=g.uuid_namespace,
263
268
  )
@@ -663,6 +668,7 @@ def build_kg(
663
668
  qc: Annotated[bool, cyclopts.Parameter(name=["--qc", "-q"], negative="")] = False,
664
669
  log: Annotated[bool, cyclopts.Parameter(name=["--log", "-l"], negative="")] = False,
665
670
  head: Annotated[bool, cyclopts.Parameter(name=["--head", "-hd"], negative="")] = False,
671
+ no_original: Annotated[bool, cyclopts.Parameter(name=["--no-original", "-no"], negative="")] = False,
666
672
  threads: Annotated[int | None, cyclopts.Parameter(name=["--threads", "-t"])] = None,
667
673
  ) -> None:
668
674
  """Build a knowledge graph from a YAML configuration file.
@@ -670,7 +676,9 @@ def build_kg(
670
676
  The positional config is a Graph YAML that orchestrates one or more table
671
677
  configs into a single knowledge-graph build.
672
678
 
673
- ``--threads`` sets the worker count for the parallel fullmap reads behind entity
679
+ ``--no-original`` omits the verbatim source-cell copies (``original_subject``,
680
+ ``original_object``, and any other ``original_*`` fields) from the final edge
681
+ NDJSON. ``--threads`` sets the worker count for the parallel fullmap reads behind entity
674
682
  resolution (auto when unset). ``--qc`` requires the ``[qc]`` extra (``pip install
675
683
  "tablassert[qc]"``); it is checked before the build starts, because the audit stage
676
684
  runs LAST and a missing extra would otherwise surface only after entity resolution
@@ -687,7 +695,9 @@ def build_kg(
687
695
  raise SystemExit(2)
688
696
  if qc:
689
697
  extras.require("qc", required_by="--qc")
690
- run(7 if qc else 6, build_pipeline, graph_configuration_file, release=release, qc=qc, log=log, head=head, threads=threads)
698
+ run(
699
+ 7 if qc else 6, build_pipeline, graph_configuration_file, release=release, qc=qc, log=log, head=head, no_original=no_original, threads=threads
700
+ )
691
701
 
692
702
 
693
703
  @APP.command(name="validate")
@@ -1050,6 +1050,29 @@ def drop_zero_effect_size(lf: pl.LazyFrame, col: str = "effect_size") -> pl.Lazy
1050
1050
  return lf.filter(pl.col(col).is_null() | (pl.col(col).cast(pl.Float64) != 0.0))
1051
1051
 
1052
1052
 
1053
+ def drop_low_case_count(lf: pl.LazyFrame, col: str = "case_count", threshold: float = 25.0) -> pl.LazyFrame:
1054
+ """Drop release-mode ``applied_to_treat`` edges whose case count is below the threshold.
1055
+
1056
+ Args:
1057
+ lf: Source LazyFrame.
1058
+ col: Case-count column name.
1059
+ threshold: Minimum case count required to keep the edge.
1060
+
1061
+ Returns:
1062
+ LazyFrame with low case-count edges removed.
1063
+
1064
+ Notes:
1065
+ Only filters when the case-count column exists; no-op for sections
1066
+ without a ``case_count`` column. Null case counts are kept (no count
1067
+ was detected for that row). Only wired in for ``applied_to_treat``
1068
+ sections at op-construction time, so it never touches other predicates.
1069
+ """
1070
+ names: list[str] = lf.collect_schema().names()
1071
+ if col not in names:
1072
+ return lf
1073
+ return lf.filter(pl.col(col).is_null() | (pl.col(col).cast(pl.Float64) >= threshold))
1074
+
1075
+
1053
1076
  def idxname(col: Any) -> str:
1054
1077
  """Convert Excel-style column letters (e.g. ``"AA"``) to a polars-style ``column_<n>`` name.
1055
1078
 
@@ -1215,6 +1238,7 @@ class Tcode(Section):
1215
1238
  (sig, ()),
1216
1239
  (drop_not_significant, ()) if self.release else None,
1217
1240
  (drop_zero_effect_size, ()) if self.release else None,
1241
+ (drop_low_case_count, ()) if self.release and self.statement.predicate == "applied_to_treat" else None,
1218
1242
  ]
1219
1243
 
1220
1244
  def _node_ops(self: Self, db: Path) -> list[Any]:
@@ -1401,6 +1425,7 @@ PHASE_OF: dict[Callable, str] = {
1401
1425
  sig: "significance",
1402
1426
  drop_not_significant: "significance",
1403
1427
  drop_zero_effect_size: "significance",
1428
+ drop_low_case_count: "significance",
1404
1429
  format_numeric: "finalize",
1405
1430
  to_store: "write",
1406
1431
  }
@@ -1670,7 +1695,11 @@ def fold_unknown_to_supporting_text(lf: pl.LazyFrame) -> pl.LazyFrame:
1670
1695
 
1671
1696
 
1672
1697
  def _collect_subframes(
1673
- subgraphs: list[Path], on_phase: Callable[[str], None] | None = None, on_subgraph: Callable[[], None] | None = None, infores_id: str | None = None
1698
+ subgraphs: list[Path],
1699
+ on_phase: Callable[[str], None] | None = None,
1700
+ on_subgraph: Callable[[], None] | None = None,
1701
+ infores_id: str | None = None,
1702
+ no_original: bool = False,
1674
1703
  ) -> tuple[list[pl.LazyFrame], list[pl.LazyFrame]]:
1675
1704
  """Scan and normalize subgraph parquets into node/edge subframes.
1676
1705
 
@@ -1685,6 +1714,8 @@ def _collect_subframes(
1685
1714
  on_subgraph: Optional callback fired once after each subgraph is
1686
1715
  processed, used to tick the progress bar.
1687
1716
  infores_id: Graph-level infores CURIE recorded as node ``provided_by``.
1717
+ no_original: When True, also drop the verbatim ``original_*``
1718
+ source-cell copies from the final edge frames.
1688
1719
 
1689
1720
  Returns:
1690
1721
  Tuple of ``(subnodes, subedges)``: per-section node and edge
@@ -1709,6 +1740,9 @@ def _collect_subframes(
1709
1740
  subnodes.append(partial)
1710
1741
  # Drop internal pre-resolution snapshot columns from final edges.
1711
1742
  lf = lf.drop([c for c in lf.collect_schema().names() if c.endswith("_pre_resolution")])
1743
+ # --no-original: drop the verbatim source-cell copies from final edges too.
1744
+ if no_original:
1745
+ lf = lf.drop([c for c in lf.collect_schema().names() if c.startswith("original_")])
1712
1746
  lf = fold_unknown_to_supporting_text(lf)
1713
1747
  subedges.append(lf)
1714
1748
  if on_subgraph is not None:
@@ -1797,6 +1831,7 @@ def compile_graph(
1797
1831
  section_sources: list[dict[str, object]] | None = None,
1798
1832
  on_phase: Callable[[str], None] | None = None,
1799
1833
  on_subgraph: Callable[[], None] | None = None,
1834
+ no_original: bool = False,
1800
1835
  uuid_fields: list[str] | None = None,
1801
1836
  uuid_domain: str | None = None,
1802
1837
  ) -> None:
@@ -1817,6 +1852,8 @@ def compile_graph(
1817
1852
  ``write-edges`` / ``dedup`` / ``rig``), used to drive progress UX.
1818
1853
  on_subgraph: Optional callback fired once per processed subgraph,
1819
1854
  used to tick the progress bar.
1855
+ no_original: When ``True``, omit the verbatim ``original_*``
1856
+ source-cell copies from the final edge NDJSON.
1820
1857
  uuid_fields: Optional edge fields that constitute edge identity
1821
1858
  (``Graph.uuid_fields``). ``None`` hashes the whole edge record, so any
1822
1859
  change to any field re-mints the id.
@@ -1853,7 +1890,7 @@ def compile_graph(
1853
1890
 
1854
1891
  subnodes: list[pl.LazyFrame]
1855
1892
  subedges: list[pl.LazyFrame]
1856
- subnodes, subedges = _collect_subframes(subgraphs, on_phase, on_subgraph, rig_cfg.source_info.infores_id)
1893
+ subnodes, subedges = _collect_subframes(subgraphs, on_phase, on_subgraph, rig_cfg.source_info.infores_id, no_original)
1857
1894
  _write_ndjson(subnodes, subedges, n, e, name, version, rig_cfg, section_sources, on_phase, domain, uuid_fields)
1858
1895
 
1859
1896
 
File without changes
File without changes
File without changes
File without changes