tablassert 7.5.1__tar.gz → 7.5.2__tar.gz

{tablassert-7.5.1 → tablassert-7.5.2}/CHANGELOG.md

@@ -2,6 +2,14 @@
 
 All notable changes to this project are documented in this file.
 
+## 7.5.2 - 2026-07-01
+
+### Changed
+- `sig()` in `lib.py` now emits a third significance label, `"INCONCLUSIVE"`, for p-values that fall between the existing significance `cutoff` (default `0.05`, inclusive) and a new `threshold` parameter (default `0.10`, exclusive). A p-value `p` is now mapped as: null → `"UNSURE"`; `p <= cutoff` → `"YES"`; `cutoff < p < threshold` → `"INCONCLUSIVE"`; `p >= threshold` → `"NO"`. The upper bound is exclusive so `0.10` (and the `0.1` `NO` cases in the existing tests) continue to map to `"NO"`. `threshold` is added to `sig()`'s signature alongside `cutoff`; the function remains wired into `Tcode.collect()` at its default arguments, so builds are unaffected unless a caller overrides the new bound.
+
+### Added
+- One regression test in `test_lib.py` (`test_sig_marks_inconclusive_band`) asserting all four bands in a single frame: a value at/below cutoff (`YES`), a value in the inconclusive range (`INCONCLUSIVE`), and a value at the exclusive threshold (`NO`).
+
 ## 7.5.1 - 2026-07-01
 
 ### Changed

{tablassert-7.5.1 → tablassert-7.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tablassert
-Version: 7.5.1
+Version: 7.5.2
 Summary: Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution and quality control built in.
 Project-URL: Homepage, https://github.com/SkyeAv/Tablassert
 Project-URL: Source, https://github.com/SkyeAv/Tablassert

tablassert-7.5.2/docs/changelog.md

@@ -0,0 +1,13 @@
+# Changelog
+
+The canonical release history lives in the repository root at [`CHANGELOG.md`](https://github.com/SkyeAv/Tablassert/blob/main/CHANGELOG.md).
+
+## Current Release Notes
+
+## 7.5.2 - 2026-07-01
+
+### Changed
+- `sig()` in `lib.py` now emits a third significance label, `"INCONCLUSIVE"`, for p-values that fall between the existing significance `cutoff` (default `0.05`, inclusive) and a new `threshold` parameter (default `0.10`, exclusive). A p-value `p` is now mapped as: null → `"UNSURE"`; `p <= cutoff` → `"YES"`; `cutoff < p < threshold` → `"INCONCLUSIVE"`; `p >= threshold` → `"NO"`. The upper bound is exclusive so `0.10` (and the `0.1` `NO` cases in the existing tests) continue to map to `"NO"`. `threshold` is added to `sig()`'s signature alongside `cutoff`; the function remains wired into `Tcode.collect()` at its default arguments, so builds are unaffected unless a caller overrides the new bound.
+
+### Added
+- One regression test in `test_lib.py` (`test_sig_marks_inconclusive_band`) asserting all four bands in a single frame: a value at/below cutoff (`YES`), a value in the inconclusive range (`INCONCLUSIVE`), and a value at the exclusive threshold (`NO`).

{tablassert-7.5.1 → tablassert-7.5.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tablassert"
-version = "7.5.1"
+version = "7.5.2"
 description = "Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution and quality control built in."
 authors = [
     { name = "Skye Lane Goetz", email = "sgoetz@isbscience.org" }
@@ -92,7 +92,7 @@ qc-cuda = [
 dev = [
     "mkdocs>=1.6.1",
     "pre-commit>=4.5.1",
-    "pyright>=1.1.408",
+    "pyright>=1.1.411",
     "pytest>=9.0.2",
     "pytest-cov>=7.1.0",
     "ruff>=0.15.6",

{tablassert-7.5.1 → tablassert-7.5.2}/src/tablassert/lib.py

@@ -5,7 +5,7 @@ import operator
 from collections.abc import Iterable
 from contextlib import ExitStack
 from functools import reduce
-from operator import add, eq, le
+from operator import add, eq, le, lt
 from os.path import basename
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Callable, Literal, Optional, Self, Union
@@ -132,6 +132,7 @@ def explode(lf: pl.LazyFrame, col: str, delimiter: str) -> pl.LazyFrame:
 def sig(
     lf: pl.LazyFrame,
     cutoff: float = 0.05,  # pyright: ignore
+    threshold: float = 0.10,
     col: str = "p value",
     out: str = "significant",
 ) -> pl.LazyFrame:
@@ -145,7 +146,13 @@ def sig(
         expr: pl.Expr = pl.col(chosen).cast(pl.Float64, strict=False)
         cond: pl.Expr = le(expr, cutoff)
         cutoff: pl.Expr = (
-            pl.when(expr.is_null()).then(pl.lit("UNSURE")).when(cond).then(pl.lit("YES")).otherwise(pl.lit("NO"))
+            pl.when(expr.is_null())
+            .then(pl.lit("UNSURE"))
+            .when(cond)
+            .then(pl.lit("YES"))
+            .when(lt(expr, threshold))
+            .then(pl.lit("INCONCLUSIVE"))
+            .otherwise(pl.lit("NO"))
         )
         return lf.with_columns(cutoff.alias(out))
     else:

{tablassert-7.5.1 → tablassert-7.5.2}/tests/test_lib.py

@@ -358,6 +358,13 @@ def test_sig_marks_null_as_unsure() -> None:
     assert list(result["significant"]) == ["UNSURE", "YES", "NO"]
 
 
+# ? sig Marks P-Values Between Cutoff And Threshold As INCONCLUSIVE
+def test_sig_marks_inconclusive_band() -> None:
+    lf: pl.LazyFrame = pl.DataFrame({"p value": [0.01, 0.07, 0.1]}).lazy()
+    result: pl.DataFrame = lib.sig(lf).collect()
+    assert list(result["significant"]) == ["YES", "INCONCLUSIVE", "NO"]
+
+
 # ? numeric_columns Matches Any Column With P Value In The Name
 def test_numeric_columns_matches_p_value_substring() -> None:
     names: list[str] = ["p value", "adjusted p value", "log p value", "subject"]

{tablassert-7.5.1 → tablassert-7.5.2}/uv.lock

@@ -1737,15 +1737,15 @@ wheels = [
 
 [[package]]
 name = "pyright"
-version = "1.1.409"
+version = "1.1.411"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "nodeenv" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/51/4e/3aa27f74211522dba7e9cbc3e74de779c6d4b654c54e50a4840623be8014/pyright-1.1.409.tar.gz", hash = "sha256:986ee05beca9e077c165758ad123667c679e050059a2546aa02473930394bc93", size = 4430434, upload-time = "2026-04-23T11:02:03.799Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/7e/ab/265f7dc69d28113ebba19092e57b075f41543b2ed048429c5f56e2b88eac/pyright-1.1.411.tar.gz", hash = "sha256:d885a0551f2e763b089a02702174e7f4ba77548cddabc972ab86d1f7f1b0f998", size = 4112861, upload-time = "2026-06-25T02:14:06.37Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/16/6b/330d8ebae582b30c2959a1ef4c3bc344ebde48c2ff0c3f113c4710735e11/pyright-1.1.409-py3-none-any.whl", hash = "sha256:aa3ea228cab90c845c7a60d28db7a844c04315356392aa09fafcee98c8c22fb3", size = 6438161, upload-time = "2026-04-23T11:02:01.309Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/49/385be530a6a5b78d1cbcd5c2e38debc8959a2fc6bdb716f4e581002979fc/pyright-1.1.411-py3-none-any.whl", hash = "sha256:dc7c72a8e2700c55baa127554040e067041ea53ccfd50bf96308cc4291c7d5d9", size = 6181526, upload-time = "2026-06-25T02:14:04.691Z" },
 ]
 
 [[package]]
@@ -2340,7 +2340,7 @@ wheels = [
 
 [[package]]
 name = "tablassert"
-version = "7.5.1"
+version = "7.5.2"
 source = { editable = "." }
 dependencies = [
     { name = "cyclopts" },
@@ -2422,7 +2422,7 @@ provides-extras = ["rt", "qc", "qc-cuda"]
 dev = [
     { name = "mkdocs", specifier = ">=1.6.1" },
     { name = "pre-commit", specifier = ">=4.5.1" },
-    { name = "pyright", specifier = ">=1.1.408" },
+    { name = "pyright", specifier = ">=1.1.411" },
     { name = "pytest", specifier = ">=9.0.2" },
     { name = "pytest-cov", specifier = ">=7.1.0" },
     { name = "ruff", specifier = ">=0.15.6" },

tablassert-7.5.1/docs/changelog.md

@@ -1,16 +0,0 @@
-# Changelog
-
-The canonical release history lives in the repository root at [`CHANGELOG.md`](https://github.com/SkyeAv/Tablassert/blob/main/CHANGELOG.md).
-
-## Current Release Notes
-
-## 7.5.1 - 2026-07-01
-
-### Changed
-- Numeric annotation columns are now coerced and emitted as controlled-notation strings in NDJSON output instead of raw values. Two new pipeline steps wired into `Tcode.collect()` (`lib.py`): `clean_numeric()` lazily casts matching columns to `Float64` with `strict=False` (non-numeric entries drop to null), and `format_numeric()` renders them as strings — p-value columns (any name containing `"p value"`, case-insensitive) in scientific notation (`{:.4e}`), and `relationship strength` / `sample size` in decimal general format (`{:.4g}`, ≥4 significant figures). Non-matching columns are left untouched, and nulls are subsequently dropped by `strip_nulls()`. `math_op()` now also casts with `strict=False` so it tolerates residual junk in numeric annotation columns. `format_numeric()` formats via numpy-backed batch conversion rather than `map_elements` for throughput.
-- Removed dead `pl.Config(set_fmt_float=...)` and `pl.Config(float_precision=...)` context managers from `compile_graph()` (`lib.py`); they were no-ops for NDJSON serialization (`write_ndjson` emits raw f64 via serde shortest-repr and ignores float display options), and the `fmt`/`precision` parameters of `compile_graph()` were removed alongside them.
-- Fixed an off-by-one in the build/validate progress bar so each section loop now shows the configuration currently being processed instead of the last-completed one. `PipelineProgress.section_loop()` (`progress.py`) previously returned a single `advance(info)` callback that set the description and ticked the completed counter together, called after each item's work — so while section *K* ran the bar still displayed section *K−1*. It now returns a `(start, advance)` pair: `start(info)` updates the description to the in-flight item without incrementing, and `advance()` ticks the counter afterwards (so the counter never claims an in-flight item is complete). All five call sites in `cli.py` (TCode build, Collect, Subgraph, Graph, Validate) were updated to `start(...)` before the work and `advance()` after; the long-running Collect and Subgraph stages continue to show the full `format_section_oneline()` summary (including the `CONFIG` name) of the in-flight section.
-
-### Added
-- Fifteen regression tests in `test_lib.py` covering `numeric_columns()` detection (p-value substring, exact-name match, case-insensitivity), `clean_numeric()` (parse/coerce numeric and scientific notation, null out non-numeric junk, leave non-matching columns untouched, noop, idempotent on Float64), `format_numeric()` (scientific notation for p-value, decimal general format for relationship strength/sample size, null preservation, floating-point-noise cleaning, noop), null-stripped NDJSON rows, `compile_graph()` NDJSON emission, and `sig()` operating over a cleaned Float64 p-value column.
-- Three regression tests in `tests/test_progress.py` pinning the new two-callback contract: `start` shows the in-flight item with the counter still at zero, `advance` ticks the counter without altering the description, and a `start`/`advance` cycle keeps the description synced to the current item rather than the previous one.