data-sampler 3.5.0__tar.gz → 3.5.1__tar.gz

{data_sampler-3.5.0 → data_sampler-3.5.1}/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## v3.5.1 — 2026-07-24
+
+- **The "skip from reduction (PCA)" toggle is hidden for non-numeric columns.**
+  PCA reduction only ever operates on continuous numeric columns (booleans and
+  datetimes are explicitly rejected; strings/categoricals never qualify), so the
+  toggle is meaningless on those columns. It now appears in the detail panel only
+  when the selected column is numeric — matching the columns table, which already
+  renders `—` in the reduce cell for non-numeric columns. No behavior change to
+  the reduction itself: skipped columns were, and remain, held out of the PCA
+  math entirely and passed through to the output unchanged.
+
 ## v3.5.0 — 2026-07-24
 
 - **Names anonymizer is now gender- and ethnicity-aware.** The bundled library

{data_sampler-3.5.0 → data_sampler-3.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-sampler
-Version: 3.5.0
+Version: 3.5.1
 Summary: Hand someone data that looks and behaves like your production data, isn't your production data, and provably kept its statistical variety — stratified sampling + consistent anonymization, with a terminal UI.
 Project-URL: Homepage, https://github.com/aaronified/data-sampler
 Project-URL: Changelog, https://github.com/aaronified/data-sampler/blob/main/CHANGELOG.md

{data_sampler-3.5.0 → data_sampler-3.5.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "data-sampler"
-version = "3.5.0"
+version = "3.5.1"
 description = "Hand someone data that looks and behaves like your production data, isn't your production data, and provably kept its statistical variety — stratified sampling + consistent anonymization, with a terminal UI."
 readme = "README.md"
 license = { file = "LICENSE" }

{data_sampler-3.5.0 → data_sampler-3.5.1}/src/data_sampler/__init__.py

@@ -18,7 +18,7 @@ Public API::
 
 from __future__ import annotations
 
-__version__ = "3.5.0"
+__version__ = "3.5.1"
 
 from .io import SUPPORTED_EXTENSIONS, list_sheets, load_file, save_output
 from .reduce import ReductionResult, reduce_columns

{data_sampler-3.5.0 → data_sampler-3.5.1}/src/data_sampler/tui/app.py

@@ -882,6 +882,12 @@ class ColumnsScreen(Screen):
             skip_reduce = self.query_one("#skip-reduce", Switch)
             if skip_reduce.value != cfg.skip_reduce:
                 skip_reduce.value = cfg.skip_reduce
+            # PCA reduction only ever touches continuous numeric columns, so the
+            # "skip from reduction" toggle is meaningless for string / categorical
+            # / boolean / datetime columns — hide the whole row for those
+            self.query_one("#reduce-skip-row").set_class(
+                self.stats[name].kind != "numeric", "hidden"
+            )
             # names gender / ethnicity controls
             gsel = self.query_one("#opt-names-gender", Select)
             if gsel.value != cfg.gender:

{data_sampler-3.5.0 → data_sampler-3.5.1}/tests/test_tui.py

@@ -584,6 +584,31 @@ def test_non_numeric_skip_reduce_shows_dash(csv_file):
     run(go())
 
 
+def test_reduce_skip_toggle_hidden_for_non_numeric(csv_file):
+    """PCA reduction only ever touches continuous numeric columns, so the
+    'skip from reduction (PCA)' row must be shown for numeric columns and
+    hidden for string / categorical / boolean columns."""
+    async def go():
+        app = DataSamplerApp(path=str(csv_file))
+        async with app.run_test(size=(160, 45)) as pilot:
+            screen = await wait_for_screen(app, pilot, ColumnsScreen)
+            row = screen.query_one("#reduce-skip-row")
+
+            screen._sync_config_panel("score")   # numeric → shown
+            assert not row.has_class("hidden")
+
+            screen._sync_config_panel("region")  # categorical → hidden
+            assert row.has_class("hidden")
+
+            screen._sync_config_panel("active")  # boolean → hidden
+            assert row.has_class("hidden")
+
+            screen._sync_config_panel("id")      # numeric again → shown
+            assert not row.has_class("hidden")
+
+    run(go())
+
+
 def test_refresh_browser_action(csv_file):
     async def go():
         app = DataSamplerApp()