Abdulrehman-PIAIC80387 commented on code in PR #42976:
URL: https://github.com/apache/superset/pull/42976#discussion_r3756122298
##########
tests/unit_tests/pandas_postprocessing/test_pivot.py:
##########
@@ -446,3 +446,191 @@ def
test_pivot_only_entirely_absent_metrics_are_restored():
assert ("metric_partial", "A") in df.columns
assert ("metric_partial", "B") not in df.columns
assert df[("metric_partial", "A")].iloc[0] == 1.0
+
+
+# --- show_values_as regression tests (#42809) --------------------------------
+#
+# ``show_values_as`` expresses each metric cell as a fraction of the row,
+# column, or grand total after pivoting. Mirrors the client-side
+# ``fractionOf`` semantic in
+# ``plugin-chart-pivot-table/src/react-pivottable/utilities.ts:739`` so
+# server-side rendering paths (CSV / XLSX exports, scheduled reports)
+# match the browser output. See #42809.
+#
+# Fixture: a tiny 3-column DataFrame that keeps row/col/grand totals easy
+# to eyeball. Two rows (``r1``, ``r2``), two columns (``c1``, ``c2``),
+# single metric ``v``. Grand total is 100 so every percent-of-total
+# assertion is trivially checkable.
+
+
+def _show_values_as_fixture() -> DataFrame:
+ """Long-format input that pivots to::
+
+ v
+ col c1 c2
+ row
+ r1 10 20
+ r2 30 40
+
+ row totals: r1=30, r2=70; col totals: c1=40, c2=60; grand=100.
+ """
+ return DataFrame(
+ {
+ "row": ["r1", "r1", "r2", "r2"],
+ "col": ["c1", "c2", "c1", "c2"],
+ "v": [10, 20, 30, 40],
+ }
+ )
+
+
+def test_pivot_show_values_as_actual_is_noop() -> None:
+ """``show_values_as='actual'`` (and ``None``) leaves values unchanged."""
+ df = _show_values_as_fixture()
+ aggregates = {"v": {"operator": "sum"}}
+ baseline = pivot(df=df, index=["row"], columns=["col"],
aggregates=aggregates)
+
+ for mode in (None, "actual"):
+ result = pivot(
+ df=df,
+ index=["row"],
+ columns=["col"],
+ aggregates=aggregates,
+ show_values_as=mode,
+ )
+ pd.testing.assert_frame_equal(result, baseline)
+
+
+def test_pivot_show_values_as_percent_row() -> None:
+ """Each cell = cell / row-total; each row sums to 1.0."""
+ result = pivot(
+ df=_show_values_as_fixture(),
+ index=["row"],
+ columns=["col"],
+ aggregates={"v": {"operator": "sum"}},
+ show_values_as="percent_row",
+ )
+ # r1: 10/30, 20/30; r2: 30/70, 40/70
+ assert result.loc["r1", ("v", "c1")] == pytest.approx(10 / 30)
+ assert result.loc["r1", ("v", "c2")] == pytest.approx(20 / 30)
+ assert result.loc["r2", ("v", "c1")] == pytest.approx(30 / 70)
+ assert result.loc["r2", ("v", "c2")] == pytest.approx(40 / 70)
+ assert result.sum(axis=1).tolist() == pytest.approx([1.0, 1.0])
+
+
+def test_pivot_show_values_as_percent_col() -> None:
+ """Each cell = cell / column-total; each column sums to 1.0."""
+ result = pivot(
+ df=_show_values_as_fixture(),
+ index=["row"],
+ columns=["col"],
+ aggregates={"v": {"operator": "sum"}},
+ show_values_as="percent_col",
+ )
+ # c1 total=40: 10/40, 30/40; c2 total=60: 20/60, 40/60
+ assert result.loc["r1", ("v", "c1")] == pytest.approx(10 / 40)
+ assert result.loc["r2", ("v", "c1")] == pytest.approx(30 / 40)
+ assert result.loc["r1", ("v", "c2")] == pytest.approx(20 / 60)
+ assert result.loc["r2", ("v", "c2")] == pytest.approx(40 / 60)
+ assert result.sum(axis=0).tolist() == pytest.approx([1.0, 1.0])
+
+
+def test_pivot_show_values_as_percent_total() -> None:
+ """Each cell = cell / grand-total; the whole frame sums to 1.0."""
+ result = pivot(
+ df=_show_values_as_fixture(),
+ index=["row"],
+ columns=["col"],
+ aggregates={"v": {"operator": "sum"}},
+ show_values_as="percent_total",
+ )
+ # grand=100: each cell divided by 100
+ assert result.loc["r1", ("v", "c1")] == pytest.approx(0.10)
+ assert result.loc["r1", ("v", "c2")] == pytest.approx(0.20)
+ assert result.loc["r2", ("v", "c1")] == pytest.approx(0.30)
+ assert result.loc["r2", ("v", "c2")] == pytest.approx(0.40)
+ assert result.values.sum() == pytest.approx(1.0)
+
+
+def test_pivot_show_values_as_preserves_nan_numerator() -> None:
+ """A NaN/NULL numerator stays NaN — matches the client-side #42810 guard
+ that a genuine SQL NULL should render blank, not "0.0%"."""
+ df = DataFrame(
+ {
+ "row": ["r1", "r1", "r2", "r2"],
+ "col": ["c1", "c2", "c1", "c2"],
+ "v": [10, np.nan, 30, 40],
+ }
+ )
+ result = pivot(
+ df=df,
+ index=["row"],
+ columns=["col"],
+ aggregates={"v": {"operator": "sum"}},
+ show_values_as="percent_row",
+ )
Review Comment:
Fixed in `80585a9678`. Verified empirically that
`pd.Series([np.nan]).sum(skipna=True) == 0.0`, so the previous fixture never
actually produced a NaN pivot cell. Rewrote the fixture to omit the (`r1`,
`c2`) row entirely — `pivot_table` then fills that cell with a genuine NaN,
which does exercise `_div_preserving_nan`'s NaN-preservation path. Test asserts
both that the NaN cell stays NaN AND that the surviving cell divides against
just its own value (`r1 c1 == 1.0` since the row-total after skipna is 10, not
10+0).
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
