ENH: Styler.relabel_index for directly specifying display of index labels (pandas-dev#47864)

Author: attack68

doc/source/reference/style.rst

@@ -41,6 +41,7 @@ Style application
    Styler.applymap_index
    Styler.format
    Styler.format_index
+   Styler.relabel_index
    Styler.hide
    Styler.concat
    Styler.set_td_classes

doc/source/whatsnew/v1.5.0.rst

@@ -44,6 +44,9 @@ e.g. totals and counts etc. (:issue:`43875`, :issue:`46186`)
 Additionally there is an alternative output method :meth:`.Styler.to_string`,
 which allows using the Styler's formatting methods to create, for example, CSVs (:issue:`44502`).
 
+A new feature :meth:`.Styler.relabel_index` is also made available to provide full customisation of the display of
+index or column headers (:issue:`47864`)
+
 Minor feature improvements are:
 
   - Adding the ability to render ``border`` and ``border-{side}`` CSS properties in Excel (:issue:`42276`)

pandas/io/formats/style_render.py

@@ -22,7 +22,10 @@
 from pandas._config import get_option
 
 from pandas._libs import lib
-from pandas._typing import Level
+from pandas._typing import (
+    Axis,
+    Level,
+)
 from pandas.compat._optional import import_optional_dependency
 
 from pandas.core.dtypes.common import (
@@ -1339,6 +1342,164 @@ def format_index(
 
         return self
 
+    def relabel_index(
+        self,
+        labels: Sequence | Index,
+        axis: Axis = 0,
+        level: Level | list[Level] | None = None,
+    ) -> StylerRenderer:
+        r"""
+        Relabel the index, or column header, keys to display a set of specified values.
+
+        .. versionadded:: 1.5.0
+
+        Parameters
+        ----------
+        labels : list-like or Index
+            New labels to display. Must have same length as the underlying values not
+            hidden.
+        axis : {"index", 0, "columns", 1}
+            Apply to the index or columns.
+        level : int, str, list, optional
+            The level(s) over which to apply the new labels. If `None` will apply
+            to all levels of an Index or MultiIndex which are not hidden.
+
+        Returns
+        -------
+        self : Styler
+
+        See Also
+        --------
+        Styler.format_index: Format the text display value of index or column headers.
+        Styler.hide: Hide the index, column headers, or specified data from display.
+
+        Notes
+        -----
+        As part of Styler, this method allows the display of an index to be
+        completely user-specified without affecting the underlying DataFrame data,
+        index, or column headers. This means that the flexibility of indexing is
+        maintained whilst the final display is customisable.
+
+        Since Styler is designed to be progressively constructed with method chaining,
+        this method is adapted to react to the **currently specified hidden elements**.
+        This is useful because it means one does not have to specify all the new
+        labels if the majority of an index, or column headers, have already been hidden.
+        The following produce equivalent display (note the length of ``labels`` in
+        each case).
+
+        .. code-block:: python
+
+            # relabel first, then hide
+            df = pd.DataFrame({"col": ["a", "b", "c"]})
+            df.style.relabel_index(["A", "B", "C"]).hide([0,1])
+            # hide first, then relabel
+            df = pd.DataFrame({"col": ["a", "b", "c"]})
+            df.style.hide([0,1]).relabel_index(["C"])
+
+        This method should be used, rather than :meth:`Styler.format_index`, in one of
+        the following cases (see examples):
+
+          - A specified set of labels are required which are not a function of the
+            underlying index keys.
+          - The function of the underlying index keys requires a counter variable,
+            such as those available upon enumeration.
+
+        Examples
+        --------
+        Basic use
+
+        >>> df = pd.DataFrame({"col": ["a", "b", "c"]})
+        >>> df.style.relabel_index(["A", "B", "C"])  # doctest: +SKIP
+             col
+        A      a
+        B      b
+        C      c
+
+        Chaining with pre-hidden elements
+
+        >>> df.style.hide([0,1]).relabel_index(["C"])  # doctest: +SKIP
+             col
+        C      c
+
+        Using a MultiIndex
+
+        >>> midx = pd.MultiIndex.from_product([[0, 1], [0, 1], [0, 1]])
+        >>> df = pd.DataFrame({"col": list(range(8))}, index=midx)
+        >>> styler = df.style  # doctest: +SKIP
+                  col
+        0  0  0     0
+              1     1
+           1  0     2
+              1     3
+        1  0  0     4
+              1     5
+           1  0     6
+              1     7
+        >>> styler.hide((midx.get_level_values(0)==0)|(midx.get_level_values(1)==0))
+        ...  # doctest: +SKIP
+        >>> styler.hide(level=[0,1])  # doctest: +SKIP
+        >>> styler.relabel_index(["binary6", "binary7"])  # doctest: +SKIP
+                  col
+        binary6     6
+        binary7     7
+
+        We can also achieve the above by indexing first and then re-labeling
+
+        >>> styler = df.loc[[(1,1,0), (1,1,1)]].style
+        >>> styler.hide(level=[0,1]).relabel_index(["binary6", "binary7"])
+        ...  # doctest: +SKIP
+                  col
+        binary6     6
+        binary7     7
+
+        Defining a formatting function which uses an enumeration counter. Also note
+        that the value of the index key is passed in the case of string labels so it
+        can also be inserted into the label, using curly brackets (or double curly
+        brackets if the string if pre-formatted),
+
+        >>> df = pd.DataFrame({"samples": np.random.rand(10)})
+        >>> styler = df.loc[np.random.randint(0,10,3)].style
+        >>> styler.relabel_index([f"sample{i+1} ({{}})" for i in range(3)])
+        ...  # doctest: +SKIP
+                         samples
+        sample1 (5)     0.315811
+        sample2 (0)     0.495941
+        sample3 (2)     0.067946
+        """
+        axis = self.data._get_axis_number(axis)
+        if axis == 0:
+            display_funcs_, obj = self._display_funcs_index, self.index
+            hidden_labels, hidden_lvls = self.hidden_rows, self.hide_index_
+        else:
+            display_funcs_, obj = self._display_funcs_columns, self.columns
+            hidden_labels, hidden_lvls = self.hidden_columns, self.hide_columns_
+        visible_len = len(obj) - len(set(hidden_labels))
+        if len(labels) != visible_len:
+            raise ValueError(
+                "``labels`` must be of length equal to the number of "
+                f"visible labels along ``axis`` ({visible_len})."
+            )
+
+        if level is None:
+            level = [i for i in range(obj.nlevels) if not hidden_lvls[i]]
+        levels_ = refactor_levels(level, obj)
+
+        def alias_(x, value):
+            if isinstance(value, str):
+                return value.format(x)
+            return value
+
+        for ai, i in enumerate([i for i in range(len(obj)) if i not in hidden_labels]):
+            if len(levels_) == 1:
+                idx = (i, levels_[0]) if axis == 0 else (levels_[0], i)
+                display_funcs_[idx] = partial(alias_, value=labels[ai])
+            else:
+                for aj, lvl in enumerate(levels_):
+                    idx = (i, lvl) if axis == 0 else (lvl, i)
+                    display_funcs_[idx] = partial(alias_, value=labels[ai][aj])
+
+        return self
+
 
 def _element(
     html_element: str,

pandas/tests/io/formats/style/test_format.py

@@ -30,6 +30,20 @@ def styler(df):
     return Styler(df, uuid_len=0)
 
 
+@pytest.fixture
+def df_multi():
+    return DataFrame(
+        data=np.arange(16).reshape(4, 4),
+        columns=MultiIndex.from_product([["A", "B"], ["a", "b"]]),
+        index=MultiIndex.from_product([["X", "Y"], ["x", "y"]]),
+    )
+
+
+@pytest.fixture
+def styler_multi(df_multi):
+    return Styler(df_multi, uuid_len=0)
+
+
 def test_display_format(styler):
     ctx = styler.format("{:0.1f}")._translate(True, True)
     assert all(["display_value" in c for c in row] for row in ctx["body"])
@@ -442,3 +456,46 @@ def test_boolean_format():
     ctx = df.style._translate(True, True)
     assert ctx["body"][0][1]["display_value"] is True
     assert ctx["body"][0][2]["display_value"] is False
+
+
+@pytest.mark.parametrize(
+    "hide, labels",
+    [
+        (False, [1, 2]),
+        (True, [1, 2, 3, 4]),
+    ],
+)
+def test_relabel_raise_length(styler_multi, hide, labels):
+    if hide:
+        styler_multi.hide(axis=0, subset=[("X", "x"), ("Y", "y")])
+    with pytest.raises(ValueError, match="``labels`` must be of length equal"):
+        styler_multi.relabel_index(labels=labels)
+
+
+def test_relabel_index(styler_multi):
+    labels = [(1, 2), (3, 4)]
+    styler_multi.hide(axis=0, subset=[("X", "x"), ("Y", "y")])
+    styler_multi.relabel_index(labels=labels)
+    ctx = styler_multi._translate(True, True)
+    assert {"value": "X", "display_value": 1}.items() <= ctx["body"][0][0].items()
+    assert {"value": "y", "display_value": 2}.items() <= ctx["body"][0][1].items()
+    assert {"value": "Y", "display_value": 3}.items() <= ctx["body"][1][0].items()
+    assert {"value": "x", "display_value": 4}.items() <= ctx["body"][1][1].items()
+
+
+def test_relabel_columns(styler_multi):
+    labels = [(1, 2), (3, 4)]
+    styler_multi.hide(axis=1, subset=[("A", "a"), ("B", "b")])
+    styler_multi.relabel_index(axis=1, labels=labels)
+    ctx = styler_multi._translate(True, True)
+    assert {"value": "A", "display_value": 1}.items() <= ctx["head"][0][3].items()
+    assert {"value": "B", "display_value": 3}.items() <= ctx["head"][0][4].items()
+    assert {"value": "b", "display_value": 2}.items() <= ctx["head"][1][3].items()
+    assert {"value": "a", "display_value": 4}.items() <= ctx["head"][1][4].items()
+
+
+def test_relabel_roundtrip(styler):
+    styler.relabel_index(["{}", "{}"])
+    ctx = styler._translate(True, True)
+    assert {"value": "x", "display_value": "x"}.items() <= ctx["body"][0][0].items()
+    assert {"value": "y", "display_value": "y"}.items() <= ctx["body"][1][0].items()