Correct bug when color and values correspond to the same color in treemap or sunburst

packages/python/plotly/plotly/express/_core.py

@@ -473,12 +473,16 @@ def make_trace_kwargs(args, trace_spec, trace_data, mapping_labels, sizeref):
             for k, v in mapping_labels.items():
                 # We need to invert the mapping here
                 k_args = invert_label(args, k)
+                print(k, k_args, args["hover_data"])
                 if k_args in args["hover_data"]:
-                    if args["hover_data"][k_args][0]:
-                        if isinstance(args["hover_data"][k_args][0], str):
-                            mapping_labels_copy[k] = v.replace(
-                                "}", "%s}" % args["hover_data"][k_args][0]
-                            )
+                    formatter = (
+                        args["hover_data"][k_args][0]
+                        if isinstance(args["hover_data"][k_args], tuple)
+                        else args["hover_data"][k_args]
+                    )
+                    if formatter:
+                        if isinstance(formatter, str):
+                            mapping_labels_copy[k] = v.replace("}", "%s}" % formatter)
                     else:
                         _ = mapping_labels_copy.pop(k)
         hover_lines = [k + "=" + v for k, v in mapping_labels_copy.items()]
@@ -1499,7 +1503,9 @@ def aggfunc_discrete(x):
 
         if args["color"]:
             if args["color"] == args["values"]:
-                aggfunc_color = "sum"
+                new_value_col_name = args["values"] + "_total"
+                df[new_value_col_name] = df[args["values"]]
+                args["values"] = new_value_col_name
         count_colname = args["values"]
     else:
         # we need a count column for the first groupby and the weighted mean of color
@@ -1518,7 +1524,7 @@ def aggfunc_discrete(x):
         if not _is_continuous(df, args["color"]):
             aggfunc_color = aggfunc_discrete
             discrete_color = True
-        elif not aggfunc_color:
+        else:
 
             def aggfunc_continuous(x):
                 return np.average(x, weights=df.loc[x.index, count_colname])
@@ -1576,6 +1582,9 @@ def aggfunc_continuous(x):
     if args["color"]:
         if not args["hover_data"]:
             args["hover_data"] = [args["color"]]
+        elif isinstance(args["hover_data"], dict):
+            if not args["hover_data"].get(args["color"]):
+                args["hover_data"][args["color"]] = True
         else:
             args["hover_data"].append(args["color"])
     return args

packages/python/plotly/plotly/tests/test_core/test_px/test_px_functions.py

@@ -149,10 +149,6 @@ def test_sunburst_treemap_with_path():
     fig = px.sunburst(df, path=path, values="values")
     assert fig.data[0].branchvalues == "total"
     assert fig.data[0].values[-1] == np.sum(values)
-    # Continuous colorscale
-    fig = px.sunburst(df, path=path, values="values", color="values")
-    assert "coloraxis" in fig.data[0].marker
-    assert np.all(np.array(fig.data[0].marker.colors) == np.array(fig.data[0].values))
     # Error when values cannot be converted to numerical data type
     df["values"] = ["1 000", "3 000", "2", "4", "2", "2", "1 000", "4 000"]
     msg = "Column `values` of `df` could not be converted to a numerical data type."
@@ -162,6 +158,12 @@ def test_sunburst_treemap_with_path():
     path = [df.total, "regions", df.sectors, "vendors"]
     fig = px.sunburst(df, path=path)
     assert fig.data[0].branchvalues == "total"
+    # Continuous colorscale
+    df["values"] = 1
+    fig = px.sunburst(df, path=path, values="values", color="values")
+    assert "coloraxis" in fig.data[0].marker
+    assert np.all(np.array(fig.data[0].marker.colors) == 1)
+    assert fig.data[0].values[-1] == 8
 
 
 def test_sunburst_treemap_with_path_and_hover():
@@ -329,28 +331,6 @@ def test_parcats_dimensions_max():
 
     # default behaviour
     fig = px.parallel_categories(df)
-    assert [d.label for d in fig.data[0].dimensions] == [
-        "sex",
-        "smoker",
-        "day",
-        "time",
-        "size",
-    ]
-
-    # explicit subset of default
-    fig = px.parallel_categories(df, dimensions=["sex", "smoker", "day"])
-    assert [d.label for d in fig.data[0].dimensions] == ["sex", "smoker", "day"]
-
-    # shrinking max
-    fig = px.parallel_categories(df, dimensions_max_cardinality=4)
-    assert [d.label for d in fig.data[0].dimensions] == [
-        "sex",
-        "smoker",
-        "day",
-        "time",
-    ]
-
-    # explicit superset of default, violating the max
     fig = px.parallel_categories(
         df, dimensions=["sex", "smoker", "day", "size"], dimensions_max_cardinality=4
     )