data: fix Marginal.visualize crash on categorical features (#119)

python/interpret-core/interpret/data/_response.py

@@ -10,6 +10,21 @@
 from ..utils._unify_data import unify_data
 
 
+def _is_numeric_bin_edges(names):
+    """Return True iff `names` looks like a numeric bin-edge sequence.
+
+    For continuous features the density payload stores numeric bin edges
+    (e.g. ``[0.0, 1.5, 3.0, ...]``); for categorical features it stores the
+    string category labels themselves (e.g. ``["a", "b", "c"]``). The
+    histogram path computes ``names[1] - names[0]`` to derive the plotly
+    bin size, which raises ``TypeError`` on the categorical case (Issue #119).
+    Use this guard before doing the subtraction.
+    """
+    return len(names) >= 2 and all(
+        isinstance(n, (int, float, np.integer, np.floating)) for n in names[:2]
+    )
+
+
 class Marginal(DataExplainer):
     """Provides a marginal plot for provided data."""
 
@@ -200,15 +215,18 @@ def visualize(self, key=None):
 
         # Show feature graph
         density_dict = data_dict["feature_density"]
-
-        bin_size = density_dict["names"][1] - density_dict["names"][0]
         is_categorical = (
             self.feature_types[key] == "nominal" or self.feature_types[key] == "ordinal"
         )
 
+        # Bin sizing only makes sense for numeric histograms. For categorical
+        # features density_dict["names"] holds string category labels (Issue #119),
+        # so subtracting them raises TypeError. Compute bin_size lazily only on
+        # the numeric branch.
         if is_categorical:
             trace1 = go.Histogram(x=data_dict["x"], name="x density", yaxis="y2")
         else:
+            bin_size = density_dict["names"][1] - density_dict["names"][0]
             trace1 = go.Histogram(
                 x=data_dict["x"],
                 name="x density",
@@ -222,19 +240,28 @@ def visualize(self, key=None):
             )
         data = []
         resp_density_dict = data_dict["response_density"]
-        resp_bin_size = density_dict["names"][1] - density_dict["names"][0]
-
-        trace2 = go.Histogram(
-            y=data_dict["y"],
-            name="y density",
-            xaxis="x2",
-            autobiny=False,
-            ybins={
-                "start": resp_density_dict["names"][0],
-                "end": resp_density_dict["names"][-1],
-                "size": resp_bin_size,
-            },
-        )
+        # The response side: only build a fixed-bin histogram when the response
+        # is numeric. response_density["names"] are bin edges; for a continuous
+        # response we can compute resp_bin_size from those. For a categorical
+        # response we let plotly auto-bin.
+        is_categorical_response = not _is_numeric_bin_edges(resp_density_dict["names"])
+        if is_categorical_response:
+            trace2 = go.Histogram(y=data_dict["y"], name="y density", xaxis="x2")
+        else:
+            resp_bin_size = (
+                resp_density_dict["names"][1] - resp_density_dict["names"][0]
+            )
+            trace2 = go.Histogram(
+                y=data_dict["y"],
+                name="y density",
+                xaxis="x2",
+                autobiny=False,
+                ybins={
+                    "start": resp_density_dict["names"][0],
+                    "end": resp_density_dict["names"][-1],
+                    "size": resp_bin_size,
+                },
+            )
         data.append(trace1)
         data.append(trace2)
         x = data_dict["feature_samples"]

python/interpret-core/tests/data/test_marginal_visualize.py

@@ -0,0 +1,73 @@
+# Copyright (c) 2026 The InterpretML Contributors
+# Distributed under the MIT software license
+
+"""Regression tests for Marginal.visualize() on categorical features.
+
+Issue #119: ``Marginal(...).explain_data(...).visualize(key)`` raised
+``TypeError: unsupported operand type(s) for -: 'str' and 'str'`` when
+``feature_types[key]`` was ``"nominal"`` because the histogram path
+unconditionally computed ``density_dict["names"][1] - density_dict["names"][0]``
+even though categorical features carry string labels in ``names``.
+"""
+
+import numpy as np
+import pandas as pd
+import pytest
+from interpret.data import Marginal
+
+
+@pytest.fixture
+def mixed_dataframe():
+    return pd.DataFrame(
+        {
+            "cat": ["a", "b", "a", "c", "b", "a", "c", "b"],
+            "cont": [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0],
+        }
+    )
+
+
+def test_visualize_nominal_feature_continuous_target_succeeds(mixed_dataframe):
+    # BEFORE: this call raised TypeError on str-str subtraction.
+    # AFTER: returns a plotly Figure.
+    y = np.array([0.5, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5])
+    explanation = Marginal(feature_types=["nominal", "continuous"]).explain_data(
+        mixed_dataframe, y
+    )
+    fig = explanation.visualize(0)
+    assert fig is not None
+    # We don't depend on plotly types beyond the .data attribute existing.
+    assert hasattr(fig, "data")
+
+
+def test_visualize_continuous_feature_still_works(mixed_dataframe):
+    # Non-regression: the continuous branch must continue to work after
+    # the categorical fix.
+    y = np.array([0.5, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5])
+    explanation = Marginal(feature_types=["nominal", "continuous"]).explain_data(
+        mixed_dataframe, y
+    )
+    fig = explanation.visualize(1)
+    assert fig is not None
+    assert hasattr(fig, "data")
+
+
+def test_visualize_nominal_feature_classification_target(mixed_dataframe):
+    # Classification target: response_density["names"] are also categorical
+    # (class labels). The fix must handle that branch too.
+    y = np.array([0, 1, 0, 1, 0, 1, 0, 1])
+    explanation = Marginal(feature_types=["nominal", "continuous"]).explain_data(
+        mixed_dataframe, y
+    )
+    fig = explanation.visualize(0)
+    assert fig is not None
+
+
+def test_visualize_overall_unaffected(mixed_dataframe):
+    # The key=None path is independent of the bug; guard against
+    # accidental regression.
+    y = np.array([0.5, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5])
+    explanation = Marginal(feature_types=["nominal", "continuous"]).explain_data(
+        mixed_dataframe, y
+    )
+    fig = explanation.visualize(None)
+    assert fig is not None