Preserve string and integer class labels in ClassHistogram

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

@@ -338,10 +338,24 @@ def explain_data(self, X, y, name=None):
             msg = f"y must be 1 dimensional, but got {y.ndim} dimensions with shape {y.shape}"
             raise ValueError(msg)
 
-        try:
-            y = y.astype(np.float64, copy=False)
-        except Exception:  # object can throw anything in their __float__ function
+        if issubclass(y.dtype.type, np.integer) or (
+            y.dtype.type is np.object_
+            and all(isinstance(value, (int, np.integer)) for value in y)
+        ):
+            # Preserve integer precision and unsigned range, including list/object inputs.
+            y = np.asarray(y)
+        elif issubclass(y.dtype.type, (str, bytes)) or (
+            y.dtype.type is np.object_
+            and any(isinstance(value, (str, bytes)) for value in y)
+        ):
+            # Numeric-looking strings are class names, not numeric values.
             y = typify_classification(y)
+        else:
+            # Retain numeric float equality (including signed zero) and ordering.
+            try:
+                y = y.astype(np.float64, copy=False)
+            except Exception:  # object can throw anything in their __float__ function
+                y = typify_classification(y)
 
         X, n_samples = preclean_X(X, self.feature_names, self.feature_types, len(y))
 

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

@@ -0,0 +1,164 @@
+# Copyright (c) 2026 The InterpretML Contributors
+# Distributed under the MIT software license
+
+import numpy as np
+import pandas as pd
+import pytest
+from interpret.data import ClassHistogram
+
+
+@pytest.mark.parametrize(
+    "labels",
+    [
+        pytest.param(["01", "1", "01", "1"], id="leading-zero-strings"),
+        pytest.param(["1", "1.0", "1", "1.0"], id="decimal-strings"),
+        pytest.param([2**53, 2**53 + 1, 2**53, 2**53 + 1], id="large-integers"),
+        pytest.param(["cat", "dog", "cat", "dog"], id="text-control"),
+        pytest.param([0, 1, 0, 1], id="integer-control"),
+        pytest.param([False, True, False, True], id="boolean-control"),
+    ],
+)
+@pytest.mark.parametrize("container", [np.array, list, pd.Series])
+def test_class_histogram_preserves_labels(labels, container):
+    X = np.arange(len(labels), dtype=float).reshape(-1, 1)
+    y = container(labels)
+    explanation = ClassHistogram().explain_data(X, y)
+
+    assert explanation.data()["y"].tolist() == labels
+    assert explanation.data(0)["y"].tolist() == labels
+    assert np.unique(explanation.data()["y"]).size == len(set(labels))
+
+
+@pytest.mark.parametrize(
+    "labels",
+    [
+        pytest.param(["01", "1", "01", "1"], id="leading-zero-strings"),
+        pytest.param([2**53, 2**53 + 1, 2**53, 2**53 + 1], id="large-integers"),
+        pytest.param(["cat", "dog", "cat", "dog"], id="text-control"),
+        pytest.param([0.0, 1.0, 0.0, 1.0], id="float-control"),
+    ],
+)
+def test_class_histogram_keeps_class_counts(labels):
+    X = np.array([["a"], ["b"], ["a"], ["b"]])
+    explanation = ClassHistogram(feature_types=["nominal"]).explain_data(X, labels)
+
+    overall = explanation.visualize()
+    assert len(overall.data) == 2
+    assert [trace.y[0] for trace in overall.data] == [2, 2]
+
+    feature = explanation.visualize(0)
+    assert len(feature.data) == 2
+    assert [trace.name for trace in feature.data] == sorted({str(y) for y in labels})
+    assert all(sum(trace.y) == 2 for trace in feature.data)
+
+
+@pytest.mark.parametrize(
+    "factory",
+    [np.array, list, pd.Series, lambda y: np.array(y, dtype=object)],
+)
+def test_exact_unsigned_values_remain_positive(factory):
+    labels = [2**63, 2**63 + 4096, 2**63, 2**63, 2**63 + 4096]
+    X = np.array([["a"], ["b"], ["c"], ["b"], ["a"]])
+    exp = ClassHistogram(feature_types=["nominal"]).explain_data(X, factory(labels))
+    for key in (None, 0):
+        assert [int(v) for v in exp.data(key)["y"]] == labels
+    fig = exp.visualize()
+    assert [int(t.x[0]) for t in fig.data] == [2**63, 2**63 + 4096]
+    assert [int(t.y[0]) for t in fig.data] == [3, 2]
+
+
+@pytest.mark.parametrize(
+    "factory",
+    [np.array, list, pd.Series, lambda y: np.array(y, dtype=object)],
+)
+def test_equal_float_zeros_remain_one_class(factory):
+    labels = [0.0, -0.0, 0.0, -0.0, 0.0]
+    X = np.array([["a"], ["b"], ["c"], ["b"], ["a"]])
+    exp = ClassHistogram(feature_types=["nominal"]).explain_data(X, factory(labels))
+    assert np.unique(exp.data()["y"]).size == 1
+    assert len(exp.visualize().data) == 1
+    assert exp.visualize().data[0].y == (5,)
+    assert len(exp.visualize(0).data) == 1
+
+
+def test_numeric_float_data_remains_numeric():
+    labels = np.array([2.5, 10.5, 2.5, 2.5, 10.5])
+    X = np.array([["a"], ["b"], ["c"], ["b"], ["a"]])
+    exp = ClassHistogram(feature_types=["nominal"]).explain_data(X, labels)
+    assert exp.data()["y"].dtype.kind == "f"
+    np.testing.assert_array_equal(exp.data()["y"], labels)
+
+
+def test_numeric_float_plot_order_remains_numeric():
+    X = np.array([["a"], ["b"], ["c"], ["b"], ["a"]])
+    exp = ClassHistogram(feature_types=["nominal"]).explain_data(
+        X, np.array([2.5, 10.5, 2.5, 2.5, 10.5])
+    )
+    assert [float(t.x[0]) for t in exp.visualize().data] == [2.5, 10.5]
+    assert [t.name for t in exp.visualize(0).data] == ["2.5", "10.5"]
+
+
+@pytest.mark.parametrize(
+    "container",
+    [
+        np.array,
+        list,
+        pd.Series,
+        lambda y: np.array(y, dtype=object),
+        lambda y: pd.Series(y, dtype="UInt64"),
+    ],
+)
+@pytest.mark.parametrize(
+    "labels",
+    [
+        [2**63, 2**63 + 4096, 2**63, 2**63, 2**63 + 4096],
+        [2**64 - 2, 2**64 - 1, 2**64 - 2, 2**64 - 2, 2**64 - 1],
+    ],
+    ids=["exact-unsigned-control", "uint64-maximum"],
+)
+def test_unsigned_class_counts_and_feature_labels(labels, container):
+    X = np.array([["a", 0], ["b", 1], ["c", 2], ["b", 3], ["a", 4]], dtype=object)
+    y = container(labels)
+    before = repr(y)
+    exp = ClassHistogram(feature_types=["nominal", "continuous"]).explain_data(X, y)
+    for key in (None, 0, 1):
+        assert [int(v) for v in exp.data(key)["y"]] == labels
+    assert [int(t.x[0]) for t in exp.visualize().data] == sorted(set(labels))
+    assert [int(t.y[0]) for t in exp.visualize().data] == [3, 2]
+    for key in (0, 1):
+        fig = exp.visualize(key)
+        assert [float(t.name) for t in fig.data] == [
+            float(v) for v in sorted(set(labels))
+        ]
+        assert [sum(t.y) for t in fig.data] == [3, 2]
+        assert isinstance(fig.to_json(), str)
+    assert repr(y) == before
+
+
+@pytest.mark.parametrize(
+    ("labels", "classes", "counts"),
+    [
+        ([0.0, -0.0, 0.0, -0.0, 0.0], [0.0], [5]),
+        ([2.5, 10.5, 2.5, 2.5, 10.5], [2.5, 10.5], [3, 2]),
+        ([1, 1.0, 2, 2.0, 1], [1.0, 2.0], [3, 2]),
+    ],
+    ids=["signed-zero", "numeric-order", "mixed-integer-float"],
+)
+@pytest.mark.parametrize(
+    "container", [np.array, list, pd.Series, lambda y: np.array(y, dtype=object)]
+)
+def test_numeric_float_feature_semantics(labels, classes, counts, container):
+    X = np.array([["a", 0], ["b", 1], ["c", 2], ["b", 3], ["a", 4]], dtype=object)
+    exp = ClassHistogram(feature_types=["nominal", "continuous"]).explain_data(
+        X, container(labels)
+    )
+    for key in (None, 0, 1):
+        assert exp.data(key)["y"].dtype.kind == "f"
+        np.testing.assert_array_equal(exp.data(key)["y"], labels)
+        fig = exp.visualize(key)
+        assert [sum(t.y) for t in fig.data] == counts
+        if key is None:
+            assert [t.x[0] for t in fig.data] == classes
+        else:
+            assert [t.name for t in fig.data] == [str(v) for v in classes]
+        assert isinstance(fig.to_json(), str)