ENH: Add default losses to KerasClassifier and KerasRegressor

scikeras/wrappers.py

@@ -1142,12 +1142,18 @@ class KerasClassifier(BaseWrapper):
         an instance of tf.keras.optimizers.Optimizer
         or a class inheriting from tf.keras.optimizers.Optimizer.
         Only strings and classes support parameter routing.
-    loss : Union[Union[str, tf.keras.losses.Loss, Type[tf.keras.losses.Loss], Callable], None], default None
+    loss : Union[Union[str, tf.keras.losses.Loss, Type[tf.keras.losses.Loss], Callable], None], default "categorical_crossentropy"
         The loss function to use for training.
         This can be a string for Keras' built in losses,
         an instance of tf.keras.losses.Loss
         or a class inheriting from tf.keras.losses.Loss .
         Only strings and classes support parameter routing.
+
+        For convience, the loss defaults to
+        `"categorical_crossentropy"`. This assumes that the model has
+        ``N`` outputs if the dataset has ``N`` classes. It assumes that
+        the input
+
     random_state : Union[int, np.random.RandomState, None], default None
         Set the Tensorflow random number generators to a
         reproducible deterministic state using this seed.
@@ -1257,7 +1263,7 @@ def __init__(
         ] = "rmsprop",
         loss: Union[
             Union[str, tf.keras.losses.Loss, Type[tf.keras.losses.Loss], Callable], None
-        ] = None,
+        ] = "categorical_crossentropy",
         metrics: Union[
             List[
                 Union[
@@ -1310,6 +1316,24 @@ def _type_of_target(self, y: np.ndarray) -> str:
             target_type = type_of_target(self.classes_)
         return target_type
 
+    def _fit_keras_model(self, *args, **kwargs):
+        try:
+            super()._fit_keras_model(*args, **kwargs)
+        except ValueError as e:
+            if (
+                self.loss == "categorical_crossentropy"
+                and hasattr(self, "model_")
+                and 1 in {o.shape[1] for o in getattr(self.model_, "outputs", [])}
+            ):
+                raise ValueError(
+                    "The model is configured to have one output, but the "
+                    f"loss='{self.loss}' is expecting multiple outputs "
+                    "(which is often used with one-hot encoded targets). "
+                    "More detail on Keras losses: https://keras.io/api/losses/"
+                ) from e
+            else:
+                raise e
+
     @staticmethod
     def scorer(y_true, y_pred, **kwargs) -> float:
         """Scoring function for KerasClassifier.

tests/test_simple_usage.py

@@ -0,0 +1,67 @@
+import numpy as np
+import pytest
+import tensorflow as tf
+
+from sklearn.datasets import make_classification
+
+from scikeras.wrappers import KerasClassifier
+
+
+N_CLASSES = 4
+FEATURES = 8
+n_eg = 100
+X = np.random.uniform(size=(n_eg, FEATURES)).astype("float32")
+y = np.random.choice(N_CLASSES, size=n_eg).astype(int)
+
+
+def clf(single_output=False):
+    model = tf.keras.Sequential()
+    model.add(tf.keras.layers.Input(shape=(FEATURES,)))
+    model.add(tf.keras.layers.Dense(FEATURES))
+
+    if single_output:
+        model.add(tf.keras.layers.Dense(1))
+    else:
+        model.add(tf.keras.layers.Dense(N_CLASSES))
+
+    return model
+
+
+def test_classifier_only_model_specified():
+    """
+    This tests uses cases where KerasClassifier works with the default loss.
+    It works for the following cases:
+
+    * binary classification
+    * one hot classification
+    * single class classification
+
+    """
+    est = KerasClassifier(model=clf)
+    est.partial_fit(X, y=y)
+    assert est.current_epoch == 1
+
+    for y2 in [
+        np.random.choice(2, size=len(X)).astype(int),
+        (np.random.choice(2, size=len(X)).astype(int) * 2 - 1),
+        np.ones(len(X)).astype(int),
+        np.zeros(len(X)).astype(int),
+    ]:
+        est = KerasClassifier(model=clf, model__single_output=True)
+        est.partial_fit(X, y=y2)
+        assert est.current_epoch == 1
+
+
+def test_classifier_raises_for_single_output_with_multiple_classes():
+    """
+    KerasClassifier does not work with one output and multiple classes
+    in the target (duh).
+    """
+    est = KerasClassifier(model=clf, model__single_output=True)
+    msg = (
+        "The model is configured to have one output, but the "
+        "loss='categorical_crossentropy' is expecting multiple outputs "
+    )
+    with pytest.raises(ValueError, match=msg):
+        est.partial_fit(X, y)
+    assert est.current_epoch == 0