Adding a special case to _common so that Data Ops get a more informative message (#1607)

Author: rcap107

CHANGES.rst

@@ -21,6 +21,9 @@ Changes
   removed in the next release of skrub.
   :pr:`1546` by :user:`Vincent Maladiere <Vincent-Maladiere>`.
 
+- Improved error messages when a DataOp is being sent to dispatched functions.
+  :pr:`1607` by :user:`Riccardo Cappuzzo<rcap107>`.
+
 Bugfixes
 --------
 

skrub/_dataframe/_common.py

@@ -119,6 +119,18 @@
 
 
 def _raise(obj, kind="object"):
+    from .._data_ops._data_ops import DataOp
+
+    if isinstance(obj, DataOp):
+        raise TypeError(
+            """Expected a Pandas or Polars DataFrame, but got a skrub DataOp.
+A function that expects an actual value cannot be applied directly to a DataOp;
+you may want to (i) use op.skb.eval() or op.skb.preview() to evaluate the
+dataop and turn it into an actual value or (ii) use op.skb.apply_func() or
+op.skb.apply() to schedule the operation for later execution (when the dataop is
+evaluated) rather than computing it immediately.
+ """
+        )
     raise TypeError(
         "Operation not supported on this object. Expecting a Pandas or Polars "
         f"{kind}, but got an object of type {type(obj)}."

skrub/_dataframe/tests/test_common.py

@@ -15,6 +15,7 @@
 from numpy.testing import assert_array_equal
 from pandas.testing import assert_frame_equal as pd_assert_frame_equal
 
+import skrub
 from skrub import selectors as s
 from skrub._dataframe import _common as ns
 
@@ -40,6 +41,12 @@ def test_not_implemented():
         params = [None] * n_params
         with pytest.raises(TypeError):
             func(*params)
+        dop = [skrub.var("a")] * n_params
+        with pytest.raises(
+            TypeError,
+            match=r"Expected a Pandas or Polars DataFrame, but got a skrub DataOp",
+        ):
+            func(*dop)
 
 
 #