Raise informative error when including target in X (#962)

* add error when target is in X_df

* add test

* rename test

* format

pymc_marketing/model_builder.py

@@ -548,6 +548,10 @@ def fit(
         self._generate_and_preprocess_model_data(X, y_df.values.flatten())
         if self.X is None or self.y is None:
             raise ValueError("X and y must be set before calling build_model!")
+        if self.output_var in X.columns:
+            raise ValueError(
+                f"X includes a column named '{self.output_var}', which conflicts with the target variable."
+            )
 
         if not hasattr(self, "model"):
             self.build_model(self.X, self.y)

tests/test_model_builder.py

@@ -256,6 +256,14 @@ def test_fit_no_t(toy_X):
     assert "posterior" in model_builder.idata.groups()
 
 
+@pytest.mark.xfail
+def test_fit_dup_Y(toy_X):
+    # create redundant target column in X
+    toy_X = pd.concat((toy_X, toy_y), axis=1)
+    model_builder = ModelBuilderTest()
+    model_builder.fit(X=toy_X, chains=1, draws=100, tune=100)
+
+
 @pytest.mark.skipif(
     sys.platform == "win32",
     reason="Permissions for temp files not granted on windows CI.",