Update InvalidTargetDataCheck to validate time series regression problems

docs/source/release_notes.rst

@@ -13,6 +13,7 @@
         * Removed empty cell in text_input.ipynb :pr:`3234`
         * Removed potential prediction explanations failure when pipelines predicted a class with probability 1 :pr:`3221`
         * Dropped NaNs before partial dependence grid generation :pr:`3235`
+        * Fixed bug where ``InvalidTargetDataCheck`` would not check time series regression targets :pr:`3251`
     * Changes
         * Raised lowest compatible numpy version to 1.21.0 to address security concerns :pr:`3207`
         * Changed the default objective to ``MedianAE`` from ``R2`` for time series regression :pr:`3205`

evalml/data_checks/invalid_target_data_check.py

@@ -11,7 +11,6 @@
 )
 from evalml.objectives import get_objective
 from evalml.problem_types import (
-    ProblemTypes,
     handle_problem_types,
     is_binary,
     is_multiclass,
@@ -329,10 +328,7 @@ def _check_for_non_positive_target(self, y, results):
         return results
 
     def _check_regression_target(self, y, results):
-        if (
-            self.problem_type == ProblemTypes.REGRESSION
-            and "numeric" not in y.ww.semantic_tags
-        ):
+        if is_regression(self.problem_type) and "numeric" not in y.ww.semantic_tags:
             DataCheck._add_message(
                 DataCheckError(
                     message="Target data type should be numeric for regression type problems.",

evalml/tests/data_checks_tests/test_data_checks.py

@@ -712,6 +712,24 @@ def test_errors_warnings_in_invalid_target_data_check(objective, ts_data):
                 "errors": [data_check_error],
                 "actions": [],
             }
+    y = ww.init_series(y, logical_type="Categorical")
+    default_data_check = DefaultDataChecks(
+        problem_type="time series regression",
+        objective=objective,
+        problem_configuration=problem_config,
+    ).data_checks
+    data_check_error_type = DataCheckError(
+        message=f"Target data type should be numeric for regression type problems.",
+        data_check_name="InvalidTargetDataCheck",
+        message_code=DataCheckMessageCode.TARGET_UNSUPPORTED_TYPE,
+    ).to_dict()
+    for check in default_data_check:
+        if check.name == "InvalidTargetDataCheck":
+            assert check.validate(X, y) == {
+                "warnings": [],
+                "errors": [data_check_error_type],
+                "actions": [],
+            }
 
 
 def test_data_checks_do_not_duplicate_actions(X_y_binary):

evalml/tests/data_checks_tests/test_invalid_target_data_check.py

@@ -493,7 +493,10 @@ def test_invalid_target_data_check_initialize_with_none_objective():
         )
 
 
-def test_invalid_target_data_check_regression_problem_nonnumeric_data():
+@pytest.mark.parametrize(
+    "problem_type", [ProblemTypes.TIME_SERIES_REGRESSION, ProblemTypes.REGRESSION]
+)
+def test_invalid_target_data_check_regression_problem_nonnumeric_data(problem_type):
     y_categorical = pd.Series(["Peace", "Is", "A", "Lie"] * 100)
     y_mixed_cat_numeric = pd.Series(["Peace", 2, "A", 4] * 100)
     y_integer = pd.Series([1, 2, 3, 4])
@@ -508,7 +511,7 @@ def test_invalid_target_data_check_regression_problem_nonnumeric_data():
     ).to_dict()
 
     invalid_targets_check = InvalidTargetDataCheck(
-        "regression", get_default_primary_search_objective("regression")
+        problem_type, get_default_primary_search_objective(problem_type)
     )
     assert invalid_targets_check.validate(
         X=pd.DataFrame({"col": range(len(y_categorical))}), y=y_categorical
@@ -527,7 +530,10 @@ def test_invalid_target_data_check_regression_problem_nonnumeric_data():
     ) == {"warnings": [], "errors": [], "actions": []}
 
 
-def test_invalid_target_data_check_multiclass_problem_binary_data():
+@pytest.mark.parametrize(
+    "problem_type", [ProblemTypes.MULTICLASS, ProblemTypes.TIME_SERIES_MULTICLASS]
+)
+def test_invalid_target_data_check_multiclass_problem_binary_data(problem_type):
     y_multiclass = pd.Series([1, 2, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3] * 25)
     y_binary = pd.Series([0, 1, 1, 1, 0, 0] * 25)
 
@@ -702,11 +708,16 @@ def test_invalid_target_data_check_different_lengths():
     }
 
 
-def test_invalid_target_data_check_numeric_binary_does_not_return_warnings():
+@pytest.mark.parametrize(
+    "problem_type", [ProblemTypes.BINARY, ProblemTypes.TIME_SERIES_BINARY]
+)
+def test_invalid_target_data_check_numeric_binary_does_not_return_warnings(
+    problem_type,
+):
     y = pd.Series([1, 5, 1, 5, 1, 1])
     X = pd.DataFrame({"col": range(len(y))})
     invalid_targets_check = InvalidTargetDataCheck(
-        "binary", get_default_primary_search_objective("binary")
+        problem_type, get_default_primary_search_objective(problem_type)
     )
     assert invalid_targets_check.validate(X, y) == {
         "warnings": [],