Refactoring test_no_variance_data_checks to reuse some of the mesages.

alteryx · Jun 29, 2020 · b5a75bd · b5a75bd
1 parent 7f21f71
commit b5a75bd
Showing 1 changed file with 11 additions and 9 deletions.
diff --git a/evalml/tests/data_checks_tests/test_no_variance_data_check.py b/evalml/tests/data_checks_tests/test_no_variance_data_check.py
@@ -19,24 +19,26 @@
 all_null_y = pd.Series([None] * 4)
 two_distinct_with_nulls_y = pd.Series(([1] * 2) + ([None] * 2))
 
+feature_0_unique = DataCheckError("Column feature has 0 unique value.", "NoVarianceDataCheck")
+feature_1_unique = DataCheckError("Column feature has 1 unique value.", "NoVarianceDataCheck")
+labels_0_unique = DataCheckError("The Labels have 0 unique value.", "NoVarianceDataCheck")
+labels_1_unique = DataCheckError("The Labels have 1 unique value.", "NoVarianceDataCheck")
+
 cases = [(all_distinct_X, all_distinct_y, True, []),
          ([1, 2, 3, 4], [1, 2, 3, 2], False, []),
          (np.arange(12).reshape(4, 3), [1, 2, 3], True, []),
-         (all_null_X, all_distinct_y, False, [DataCheckError("Column feature has 0 unique value.", "NoVarianceDataCheck")]),
-         (all_null_X, [1] * 4, False, [DataCheckError("Column feature has 0 unique value.", "NoVarianceDataCheck"),
-                                       DataCheckError("The Labels have 1 unique value.", "NoVarianceDataCheck")]),
-         (all_null_X, all_distinct_y, True, [DataCheckError("Column feature has 1 unique value.", "NoVarianceDataCheck")]),
-         (all_distinct_X, all_null_y, True, [DataCheckError("The Labels have 1 unique value.", "NoVarianceDataCheck")]),
-         (all_distinct_X, all_null_y, False, [DataCheckError("The Labels have 0 unique value.", "NoVarianceDataCheck")]),
+         (all_null_X, all_distinct_y, False, [feature_0_unique]),
+         (all_null_X, [1] * 4, False, [feature_0_unique, labels_1_unique]),
+         (all_null_X, all_distinct_y, True, [feature_1_unique]),
+         (all_distinct_X, all_null_y, True, [labels_1_unique]),
+         (all_distinct_X, all_null_y, False, [labels_0_unique]),
          (two_distinct_with_nulls_X, two_distinct_with_nulls_y, True,
           [DataCheckWarning("Column feature has two unique values including nulls. Consider encoding the nulls for "
                             "this column to be useful for machine learning.", "NoVarianceDataCheck"),
            DataCheckWarning("The Labels have two unique values including nulls. Consider encoding the nulls for "
                             "this column to be useful for machine learning.", "NoVarianceDataCheck")
            ]),
-         (two_distinct_with_nulls_X, two_distinct_with_nulls_y, False,
-          [DataCheckError("Column feature has 1 unique value.", "NoVarianceDataCheck"),
-           DataCheckError("The Labels have 1 unique value.", "NoVarianceDataCheck")])
+         (two_distinct_with_nulls_X, two_distinct_with_nulls_y, False, [feature_1_unique, labels_1_unique])
          ]