Fixed flow_functions and dataset factorize bugs

Author: satvshr

tests/test_datasets/test_dataset.py

@@ -105,18 +105,18 @@ def test_get_data_pandas(self):
         col_dtype = {
             "pclass": "uint8",
             "survived": "category",
-            "name": "object",
+            "name": "str",
             "sex": "category",
             "age": "float64",
             "sibsp": "uint8",
             "parch": "uint8",
-            "ticket": "object",
+            "ticket": "str",
             "fare": "float64",
-            "cabin": "object",
+            "cabin": "str",
             "embarked": "category",
-            "boat": "object",
+            "boat": "str",
             "body": "float64",
-            "home.dest": "object",
+            "home.dest": "str",
         }
         for col_name in data.columns:
             assert data[col_name].dtype.name == col_dtype[col_name]

tests/test_flows/test_flow_functions.py

@@ -41,8 +41,9 @@ def _check_flow(self, flow):
         assert isinstance(flow["full_name"], str)
         assert isinstance(flow["version"], str)
         # There are some runs on openml.org that can have an empty external version
+        ext_version = flow["external_version"]
         ext_version_str_or_none = (
-            isinstance(flow["external_version"], str) or flow["external_version"] is None
+            isinstance(ext_version, str) or ext_version is None or pd.isna(ext_version)
         )
         assert ext_version_str_or_none