Merge pull request #1271 from openml/pre-commit-ci-update-config

[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/psf/black
-    rev: 23.3.0
+    rev: 23.7.0
     hooks:
       - id: black
         args: [--line-length=100]
@@ -28,7 +28,7 @@ repos:
         args: [ --disallow-untyped-defs, --disallow-any-generics,
                 --disallow-any-explicit, --implicit-optional ]
   - repo: https://github.com/pycqa/flake8
-    rev: 6.0.0
+    rev: 6.1.0
     hooks:
       - id: flake8
         name: flake8 openml

openml/datasets/data_feature.py

@@ -18,6 +18,7 @@ class OpenMLDataFeature(object):
     nominal_values : list(str)
         list of the possible values, in case of nominal attribute
     number_missing_values : int
+        Number of rows that have a missing value for this feature.
     """
 
     LEGAL_DATA_TYPES = ["nominal", "numeric", "string", "date"]
@@ -30,8 +31,8 @@ def __init__(
         nominal_values: List[str],
         number_missing_values: int,
     ):
-        if type(index) != int:
-            raise ValueError("Index is of wrong datatype")
+        if not isinstance(index, int):
+            raise TypeError(f"Index must be `int` but is {type(index)}")
         if data_type not in self.LEGAL_DATA_TYPES:
             raise ValueError(
                 "data type should be in %s, found: %s" % (str(self.LEGAL_DATA_TYPES), data_type)
@@ -50,8 +51,9 @@ def __init__(
         else:
             if nominal_values is not None:
                 raise TypeError("Argument `nominal_values` must be None for non-nominal feature.")
-        if type(number_missing_values) != int:
-            raise ValueError("number_missing_values is of wrong datatype")
+        if not isinstance(number_missing_values, int):
+            msg = f"number_missing_values must be int but is {type(number_missing_values)}"
+            raise TypeError(msg)
 
         self.index = index
         self.name = str(name)

openml/datasets/functions.py

@@ -192,7 +192,9 @@ def __list_datasets(api_call, output_format="dict"):
     datasets_dict = xmltodict.parse(xml_string, force_list=("oml:dataset",))
 
     # Minimalistic check if the XML is useful
-    assert type(datasets_dict["oml:data"]["oml:dataset"]) == list, type(datasets_dict["oml:data"])
+    assert isinstance(datasets_dict["oml:data"]["oml:dataset"], list), type(
+        datasets_dict["oml:data"]
+    )
     assert datasets_dict["oml:data"]["@xmlns:oml"] == "http://openml.org/openml", datasets_dict[
         "oml:data"
     ]["@xmlns:oml"]

openml/evaluations/functions.py

@@ -197,7 +197,7 @@ def __list_evaluations(api_call, output_format="object"):
             "Error in return XML, does not contain " '"oml:evaluations": %s' % str(evals_dict)
         )
 
-    assert type(evals_dict["oml:evaluations"]["oml:evaluation"]) == list, type(
+    assert isinstance(evals_dict["oml:evaluations"]["oml:evaluation"], list), type(
         evals_dict["oml:evaluations"]
     )
 

openml/flows/functions.py

@@ -341,7 +341,7 @@ def __list_flows(api_call: str, output_format: str = "dict") -> Union[Dict, pd.D
     flows_dict = xmltodict.parse(xml_string, force_list=("oml:flow",))
 
     # Minimalistic check if the XML is useful
-    assert type(flows_dict["oml:flows"]["oml:flow"]) == list, type(flows_dict["oml:flows"])
+    assert isinstance(flows_dict["oml:flows"]["oml:flow"], list), type(flows_dict["oml:flows"])
     assert flows_dict["oml:flows"]["@xmlns:oml"] == "http://openml.org/openml", flows_dict[
         "oml:flows"
     ]["@xmlns:oml"]

openml/runs/functions.py

@@ -1139,7 +1139,7 @@ def __list_runs(api_call, output_format="dict"):
             '"http://openml.org/openml": %s' % str(runs_dict)
         )
 
-    assert type(runs_dict["oml:runs"]["oml:run"]) == list, type(runs_dict["oml:runs"])
+    assert isinstance(runs_dict["oml:runs"]["oml:run"], list), type(runs_dict["oml:runs"])
 
     runs = OrderedDict()
     for run_ in runs_dict["oml:runs"]["oml:run"]:

openml/setups/functions.py

@@ -220,7 +220,7 @@ def __list_setups(api_call, output_format="object"):
             '"%s": %s' % (openml_uri, str(setups_dict))
         )
 
-    assert type(setups_dict["oml:setups"]["oml:setup"]) == list, type(setups_dict["oml:setups"])
+    assert isinstance(setups_dict["oml:setups"]["oml:setup"], list), type(setups_dict["oml:setups"])
 
     setups = dict()
     for setup_ in setups_dict["oml:setups"]["oml:setup"]:

openml/study/functions.py

@@ -595,7 +595,7 @@ def __list_studies(api_call, output_format="object") -> Union[Dict, pd.DataFrame
     study_dict = xmltodict.parse(xml_string, force_list=("oml:study",))
 
     # Minimalistic check if the XML is useful
-    assert type(study_dict["oml:study_list"]["oml:study"]) == list, type(
+    assert isinstance(study_dict["oml:study_list"]["oml:study"], list), type(
         study_dict["oml:study_list"]
     )
     assert study_dict["oml:study_list"]["@xmlns:oml"] == "http://openml.org/openml", study_dict[

openml/tasks/functions.py

@@ -246,7 +246,7 @@ def __list_tasks(api_call, output_format="dict"):
             '"http://openml.org/openml": %s' % str(tasks_dict)
         )
 
-    assert type(tasks_dict["oml:tasks"]["oml:task"]) == list, type(tasks_dict["oml:tasks"])
+    assert isinstance(tasks_dict["oml:tasks"]["oml:task"], list), type(tasks_dict["oml:tasks"])
 
     tasks = dict()
     procs = _get_estimation_procedure_list()

openml/tasks/split.py

@@ -43,7 +43,7 @@ def __init__(self, name, description, split):
 
     def __eq__(self, other):
         if (
-            type(self) != type(other)
+            (not isinstance(self, type(other)))
             or self.name != other.name
             or self.description != other.description
             or self.split.keys() != other.split.keys()

tests/test_runs/test_run_functions.py

@@ -150,7 +150,7 @@ def _assert_predictions_equal(self, predictions, predictions_prime):
             for col_idx in compare_slice:
                 val_1 = predictions["data"][idx][col_idx]
                 val_2 = predictions_prime["data"][idx][col_idx]
-                if type(val_1) == float or type(val_2) == float:
+                if isinstance(val_1, float) or isinstance(val_2, float):
                     self.assertAlmostEqual(
                         float(val_1),
                         float(val_2),