Infra: Add tests for python 3.11/3.12, remove tests for python 3.7

.github/workflows/python-package.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.7, 3.8, 3.9, "3.10"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v2

.github/workflows/run-linters.yaml

@@ -24,7 +24,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v1
         with:
-          python-version: 3.7
+          python-version: 3.12
 
       - name: Install Python dependencies
         run: pip install flake8

dagshub/common/api/repo.py

@@ -167,7 +167,7 @@ def list_path(self, path: str, revision: Optional[str] = None, include_size: boo
             raise RuntimeError(error_msg)
 
         content = res.json()
-        if type(content) == dict:
+        if type(content) is dict:
             content = [content]
         return [dacite.from_dict(ContentAPIEntry, entry) for entry in content]
 

dagshub/data_engine/client/loaders/base.py

@@ -58,7 +58,7 @@ def __init__(
 
         self.tensorizers = (
             self._get_tensorizers(tensorizers)
-            if type(tensorizers) == str or type(tensorizers[0]) == str
+            if type(tensorizers) is str or type(tensorizers[0]) is str
             else tensorizers
         )
 
@@ -192,8 +192,8 @@ def _get_tensorizers(self, datatypes: Union[str, List[Union[str, FunctionType]]]
             return [
                 getattr(self.tensorlib, datatypes),
             ] * (len(self.metadata_columns) + 1)
-        elif type(datatypes) == list and len(datatypes) == len(self.metadata_columns) + 1:
-            return [getattr(self.tensorlib, datatype) if type(datatype) == str else datatype for datatype in datatypes]
+        elif type(datatypes) is list and len(datatypes) == len(self.metadata_columns) + 1:
+            return [getattr(self.tensorlib, datatype) if type(datatype) is str else datatype for datatype in datatypes]
         else:
             raise ValueError(
                 "Unable to set tensorizers. "

dagshub/data_engine/model/metadata_field_builder.py

@@ -105,7 +105,7 @@ def _get_backing_type(t: Union[Type, DagshubDataType]) -> MetadataFieldType:
         if issubclass(t, DagshubDataType):
             return t.backing_field_type
 
-        if type(t) == type:
+        if type(t) is type:
             if t not in metadataTypeLookup.keys():
                 raise ValueError(f"Primitive type {type(t)} is not supported")
             return metadataTypeLookup[t]

dagshub/data_engine/model/query_result.py

@@ -192,7 +192,7 @@ def as_ml_dataloader(self, flavor, **kwargs):
         def keypairs(keys):
             return {key: kwargs[key] for key in keys}
 
-        if type(flavor) != str:
+        if type(flavor) is not str:
             if flavor.type == "torch":
                 from dagshub.data_engine.client.loaders.torch import PyTorchDataLoader
 
@@ -205,7 +205,7 @@ def keypairs(keys):
         kwargs["for_dataloader"] = True
         dataset_kwargs = set(list(inspect.signature(DagsHubDataset).parameters.keys())[1:])
         global_kwargs = set(kwargs.keys())
-        flavor = flavor.lower() if type(flavor) == str else flavor
+        flavor = flavor.lower() if type(flavor) is str else flavor
         if flavor == "torch":
             from dagshub.data_engine.client.loaders.torch import PyTorchDataLoader
 

tests/data_engine/test_queryresult.py

@@ -17,7 +17,7 @@ def test_getitem_index(query_result):
 
 def test_getitem_slice_returns_query_result(query_result):
     qr = query_result[0:len(query_result):2]
-    assert type(qr) == QueryResult
+    assert type(qr) is QueryResult
     assert len(qr) == math.ceil(len(query_result) / 2)
     for i in range(len(qr)):
         assert qr[i].datapoint_id is query_result[i * 2].datapoint_id