FIX-#6427: make code compatible with flake8==6.1.0 (#6428)

Signed-off-by: Anatoly Myachev <[email protected]>

modin/core/dataframe/algebra/default2pandas/default.py

@@ -103,7 +103,7 @@ def register(cls, func, obj_type=None, inplace=None, fn_name=None):
         else:
             fn = func
 
-        if type(fn) == property:
+        if type(fn) is property:
             fn = cls.build_property_wrapper(fn)
 
         def applyier(df, *args, **kwargs):

modin/core/dataframe/algebra/default2pandas/resample.py

@@ -46,7 +46,7 @@ def fn(df, resample_kwargs, *args, **kwargs):
                 df = df.squeeze(axis=1)
             resampler = df.resample(**resample_kwargs)
 
-            if type(func) == property:
+            if type(func) is property:
                 return func.fget(resampler)
 
             return func(resampler, *args, **kwargs)

modin/core/dataframe/algebra/default2pandas/rolling.py

@@ -41,7 +41,7 @@ def fn(df, rolling_kwargs, *args, **kwargs):
             """Create rolling window for the passed frame and execute specified `func` on it."""
             roller = df.rolling(**rolling_kwargs)
 
-            if type(func) == property:
+            if type(func) is property:
                 return func.fget(roller)
 
             return func(roller, *args, **kwargs)
@@ -100,7 +100,7 @@ def fn(df, rolling_args, *args, **kwargs):
                 df = df.squeeze(axis=1)
             roller = df.expanding(*rolling_args)
 
-            if type(func) == property:
+            if type(func) is property:
                 return func.fget(roller)
 
             return func(roller, *args, **kwargs)

modin/core/dataframe/pandas/dataframe/dataframe.py

@@ -3852,7 +3852,7 @@ def from_dataframe(cls, df: "ProtocolDataframe") -> "PandasDataframe":
         PandasDataframe
             A new Core Modin Dataframe object.
         """
-        if type(df) == cls:
+        if type(df) is cls:
             return df
 
         if not hasattr(df, "__dataframe__"):

modin/core/dataframe/pandas/interchange/dataframe_protocol/column.py

@@ -364,7 +364,7 @@ def _get_data_buffer(
 
             # TODO: this for-loop is slow; can be implemented in Cython/C/C++ later
             for i in range(buf.size):
-                if type(buf[i]) == str:
+                if type(buf[i]) is str:
                     b.extend(buf[i].encode(encoding="utf-8"))
 
             # Convert the byte array to a pandas "buffer" using a NumPy array as the backing store
@@ -413,7 +413,7 @@ def _get_validity_buffer(self) -> Tuple[PandasProtocolBuffer, Any]:
             # Determine the encoding for valid values
             valid = 1 if invalid == 0 else 0
 
-            mask = [valid if type(buf[i]) == str else invalid for i in range(buf.size)]
+            mask = [valid if type(buf[i]) is str else invalid for i in range(buf.size)]
 
             # Convert the mask array to a Pandas "buffer" using a NumPy array as the backing store
             buffer = PandasProtocolBuffer(np.asarray(mask, dtype="uint8"))
@@ -459,7 +459,7 @@ def _get_offsets_buffer(self) -> Tuple[PandasProtocolBuffer, Any]:
             offsets = [ptr] + [None] * len(values)
             for i, v in enumerate(values):
                 # For missing values (in this case, `np.nan` values), we don't increment the pointer)
-                if type(v) == str:
+                if type(v) is str:
                     b = v.encode(encoding="utf-8")
                     ptr += len(b)
 

modin/experimental/core/execution/native/implementations/hdk_on_native/partitioning/partition_manager.py

@@ -175,7 +175,7 @@ def _get_unsupported_cols(cls, obj):
                 # The TypeError could be raised when converting a sparse data to
                 # arrow table - https://github.com/apache/arrow/pull/4497. If this
                 # is the case - fall back to pandas, otherwise - rethrow the error.
-                if type(err) == TypeError:
+                if type(err) is TypeError:
                     if any([isinstance(t, pandas.SparseDtype) for t in obj.dtypes]):
                         ErrorMessage.single_warning(
                             "Sparse data is not currently supported!"
@@ -187,7 +187,7 @@ def _get_unsupported_cols(cls, obj):
                 # We catch and handle this error here. If there are no duplicates
                 # (is_unique is True), then the error is caused by something different
                 # and we just rethrow it.
-                if (type(err) == ValueError) and obj.columns.is_unique:
+                if (type(err) is ValueError) and obj.columns.is_unique:
                     raise err
 
                 regex = r"Conversion failed for column ([^\W]*)"

modin/experimental/core/execution/native/implementations/hdk_on_native/test/test_dataframe.py

@@ -2726,7 +2726,7 @@ def test_dict(self):
         assert str(mdt) == str(pdt)
 
         # Make sure the lazy proxy dtype is not materialized yet.
-        assert type(mdt) != pandas.CategoricalDtype
+        assert type(mdt) is not pandas.CategoricalDtype
         assert mdt._parent is not None
         assert mdt._update_proxy(at, at.column(0)._name) is mdt
         assert mdt._update_proxy(at, at.column(2)._name) is not mdt

modin/experimental/core/io/text/csv_glob_dispatcher.py

@@ -399,7 +399,7 @@ def partitioned_file(
         -----
         The logic gets really complicated if we try to use the `TextFileDispatcher.partitioned_file`.
         """
-        if type(files) != list:
+        if type(files) is not list:
             files = [files]
 
         if num_partitions is None:

modin/numpy/test/test_array.py

@@ -338,5 +338,5 @@ def test__array__():
     modin_arr = np.array(numpy_arr)
     # this implicitly calls `__array__`
     converted_array = numpy.array(modin_arr)
-    assert type(converted_array) == type(numpy_arr)
+    assert type(converted_array) is type(numpy_arr)
     assert_scalar_or_array_equal(converted_array, numpy_arr)

modin/pandas/dataframe.py

@@ -762,7 +762,7 @@ def equals(self, other):  # noqa: PR01, RT01, D200
             other = self.__constructor__(other)
 
         if (
-            type(self) != type(other)
+            type(self) is not type(other)
             or not self.index.equals(other.index)
             or not self.columns.equals(other.columns)
         ):

modin/pandas/groupby.py

@@ -797,7 +797,7 @@ def aggregate(self, func=None, *args, engine=None, engine_kwargs=None, **kwargs)
 
             if relabeling_required:
 
-                def do_relabel(obj_to_relabel):
+                def do_relabel(obj_to_relabel):  # noqa: F811
                     new_order, new_columns_idx = order, pandas.Index(new_columns)
                     if not self._as_index:
                         nby_cols = len(obj_to_relabel.columns) - len(new_columns_idx)

modin/pandas/series.py

@@ -933,7 +933,7 @@ def equals(self, other):  # noqa: PR01, RT01, D200
             # Copy into a Modin Series to simplify logic below
             other = self.__constructor__(other)
 
-        if type(self) != type(other) or not self.index.equals(other.index):
+        if type(self) is not type(other) or not self.index.equals(other.index):
             return False
 
         old_name_self = self.name

modin/pandas/test/test_groupby.py

@@ -2276,7 +2276,7 @@ def test_validate_by():
     """Test ``modin.core.dataframe.algebra.default2pandas.groupby.GroupBy.validate_by``."""
 
     def compare(obj1, obj2):
-        assert type(obj1) == type(
+        assert type(obj1) is type(
             obj2
         ), f"Both objects must be instances of the same type: {type(obj1)} != {type(obj2)}."
         if isinstance(obj1, list):

modin/pandas/test/test_series.py

@@ -237,7 +237,7 @@ def test_to_list(data):
     modin_series, pandas_series = create_test_series(data)
     pd_res = pandas_series.to_list()
     md_res = modin_series.to_list()
-    assert type(pd_res) == type(md_res)
+    assert type(pd_res) is type(md_res)
     assert np.array_equal(pd_res, md_res, equal_nan=True)
 
 

modin/pandas/test/utils.py

@@ -582,7 +582,7 @@ def assert_empty_frame_equal(df1, df2):
 
     if (df1.empty and not df2.empty) or (df2.empty and not df1.empty):
         assert False, "One of the passed frames is empty, when other isn't"
-    elif df1.empty and df2.empty and type(df1) != type(df2):
+    elif df1.empty and df2.empty and type(df1) is not type(df2):
         assert False, f"Empty frames have different types: {type(df1)} != {type(df2)}"