STYLE upgrade black formatter

.pre-commit-config.yaml

@@ -125,7 +125,7 @@ repos:
         language: python
         require_serial: true
         types_or: [python, pyi]
-        additional_dependencies: [black==22.10.0]
+        additional_dependencies: [black==23.1.0]
     -   id: pyright
         # note: assumes python env is setup and activated
         name: pyright

asv_bench/benchmarks/algorithms.py

@@ -15,7 +15,6 @@
 
 
 class Factorize:
-
     params = [
         [True, False],
         [True, False],
@@ -65,7 +64,6 @@ def time_factorize(self, unique, sort, dtype):
 
 
 class Duplicated:
-
     params = [
         [True, False],
         ["first", "last", False],
@@ -96,7 +94,6 @@ def time_duplicated(self, unique, keep, dtype):
 
 
 class DuplicatedMaskedArray:
-
     params = [
         [True, False],
         ["first", "last", False],

asv_bench/benchmarks/algos/isin.py

@@ -12,7 +12,6 @@
 
 
 class IsIn:
-
     params = [
         "int64",
         "uint64",
@@ -183,7 +182,6 @@ def time_isin(self, dtype, M, offset_factor):
 
 
 class IsInFloat64:
-
     params = [
         [np.float64, "Float64"],
         ["many_different_values", "few_different_values", "only_nans_values"],

asv_bench/benchmarks/arithmetic.py

@@ -173,7 +173,6 @@ def time_op_same_blocks(self, op, shape):
 
 
 class Ops:
-
     params = [[True, False], ["default", 1]]
     param_names = ["use_numexpr", "threads"]
 
@@ -257,7 +256,6 @@ def time_frame_series_dot(self):
 
 
 class Timeseries:
-
     params = [None, "US/Eastern"]
     param_names = ["tz"]
 
@@ -316,7 +314,6 @@ def time_categorical_op(self, op):
 
 
 class IndexArithmetic:
-
     params = ["float", "int"]
     param_names = ["dtype"]
 
@@ -387,7 +384,6 @@ def time_add_timedeltas(self, df):
 
 
 class AddOverflowScalar:
-
     params = [1, -1, 0]
     param_names = ["scalar"]
 
@@ -455,7 +451,6 @@ def time_add_overflow_both_arg_nan(self):
 
 
 class OffsetArrayArithmetic:
-
     params = offsets
     param_names = ["offset"]
 

asv_bench/benchmarks/array.py

@@ -72,7 +72,6 @@ def time_from_list(self):
 
 
 class ArrowStringArray:
-
     params = [False, True]
     param_names = ["multiple_chunks"]
 
@@ -107,7 +106,6 @@ def time_tolist(self, multiple_chunks):
 
 
 class ArrowExtensionArray:
-
     params = [
         [
             "boolean[pyarrow]",

asv_bench/benchmarks/attrs_caching.py

@@ -22,7 +22,6 @@ def time_set_index(self):
 
 
 class SeriesArrayAttribute:
-
     params = [["numeric", "object", "category", "datetime64", "datetime64tz"]]
     param_names = ["dtype"]
 

asv_bench/benchmarks/categoricals.py

@@ -143,7 +143,6 @@ def time_concat_non_overlapping_index(self):
 
 
 class ValueCounts:
-
     params = [True, False]
     param_names = ["dropna"]
 
@@ -254,7 +253,6 @@ def time_categorical_contains(self):
 
 
 class CategoricalSlicing:
-
     params = ["monotonic_incr", "monotonic_decr", "non_monotonic"]
     param_names = ["index"]
 

asv_bench/benchmarks/ctors.py

@@ -49,7 +49,6 @@ def list_of_lists_with_none(arr):
 
 
 class SeriesConstructors:
-
     param_names = ["data_fmt", "with_index", "dtype"]
     params = [
         [
@@ -124,7 +123,6 @@ def time_multiindex_from_iterables(self):
 
 class DatetimeIndexConstructor:
     def setup(self):
-
         N = 20_000
         dti = date_range("1900-01-01", periods=N)
 

asv_bench/benchmarks/dtypes.py

@@ -49,7 +49,6 @@ def time_pandas_dtype_invalid(self, dtype):
 
 
 class SelectDtypes:
-
     try:
         params = [
             tm.ALL_INT_NUMPY_DTYPES

asv_bench/benchmarks/eval.py

@@ -9,7 +9,6 @@
 
 
 class Eval:
-
     params = [["numexpr", "python"], [1, "all"]]
     param_names = ["engine", "threads"]
 

asv_bench/benchmarks/frame_ctor.py

@@ -74,7 +74,6 @@ def time_mi_series(self):
 
 
 class FromDictwithTimestamp:
-
     params = [Nano(1), Hour(1)]
     param_names = ["offset"]
 
@@ -89,7 +88,6 @@ def time_dict_with_timestamp_offsets(self, offset):
 
 
 class FromRecords:
-
     params = [None, 1000]
     param_names = ["nrows"]
 
@@ -116,7 +114,6 @@ def time_frame_from_ndarray(self):
 
 
 class FromLists:
-
     goal_time = 0.2
 
     def setup(self):
@@ -129,7 +126,6 @@ def time_frame_from_lists(self):
 
 
 class FromRange:
-
     goal_time = 0.2
 
     def setup(self):
@@ -162,7 +158,6 @@ def time_frame_from_scalar_ea_float64_na(self):
 
 
 class FromArrays:
-
     goal_time = 0.2
 
     def setup(self):

asv_bench/benchmarks/frame_methods.py

@@ -371,7 +371,6 @@ def time_isnull_obj(self):
 
 
 class Fillna:
-
     params = (
         [True, False],
         ["pad", "bfill"],
@@ -412,7 +411,6 @@ def time_frame_fillna(self, inplace, method, dtype):
 
 
 class Dropna:
-
     params = (["all", "any"], [0, 1])
     param_names = ["how", "axis"]
 
@@ -432,7 +430,6 @@ def time_dropna_axis_mixed_dtypes(self, how, axis):
 
 
 class Count:
-
     params = [0, 1]
     param_names = ["axis"]
 
@@ -531,7 +528,6 @@ def time_frame_object_unequal(self):
 
 
 class Interpolate:
-
     params = [None, "infer"]
     param_names = ["downcast"]
 
@@ -616,7 +612,6 @@ def time_frame_duplicated_subset(self):
 
 
 class XS:
-
     params = [0, 1]
     param_names = ["axis"]
 
@@ -629,7 +624,6 @@ def time_frame_xs(self, axis):
 
 
 class SortValues:
-
     params = [True, False]
     param_names = ["ascending"]
 
@@ -657,7 +651,6 @@ def time_frame_sort_values_by_columns(self):
 
 
 class Quantile:
-
     params = [0, 1]
     param_names = ["axis"]
 
@@ -697,7 +690,6 @@ def time_info(self):
 
 
 class NSort:
-
     params = ["first", "last", "all"]
     param_names = ["keep"]
 

asv_bench/benchmarks/gil.py

@@ -87,12 +87,10 @@ def inner(*args, **kwargs):
 
 
 class ParallelGroupbyMethods:
-
     params = ([2, 4, 8], ["count", "last", "max", "mean", "min", "prod", "sum", "var"])
     param_names = ["threads", "method"]
 
     def setup(self, threads, method):
-
         N = 10**6
         ngroups = 10**3
         df = DataFrame(
@@ -119,12 +117,10 @@ def time_loop(self, threads, method):
 
 
 class ParallelGroups:
-
     params = [2, 4, 8]
     param_names = ["threads"]
 
     def setup(self, threads):
-
         size = 2**22
         ngroups = 10**3
         data = Series(np.random.randint(0, ngroups, size=size))
@@ -140,12 +136,10 @@ def time_get_groups(self, threads):
 
 
 class ParallelTake1D:
-
     params = ["int64", "float64"]
     param_names = ["dtype"]
 
     def setup(self, dtype):
-
         N = 10**6
         df = DataFrame({"col": np.arange(N, dtype=dtype)})
         indexer = np.arange(100, len(df) - 100)
@@ -167,7 +161,6 @@ class ParallelKth:
     repeat = 5
 
     def setup(self):
-
         N = 10**7
         k = 5 * 10**5
         kwargs_list = [{"arr": np.random.randn(N)}, {"arr": np.random.randn(N)}]
@@ -184,7 +177,6 @@ def time_kth_smallest(self):
 
 class ParallelDatetimeFields:
     def setup(self):
-
         N = 10**6
         self.dti = date_range("1900-01-01", periods=N, freq="T")
         self.period = self.dti.to_period("D")
@@ -233,12 +225,10 @@ def run(period):
 
 
 class ParallelRolling:
-
     params = ["median", "mean", "min", "max", "var", "skew", "kurt", "std"]
     param_names = ["method"]
 
     def setup(self, method):
-
         win = 100
         arr = np.random.rand(100000)
         if hasattr(DataFrame, "rolling"):
@@ -274,14 +264,12 @@ def time_rolling(self, method):
 
 
 class ParallelReadCSV(BaseIO):
-
     number = 1
     repeat = 5
     params = ["float", "object", "datetime"]
     param_names = ["dtype"]
 
     def setup(self, dtype):
-
         rows = 10000
         cols = 50
         data = {
@@ -309,14 +297,12 @@ def time_read_csv(self, dtype):
 
 
 class ParallelFactorize:
-
     number = 1
     repeat = 5
     params = [2, 4, 8]
     param_names = ["threads"]
 
     def setup(self, threads):
-
         strings = tm.makeStringIndex(100000)
 
         @test_parallel(num_threads=threads)