Merge branch 'main' into stata-read-dta104

Author: cmjcharlton

.github/workflows/cache-cleanup-weekly.yml renamed to .github/workflows/cache-cleanup-daily.yml

@@ -1,8 +1,8 @@
-name: Purge caches once a week
+name: Purge caches daily
 on:
   schedule:
-    # 4:10 UTC on Sunday
-    - cron: "10 4 * * 0"
+    # 4:10 UTC daily
+    - cron: "10 4 * * *"
 
 jobs:
   cleanup:

.github/workflows/wheels.yml

@@ -140,7 +140,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.17.0
+        uses: pypa/cibuildwheel@v2.18.1
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

.pre-commit-config.yaml

@@ -90,6 +90,7 @@ repos:
     rev: v0.9.1
     hooks:
     - id: sphinx-lint
+      args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
     rev: v18.1.4
     hooks:

LICENSES/XARRAY_LICENSE

@@ -445,16 +445,6 @@ def setup(self, engine):
         data = data.format(*two_cols)
         self.StringIO_input = StringIO(data)
 
-    def time_multiple_date(self, engine):
-        read_csv(
-            self.data(self.StringIO_input),
-            engine=engine,
-            sep=",",
-            header=None,
-            names=list(string.digits[:9]),
-            parse_dates=[[1, 2], [1, 3]],
-        )
-
     def time_baseline(self, engine):
         read_csv(
             self.data(self.StringIO_input),

asv_bench/benchmarks/io/csv.py

@@ -1,10 +1,5 @@
-import numpy as np
-
 try:
-    from pandas._libs.tslibs.parsing import (
-        _does_string_look_like_datetime,
-        concat_date_cols,
-    )
+    from pandas._libs.tslibs.parsing import _does_string_look_like_datetime
 except ImportError:
     # Avoid whole benchmark suite import failure on asv (currently 0.4)
     pass
@@ -20,21 +15,3 @@ def setup(self, value):
     def time_check_datetimes(self, value):
         for obj in self.objects:
             _does_string_look_like_datetime(obj)
-
-
-class ConcatDateCols:
-    params = ([1234567890, "AAAA"], [1, 2])
-    param_names = ["value", "dim"]
-
-    def setup(self, value, dim):
-        count_elem = 10000
-        if dim == 1:
-            self.object = (np.array([value] * count_elem),)
-        if dim == 2:
-            self.object = (
-                np.array([value] * count_elem),
-                np.array([value] * count_elem),
-            )
-
-    def time_check_concat(self, value, dim):
-        concat_date_cols(self.object)

asv_bench/benchmarks/io/parsers.py

@@ -148,10 +148,14 @@ def time_searchsorted(self, dtype):
 
 
 class Map:
-    params = (["dict", "Series", "lambda"], ["object", "category", "int"])
-    param_names = "mapper"
-
-    def setup(self, mapper, dtype):
+    params = (
+        ["dict", "Series", "lambda"],
+        ["object", "category", "int"],
+        [None, "ignore"],
+    )
+    param_names = ["mapper", "dtype", "na_action"]
+
+    def setup(self, mapper, dtype, na_action):
         map_size = 1000
         map_data = Series(map_size - np.arange(map_size), dtype=dtype)
 
@@ -168,8 +172,8 @@ def setup(self, mapper, dtype):
 
         self.s = Series(np.random.randint(0, map_size, 10000), dtype=dtype)
 
-    def time_map(self, mapper, *args, **kwargs):
-        self.s.map(self.map_data)
+    def time_map(self, mapper, dtype, na_action):
+        self.s.map(self.map_data, na_action=na_action)
 
 
 class Clip:

asv_bench/benchmarks/series_methods.py

@@ -19,10 +19,15 @@ class TimeGetTimedeltaField:
     def setup(self, size, field):
         arr = np.random.randint(0, 10, size=size, dtype="i8")
         self.i8data = arr
+        arr = np.random.randint(-86400 * 1_000_000_000, 0, size=size, dtype="i8")
+        self.i8data_negative = arr
 
     def time_get_timedelta_field(self, size, field):
         get_timedelta_field(self.i8data, field)
 
+    def time_get_timedelta_field_negative_td(self, size, field):
+        get_timedelta_field(self.i8data_negative, field)
+
 
 class TimeGetDateField:
     params = [
@@ -72,3 +77,6 @@ def setup(self, size, side, period, freqstr, month_kw):
 
     def time_get_start_end_field(self, size, side, period, freqstr, month_kw):
         get_start_end_field(self.i8data, self.attrname, freqstr, month_kw=month_kw)
+
+
+from ..pandas_vb_common import setup  # noqa: F401 isort:skip