Merge remote-tracking branch 'upstream/main' into pr/jorisvandenbossche/ruff

Author: MarcoGorelli

asv_bench/benchmarks/array.py

@@ -44,6 +44,15 @@ def time_from_integer_array(self):
         pd.array(self.values_integer, dtype="Int64")
 
 
+class IntervalArray:
+    def setup(self):
+        N = 10_000
+        self.tuples = [(i, i + 1) for i in range(N)]
+
+    def time_from_tuples(self):
+        pd.arrays.IntervalArray.from_tuples(self.tuples)
+
+
 class StringArray:
     def setup(self):
         N = 100_000

asv_bench/benchmarks/indexing.py

@@ -476,6 +476,19 @@ def time_assign_list_of_columns_concat(self):
         concat([self.df, df], axis=1)
 
 
+class Setitem:
+    def setup(self):
+        N = 500_000
+        cols = 500
+        self.df = DataFrame(np.random.rand(N, cols))
+
+    def time_setitem(self):
+        self.df[100] = 100
+
+    def time_setitem_list(self):
+        self.df[[100, 200, 300]] = 100
+
+
 class ChainIndexing:
 
     params = [None, "warn"]

asv_bench/benchmarks/rolling.py

@@ -292,7 +292,7 @@ class Groupby:
         ["sum", "median", "mean", "max", "min", "kurt", "sum"],
         [
             ("rolling", {"window": 2}),
-            ("rolling", {"window": "30s", "on": "C"}),
+            ("rolling", {"window": "30s"}),
             ("expanding", {}),
         ],
     )
@@ -304,9 +304,10 @@ def setup(self, method, window_kwargs):
             {
                 "A": [str(i) for i in range(N)] * 10,
                 "B": list(range(N)) * 10,
-                "C": pd.date_range(start="1900-01-01", freq="1min", periods=N * 10),
             }
         )
+        if isinstance(kwargs.get("window", None), str):
+            df.index = pd.date_range(start="1900-01-01", freq="1min", periods=N * 10)
         self.groupby_window = getattr(df.groupby("A"), window)(**kwargs)
 
     def time_method(self, method, window_kwargs):

asv_bench/benchmarks/series_methods.py

@@ -382,4 +382,23 @@ def time_iter(self, dtype):
             pass
 
 
+class ToNumpy:
+    def setup(self):
+        N = 1_000_000
+        self.ser = Series(
+            np.random.randn(
+                N,
+            )
+        )
+
+    def time_to_numpy(self):
+        self.ser.to_numpy()
+
+    def time_to_numpy_double_copy(self):
+        self.ser.to_numpy(dtype="float64", copy=True)
+
+    def time_to_numpy_copy(self):
+        self.ser.to_numpy(copy=True)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

ci/code_checks.sh

@@ -83,6 +83,36 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
     $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05,SS06
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Partially validate docstrings (RT02)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=RT02 --ignore_functions \
+    	    pandas.Series.align \
+	    pandas.Series.dt.total_seconds \
+	    pandas.Series.cat.rename_categories \
+	    pandas.Series.cat.reorder_categories \
+	    pandas.Series.cat.add_categories \
+	    pandas.Series.cat.remove_categories \
+	    pandas.Series.cat.remove_unused_categories \
+	    pandas.Index.all \
+	    pandas.Index.any \
+	    pandas.CategoricalIndex.rename_categories \
+	    pandas.CategoricalIndex.reorder_categories \
+	    pandas.CategoricalIndex.add_categories \
+	    pandas.CategoricalIndex.remove_categories \
+	    pandas.CategoricalIndex.remove_unused_categories \
+	    pandas.MultiIndex.drop \
+	    pandas.DatetimeIndex.to_pydatetime \
+	    pandas.TimedeltaIndex.to_pytimedelta \
+	    pandas.core.groupby.SeriesGroupBy.apply \
+	    pandas.core.groupby.DataFrameGroupBy.apply \
+	    pandas.io.formats.style.Styler.export \
+	    pandas.api.extensions.ExtensionArray.astype \
+	    pandas.api.extensions.ExtensionArray.dropna \
+	    pandas.api.extensions.ExtensionArray.isna \
+	    pandas.api.extensions.ExtensionArray.repeat \
+	    pandas.api.extensions.ExtensionArray.unique \
+	    pandas.DataFrame.align
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
 fi
 
 ### DOCUMENTATION NOTEBOOKS ###

ci/deps/actions-310.yaml

@@ -48,7 +48,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy
+  - sqlalchemy<1.4.46
   - tabulate
   - tzdata>=2022a
   - xarray

ci/deps/actions-38-downstream_compat.yaml

@@ -48,7 +48,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy
+  - sqlalchemy<1.4.46
   - tabulate
   - xarray
   - xlrd

ci/deps/actions-38.yaml

@@ -48,7 +48,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy
+  - sqlalchemy<1.4.46
   - tabulate
   - xarray
   - xlrd

ci/deps/actions-39.yaml

@@ -48,7 +48,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy
+  - sqlalchemy<1.4.46
   - tabulate
   - tzdata>=2022a
   - xarray

ci/deps/circle-38-arm64.yaml

@@ -49,7 +49,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy
+  - sqlalchemy<1.4.46
   - tabulate
   - xarray
   - xlrd