Merge branch 'main' into depr-sparse-astype

Author: jbrockmendel

.github/workflows/posix.yml

@@ -28,13 +28,13 @@ jobs:
           [actions-38-downstream_compat.yaml, "not slow and not network and not clipboard", "", "", "", "", ""],
           [actions-38-minimum_versions.yaml, "slow", "", "", "", "", ""],
           [actions-38-minimum_versions.yaml, "not slow and not network and not clipboard", "", "", "", "", ""],
-          [actions-38-locale_slow.yaml, "slow", "language-pack-it xsel", "it_IT.utf8", "it_IT.utf8", "", ""],
+          [actions-38.yaml, "not slow and not network", "language-pack-it xsel", "it_IT.utf8", "it_IT.utf8", "", ""],
+          [actions-38.yaml, "not slow and not network", "language-pack-zh-hans xsel", "zh_CN.utf8", "zh_CN.utf8", "", ""],
           [actions-38.yaml, "not slow and not clipboard", "", "", "", "", ""],
-          [actions-38-slow.yaml, "slow", "", "", "", "", ""],
-          [actions-38-locale.yaml, "not slow and not network", "language-pack-zh-hans xsel", "zh_CN.utf8", "zh_CN.utf8", "", ""],
-          [actions-39-slow.yaml, "slow", "", "", "", "", ""],
+          [actions-38.yaml, "slow", "", "", "", "", ""],
           [actions-pypy-38.yaml, "not slow and not clipboard", "", "", "", "", "--max-worker-restart 0"],
           [actions-39-numpydev.yaml, "not slow and not network", "xsel", "", "", "deprecate", "-W error"],
+          [actions-39.yaml, "slow", "", "", "", "", ""],
           [actions-39.yaml, "not slow and not clipboard", "", "", "", "", ""]
         ]
       fail-fast: false

.github/workflows/stale-pr.yml

@@ -14,7 +14,8 @@ jobs:
         stale-pr-message: "This pull request is stale because it has been open for thirty days with no activity. Please [update](https://pandas.pydata.org/pandas-docs/stable/development/contributing.html#updating-your-pull-request) and respond to this comment if you're still interested in working on this."
         stale-pr-label: "Stale"
         exempt-pr-labels: "Needs Review,Blocked,Needs Discussion"
-        days-before-stale: 30
+        days-before-issue-stale: -1
+        days-before-pr-stale: 30
         days-before-close: -1
         remove-stale-when-updated: false
         debug-only: false

asv_bench/benchmarks/strings.py

@@ -3,10 +3,12 @@
 import numpy as np
 
 from pandas import (
+    NA,
     Categorical,
     DataFrame,
     Series,
 )
+from pandas.arrays import StringArray
 
 from .pandas_vb_common import tm
 
@@ -285,3 +287,18 @@ class Iter(Dtypes):
     def time_iter(self, dtype):
         for i in self.s:
             pass
+
+
+class StringArrayConstruction:
+    def setup(self):
+        self.series_arr = tm.rands_array(nchars=10, size=10 ** 5)
+        self.series_arr_nan = np.concatenate([self.series_arr, np.array([NA] * 1000)])
+
+    def time_string_array_construction(self):
+        StringArray(self.series_arr)
+
+    def time_string_array_with_nan_construction(self):
+        StringArray(self.series_arr_nan)
+
+    def peakmem_stringarray_construction(self):
+        StringArray(self.series_arr)

ci/deps/actions-38-locale.yaml

@@ -1,20 +1,50 @@
 name: pandas-dev
 channels:
-  - defaults
   - conda-forge
 dependencies:
   - python=3.8
 
-  # tools
-  - cython>=0.29.24
+  # test dependencies
+  - cython=0.29.24
   - pytest>=6.0
   - pytest-cov
   - pytest-xdist>=1.31
   - hypothesis>=5.5.3
+  - psutil
 
-  # pandas dependencies
-  - numpy
+  # required dependencies
   - python-dateutil
-  - nomkl
+  - numpy
   - pytz
+
+  # optional dependencies
+  - beautifulsoup4
+  - blosc
+  - bottleneck
+  - fastparquet
+  - fsspec
+  - html5lib
+  - gcsfs
+  - jinja2
+  - lxml
+  - matplotlib
+  - numba
+  - numexpr
+  - openpyxl
+  - odfpy
+  - pandas-gbq
+  - psycopg2
+  - pymysql
+  - pytables
+  - pyarrow
+  - pyreadstat
+  - pyxlsb
+  - s3fs
+  - scipy
+  - sqlalchemy
   - tabulate
+  - xarray
+  - xlrd
+  - xlsxwriter
+  - xlwt
+  - zstandard

ci/deps/actions-38-locale_slow.yaml

@@ -4,37 +4,47 @@ channels:
 dependencies:
   - python=3.9
 
-  # tools
-  - cython>=0.29.24
+  # test dependencies
+  - cython=0.29.24
   - pytest>=6.0
   - pytest-cov
   - pytest-xdist>=1.31
   - hypothesis>=5.5.3
+  - psutil
 
-  # pandas dependencies
+  # required dependencies
+  - python-dateutil
+  - numpy
+  - pytz
+
+  # optional dependencies
   - beautifulsoup4
+  - blosc
   - bottleneck
-  - boto3
-  - fsspec>=0.8.0
-  - gcsfs
+  - fastparquet
+  - fsspec
   - html5lib
+  - gcsfs
   - jinja2
   - lxml
   - matplotlib
-  - numpy  # move up to solve before numba
   - numba
   - numexpr
   - openpyxl
-  - pyarrow>2.0.1
+  - odfpy
+  - pandas-gbq
+  - psycopg2
+  - pymysql
   - pytables
-  - python-dateutil
-  - pytz
-  - s3fs>=0.4.2
+  - pyarrow
+  - pyreadstat
+  - pyxlsb
+  - s3fs
   - scipy
   - sqlalchemy
+  - tabulate
+  - xarray
   - xlrd
   - xlsxwriter
   - xlwt
-  - pyreadstat
-  - pyxlsb
   - zstandard

ci/deps/actions-38-slow.yaml

@@ -464,7 +464,7 @@ be stored efficiently as a :class:`arrays.SparseArray`.
 
 The ``Series.sparse`` accessor may be used to access sparse-specific attributes
 and methods if the :class:`Series` contains sparse values. See
-:ref:`api.series.sparse` for more.
+:ref:`api.series.sparse` and :ref:`the user guide <sparse>` for more.
 
 
 .. _api.arrays.string: