Merge remote-tracking branch 'upstream/main' into feat/cleanup_docs

Author: mroeschke

.circleci/config.yml

@@ -46,6 +46,7 @@ jobs:
             fi
       - run:
           name: Build aarch64 wheels
+          no_output_timeout: 30m # Sometimes the tests won't generate any output, make sure the job doesn't get killed by that
           command: |
             pip3 install cibuildwheel==2.14.1
             cibuildwheel --prerelease-pythons --output-dir wheelhouse

.github/workflows/wheels.yml

@@ -139,7 +139,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.14.1
+        uses: pypa/cibuildwheel@v2.15.0
         with:
          package-dir: ./dist/${{ matrix.buildplat[1] == 'macosx_*' && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
     hooks:
       - id: black
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.0.282
+    rev: v0.0.284
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]

asv_bench/benchmarks/algos/isin.py

@@ -247,7 +247,7 @@ def setup(self, series_type, vals_type):
         elif series_type == "long":
             ser_vals = np.arange(N_many)
         elif series_type == "long_floats":
-            ser_vals = np.arange(N_many, dtype=np.float_)
+            ser_vals = np.arange(N_many, dtype=np.float64)
 
         self.series = Series(ser_vals).astype(object)
 
@@ -258,7 +258,7 @@ def setup(self, series_type, vals_type):
         elif vals_type == "long":
             values = np.arange(N_many)
         elif vals_type == "long_floats":
-            values = np.arange(N_many, dtype=np.float_)
+            values = np.arange(N_many, dtype=np.float64)
 
         self.values = values.astype(object)
 

doc/source/conf.py

@@ -242,7 +242,10 @@
     "footer_start": ["pandas_footer", "sphinx-version"],
     "github_url": "https://github.com/pandas-dev/pandas",
     "twitter_url": "https://twitter.com/pandas_dev",
-    "analytics": {"google_analytics_id": "G-5RE31C1RNW"},
+    "analytics": {
+        "plausible_analytics_domain": "pandas.pydata.org",
+        "plausible_analytics_url": "https://views.scientific-python.org/js/script.js",
+    },
     "logo": {"image_dark": "https://pandas.pydata.org/static/img/pandas_white.svg"},
     "navbar_end": ["version-switcher", "theme-switcher", "navbar-icon-links"],
     "switcher": {

doc/source/getting_started/comparison/comparison_with_sql.rst

@@ -107,7 +107,7 @@ methods.
 .. ipython:: python
 
     frame = pd.DataFrame(
-        {"col1": ["A", "B", np.NaN, "C", "D"], "col2": ["F", np.NaN, "G", "H", "I"]}
+        {"col1": ["A", "B", np.nan, "C", "D"], "col2": ["F", np.nan, "G", "H", "I"]}
     )
     frame
 

doc/source/getting_started/install.rst

@@ -206,6 +206,7 @@ Package                                                          Minimum support
 `NumPy <https://numpy.org>`__                                    1.22.4
 `python-dateutil <https://dateutil.readthedocs.io/en/stable/>`__ 2.8.2
 `pytz <https://pypi.org/project/pytz/>`__                        2020.1
+`tzdata <https://pypi.org/project/tzdata/>`__                    2022.1
 ================================================================ ==========================
 
 .. _install.optional_dependencies:

doc/source/reference/series.rst

@@ -314,6 +314,7 @@ Datetime properties
    Series.dt.weekday
    Series.dt.dayofyear
    Series.dt.day_of_year
+   Series.dt.days_in_month
    Series.dt.quarter
    Series.dt.is_month_start
    Series.dt.is_month_end
@@ -327,6 +328,7 @@ Datetime properties
    Series.dt.tz
    Series.dt.freq
    Series.dt.unit
+   Series.dt.normalize
 
 Datetime methods
 ^^^^^^^^^^^^^^^^

doc/source/user_guide/enhancingperf.rst

@@ -183,8 +183,8 @@ can be improved by passing an ``np.ndarray``.
       ...:     return s * dx
       ...: cpdef np.ndarray[double] apply_integrate_f(np.ndarray col_a, np.ndarray col_b,
       ...:                                            np.ndarray col_N):
-      ...:     assert (col_a.dtype == np.float_
-      ...:             and col_b.dtype == np.float_ and col_N.dtype == np.int_)
+      ...:     assert (col_a.dtype == np.float64
+      ...:             and col_b.dtype == np.float64 and col_N.dtype == np.int_)
       ...:     cdef Py_ssize_t i, n = len(col_N)
       ...:     assert (len(col_a) == len(col_b) == n)
       ...:     cdef np.ndarray[double] res = np.empty(n)

doc/source/user_guide/gotchas.rst

@@ -327,7 +327,7 @@ present in the more domain-specific statistical programming language `R
    ``numpy.unsignedinteger`` | ``uint8, uint16, uint32, uint64``
    ``numpy.object_`` | ``object_``
    ``numpy.bool_`` | ``bool_``
-   ``numpy.character`` | ``string_, unicode_``
+   ``numpy.character`` | ``bytes_, str_``
 
 The R language, by contrast, only has a handful of built-in data types:
 ``integer``, ``numeric`` (floating-point), ``character``, and

doc/source/user_guide/io.rst

@@ -4881,7 +4881,7 @@ unspecified columns of the given DataFrame. The argument ``selector``
 defines which table is the selector table (which you can make queries from).
 The argument ``dropna`` will drop rows from the input ``DataFrame`` to ensure
 tables are synchronized.  This means that if a row for one of the tables
-being written to is entirely ``np.NaN``, that row will be dropped from all tables.
+being written to is entirely ``np.nan``, that row will be dropped from all tables.
 
 If ``dropna`` is False, **THE USER IS RESPONSIBLE FOR SYNCHRONIZING THE TABLES**.
 Remember that entirely ``np.Nan`` rows are not written to the HDFStore, so if