Merge branch 'main' into depr-setops

Author: jbrockmendel

.pre-commit-config.yaml

@@ -18,16 +18,16 @@ repos:
         pass_filenames: true
         require_serial: false
 -   repo: https://github.com/python/black
-    rev: 22.8.0
+    rev: 22.10.0
     hooks:
     -   id: black
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.2.1
+    rev: v2.2.2
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown]
 -   repo: https://github.com/MarcoGorelli/cython-lint
-    rev: v0.1.8
+    rev: v0.2.1
     hooks:
     -   id: cython-lint
 -   repo: https://github.com/pre-commit/pre-commit-hooks
@@ -60,15 +60,15 @@ repos:
         - flake8-bugbear==22.7.1
         - pandas-dev-flaker==0.5.0
 -   repo: https://github.com/pycqa/pylint
-    rev: v2.15.3
+    rev: v2.15.5
     hooks:
     -   id: pylint
 -   repo: https://github.com/PyCQA/isort
     rev: 5.10.1
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.38.2
+    rev: v3.2.0
     hooks:
     -   id: pyupgrade
         args: [--py38-plus]
@@ -83,7 +83,7 @@ repos:
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
 -   repo: https://github.com/sphinx-contrib/sphinx-lint
-    rev: v0.6.1
+    rev: v0.6.7
     hooks:
     - id: sphinx-lint
 -   repo: https://github.com/asottile/yesqa

asv_bench/benchmarks/inference.py

@@ -223,7 +223,7 @@ class ToDatetimeFormat:
     def setup(self):
         N = 100000
         self.s = Series(["19MAY11", "19MAY11:00:00:00"] * N)
-        self.s2 = self.s.str.replace(":\\S+$", "")
+        self.s2 = self.s.str.replace(":\\S+$", "", regex=True)
 
         self.same_offset = ["10/11/2018 00:00:00.045-07:00"] * N
         self.diff_offset = [

asv_bench/benchmarks/io/hdf.py

@@ -43,7 +43,7 @@ def setup(self):
             np.random.randn(N, 100), index=date_range("1/1/2000", periods=N)
         )
         self.df_dc = DataFrame(
-            np.random.randn(N, 10), columns=["C%03d" % i for i in range(10)]
+            np.random.randn(N, 10), columns=[f"C{i:03d}" for i in range(10)]
         )
 
         self.fname = "__test__.h5"

asv_bench/benchmarks/tslibs/timestamp.py

@@ -50,62 +50,58 @@ def time_from_pd_timestamp(self):
 
 
 class TimestampProperties:
-    _freqs = [None, "B"]
-    params = [_tzs, _freqs]
-    param_names = ["tz", "freq"]
+    params = [_tzs]
+    param_names = ["tz"]
 
-    def setup(self, tz, freq):
-        self.ts = Timestamp("2017-08-25 08:16:14", tzinfo=tz, freq=freq)
+    def setup(self, tz):
+        self.ts = Timestamp("2017-08-25 08:16:14", tzinfo=tz)
 
-    def time_tz(self, tz, freq):
+    def time_tz(self, tz):
         self.ts.tz
 
-    def time_dayofweek(self, tz, freq):
+    def time_dayofweek(self, tz):
         self.ts.dayofweek
 
-    def time_dayofyear(self, tz, freq):
+    def time_dayofyear(self, tz):
         self.ts.dayofyear
 
-    def time_week(self, tz, freq):
+    def time_week(self, tz):
         self.ts.week
 
-    def time_quarter(self, tz, freq):
+    def time_quarter(self, tz):
         self.ts.quarter
 
-    def time_days_in_month(self, tz, freq):
+    def time_days_in_month(self, tz):
         self.ts.days_in_month
 
-    def time_freqstr(self, tz, freq):
-        self.ts.freqstr
-
-    def time_is_month_start(self, tz, freq):
+    def time_is_month_start(self, tz):
         self.ts.is_month_start
 
-    def time_is_month_end(self, tz, freq):
+    def time_is_month_end(self, tz):
         self.ts.is_month_end
 
-    def time_is_quarter_start(self, tz, freq):
+    def time_is_quarter_start(self, tz):
         self.ts.is_quarter_start
 
-    def time_is_quarter_end(self, tz, freq):
+    def time_is_quarter_end(self, tz):
         self.ts.is_quarter_end
 
-    def time_is_year_start(self, tz, freq):
+    def time_is_year_start(self, tz):
         self.ts.is_year_start
 
-    def time_is_year_end(self, tz, freq):
+    def time_is_year_end(self, tz):
         self.ts.is_year_end
 
-    def time_is_leap_year(self, tz, freq):
+    def time_is_leap_year(self, tz):
         self.ts.is_leap_year
 
-    def time_microsecond(self, tz, freq):
+    def time_microsecond(self, tz):
         self.ts.microsecond
 
-    def time_month_name(self, tz, freq):
+    def time_month_name(self, tz):
         self.ts.month_name()
 
-    def time_weekday_name(self, tz, freq):
+    def time_weekday_name(self, tz):
         self.ts.day_name()
 
 

ci/fix_wheels.py

@@ -4,7 +4,12 @@
 import zipfile
 
 try:
-    _, wheel_path, dest_dir = sys.argv
+    if len(sys.argv) != 3:
+        raise ValueError(
+            "User must pass the path to the wheel and the destination directory."
+        )
+    wheel_path = sys.argv[1]
+    dest_dir = sys.argv[2]
     # Figure out whether we are building on 32 or 64 bit python
     is_32 = sys.maxsize <= 2**32
     PYTHON_ARCH = "x86" if is_32 else "x64"
@@ -50,5 +55,4 @@
 if not success:
     os.remove(repaired_wheel_path)
     raise exception
-else:
-    print(f"Successfully repaired wheel was written to {repaired_wheel_path}")
+print(f"Successfully repaired wheel was written to {repaired_wheel_path}")

doc/make.py

@@ -259,8 +259,7 @@ def latex(self, force=False):
                     "You should check the file "
                     '"build/latex/pandas.pdf" for problems.'
                 )
-            else:
-                self._run_os("make")
+            self._run_os("make")
             return ret_code
 
     def latex_forced(self):

doc/redirects.csv

@@ -1321,8 +1321,6 @@ generated/pandas.Timestamp.daysinmonth,../reference/api/pandas.Timestamp.daysinm
 generated/pandas.Timestamp.dst,../reference/api/pandas.Timestamp.dst
 generated/pandas.Timestamp.floor,../reference/api/pandas.Timestamp.floor
 generated/pandas.Timestamp.fold,../reference/api/pandas.Timestamp.fold
-generated/pandas.Timestamp.freq,../reference/api/pandas.Timestamp.freq
-generated/pandas.Timestamp.freqstr,../reference/api/pandas.Timestamp.freqstr
 generated/pandas.Timestamp.fromisoformat,../reference/api/pandas.Timestamp.fromisoformat
 generated/pandas.Timestamp.fromordinal,../reference/api/pandas.Timestamp.fromordinal
 generated/pandas.Timestamp.fromtimestamp,../reference/api/pandas.Timestamp.fromtimestamp

doc/scripts/eval_performance.py

@@ -17,7 +17,7 @@ def bench_with(n, times=10, repeat=3, engine="numexpr"):
     return (
         np.array(
             timeit(
-                "df.eval(s, engine=%r)" % engine,
+                f"df.eval(s, engine={repr(engine)})",
                 setup=setup_common % (n, setup_with),
                 repeat=repeat,
                 number=times,
@@ -34,7 +34,7 @@ def bench_subset(n, times=20, repeat=3, engine="numexpr"):
     return (
         np.array(
             timeit(
-                "df.query(s, engine=%r)" % engine,
+                f"df.query(s, engine={repr(engine)})",
                 setup=setup_common % (n, setup_subset),
                 repeat=repeat,
                 number=times,
@@ -55,7 +55,7 @@ def bench(mn=3, mx=7, num=100, engines=("python", "numexpr"), verbose=False):
     for engine in engines:
         for i, n in enumerate(r):
             if verbose & (i % 10 == 0):
-                print("engine: %r, i == %d" % (engine, i))
+                print(f"engine: {repr(engine)}, i == {i:d}")
             ev_times = bench_with(n, times=1, repeat=1, engine=engine)
             ev.loc[i, engine] = np.mean(ev_times)
             qu_times = bench_subset(n, times=1, repeat=1, engine=engine)

doc/source/getting_started/install.rst

@@ -417,7 +417,7 @@ Dependency                Minimum Version    optional_extra   Notes
 PyTables                  3.6.1              hdf5             HDF5-based reading / writing
 blosc                     1.21.0             hdf5             Compression for HDF5
 zlib                                         hdf5             Compression for HDF5
-fastparquet               0.4.0              -                Parquet reading / writing (pyarrow is default)
+fastparquet               0.6.3              -                Parquet reading / writing (pyarrow is default)
 pyarrow                   6.0.0              parquet, feather Parquet, ORC, and feather reading / writing
 pyreadstat                1.1.2              spss             SPSS files (.sav) reading
 odfpy                     1.4.1              excel            Open document format (.odf, .ods, .odt) reading / writing

doc/source/reference/arrays.rst

@@ -157,8 +157,6 @@ Methods
    Timestamp.day_name
    Timestamp.dst
    Timestamp.floor
-   Timestamp.freq
-   Timestamp.freqstr
    Timestamp.fromordinal
    Timestamp.fromtimestamp
    Timestamp.isocalendar

doc/source/user_guide/timedeltas.rst

@@ -236,9 +236,7 @@ Numeric reduction operation for ``timedelta64[ns]`` will return ``Timedelta`` ob
 Frequency conversion
 --------------------
 
-Timedelta Series, ``TimedeltaIndex``, and ``Timedelta`` scalars can be converted to other 'frequencies' by dividing by another timedelta,
-or by astyping to a specific timedelta type. These operations yield Series and propagate ``NaT`` -> ``nan``.
-Note that division by the NumPy scalar is true division, while astyping is equivalent of floor division.
+Timedelta Series and ``TimedeltaIndex``, and ``Timedelta`` can be converted to other frequencies by astyping to a specific timedelta dtype.
 
 .. ipython:: python
 
@@ -250,14 +248,17 @@ Note that division by the NumPy scalar is true division, while astyping is equiv
    td[3] = np.nan
    td
 
-   # to days
-   td / np.timedelta64(1, "D")
-   td.astype("timedelta64[D]")
-
    # to seconds
-   td / np.timedelta64(1, "s")
    td.astype("timedelta64[s]")
 
+For timedelta64 resolutions other than the supported "s", "ms", "us", "ns",
+an alternative is to divide by another timedelta object. Note that division by the NumPy scalar is true division, while astyping is equivalent of floor division.
+
+.. ipython:: python
+
+   # to days
+   td / np.timedelta64(1, "D")
+
    # to months (these are constant months)
    td / np.timedelta64(1, "M")
 

doc/source/whatsnew/v0.13.0.rst

@@ -532,6 +532,7 @@ Enhancements
   is frequency conversion. See :ref:`the docs<timedeltas.timedeltas_convert>` for the docs.
 
   .. ipython:: python
+     :okexcept:
 
      import datetime
      td = pd.Series(pd.date_range('20130101', periods=4)) - pd.Series(

doc/source/whatsnew/v0.24.0.rst

@@ -1357,6 +1357,7 @@ the object's ``freq`` attribute (:issue:`21939`, :issue:`23878`).
 *New behavior*:
 
 .. ipython:: python
+    :okexcept:
     :okwarning:
 
     ts = pd.Timestamp('1994-05-06 12:15:16', freq=pd.offsets.Hour())