Merge remote-tracking branch 'upstream/master' into TYP-io-formats-style

Author: MomIsBestFriend

asv_bench/asv.conf.json

@@ -43,6 +43,7 @@
         "matplotlib": [],
         "sqlalchemy": [],
         "scipy": [],
+        "numba": [],
         "numexpr": [],
         "pytables": [null, ""],  // platform dependent, see excludes below
         "tables": [null, ""],

asv_bench/benchmarks/rolling.py

@@ -44,6 +44,27 @@ def time_rolling(self, constructor, window, dtype, function, raw):
         self.roll.apply(function, raw=raw)
 
 
+class Engine:
+    params = (
+        ["DataFrame", "Series"],
+        ["int", "float"],
+        [np.sum, lambda x: np.sum(x) + 5],
+        ["cython", "numba"],
+    )
+    param_names = ["constructor", "dtype", "function", "engine"]
+
+    def setup(self, constructor, dtype, function, engine):
+        N = 10 ** 3
+        arr = (100 * np.random.random(N)).astype(dtype)
+        self.data = getattr(pd, constructor)(arr)
+
+    def time_rolling_apply(self, constructor, dtype, function, engine):
+        self.data.rolling(10).apply(function, raw=True, engine=engine)
+
+    def time_expanding_apply(self, constructor, dtype, function, engine):
+        self.data.expanding().apply(function, raw=True, engine=engine)
+
+
 class ExpandingMethods:
 
     params = (

ci/code_checks.sh

@@ -314,8 +314,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (GL03, GL04, GL05, GL06, GL07, GL09, GL10, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT01, RT04, RT05, SA01, SA02, SA03, SA05)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL03,GL04,GL05,GL06,GL07,GL09,GL10,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT01,RT04,RT05,SA01,SA02,SA03,SA05
+    MSG='Validate docstrings (GL03, GL04, GL05, GL06, GL07, GL09, GL10, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT01, RT04, RT05, SA02, SA03, SA05)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=GL03,GL04,GL05,GL06,GL07,GL09,GL10,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT01,RT04,RT05,SA02,SA03,SA05
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

doc/source/conf.py

@@ -10,6 +10,7 @@
 # All configuration values have a default; values that are commented out
 # serve to show the default.
 
+from datetime import datetime
 import importlib
 import inspect
 import logging
@@ -137,7 +138,7 @@
 
 # General information about the project.
 project = "pandas"
-copyright = "2008-2020, the pandas development team"
+copyright = f"2008-{datetime.now().year}, the pandas development team"
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the

doc/source/ecosystem.rst

@@ -41,6 +41,16 @@ Pyjanitor provides a clean API for cleaning data, using method chaining.
 Engarde is a lightweight library used to explicitly state assumptions about your datasets
 and check that they're *actually* true.
 
+`pandas-path <https://github.com/drivendataorg/pandas-path/>`__
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Since Python 3.4, `pathlib <https://docs.python.org/3/library/pathlib.html>`_ has been
+included in the Python standard library. Path objects provide a simple
+and delightful way to interact with the file system. The pandas-path package enables the
+Path API for pandas through a custom accessor ``.path``. Getting just the filenames from
+a series of full file paths is as simple as ``my_files.path.name``. Other convenient operations like
+joining paths, replacing file extensions, and checking if files exist are also available.
+
 .. _ecosystem.stats:
 
 Statistics and machine learning
@@ -386,12 +396,16 @@ A directory of projects providing
 :ref:`extension accessors <extending.register-accessors>`. This is for users to
 discover new accessors and for library authors to coordinate on the namespace.
 
-============== ========== =========================
-Library        Accessor   Classes
-============== ========== =========================
-`cyberpandas`_ ``ip``     ``Series``
-`pdvega`_      ``vgplot`` ``Series``, ``DataFrame``
-============== ========== =========================
+=============== ========== ========================= ===============================================================
+Library         Accessor   Classes                   Description
+=============== ========== ========================= ===============================================================
+`cyberpandas`_  ``ip``     ``Series``                Provides common operations for working with IP addresses.
+`pdvega`_       ``vgplot`` ``Series``, ``DataFrame`` Provides plotting functions from the Altair_ library.
+`pandas_path`_  ``path``   ``Index``, ``Series``     Provides `pathlib.Path`_ functions for Series.
+=============== ========== ========================= ===============================================================
 
 .. _cyberpandas: https://cyberpandas.readthedocs.io/en/latest
 .. _pdvega: https://altair-viz.github.io/pdvega/
+.. _Altair: https://altair-viz.github.io/
+.. _pandas_path: https://github.com/drivendataorg/pandas-path/
+.. _pathlib.Path: https://docs.python.org/3/library/pathlib.html

doc/source/user_guide/computation.rst

@@ -348,6 +348,7 @@ Numba will be applied in potentially two routines:
 
 1. If ``func`` is a standard Python function, the engine will `JIT <http://numba.pydata.org/numba-doc/latest/user/overview.html>`__
 the passed function. ``func`` can also be a JITed function in which case the engine will not JIT the function again.
+
 2. The engine will JIT the for loop where the apply function is applied to each window.
 
 The ``engine_kwargs`` argument is a dictionary of keyword arguments that will be passed into the

doc/source/whatsnew/v1.0.0.rst

@@ -159,14 +159,14 @@ You can use the alias ``"boolean"`` as well.
 
 .. _whatsnew_100.numba_rolling_apply:
 
-Using Numba in ``rolling.apply``
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Using Numba in ``rolling.apply`` and ``expanding.apply``
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-We've added an ``engine`` keyword to :meth:`~core.window.rolling.Rolling.apply` that allows the user to execute the
-routine using `Numba <https://numba.pydata.org/>`__ instead of Cython. Using the Numba engine
-can yield significant performance gains if the apply function can operate on numpy arrays and
+We've added an ``engine`` keyword to :meth:`~core.window.rolling.Rolling.apply` and :meth:`~core.window.expanding.Expanding.apply`
+that allows the user to execute the routine using `Numba <https://numba.pydata.org/>`__ instead of Cython.
+Using the Numba engine can yield significant performance gains if the apply function can operate on numpy arrays and
 the data set is larger (1 million rows or greater). For more details, see
-:ref:`rolling apply documentation <stats.rolling_apply>` (:issue:`28987`)
+:ref:`rolling apply documentation <stats.rolling_apply>` (:issue:`28987`, :issue:`30936`)
 
 .. _whatsnew_100.custom_window:
 

environment.yml

@@ -27,7 +27,6 @@ dependencies:
   # documentation
   - gitpython  # obtain contributors from git for whatsnew
   - sphinx
-  - numpydoc>=0.9.0
 
   # documentation (jupyter notebooks)
   - nbconvert>=5.4.1
@@ -105,3 +104,4 @@ dependencies:
   - tabulate>=0.8.3  # DataFrame.to_markdown
   - pip:
     - git+https://github.com/pandas-dev/pandas-sphinx-theme.git@master
+    - git+https://github.com/numpy/numpydoc