Merge branch 'master' into 41457-upgrade-to-bootstrap5

Merge to pass CI tests

Author: calvh

.pre-commit-config.yaml

@@ -19,14 +19,14 @@ repos:
         types_or: [python, rst, markdown]
         files: ^(pandas|doc)/
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v3.4.0
+    rev: v4.0.1
     hooks:
     -   id: debug-statements
     -   id: end-of-file-fixer
         exclude: \.txt$
     -   id: trailing-whitespace
 -   repo: https://github.com/cpplint/cpplint
-    rev: f7061b1 # the latest tag does not have the hook
+    rev: 1.5.5
     hooks:
     -   id: cpplint
         # We don't lint all C files because we don't want to lint any that are built
@@ -57,7 +57,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.12.0
+    rev: v2.18.3
     hooks:
     -   id: pyupgrade
         args: [--py37-plus]
@@ -72,7 +72,7 @@ repos:
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
 -   repo: https://github.com/asottile/yesqa
-    rev: v1.2.2
+    rev: v1.2.3
     hooks:
     -   id: yesqa
         additional_dependencies:

.travis.yml

@@ -17,6 +17,7 @@
 [![Gitter](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/pydata/pandas)
 [![Powered by NumFOCUS](https://img.shields.io/badge/powered%20by-NumFOCUS-orange.svg?style=flat&colorA=E1523D&colorB=007D8A)](https://numfocus.org)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
 
 ## What is it?
 
@@ -101,8 +102,8 @@ pip install pandas
 
 ## Dependencies
 - [NumPy - Adds support for large, multi-dimensional arrays, matrices and high-level mathematical functions to operate on these arrays](https://www.numpy.org)
-- [python-dateutil - Provides powerful extensions to the standard datetime module](https://labix.org/python-dateutil)
-- [pytz - Brings the Olson tz database into Python which allows accurate and cross platform timezone calculations](https://pythonhosted.org/pytz)
+- [python-dateutil - Provides powerful extensions to the standard datetime module](https://dateutil.readthedocs.io/en/stable/index.html)
+- [pytz - Brings the Olson tz database into Python which allows accurate and cross platform timezone calculations](https://github.com/stub42/pytz)
 
 See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies) for minimum supported versions of required, recommended and optional dependencies.
 
@@ -121,7 +122,7 @@ cloning the git repo), execute:
 python setup.py install
 ```
 
-or for installing in [development mode](https://pip.pypa.io/en/latest/reference/pip_install.html#editable-installs):
+or for installing in [development mode](https://pip.pypa.io/en/latest/cli/pip_install/#install-editable):
 
 
 ```sh

README.md

@@ -23,41 +23,38 @@ class Factorize:
             "int",
             "uint",
             "float",
-            "string",
+            "object",
             "datetime64[ns]",
             "datetime64[ns, tz]",
             "Int64",
             "boolean",
-            "string_arrow",
+            "string[pyarrow]",
         ],
     ]
     param_names = ["unique", "sort", "dtype"]
 
     def setup(self, unique, sort, dtype):
         N = 10 ** 5
         string_index = tm.makeStringIndex(N)
-        try:
-            from pandas.core.arrays.string_arrow import ArrowStringDtype
-
-            string_arrow = pd.array(string_index, dtype=ArrowStringDtype())
-        except ImportError:
-            string_arrow = None
-
-        if dtype == "string_arrow" and not string_arrow:
-            raise NotImplementedError
+        string_arrow = None
+        if dtype == "string[pyarrow]":
+            try:
+                string_arrow = pd.array(string_index, dtype="string[pyarrow]")
+            except ImportError:
+                raise NotImplementedError
 
         data = {
             "int": pd.Int64Index(np.arange(N)),
             "uint": pd.UInt64Index(np.arange(N)),
             "float": pd.Float64Index(np.random.randn(N)),
-            "string": string_index,
+            "object": string_index,
             "datetime64[ns]": pd.date_range("2011-01-01", freq="H", periods=N),
             "datetime64[ns, tz]": pd.date_range(
                 "2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
             ),
             "Int64": pd.array(np.arange(N), dtype="Int64"),
             "boolean": pd.array(np.random.randint(0, 2, N), dtype="boolean"),
-            "string_arrow": string_arrow,
+            "string[pyarrow]": string_arrow,
         }[dtype]
         if not unique:
             data = data.repeat(5)

asv_bench/benchmarks/algorithms.py

@@ -25,8 +25,8 @@ class IsIn:
         "category[object]",
         "category[int]",
         "str",
-        "string",
-        "arrow_string",
+        "string[python]",
+        "string[pyarrow]",
     ]
     param_names = ["dtype"]
 
@@ -62,9 +62,7 @@ def setup(self, dtype):
             self.values = np.random.choice(arr, sample_size)
             self.series = Series(arr).astype("category")
 
-        elif dtype in ["str", "string", "arrow_string"]:
-            from pandas.core.arrays.string_arrow import ArrowStringDtype  # noqa: F401
-
+        elif dtype in ["str", "string[python]", "string[pyarrow]"]:
             try:
                 self.series = Series(tm.makeStringIndex(N), dtype=dtype)
             except ImportError:

asv_bench/benchmarks/algos/isin.py

@@ -652,7 +652,9 @@ class Rank:
     ]
 
     def setup(self, dtype):
-        self.df = DataFrame(np.random.randn(10000, 10), columns=range(10), dtype=dtype)
+        self.df = DataFrame(
+            np.random.randn(10000, 10).astype(dtype), columns=range(10), dtype=dtype
+        )
 
     def time_rank(self, dtype):
         self.df.rank()

asv_bench/benchmarks/frame_methods.py

@@ -1,5 +1,9 @@
+import importlib
+import sys
+
 import matplotlib
 import numpy as np
+import pkg_resources
 
 from pandas import (
     DataFrame,
@@ -13,6 +17,8 @@
 except ImportError:
     from pandas.tools.plotting import andrews_curves
 
+from pandas.plotting._core import _get_plot_backend
+
 matplotlib.use("Agg")
 
 
@@ -99,4 +105,28 @@ def time_plot_andrews_curves(self):
         andrews_curves(self.df, "Name")
 
 
+class BackendLoading:
+    repeat = 1
+    number = 1
+    warmup_time = 0
+
+    def setup(self):
+        dist = pkg_resources.get_distribution("pandas")
+        spec = importlib.machinery.ModuleSpec("my_backend", None)
+        mod = importlib.util.module_from_spec(spec)
+        mod.plot = lambda *args, **kwargs: 1
+
+        backends = pkg_resources.get_entry_map("pandas")
+        my_entrypoint = pkg_resources.EntryPoint(
+            "pandas_plotting_backend", mod.__name__, dist=dist
+        )
+        backends["pandas_plotting_backends"][mod.__name__] = my_entrypoint
+        for i in range(10):
+            backends["pandas_plotting_backends"][str(i)] = my_entrypoint
+        sys.modules["my_backend"] = mod
+
+    def time_get_plot_backend(self):
+        _get_plot_backend("my_backend")
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/plotting.py

@@ -12,12 +12,10 @@
 
 
 class Dtypes:
-    params = ["str", "string", "arrow_string"]
+    params = ["str", "string[python]", "string[pyarrow]"]
     param_names = ["dtype"]
 
     def setup(self, dtype):
-        from pandas.core.arrays.string_arrow import ArrowStringDtype  # noqa: F401
-
         try:
             self.s = Series(tm.makeStringIndex(10 ** 5), dtype=dtype)
         except ImportError:

asv_bench/benchmarks/strings.py

@@ -12,7 +12,7 @@ dependencies:
 
   # pandas dependencies
   - pytz
-  - pip=20.2
+  - pip
   - pip:
     - cython==0.29.21 # GH#34014
     - "git+git://github.com/dateutil/dateutil.git"