Merge branch 'master' of https://github.com/pandas-dev/pandas into alexdev

Author: alexprincel

.github/actions/build_pandas/action.yml

@@ -0,0 +1,17 @@
+name: Build pandas
+description: Rebuilds the C extensions and installs pandas
+runs:
+  using: composite
+  steps:
+
+    - name: Environment Detail
+      run: |
+        conda info
+        conda list
+      shell: bash -l {0}
+
+    - name: Build Pandas
+      run: |
+        python setup.py build_ext -j 2
+        python -m pip install -e . --no-build-isolation --no-use-pep517
+      shell: bash -l {0}

.github/actions/setup/action.yml

@@ -0,0 +1,12 @@
+name: Set up pandas
+description: Runs all the setup steps required to have a built pandas ready to use
+runs:
+  using: composite
+  steps:
+    - name: Setting conda path
+      run: echo "${HOME}/miniconda3/bin" >> $GITHUB_PATH
+      shell: bash -l {0}
+
+    - name: Setup environment and build pandas
+      run: ci/setup_env.sh
+      shell: bash -l {0}

.github/workflows/ci.yml

@@ -41,15 +41,8 @@ jobs:
         environment-file: ${{ env.ENV_FILE }}
         use-only-tar-bz2: true
 
-    - name: Environment Detail
-      run: |
-        conda info
-        conda list
-
     - name: Build Pandas
-      run: |
-        python setup.py build_ext -j 2
-        python -m pip install -e . --no-build-isolation --no-use-pep517
+      uses: ./.github/actions/build_pandas
 
     - name: Linting
       run: ci/code_checks.sh lint
@@ -100,14 +93,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
 
-    - name: Setting conda path
-      run: echo "${HOME}/miniconda3/bin" >> $GITHUB_PATH
-
     - name: Checkout
       uses: actions/checkout@v1
 
-    - name: Setup environment and build pandas
-      run: ci/setup_env.sh
+    - name: Set up pandas
+      uses: ./.github/actions/setup
 
     - name: Build website
       run: |
@@ -139,19 +129,25 @@ jobs:
       run: rsync -az --delete doc/build/html/ docs@${{ secrets.server_ip }}:/usr/share/nginx/pandas/pandas-docs/dev
       if: github.event_name == 'push'
 
+    - name: Move docs into site directory
+      run: mv doc/build/html web/build/docs
+    - name: Save website as an artifact
+      uses: actions/upload-artifact@v2
+      with:
+        name: website
+        path: web/build
+        retention-days: 14
+
   data_manager:
     name: Test experimental data manager
     runs-on: ubuntu-latest
     steps:
 
-    - name: Setting conda path
-      run: echo "${HOME}/miniconda3/bin" >> $GITHUB_PATH
-
     - name: Checkout
       uses: actions/checkout@v1
 
-    - name: Setup environment and build pandas
-      run: ci/setup_env.sh
+    - name: Set up pandas
+      uses: ./.github/actions/setup
 
     - name: Run tests
       run: |

.github/workflows/database.yml

@@ -72,15 +72,8 @@ jobs:
         environment-file: ${{ env.ENV_FILE }}
         use-only-tar-bz2: true
 
-    - name: Environment Detail
-      run: |
-        conda info
-        conda list
-
     - name: Build Pandas
-      run: |
-        python setup.py build_ext -j 2
-        python -m pip install -e . --no-build-isolation --no-use-pep517
+      uses: ./.github/actions/build_pandas
 
     - name: Test
       run: ci/run_tests.sh
@@ -158,15 +151,8 @@ jobs:
         environment-file: ${{ env.ENV_FILE }}
         use-only-tar-bz2: true
 
-    - name: Environment Detail
-      run: |
-        conda info
-        conda list
-
     - name: Build Pandas
-      run: |
-        python setup.py build_ext -j 2
-        python -m pip install -e . --no-build-isolation --no-use-pep517
+      uses: ./.github/actions/build_pandas
 
     - name: Test
       run: ci/run_tests.sh

asv_bench/benchmarks/dtypes.py

@@ -2,9 +2,10 @@
 
 import numpy as np
 
+import pandas as pd
 from pandas import DataFrame
 import pandas._testing as tm
-from pandas.api.types import pandas_dtype
+from pandas.api.types import is_extension_array_dtype, pandas_dtype
 
 from .pandas_vb_common import (
     datetime_dtypes,
@@ -119,4 +120,16 @@ def time_select_dtype_string_exclude(self, dtype):
         self.df_string.select_dtypes(exclude=dtype)
 
 
+class CheckDtypes:
+    def setup(self):
+        self.ext_dtype = pd.Int64Dtype()
+        self.np_dtype = np.dtype("int64")
+
+    def time_is_extension_array_dtype_true(self):
+        is_extension_array_dtype(self.ext_dtype)
+
+    def time_is_extension_array_dtype_false(self):
+        is_extension_array_dtype(self.np_dtype)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/gil.py

@@ -1,7 +1,7 @@
 import numpy as np
 
 from pandas import DataFrame, Series, date_range, factorize, read_csv
-from pandas.core.algorithms import take_1d
+from pandas.core.algorithms import take_nd
 
 from .pandas_vb_common import tm
 
@@ -110,7 +110,7 @@ def setup(self, dtype):
 
         @test_parallel(num_threads=2)
         def parallel_take1d():
-            take_1d(df["col"].values, indexer)
+            take_nd(df["col"].values, indexer)
 
         self.parallel_take1d = parallel_take1d
 

doc/cheatsheet/Pandas_Cheat_Sheet.pdf

@@ -629,6 +629,17 @@ the documentation are also built by Travis-CI. These docs are then hosted `here
 <https://pandas.pydata.org/docs/dev/>`__, see also
 the :ref:`Continuous Integration <contributing.ci>` section.
 
+Previewing changes
+------------------
+
+Once, the pull request is submitted, GitHub Actions will automatically build the
+documentation. To view the built site:
+
+#. Wait for the ``CI / Web and docs`` check to complete.
+#. Click ``Details`` next to it.
+#. From the ``Artifacts`` drop-down, click ``docs`` or ``website`` to download
+   the site as a ZIP file.
+
 .. _contributing.code:
 
 Contributing to the code base

doc/cheatsheet/Pandas_Cheat_Sheet.pptx

@@ -31,7 +31,7 @@ namespace:
 * :func:`~pandas.option_context` - execute a codeblock with a set of options
   that revert to prior settings after execution.
 
-**Note:** Developers can check out `pandas/core/config.py <https://github.com/pandas-dev/pandas/blob/master/pandas/core/config.py>`_ for more information.
+**Note:** Developers can check out `pandas/core/config_init.py <https://github.com/pandas-dev/pandas/blob/master/pandas/core/config_init.py>`_ for more information.
 
 All of the functions above accept a regexp pattern (``re.search`` style) as an argument,
 and so passing in a substring will work - as long as it is unambiguous:

doc/source/development/contributing.rst

@@ -58,7 +58,7 @@ Other enhancements
 - :meth:`.Styler.apply` now more consistently accepts ndarray function returns, i.e. in all cases for ``axis`` is ``0, 1 or None``. (:issue:`39359`)
 - :meth:`Series.loc.__getitem__` and :meth:`Series.loc.__setitem__` with :class:`MultiIndex` now raising helpful error message when indexer has too many dimensions (:issue:`35349`)
 - :meth:`pandas.read_stata` and :class:`StataReader` support reading data from compressed files.
-
+- Add support for parsing ``ISO 8601``-like timestamps with negative signs to :meth:`pandas.Timedelta` (:issue:`37172`)
 
 .. ---------------------------------------------------------------------------
 
@@ -292,7 +292,7 @@ Timedelta
 ^^^^^^^^^
 - Bug in constructing :class:`Timedelta` from ``np.timedelta64`` objects with non-nanosecond units that are out of bounds for ``timedelta64[ns]`` (:issue:`38965`)
 - Bug in constructing a :class:`TimedeltaIndex` incorrectly accepting ``np.datetime64("NaT")`` objects (:issue:`39462`)
--
+- Bug in constructing :class:`Timedelta` from input string with only symbols and no digits failed to raise an error (:issue:`39710`)
 
 Timezones
 ^^^^^^^^^
@@ -335,6 +335,7 @@ Indexing
 - Bug in :meth:`DataFrame.__setitem__` raising ``ValueError`` when setting multiple values to duplicate columns (:issue:`15695`)
 - Bug in :meth:`DataFrame.loc`, :meth:`Series.loc`, :meth:`DataFrame.__getitem__` and :meth:`Series.__getitem__` returning incorrect elements for non-monotonic :class:`DatetimeIndex` for string slices (:issue:`33146`)
 - Bug in :meth:`DataFrame.reindex` and :meth:`Series.reindex` with timezone aware indexes raising ``TypeError`` for ``method="ffill"`` and ``method="bfill"`` and specified ``tolerance`` (:issue:`38566`)
+- Bug in :meth:`DataFrame.reindex` with ``datetime64[ns]`` or ``timedelta64[ns]`` incorrectly casting to integers when the ``fill_value`` requires casting to object dtype (:issue:`39755`)
 - Bug in :meth:`DataFrame.__setitem__` raising ``ValueError`` with empty :class:`DataFrame` and specified columns for string indexer and non empty :class:`DataFrame` to set (:issue:`38831`)
 - Bug in :meth:`DataFrame.loc.__setitem__` raising ValueError when expanding unique column for :class:`DataFrame` with duplicate columns (:issue:`38521`)
 - Bug in :meth:`DataFrame.iloc.__setitem__` and :meth:`DataFrame.loc.__setitem__` with mixed dtypes when setting with a dictionary value (:issue:`38335`)
@@ -450,11 +451,13 @@ Other
 - Bug in constructing a :class:`Series` from a list and a :class:`PandasDtype` (:issue:`39357`)
 - Bug in :class:`Styler` which caused CSS to duplicate on multiple renders. (:issue:`39395`)
 - ``inspect.getmembers(Series)`` no longer raises an ``AbstractMethodError`` (:issue:`38782`)
+- Bug in :meth:`Series.where` with numeric dtype and ``other = None`` not casting to ``nan`` (:issue:`39761`)
 - :meth:`Index.where` behavior now mirrors :meth:`Index.putmask` behavior, i.e. ``index.where(mask, other)`` matches ``index.putmask(~mask, other)`` (:issue:`39412`)
 - Bug in :func:`pandas.testing.assert_series_equal`, :func:`pandas.testing.assert_frame_equal`, :func:`pandas.testing.assert_index_equal` and :func:`pandas.testing.assert_extension_array_equal` incorrectly raising when an attribute has an unrecognized NA type (:issue:`39461`)
 - Bug in :class:`Styler` where ``subset`` arg in methods raised an error for some valid multiindex slices (:issue:`33562`)
 - :class:`Styler` rendered HTML output minor alterations to support w3 good code standard (:issue:`39626`)
--
+- Bug in :meth:`DataFrame.equals`, :meth:`Series.equals`, :meth:`Index.equals` with object-dtype containing ``np.datetime64("NaT")`` or ``np.timedelta64("NaT")`` (:issue:`39650`)
+
 
 .. ---------------------------------------------------------------------------
 

doc/source/user_guide/options.rst

@@ -4,12 +4,13 @@
 
 import locale
 import sys
+from typing import Optional
 
 from pandas._config import config as cf
 
 # -----------------------------------------------------------------------------
 # Global formatting options
-_initial_defencoding = None
+_initial_defencoding: Optional[str] = None
 
 
 def detect_console_encoding() -> str:

doc/source/whatsnew/v1.3.0.rst

@@ -73,6 +73,7 @@ from pandas._libs.tslib import array_to_datetime
 from pandas._libs.missing cimport (
     C_NA,
     checknull,
+    is_matching_na,
     is_null_datetime64,
     is_null_timedelta64,
     isnaobj,
@@ -584,8 +585,10 @@ def array_equivalent_object(left: object[:], right: object[:]) -> bool:
                     return False
             elif (x is C_NA) ^ (y is C_NA):
                 return False
-            elif not (PyObject_RichCompareBool(x, y, Py_EQ) or
-                      (x is None or is_nan(x)) and (y is None or is_nan(y))):
+            elif not (
+                PyObject_RichCompareBool(x, y, Py_EQ)
+                or is_matching_na(x, y, nan_matches_none=True)
+            ):
                 return False
         except ValueError:
             # Avoid raising ValueError when comparing Numpy arrays to other types

pandas/_config/display.py

@@ -1,6 +1,8 @@
 from numpy cimport ndarray, uint8_t
 
 
+cpdef bint is_matching_na(object left, object right, bint nan_matches_none=*)
+
 cpdef bint checknull(object val)
 cpdef bint checknull_old(object val)
 cpdef ndarray[uint8_t] isnaobj(ndarray arr)

pandas/_libs/lib.pyx

@@ -29,6 +29,58 @@ cdef:
     bint is_32bit = not IS64
 
 
+cpdef bint is_matching_na(object left, object right, bint nan_matches_none=False):
+    """
+    Check if two scalars are both NA of matching types.
+
+    Parameters
+    ----------
+    left : Any
+    right : Any
+    nan_matches_none : bool, default False
+        For backwards compatibility, consider NaN as matching None.
+
+    Returns
+    -------
+    bool
+    """
+    if left is None:
+        if nan_matches_none and util.is_nan(right):
+            return True
+        return right is None
+    elif left is C_NA:
+        return right is C_NA
+    elif left is NaT:
+        return right is NaT
+    elif util.is_float_object(left):
+        if nan_matches_none and right is None:
+            return True
+        return (
+            util.is_nan(left)
+            and util.is_float_object(right)
+            and util.is_nan(right)
+        )
+    elif util.is_complex_object(left):
+        return (
+            util.is_nan(left)
+            and util.is_complex_object(right)
+            and util.is_nan(right)
+        )
+    elif util.is_datetime64_object(left):
+        return (
+            get_datetime64_value(left) == NPY_NAT
+            and util.is_datetime64_object(right)
+            and get_datetime64_value(right) == NPY_NAT
+        )
+    elif util.is_timedelta64_object(left):
+        return (
+            get_timedelta64_value(left) == NPY_NAT
+            and util.is_timedelta64_object(right)
+            and get_timedelta64_value(right) == NPY_NAT
+        )
+    return False
+
+
 cpdef bint checknull(object val):
     """
     Return boolean describing of the input is NA-like, defined here as any