Merge remote-tracking branch 'upstream/master' into allow-special-characters-query

Author: hwalinga

asv_bench/benchmarks/index_object.py

@@ -7,6 +7,7 @@
     Float64Index,
     Index,
     IntervalIndex,
+    MultiIndex,
     RangeIndex,
     Series,
     date_range,
@@ -111,6 +112,18 @@ def time_get_loc_dec(self):
         self.idx_dec.get_loc(100000)
 
 
+class IndexEquals:
+    def setup(self):
+        idx_large_fast = RangeIndex(100000)
+        idx_small_slow = date_range(start="1/1/2012", periods=1)
+        self.mi_large_slow = MultiIndex.from_product([idx_large_fast, idx_small_slow])
+
+        self.idx_non_object = RangeIndex(1)
+
+    def time_non_object_equals_multiindex(self):
+        self.idx_non_object.equals(self.mi_large_slow)
+
+
 class IndexAppend:
     def setup(self):
 

asv_bench/benchmarks/multiindex_object.py

@@ -2,7 +2,7 @@
 
 import numpy as np
 
-from pandas import DataFrame, MultiIndex, date_range
+from pandas import DataFrame, MultiIndex, RangeIndex, date_range
 import pandas.util.testing as tm
 
 
@@ -147,4 +147,16 @@ def time_categorical_level(self):
         self.df.set_index(["a", "b"])
 
 
+class Equals:
+    def setup(self):
+        idx_large_fast = RangeIndex(100000)
+        idx_small_slow = date_range(start="1/1/2012", periods=1)
+        self.mi_large_slow = MultiIndex.from_product([idx_large_fast, idx_small_slow])
+
+        self.idx_non_object = RangeIndex(1)
+
+    def time_equals_non_object_index(self):
+        self.mi_large_slow.equals(self.idx_non_object)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

ci/azure/posix.yml

@@ -20,14 +20,14 @@ jobs:
           CONDA_PY: "36"
           PATTERN: "not slow and not network"
         py36_locale_slow_old_np:
-          ENV_FILE: ci/deps/azure-36-locale.yaml
+          ENV_FILE: ci/deps/azure-36-locale_slow.yaml
           CONDA_PY: "36"
           PATTERN: "slow"
           LOCALE_OVERRIDE: "zh_CN.UTF-8"
           EXTRA_APT: "language-pack-zh-hans"
 
-        py36_locale_slow:
-          ENV_FILE: ci/deps/azure-36-locale_slow.yaml
+        py36_locale:
+          ENV_FILE: ci/deps/azure-36-locale.yaml
           CONDA_PY: "36"
           PATTERN: "not slow and not network"
           LOCALE_OVERRIDE: "it_IT.UTF-8"

ci/code_checks.sh

@@ -105,7 +105,12 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
 
     # Imports - Check formatting using isort see setup.cfg for settings
     MSG='Check import format using isort ' ; echo $MSG
-    isort --recursive --check-only pandas asv_bench
+    ISORT_CMD="isort --recursive --check-only pandas asv_bench"
+    if [[ "$GITHUB_ACTIONS" == "true" ]]; then
+        eval $ISORT_CMD | awk '{print "##[error]" $0}'; RET=$(($RET + ${PIPESTATUS[0]}))
+    else
+        eval $ISORT_CMD
+    fi
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

ci/deps/azure-36-locale.yaml

@@ -13,23 +13,27 @@ dependencies:
   - pytest-azurepipelines
 
   # pandas dependencies
-  - beautifulsoup4==4.6.0
-  - bottleneck=1.2.*
+  - beautifulsoup4
+  - gcsfs
+  - html5lib
+  - ipython
+  - jinja2
   - lxml
-  - matplotlib=2.2.2
-  - numpy=1.14.*
-  - openpyxl=2.4.8
-  - python-dateutil
-  - python-blosc
-  - pytz=2017.2
-  - scipy
-  - sqlalchemy=1.1.4
-  - xlrd=1.1.0
-  - xlsxwriter=0.9.8
-  - xlwt=1.2.0
+  - matplotlib=3.0.*
+  - nomkl
+  - numexpr
+  - numpy=1.15.*
+  - openpyxl
   # lowest supported version of pyarrow (putting it here instead of in
   # azure-36-minimum_versions because it needs numpy >= 1.14)
   - pyarrow=0.12
-  - pip
-  - pip:
-    - html5lib==1.0b2
+  - pytables
+  - python-dateutil
+  - pytz
+  - s3fs
+  - scipy
+  - xarray
+  - xlrd
+  - xlsxwriter
+  - xlwt
+  - moto

ci/deps/azure-36-locale_slow.yaml

@@ -13,24 +13,20 @@ dependencies:
   - pytest-azurepipelines
 
   # pandas dependencies
-  - beautifulsoup4
-  - gcsfs
-  - html5lib
-  - ipython
-  - jinja2
+  - beautifulsoup4==4.6.0
+  - bottleneck=1.2.*
   - lxml
-  - matplotlib=3.0.*
-  - nomkl
-  - numexpr
-  - numpy=1.15.*
-  - openpyxl
-  - pytables
+  - matplotlib=2.2.2
+  - numpy=1.14.*
+  - openpyxl=2.4.8
   - python-dateutil
-  - pytz
-  - s3fs
+  - python-blosc
+  - pytz=2017.2
   - scipy
-  - xarray
-  - xlrd
-  - xlsxwriter
-  - xlwt
-  - moto
+  - sqlalchemy=1.1.4
+  - xlrd=1.1.0
+  - xlsxwriter=0.9.8
+  - xlwt=1.2.0
+  - pip
+  - pip:
+    - html5lib==1.0b2

doc/redirects.csv

@@ -319,7 +319,6 @@ generated/pandas.DataFrame.clip_upper,../reference/api/pandas.DataFrame.clip_upp
 generated/pandas.DataFrame.columns,../reference/api/pandas.DataFrame.columns
 generated/pandas.DataFrame.combine_first,../reference/api/pandas.DataFrame.combine_first
 generated/pandas.DataFrame.combine,../reference/api/pandas.DataFrame.combine
-generated/pandas.DataFrame.compound,../reference/api/pandas.DataFrame.compound
 generated/pandas.DataFrame.convert_objects,../reference/api/pandas.DataFrame.convert_objects
 generated/pandas.DataFrame.copy,../reference/api/pandas.DataFrame.copy
 generated/pandas.DataFrame.corr,../reference/api/pandas.DataFrame.corr
@@ -950,7 +949,6 @@ generated/pandas.Series.clip_lower,../reference/api/pandas.Series.clip_lower
 generated/pandas.Series.clip_upper,../reference/api/pandas.Series.clip_upper
 generated/pandas.Series.combine_first,../reference/api/pandas.Series.combine_first
 generated/pandas.Series.combine,../reference/api/pandas.Series.combine
-generated/pandas.Series.compound,../reference/api/pandas.Series.compound
 generated/pandas.Series.compress,../reference/api/pandas.Series.compress
 generated/pandas.Series.convert_objects,../reference/api/pandas.Series.convert_objects
 generated/pandas.Series.copy,../reference/api/pandas.Series.copy

doc/source/getting_started/10min.rst

@@ -75,8 +75,8 @@ will be completed:
    df2.all                df2.columns
    df2.any                df2.combine
    df2.append             df2.combine_first
-   df2.apply              df2.compound
-   df2.applymap           df2.consolidate
+   df2.apply              df2.consolidate
+   df2.applymap
    df2.D
 
 As you can see, the columns ``A``, ``B``, ``C``, and ``D`` are automatically

doc/source/reference/frame.rst

@@ -137,7 +137,6 @@ Computations / descriptive stats
    DataFrame.all
    DataFrame.any
    DataFrame.clip
-   DataFrame.compound
    DataFrame.corr
    DataFrame.corrwith
    DataFrame.count

doc/source/reference/series.rst

@@ -174,7 +174,6 @@ Computations / descriptive stats
    Series.is_monotonic_increasing
    Series.is_monotonic_decreasing
    Series.value_counts
-   Series.compound
 
 Reindexing / selection / label manipulation
 -------------------------------------------

doc/source/user_guide/missing_data.rst

@@ -190,15 +190,15 @@ The sum of an empty or all-NA Series or column of a DataFrame is 0.
 
    pd.Series([np.nan]).sum()
 
-   pd.Series([]).sum()
+   pd.Series([], dtype="float64").sum()
 
 The product of an empty or all-NA Series or column of a DataFrame is 1.
 
 .. ipython:: python
 
    pd.Series([np.nan]).prod()
 
-   pd.Series([]).prod()
+   pd.Series([], dtype="float64").prod()
 
 
 NA values in GroupBy

doc/source/user_guide/scale.rst

@@ -358,6 +358,7 @@ results will fit in memory, so we can safely call ``compute`` without running
 out of memory. At that point it's just a regular pandas object.
 
 .. ipython:: python
+   :okwarning:
 
    @savefig dask_resample.png
    ddf[['x', 'y']].resample("1D").mean().cumsum().compute().plot()

doc/source/whatsnew/v0.19.0.rst

@@ -707,6 +707,7 @@ A ``Series`` will now correctly promote its dtype for assignment with incompat v
 
 
 .. ipython:: python
+   :okwarning:
 
    s = pd.Series()
 

doc/source/whatsnew/v0.21.0.rst

@@ -428,6 +428,7 @@ Note that this also changes the sum of an empty ``Series``. Previously this alwa
 but for consistency with the all-NaN case, this was changed to return NaN as well:
 
 .. ipython:: python
+   :okwarning:
 
    pd.Series([]).sum()
 

doc/source/whatsnew/v0.22.0.rst

@@ -55,6 +55,7 @@ The default sum for empty or all-*NA* ``Series`` is now ``0``.
 *pandas 0.22.0*
 
 .. ipython:: python
+   :okwarning:
 
    pd.Series([]).sum()
    pd.Series([np.nan]).sum()
@@ -67,6 +68,7 @@ pandas 0.20.3 without bottleneck, or pandas 0.21.x), use the ``min_count``
 keyword.
 
 .. ipython:: python
+   :okwarning:
 
    pd.Series([]).sum(min_count=1)
 
@@ -85,6 +87,7 @@ required for a non-NA sum or product.
 returning ``1`` instead.
 
 .. ipython:: python
+   :okwarning:
 
    pd.Series([]).prod()
    pd.Series([np.nan]).prod()

doc/source/whatsnew/v1.0.0.rst

@@ -366,6 +366,23 @@ When :class:`Categorical` contains ``np.nan``,
 
    pd.Categorical([1, 2, np.nan], ordered=True).min()
 
+
+Default dtype of empty :class:`pandas.Series`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Initialising an empty :class:`pandas.Series` without specifying a dtype will raise a `DeprecationWarning` now
+(:issue:`17261`). The default dtype will change from ``float64`` to ``object`` in future releases so that it is
+consistent with the behaviour of :class:`DataFrame` and :class:`Index`.
+
+*pandas 1.0.0*
+
+.. code-block:: ipython
+
+   In [1]: pd.Series()
+   Out[2]:
+   DeprecationWarning: The default dtype for empty Series will be 'object' instead of 'float64' in a future version. Specify a dtype explicitly to silence this warning.
+   Series([], dtype: float64)
+
 .. _whatsnew_1000.api_breaking.deps:
 
 Increased minimum versions for dependencies
@@ -494,7 +511,7 @@ Removal of prior version deprecations/changes
 
 Previously, pandas would register converters with matplotlib as a side effect of importing pandas (:issue:`18720`).
 This changed the output of plots made via matplotlib plots after pandas was imported, even if you were using
-matplotlib directly rather than rather than :meth:`~DataFrame.plot`.
+matplotlib directly rather than :meth:`~DataFrame.plot`.
 
 To use pandas formatters with a matplotlib plot, specify
 
@@ -518,11 +535,13 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - Removed the previously deprecated :meth:`Index.summary` (:issue:`18217`)
 - Removed the previously deprecated "fastpath" keyword from the :class:`Index` constructor (:issue:`23110`)
 - Removed the previously deprecated :meth:`Series.get_value`, :meth:`Series.set_value`, :meth:`DataFrame.get_value`, :meth:`DataFrame.set_value` (:issue:`17739`)
+- Removed the previously deprecated :meth:`Series.compound` and :meth:`DataFrame.compound` (:issue:`26405`)
 - Changed the the default value of `inplace` in :meth:`DataFrame.set_index` and :meth:`Series.set_axis`. It now defaults to ``False`` (:issue:`27600`)
 - Removed the previously deprecated :attr:`Series.cat.categorical`, :attr:`Series.cat.index`, :attr:`Series.cat.name` (:issue:`24751`)
 - Removed the previously deprecated ``time_rule`` keyword from (non-public) :func:`offsets.generate_range`, which has been moved to :func:`core.arrays._ranges.generate_range` (:issue:`24157`)
 - :meth:`DataFrame.loc` or :meth:`Series.loc` with listlike indexers and missing labels will no longer reindex (:issue:`17295`)
 - :meth:`DataFrame.to_excel` and :meth:`Series.to_excel` with non-existent columns will no longer reindex (:issue:`17295`)
+- :func:`concat` parameter "join_axes" has been removed, use ``reindex_like`` on the result instead (:issue:`22318`)
 - Removed the previously deprecated "by" keyword from :meth:`DataFrame.sort_index`, use :meth:`DataFrame.sort_values` instead (:issue:`10726`)
 - Removed support for nested renaming in :meth:`DataFrame.aggregate`, :meth:`Series.aggregate`, :meth:`DataFrameGroupBy.aggregate`, :meth:`SeriesGroupBy.aggregate`, :meth:`Rolling.aggregate` (:issue:`18529`)
 - Passing ``datetime64`` data to :class:`TimedeltaIndex` or ``timedelta64`` data to ``DatetimeIndex`` now raises ``TypeError`` (:issue:`23539`, :issue:`23937`)
@@ -585,6 +604,7 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - Removed the previously deprecated :meth:`Series.to_dense`, :meth:`DataFrame.to_dense` (:issue:`26684`)
 - Removed the previously deprecated :meth:`Index.dtype_str`, use ``str(index.dtype)`` instead (:issue:`27106`)
 - :meth:`Categorical.ravel` returns a :class:`Categorical` instead of a ``ndarray`` (:issue:`27199`)
+- The 'outer' method on Numpy ufuncs, e.g. ``np.subtract.outer`` operating on :class:`Series` objects is no longer supported, and will raise ``NotImplementedError`` (:issue:`27198`)
 - Removed previously deprecated :meth:`Series.get_dtype_counts` and :meth:`DataFrame.get_dtype_counts` (:issue:`27145`)
 - Changed the default ``fill_value`` in :meth:`Categorical.take` from ``True`` to ``False`` (:issue:`20841`)
 - Changed the default value for the `raw` argument in :func:`Series.rolling().apply() <pandas.core.window.Rolling.apply>`, :func:`DataFrame.rolling().apply() <pandas.core.window.Rolling.apply>`,
@@ -594,6 +614,7 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - Changed :meth:`Timedelta.resolution` to match the behavior of the standard library ``datetime.timedelta.resolution``, for the old behavior, use :meth:`Timedelta.resolution_string` (:issue:`26839`)
 - Removed previously deprecated :attr:`Timestamp.weekday_name`, :attr:`DatetimeIndex.weekday_name`, and :attr:`Series.dt.weekday_name` (:issue:`18164`)
 - Removed previously deprecated ``errors`` argument in :meth:`Timestamp.tz_localize`, :meth:`DatetimeIndex.tz_localize`, and :meth:`Series.tz_localize` (:issue:`22644`)
+- :meth:`Series.set_axis` and :meth:`DataFrame.set_axis` now require "labels" as the first argument and "axis" as an optional named parameter (:issue:`30089`)
 -
 
 .. _whatsnew_1000.performance:
@@ -611,6 +632,7 @@ Performance improvements
 - Performance improvement when comparing a :class:`Categorical` with a scalar and the scalar is not found in the categories (:issue:`29750`)
 - Performance improvement when checking if values in a :class:`Categorical` are equal, equal or larger or larger than a given scalar.
   The improvement is not present if checking if the :class:`Categorical` is less than or less than or equal than the scalar (:issue:`29820`)
+- Performance improvement in :meth:`Index.equals` and  :meth:`MultiIndex.equals` (:issue:`29134`)
 
 .. _whatsnew_1000.bug_fixes:
 

pandas/compat/pickle_compat.py

@@ -64,7 +64,7 @@ def __new__(cls) -> "Series":  # type: ignore
             stacklevel=6,
         )
 
-        return Series()
+        return Series(dtype=object)
 
 
 class _LoadSparseFrame: