Merge remote-tracking branch 'upstream/master' into parser-cleanup

Author: WillAyd

.travis.yml

@@ -86,6 +86,14 @@ install:
   - ci/submit_cython_cache.sh
   - echo "install done"
 
+before_script:
+  # display server (for clipboard functionality) needs to be started here,
+  # does not work if done in install:setup_env.sh (GH-26103)
+  - export DISPLAY=":99.0"
+  - echo "sh -e /etc/init.d/xvfb start"
+  - sh -e /etc/init.d/xvfb start
+  - sleep 3
+
 script:
   - echo "script start"
   - source activate pandas-dev

ci/azure/windows.yml

@@ -19,10 +19,13 @@ jobs:
   steps:
     - powershell: Write-Host "##vso[task.prependpath]$env:CONDA\Scripts"
       displayName: Add conda to PATH
-    - script: conda env create --file ci\\deps\\azure-windows-$(CONDA_PY).yaml
+    - script: conda update -q -n base conda
+      displayName: Update conda
+    - script: conda env create -q --file ci\\deps\\azure-windows-$(CONDA_PY).yaml
       displayName: Create anaconda environment
     - script: |
         call activate pandas-dev
+        call conda list
         ci\\incremental\\build.cmd
       displayName: 'Build'
     - script: |

ci/code_checks.sh

@@ -169,15 +169,6 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     invgrep -r -E --include '*.py' '(unittest(\.| import )mock|mock\.Mock\(\)|mock\.patch)' pandas/tests/
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
-    # Check that we use pytest.raises only as a context manager
-    #
-    # For any flake8-compliant code, the only way this regex gets
-    # matched is if there is no "with" statement preceding "pytest.raises"
-    MSG='Check for pytest.raises as context manager (a line starting with `pytest.raises` is invalid, needs a `with` to precede it)' ; echo $MSG
-    MSG='TODO: This check is currently skipped because so many files fail this. Please enable when all are corrected (xref gh-24332)' ; echo $MSG
-    # invgrep -R --include '*.py' -E '[[:space:]] pytest.raises' pandas/tests
-    # RET=$(($RET + $?)) ; echo $MSG "DONE"
-
     MSG='Check for wrong space after code-block directive and before colon (".. code-block ::" instead of ".. code-block::")' ; echo $MSG
     invgrep -R --include="*.rst" ".. code-block ::" doc/source
     RET=$(($RET + $?)) ; echo $MSG "DONE"

ci/deps/azure-windows-37.yaml

@@ -1,9 +1,11 @@
 name: pandas-dev
 channels:
   - defaults
+  - conda-forge
 dependencies:
   - beautifulsoup4
   - bottleneck
+  - gcsfs
   - html5lib
   - jinja2
   - lxml

ci/setup_env.sh

@@ -118,16 +118,10 @@ echo "conda list"
 conda list
 
 # Install DB for Linux
-export DISPLAY=":99."
 if [ ${TRAVIS_OS_NAME} == "linux" ]; then
   echo "installing dbs"
   mysql -e 'create database pandas_nosetest;'
   psql -c 'create database pandas_nosetest;' -U postgres
-
-  echo
-  echo "sh -e /etc/init.d/xvfb start"
-  sh -e /etc/init.d/xvfb start
-  sleep 3
 else
    echo "not using dbs on non-linux"
 fi

doc/source/ecosystem.rst

@@ -285,6 +285,11 @@ provides a familiar ``DataFrame`` interface for out-of-core, parallel and distri
 
 Dask-ML enables parallel and distributed machine learning using Dask alongside existing machine learning libraries like Scikit-Learn, XGBoost, and TensorFlow.
 
+`Koalas <https://koalas.readthedocs.io/en/latest/>`__
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Koalas provides a familiar pandas DataFrame interface on top of Apache Spark. It enables users to leverage multi-cores on one machine or a cluster of machines to speed up or scale their DataFrame code.
+
 `Odo <http://odo.pydata.org>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

doc/source/user_guide/computation.rst

@@ -865,7 +865,7 @@ which is equivalent to using weights
 
 The difference between the above two variants arises because we are
 dealing with series which have finite history. Consider a series of infinite
-history:
+history, with ``adjust=True``:
 
 .. math::
 
@@ -884,10 +884,11 @@ and a ratio of :math:`1 - \alpha` we have
     &= \alpha x_t + (1 - \alpha)[x_{t-1} + (1 - \alpha) x_{t-2} + ...]\alpha\\
     &= \alpha x_t + (1 - \alpha) y_{t-1}
 
-which shows the equivalence of the above two variants for infinite series.
-When ``adjust=True`` we have :math:`y_0 = x_0` and from the last
-representation above we have :math:`y_t = \alpha x_t + (1 - \alpha) y_{t-1}`,
-therefore there is an assumption that :math:`x_0` is not an ordinary value
+which is the same expression as ``adjust=False`` above and therefore
+shows the equivalence of the two variants for infinite series.
+When ``adjust=False``, we have :math:`y_0 = x_0` and
+:math:`y_t = \alpha x_t + (1 - \alpha) y_{t-1}`.
+Therefore, there is an assumption that :math:`x_0` is not an ordinary value
 but rather an exponentially weighted moment of the infinite series up to that
 point.
 

doc/source/whatsnew/v0.11.0.rst

@@ -238,14 +238,9 @@ Enhancements
 
     - support ``read_hdf/to_hdf`` API similar to ``read_csv/to_csv``
 
-      .. ipython:: python
-          :suppress:
-
-          from pandas.compat import lrange
-
       .. ipython:: python
 
-          df = pd.DataFrame({'A': lrange(5), 'B': lrange(5)})
+          df = pd.DataFrame({'A': range(5), 'B': range(5)})
           df.to_hdf('store.h5', 'table', append=True)
           pd.read_hdf('store.h5', 'table', where=['index > 2'])
 

doc/source/whatsnew/v0.12.0.rst

@@ -83,13 +83,8 @@ API changes
     ``iloc`` API to be *purely* positional based.
 
     .. ipython:: python
-       :suppress:
 
-       from pandas.compat import lrange
-
-    .. ipython:: python
-
-       df = pd.DataFrame(lrange(5), list('ABCDE'), columns=['a'])
+       df = pd.DataFrame(range(5), index=list('ABCDE'), columns=['a'])
        mask = (df.a % 2 == 0)
        mask
 

doc/source/whatsnew/v0.25.0.rst

@@ -249,6 +249,7 @@ Other API Changes
 - Comparing :class:`Timestamp` with unsupported objects now returns :py:obj:`NotImplemented` instead of raising ``TypeError``. This implies that unsupported rich comparisons are delegated to the other object, and are now consistent with Python 3 behavior for ``datetime`` objects (:issue:`24011`)
 - Bug in :meth:`DatetimeIndex.snap` which didn't preserving the ``name`` of the input :class:`Index` (:issue:`25575`)
 - The ``arg`` argument in :meth:`pandas.core.groupby.DataFrameGroupBy.agg` has been renamed to ``func`` (:issue:`26089`)
+- The ``arg`` argument in :meth:`pandas.core.window._Window.aggregate` has been renamed to ``func`` (:issue:`26372`)
 
 .. _whatsnew_0250.deprecations:
 
@@ -257,6 +258,8 @@ Deprecations
 
 - Deprecated the ``units=M`` (months) and ``units=Y`` (year) parameters for ``units`` of :func:`pandas.to_timedelta`, :func:`pandas.Timedelta` and :func:`pandas.TimedeltaIndex` (:issue:`16344`)
 - The functions :func:`pandas.to_datetime` and :func:`pandas.to_timedelta` have deprecated the ``box`` keyword. Instead, use :meth:`to_numpy` or :meth:`Timestamp.to_datetime64` or :meth:`Timedelta.to_timedelta64`. (:issue:`24416`)
+- The :meth:`DataFrame.compound` and :meth:`Series.compound` methods are deprecated and will be removed in a future version.
+
 
 .. _whatsnew_0250.prior_deprecations:
 
@@ -317,7 +320,7 @@ Timedelta
 
 - Bug in :func:`TimedeltaIndex.intersection` where for non-monotonic indices in some cases an empty ``Index`` was returned when in fact an intersection existed (:issue:`25913`)
 - Bug with comparisons between :class:`Timedelta` and ``NaT`` raising ``TypeError`` (:issue:`26039`)
--
+- Bug when adding or subtracting a :class:`BusinessHour` to a :class:`Timestamp` with the resulting time landing in a following or prior day respectively (:issue:`26381`)
 
 Timezones
 ^^^^^^^^^
@@ -373,7 +376,7 @@ Indexing
 - Improved exception message when calling :meth:`DataFrame.iloc` with a list of non-numeric objects (:issue:`25753`).
 - Bug in :meth:`DataFrame.loc` and :meth:`Series.loc` where ``KeyError`` was not raised for a ``MultiIndex`` when the key was less than or equal to the number of levels in the :class:`MultiIndex` (:issue:`14885`).
 - Bug in which :meth:`DataFrame.append` produced an erroneous warning indicating that a ``KeyError`` will be thrown in the future when the data to be appended contains new columns (:issue:`22252`).
--
+- Bug in which :meth:`DataFrame.to_csv` caused a segfault for a reindexed data frame, when the indices were single-level :class:`MultiIndex` (:issue:`26303`).
 
 
 Missing
@@ -441,6 +444,7 @@ Groupby/Resample/Rolling
 - Bug in :meth:`pandas.core.groupby.GroupBy.cumsum`, :meth:`pandas.core.groupby.GroupBy.cumprod`, :meth:`pandas.core.groupby.GroupBy.cummin` and :meth:`pandas.core.groupby.GroupBy.cummax` with categorical column having absent categories, would return incorrect result or segfault (:issue:`16771`)
 - Bug in :meth:`pandas.core.groupby.GroupBy.nth` where NA values in the grouping would return incorrect results (:issue:`26011`)
 - Bug in :meth:`pandas.core.groupby.SeriesGroupBy.transform` where transforming an empty group would raise error (:issue:`26208`)
+- Bug in :meth:`pandas.core.groupby.GroupBy.agg` where incorrect results are returned for uint64 columns. (:issue:`26310`)
 
 
 Reshaping

mypy.ini

@@ -15,43 +15,4 @@ ignore_errors=True
 ignore_errors=True
 
 [mypy-pandas.core.indexes.timedeltas]
-ignore_errors=True
-
-[mypy-pandas.core.indexing]
-ignore_errors=True
-
-[mypy-pandas.core.internals.blocks]
-ignore_errors=True
-
-[mypy-pandas.core.ops]
-ignore_errors=True
-
-[mypy-pandas.core.panel]
-ignore_errors=True
-
-[mypy-pandas.core.resample]
-ignore_errors=True
-
-[mypy-pandas.core.reshape.merge]
-ignore_errors=True
-
-[mypy-pandas.core.reshape.reshape]
-ignore_errors=True
-
-[mypy-pandas.core.series]
-ignore_errors=True
-
-[mypy-pandas.core.util.hashing]
-ignore_errors=True
-
-[mypy-pandas.core.window]
-ignore_errors=True
-
-[mypy-pandas.io.pytables]
-ignore_errors=True
-
-[mypy-pandas.util._doctools]
-ignore_errors=True
-
-[mypy-pandas.util.testing]
-ignore_errors=True
+ignore_errors=True

pandas/_libs/tslibs/period.pyx

@@ -2208,10 +2208,6 @@ cdef class _Period:
     def now(cls, freq=None):
         return Period(datetime.now(), freq=freq)
 
-    # HACK IT UP AND YOU BETTER FIX IT SOON
-    def __str__(self):
-        return self.__unicode__()
-
     @property
     def freqstr(self):
         return self.freq.freqstr
@@ -2221,9 +2217,9 @@ cdef class _Period:
         formatted = period_format(self.ordinal, base)
         return "Period('%s', '%s')" % (formatted, self.freqstr)
 
-    def __unicode__(self):
+    def __str__(self):
         """
-        Return a unicode string representation for a particular DataFrame
+        Return a string representation for a particular DataFrame
         """
         base, mult = get_freq_code(self.freq)
         formatted = period_format(self.ordinal, base)

pandas/core/arrays/categorical.py

@@ -2022,9 +2022,9 @@ def _get_repr(self, length=True, na_rep='NaN', footer=True):
         result = formatter.to_string()
         return str(result)
 
-    def __unicode__(self):
+    def __str__(self):
         """
-        Unicode representation.
+        String representation.
         """
         _maxlen = 10
         if len(self._codes) > _maxlen:

pandas/core/arrays/sparse.py

@@ -1823,7 +1823,7 @@ def _add_comparison_ops(cls):
     # ----------
     # Formatting
     # -----------
-    def __unicode__(self):
+    def __str__(self):
         return '{self}\nFill: {fill}\n{index}'.format(
             self=printing.pprint_thing(self),
             fill=printing.pprint_thing(self.fill_value),

pandas/core/base.py

@@ -34,31 +34,28 @@
 
 class StringMixin:
     """
-    Implements string methods so long as object defines a `__unicode__` method.
+    Implements string methods so long as object defines a `__str__` method.
     """
     # side note - this could be made into a metaclass if more than one
     #             object needs
 
     # ----------------------------------------------------------------------
     # Formatting
 
-    def __unicode__(self):
-        raise AbstractMethodError(self)
-
     def __str__(self):
         """
         Return a string representation for a particular Object
         """
-        return self.__unicode__()
+        raise AbstractMethodError(self)
 
     def __bytes__(self):
         """
-        Return a string representation for a particular object.
+        Return a bytes representation for a particular object.
         """
         from pandas._config import get_option
 
         encoding = get_option("display.encoding")
-        return self.__unicode__().encode(encoding, 'replace')
+        return str(self).encode(encoding, 'replace')
 
     def __repr__(self):
         """
@@ -76,7 +73,7 @@ def _constructor(self):
         """class constructor (for this class it's just `__class__`"""
         return self.__class__
 
-    def __unicode__(self):
+    def __str__(self):
         """
         Return a string representation for a particular object.
         """
@@ -1572,5 +1569,5 @@ def duplicated(self, keep='first'):
     # ----------------------------------------------------------------------
     # abstracts
 
-    def _update_inplace(self, result, **kwargs):
+    def _update_inplace(self, result, verify_is_copy=True, **kwargs):
         raise AbstractMethodError(self)

pandas/core/computation/expr.py

@@ -734,7 +734,7 @@ def assigner(self):
     def __call__(self):
         return self.terms(self.env)
 
-    def __unicode__(self):
+    def __str__(self):
         return printing.pprint_thing(self.terms)
 
     def __len__(self):

pandas/core/computation/ops.py

@@ -67,7 +67,7 @@ def __init__(self, name, env, side=None, encoding=None):
     def local_name(self):
         return self.name.replace(_LOCAL_TAG, '')
 
-    def __unicode__(self):
+    def __str__(self):
         return pprint_thing(self.name)
 
     def __call__(self, *args, **kwargs):
@@ -166,7 +166,7 @@ def _resolve_name(self):
     def name(self):
         return self.value
 
-    def __unicode__(self):
+    def __str__(self):
         # in python 2 str() of float
         # can truncate shorter than repr()
         return repr(self.name)
@@ -188,7 +188,7 @@ def __init__(self, op, operands, *args, **kwargs):
     def __iter__(self):
         return iter(self.operands)
 
-    def __unicode__(self):
+    def __str__(self):
         """Print a generic n-ary operator and its operands using infix
         notation"""
         # recurse over the operands
@@ -506,7 +506,7 @@ def __call__(self, env):
         operand = self.operand(env)
         return self.func(operand)
 
-    def __unicode__(self):
+    def __str__(self):
         return pprint_thing('{0}({1})'.format(self.op, self.operand))
 
     @property
@@ -531,7 +531,7 @@ def __call__(self, env):
         with np.errstate(all='ignore'):
             return self.func.func(*operands)
 
-    def __unicode__(self):
+    def __str__(self):
         operands = map(str, self.operands)
         return pprint_thing('{0}({1})'.format(self.op, ','.join(operands)))