Merge remote-tracking branch 'upstream/master' into close_other_tz_issues

Author: Matt Roeschke

ci/deps/azure-35-compat.yaml

@@ -11,7 +11,7 @@ dependencies:
   - openpyxl=2.4.8
   - pytables=3.4.2
   - python-dateutil=2.6.1
-  - python=3.5.*
+  - python=3.5.3
   - pytz=2017.2
   - scipy=0.19.0
   - xlrd=1.1.0

doc/source/user_guide/advanced.rst

@@ -1108,6 +1108,8 @@ the :meth:`~Index.is_unique` attribute.
    weakly_monotonic.is_monotonic_increasing
    weakly_monotonic.is_monotonic_increasing & weakly_monotonic.is_unique
 
+.. _advanced.endpoints_are_inclusive:
+
 Endpoints are inclusive
 ~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -1137,7 +1139,7 @@ index can be somewhat complicated. For example, the following does not work:
     s.loc['c':'e' + 1]
 
 A very common use case is to limit a time series to start and end at two
-specific dates. To enable this, we made the design to make label-based
+specific dates. To enable this, we made the design choice to make label-based
 slicing include both endpoints:
 
 .. ipython:: python

doc/source/user_guide/indexing.rst

@@ -61,8 +61,8 @@ of multi-axis indexing.
     * A list or array of labels ``['a', 'b', 'c']``.
     * A slice object with labels ``'a':'f'`` (Note that contrary to usual python
       slices, **both** the start and the stop are included, when present in the
-      index! See :ref:`Slicing with labels
-      <indexing.slicing_with_labels>`.).
+      index! See :ref:`Slicing with labels <indexing.slicing_with_labels>`
+      and :ref:`Endpoints are inclusive <advanced.endpoints_are_inclusive>`.)
     * A boolean array
     * A ``callable`` function with one argument (the calling Series or DataFrame) and
       that returns valid output for indexing (one of the above).
@@ -335,8 +335,7 @@ The ``.loc`` attribute is the primary access method. The following are valid inp
 * A list or array of labels ``['a', 'b', 'c']``.
 * A slice object with labels ``'a':'f'`` (Note that contrary to usual python
   slices, **both** the start and the stop are included, when present in the
-  index! See :ref:`Slicing with labels
-  <indexing.slicing_with_labels>`.).
+  index! See :ref:`Slicing with labels <indexing.slicing_with_labels>`.
 * A boolean array.
 * A ``callable``, see :ref:`Selection By Callable <indexing.callable>`.
 
@@ -418,6 +417,9 @@ error will be raised (since doing otherwise would be computationally expensive,
 as well as potentially ambiguous for mixed type indexes). For instance, in the
 above example, ``s.loc[1:6]`` would raise ``KeyError``.
 
+For the rationale behind this behavior, see
+:ref:`Endpoints are inclusive <advanced.endpoints_are_inclusive>`.
+
 .. _indexing.integer:
 
 Selection by position

doc/source/user_guide/timeseries.rst

@@ -474,16 +474,6 @@ resulting ``DatetimeIndex``:
 Custom frequency ranges
 ~~~~~~~~~~~~~~~~~~~~~~~
 
-.. warning::
-
-   This functionality was originally exclusive to ``cdate_range``, which is
-   deprecated as of version 0.21.0 in favor of ``bdate_range``.  Note that
-   ``cdate_range`` only utilizes the ``weekmask`` and ``holidays`` parameters
-   when custom business day, 'C', is passed as the frequency string. Support has
-   been expanded with ``bdate_range`` to work with any custom frequency string.
-
-.. versionadded:: 0.21.0
-
 ``bdate_range`` can also generate a range of custom frequency dates by using
 the ``weekmask`` and ``holidays`` parameters.  These parameters will only be
 used if a custom frequency string is passed.

doc/source/whatsnew/v0.25.0.rst

@@ -5,9 +5,13 @@ What's new in 0.25.0 (April XX, 2019)
 
 .. warning::
 
-   Starting with the 0.25.x series of releases, pandas only supports Python 3.5 and higher.
+   Starting with the 0.25.x series of releases, pandas only supports Python 3.5.3 and higher.
    See :ref:`install.dropping-27` for more details.
 
+.. warning::
+
+   The minimum supported Python version will be bumped to 3.6 in a future release.
+
 .. warning::
 
    `Panel` has been fully removed. For N-D labeled data structures, please
@@ -634,6 +638,9 @@ Removal of prior version deprecations/changes
 - Removed the previously deprecated behavior of altering column or index labels with :meth:`Series.rename_axis` or :meth:`DataFrame.rename_axis` (:issue:`17842`)
 - Removed the previously deprecated ``tupleize_cols`` keyword argument in :meth:`read_html`, :meth:`read_csv`, and :meth:`DataFrame.to_csv` (:issue:`17877`, :issue:`17820`)
 - Removed the previously deprecated ``DataFrame.from.csv`` and ``Series.from_csv`` (:issue:`17812`)
+- Removed the previously deprecated ``raise_on_error`` keyword argument in :meth:`DataFrame.where` and :meth:`DataFrame.mask` (:issue:`17744`)
+- Removed the previously deprecated ``ordered`` and ``categories`` keyword arguments in ``astype`` (:issue:`17742`)
+- Removed the previously deprecated ``cdate_range`` (:issue:`17691`)
 
 .. _whatsnew_0250.performance:
 

pandas/core/generic.py

@@ -8644,13 +8644,6 @@ def _where(self, cond, other=np.nan, inplace=False, axis=None, level=None,
 
         try_cast : bool, default False
             Try to cast the result back to the input type (if possible).
-        raise_on_error : bool, default True
-            Whether to raise on invalid data types (e.g. trying to where on
-            strings).
-
-            .. deprecated:: 0.21.0
-
-               Use `errors`.
 
         Returns
         -------
@@ -8738,18 +8731,7 @@ def _where(self, cond, other=np.nan, inplace=False, axis=None, level=None,
                                            cond_rev="False", name='where',
                                            name_other='mask'))
     def where(self, cond, other=np.nan, inplace=False, axis=None, level=None,
-              errors='raise', try_cast=False, raise_on_error=None):
-
-        if raise_on_error is not None:
-            warnings.warn(
-                "raise_on_error is deprecated in "
-                "favor of errors='raise|ignore'",
-                FutureWarning, stacklevel=2)
-
-            if raise_on_error:
-                errors = 'raise'
-            else:
-                errors = 'ignore'
+              errors='raise', try_cast=False):
 
         other = com.apply_if_callable(other, self)
         return self._where(cond, other, inplace, axis, level,
@@ -8759,18 +8741,7 @@ def where(self, cond, other=np.nan, inplace=False, axis=None, level=None,
                                            cond_rev="True", name='mask',
                                            name_other='where'))
     def mask(self, cond, other=np.nan, inplace=False, axis=None, level=None,
-             errors='raise', try_cast=False, raise_on_error=None):
-
-        if raise_on_error is not None:
-            warnings.warn(
-                "raise_on_error is deprecated in "
-                "favor of errors='raise|ignore'",
-                FutureWarning, stacklevel=2)
-
-            if raise_on_error:
-                errors = 'raise'
-            else:
-                errors = 'ignore'
+             errors='raise', try_cast=False):
 
         inplace = validate_bool_kwarg(inplace, 'inplace')
         cond = com.apply_if_callable(cond, self)

pandas/core/indexes/datetimes.py

@@ -29,7 +29,7 @@
 import pandas.core.tools.datetimes as tools
 
 from pandas.tseries.frequencies import Resolution, to_offset
-from pandas.tseries.offsets import CDay, Nano, prefix_mapping
+from pandas.tseries.offsets import Nano, prefix_mapping
 
 
 def _new_DatetimeIndex(cls, d):
@@ -1568,66 +1568,6 @@ def bdate_range(start=None, end=None, periods=None, freq='B', tz=None,
                       closed=closed, **kwargs)
 
 
-def cdate_range(start=None, end=None, periods=None, freq='C', tz=None,
-                normalize=True, name=None, closed=None, **kwargs):
-    """
-    Return a fixed frequency DatetimeIndex, with CustomBusinessDay as the
-    default frequency
-
-    .. deprecated:: 0.21.0
-
-    Parameters
-    ----------
-    start : string or datetime-like, default None
-        Left bound for generating dates
-    end : string or datetime-like, default None
-        Right bound for generating dates
-    periods : integer, default None
-        Number of periods to generate
-    freq : string or DateOffset, default 'C' (CustomBusinessDay)
-        Frequency strings can have multiples, e.g. '5H'
-    tz : string, default None
-        Time zone name for returning localized DatetimeIndex, for example
-        Asia/Beijing
-    normalize : bool, default False
-        Normalize start/end dates to midnight before generating date range
-    name : string, default None
-        Name of the resulting DatetimeIndex
-    weekmask : string, Default 'Mon Tue Wed Thu Fri'
-        weekmask of valid business days, passed to ``numpy.busdaycalendar``
-    holidays : list
-        list/array of dates to exclude from the set of valid business days,
-        passed to ``numpy.busdaycalendar``
-    closed : string, default None
-        Make the interval closed with respect to the given frequency to
-        the 'left', 'right', or both sides (None)
-
-    Notes
-    -----
-    Of the three parameters: ``start``, ``end``, and ``periods``, exactly two
-    must be specified.
-
-    To learn more about the frequency strings, please see `this link
-    <http://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases>`__.
-
-    Returns
-    -------
-    rng : DatetimeIndex
-    """
-    warnings.warn("cdate_range is deprecated and will be removed in a future "
-                  "version, instead use pd.bdate_range(..., freq='{freq}')"
-                  .format(freq=freq), FutureWarning, stacklevel=2)
-
-    if freq == 'C':
-        holidays = kwargs.pop('holidays', [])
-        weekmask = kwargs.pop('weekmask', 'Mon Tue Wed Thu Fri')
-        freq = CDay(holidays=holidays, weekmask=weekmask)
-
-    return date_range(start=start, end=end, periods=periods, freq=freq,
-                      tz=tz, normalize=normalize, name=name,
-                      closed=closed, **kwargs)
-
-
 def _time_to_micros(time):
     seconds = time.hour * 60 * 60 + 60 * time.minute + time.second
     return 1000000 * seconds + time.microsecond

pandas/core/internals/blocks.py

@@ -542,17 +542,10 @@ def _astype(self, dtype, copy=False, errors='raise', values=None,
         if self.is_categorical_astype(dtype):
 
             # deprecated 17636
-            if ('categories' in kwargs or 'ordered' in kwargs):
-                if isinstance(dtype, CategoricalDtype):
-                    raise TypeError(
-                        "Cannot specify a CategoricalDtype and also "
-                        "`categories` or `ordered`. Use "
-                        "`dtype=CategoricalDtype(categories, ordered)`"
-                        " instead.")
-                warnings.warn("specifying 'categories' or 'ordered' in "
-                              ".astype() is deprecated; pass a "
-                              "CategoricalDtype instead",
-                              FutureWarning, stacklevel=7)
+            for deprecated_arg in ('categories', 'ordered'):
+                if deprecated_arg in kwargs:
+                    raise ValueError('Got an unexpected argument: {}'.format(
+                        deprecated_arg))
 
             categories = kwargs.get('categories', None)
             ordered = kwargs.get('ordered', None)

pandas/tests/api/test_api.py

@@ -131,13 +131,3 @@ def test_testing(self):
 
         from pandas import testing
         self.check(testing, self.funcs)
-
-
-class TestCDateRange:
-
-    def test_deprecation_cdaterange(self):
-        # GH17596
-        from pandas.core.indexes.datetimes import cdate_range
-        with tm.assert_produces_warning(FutureWarning,
-                                        check_stacklevel=False):
-            cdate_range('2017-01-01', '2017-12-31')

pandas/tests/io/data/test4.xls

@@ -31,24 +31,29 @@ def ignore_xlrd_time_clock_warning():
         yield
 
 
+@pytest.fixture(params=[
+    # Add any engines to test here
+    pytest.param('xlrd', marks=td.skip_if_no('xlrd')),
+    pytest.param('openpyxl', marks=td.skip_if_no('openpyxl')),
+    pytest.param(None, marks=td.skip_if_no('xlrd')),
+])
+def engine(request):
+    """
+    A fixture for Excel reader engines.
+    """
+    return request.param
+
+
 class TestReaders:
 
-    @pytest.fixture(autouse=True, params=[
-        # Add any engines to test here
-        pytest.param('xlrd', marks=pytest.mark.skipif(
-            not td.safe_import("xlrd"), reason="no xlrd")),
-        pytest.param('openpyxl', marks=pytest.mark.skipif(
-            not td.safe_import("openpyxl"), reason="no openpyxl")),
-        pytest.param(None, marks=pytest.mark.skipif(
-            not td.safe_import("xlrd"), reason="no xlrd")),
-    ])
-    def cd_and_set_engine(self, request, datapath, monkeypatch, read_ext):
+    @pytest.fixture(autouse=True)
+    def cd_and_set_engine(self, engine, datapath, monkeypatch, read_ext):
         """
         Change directory and set engine for read_excel calls.
         """
-        if request.param == 'openpyxl' and read_ext == '.xls':
+        if engine == 'openpyxl' and read_ext == '.xls':
             pytest.skip()
-        func = partial(pd.read_excel, engine=request.param)
+        func = partial(pd.read_excel, engine=engine)
         monkeypatch.chdir(datapath("io", "data"))
         monkeypatch.setattr(pd, 'read_excel', func)
 
@@ -726,23 +731,15 @@ def test_read_excel_squeeze(self, read_ext):
 
 class TestExcelFileRead:
 
-    @pytest.fixture(autouse=True, params=[
-        # Add any engines to test here
-        pytest.param('xlrd', marks=pytest.mark.skipif(
-            not td.safe_import("xlrd"), reason="no xlrd")),
-        pytest.param('openpyxl', marks=pytest.mark.skipif(
-            not td.safe_import("openpyxl"), reason="no openpyxl")),
-        pytest.param(None, marks=pytest.mark.skipif(
-            not td.safe_import("xlrd"), reason="no xlrd")),
-    ])
-    def cd_and_set_engine(self, request, datapath, monkeypatch, read_ext):
+    @pytest.fixture(autouse=True)
+    def cd_and_set_engine(self, engine, datapath, monkeypatch, read_ext):
         """
         Change directory and set engine for ExcelFile objects.
         """
-        if request.param == 'openpyxl' and read_ext == '.xls':
+        if engine == 'openpyxl' and read_ext == '.xls':
             pytest.skip()
 
-        func = partial(pd.ExcelFile, engine=request.param)
+        func = partial(pd.ExcelFile, engine=engine)
         monkeypatch.chdir(datapath("io", "data"))
         monkeypatch.setattr(pd, 'ExcelFile', func)
 
@@ -830,20 +827,18 @@ def test_sheet_name(self, read_ext, df_ref):
         tm.assert_frame_equal(df1_parse, df_ref, check_names=False)
         tm.assert_frame_equal(df2_parse, df_ref, check_names=False)
 
-    def test_excel_read_buffer(self, read_ext):
+    def test_excel_read_buffer(self, engine, read_ext):
         pth = 'test1' + read_ext
-        engine = pd.ExcelFile.keywords['engine']  # TODO: fixturize
         expected = pd.read_excel(pth, 'Sheet1', index_col=0, engine=engine)
 
         with open(pth, 'rb') as f:
             with pd.ExcelFile(f) as xls:
                 actual = pd.read_excel(xls, 'Sheet1', index_col=0)
 
-            tm.assert_frame_equal(expected, actual)
+        tm.assert_frame_equal(expected, actual)
 
-    def test_reader_closes_file(self, read_ext):
+    def test_reader_closes_file(self, engine, read_ext):
         f = open('test1' + read_ext, 'rb')
-        engine = pd.ExcelFile.keywords['engine']  # TODO: fixturize
         with pd.ExcelFile(f) as xlsx:
             # parses okay
             pd.read_excel(xlsx, 'Sheet1', index_col=0, engine=engine)