Merge remote-tracking branch 'upstream/master' into ea-take

Author: TomAugspurger

doc/source/whatsnew/v0.23.0.txt

@@ -886,6 +886,9 @@ Deprecations
 - The ``convert_datetime64`` parameter in :func:`DataFrame.to_records` has been deprecated and will be removed in a future version. The NumPy bug motivating this parameter has been resolved. The default value for this parameter has also changed from ``True`` to ``None`` (:issue:`18160`).
 - :func:`Series.rolling().apply() <pandas.core.window.Rolling.apply>`, :func:`DataFrame.rolling().apply() <pandas.core.window.Rolling.apply>`,
   :func:`Series.expanding().apply() <pandas.core.window.Expanding.apply>`, and :func:`DataFrame.expanding().apply() <pandas.core.window.Expanding.apply>` have deprecated passing an ``np.array`` by default. One will need to pass the new ``raw`` parameter to be explicit about what is passed (:issue:`20584`)
+- The ``data``, ``base``, ``strides``, ``flags`` and ``itemsize`` properties
+  of the ``Series`` and ``Index`` classes have been deprecated and will be
+  removed in a future version (:issue:`20419`).
 - ``DatetimeIndex.offset`` is deprecated. Use ``DatetimeIndex.freq`` instead (:issue:`20716`)
 - ``Index.get_duplicates()`` is deprecated and will be removed in a future version (:issue:`20239`)
 

pandas/core/algorithms.py

@@ -1586,6 +1586,8 @@ def take_nd(arr, indexer, axis=0, out=None, fill_value=np.nan, mask_info=None,
     if is_sparse(arr):
         arr = arr.get_values()
 
+    arr = np.asarray(arr)
+
     if indexer is None:
         indexer = np.arange(arr.shape[axis], dtype=np.int64)
         dtype, fill_value = arr.dtype, arr.dtype.type()

pandas/core/apply.py

@@ -111,8 +111,14 @@ def get_result(self):
 
         # string dispatch
         if isinstance(self.f, compat.string_types):
-            self.kwds['axis'] = self.axis
-            return getattr(self.obj, self.f)(*self.args, **self.kwds)
+            # Support for `frame.transform('method')`
+            # Some methods (shift, etc.) require the axis argument, others
+            # don't, so inspect and insert if nescessary.
+            func = getattr(self.obj, self.f)
+            sig = compat.signature(func)
+            if 'axis' in sig.args:
+                self.kwds['axis'] = self.axis
+            return func(*self.args, **self.kwds)
 
         # ufunc
         elif isinstance(self.f, np.ufunc):

pandas/core/base.py

@@ -737,11 +737,17 @@ def item(self):
     @property
     def data(self):
         """ return the data pointer of the underlying data """
+        warnings.warn("{obj}.data is deprecated and will be removed "
+                      "in a future version".format(obj=type(self).__name__),
+                      FutureWarning, stacklevel=2)
         return self.values.data
 
     @property
     def itemsize(self):
         """ return the size of the dtype of the item of the underlying data """
+        warnings.warn("{obj}.itemsize is deprecated and will be removed "
+                      "in a future version".format(obj=type(self).__name__),
+                      FutureWarning, stacklevel=2)
         return self._ndarray_values.itemsize
 
     @property
@@ -752,6 +758,9 @@ def nbytes(self):
     @property
     def strides(self):
         """ return the strides of the underlying data """
+        warnings.warn("{obj}.strudes is deprecated and will be removed "
+                      "in a future version".format(obj=type(self).__name__),
+                      FutureWarning, stacklevel=2)
         return self._ndarray_values.strides
 
     @property
@@ -762,13 +771,19 @@ def size(self):
     @property
     def flags(self):
         """ return the ndarray.flags for the underlying data """
+        warnings.warn("{obj}.flags is deprecated and will be removed "
+                      "in a future version".format(obj=type(self).__name__),
+                      FutureWarning, stacklevel=2)
         return self.values.flags
 
     @property
     def base(self):
         """ return the base object if the memory of the underlying data is
         shared
         """
+        warnings.warn("{obj}.base is deprecated and will be removed "
+                      "in a future version".format(obj=type(self).__name__),
+                      FutureWarning, stacklevel=2)
         return self.values.base
 
     @property

pandas/core/indexes/base.py

@@ -550,6 +550,9 @@ def _deepcopy_if_needed(self, orig, copy=False):
         """
         if copy:
             # Retrieve the "base objects", i.e. the original memory allocations
+            if not isinstance(orig, np.ndarray):
+                # orig is a DatetimeIndex
+                orig = orig.values
             orig = orig if orig.base is None else orig.base
             new = self._data if self._data.base is None else self._data.base
             if orig is new:

pandas/core/internals.py

@@ -2822,6 +2822,12 @@ def _maybe_coerce_values(self, values, dtype=None):
 
         return values
 
+    @property
+    def is_view(self):
+        """ return a boolean if I am possibly a view """
+        # check the ndarray values of the DatetimeIndex values
+        return self.values.values.base is not None
+
     def copy(self, deep=True, mgr=None):
         """ copy constructor """
         values = self.values

pandas/core/window.py

@@ -1271,12 +1271,12 @@ def kurt(self, **kwargs):
                            check_minp=_require_min_periods(4), **kwargs)
 
     _shared_docs['quantile'] = dedent("""
-    %(name)s quantile
+    %(name)s quantile.
 
     Parameters
     ----------
     quantile : float
-        0 <= quantile <= 1
+        Quantile to compute. 0 <= quantile <= 1.
     interpolation : {'linear', 'lower', 'higher', 'midpoint', 'nearest'}
         .. versionadded:: 0.23.0
 
@@ -1289,6 +1289,9 @@ def kurt(self, **kwargs):
             * higher: `j`.
             * nearest: `i` or `j` whichever is nearest.
             * midpoint: (`i` + `j`) / 2.
+    **kwargs:
+        For compatibility with other %(name)s methods. Has no effect on
+        the result.
 
     Returns
     -------
@@ -1298,7 +1301,7 @@ def kurt(self, **kwargs):
 
     Examples
     --------
-    >>> s = Series([1, 2, 3, 4])
+    >>> s = pd.Series([1, 2, 3, 4])
     >>> s.rolling(2).quantile(.4, interpolation='lower')
     0    NaN
     1    1.0
@@ -1319,7 +1322,6 @@ def kurt(self, **kwargs):
         in Series.
     pandas.DataFrame.quantile : Computes values at the given quantile over
         requested axis in DataFrame.
-
     """)
 
     def quantile(self, quantile, interpolation='linear', **kwargs):
@@ -1656,7 +1658,6 @@ def kurt(self, **kwargs):
         return super(Rolling, self).kurt(**kwargs)
 
     @Substitution(name='rolling')
-    @Appender(_doc_template)
     @Appender(_shared_docs['quantile'])
     def quantile(self, quantile, interpolation='linear', **kwargs):
         return super(Rolling, self).quantile(quantile=quantile,
@@ -1917,7 +1918,6 @@ def kurt(self, **kwargs):
         return super(Expanding, self).kurt(**kwargs)
 
     @Substitution(name='expanding')
-    @Appender(_doc_template)
     @Appender(_shared_docs['quantile'])
     def quantile(self, quantile, interpolation='linear', **kwargs):
         return super(Expanding, self).quantile(quantile=quantile,

pandas/tests/frame/test_apply.py

@@ -4,6 +4,7 @@
 
 import pytest
 
+import operator
 from datetime import datetime
 
 import warnings
@@ -880,6 +881,16 @@ def f():
             with np.errstate(all='ignore'):
                 df.agg({'A': ['abs', 'sum'], 'B': ['mean', 'max']})
 
+    @pytest.mark.parametrize('method', [
+        'abs', 'shift', 'pct_change', 'cumsum', 'rank',
+    ])
+    def test_transform_method_name(self, method):
+        # https://github.com/pandas-dev/pandas/issues/19760
+        df = pd.DataFrame({"A": [-1, 2]})
+        result = df.transform(method)
+        expected = operator.methodcaller(method)(df)
+        tm.assert_frame_equal(result, expected)
+
     def test_demo(self):
         # demonstration tests
         df = pd.DataFrame({'A': range(5), 'B': 5})

pandas/tests/groupby/aggregate/test_other.py

@@ -328,7 +328,7 @@ def test_series_agg_multi_pure_python():
          'F': np.random.randn(11)})
 
     def bad(x):
-        assert (len(x.base) > 0)
+        assert (len(x.values.base) > 0)
         return 'foo'
 
     result = data.groupby(['A', 'B']).agg(bad)

pandas/tests/groupby/test_groupby.py

@@ -1066,7 +1066,7 @@ def convert_fast(x):
 
     def convert_force_pure(x):
         # base will be length 0
-        assert (len(x.base) > 0)
+        assert (len(x.values.base) > 0)
         return Decimal(str(x.mean()))
 
     grouped = s.groupby(labels)

pandas/tests/indexes/common.py

@@ -24,7 +24,7 @@
 class Base(object):
     """ base class for index sub-class tests """
     _holder = None
-    _compat_props = ['shape', 'ndim', 'size', 'itemsize', 'nbytes']
+    _compat_props = ['shape', 'ndim', 'size', 'nbytes']
 
     def setup_indices(self):
         for name, idx in self.indices.items():

pandas/tests/indexes/test_multi.py

@@ -30,7 +30,7 @@
 
 class TestMultiIndex(Base):
     _holder = MultiIndex
-    _compat_props = ['shape', 'ndim', 'size', 'itemsize']
+    _compat_props = ['shape', 'ndim', 'size']
 
     def setup_method(self, method):
         major_axis = Index(['foo', 'bar', 'baz', 'qux'])

pandas/tests/indexes/test_range.py

@@ -22,7 +22,7 @@
 
 class TestRangeIndex(Numeric):
     _holder = RangeIndex
-    _compat_props = ['shape', 'ndim', 'size', 'itemsize']
+    _compat_props = ['shape', 'ndim', 'size']
 
     def setup_method(self, method):
         self.indices = dict(index=RangeIndex(0, 20, 2, name='foo'),

pandas/tests/internals/test_internals.py

@@ -466,16 +466,20 @@ def test_copy(self, mgr):
 
             # view assertion
             assert cp_blk.equals(blk)
-            assert cp_blk.values.base is blk.values.base
+            if isinstance(blk.values, np.ndarray):
+                assert cp_blk.values.base is blk.values.base
+            else:
+                # DatetimeTZBlock has DatetimeIndex values
+                assert cp_blk.values.values.base is blk.values.values.base
 
         cp = mgr.copy(deep=True)
         for blk, cp_blk in zip(mgr.blocks, cp.blocks):
 
             # copy assertion we either have a None for a base or in case of
             # some blocks it is an array (e.g. datetimetz), but was copied
             assert cp_blk.equals(blk)
-            if cp_blk.values.base is not None and blk.values.base is not None:
-                assert cp_blk.values.base is not blk.values.base
+            if not isinstance(cp_blk.values, np.ndarray):
+                assert cp_blk.values.values.base is not blk.values.values.base
             else:
                 assert cp_blk.values.base is None and blk.values.base is None
 

pandas/tests/test_base.py

@@ -316,16 +316,22 @@ def test_ndarray_compat_properties(self):
 
         for o in self.objs:
             # Check that we work.
-            for p in ['shape', 'dtype', 'flags', 'T',
-                      'strides', 'itemsize', 'nbytes']:
+            for p in ['shape', 'dtype', 'T', 'nbytes']:
                 assert getattr(o, p, None) is not None
 
-            assert hasattr(o, 'base')
+            # deprecated properties
+            for p in ['flags', 'strides', 'itemsize']:
+                with tm.assert_produces_warning(FutureWarning):
+                    assert getattr(o, p, None) is not None
+
+            with tm.assert_produces_warning(FutureWarning):
+                assert hasattr(o, 'base')
 
             # If we have a datetime-like dtype then needs a view to work
             # but the user is responsible for that
             try:
-                assert o.data is not None
+                with tm.assert_produces_warning(FutureWarning):
+                    assert o.data is not None
             except ValueError:
                 pass