Merge remote-tracking branch 'upstream/master' into drop_py2_ci

Author: h-vetinari

doc/source/conf.py

@@ -98,9 +98,9 @@
                 if (fname == 'index.rst'
                         and os.path.abspath(dirname) == source_path):
                     continue
-                elif pattern == '-api' and dirname == 'api':
+                elif pattern == '-api' and dirname == 'reference':
                     exclude_patterns.append(fname)
-                elif fname != pattern:
+                elif pattern != '-api' and fname != pattern:
                     exclude_patterns.append(fname)
 
 with open(os.path.join(source_path, 'index.rst.template')) as f:

doc/source/development/contributing.rst

@@ -54,7 +54,7 @@ Bug reports must:
       ...
       ```
 
-#. Include the full version string of *pandas* and its dependencies. You can use the built in function::
+#. Include the full version string of *pandas* and its dependencies. You can use the built-in function::
 
       >>> import pandas as pd
       >>> pd.show_versions()
@@ -211,7 +211,7 @@ See the full conda docs `here <http://conda.pydata.org/docs>`__.
 Creating a Python Environment (pip)
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-If you aren't using conda for you development environment, follow these instructions.
+If you aren't using conda for your development environment, follow these instructions.
 You'll need to have at least python3.5 installed on your system.
 
 .. code-block:: none
@@ -484,7 +484,7 @@ contributing them to the project::
 
    ./ci/code_checks.sh
 
-The script verify the linting of code files, it looks for common mistake patterns
+The script verifies the linting of code files, it looks for common mistake patterns
 (like missing spaces around sphinx directives that make the documentation not
 being rendered properly) and it also validates the doctests. It is possible to
 run the checks independently by using the parameters ``lint``, ``patterns`` and
@@ -675,7 +675,7 @@ Otherwise, you need to do it manually:
 
 You'll also need to
 
-1. write a new test that asserts a warning is issued when calling with the deprecated argument
+1. Write a new test that asserts a warning is issued when calling with the deprecated argument
 2. Update all of pandas existing tests and code to use the new argument
 
 See :ref:`contributing.warnings` for more.

doc/source/getting_started/basics.rst

@@ -505,7 +505,7 @@ So, for instance, to reproduce :meth:`~DataFrame.combine_first` as above:
 .. ipython:: python
 
    def combiner(x, y):
-       np.where(pd.isna(x), y, x)
+       return np.where(pd.isna(x), y, x)
    df1.combine(df2, combiner)
 
 .. _basics.stats:

doc/source/whatsnew/v0.25.0.rst

@@ -59,6 +59,13 @@ minimum versions. If installed, we now require:
 Other API Changes
 ^^^^^^^^^^^^^^^^^
 
+- :meth:`Timestamp.strptime` will now raise a NotImplementedError (:issue:`21257`)
+
+.. _whatsnew_0250.api.other:
+
+Other API Changes
+^^^^^^^^^^^^^^^^^
+
 - :class:`DatetimeTZDtype` will now standardize pytz timezones to a common timezone instance (:issue:`24713`)
 - ``Timestamp`` and ``Timedelta`` scalars now implement the :meth:`to_numpy` method as aliases to :meth:`Timestamp.to_datetime64` and :meth:`Timedelta.to_timedelta64`, respectively. (:issue:`24653`)
 -
@@ -175,10 +182,9 @@ Missing
 MultiIndex
 ^^^^^^^^^^
 
+- Bug in which incorrect exception raised by :meth:`pd.Timedelta` when testing the membership of :class:`MultiIndex` (:issue:`24570`)
 -
 -
--
-
 
 I/O
 ^^^

pandas/_libs/tslibs/nattype.pyx

@@ -374,7 +374,6 @@ class NaTType(_NaT):
     utctimetuple = _make_error_func('utctimetuple', datetime)
     timetz = _make_error_func('timetz', datetime)
     timetuple = _make_error_func('timetuple', datetime)
-    strptime = _make_error_func('strptime', datetime)
     strftime = _make_error_func('strftime', datetime)
     isocalendar = _make_error_func('isocalendar', datetime)
     dst = _make_error_func('dst', datetime)
@@ -388,6 +387,14 @@ class NaTType(_NaT):
     # The remaining methods have docstrings copy/pasted from the analogous
     # Timestamp methods.
 
+    strptime = _make_error_func('strptime',  # noqa:E128
+        """
+        Timestamp.strptime(string, format)
+
+        Function is not implemented. Use pd.to_datetime().
+        """
+    )
+
     utcfromtimestamp = _make_error_func('utcfromtimestamp',  # noqa:E128
         """
         Timestamp.utcfromtimestamp(ts)

pandas/_libs/tslibs/timestamps.pyx

@@ -697,6 +697,17 @@ class Timestamp(_Timestamp):
         """
         return cls(datetime.fromtimestamp(ts))
 
+    # Issue 25016.
+    @classmethod
+    def strptime(cls, date_string, format):
+        """
+        Timestamp.strptime(string, format)
+
+        Function is not implemented. Use pd.to_datetime().
+        """
+        raise NotImplementedError("Timestamp.strptime() is not implmented."
+                                  "Use to_datetime() to parse date strings.")
+
     @classmethod
     def combine(cls, date, time):
         """

pandas/core/generic.py

@@ -1333,7 +1333,6 @@ def _set_axis_name(self, name, axis=0, inplace=False):
                cat        4
                monkey     2
         """
-        pd.MultiIndex.from_product([["mammal"], ['dog', 'cat', 'monkey']])
         axis = self._get_axis_number(axis)
         idx = self._get_axis(axis).set_names(name)
 

pandas/core/indexes/multi.py

@@ -840,7 +840,7 @@ def __contains__(self, key):
         try:
             self.get_loc(key)
             return True
-        except (LookupError, TypeError):
+        except (LookupError, TypeError, ValueError):
             return False
 
     contains = __contains__

pandas/tests/frame/test_combine_concat.py

@@ -504,6 +504,16 @@ def test_concat_numerical_names(self):
                                                                 names=[1, 2]))
         tm.assert_frame_equal(result, expected)
 
+    def test_concat_astype_dup_col(self):
+        # gh 23049
+        df = pd.DataFrame([{'a': 'b'}])
+        df = pd.concat([df, df], axis=1)
+
+        result = df.astype('category')
+        expected = pd.DataFrame(np.array(["b", "b"]).reshape(1, 2),
+                                columns=["a", "a"]).astype("category")
+        tm.assert_frame_equal(result, expected)
+
 
 class TestDataFrameCombineFirst(TestData):
 

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -286,3 +286,20 @@ def test_multi_function_flexible_mix(df):
     with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
         result = grouped.aggregate(d)
     tm.assert_frame_equal(result, expected)
+
+
+def test_groupby_agg_coercing_bools():
+    # issue 14873
+    dat = pd.DataFrame(
+        {'a': [1, 1, 2, 2], 'b': [0, 1, 2, 3], 'c': [None, None, 1, 1]})
+    gp = dat.groupby('a')
+
+    index = Index([1, 2], name='a')
+
+    result = gp['b'].aggregate(lambda x: (x != 0).all())
+    expected = Series([False, True], index=index, name='b')
+    tm.assert_series_equal(result, expected)
+
+    result = gp['c'].aggregate(lambda x: x.isnull().all())
+    expected = Series([True, False], index=index, name='c')
+    tm.assert_series_equal(result, expected)

pandas/tests/groupby/test_groupby.py

@@ -1698,3 +1698,19 @@ def test_groupby_agg_ohlc_non_first():
     result = df.groupby(pd.Grouper(freq='D')).agg(['sum', 'ohlc'])
 
     tm.assert_frame_equal(result, expected)
+
+
+def test_groupby_multiindex_nat():
+    # GH 9236
+    values = [
+        (pd.NaT, 'a'),
+        (datetime(2012, 1, 2), 'a'),
+        (datetime(2012, 1, 2), 'b'),
+        (datetime(2012, 1, 3), 'a')
+    ]
+    mi = pd.MultiIndex.from_tuples(values, names=['date', None])
+    ser = pd.Series([3, 2, 2.5, 4], index=mi)
+
+    result = ser.groupby(level=1).mean()
+    expected = pd.Series([3., 2.5], index=["a", "b"])
+    assert_series_equal(result, expected)

pandas/tests/indexing/multiindex/test_multiindex.py

@@ -84,3 +84,11 @@ def test_multi_nan_indexing(self):
                                           name='a'),
                                     Index(['C1', 'C2', 'C3', 'C4'], name='b')])
         tm.assert_frame_equal(result, expected)
+
+    def test_contains(self):
+        # GH 24570
+        tx = pd.timedelta_range('09:30:00', '16:00:00', freq='30 min')
+        idx = MultiIndex.from_arrays([tx, np.arange(len(tx))])
+        assert tx[0] in idx
+        assert 'element_not_exit' not in idx
+        assert '0 day 09:30:00' in idx

pandas/tests/scalar/timestamp/test_timestamp.py

@@ -355,6 +355,14 @@ def test_constructor_invalid_tz(self):
             # interpreted as a `freq`
             Timestamp('2012-01-01', 'US/Pacific')
 
+    def test_constructor_strptime(self):
+        # GH25016
+        # Test support for Timestamp.strptime
+        fmt = '%Y%m%d-%H%M%S-%f%z'
+        ts = '20190129-235348-000001+0000'
+        with pytest.raises(NotImplementedError):
+            Timestamp.strptime(ts, fmt)
+
     def test_constructor_tz_or_tzinfo(self):
         # GH#17943, GH#17690, GH#5168
         stamps = [Timestamp(year=2017, month=10, day=22, tz='UTC'),