Merge remote-tracking branch 'upstream/master' into Zac-HD-hypothesis

Author: TomAugspurger

ci/circle-27-compat.yaml

@@ -7,7 +7,7 @@ dependencies:
   - cython=0.28.2
   - jinja2=2.8
   - numexpr=2.4.4 # we test that we correctly don't use an unsupported numexpr
-  - numpy=1.9.2
+  - numpy=1.9.3
   - openpyxl
   - psycopg2
   - pytables=3.2.2

ci/doctests.sh

@@ -28,7 +28,7 @@ if [ "$DOCTEST" ]; then
     fi
 
     pytest --doctest-modules -v pandas/core/series.py \
-        -k"-agg -map -nlargest -nonzero -nsmallest -reindex -searchsorted -to_dict"
+        -k"-nlargest -nonzero -nsmallest -reindex -searchsorted -to_dict"
 
     if [ $? -ne "0" ]; then
         RET=1

ci/travis-27-locale.yaml

@@ -7,7 +7,7 @@ dependencies:
   - cython=0.28.2
   - lxml
   - matplotlib=1.4.3
-  - numpy=1.9.2
+  - numpy=1.9.3
   - openpyxl=2.4.0
   - python-dateutil
   - python-blosc

doc/source/whatsnew/v0.24.0.txt

@@ -239,7 +239,7 @@ without timezone localization. This is inconsistent from parsing the same
 datetime string with :class:`Timestamp` which would preserve the UTC
 offset in the ``tz`` attribute. Now, :func:`to_datetime` preserves the UTC
 offset in the ``tz`` attribute when all the datetime strings have the same
-UTC offset (:issue:`17697`, :issue:`11736`)
+UTC offset (:issue:`17697`, :issue:`11736`, :issue:`22457`)
 
 *Previous Behavior*:
 

pandas/core/generic.py

@@ -4439,7 +4439,6 @@ def pipe(self, func, *args, **kwargs):
         - function.
         - list of functions.
         - dict of column names -> functions (or list of functions).
-
     %(axis)s
     *args
         Positional arguments to pass to `func`.
@@ -8146,7 +8145,7 @@ def mask(self, cond, other=np.nan, inplace=False, axis=None, level=None,
         Parameters
         ----------
         periods : int
-            Number of periods to move, can be positive or negative
+            Number of periods to move, can be positive or negative.
         freq : DateOffset, timedelta, or time rule string, optional
             Increment to use from the tseries module or time rule (e.g. 'EOM').
             See Notes.

pandas/core/series.py

@@ -1132,7 +1132,6 @@ def reset_index(self, level=None, drop=False, name=None, inplace=False):
 
         Examples
         --------
-
         >>> s = pd.Series([1, 2, 3, 4], name='foo',
         ...               index=pd.Index(['a', 'b', 'c', 'd'], name='idx'))
 
@@ -3046,21 +3045,27 @@ def _gotitem(self, key, ndim, subset=None):
     Examples
     --------
 
-    >>> s = pd.Series(np.random.randn(10))
+    >>> s = pd.Series([1, 2, 3, 4])
+    >>> s
+    0    1
+    1    2
+    2    3
+    3    4
+    dtype: int64
 
     >>> s.agg('min')
-    -1.3018049988556679
+    1
 
     >>> s.agg(['min', 'max'])
-    min   -1.301805
-    max    1.127688
-    dtype: float64
+    min   1
+    max   4
+    dtype: int64
 
     See also
     --------
-    pandas.Series.apply
-    pandas.Series.transform
-
+    pandas.Series.apply : Invoke function on a Series.
+    pandas.Series.transform : Transform function producing
+        a Series with like indexes.
     """)
 
     @Appender(_agg_doc)
@@ -3315,7 +3320,6 @@ def rename(self, index=None, **kwargs):
 
         Examples
         --------
-
         >>> s = pd.Series([1, 2, 3])
         >>> s
         0    1
@@ -3337,7 +3341,6 @@ def rename(self, index=None, **kwargs):
         3    2
         5    3
         dtype: int64
-
         """
         kwargs['inplace'] = validate_bool_kwarg(kwargs.get('inplace', False),
                                                 'inplace')
@@ -3507,7 +3510,6 @@ def memory_usage(self, index=True, deep=False):
 
         Examples
         --------
-
         >>> s = pd.Series(range(3))
         >>> s.memory_usage()
         104
@@ -3591,7 +3593,6 @@ def isin(self, values):
 
         Examples
         --------
-
         >>> s = pd.Series(['lama', 'cow', 'lama', 'beetle', 'lama',
         ...                'hippo'], name='animal')
         >>> s.isin(['cow', 'lama'])

pandas/core/tools/datetimes.py

@@ -275,14 +275,25 @@ def _convert_listlike_datetimes(arg, box, format, name=None, tz=None,
                 yearfirst=yearfirst,
                 require_iso8601=require_iso8601
             )
-            if tz_parsed is not None and box:
-                return DatetimeIndex._simple_new(result, name=name,
-                                                 tz=tz_parsed)
+            if tz_parsed is not None:
+                if box:
+                    # We can take a shortcut since the datetime64 numpy array
+                    # is in UTC
+                    return DatetimeIndex._simple_new(result, name=name,
+                                                     tz=tz_parsed)
+                else:
+                    # Convert the datetime64 numpy array to an numpy array
+                    # of datetime objects
+                    result = [Timestamp(ts, tz=tz_parsed).to_pydatetime()
+                              for ts in result]
+                    return np.array(result, dtype=object)
 
         if box:
+            # Ensure we return an Index in all cases where box=True
             if is_datetime64_dtype(result):
                 return DatetimeIndex(result, tz=tz, name=name)
             elif is_object_dtype(result):
+                # e.g. an Index of datetime objects
                 from pandas import Index
                 return Index(result, name=name)
         return result

pandas/tests/indexes/datetimes/test_tools.py

@@ -592,6 +592,17 @@ def test_iso_8601_strings_with_same_offset(self):
         result = DatetimeIndex([ts_str] * 2)
         tm.assert_index_equal(result, expected)
 
+    def test_iso_8601_strings_same_offset_no_box(self):
+        # GH 22446
+        data = ['2018-01-04 09:01:00+09:00', '2018-01-04 09:02:00+09:00']
+        result = pd.to_datetime(data, box=False)
+        expected = np.array([
+            datetime(2018, 1, 4, 9, 1, tzinfo=pytz.FixedOffset(540)),
+            datetime(2018, 1, 4, 9, 2, tzinfo=pytz.FixedOffset(540))
+        ],
+            dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
     def test_iso_8601_strings_with_different_offsets(self):
         # GH 17697, 11736
         ts_strings = ["2015-11-18 15:30:00+05:30",

pandas/tests/test_algos.py

@@ -330,10 +330,9 @@ def test_datetime64_dtype_array_returned(self):
              '2015-01-01T00:00:00.000000000+0000'],
             dtype='M8[ns]')
 
-        dt_index = pd.to_datetime(['2015-01-03T00:00:00.000000000+0000',
-                                   '2015-01-01T00:00:00.000000000+0000',
-                                   '2015-01-01T00:00:00.000000000+0000'],
-                                  box=False)
+        dt_index = pd.to_datetime(['2015-01-03T00:00:00.000000000',
+                                   '2015-01-01T00:00:00.000000000',
+                                   '2015-01-01T00:00:00.000000000'])
         result = algos.unique(dt_index)
         tm.assert_numpy_array_equal(result, expected)
         assert result.dtype == expected.dtype