From 8da210c81195375e4be5653767c8a038414798d4 Mon Sep 17 00:00:00 2001
From: rockg <grant.roch@gmail.com>
Date: Sun, 3 Aug 2014 15:36:41 -0400
Subject: [PATCH] Remove from start/end dates if tz is not None (remove check
 of inferred_tz).

---
 doc/source/timeseries.rst              |  6 ++++
 doc/source/v0.15.0.txt                 |  4 ++-
 pandas/tseries/index.py                |  2 +-
 pandas/tseries/tests/test_daterange.py | 38 ++++++++++++++++++++++----
 4 files changed, 42 insertions(+), 8 deletions(-)

diff --git a/doc/source/timeseries.rst b/doc/source/timeseries.rst
index 05fd82b2f448d..9dd7845864e59 100644
--- a/doc/source/timeseries.rst
+++ b/doc/source/timeseries.rst
@@ -1364,6 +1364,12 @@ tz-aware data to another time zone:
        is localized using one version and operated on with a different version.  
        See :ref:`here<io.hdf5-notes>` for how to handle such a situation.
 
+.. warning::
+
+       It is incorrect to pass a timezone directly into the ``datetime.datetime`` constructor (e.g.,
+       ``datetime.datetime(2011, 1, 1, tz=timezone('US/Eastern'))``.  Instead, the datetime
+       needs to be localized using the the localize method on the timezone.
+
 Under the hood, all timestamps are stored in UTC. Scalar values from a
 ``DatetimeIndex`` with a time zone will have their fields (day, hour, minute)
 localized to the time zone. However, timestamps with the same UTC value are
diff --git a/doc/source/v0.15.0.txt b/doc/source/v0.15.0.txt
index 109ed8b286c22..2e3aeaf69957b 100644
--- a/doc/source/v0.15.0.txt
+++ b/doc/source/v0.15.0.txt
@@ -358,7 +358,9 @@ Bug Fixes
 
 
 - Bug in ``GroupBy.filter()`` where fast path vs. slow path made the filter
-  return a non scalar value that appeared valid but wasnt' (:issue:`7870`).
+  return a non scalar value that appeared valid but wasn't (:issue:`7870`).
+- Bug in ``date_range()``/``DatetimeIndex()`` when the timezone was inferred from input dates yet incorrect
+  times were returned when crossing DST boundaries (:issue:`7835`, :issue:`7901`).  
 
 
 
diff --git a/pandas/tseries/index.py b/pandas/tseries/index.py
index 5f7c93d38653a..80f9e6cd8db7a 100644
--- a/pandas/tseries/index.py
+++ b/pandas/tseries/index.py
@@ -416,7 +416,7 @@ def _generate(cls, start, end, periods, name, offset,
 
         else:
 
-            if inferred_tz is None and tz is not None:
+            if tz is not None:
                 # naive dates
                 if start is not None and start.tz is not None:
                     start = start.replace(tzinfo=None)
diff --git a/pandas/tseries/tests/test_daterange.py b/pandas/tseries/tests/test_daterange.py
index 81cf34bbc269b..7b0bfa98690e2 100644
--- a/pandas/tseries/tests/test_daterange.py
+++ b/pandas/tseries/tests/test_daterange.py
@@ -354,25 +354,51 @@ def test_range_bug(self):
     def test_range_tz_pytz(self):
         # GH 2906
         tm._skip_if_no_pytz()
-        from pytz import timezone as tz
+        from pytz import timezone
 
-        start = datetime(2011, 1, 1, tzinfo=tz('US/Eastern'))
-        end = datetime(2011, 1, 3, tzinfo=tz('US/Eastern'))
+        tz = timezone('US/Eastern')
+        start = tz.localize(datetime(2011, 1, 1))
+        end = tz.localize(datetime(2011, 1, 3))
 
         dr = date_range(start=start, periods=3)
-        self.assertEqual(dr.tz, tz('US/Eastern'))
+        self.assertEqual(dr.tz.zone, tz.zone)
         self.assertEqual(dr[0], start)
         self.assertEqual(dr[2], end)
 
         dr = date_range(end=end, periods=3)
-        self.assertEqual(dr.tz, tz('US/Eastern'))
+        self.assertEqual(dr.tz.zone, tz.zone)
         self.assertEqual(dr[0], start)
         self.assertEqual(dr[2], end)
 
         dr = date_range(start=start, end=end)
-        self.assertEqual(dr.tz, tz('US/Eastern'))
+        self.assertEqual(dr.tz.zone, tz.zone)
         self.assertEqual(dr[0], start)
         self.assertEqual(dr[2], end)
+    
+    def test_range_tz_dst_straddle_pytz(self):
+        
+        tm._skip_if_no_pytz()
+        from pytz import timezone
+        tz = timezone('US/Eastern')
+        dates = [(tz.localize(datetime(2014, 3, 6)), 
+                  tz.localize(datetime(2014, 3, 12))),
+                 (tz.localize(datetime(2013, 11, 1)), 
+                  tz.localize(datetime(2013, 11, 6)))]
+        for (start, end) in dates:
+            dr = date_range(start, end, freq='D')
+            self.assertEqual(dr[0], start)
+            self.assertEqual(dr[-1], end)
+            self.assertEqual(np.all(dr.hour==0), True)
+            
+            dr = date_range(start, end, freq='D', tz='US/Eastern')
+            self.assertEqual(dr[0], start)
+            self.assertEqual(dr[-1], end)
+            self.assertEqual(np.all(dr.hour==0), True)        
+            
+            dr = date_range(start.replace(tzinfo=None), end.replace(tzinfo=None), freq='D', tz='US/Eastern')
+            self.assertEqual(dr[0], start)
+            self.assertEqual(dr[-1], end)
+            self.assertEqual(np.all(dr.hour==0), True)        
 
     def test_range_tz_dateutil(self):
         # GH 2906