Merge pull request #7798 from sinhrks/tz_convert_bug

jreback · jreback · commit ce5a4ef21ee6 · 2014-08-02T21:41:58.000-04:00
BUG: tslib.tz_convert and tslib.tz_convert_single may output different result in DST
diff --git a/doc/source/v0.15.0.txt b/doc/source/v0.15.0.txt
@@ -233,8 +233,8 @@ Enhancements
 
 
 
-
-
+- Bug in ``tslib.tz_convert`` and ``tslib.tz_convert_single`` may return different results (:issue:`7798`)
+- Bug in ``DatetimeIndex.intersection`` of non-overlapping timestamps with tz raises ``IndexError`` (:issue:`7880`)
 
 
 
diff --git a/pandas/tests/test_frame.py b/pandas/tests/test_frame.py
@@ -12636,23 +12636,6 @@ def test_consolidate_datetime64(self):
         assert_array_equal(df.starting.values, ser_starting.index.values)
         assert_array_equal(df.ending.values, ser_ending.index.values)
 
-    def test_tslib_tz_convert_trans_pos_plus_1__bug(self):
-        # Regression test for tslib.tz_convert(vals, tz1, tz2).
-        # See https://github.com/pydata/pandas/issues/4496 for details.
-        idx = pd.date_range(datetime(2011, 3, 26, 23), datetime(2011, 3, 27, 1), freq='1min')
-        idx = idx.tz_localize('UTC')
-        idx = idx.tz_convert('Europe/Moscow')
-
-        test_vector = pd.Series([3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
-                                 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
-                                 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
-                                 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
-                                 4, 4, 4, 4, 4, 4, 4, 4, 5], dtype=int)
-
-        hours = idx.hour
-
-        np.testing.assert_equal(hours, test_vector.values)
-
     def _check_bool_op(self, name, alternative, frame=None, has_skipna=True,
                        has_bool_only=False):
         if frame is None:
diff --git a/pandas/tseries/frequencies.py b/pandas/tseries/frequencies.py
@@ -683,25 +683,6 @@ def infer_freq(index, warn=True):
 _ONE_HOUR = 60 * _ONE_MINUTE
 _ONE_DAY = 24 * _ONE_HOUR
 
-def _tz_convert_with_transitions(values, to_tz, from_tz):
-    """
-    convert i8 values from the specificed timezone to the to_tz zone, taking
-    into account DST transitions
-    """
-
-    # vectorization is slow, so tests if we can do this via the faster tz_convert
-    f = lambda x: tslib.tz_convert_single(x, to_tz, from_tz)
-
-    if len(values) > 2:
-        first_slow, last_slow = f(values[0]),f(values[-1])
-
-        first_fast, last_fast = tslib.tz_convert(np.array([values[0],values[-1]],dtype='i8'),to_tz,from_tz)
-
-        # don't cross a DST, so ok
-        if first_fast == first_slow and last_fast == last_slow:
-            return tslib.tz_convert(values,to_tz,from_tz)
-
-    return np.vectorize(f)(values)
 
 class _FrequencyInferer(object):
     """
@@ -713,7 +694,7 @@ def __init__(self, index, warn=True):
         self.values = np.asarray(index).view('i8')
 
         if index.tz is not None:
-            self.values = _tz_convert_with_transitions(self.values,'UTC',index.tz)
+            self.values = tslib.tz_convert(self.values, 'UTC', index.tz)
 
         self.warn = warn
 
diff --git a/pandas/tseries/index.py b/pandas/tseries/index.py
@@ -14,7 +14,7 @@
 from pandas.compat import u
 from pandas.tseries.frequencies import (
     infer_freq, to_offset, get_period_alias,
-    Resolution, _tz_convert_with_transitions)
+    Resolution)
 from pandas.core.base import DatetimeIndexOpsMixin
 from pandas.tseries.offsets import DateOffset, generate_range, Tick, CDay
 from pandas.tseries.tools import parse_time_string, normalize_date
@@ -1569,7 +1569,7 @@ def insert(self, loc, item):
             new_dates = np.concatenate((self[:loc].asi8, [item.view(np.int64)],
                                         self[loc:].asi8))
             if self.tz is not None:
-                new_dates = _tz_convert_with_transitions(new_dates,'UTC',self.tz)
+                new_dates = tslib.tz_convert(new_dates, 'UTC', self.tz)
             return DatetimeIndex(new_dates, name=self.name, freq=freq, tz=self.tz)
 
         except (AttributeError, TypeError):
@@ -1606,7 +1606,7 @@ def delete(self, loc):
                     freq = self.freq
 
         if self.tz is not None:
-            new_dates = _tz_convert_with_transitions(new_dates, 'UTC', self.tz)
+            new_dates = tslib.tz_convert(new_dates, 'UTC', self.tz)
         return DatetimeIndex(new_dates, name=self.name, freq=freq, tz=self.tz)
 
     def _view_like(self, ndarray):
diff --git a/pandas/tseries/tests/test_timeseries.py b/pandas/tseries/tests/test_timeseries.py
@@ -3203,8 +3203,8 @@ def test_union(self):
 
     def test_intersection(self):
         # GH 4690 (with tz)
-        for tz in [None, 'Asia/Tokyo']:
-            rng = date_range('6/1/2000', '6/30/2000', freq='D', name='idx')
+        for tz in [None, 'Asia/Tokyo', 'US/Eastern', 'dateutil/US/Pacific']:
+            base = date_range('6/1/2000', '6/30/2000', freq='D', name='idx')
 
             # if target has the same name, it is preserved
             rng2 = date_range('5/15/2000', '6/20/2000', freq='D', name='idx')
@@ -3214,16 +3214,18 @@ def test_intersection(self):
             rng3 = date_range('5/15/2000', '6/20/2000', freq='D', name='other')
             expected3 = date_range('6/1/2000', '6/20/2000', freq='D', name=None)
 
-            result2 = rng.intersection(rng2)
-            result3 = rng.intersection(rng3)
-            for (result, expected) in [(result2, expected2), (result3, expected3)]:
+            rng4 = date_range('7/1/2000', '7/31/2000', freq='D', name='idx')
+            expected4 = DatetimeIndex([], name='idx')
+
+            for (rng, expected) in [(rng2, expected2), (rng3, expected3), (rng4, expected4)]:
+                result = base.intersection(rng)
                 self.assertTrue(result.equals(expected))
                 self.assertEqual(result.name, expected.name)
                 self.assertEqual(result.freq, expected.freq)
                 self.assertEqual(result.tz, expected.tz)
 
             # non-monotonic
-            rng = DatetimeIndex(['2011-01-05', '2011-01-04', '2011-01-02', '2011-01-03'],
+            base = DatetimeIndex(['2011-01-05', '2011-01-04', '2011-01-02', '2011-01-03'],
                                 tz=tz, name='idx')
 
             rng2 = DatetimeIndex(['2011-01-04', '2011-01-02', '2011-02-02', '2011-02-03'],
@@ -3234,10 +3236,12 @@ def test_intersection(self):
                                  tz=tz, name='other')
             expected3 = DatetimeIndex(['2011-01-04', '2011-01-02'], tz=tz, name=None)
 
-            result2 = rng.intersection(rng2)
-            result3 = rng.intersection(rng3)
-            for (result, expected) in [(result2, expected2), (result3, expected3)]:
-                print(result, expected)
+            # GH 7880
+            rng4 = date_range('7/1/2000', '7/31/2000', freq='D', tz=tz, name='idx')
+            expected4 = DatetimeIndex([], tz=tz, name='idx')
+
+            for (rng, expected) in [(rng2, expected2), (rng3, expected3), (rng4, expected4)]:
+                result = base.intersection(rng)
                 self.assertTrue(result.equals(expected))
                 self.assertEqual(result.name, expected.name)
                 self.assertIsNone(result.freq)
diff --git a/pandas/tseries/tests/test_timezones.py b/pandas/tseries/tests/test_timezones.py
@@ -787,6 +787,64 @@ def test_utc_with_system_utc(self):
         # check that the time hasn't changed.
         self.assertEqual(ts, ts.tz_convert(dateutil.tz.tzutc()))
 
+    def test_tslib_tz_convert_trans_pos_plus_1__bug(self):
+        # Regression test for tslib.tz_convert(vals, tz1, tz2).
+        # See https://github.com/pydata/pandas/issues/4496 for details.
+        for freq, n in [('H', 1), ('T', 60), ('S', 3600)]:
+            idx = date_range(datetime(2011, 3, 26, 23), datetime(2011, 3, 27, 1), freq=freq)
+            idx = idx.tz_localize('UTC')
+            idx = idx.tz_convert('Europe/Moscow')
+
+            expected = np.repeat(np.array([3, 4, 5]), np.array([n, n, 1]))
+            self.assert_numpy_array_equal(idx.hour, expected)
+
+    def test_tslib_tz_convert_dst(self):
+        for freq, n in [('H', 1), ('T', 60), ('S', 3600)]:
+            # Start DST
+            idx = date_range('2014-03-08 23:00', '2014-03-09 09:00', freq=freq, tz='UTC')
+            idx = idx.tz_convert('US/Eastern')
+            expected = np.repeat(np.array([18, 19, 20, 21, 22, 23, 0, 1, 3, 4, 5]),
+                                 np.array([n, n, n, n, n, n, n, n, n, n, 1]))
+            self.assert_numpy_array_equal(idx.hour, expected)
+
+            idx = date_range('2014-03-08 18:00', '2014-03-09 05:00', freq=freq, tz='US/Eastern')
+            idx = idx.tz_convert('UTC')
+            expected = np.repeat(np.array([23, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9]),
+                                 np.array([n, n, n, n, n, n, n, n, n, n, 1]))
+            self.assert_numpy_array_equal(idx.hour, expected)
+
+            # End DST
+            idx = date_range('2014-11-01 23:00', '2014-11-02 09:00', freq=freq, tz='UTC')
+            idx = idx.tz_convert('US/Eastern')
+            expected = np.repeat(np.array([19, 20, 21, 22, 23, 0, 1, 1, 2, 3, 4]),
+                                 np.array([n, n, n, n, n, n, n, n, n, n, 1]))
+            self.assert_numpy_array_equal(idx.hour, expected)
+
+            idx = date_range('2014-11-01 18:00', '2014-11-02 05:00', freq=freq, tz='US/Eastern')
+            idx = idx.tz_convert('UTC')
+            expected = np.repeat(np.array([22, 23, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),
+                                 np.array([n, n, n, n, n, n, n, n, n, n, n, n, 1]))
+            self.assert_numpy_array_equal(idx.hour, expected)
+
+        # daily
+        # Start DST
+        idx = date_range('2014-03-08 00:00', '2014-03-09 00:00', freq='D', tz='UTC')
+        idx = idx.tz_convert('US/Eastern')
+        self.assert_numpy_array_equal(idx.hour, np.array([19, 19]))
+
+        idx = date_range('2014-03-08 00:00', '2014-03-09 00:00', freq='D', tz='US/Eastern')
+        idx = idx.tz_convert('UTC')
+        self.assert_numpy_array_equal(idx.hour, np.array([5, 5]))
+
+        # End DST
+        idx = date_range('2014-11-01 00:00', '2014-11-02 00:00', freq='D', tz='UTC')
+        idx = idx.tz_convert('US/Eastern')
+        self.assert_numpy_array_equal(idx.hour, np.array([20, 20]))
+
+        idx = date_range('2014-11-01 00:00', '2014-11-02 000:00', freq='D', tz='US/Eastern')
+        idx = idx.tz_convert('UTC')
+        self.assert_numpy_array_equal(idx.hour, np.array([4, 4]))
+
 
 class TestTimeZoneCacheKey(tm.TestCase):
     def test_cache_keys_are_distinct_for_pytz_vs_dateutil(self):
diff --git a/pandas/tseries/tests/test_tslib.py b/pandas/tseries/tests/test_tslib.py
@@ -425,6 +425,44 @@ def test_period_ordinal_business_day(self):
         # Tuesday
         self.assertEqual(11418, period_ordinal(2013, 10, 8, 0, 0, 0, 0, 0, get_freq('B')))
 
+    def test_tslib_tz_convert(self):
+        def compare_utc_to_local(tz_didx, utc_didx):
+            f = lambda x: tslib.tz_convert_single(x, 'UTC', tz_didx.tz)
+            result = tslib.tz_convert(tz_didx.asi8, 'UTC', tz_didx.tz)
+            result_single = np.vectorize(f)(tz_didx.asi8)
+            self.assert_numpy_array_equal(result, result_single)
+
+        def compare_local_to_utc(tz_didx, utc_didx):
+            f = lambda x: tslib.tz_convert_single(x, tz_didx.tz, 'UTC')
+            result = tslib.tz_convert(utc_didx.asi8, tz_didx.tz, 'UTC')
+            result_single = np.vectorize(f)(utc_didx.asi8)
+            self.assert_numpy_array_equal(result, result_single)
+
+        for tz in ['UTC', 'Asia/Tokyo', 'US/Eastern', 'Europe/Moscow']:
+            # US: 2014-03-09 - 2014-11-11
+            # MOSCOW: 2014-10-26  /  2014-12-31
+            tz_didx = date_range('2014-03-01', '2015-01-10', freq='H', tz=tz)
+            utc_didx = date_range('2014-03-01', '2015-01-10', freq='H')
+            compare_utc_to_local(tz_didx, utc_didx)
+            # local tz to UTC can be differ in hourly (or higher) freqs because of DST
+            compare_local_to_utc(tz_didx, utc_didx)
+
+            tz_didx = date_range('2000-01-01', '2020-01-01', freq='D', tz=tz)
+            utc_didx = date_range('2000-01-01', '2020-01-01', freq='D')
+            compare_utc_to_local(tz_didx, utc_didx)
+            compare_local_to_utc(tz_didx, utc_didx)
+
+            tz_didx = date_range('2000-01-01', '2100-01-01', freq='A', tz=tz)
+            utc_didx = date_range('2000-01-01', '2100-01-01', freq='A')
+            compare_utc_to_local(tz_didx, utc_didx)
+            compare_local_to_utc(tz_didx, utc_didx)
+
+        # Check empty array
+        result = tslib.tz_convert(np.array([], dtype=np.int64),
+                                  tslib.maybe_get_tz('US/Eastern'),
+                                  tslib.maybe_get_tz('Asia/Tokyo'))
+        self.assert_numpy_array_equal(result, np.array([], dtype=np.int64))
+
 class TestTimestampOps(tm.TestCase):
     def test_timestamp_and_datetime(self):
         self.assertEqual((Timestamp(datetime.datetime(2013, 10, 13)) - datetime.datetime(2013, 10, 12)).days, 1)
diff --git a/pandas/tslib.pyx b/pandas/tslib.pyx
@@ -1907,10 +1907,14 @@ def tz_convert(ndarray[int64_t] vals, object tz1, object tz2):
         Py_ssize_t i, pos, n = len(vals)
         int64_t v, offset
         pandas_datetimestruct dts
+        Py_ssize_t trans_len
 
     if not have_pytz:
         import pytz
 
+    if len(vals) == 0:
+        return np.array([], dtype=np.int64)
+
     # Convert to UTC
 
     if _get_zone(tz1) != 'UTC':
@@ -1927,14 +1931,15 @@ def tz_convert(ndarray[int64_t] vals, object tz1, object tz2):
         else:
             deltas = _get_deltas(tz1)
             trans = _get_transitions(tz1)
+            trans_len = len(trans)
             pos = trans.searchsorted(vals[0]) - 1
             if pos < 0:
                 raise ValueError('First time before start of DST info')
 
             offset = deltas[pos]
             for i in range(n):
                 v = vals[i]
-                if v >= [pos + 1]:
+                while pos + 1 < trans_len and v >= trans[pos + 1]:
                     pos += 1
                     offset = deltas[pos]
                 utc_dates[i] = v - offset
@@ -1957,29 +1962,23 @@ def tz_convert(ndarray[int64_t] vals, object tz1, object tz2):
 
     # Convert UTC to other timezone
     trans = _get_transitions(tz2)
+    trans_len = len(trans)
     deltas = _get_deltas(tz2)
-    pos = trans.searchsorted(utc_dates[0])
-    if pos == 0:
+    pos = trans.searchsorted(utc_dates[0]) - 1
+    if pos < 0:
         raise ValueError('First time before start of DST info')
-    elif pos == len(trans):
-        return utc_dates + deltas[-1]
 
     # TODO: this assumed sortedness :/
-    pos -= 1
-
     offset = deltas[pos]
-    cdef Py_ssize_t trans_len = len(trans)
-
     for i in range(n):
         v = utc_dates[i]
         if vals[i] == NPY_NAT:
             result[i] = vals[i]
         else:
-            if (pos + 1) < trans_len and v >= trans[pos + 1]:
+            while pos + 1 < trans_len and v >= trans[pos + 1]:
                 pos += 1
                 offset = deltas[pos]
             result[i] = v + offset
-
     return result
 
 def tz_convert_single(int64_t val, object tz1, object tz2):
@@ -2005,7 +2004,7 @@ def tz_convert_single(int64_t val, object tz1, object tz2):
     elif _get_zone(tz1) != 'UTC':
         deltas = _get_deltas(tz1)
         trans = _get_transitions(tz1)
-        pos = trans.searchsorted(val) - 1
+        pos = trans.searchsorted(val, side='right') - 1
         if pos < 0:
             raise ValueError('First time before start of DST info')
         offset = deltas[pos]
@@ -2024,7 +2023,7 @@ def tz_convert_single(int64_t val, object tz1, object tz2):
     # Convert UTC to other timezone
     trans = _get_transitions(tz2)
     deltas = _get_deltas(tz2)
-    pos = trans.searchsorted(utc_date) - 1
+    pos = trans.searchsorted(utc_date, side='right') - 1
     if pos < 0:
         raise ValueError('First time before start of DST info')
 
