Merge pull request #11134 from chris-b1/timedelta-hash

BUG: nested construction with timedelta #11129

Author: jreback

doc/source/whatsnew/v0.17.0.txt

@@ -1155,3 +1155,4 @@ Bug Fixes
 - Remove use of some deprecated numpy comparison operations, mainly in tests. (:issue:`10569`)
 - Bug in ``Index`` dtype may not applied properly (:issue:`11017`)
 - Bug in ``io.gbq`` when testing for minimum google api client version (:issue:`10652`)
+- Bug in ``DataFrame`` construction from nested ``dict`` with ``timedelta`` keys (:issue:`11129`)

pandas/core/common.py

@@ -1848,9 +1848,9 @@ def _maybe_box(indexer, values, obj, key):
 def _maybe_box_datetimelike(value):
     # turn a datetime like into a Timestamp/timedelta as needed
 
-    if isinstance(value, np.datetime64):
+    if isinstance(value, (np.datetime64, datetime)):
         value = tslib.Timestamp(value)
-    elif isinstance(value, np.timedelta64):
+    elif isinstance(value, (np.timedelta64, timedelta)):
         value = tslib.Timedelta(value)
 
     return value

pandas/tests/test_frame.py

@@ -3037,6 +3037,29 @@ def create_data(constructor):
         assert_frame_equal(result_datetime, expected)
         assert_frame_equal(result_Timestamp, expected)
 
+    def test_constructor_dict_timedelta64_index(self):
+        # GH 10160
+        td_as_int = [1, 2, 3, 4]
+
+        def create_data(constructor):
+            return dict((i, {constructor(s): 2*i}) for i, s in enumerate(td_as_int))
+
+        data_timedelta64 = create_data(lambda x: np.timedelta64(x, 'D'))
+        data_timedelta = create_data(lambda x: timedelta(days=x))
+        data_Timedelta = create_data(lambda x: Timedelta(x, 'D'))
+
+        expected = DataFrame([{0: 0, 1: None, 2: None, 3: None},
+                              {0: None, 1: 2, 2: None, 3: None},
+                              {0: None, 1: None, 2: 4, 3: None},
+                              {0: None, 1: None, 2: None, 3: 6}],
+                             index=[Timedelta(td, 'D') for td in td_as_int])
+
+        result_timedelta64 = DataFrame(data_timedelta64)
+        result_timedelta = DataFrame(data_timedelta)
+        result_Timedelta = DataFrame(data_Timedelta)
+        assert_frame_equal(result_timedelta64, expected)
+        assert_frame_equal(result_timedelta, expected)
+        assert_frame_equal(result_Timedelta, expected)
 
     def _check_basic_constructor(self, empty):
         "mat: 2d matrix with shpae (3, 2) to input. empty - makes sized objects"

pandas/tseries/tests/test_timedeltas.py

@@ -885,6 +885,24 @@ def test_pickle(self):
         v_p = self.round_trip_pickle(v)
         self.assertEqual(v,v_p)
 
+    def test_timedelta_hash_equality(self):
+        #GH 11129
+        v = Timedelta(1, 'D')
+        td = timedelta(days=1)
+        self.assertEqual(hash(v), hash(td))
+
+        d = {td: 2}
+        self.assertEqual(d[v], 2)
+
+        tds = timedelta_range('1 second', periods=20)
+        self.assertTrue(
+            all(hash(td) == hash(td.to_pytimedelta()) for td in tds))
+
+        # python timedeltas drop ns resolution
+        ns_td = Timedelta(1, 'ns')
+        self.assertNotEqual(hash(ns_td), hash(ns_td.to_pytimedelta()))
+
+
 class TestTimedeltaIndex(tm.TestCase):
     _multiprocess_can_split_ = True
 

pandas/tslib.pyx

@@ -2061,7 +2061,10 @@ cdef class _Timedelta(timedelta):
         int64_t _sign, _d, _h, _m, _s, _ms, _us, _ns
 
     def __hash__(_Timedelta self):
-        return hash(self.value)
+        if self._has_ns():
+            return hash(self.value)
+        else:
+            return timedelta.__hash__(self)
 
     def __richcmp__(_Timedelta self, object other, int op):
         cdef:
@@ -2110,63 +2113,63 @@ cdef class _Timedelta(timedelta):
         cdef float64_t frac
 
         if self.is_populated:
-           return
+            return
 
         # put frac in seconds
-        frac   = float(ivalue)/1e9
+        frac = float(ivalue)/1e9
         if frac < 0:
-           self._sign = -1
-
-           # even fraction
-           if int(-frac/86400) != -frac/86400.0:
-               self._d = int(-frac/86400.0+1)
-               frac += 86400*self._d
-           else:
-               frac = -frac
+            self._sign = -1
+
+            # even fraction
+            if int(-frac/86400) != -frac/86400.0:
+                self._d = int(-frac/86400.0+1)
+                frac += 86400*self._d
+            else:
+                frac = -frac
         else:
-           self._sign = 1
-           self._d = 0
+            self._sign = 1
+            self._d = 0
 
         if frac >= 86400:
-           self._d += int(frac / 86400)
-           frac   -= self._d * 86400
+            self._d += int(frac / 86400)
+            frac   -= self._d * 86400
 
         if frac >= 3600:
-           self._h  = int(frac / 3600)
-           frac    -= self._h * 3600
+            self._h  = int(frac / 3600)
+            frac    -= self._h * 3600
         else:
-           self._h = 0
+            self._h = 0
 
         if frac >= 60:
-           self._m = int(frac / 60)
-           frac   -= self._m * 60
+            self._m = int(frac / 60)
+            frac   -= self._m * 60
         else:
-           self._m = 0
+            self._m = 0
 
         if frac >= 0:
-           self._s = int(frac)
-           frac   -= self._s
+            self._s = int(frac)
+            frac   -= self._s
         else:
-           self._s = 0
+            self._s = 0
 
         if frac != 0:
 
-           # reset so we don't lose precision
-           sfrac = int((self._h*3600 + self._m*60 + self._s)*1e9)
-           if self._sign < 0:
-               ifrac = ivalue + self._d*DAY_NS - sfrac
-           else:
-               ifrac = ivalue - (self._d*DAY_NS + sfrac)
-
-           self._ms = int(ifrac/1e6)
-           ifrac -= self._ms*1000*1000
-           self._us = int(ifrac/1e3)
-           ifrac -= self._us*1000
-           self._ns = ifrac
+            # reset so we don't lose precision
+            sfrac = int((self._h*3600 + self._m*60 + self._s)*1e9)
+            if self._sign < 0:
+                ifrac = ivalue + self._d*DAY_NS - sfrac
+            else:
+                ifrac = ivalue - (self._d*DAY_NS + sfrac)
+
+            self._ms = int(ifrac/1e6)
+            ifrac -= self._ms*1000*1000
+            self._us = int(ifrac/1e3)
+            ifrac -= self._us*1000
+            self._ns = ifrac
         else:
-           self._ms = 0
-           self._us = 0
-           self._ns = 0
+            self._ms = 0
+            self._us = 0
+            self._ns = 0
 
         self.is_populated = 1
 
@@ -2177,6 +2180,9 @@ cdef class _Timedelta(timedelta):
         """
         return timedelta(microseconds=int(self.value)/1000)
 
+    cpdef bint _has_ns(self):
+        return self.value % 1000 != 0
+
 # components named tuple
 Components = collections.namedtuple('Components',['days','hours','minutes','seconds','milliseconds','microseconds','nanoseconds'])
 
@@ -2433,7 +2439,7 @@ class Timedelta(_Timedelta):
         """
         self._ensure_components()
         return self._ns
-    
+
     def total_seconds(self):
         """
         Total duration of timedelta in seconds (to ns precision)