BUG/API: to_timedelta unit-argument ignored for string input

doc/source/whatsnew/v1.1.0.rst

@@ -701,6 +701,8 @@ Deprecations
   instead (:issue:`34191`).
 - The ``squeeze`` keyword in the ``groupby`` function is deprecated and will be removed in a future version (:issue:`32380`)
 
+- A timedelta passed a number string without a defined unit is deprecated (:issue:`12136`)
+
 .. ---------------------------------------------------------------------------
 
 
@@ -777,6 +779,7 @@ Timedelta
 - Bug in :func:`timedelta_range` that produced an extra point on a edge case (:issue:`30353`, :issue:`33498`)
 - Bug in :meth:`DataFrame.resample` that produced an extra point on a edge case (:issue:`30353`, :issue:`13022`, :issue:`33498`)
 - Bug in :meth:`DataFrame.resample` that ignored the ``loffset`` argument when dealing with timedelta (:issue:`7687`, :issue:`33498`)
+- Bug in :class:`Timedelta` (and :func: `to_timedelta`) where passing a string of a pure number would not take the unit into account. Now raises for an ambiguous or duplicate unit specification.(:issue:`12136`)
 
 Timezones
 ^^^^^^^^^

pandas/_libs/tslibs/timedeltas.pxd

@@ -1,6 +1,7 @@
 from numpy cimport int64_t
 
 # Exposed for tslib, not intended for outside use.
+cpdef parse_timedelta_string(object ts, object specified_unit=*)
 cpdef int64_t delta_to_nanoseconds(delta) except? -1
-cdef convert_to_timedelta64(object ts, object unit)
+cpdef convert_to_timedelta64(object ts, object unit=*)
 cdef bint is_any_td_scalar(object obj)

pandas/_libs/tslibs/timedeltas.pyx

@@ -1,4 +1,5 @@
 import collections
+import warnings
 
 import cython
 
@@ -160,7 +161,7 @@ cpdef int64_t delta_to_nanoseconds(delta) except? -1:
     raise TypeError(type(delta))
 
 
-cdef convert_to_timedelta64(object ts, object unit):
+cpdef convert_to_timedelta64(object ts, object unit=None):
     """
     Convert an incoming object to a timedelta64 if possible.
     Before calling, unit must be standardized to avoid repeated unit conversion
@@ -174,6 +175,8 @@ cdef convert_to_timedelta64(object ts, object unit):
 
     Return an ns based int64
     """
+    if unit is None:
+        unit = 'ns'
     if checknull_with_nat(ts):
         return np.timedelta64(NPY_NAT)
     elif isinstance(ts, _Timedelta):
@@ -218,7 +221,7 @@ cdef convert_to_timedelta64(object ts, object unit):
 
 @cython.boundscheck(False)
 @cython.wraparound(False)
-def array_to_timedelta64(object[:] values, unit='ns', errors='raise'):
+def array_to_timedelta64(object[:] values, unit=None, errors='raise'):
     """
     Convert an ndarray to an array of timedeltas. If errors == 'coerce',
     coerce non-convertible objects to NaT. Otherwise, raise.
@@ -240,13 +243,8 @@ def array_to_timedelta64(object[:] values, unit='ns', errors='raise'):
     # this is where all of the error handling will take place.
     try:
         for i in range(n):
-            if values[i] is NaT:
-                # we allow this check in the fast-path because NaT is a C-object
-                #  so this is an inexpensive check
-                iresult[i] = NPY_NAT
-            else:
-                result[i] = parse_timedelta_string(values[i])
-    except (TypeError, ValueError):
+            result[i] = parse_timedelta_string(values[i], specified_unit=unit)
+    except:
         unit = parse_timedelta_unit(unit)
         for i in range(n):
             try:
@@ -260,7 +258,7 @@ def array_to_timedelta64(object[:] values, unit='ns', errors='raise'):
     return iresult.base  # .base to access underlying np.ndarray
 
 
-cdef inline int64_t parse_timedelta_string(str ts) except? -1:
+cpdef inline parse_timedelta_string(object ts, specified_unit=None):
     """
     Parse a regular format timedelta string. Return an int64_t (in ns)
     or raise a ValueError on an invalid parse.
@@ -371,6 +369,17 @@ cdef inline int64_t parse_timedelta_string(str ts) except? -1:
             have_value = 1
             have_dot = 0
 
+    # Consider units from outside
+    if not unit:
+        if specified_unit:
+            unit = [specified_unit]
+    else:
+        if specified_unit:
+            raise ValueError(
+                "units were doubly specified, both as an argument ({}) "
+                "and inside string ({})".format(specified_unit, unit)
+            )
+
     # we had a dot, but we have a fractional
     # value since we have an unit
     if have_dot and len(unit):
@@ -412,14 +421,17 @@ cdef inline int64_t parse_timedelta_string(str ts) except? -1:
         else:
             raise ValueError("unit abbreviation w/o a number")
 
-    # treat as nanoseconds
-    # but only if we don't have anything else
+    # raise if we just have a number without units
     else:
         if have_value:
             raise ValueError("have leftover units")
         if len(number):
-            r = timedelta_from_spec(number, frac, 'ns')
-            result += timedelta_as_neg(r, neg)
+            warnings.warn(
+            "number string without units is deprecated and "
+            "will raise an exception in future versions. Considering as nanoseconds.",
+            FutureWarning
+            )
+            result = timedelta_from_spec(number, frac, 'ns')
 
     return result
 
@@ -478,10 +490,12 @@ cpdef inline str parse_timedelta_unit(object unit):
     ------
     ValueError : on non-parseable input
     """
-    if unit is None:
-        return "ns"
-    elif unit == "M":
+
+    # Preserve unit if None, will be cast to nanoseconds
+    # later on at the proper functions
+    if unit is None or unit == 'M':
         return unit
+
     try:
         return timedelta_abbrevs[unit.lower()]
     except (KeyError, AttributeError):
@@ -1158,7 +1172,7 @@ class Timedelta(_Timedelta):
             if len(value) > 0 and value[0] == 'P':
                 value = parse_iso_format_string(value)
             else:
-                value = parse_timedelta_string(value)
+                value = parse_timedelta_string(value, specified_unit=unit)
             value = np.timedelta64(value)
         elif PyDelta_Check(value):
             value = convert_to_timedelta64(value, 'ns')

pandas/core/computation/pytables.py

@@ -200,7 +200,7 @@ def stringify(value):
                 v = v.tz_convert("UTC")
             return TermValue(v, v.value, kind)
         elif kind == "timedelta64" or kind == "timedelta":
-            v = Timedelta(v, unit="s").value
+            v = Timedelta(v).value
             return TermValue(int(v), v, kind)
         elif meta == "category":
             metadata = extract_array(self.metadata, extract_numpy=True)

pandas/core/tools/timedeltas.py

@@ -13,7 +13,7 @@
 from pandas.core.arrays.timedeltas import sequence_to_td64ns
 
 
-def to_timedelta(arg, unit="ns", errors="raise"):
+def to_timedelta(arg, unit=None, box=True, errors="raise"):
     """
     Convert argument to timedelta.
 
@@ -108,7 +108,7 @@ def to_timedelta(arg, unit="ns", errors="raise"):
     return _coerce_scalar_to_timedelta_type(arg, unit=unit, errors=errors)
 
 
-def _coerce_scalar_to_timedelta_type(r, unit="ns", errors="raise"):
+def _coerce_scalar_to_timedelta_type(r, unit=None, box=True, errors="raise"):
     """Convert string 'r' to a timedelta object."""
     try:
         result = Timedelta(r, unit)
@@ -124,7 +124,7 @@ def _coerce_scalar_to_timedelta_type(r, unit="ns", errors="raise"):
     return result
 
 
-def _convert_listlike(arg, unit="ns", errors="raise", name=None):
+def _convert_listlike(arg, unit=None, box=True, errors="raise", name=None):
     """Convert a list of objects to a timedelta index object."""
     if isinstance(arg, (list, tuple)) or not hasattr(arg, "dtype"):
         # This is needed only to ensure that in the case where we end up

pandas/tests/arrays/test_datetimelike.py

@@ -946,7 +946,7 @@ def test_invalid_nat_setitem_array(array, non_casting_nats):
     "array",
     [
         pd.date_range("2000", periods=4).array,
-        pd.timedelta_range("2000", periods=4).array,
+        pd.timedelta_range("2000ns", periods=4).array,
     ],
 )
 def test_to_numpy_extra(array):

pandas/tests/frame/test_arithmetic.py

@@ -396,7 +396,7 @@ def test_floordiv_axis0_numexpr_path(self, opname):
     def test_df_add_td64_columnwise(self):
         # GH 22534 Check that column-wise addition broadcasts correctly
         dti = pd.date_range("2016-01-01", periods=10)
-        tdi = pd.timedelta_range("1", periods=10)
+        tdi = pd.timedelta_range("1ns", periods=10)
         tser = pd.Series(tdi)
         df = pd.DataFrame({0: dti, 1: tdi})
 

pandas/tests/indexes/timedeltas/test_ops.py

@@ -180,7 +180,7 @@ def test_drop_duplicates(self, freq_sample, keep, expected, index):
 
     def test_infer_freq(self, freq_sample):
         # GH#11018
-        idx = pd.timedelta_range("1", freq=freq_sample, periods=10)
+        idx = pd.timedelta_range("1ns", freq=freq_sample, periods=10)
         result = pd.TimedeltaIndex(idx.asi8, freq="infer")
         tm.assert_index_equal(idx, result)
         assert result.freq == freq_sample

pandas/tests/plotting/test_datetimelike.py

@@ -1360,7 +1360,7 @@ def test_format_timedelta_ticks_narrow(self):
 
         expected_labels = [f"00:00:00.0000000{i:0>2d}" for i in np.arange(10)]
 
-        rng = timedelta_range("0", periods=10, freq="ns")
+        rng = timedelta_range("0ns", periods=10, freq="ns")
         df = DataFrame(np.random.randn(len(rng), 3), rng)
         fig, ax = self.plt.subplots()
         df.plot(fontsize=2, ax=ax)
@@ -1384,7 +1384,7 @@ def test_format_timedelta_ticks_wide(self):
             "9 days 06:13:20",
         ]
 
-        rng = timedelta_range("0", periods=10, freq="1 d")
+        rng = timedelta_range("0ns", periods=10, freq="1 d")
         df = DataFrame(np.random.randn(len(rng), 3), rng)
         fig, ax = self.plt.subplots()
         ax = df.plot(fontsize=2, ax=ax)

pandas/tests/resample/test_timedelta.py

@@ -73,7 +73,7 @@ def test_resample_single_period_timedelta():
 def test_resample_timedelta_idempotency():
 
     # GH 12072
-    index = pd.timedelta_range("0", periods=9, freq="10L")
+    index = pd.timedelta_range("0ns", periods=9, freq="10L")
     series = Series(range(9), index=index)
     result = series.resample("10L").mean()
     expected = series

pandas/tests/scalar/timedelta/test_constructors.py

@@ -289,3 +289,28 @@ def test_timedelta_constructor_identity():
     expected = Timedelta(np.timedelta64(1, "s"))
     result = Timedelta(expected)
     assert result is expected
+
+
+@pytest.mark.parametrize(
+    "value, str_unit, unit, expectation",
+    [
+        # Units doubly defined
+        (10, "s", "d", (ValueError, "units were doubly specified")),
+        # Units doubly defined (same)
+        (10, "s", "s", (ValueError, "units were doubly specified")),
+        # No units, decimal string
+        (3.1415, "", None, (ValueError, "no units specified")),
+    ],
+)
+def test_string_with_unit(value, str_unit, unit, expectation):
+    exp, match = expectation
+    with pytest.raises(exp, match=match):
+        val_str = "{}{}".format(value, str_unit)
+        expected_td = Timedelta(value, unit=unit)
+
+        assert Timedelta(val_str, unit=unit) == expected_td
+        assert to_timedelta(val_str, unit=unit) == expected_td
+        assert all(
+            to_timedelta([val_str, val_str], unit=unit)
+            == to_timedelta([expected_td, expected_td])
+        )