Merge branch 'main' into regular-expression-50465

Author: ShashwatAgrawal20

doc/source/whatsnew/v2.0.0.rst

@@ -496,6 +496,7 @@ Other API changes
   new DataFrame (shallow copy) instead of the original DataFrame, consistent with other
   methods to get a full slice (for example ``df.loc[:]`` or ``df[:]``) (:issue:`49469`)
 - Disallow computing ``cumprod`` for :class:`Timedelta` object; previously this returned incorrect values (:issue:`50246`)
+- :func:`to_datetime` with ``unit`` of either "Y" or "M" will now raise if a sequence contains a non-round ``float`` value, matching the ``Timestamp`` behavior (:issue:`50301`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/_libs/tslib.pyx

@@ -263,9 +263,13 @@ def array_with_unit_to_datetime(
         ndarray[int64_t] iresult
         ndarray[object] oresult
         object tz = None
+        bint is_ym
+        float fval
 
     assert is_ignore or is_coerce or is_raise
 
+    is_ym = unit in "YM"
+
     if unit == "ns":
         result, tz = array_to_datetime(
             values.astype(object, copy=False),
@@ -290,6 +294,18 @@ def array_with_unit_to_datetime(
                 if val != val or val == NPY_NAT:
                     iresult[i] = NPY_NAT
                 else:
+                    if is_ym and is_float_object(val) and not val.is_integer():
+                        # Analogous to GH#47266 for Timestamp
+                        if is_raise:
+                            raise ValueError(
+                                f"Conversion of non-round float with unit={unit} "
+                                "is ambiguous"
+                            )
+                        elif is_ignore:
+                            raise AssertionError
+                        iresult[i] = NPY_NAT
+                        continue
+
                     try:
                         iresult[i] = cast_from_unit(val, unit)
                     except OverflowError:
@@ -306,8 +322,33 @@ def array_with_unit_to_datetime(
                     iresult[i] = NPY_NAT
 
                 else:
+
+                    try:
+                        fval = float(val)
+                    except ValueError:
+                        if is_raise:
+                            raise ValueError(
+                                f"non convertible value {val} with the unit '{unit}'"
+                            )
+                        elif is_ignore:
+                            raise AssertionError
+                        iresult[i] = NPY_NAT
+                        continue
+
+                    if is_ym and not fval.is_integer():
+                        # Analogous to GH#47266 for Timestamp
+                        if is_raise:
+                            raise ValueError(
+                                f"Conversion of non-round float with unit={unit} "
+                                "is ambiguous"
+                            )
+                        elif is_ignore:
+                            raise AssertionError
+                        iresult[i] = NPY_NAT
+                        continue
+
                     try:
-                        iresult[i] = cast_from_unit(float(val), unit)
+                        iresult[i] = cast_from_unit(fval, unit)
                     except ValueError:
                         if is_raise:
                             raise ValueError(
@@ -345,6 +386,7 @@ def array_with_unit_to_datetime(
     # and are in ignore mode
     # redo as object
 
+    # TODO: fix subtle differences between this and no-unit code
     oresult = cnp.PyArray_EMPTY(values.ndim, values.shape, cnp.NPY_OBJECT, 0)
     for i in range(n):
         val = values[i]
@@ -357,7 +399,7 @@ def array_with_unit_to_datetime(
                 oresult[i] = <object>NaT
             else:
                 try:
-                    oresult[i] = Timestamp(cast_from_unit(val, unit))
+                    oresult[i] = Timestamp(val, unit=unit)
                 except OverflowError:
                     oresult[i] = val
 

pandas/tests/tools/test_to_datetime.py

@@ -1498,6 +1498,38 @@ def test_to_datetime_fixed_offset(self):
 
 
 class TestToDatetimeUnit:
+    @pytest.mark.parametrize("unit", ["Y", "M"])
+    def test_to_datetime_month_or_year_unit_non_round_float(self, cache, unit):
+        # GH#50301
+        # Match Timestamp behavior in disallowing non-round floats with
+        #  Y or M unit
+        msg = f"Conversion of non-round float with unit={unit} is ambiguous"
+        with pytest.raises(ValueError, match=msg):
+            to_datetime([1.5], unit=unit, errors="raise")
+        with pytest.raises(ValueError, match=msg):
+            to_datetime(["1.5"], unit=unit, errors="raise")
+
+        # with errors="ignore" we also end up raising within the Timestamp
+        #  constructor; this may not be ideal
+        with pytest.raises(ValueError, match=msg):
+            to_datetime([1.5], unit=unit, errors="ignore")
+        # TODO: we are NOT consistent with the Timestamp behavior in the
+        #  float-like string case
+        # with pytest.raises(ValueError, match=msg):
+        #    to_datetime(["1.5"], unit=unit, errors="ignore")
+
+        res = to_datetime([1.5], unit=unit, errors="coerce")
+        expected = Index([NaT], dtype="M8[ns]")
+        tm.assert_index_equal(res, expected)
+
+        res = to_datetime(["1.5"], unit=unit, errors="coerce")
+        tm.assert_index_equal(res, expected)
+
+        # round floats are OK
+        res = to_datetime([1.0], unit=unit)
+        expected = to_datetime([1], unit=unit)
+        tm.assert_index_equal(res, expected)
+
     def test_unit(self, cache):
         # GH 11758
         # test proper behavior with errors