CLN: do length-checking in boilerplate deocrator (#34081)

Author: jbrockmendel

pandas/core/arrays/categorical.py

@@ -66,10 +66,6 @@ def _cat_compare_op(op):
 
     @unpack_zerodim_and_defer(opname)
     def func(self, other):
-        if is_list_like(other) and len(other) != len(self):
-            # TODO: Could this fail if the categories are listlike objects?
-            raise ValueError("Lengths must match.")
-
         if not self.ordered:
             if opname in ["__lt__", "__gt__", "__le__", "__ge__"]:
                 raise TypeError(

pandas/core/arrays/datetimelike.py

@@ -85,9 +85,6 @@ def _validate_comparison_value(self, other):
         elif not is_list_like(other):
             raise InvalidComparison(other)
 
-        elif len(other) != len(self):
-            raise ValueError("Lengths must match")
-
         else:
             try:
                 other = self._validate_listlike(other, opname, allow_object=True)
@@ -1230,9 +1227,6 @@ def _add_timedelta_arraylike(self, other):
         """
         # overridden by PeriodArray
 
-        if len(self) != len(other):
-            raise ValueError("cannot add indices of unequal length")
-
         if isinstance(other, np.ndarray):
             # ndarray[timedelta64]; wrap in TimedeltaIndex for op
             from pandas.core.arrays import TimedeltaArray

pandas/core/arrays/datetimes.py

@@ -652,9 +652,6 @@ def _assert_tzawareness_compat(self, other):
 
     def _sub_datetime_arraylike(self, other):
         """subtract DatetimeArray/Index or ndarray[datetime64]"""
-        if len(self) != len(other):
-            raise ValueError("cannot add indices of unequal length")
-
         if isinstance(other, np.ndarray):
             assert is_datetime64_dtype(other)
             other = type(self)(other)

pandas/core/arrays/integer.py

@@ -517,8 +517,6 @@ def cmp_method(self, other):
                     raise NotImplementedError(
                         "can only perform ops with 1-d structures"
                     )
-                if len(self) != len(other):
-                    raise ValueError("Lengths must match to compare")
 
             if other is libmissing.NA:
                 # numpy does not handle pd.NA well as "other" scalar (it returns
@@ -622,8 +620,6 @@ def integer_arithmetic_method(self, other):
                     raise NotImplementedError(
                         "can only perform ops with 1-d structures"
                     )
-                if len(self) != len(other):
-                    raise ValueError("Lengths must match")
                 if not (is_float_dtype(other) or is_integer_dtype(other)):
                     raise TypeError("can only perform ops with numeric values")
 

pandas/core/arrays/timedeltas.py

@@ -460,10 +460,6 @@ def __mul__(self, other):
         if not hasattr(other, "dtype"):
             # list, tuple
             other = np.array(other)
-        if len(other) != len(self) and not is_timedelta64_dtype(other):
-            # Exclude timedelta64 here so we correctly raise TypeError
-            #  for that instead of ValueError
-            raise ValueError("Cannot multiply with unequal lengths")
 
         if is_object_dtype(other.dtype):
             # this multiplication will succeed only if all elements of other
@@ -507,10 +503,7 @@ def __truediv__(self, other):
             # e.g. list, tuple
             other = np.array(other)
 
-        if len(other) != len(self):
-            raise ValueError("Cannot divide vectors with unequal lengths")
-
-        elif is_timedelta64_dtype(other.dtype):
+        if is_timedelta64_dtype(other.dtype):
             # let numpy handle it
             return self._data / other
 
@@ -560,10 +553,7 @@ def __rtruediv__(self, other):
             # e.g. list, tuple
             other = np.array(other)
 
-        if len(other) != len(self):
-            raise ValueError("Cannot divide vectors with unequal lengths")
-
-        elif is_timedelta64_dtype(other.dtype):
+        if is_timedelta64_dtype(other.dtype):
             # let numpy handle it
             return other / self._data
 
@@ -612,10 +602,8 @@ def __floordiv__(self, other):
         if not hasattr(other, "dtype"):
             # list, tuple
             other = np.array(other)
-        if len(other) != len(self):
-            raise ValueError("Cannot divide with unequal lengths")
 
-        elif is_timedelta64_dtype(other.dtype):
+        if is_timedelta64_dtype(other.dtype):
             other = type(self)(other)
 
             # numpy timedelta64 does not natively support floordiv, so operate
@@ -666,10 +654,8 @@ def __rfloordiv__(self, other):
         if not hasattr(other, "dtype"):
             # list, tuple
             other = np.array(other)
-        if len(other) != len(self):
-            raise ValueError("Cannot divide with unequal lengths")
 
-        elif is_timedelta64_dtype(other.dtype):
+        if is_timedelta64_dtype(other.dtype):
             other = type(self)(other)
 
             # numpy timedelta64 does not natively support floordiv, so operate

pandas/core/indexes/base.py

@@ -75,6 +75,7 @@
 from pandas.core.indexes.frozen import FrozenList
 import pandas.core.missing as missing
 from pandas.core.ops import get_op_result_name
+from pandas.core.ops.common import unpack_zerodim_and_defer
 from pandas.core.ops.invalid import make_invalid_op
 from pandas.core.sorting import ensure_key_mapped
 from pandas.core.strings import StringMethods
@@ -108,10 +109,8 @@
 
 
 def _make_comparison_op(op, cls):
+    @unpack_zerodim_and_defer(op.__name__)
     def cmp_method(self, other):
-        if isinstance(other, (np.ndarray, Index, ABCSeries, ExtensionArray)):
-            if other.ndim > 0 and len(self) != len(other):
-                raise ValueError("Lengths must match to compare")
 
         if is_object_dtype(self.dtype) and isinstance(other, ABCCategorical):
             left = type(other)(self._values, dtype=other.dtype)

pandas/core/ops/common.py

@@ -1,10 +1,13 @@
 """
 Boilerplate functions used in defining binary operations.
 """
+from collections import UserDict
 from functools import wraps
 from typing import Callable
 
-from pandas._libs.lib import item_from_zerodim
+import numpy as np
+
+from pandas._libs.lib import is_list_like, item_from_zerodim
 from pandas._typing import F
 
 from pandas.core.dtypes.generic import ABCDataFrame, ABCIndexClass, ABCSeries
@@ -62,6 +65,25 @@ def new_method(self, other):
 
         other = item_from_zerodim(other)
 
+        if isinstance(self, (ABCSeries, ABCDataFrame)) and isinstance(
+            other, (ABCSeries, ABCDataFrame)
+        ):
+            # we dont require length matches
+            pass
+        elif is_list_like(other, allow_sets=False) and not isinstance(
+            other, (dict, UserDict)
+        ):
+            if len(other) != len(self):
+                if len(other) == 1 and not hasattr(other, "dtype"):
+                    # i.e. unpack scalar list, but leave e.g. Categorical,
+                    #  for which the scalar behavior doesnt match the
+                    #  array behavior
+                    other = other[0]
+                else:
+                    raise ValueError(
+                        "Lengths must match", self.shape, np.shape(other), type(other)
+                    )
+
         return method(self, other)
 
     return new_method

pandas/tests/arithmetic/test_datetime64.py

@@ -2206,7 +2206,7 @@ def test_sub_dti_dti(self):
         # different length raises ValueError
         dti1 = date_range("20130101", periods=3)
         dti2 = date_range("20130101", periods=4)
-        msg = "cannot add indices of unequal length"
+        msg = "Lengths must match"
         with pytest.raises(ValueError, match=msg):
             dti1 - dti2
 

pandas/tests/arithmetic/test_numeric.py

@@ -647,7 +647,7 @@ def test_mul_datelike_raises(self, numeric_idx):
 
     def test_mul_size_mismatch_raises(self, numeric_idx):
         idx = numeric_idx
-        msg = "operands could not be broadcast together"
+        msg = "Lengths must match"
         with pytest.raises(ValueError, match=msg):
             idx * idx[0:3]
         with pytest.raises(ValueError, match=msg):

pandas/tests/arithmetic/test_timedelta64.py

@@ -451,7 +451,7 @@ def test_addition_ops(self):
         tm.assert_index_equal(result, expected)
 
         # unequal length
-        msg = "cannot add indices of unequal length"
+        msg = "Lengths must match"
         with pytest.raises(ValueError, match=msg):
             tdi + dti[0:1]
         with pytest.raises(ValueError, match=msg):
@@ -1730,7 +1730,7 @@ def test_tdarr_div_length_mismatch(self, box_with_array):
         mismatched = [1, 2, 3, 4]
 
         rng = tm.box_expected(rng, box_with_array)
-        msg = "Cannot divide vectors|Unable to coerce to Series"
+        msg = "Lengths must match|Unable to coerce to Series"
         for obj in [mismatched, mismatched[:2]]:
             # one shorter, one longer
             for other in [obj, np.array(obj), pd.Index(obj)]:
@@ -1912,12 +1912,15 @@ def test_td64arr_mul_tdscalar_invalid(self, box_with_array, scalar_td):
     def test_td64arr_mul_too_short_raises(self, box_with_array):
         idx = TimedeltaIndex(np.arange(5, dtype="int64"))
         idx = tm.box_expected(idx, box_with_array)
-        msg = (
-            "cannot use operands with types dtype|"
-            "Cannot multiply with unequal lengths|"
-            "Unable to coerce to Series"
+        msg = "|".join(
+            [
+                "Lengths must match",  # <- EA, Index, Series
+                "cannot use operands with types dtype",  # <- DataFrame
+                "Unable to coerce to Series",  # <- Series
+            ]
         )
-        with pytest.raises(TypeError, match=msg):
+        with pytest.raises((ValueError, TypeError), match=msg):
+            # length check before dtype check
             idx * idx[:3]
         with pytest.raises(ValueError, match=msg):
             idx * np.array([1, 2])

pandas/tests/arrays/boolean/test_logical.py

@@ -46,7 +46,7 @@ def test_empty_ok(self, all_logical_operators):
     def test_logical_length_mismatch_raises(self, all_logical_operators):
         op_name = all_logical_operators
         a = pd.array([True, False, None], dtype="boolean")
-        msg = "Lengths must match to compare"
+        msg = "Lengths must match"
 
         with pytest.raises(ValueError, match=msg):
             getattr(a, op_name)([True, False])

pandas/tests/arrays/integer/test_arithmetic.py

@@ -232,8 +232,9 @@ def test_error(self, data, all_arithmetic_operators):
         result = opa(pd.DataFrame({"A": s}))
         assert result is NotImplemented
 
-        msg = r"can only perform ops with 1-d structures"
-        with pytest.raises(NotImplementedError, match=msg):
+        # msg = r"can only perform ops with 1-d structures"
+        msg = "Lengths must match"
+        with pytest.raises(ValueError, match=msg):
             opa(np.arange(len(s)).reshape(-1, len(s)))
 
     @pytest.mark.parametrize("zero, negative", [(0, False), (0.0, False), (-0.0, True)])

pandas/tests/arrays/string_/test_string.py

@@ -98,7 +98,7 @@ def test_add_2d():
         a + b
 
     s = pd.Series(a)
-    with pytest.raises(ValueError, match="3 != 1"):
+    with pytest.raises(ValueError, match="Lengths must match"):
         s + b
 
 

pandas/tests/indexes/interval/test_interval.py

@@ -575,7 +575,7 @@ def test_comparison(self):
         msg = r"unorderable types: Interval\(\) > int\(\)"
         with pytest.raises(TypeError, match=msg):
             self.index > np.arange(2)
-        msg = "Lengths must match to compare"
+        msg = "Lengths must match"
         with pytest.raises(ValueError, match=msg):
             self.index > np.arange(3)