Attempt better error for mismatched index, data

Author: Lewiscowles1986

pandas/core/internals/construction.py

@@ -10,6 +10,7 @@
 
 from pandas._libs import lib
 from pandas._typing import Axis, DtypeObj, Scalar
+from pandas.errors import MismatchedIndexValueError
 
 from pandas.core.dtypes.cast import (
     construct_1d_arraylike_from_scalar,
@@ -743,10 +744,13 @@ def sanitize_index(data, index: Index):
     Sanitize an index type to return an ndarray of the underlying, pass
     through a non-Index.
     """
-    if len(data) > len(index):
-        raise ValueError("Length of values is greater than length of index")
-    if len(index) > len(data):
-        raise ValueError("Length of index is greater than length of values")
+    if len(data) != len(index):
+        raise MismatchedIndexValueError(
+            "Length of values "
+            f"({len(data)}) "
+            "does not match length of index "
+            f"({len(index)})"
+        )
 
     if isinstance(data, np.ndarray):
 

pandas/errors/__init__.py

@@ -208,3 +208,9 @@ class InvalidIndexError(Exception):
 
     .. versionadded:: 1.1.0
     """
+
+
+class MismatchedIndexValueError(ValueError):
+    """
+    Error raised when Index and Value are mismatched
+    """

pandas/tests/extension/base/setitem.py

@@ -1,8 +1,10 @@
 import numpy as np
 import pytest
 
+from pandas.errors import MismatchedIndexValueError
+
 import pandas as pd
-import pandas._testing as tm
+from pandas import _testing as tm
 
 from .base import BaseExtensionTests
 
@@ -244,8 +246,10 @@ def test_setitem_expand_with_extension(self, data):
 
     def test_setitem_frame_invalid_length(self, data):
         df = pd.DataFrame({"A": [1] * len(data)})
-        xpr = "Length of values does not match length of index"
-        with pytest.raises(ValueError, match=xpr):
+        xpr = (
+            f"Length of values \({len(data[:5])}\) "
+            f"does not match length of index \({len(df)}\)")
+        with pytest.raises(MismatchedIndexValueError, match=xpr):
             df["B"] = data[:5]
 
     @pytest.mark.xfail(reason="GH#20441: setitem on extension types.")

pandas/tests/frame/indexing/test_indexing.py

@@ -5,6 +5,7 @@
 import pytest
 
 from pandas._libs import iNaT
+from pandas.errors import MismatchedIndexValueError
 
 from pandas.core.dtypes.common import is_float_dtype, is_integer
 
@@ -16,12 +17,12 @@
     MultiIndex,
     Series,
     Timestamp,
+    _testing as tm,
     date_range,
     isna,
     notna,
 )
-import pandas._testing as tm
-import pandas.core.common as com
+from pandas.core import common as com
 from pandas.core.indexing import IndexingError
 
 from pandas.tseries.offsets import BDay
@@ -160,10 +161,12 @@ def test_setitem_list(self, float_frame):
         msg = "Columns must be same length as key"
         with pytest.raises(ValueError, match=msg):
             data[["A"]] = float_frame[["A", "B"]]
-
-        msg = "Length of values does not match length of index"
-        with pytest.raises(ValueError, match=msg):
-            data["A"] = range(len(data.index) - 1)
+        newcolumndata = range(len(data.index) - 1)
+        msg = (
+            f"Length of values \({len(newcolumndata)}\) "
+            f"does not match length of index \({len(data)}\)")
+        with pytest.raises(MismatchedIndexValueError, match=msg):
+            data["A"] = newcolumndata
 
         df = DataFrame(0, index=range(3), columns=["tt1", "tt2"], dtype=np.int_)
         df.loc[1, ["tt1", "tt2"]] = [1, 2]

pandas/tests/frame/indexing/test_setitem.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas.errors import MismatchedIndexValueError
+
 from pandas.core.dtypes.dtypes import DatetimeTZDtype, IntervalDtype, PeriodDtype
 
 from pandas import (
@@ -117,8 +119,11 @@ def test_setitem_wrong_length_categorical_dtype_raises(self):
         cat = Categorical.from_codes([0, 1, 1, 0, 1, 2], ["a", "b", "c"])
         df = DataFrame(range(10), columns=["bar"])
 
-        msg = "Length of values does not match length of index"
-        with pytest.raises(ValueError, match=msg):
+        msg = (
+            f"Length of values \({len(cat)}\) "
+            f"does not match length of index \({len(df)}\)"
+        )
+        with pytest.raises(MismatchedIndexValueError, match=msg):
             df["foo"] = cat
 
     def test_setitem_with_sparse_value(self):