BUG: Fix Series constructor for Categorical with index

Fixes Series constructor so that ValueError is raised when a Categorical and index of different length are given.

Author: cbertinato

doc/source/whatsnew/v0.23.0.txt

@@ -844,6 +844,7 @@ Reshaping
 - Improved error message for :func:`DataFrame.merge` when there is no common merge key (:issue:`19427`)
 - Bug in :func:`DataFrame.join` which does an *outer* instead of a *left* join when being called with multiple DataFrames and some have non-unique indices (:issue:`19624`)
 - :func:`Series.rename` now accepts ``axis`` as a kwarg (:issue:`18589`)
+- Bug in :class:`Series` constructor with ``Categorical`` where an error is not raised when an index of different length is given (:issue:`19342`)
 
 Other
 ^^^^^

pandas/core/series.py

@@ -210,6 +210,7 @@ def __init__(self, data=None, index=None, dtype=None, name=None,
                     raise ValueError("cannot specify a dtype with a "
                                      "Categorical unless "
                                      "dtype='category'")
+
             elif (isinstance(data, types.GeneratorType) or
                   (compat.PY3 and isinstance(data, map))):
                 data = list(data)
@@ -238,6 +239,11 @@ def __init__(self, data=None, index=None, dtype=None, name=None,
                 data = _sanitize_array(data, index, dtype, copy,
                                        raise_cast_failure=True)
 
+                if index is not None and len(index) != len(data):
+                    raise ValueError('Length of passed values is {val}, '
+                                     'index implies {ind}'
+                                     .format(val=len(data), ind=len(index)))
+
                 data = SingleBlockManager(data, index, fastpath=True)
 
         generic.NDFrame.__init__(self, data, fastpath=True)

pandas/tests/series/test_constructors.py

@@ -5,6 +5,7 @@
 
 from datetime import datetime, timedelta
 from collections import OrderedDict
+import types
 
 from numpy import nan
 import numpy as np
@@ -22,6 +23,7 @@
 from pandas._libs import lib
 from pandas._libs.tslib import iNaT
 
+from pandas import compat
 from pandas.compat import lrange, range, zip, long
 from pandas.util.testing import assert_series_equal
 import pandas.util.testing as tm
@@ -393,6 +395,20 @@ def test_constructor_default_index(self):
         s = Series([0, 1, 2])
         tm.assert_index_equal(s.index, pd.Index(np.arange(3)))
 
+    @pytest.mark.parametrize('input', [[1, 2, 3],
+                                       (1, 2, 3),
+                                       list(range(3)),
+                                       pd.Categorical(['a', 'b', 'a']),
+                                       (i for i in range(3)),
+                                       map(lambda x: x, range(3))])
+    def test_constructor_index_mismatch(self, input):
+        # GH 19342
+        # test that construction of a Series with an index of different length
+        # raises an error
+        msg = 'Length of passed values is 3, index implies 4'
+        with pytest.raises(ValueError, message=msg):
+            Series(input, index=np.arange(4))
+
     def test_constructor_corner(self):
         df = tm.makeTimeDataFrame()
         objs = [df, df]