BUG: Check for wrong arguments in index subclasses constructors

Tidy up constructor signatures for different types of index

Author: spacesphere

doc/source/whatsnew/v0.23.0.txt

@@ -932,6 +932,7 @@ Indexing
 - Bug in :func:`IntervalIndex.symmetric_difference` where the symmetric difference with a non-``IntervalIndex`` did not raise (:issue:`18475`)
 - Bug in :class:`IntervalIndex` where set operations that returned an empty ``IntervalIndex`` had the wrong dtype (:issue:`19101`)
 - Bug in :meth:`DataFrame.drop_duplicates` where no ``KeyError`` is raised when passing in columns that don't exist on the ``DataFrame`` (issue:`19726`)
+- Bug in ``Index`` subclasses constructors that ignore unexpected keyword arguments (:issue:`19348`)
 
 
 MultiIndex

pandas/core/indexes/category.py

@@ -76,7 +76,7 @@ class CategoricalIndex(Index, accessor.PandasDelegate):
     _attributes = ['name']
 
     def __new__(cls, data=None, categories=None, ordered=None, dtype=None,
-                copy=False, name=None, fastpath=False, **kwargs):
+                copy=False, name=None, fastpath=False):
 
         if fastpath:
             return cls._simple_new(data, name=name, dtype=dtype)

pandas/core/indexes/datetimes.py

@@ -213,6 +213,12 @@ class DatetimeIndex(DatelikeOps, TimelikeOps, DatetimeIndexOpsMixin,
            Attempt to infer fall dst-transition hours based on order
     name : object
         Name to be stored in the index
+    dayfirst : bool, default False
+        If True, parse dates in `data` with the day first order
+        (see `pandas.to_datetime`)
+    yearfirst : bool, default False
+        If True parse dates in `data` with the year first order
+        (see `pandas.to_datetime`)
 
     Attributes
     ----------
@@ -327,10 +333,10 @@ def _add_comparison_methods(cls):
     @deprecate_kwarg(old_arg_name='infer_dst', new_arg_name='ambiguous',
                      mapping={True: 'infer', False: 'raise'})
     def __new__(cls, data=None,
-                freq=None, start=None, end=None, periods=None,
-                copy=False, name=None, tz=None,
-                verify_integrity=True, normalize=False,
-                closed=None, ambiguous='raise', dtype=None, **kwargs):
+                freq=None, start=None, end=None, periods=None, tz=None,
+                verify_integrity=True, normalize=False, closed=None,
+                ambiguous='raise', dayfirst=False, yearfirst=False,
+                dtype=None, copy=False, name=None):
 
         # This allows to later ensure that the 'copy' parameter is honored:
         if isinstance(data, Index):
@@ -341,9 +347,6 @@ def __new__(cls, data=None,
         if name is None and hasattr(data, 'name'):
             name = data.name
 
-        dayfirst = kwargs.pop('dayfirst', None)
-        yearfirst = kwargs.pop('yearfirst', None)
-
         freq_infer = False
         if not isinstance(freq, DateOffset):
 

pandas/core/indexes/interval.py

@@ -213,8 +213,8 @@ class IntervalIndex(IntervalMixin, Index):
 
     _mask = None
 
-    def __new__(cls, data, closed=None, name=None, copy=False, dtype=None,
-                fastpath=False, verify_integrity=True):
+    def __new__(cls, data, closed=None, verify_integrity=True,
+                dtype=None, copy=False, name=None, fastpath=False):
 
         if fastpath:
             return cls._simple_new(data.left, data.right, closed, name,

pandas/core/indexes/multi.py

@@ -208,8 +208,8 @@ class MultiIndex(Index):
     rename = Index.set_names
 
     def __new__(cls, levels=None, labels=None, sortorder=None, names=None,
-                copy=False, verify_integrity=True, _set_identity=True,
-                name=None, **kwargs):
+                verify_integrity=True, _set_identity=True,
+                dtype=None, copy=False, name=None):
 
         # compat with Index
         if name is not None:

pandas/core/indexes/period.py

@@ -234,8 +234,17 @@ def _add_comparison_methods(cls):
         cls.__ge__ = _period_index_cmp('__ge__', cls)
 
     def __new__(cls, data=None, ordinal=None, freq=None, start=None, end=None,
-                periods=None, copy=False, name=None, tz=None, dtype=None,
-                **kwargs):
+                periods=None, tz=None, dtype=None, copy=False, name=None,
+                **fields):
+
+        valid_field_set = {
+            'year', 'month', 'day', 'quarter',
+            'hour', 'minute', 'second'
+        }
+
+        if not set(fields).issubset(valid_field_set):
+            raise TypeError('__new__() got an unexpected keyword argument {}'.
+                            format(list(set(fields) - valid_field_set)[0]))
 
         if periods is not None:
             if is_float(periods):
@@ -267,7 +276,7 @@ def __new__(cls, data=None, ordinal=None, freq=None, start=None, end=None,
                 data = np.asarray(ordinal, dtype=np.int64)
             else:
                 data, freq = cls._generate_range(start, end, periods,
-                                                 freq, kwargs)
+                                                 freq, fields)
             return cls._from_ordinals(data, name=name, freq=freq)
 
         if isinstance(data, PeriodIndex):

pandas/core/indexes/range.py

@@ -65,8 +65,8 @@ class RangeIndex(Int64Index):
     _typ = 'rangeindex'
     _engine_type = libindex.Int64Engine
 
-    def __new__(cls, start=None, stop=None, step=None, name=None, dtype=None,
-                fastpath=False, copy=False, **kwargs):
+    def __new__(cls, start=None, stop=None, step=None,
+                dtype=None, copy=False, name=None, fastpath=False):
 
         if fastpath:
             return cls._simple_new(start, stop, step, name=name)
@@ -550,7 +550,7 @@ def __getitem__(self, key):
             stop = self._start + self._step * stop
             step = self._step * step
 
-            return RangeIndex(start, stop, step, self.name, fastpath=True)
+            return RangeIndex(start, stop, step, name=self.name, fastpath=True)
 
         # fall back to Int64Index
         return super_getitem(key)

pandas/core/indexes/timedeltas.py

@@ -197,10 +197,9 @@ def _add_comparison_methods(cls):
 
     freq = None
 
-    def __new__(cls, data=None, unit=None,
-                freq=None, start=None, end=None, periods=None,
-                copy=False, name=None,
-                closed=None, verify_integrity=True, **kwargs):
+    def __new__(cls, data=None, unit=None, freq=None, start=None, end=None,
+                periods=None, closed=None, verify_integrity=True,
+                dtype=None, copy=False, name=None):
 
         if isinstance(data, TimedeltaIndex) and freq is None and name is None:
             if copy:

pandas/tests/indexes/test_base.py

@@ -2326,3 +2326,10 @@ def test_generated_op_names(opname, indices):
     opname = '__{name}__'.format(name=opname)
     method = getattr(index, opname)
     assert method.__name__ == opname
+
+
+@pytest.mark.parametrize('idx_maker', tm.index_subclass_makers_generator())
+def test_index_subclass_constructor_wrong_kwargs(idx_maker):
+    # GH #19348
+    with tm.assert_raises_regex(TypeError, 'unexpected keyword argument'):
+        idx_maker(foo='bar')

pandas/util/testing.py

@@ -1539,16 +1539,16 @@ def makeUnicodeIndex(k=10, name=None):
     return Index(randu_array(nchars=10, size=k), name=name)
 
 
-def makeCategoricalIndex(k=10, n=3, name=None):
+def makeCategoricalIndex(k=10, n=3, name=None, **kwargs):
     """ make a length k index or n categories """
     x = rands_array(nchars=4, size=n)
-    return CategoricalIndex(np.random.choice(x, k), name=name)
+    return CategoricalIndex(np.random.choice(x, k), name=name, **kwargs)
 
 
-def makeIntervalIndex(k=10, name=None):
+def makeIntervalIndex(k=10, name=None, **kwargs):
     """ make a length k IntervalIndex """
     x = np.linspace(0, 100, num=(k + 1))
-    return IntervalIndex.from_breaks(x, name=name)
+    return IntervalIndex.from_breaks(x, name=name, **kwargs)
 
 
 def makeBoolIndex(k=10, name=None):
@@ -1567,31 +1567,37 @@ def makeUIntIndex(k=10, name=None):
     return Index([2**63 + i for i in lrange(k)], name=name)
 
 
-def makeRangeIndex(k=10, name=None):
-    return RangeIndex(0, k, 1, name=name)
+def makeRangeIndex(k=10, name=None, **kwargs):
+    return RangeIndex(0, k, 1, name=name, **kwargs)
 
 
 def makeFloatIndex(k=10, name=None):
     values = sorted(np.random.random_sample(k)) - np.random.random_sample(1)
     return Index(values * (10 ** np.random.randint(0, 9)), name=name)
 
 
-def makeDateIndex(k=10, freq='B', name=None):
+def makeDateIndex(k=10, freq='B', name=None, **kwargs):
     dt = datetime(2000, 1, 1)
     dr = bdate_range(dt, periods=k, freq=freq, name=name)
-    return DatetimeIndex(dr, name=name)
+    return DatetimeIndex(dr, name=name, **kwargs)
 
 
-def makeTimedeltaIndex(k=10, freq='D', name=None):
-    return TimedeltaIndex(start='1 day', periods=k, freq=freq, name=name)
+def makeTimedeltaIndex(k=10, freq='D', name=None, **kwargs):
+    return TimedeltaIndex(start='1 day', periods=k, freq=freq,
+                          name=name, **kwargs)
 
 
-def makePeriodIndex(k=10, name=None):
+def makePeriodIndex(k=10, name=None, **kwargs):
     dt = datetime(2000, 1, 1)
-    dr = PeriodIndex(start=dt, periods=k, freq='B', name=name)
+    dr = PeriodIndex(start=dt, periods=k, freq='B', name=name, **kwargs)
     return dr
 
 
+def makeMultiIndex(k=10, names=None, **kwargs):
+    return MultiIndex.from_product(
+        (('foo', 'bar'), (1, 2)), names=names, **kwargs)
+
+
 def all_index_generator(k=10):
     """Generator which can be iterated over to get instances of all the various
     index classes.
@@ -1609,6 +1615,17 @@ def all_index_generator(k=10):
         yield make_index_func(k=k)
 
 
+def index_subclass_makers_generator():
+    make_index_funcs = [
+        makeDateIndex, makePeriodIndex,
+        makeTimedeltaIndex, makeRangeIndex,
+        makeIntervalIndex, makeCategoricalIndex,
+        makeMultiIndex
+    ]
+    for make_index_func in make_index_funcs:
+        yield make_index_func
+
+
 def all_timeseries_index_generator(k=10):
     """Generator which can be iterated over to get instances of all the classes
     which represent time-seires.