def astype(self, dtype, copy=True):
if is_interval_dtype(dtype):
if copy:
self = self.copy()
return self
elif is_object_dtype(dtype):
return Index(self.values, dtype=object)
elif is_categorical_dtype(dtype):
from pandas import Categorical
return Categorical(self, ordered=True)
raise ValueError('Cannot cast IntervalIndex to dtype %s' % dtype)
def _evaluate_numeric_binop(self, other):
other = self._validate_for_numeric_binop(other, op, opstr)
attrs = self._get_attributes_dict()
attrs = self._maybe_update_attributes(attrs)
if reversed:
self, other = other, self
try:
# alppy if we have an override
if step:
with np.errstate(all='ignore'):
rstep = step(self._step, other)
# we don't have a representable op
# so return a base index
if not is_integer(rstep) or not rstep:
raise ValueError
else:
rstep = self._step
with np.errstate(all='ignore'):
rstart = op(self._start, other)
rstop = op(self._stop, other)
result = RangeIndex(rstart,
rstop,
rstep,
**attrs)
# for compat with numpy / Int64Index
# even if we can represent as a RangeIndex, return
# as a Float64Index if we have float-like descriptors
if not all([is_integer(x) for x in
[rstart, rstop, rstep]]):
result = result.astype('float64')
return result
except (ValueError, TypeError, AttributeError):
pass
# convert to Int64Index ops
if isinstance(self, RangeIndex):
self = self.values
if isinstance(other, RangeIndex):
other = other.values
with np.errstate(all='ignore'):
results = op(self, other)
return Index(results, **attrs)
def equals(self, other):
if self.is_(other):
return True
# if we can coerce to an II
# then we can compare
if not isinstance(other, IntervalIndex):
if not is_interval_dtype(other):
return False
other = Index(getattr(other, '.values', other))
return (self.left.equals(other.left) and self.right.equals(other.right)
and self.closed == other.closed)
def _get_combined_index(indexes, intersect=False):
# TODO: handle index names!
indexes = _get_distinct_indexes(indexes)
if len(indexes) == 0:
return Index([])
if len(indexes) == 1:
return indexes[0]
if intersect:
index = indexes[0]
for other in indexes[1:]:
index = index.intersection(other)
return index
union = _union_indexes(indexes)
return _ensure_index(union)
def astype(self, dtype, copy=True):
dtype = pandas_dtype(dtype)
if is_float_dtype(dtype):
values = self._values.astype(dtype, copy=copy)
elif is_integer_dtype(dtype):
if self.hasnans:
raise ValueError('cannot convert float NaN to integer')
values = self._values.astype(dtype, copy=copy)
elif is_object_dtype(dtype):
values = self._values.astype('object', copy=copy)
else:
raise TypeError('Setting %s dtype to anything other than '
'float64 or object is not supported' %
self.__class__)
return Index(values, name=self.name, dtype=dtype)
def _convert_list_indexer(self, keyarr, kind=None):
# Return our indexer or raise if all of the values are not included in
# the categories
if self.categories._defer_to_indexing:
indexer = self.categories._convert_list_indexer(keyarr, kind=kind)
return Index(self.codes).get_indexer_for(indexer)
indexer = self.categories.get_indexer(keyarr)
if (indexer == -1).any():
raise KeyError("a list-indexer must only "
"include values that are "
"in the categories")
return self.get_indexer(keyarr)
def _sanitize_and_check(indexes):
kinds = list(set([type(index) for index in indexes]))
if list in kinds:
if len(kinds) > 1:
indexes = [Index(com._try_sort(x))
if not isinstance(x, Index) else
x for x in indexes]
kinds.remove(list)
else:
return indexes, 'list'
if len(kinds) > 1 or Index not in kinds:
return indexes, 'special'
else:
return indexes, 'array'
def _simple_new(cls, start, stop=None, step=None, name=None,
dtype=None, **kwargs):
result = object.__new__(cls)
# handle passed None, non-integers
if start is None or not com.is_integer(start):
try:
return RangeIndex(start, stop, step, name=name, **kwargs)
except TypeError:
return Index(start, stop, step, name=name, **kwargs)
result._start = start
result._stop = stop or 0
result._step = step or 1
result.name = name
for k, v in compat.iteritems(kwargs):
setattr(result, k, v)
result._reset_identity()
return result
def _union_indexes(indexes):
if len(indexes) == 0:
raise AssertionError('Must have at least 1 Index to union')
if len(indexes) == 1:
result = indexes[0]
if isinstance(result, list):
result = Index(sorted(result))
return result
indexes, kind = _sanitize_and_check(indexes)
def _unique_indices(inds):
def conv(i):
if isinstance(i, Index):
i = i.tolist()
return i
return Index(lib.fast_unique_multiple_list([conv(i) for i in inds]))
if kind == 'special':
result = indexes[0]
if hasattr(result, 'union_many'):
return result.union_many(indexes[1:])
else:
for other in indexes[1:]:
result = result.union(other)
return result
elif kind == 'array':
index = indexes[0]
for other in indexes[1:]:
if not index.equals(other):
return _unique_indices(indexes)
name = _get_consensus_names(indexes)[0]
if name != index.name:
index = index._shallow_copy(name=name)
return index
else:
return _unique_indices(indexes)
def reindex(self,
target,
method=None,
level=None,
limit=None,
tolerance=None):
"""
Create index with target's values (move/add/delete values as necessary)
Returns
-------
new_index : pd.Index
Resulting index
indexer : np.ndarray or None
Indices of output values in original index
"""
if method is not None:
raise NotImplementedError("argument method is not implemented for "
"CategoricalIndex.reindex")
if level is not None:
raise NotImplementedError("argument level is not implemented for "
"CategoricalIndex.reindex")
if limit is not None:
raise NotImplementedError("argument limit is not implemented for "
"CategoricalIndex.reindex")
target = ibase._ensure_index(target)
if not is_categorical_dtype(target) and not target.is_unique:
raise ValueError("cannot reindex with a non-unique indexer")
indexer, missing = self.get_indexer_non_unique(np.array(target))
new_target = self.take(indexer)
# filling in missing if needed
if len(missing):
cats = self.categories.get_indexer(target)
if (cats == -1).any():
# coerce to a regular index here!
result = Index(np.array(self), name=self.name)
new_target, indexer, _ = result._reindex_non_unique(
np.array(target))
else:
codes = new_target.codes.copy()
codes[indexer == -1] = cats[missing]
new_target = self._create_from_codes(codes)
# we always want to return an Index type here
# to be consistent with .reindex for other index types (e.g. they don't
# coerce based on the actual values, only on the dtype)
# unless we had an inital Categorical to begin with
# in which case we are going to conform to the passed Categorical
new_target = np.asarray(new_target)
if is_categorical_dtype(target):
new_target = target._shallow_copy(new_target, name=self.name)
else:
new_target = Index(new_target, name=self.name)
return new_target, indexer
def to_tuples(self):
return Index(com._asarray_tuplesafe(zip(self.left, self.right)))
def astype(self, dtype):
if np.dtype(dtype) not in (np.object, np.float64):
raise TypeError('Setting %s dtype to anything other than '
'float64 or object is not supported' %
self.__class__)
return Index(self._values, name=self.name, dtype=dtype)