Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

BUG: Fix Index construction when given empty generator (#21470). #21481

Merged
merged 8 commits into from
Jun 18, 2018
Merged
Show file tree
Hide file tree
Changes from 5 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions pandas/core/arrays/categorical.py
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,6 @@
import numpy as np
from warnings import warn
import textwrap
import types

from pandas import compat
from pandas.compat import u, lzip
Expand All @@ -28,7 +27,7 @@
is_categorical,
is_categorical_dtype,
is_list_like, is_sequence,
is_scalar,
is_scalar, is_iterator,
is_dict_like)

from pandas.core.algorithms import factorize, take_1d, unique1d, take
Expand Down Expand Up @@ -2483,7 +2482,7 @@ def _convert_to_list_like(list_like):
if isinstance(list_like, list):
return list_like
if (is_sequence(list_like) or isinstance(list_like, tuple) or
isinstance(list_like, types.GeneratorType)):
is_iterator(list_like)):
return list(list_like)
elif is_scalar(list_like):
return [list_like]
Expand Down
10 changes: 6 additions & 4 deletions pandas/core/indexes/base.py
Original file line number Diff line number Diff line change
Expand Up @@ -430,12 +430,14 @@ def __new__(cls, data=None, dtype=None, copy=False, name=None,
elif data is None or is_scalar(data):
cls._scalar_data_error(data)
else:
if tupleize_cols and is_list_like(data) and data:
if tupleize_cols and is_list_like(data):
# GH21470: convert iterable to list before determining if empty
if is_iterator(data):
data = list(data)
# we must be all tuples, otherwise don't construct
# 10697
if all(isinstance(e, tuple) for e in data):

if data and all(isinstance(e, tuple) for e in data):
# we must be all tuples, otherwise don't construct
# 10697
from .multi import MultiIndex
return MultiIndex.from_tuples(
data, names=name or kwargs.get('names'))
Expand Down
19 changes: 11 additions & 8 deletions pandas/tests/indexes/test_base.py
Original file line number Diff line number Diff line change
Expand Up @@ -445,21 +445,24 @@ def test_constructor_dtypes_timedelta(self, attr, klass):
result = klass(list(values), dtype=dtype)
tm.assert_index_equal(result, index)

def test_constructor_empty_gen(self):
skip_index_keys = ["repeats", "periodIndex", "rangeIndex",
"tuples"]
for key, index in self.generate_index_types(skip_index_keys):
empty = index.__class__([])
assert isinstance(empty, index.__class__)
assert not len(empty)
@pytest.mark.parametrize("value", [[], iter([]), (x for x in [])])
@pytest.mark.parametrize("klass",
[Index, Float64Index, Int64Index, UInt64Index,
CategoricalIndex, DatetimeIndex, TimedeltaIndex])
def test_constructor_empty(self, value, klass):
empty = klass(value)
assert isinstance(empty, klass)
assert not len(empty)

@pytest.mark.parametrize("empty,klass", [
(PeriodIndex([], freq='B'), PeriodIndex),
(PeriodIndex(iter([]), freq='B'), PeriodIndex),
(PeriodIndex((x for x in []), freq='B'), PeriodIndex),
(RangeIndex(step=1), pd.RangeIndex),
(MultiIndex(levels=[[1, 2], ['blue', 'red']],
labels=[[], []]), MultiIndex)
])
def test_constructor_empty(self, empty, klass):
def test_constructor_empty_special(self, empty, klass):
assert isinstance(empty, klass)
assert not len(empty)

Expand Down