def extract_index(data) -> Index:
"""
Try to infer an Index from the passed data, raise ValueError on failure.
"""
index = None
if len(data) == 0:
index = Index([])
elif len(data) > 0:
raw_lengths = []
indexes: List[Union[List[Hashable], Index]] = []
have_raw_arrays = False
have_series = False
have_dicts = False
for val in data:
if isinstance(val, ABCSeries):
have_series = True
indexes.append(val.index)
elif isinstance(val, dict):
have_dicts = True
indexes.append(list(val.keys()))
elif is_list_like(val) and getattr(val, "ndim", 1) == 1:
have_raw_arrays = True
raw_lengths.append(len(val))
if not indexes and not raw_lengths:
raise ValueError("If using all scalar values, you must pass an index")
if have_series:
index = union_indexes(indexes)
elif have_dicts:
index = union_indexes(indexes, sort=False)
if have_raw_arrays:
lengths = list(set(raw_lengths))
if len(lengths) > 1:
raise ValueError("All arrays must be of the same length")
if have_dicts:
raise ValueError(
"Mixing dicts with non-Series may lead to ambiguous ordering."
)
if have_series:
assert index is not None # for mypy
if lengths[0] != len(index):
msg = (
f"array length {lengths[0]} does not match index "
f"length {len(index)}"
)
raise ValueError(msg)
else:
index = ibase.default_index(lengths[0])
# error: Argument 1 to "ensure_index" has incompatible type "Optional[Index]";
# expected "Union[Union[Union[ExtensionArray, ndarray], Index, Series],
# Sequence[Any]]"
return ensure_index(index) # type: ignore[arg-type]
def extract_index(data) -> Index:
"""
Try to infer an Index from the passed data, raise ValueError on failure.
"""
index = None
if len(data) == 0:
index = Index([])
elif len(data) > 0:
raw_lengths = []
indexes: List[Union[List[Label], Index]] = []
have_raw_arrays = False
have_series = False
have_dicts = False
for val in data:
if isinstance(val, ABCSeries):
have_series = True
indexes.append(val.index)
elif isinstance(val, dict):
have_dicts = True
indexes.append(list(val.keys()))
elif is_list_like(val) and getattr(val, "ndim", 1) == 1:
have_raw_arrays = True
raw_lengths.append(len(val))
if not indexes and not raw_lengths:
raise ValueError(
"If using all scalar values, you must pass an index")
if have_series:
index = union_indexes(indexes)
elif have_dicts:
index = union_indexes(indexes, sort=False)
if have_raw_arrays:
lengths = list(set(raw_lengths))
if len(lengths) > 1:
raise ValueError("arrays must all be same length")
if have_dicts:
raise ValueError(
"Mixing dicts with non-Series may lead to ambiguous ordering."
)
if have_series:
assert index is not None # for mypy
if lengths[0] != len(index):
msg = (f"array length {lengths[0]} does not match index "
f"length {len(index)}")
raise ValueError(msg)
else:
index = ibase.default_index(lengths[0])
return ensure_index(index)
def extract_index(data):
index = None
if len(data) == 0:
index = Index([])
elif len(data) > 0:
raw_lengths = []
indexes = []
have_raw_arrays = False
have_series = False
have_dicts = False
for val in data:
if isinstance(val, ABCSeries):
have_series = True
indexes.append(val.index)
elif isinstance(val, dict):
have_dicts = True
indexes.append(list(val.keys()))
elif is_list_like(val) and getattr(val, "ndim", 1) == 1:
have_raw_arrays = True
raw_lengths.append(len(val))
if not indexes and not raw_lengths:
raise ValueError(
"If using all scalar values, you must pass an index")
if have_series:
index = union_indexes(indexes)
elif have_dicts:
index = union_indexes(indexes, sort=False)
if have_raw_arrays:
lengths = list(set(raw_lengths))
if len(lengths) > 1:
raise ValueError("arrays must all be same length")
if have_dicts:
raise ValueError(
"Mixing dicts with non-Series may lead to ambiguous ordering."
)
if have_series:
if lengths[0] != len(index):
msg = ("array length {length} does not match index "
"length {idx_len}".format(length=lengths[0],
idx_len=len(index)))
raise ValueError(msg)
else:
index = ibase.default_index(lengths[0])
return ensure_index(index)
def test_union_index_no_sort(arr, sort, dtype):
# GH 35092. Check that we don't sort with sort=False
ind1 = Index(arr[:2], dtype=dtype)
ind2 = Index(arr[2:], dtype=dtype)
# sort is None indicates that we sort the combined index
if sort is None:
arr.sort()
expected = Index(arr, dtype=dtype)
result = union_indexes([ind1, ind2], sort=sort)
tm.assert_index_equal(result, expected)
