Skip to content

REF: simplify maybe_casted_values #38421

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
Dec 12, 2020
Merged

REF: simplify maybe_casted_values #38421

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
55 changes: 1 addition & 54 deletions pandas/core/dtypes/cast.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,17 +88,11 @@
ABCSeries,
)
from pandas.core.dtypes.inference import is_list_like
from pandas.core.dtypes.missing import (
is_valid_nat_for_dtype,
isna,
na_value_for_dtype,
notna,
)
from pandas.core.dtypes.missing import is_valid_nat_for_dtype, isna, notna

if TYPE_CHECKING:
from pandas import Series
from pandas.core.arrays import ExtensionArray
from pandas.core.indexes.base import Index

_int8_max = np.iinfo(np.int8).max
_int16_max = np.iinfo(np.int16).max
Expand Down Expand Up @@ -488,53 +482,6 @@ def changeit():
return result, False


def maybe_casted_values(
index: "Index", codes: Optional[np.ndarray] = None
) -> ArrayLike:
"""
Convert an index, given directly or as a pair (level, code), to a 1D array.

Parameters
----------
index : Index
codes : np.ndarray[intp] or None, default None

Returns
-------
ExtensionArray or ndarray
If codes is `None`, the values of `index`.
If codes is passed, an array obtained by taking from `index` the indices
contained in `codes`.
"""

values = index._values
if values.dtype == np.object_:
values = lib.maybe_convert_objects(values)

# if we have the codes, extract the values with a mask
if codes is not None:
mask: np.ndarray = codes == -1

if mask.size > 0 and mask.all():
# we can have situations where the whole mask is -1,
# meaning there is nothing found in codes, so make all nan's

dtype = index.dtype
fill_value = na_value_for_dtype(dtype)
values = construct_1d_arraylike_from_scalar(fill_value, len(mask), dtype)

else:
values = values.take(codes)

if mask.any():
if isinstance(values, np.ndarray):
values, _ = maybe_upcast_putmask(values, mask, np.nan)
else:
values[mask] = np.nan

return values


def maybe_promote(dtype, fill_value=np.nan):
"""
Find the minimal dtype that can hold both the given dtype and fill_value.
Expand Down
13 changes: 11 additions & 2 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,6 @@
infer_dtype_from_scalar,
invalidate_string_dtypes,
maybe_box_datetimelike,
maybe_casted_values,
maybe_convert_platform,
maybe_downcast_to_dtype,
maybe_infer_to_datetimelike,
Expand Down Expand Up @@ -5021,8 +5020,18 @@ class max type
missing = self.columns.nlevels - len(name_lst)
name_lst += [col_fill] * missing
name = tuple(name_lst)

# to ndarray and maybe infer different dtype
level_values = maybe_casted_values(lev, lab)
level_values = lev._values
if level_values.dtype == np.object_:
level_values = lib.maybe_convert_objects(level_values)

if lab is not None:
# if we have the codes, extract the values with a mask
level_values = algorithms.take(
level_values, lab, allow_fill=True, fill_value=lev._na_value
)

new_obj.insert(0, name, level_values)

new_obj.index = new_index
Expand Down