Skip to content

REF: implement sanitize_masked_array #38398

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 2 commits into from
Dec 11, 2020
Merged

REF: implement sanitize_masked_array #38398

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2eaa9f9
REF: implement sanitize_masked_array
jbrockmendel Dec 10, 2020
06e467c
Merge branch 'master' of https://github.com/pandas-dev/pandas into re…
jbrockmendel Dec 10, 2020
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
22 changes: 15 additions & 7 deletions pandas/core/construction.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -420,6 +420,20 @@ def ensure_wrapped_if_datetimelike(arr):
return arr


def sanitize_masked_array(data: ma.MaskedArray) -> np.ndarray:
"""
Convert numpy MaskedArray to ensure mask is softened.
"""
mask = ma.getmaskarray(data)
if mask.any():
data, fill_value = maybe_upcast(data, copy=True)
data.soften_mask() # set hardmask False if it was True
data[mask] = fill_value
else:
data = data.copy()
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

removing this copy does not break any tests, not clear why it is needed

return data


def sanitize_array(
data,
index: Optional[Index],
Expand All @@ -433,13 +447,7 @@ def sanitize_array(
"""

if isinstance(data, ma.MaskedArray):
mask = ma.getmaskarray(data)
if mask.any():
data, fill_value = maybe_upcast(data, copy=True)
data.soften_mask() # set hardmask False if it was True
data[mask] = fill_value
else:
data = data.copy()
data = sanitize_masked_array(data)

# extract ndarray or ExtensionArray, ensure we have no PandasArray
data = extract_array(data, extract_numpy=True)
Expand Down
11 changes: 2 additions & 9 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,6 @@
maybe_convert_platform,
maybe_downcast_to_dtype,
maybe_infer_to_datetimelike,
maybe_upcast,
validate_numeric_casting,
)
from pandas.core.dtypes.common import (
Expand Down Expand Up @@ -127,7 +126,7 @@
from pandas.core.arraylike import OpsMixin
from pandas.core.arrays import Categorical, ExtensionArray
from pandas.core.arrays.sparse import SparseFrameAccessor
from pandas.core.construction import extract_array
from pandas.core.construction import extract_array, sanitize_masked_array
from pandas.core.generic import NDFrame, _shared_docs
from pandas.core.indexes import base as ibase
from pandas.core.indexes.api import (
Expand Down Expand Up @@ -536,13 +535,7 @@ def __init__(

# a masked array
else:
mask = ma.getmaskarray(data)
if mask.any():
data, fill_value = maybe_upcast(data, copy=True)
data.soften_mask() # set hardmask False if it was True
data[mask] = fill_value
else:
data = data.copy()
data = sanitize_masked_array(data)
mgr = init_ndarray(data, index, columns, dtype=dtype, copy=copy)

elif isinstance(data, (np.ndarray, Series, Index)):
Expand Down
15 changes: 8 additions & 7 deletions pandas/core/internals/construction.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,8 @@
)

if TYPE_CHECKING:
from numpy.ma.mrecords import MaskedRecords

from pandas import Series

# ---------------------------------------------------------------------
Expand Down Expand Up @@ -96,13 +98,12 @@ def arrays_to_mgr(


def masked_rec_array_to_mgr(
data, index, columns, dtype: Optional[DtypeObj], copy: bool
data: "MaskedRecords", index, columns, dtype: Optional[DtypeObj], copy: bool
):
"""
Extract from a masked rec array and create the manager.
"""
# essentially process a record array then fill it
fill_value = data.fill_value
fdata = ma.getdata(data)
if index is None:
index = get_names_from_index(fdata)
Expand All @@ -116,11 +117,11 @@ def masked_rec_array_to_mgr(

# fill if needed
new_arrays = []
for fv, arr, col in zip(fill_value, arrays, arr_columns):
# TODO: numpy docs suggest fv must be scalar, but could it be
# non-scalar for object dtype?
assert lib.is_scalar(fv), fv
mask = ma.getmaskarray(data[col])
for col in arr_columns:
arr = data[col]
fv = arr.fill_value

mask = ma.getmaskarray(arr)
if mask.any():
arr, fv = maybe_upcast(arr, fill_value=fv, copy=True)
arr[mask] = fv
Expand Down