Skip to content

REF: arrays_to_manager dont need names #43110

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
Aug 19, 2021
Merged

REF: arrays_to_manager dont need names #43110

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
b350373
REF: arrays_to_manager dont need names
jbrockmendel Aug 19, 2021
6c6ed56
annotation and docstring
jbrockmendel Aug 19, 2021
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
41 changes: 22 additions & 19 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -700,7 +700,6 @@ def __init__(
arrays,
columns,
index,
columns,
dtype=dtype,
typ=manager,
)
Expand Down Expand Up @@ -746,9 +745,7 @@ def __init__(
construct_1d_arraylike_from_scalar(data, len(index), dtype)
for _ in range(len(columns))
]
mgr = arrays_to_mgr(
values, columns, index, columns, dtype=None, typ=manager
)
mgr = arrays_to_mgr(values, columns, index, dtype=None, typ=manager)
else:
arr2d = construct_2d_arraylike_from_scalar(
data,
Expand Down Expand Up @@ -2025,6 +2022,20 @@ def from_records(
if columns is not None:
columns = ensure_index(columns)

def maybe_reorder(arrays, arr_columns, columns, index):
Copy link
Contributor

Choose a reason for hiding this comment

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

can you type

Copy link
Member Author

Choose a reason for hiding this comment

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

sure

if len(arrays):
length = len(arrays[0])
else:
length = 0

result_index = None
if len(arrays) == 0 and index is None and length == 0:
# for backward compat use an object Index instead of RangeIndex
result_index = Index([])

arrays, arr_columns = reorder_arrays(arrays, arr_columns, columns, length)
return arrays, arr_columns, result_index

if is_iterator(data):
if nrows == 0:
return cls()
Expand Down Expand Up @@ -2062,20 +2073,9 @@ def from_records(
arr_columns_list.append(k)
arrays.append(v)

if len(arrays):
length = len(arrays[0])
elif index is not None:
length = len(index)
else:
length = 0

arr_columns = Index(arr_columns_list)
if len(arrays) == 0 and index is None and length == 0:
# for backward compat use an object Index instead of RangeIndex
result_index = Index([])

arrays, arr_columns = reorder_arrays(
arrays, arr_columns, columns, length
arrays, arr_columns, result_index = maybe_reorder(
arrays, arr_columns, columns, index
)

elif isinstance(data, (np.ndarray, DataFrame)):
Expand All @@ -2097,6 +2097,10 @@ def from_records(
arr_columns = ensure_index(arr_columns)
if columns is None:
columns = arr_columns
else:
arrays, arr_columns, result_index = maybe_reorder(
arrays, arr_columns, columns, index
)

if exclude is None:
exclude = set()
Expand Down Expand Up @@ -2130,7 +2134,7 @@ def from_records(
columns = columns.drop(exclude)

manager = get_option("mode.data_manager")
mgr = arrays_to_mgr(arrays, arr_columns, result_index, columns, typ=manager)
mgr = arrays_to_mgr(arrays, columns, result_index, typ=manager)

return cls(mgr)

Expand Down Expand Up @@ -2343,7 +2347,6 @@ def _from_arrays(
arrays,
columns,
index,
columns,
dtype=dtype,
verify_integrity=verify_integrity,
typ=manager,
Expand Down
20 changes: 8 additions & 12 deletions pandas/core/internals/construction.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,9 +99,8 @@

def arrays_to_mgr(
arrays,
arr_names: Index,
columns: Index,
index,
columns,
*,
dtype: DtypeObj | None = None,
verify_integrity: bool = True,
Expand Down Expand Up @@ -133,7 +132,7 @@ def arrays_to_mgr(

if typ == "block":
return create_block_manager_from_arrays(
arrays, arr_names, axes, consolidate=consolidate
arrays, columns, axes, consolidate=consolidate
)
elif typ == "array":
if len(columns) != len(arrays):
Expand Down Expand Up @@ -187,7 +186,7 @@ def rec_array_to_mgr(
if columns is None:
columns = arr_columns

mgr = arrays_to_mgr(arrays, columns, index, columns, dtype=dtype, typ=typ)
mgr = arrays_to_mgr(arrays, columns, index, dtype=dtype, typ=typ)

if copy:
mgr = mgr.copy()
Expand Down Expand Up @@ -226,7 +225,7 @@ def mgr_to_mgr(mgr, typ: str, copy: bool = True):
else:
if mgr.ndim == 2:
new_mgr = arrays_to_mgr(
mgr.arrays, mgr.axes[0], mgr.axes[1], mgr.axes[0], typ="block"
mgr.arrays, mgr.axes[0], mgr.axes[1], typ="block"
)
else:
new_mgr = SingleBlockManager.from_array(mgr.arrays[0], mgr.index)
Expand Down Expand Up @@ -288,7 +287,7 @@ def ndarray_to_mgr(
else:
columns = ensure_index(columns)

return arrays_to_mgr(values, columns, index, columns, dtype=dtype, typ=typ)
return arrays_to_mgr(values, columns, index, dtype=dtype, typ=typ)

elif is_extension_array_dtype(vdtype) and not is_1d_only_ea_dtype(vdtype):
# i.e. Datetime64TZ
Expand Down Expand Up @@ -409,7 +408,6 @@ def dict_to_mgr(
from pandas.core.series import Series

arrays = Series(data, index=columns, dtype=object)
data_names = arrays.index
missing = arrays.isna()
if index is None:
# GH10856
Expand All @@ -433,11 +431,11 @@ def dict_to_mgr(
arrays.loc[missing] = [val] * missing.sum()

arrays = list(arrays)
data_names = ensure_index(columns)
columns = ensure_index(columns)

else:
keys = list(data.keys())
columns = data_names = Index(keys)
columns = Index(keys)
arrays = [com.maybe_iterable_to_list(data[k]) for k in keys]
# GH#24096 need copy to be deep for datetime64tz case
# TODO: See if we can avoid these copies
Expand All @@ -457,9 +455,7 @@ def dict_to_mgr(
]
# TODO: can we get rid of the dt64tz special case above?

return arrays_to_mgr(
arrays, data_names, index, columns, dtype=dtype, typ=typ, consolidate=copy
)
return arrays_to_mgr(arrays, columns, index, dtype=dtype, typ=typ, consolidate=copy)


def nested_data_to_arrays(
Expand Down