10000 Switch dataframe constructor to use dispatch by saulshanabrook · Pull Request #32844 · pandas-dev/pandas · GitHub
[go: up one dir, main page]
Skip to content

Switch dataframe constructor to use dispatch #32844

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

Closed
wants to merge 14 commits into from
Closed

Switch dataframe constructor to use dispatch #32844

Changes from 1 commit
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
6fe0831
Switch dataframe constructor to use dispatch
saulshanabrook Mar 19, 2020
e123ab4
blacken
saulshanabrook Mar 19, 2020
4dfb4b7
flake8
saulshanabrook Mar 19, 2020
522029d
mypy fixes
saulshanabrook Mar 19, 2020
b8dd353
style fixes
saulshanabrook Mar 19, 2020
7259590
Merge pandas/master into rework-constructor
saulshanabrook Mar 19, 2020
3e4b466
rename and take class instead of instance
saulshanabrook Mar 19, 2020
898e3d7
Move create_dataframe to construction
saulshanabrook Mar 19, 2020
7e82826
Sort imports
saulshanabrook Mar 19, 2020
b307c4b
Fix calling
saulshanabrook Mar 19, 2020
edd85c3
Add test for custom constructor
saulshanabrook Mar 20, 2020
8240d86
Added whats new
saulshanabrook Mar 20, 2020
b856214
unused imports
saulshanabrook Mar 20, 2020
a4b3ed0
Merge pandas/master into rework-constructor
saulshanabrook Mar 20, 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
Prev Previous commit
Next Next commit
rename and take class instead of instance
  • Loading branch information
@saulshanabrook
saulshanabrook committed Mar 19, 2020
commit 3e4b466a20fecbda52ff6f15223cb1bdedaceaa1
64 changes: 32 additions & 32 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -431,7 +431,7 @@ def __init__(
):
if dtype is not None:
dtype = self._validate_dtype(dtype)
mgr = create_block_manager(data, self, index, columns, dtype, copy)
mgr = create_dataframe(data, self, index, columns, dtype, copy)
NDFrame.__init__(self, mgr)

# ----------------------------------------------------------------------
Expand Down Expand Up @@ -8463,18 +8463,19 @@ def isin(self, values) -> "DataFrame":


@functools.singledispatch
def create_block_manager(
def create_dataframe(
data: Any,
df: DataFrame,
index: Optional[Axes],
columns: Optional[Axes],
dtype: Optional[Dtype],
copy: bool,
cls: Type[DataFrame],
) -> BlockManager:
"""
Convert an object into a BlockManager. Used inside the DataFrame constructor
so if you want to provide a custom way to convert from your objec to a DataFrame
you can register a dispatch on this method.
Create a BlockManager for some given data. Used inside the DataFrame constructor
to convert different input types.
If you want to provide a custom way to convert from your objec to a DataFrame
you can register a dispatch on this function.
"""
# Base case is to try to cast to NumPy array
try:
Expand All @@ -8492,34 +8493,33 @@ def create_block_manager(
raise ValueError("DataFrame constructor not properly called!")


@create_block_manager.register
def _create_block_manager_none(data: None, *args, **kwargs):
return create_block_manager({}, *args, **kwargs)
@create_dataframe.register
def _create_dataframe_none(data: None, *args, **kwargs):
return create_dataframe({}, *args, **kwargs)


@create_block_manager.register
def _create_block_manager_dataframe(data: DataFrame, *args, **kwargs):
return create_block_manager(data._data, *args, **kwargs)
@create_dataframe.register
def _create_dataframe_dataframe(data: DataFrame, *args, **kwargs):
return create_dataframe(data._data, *args, **kwargs)


@create_block_manager.register
def _create_block_manager_blockmanager(
data: BlockManager, df, index, columns, dtype, copy
@create_dataframe.register
def _create_dataframe_blockmanager(
data: BlockManager, index, columns, dtype, copy, cls
):
mgr = df._init_mgr(
return cls._init_mgr(
data, axes=dict(index=index, columns=columns), dtype=dtype, copy=copy
)
return mgr


@create_block_manager.register
def _create_block_manager_dict(data: dict, df, index, columns, dtype, copy):
@create_dataframe.register
def _create_dataframe_dict(data: dict, index, columns, dtype, copy, cls):
return init_dict(data, index, columns, dtype=dtype)


@create_block_manager.register
def _create_block_manager_masked_array(
data: ma.MaskedArray, df, index, columns, dtype, copy
@create_dataframe.register
def _create_dataframe_masked_array(
data: ma.MaskedArray, index, columns, dtype, copy, cls
):
mask = ma.getmaskarray(data)
if mask.any():
Expand All @@ -8531,18 +8531,18 @@ def _create_block_manager_masked_array(
return init_ndarray(data, index, columns, dtype=dtype, copy=copy)


@create_block_manager.register
def _create_block_manager_masked_record(
data: mrecords.MaskedRecords, df, index, columns, dtype, copy
@create_dataframe.register
def _create_dataframe_masked_record(
data: mrecords.MaskedRecords, index, columns, dtype, copy, cls
):
return masked_rec_array_to_mgr(data, index, columns, dtype, copy)


@create_block_manager.register(np.ndarray)
@create_block_manager.register(Series)
@create_block_manager.register(Index)
def _create_block_manager_array_series_index(
data: Union[np.ndarray, Series, Index], df, index, columns, dtype, copy
@create_dataframe.register(np.ndarray)
@create_dataframe.register(Series)
@create_dataframe.register(Index)
def _create_dataframe_array_series_index(
data: Union[np.ndarray, Series, Index], index, columns, dtype, copy, cls
):
if data.dtype.names:
data_columns = list(data.dtype.names)
Expand All @@ -8569,8 +8569,8 @@ class _IterableExceptStringOrBytes(metaclass=_IterableExceptStringOrBytesMeta):
pass


@create_block_manager.register(_IterableExceptStringOrBytes)
def _create_block_manager_iterable(data: abc.Iterable, df, index, columns, dtype, copy):
@create_dataframe.register(_IterableExceptStringOrBytes)
def _create_dataframe_iterable(data: abc.Iterable, index, columns, dtype, copy, cls):
if not isinstance(data, (abc.Sequence, ExtensionArray)):
data = list(data)
if len(data) > 0:
Expand Down
0