Skip to content

List accessor #55777

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.

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 29 commits into from
Nov 3, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
17 changes: 17 additions & 0 deletions doc/source/reference/series.rst
Original file line number Diff line number Diff line change
Expand Up @@ -526,6 +526,23 @@ Sparse-dtype specific methods and attributes are provided under the
Series.sparse.to_coo


.. _api.series.list:

List accessor
~~~~~~~~~~~~~

Arrow list-dtype specific methods and attributes are provided under the
``Series.list`` accessor.

.. autosummary::
:toctree: api/
:template: autosummary/accessor_method.rst

Series.list.flatten
Series.list.len
Series.list.__getitem__


.. _api.series.struct:

Struct accessor
Expand Down
26 changes: 23 additions & 3 deletions doc/source/whatsnew/v2.2.0.rst
Original file line number Diff line number Diff line change
Expand Up @@ -64,10 +64,30 @@ DataFrame. (:issue:`54938`)
)
series.struct.explode()

.. _whatsnew_220.enhancements.enhancement2:
.. _whatsnew_220.enhancements.list_accessor:

enhancement2
^^^^^^^^^^^^
Series.list accessor for PyArrow list data
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

The ``Series.list`` accessor provides attributes and methods for processing
data with ``list[pyarrow]`` dtype Series. For example,
:meth:`Series.list.__getitem__` allows indexing pyarrow lists in
a Series. (:issue:`55323`)

.. ipython:: python

import pyarrow as pa
series = pd.Series(
[
[1, 2, 3],
[4, 5],
[6],
],
dtype=pd.ArrowDtype(
pa.list_(pa.int64())
),
)
series.list[0]

.. _whatsnew_220.enhancements.other:

Expand Down
7 changes: 5 additions & 2 deletions pandas/core/arrays/arrow/__init__.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,7 @@
from pandas.core.arrays.arrow.accessors import StructAccessor
from pandas.core.arrays.arrow.accessors import (
ListAccessor,
StructAccessor,
)
from pandas.core.arrays.arrow.array import ArrowExtensionArray

__all__ = ["ArrowExtensionArray", "StructAccessor"]
__all__ = ["ArrowExtensionArray", "StructAccessor", "ListAccessor"]
224 changes: 203 additions & 21 deletions pandas/core/arrays/arrow/accessors.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,16 @@

from __future__ import annotations

from abc import (
ABCMeta,
abstractmethod,
)
from typing import TYPE_CHECKING

from pandas.compat import pa_version_under10p1
from pandas.compat import (
pa_version_under10p1,
pa_version_under11p0,
)

if not pa_version_under10p1:
import pyarrow as pa
Expand All @@ -13,13 +20,194 @@
from pandas.core.dtypes.dtypes import ArrowDtype

if TYPE_CHECKING:
from collections.abc import Iterator

from pandas import (
DataFrame,
Series,
)


class StructAccessor:
class ArrowAccessor(metaclass=ABCMeta):
@abstractmethod
def __init__(self, data, validation_msg: str) -> None:
self._data = data
self._validation_msg = validation_msg
self._validate(data)

@abstractmethod
def _is_valid_pyarrow_dtype(self, pyarrow_dtype) -> bool:
pass

def _validate(self, data):
dtype = data.dtype
if not isinstance(dtype, ArrowDtype):
# Raise AttributeError so that inspect can handle non-struct Series.
raise AttributeError(self._validation_msg.format(dtype=dtype))

if not self._is_valid_pyarrow_dtype(dtype.pyarrow_dtype):
# Raise AttributeError so that inspect can handle invalid Series.
raise AttributeError(self._validation_msg.format(dtype=dtype))

@property
def _pa_array(self):
return self._data.array._pa_array


class ListAccessor(ArrowAccessor):
"""
Accessor object for list data properties of the Series values.

Parameters
----------
data : Series
Series containing Arrow list data.
"""

def __init__(self, data=None) -> None:
super().__init__(
data,
validation_msg="Can only use the '.list' accessor with "
"'list[pyarrow]' dtype, not {dtype}.",
)

def _is_valid_pyarrow_dtype(self, pyarrow_dtype) -> bool:
return (
pa.types.is_list(pyarrow_dtype)
or pa.types.is_fixed_size_list(pyarrow_dtype)
or pa.types.is_large_list(pyarrow_dtype)
)

def len(self) -> Series:
"""
Return the length of each list in the Series.

Returns
-------
pandas.Series
The length of each list.

Examples
--------
>>> import pyarrow as pa
>>> s = pd.Series(
... [
... [1, 2, 3],
... [3],
... ],
... dtype=pd.ArrowDtype(pa.list_(
... pa.int64()
... ))
... )
>>> s.list.len()
0 3
1 1
dtype: int32[pyarrow]
"""
from pandas import Series

value_lengths = pc.list_value_length(self._pa_array)
return Series(value_lengths, dtype=ArrowDtype(value_lengths.type))

def __getitem__(self, key: int | slice) -> Series:
"""
Index or slice lists in the Series.

Parameters
----------
key : int | slice
Index or slice of indices to access from each list.

Returns
-------
pandas.Series
The list at requested index.

Examples
--------
>>> import pyarrow as pa
>>> s = pd.Series(
... [
... [1, 2, 3],
... [3],
... ],
... dtype=pd.ArrowDtype(pa.list_(
... pa.int64()
... ))
... )
>>> s.list[0]
0 1
1 3
dtype: int64[pyarrow]
"""
from pandas import Series

if isinstance(key, int):
# TODO: Support negative key but pyarrow does not allow
# element index to be an array.
# if key < 0:
# key = pc.add(key, pc.list_value_length(self._pa_array))
element = pc.list_element(self._pa_array, key)
return Series(element, dtype=ArrowDtype(element.type))
elif isinstance(key, slice):
if pa_version_under11p0:
raise NotImplementedError(
f"List slice not supported by pyarrow {pa.__version__}."
)

# TODO: Support negative start/stop/step, ideally this would be added
# upstream in pyarrow.
start, stop, step = key.start, key.stop, key.step
if start is None:
# TODO: When adding negative step support
# this should be setto last element of array
# when step is negative.
start = 0
if step is None:
step = 1
sliced = pc.list_slice(self._pa_array, start, stop, step)
return Series(sliced, dtype=ArrowDtype(sliced.type))
else:
raise ValueError(f"key must be an int or slice, got {type(key).__name__}")

def __iter__(self) -> Iterator:
raise TypeError(f"'{type(self).__name__}' object is not iterable")

def flatten(self) -> Series:
"""
Flatten list values.

Returns
-------
pandas.Series
The data from all lists in the series flattened.

Examples
--------
>>> import pyarrow as pa
>>> s = pd.Series(
... [
... [1, 2, 3],
... [3],
... ],
... dtype=pd.ArrowDtype(pa.list_(
... pa.int64()
... ))
... )
>>> s.list.flatten()
0 1
1 2
2 3
3 3
dtype: int64[pyarrow]
"""
from pandas import Series

flattened = pc.list_flatten(self._pa_array)
return Series(flattened, dtype=ArrowDtype(flattened.type))


class StructAccessor(ArrowAccessor):
"""
Accessor object for structured data properties of the Series values.

Expand All @@ -29,23 +217,17 @@ class StructAccessor:
Series containing Arrow struct data.
"""

_validation_msg = (
"Can only use the '.struct' accessor with 'struct[pyarrow]' dtype, not {dtype}."
)

def __init__(self, data=None) -> None:
self._parent = data
self._validate(data)

def _validate(self, data):
dtype = data.dtype
if not isinstance(dtype, ArrowDtype):
# Raise AttributeError so that inspect can handle non-struct Series.
raise AttributeError(self._validation_msg.format(dtype=dtype))
super().__init__(
data,
validation_msg=(
"Can only use the '.struct' accessor with 'struct[pyarrow]' "
"dtype, not {dtype}."
),
)

if not pa.types.is_struct(dtype.pyarrow_dtype):
# Raise AttributeError so that inspect can handle non-struct Series.
raise AttributeError(self._validation_msg.format(dtype=dtype))
def _is_valid_pyarrow_dtype(self, pyarrow_dtype) -> bool:
return pa.types.is_struct(pyarrow_dtype)

@property
def dtypes(self) -> Series:
Expand Down Expand Up @@ -80,7 +262,7 @@ def dtypes(self) -> Series:
Series,
)

pa_type = self._parent.dtype.pyarrow_dtype
pa_type = self._data.dtype.pyarrow_dtype
types = [ArrowDtype(struct.type) for struct in pa_type]
names = [struct.name for struct in pa_type]
return Series(types, index=Index(names))
Expand Down Expand Up @@ -135,7 +317,7 @@ def field(self, name_or_index: str | int) -> Series:
"""
from pandas import Series

pa_arr = self._parent.array._pa_array
pa_arr = self._data.array._pa_array
if isinstance(name_or_index, int):
index = name_or_index
elif isinstance(name_or_index, str):
Expand All @@ -151,7 +333,7 @@ def field(self, name_or_index: str | int) -> Series:
return Series(
field_arr,
dtype=ArrowDtype(field_arr.type),
index=self._parent.index,
index=self._data.index,
name=pa_field.name,
)

Expand Down Expand Up @@ -190,7 +372,7 @@ def explode(self) -> DataFrame:
"""
from pandas import concat

pa_type = self._parent.dtype.pyarrow_dtype
pa_type = self._pa_array.type
return concat(
[self.field(i) for i in range(pa_type.num_fields)], axis="columns"
)
6 changes: 5 additions & 1 deletion pandas/core/series.py
Original file line number Diff line number Diff line change
Expand Up @@ -100,7 +100,10 @@
from pandas.core.accessor import CachedAccessor
from pandas.core.apply import SeriesApply
from pandas.core.arrays import ExtensionArray
from pandas.core.arrays.arrow import StructAccessor
from pandas.core.arrays.arrow import (
ListAccessor,
StructAccessor,
)
from pandas.core.arrays.categorical import CategoricalAccessor
from pandas.core.arrays.sparse import SparseAccessor
from pandas.core.arrays.string_ import StringDtype
Expand Down Expand Up @@ -5891,6 +5894,7 @@ def to_period(self, freq: str | None = None, copy: bool | None = None) -> Series
plot = CachedAccessor("plot", pandas.plotting.PlotAccessor)
sparse = CachedAccessor("sparse", SparseAccessor)
struct = CachedAccessor("struct", StructAccessor)
list = CachedAccessor("list", ListAccessor)

# ----------------------------------------------------------------------
# Add plotting methods to Series
Expand Down
Loading