Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Commit dfd045a

Browse filesBrowse files
hanxiaohanxiao
committed
feat(array): add traverse sugar
1 parent 7093585 commit dfd045a
Copy full SHA for dfd045a

13 files changed

+50-31Lines changed: 50 additions & 31 deletions

File tree

Expand file treeCollapse file tree
Open diff view settings
Filter options
Expand file treeCollapse file tree
Open diff view settings
Collapse file

‎docarray/array/document.py‎

Copy file name to clipboardExpand all lines: docarray/array/document.py
+16-5Lines changed: 16 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -98,7 +98,10 @@ def __getitem__(
9898
if isinstance(index, (int, np.generic)):
9999
return self._data[int(index)]
100100
elif isinstance(index, str):
101-
return self._data[self._id2offset[index]]
101+
if index.startswith('@'):
102+
return self.traverse_flat(index[1:])
103+
else:
104+
return self._data[self._id2offset[index]]
102105
elif isinstance(index, slice):
103106
return DocumentArray(self._data[index])
104107
elif index is Ellipsis:
@@ -129,9 +132,14 @@ def __setitem__(
129132
self._data[index] = value
130133
self._id2offset[value.id] = index
131134
elif isinstance(index, str):
132-
old_idx = self._id2offset.pop(index)
133-
self._data[old_idx] = value
134-
self._id2offset[value.id] = old_idx
135+
if index.startswith('@'):
136+
for _d, _v in zip(self.traverse_flat(index[1:]), value):
137+
_d._data = _v._data
138+
self._rebuild_id2offset()
139+
else:
140+
old_idx = self._id2offset.pop(index)
141+
self._data[old_idx] = value
142+
self._id2offset[value.id] = old_idx
135143
elif isinstance(index, slice):
136144
self._data[index] = value
137145
self._rebuild_id2offset()
@@ -177,7 +185,10 @@ def __delitem__(self, index: 'DocumentArrayIndexType'):
177185
self._id2offset.pop(self._data[index].id)
178186
del self._data[index]
179187
elif isinstance(index, str):
180-
del self._data[self._id2offset[index]]
188+
if index.startswith('@'):
189+
raise NotImplementedError('Delete elements along traversal paths is not implemented')
190+
else:
191+
del self._data[self._id2offset[index]]
181192
self._id2offset.pop(index)
182193
elif isinstance(index, slice):
183194
del self._data[index]
Collapse file

‎docarray/array/mixins/__init__.py‎

Copy file name to clipboardExpand all lines: docarray/array/mixins/__init__.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -45,6 +45,6 @@ class AllMixins(
4545
DataframeIOMixin,
4646
ABC,
4747
):
48-
"""All plugins that can be used in :class:`DocumentArray` or :class:`DocumentArrayMemmap`. """
48+
"""All plugins that can be used in :class:`DocumentArray`. """
4949

5050
...
Collapse file

‎docarray/array/mixins/content.py‎

Copy file name to clipboardExpand all lines: docarray/array/mixins/content.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -54,7 +54,7 @@ def blobs(self) -> Optional['ArrayType']:
5454
5555
.. warning:: This operation assumes all blobs have the same shape and dtype.
5656
All dtype and shape values are assumed to be equal to the values of the
57-
first element in the DocumentArray / DocumentArrayMemmap
57+
first element in the DocumentArray
5858
5959
:return: a :class:`ArrayType` of blobs
6060
"""
Collapse file

‎docarray/array/mixins/empty.py‎

Copy file name to clipboardExpand all lines: docarray/array/mixins/empty.py
+2-2Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -11,10 +11,10 @@ class EmptyMixin:
1111

1212
@classmethod
1313
def empty(cls: Type['T'], size: int = 0) -> 'T':
14-
"""Create a :class:`DocumentArray` or :class:`DocumentArrayMemmap` object with :attr:`size` empty
14+
"""Create a :class:`DocumentArray` object with :attr:`size` empty
1515
:class:`Document` objects.
1616
1717
:param size: the number of empty Documents in this container
18-
:return: a :class:`DocumentArray` or :class:`DocumentArrayMemmap` object
18+
:return: a :class:`DocumentArray` object
1919
"""
2020
return cls(Document() for _ in range(size))
Collapse file

‎docarray/array/mixins/group.py‎

Copy file name to clipboardExpand all lines: docarray/array/mixins/group.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@
1010

1111
class GroupMixin:
1212
"""These helpers yield groups of :class:`DocumentArray` from
13-
a source :class:`DocumentArray` or :class:`DocumentArrayMemmap`."""
13+
a source :class:`DocumentArray`."""
1414

1515
def split(self, tag: str) -> Dict[Any, 'DocumentArray']:
1616
"""Split the `DocumentArray` into multiple DocumentArray according to the tag value of each `Document`.
Collapse file

‎docarray/array/mixins/match.py‎

Copy file name to clipboardExpand all lines: docarray/array/mixins/match.py
+3-3Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -43,7 +43,7 @@ def match(
4343
- To invert the distance as score and make all values in range [0, 1],
4444
use ``dA.match(dB, normalization=(1, 0))``. Note, how ``normalization`` differs from the previous.
4545
- If a custom metric distance is provided. Make sure that it returns scores as distances and not similarity, meaning the smaller the better.
46-
:param darray: the other DocumentArray or DocumentArrayMemmap to match against
46+
:param darray: the other DocumentArray to match against
4747
:param metric: the distance metric
4848
:param limit: the maximum number of matches, when not given defaults to 20.
4949
:param normalization: a tuple [a, b] to be used with min-max normalization,
@@ -136,7 +136,7 @@ def match(
136136
def _match(self, darray, cdist, limit, normalization, metric_name):
137137
"""
138138
Computes the matches between self and `darray` loading `darray` into main memory.
139-
:param darray: the other DocumentArray or DocumentArrayMemmap to match against
139+
:param darray: the other DocumentArray or to match against
140140
:param cdist: the distance metric
141141
:param limit: the maximum number of matches, when not given
142142
all Documents in `darray` are considered as matches
@@ -173,7 +173,7 @@ def _match_online(
173173
"""
174174
Computes the matches between self and `darray` loading `darray` into main memory in chunks of size `batch_size`.
175175
176-
:param darray: the other DocumentArray or DocumentArrayMemmap to match against
176+
:param darray: the other DocumentArray or to match against
177177
:param cdist: the distance metric
178178
:param limit: the maximum number of matches, when not given
179179
all Documents in `another` are considered as matches
Collapse file

‎docarray/array/mixins/parallel.py‎

Copy file name to clipboardExpand all lines: docarray/array/mixins/parallel.py
+5-5Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@
1010

1111

1212
class ParallelMixin:
13-
"""Helper functions that provide parallel map to :class:`DocumentArray` or :class:`DocumentArrayMemmap`."""
13+
"""Helper functions that provide parallel map to :class:`DocumentArray`"""
1414

1515
@overload
1616
def apply(
@@ -42,7 +42,7 @@ def apply(self: 'T', *args, **kwargs) -> 'T':
4242
# noqa: DAR102
4343
# noqa: DAR101
4444
# noqa: DAR201
45-
:return: a new :class:`DocumentArray` or :class:`DocumentArrayMemmap`
45+
:return: a new :class:`DocumentArray`
4646
"""
4747
new_da = type(self)()
4848
new_da.extend(self.map(*args, **kwargs))
@@ -60,7 +60,7 @@ def map(
6060
6161
.. seealso::
6262
- To process on a batch of elements, please use :meth:`.map_batch`;
63-
- To return a :class:`DocumentArray`/:class:`DocumentArrayMemmap`, please use :meth:`.apply`.
63+
- To return a :class:`DocumentArray`, please use :meth:`.apply`.
6464
6565
:param func: a function that takes :class:`Document` as input and outputs anything. You can either modify elements
6666
in-place (only with `thread` backend) or work later on return elements.
@@ -116,7 +116,7 @@ def apply_batch(self: 'T', *args, **kwargs) -> 'T':
116116
# noqa: DAR102
117117
# noqa: DAR101
118118
# noqa: DAR201
119-
:return: a new :class:`DocumentArray` or :class:`DocumentArrayMemmap`
119+
:return: a new :class:`DocumentArray`
120120
"""
121121
new_da = type(self)()
122122
for _b in self.map_batch(*args, **kwargs):
@@ -138,7 +138,7 @@ def map_batch(
138138
139139
.. seealso::
140140
- To process single element, please use :meth:`.map`;
141-
- To return :class:`DocumentArray` or :class:`DocumentArrayMemmap`, please use :meth:`.apply_batch`.
141+
- To return :class:`DocumentArray`, please use :meth:`.apply_batch`.
142142
143143
:param batch_size: Size of each generated batch (except the last one, which might be smaller, default: 32)
144144
:param shuffle: If set, shuffle the Documents before dividing into minibatches.
Collapse file

‎docarray/array/mixins/reduce.py‎

Copy file name to clipboardExpand all lines: docarray/array/mixins/reduce.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -23,7 +23,7 @@ def _reduce_doc_props(doc1: 'Document', doc2: 'Document'):
2323

2424
class ReduceMixin:
2525
"""
26-
A mixin that provides reducing logic for :class:`DocumentArray` or :class:`DocumentArrayMemmap`
26+
A mixin that provides reducing logic for :class:`DocumentArray`
2727
Reducing 2 or more DocumentArrays consists in merging all Documents into the same DocumentArray.
2828
If a Document belongs to 2 or more DocumentArrays, it is added once and data attributes are merged with priority to
2929
the Document belonging to the left-most DocumentArray. Matches and chunks are also reduced in the same way.
Collapse file

‎docarray/array/mixins/sample.py‎

Copy file name to clipboardExpand all lines: docarray/array/mixins/sample.py
+2-3Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -22,9 +22,8 @@ def sample(self, k: int, seed: Optional[int] = None) -> 'DocumentArray':
2222
random.seed(seed)
2323
# NOTE, this could simplified to random.sample(self, k)
2424
# without getting indices and itemgetter etc.
25-
# however it's only work on DocumentArray, not DocumentArrayMemmap.
26-
indices = random.sample(range(len(self)), k)
27-
sampled = operator.itemgetter(*indices)(self)
25+
# however it's only work on DocumentArray.
26+
sampled = random.sample(self, k)
2827

2928
from ..document import DocumentArray
3029

Collapse file

‎docarray/array/mixins/traverse.py‎

Copy file name to clipboardExpand all lines: docarray/array/mixins/traverse.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -34,7 +34,7 @@ def _check_traversal_path_type(tp):
3434

3535
class TraverseMixin:
3636
"""
37-
A mixin used for traversing :class:`DocumentArray` or :class:`DocumentArrayMemmap`.
37+
A mixin used for traversing :class:`DocumentArray`.
3838
"""
3939

4040
def traverse(

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.