renard-pipeline 0.4.0__py3-none-any.whl → 0.4.1__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of renard-pipeline might be problematic. Click here for more details.
- renard/pipeline/core.py +7 -0
- {renard_pipeline-0.4.0.dist-info → renard_pipeline-0.4.1.dist-info}/METADATA +32 -2
- {renard_pipeline-0.4.0.dist-info → renard_pipeline-0.4.1.dist-info}/RECORD +5 -5
- {renard_pipeline-0.4.0.dist-info → renard_pipeline-0.4.1.dist-info}/WHEEL +1 -1
- {renard_pipeline-0.4.0.dist-info → renard_pipeline-0.4.1.dist-info}/LICENSE +0 -0
renard/pipeline/core.py
CHANGED
|
@@ -50,6 +50,13 @@ class Mention:
|
|
|
50
50
|
self_dict["end_idx"] = self.end_idx + shift
|
|
51
51
|
return self.__class__(**self_dict)
|
|
52
52
|
|
|
53
|
+
def __eq__(self, other: Mention) -> bool:
|
|
54
|
+
return (
|
|
55
|
+
self.tokens == other.tokens
|
|
56
|
+
and self.start_idx == other.start_idx
|
|
57
|
+
and self.end_idx == other.end_idx
|
|
58
|
+
)
|
|
59
|
+
|
|
53
60
|
def __hash__(self) -> int:
|
|
54
61
|
return hash(tuple(self.tokens) + (self.start_idx, self.end_idx))
|
|
55
62
|
|
|
@@ -1,7 +1,8 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: renard-pipeline
|
|
3
|
-
Version: 0.4.
|
|
3
|
+
Version: 0.4.1
|
|
4
4
|
Summary: Relationships Extraction from NARrative Documents
|
|
5
|
+
Home-page: https://github.com/CompNet/Renard
|
|
5
6
|
License: GPL-3.0-only
|
|
6
7
|
Author: Arthur Amalvy
|
|
7
8
|
Author-email: arthur.amalvy@univ-avignon.fr
|
|
@@ -31,6 +32,8 @@ Requires-Dist: tibert (>=0.3.0,<0.4.0)
|
|
|
31
32
|
Requires-Dist: torch (>=2.0.0,!=2.0.1)
|
|
32
33
|
Requires-Dist: tqdm (>=4.62.3,<5.0.0)
|
|
33
34
|
Requires-Dist: transformers (>=4.36.0,<5.0.0)
|
|
35
|
+
Project-URL: Documentation, https://compnet.github.io/Renard/
|
|
36
|
+
Project-URL: Repository, https://github.com/CompNet/Renard
|
|
34
37
|
Description-Content-Type: text/markdown
|
|
35
38
|
|
|
36
39
|
# Renard
|
|
@@ -46,6 +49,8 @@ You can install the latest version using pip:
|
|
|
46
49
|
|
|
47
50
|
> pip install renard-pipeline
|
|
48
51
|
|
|
52
|
+
Currently, Renard supports Python 3.8, 3.9 and 3.10.
|
|
53
|
+
|
|
49
54
|
|
|
50
55
|
# Documentation
|
|
51
56
|
|
|
@@ -56,7 +61,32 @@ If you need local documentation, it can be generated using `Sphinx`. From the `d
|
|
|
56
61
|
|
|
57
62
|
# Tutorial
|
|
58
63
|
|
|
59
|
-
|
|
64
|
+
Renard's central concept is the `Pipeline`.A `Pipeline` is a list of `PipelineStep` that are run sequentially in order to extract a character graph from a document. Here is a simple example:
|
|
65
|
+
|
|
66
|
+
```python
|
|
67
|
+
from renard.pipeline import Pipeline
|
|
68
|
+
from renard.pipeline.tokenization import NLTKTokenizer
|
|
69
|
+
from renard.pipeline.ner import NLTKNamedEntityRecognizer
|
|
70
|
+
from renard.pipeline.character_unification import GraphRulesCharacterUnifier
|
|
71
|
+
from renard.pipeline.graph_extraction import CoOccurrencesGraphExtractor
|
|
72
|
+
|
|
73
|
+
with open("./my_doc.txt") as f:
|
|
74
|
+
text = f.read()
|
|
75
|
+
|
|
76
|
+
pipeline = Pipeline(
|
|
77
|
+
[
|
|
78
|
+
NLTKTokenizer(),
|
|
79
|
+
NLTKNamedEntityRecognizer(),
|
|
80
|
+
GraphRulesCharacterUnifier(min_appearance=10),
|
|
81
|
+
CoOccurrencesGraphExtractor(co_occurrences_dist=25)
|
|
82
|
+
]
|
|
83
|
+
)
|
|
84
|
+
|
|
85
|
+
out = pipeline(text)
|
|
86
|
+
```
|
|
87
|
+
|
|
88
|
+
For more information, see `renard_tutorial.py`, which is a tutorial in the `jupytext` format. You can open it as a notebook in Jupyter Notebook (or export it as a notebook with `jupytext --to ipynb renard-tutorial.py`).
|
|
89
|
+
|
|
60
90
|
|
|
61
91
|
|
|
62
92
|
# Running tests
|
|
@@ -5,7 +5,7 @@ renard/nltk_utils.py,sha256=mUJiwMrEDZV4Fla7WuMR-hA_OC2ZIwSXgW_0Ew18VSo,977
|
|
|
5
5
|
renard/pipeline/__init__.py,sha256=8Yim2mmny8YGvM7N5-na5zK-C9UDxUb77K9ml-VirUA,35
|
|
6
6
|
renard/pipeline/character_unification.py,sha256=GcnC8UYqn1RBOGVhYS9LVcTNqpxm9YoT-lPsE3vodek,14818
|
|
7
7
|
renard/pipeline/characters_extraction.py,sha256=NzF8H9X19diW6rqwS5ERrRku7rFueO3S077H5C6kb7I,363
|
|
8
|
-
renard/pipeline/core.py,sha256=
|
|
8
|
+
renard/pipeline/core.py,sha256=luKNUTCDtZfwKzxVIaImyIMwFFvIknfT1LdQtongj24,22570
|
|
9
9
|
renard/pipeline/corefs/__init__.py,sha256=9c9AaXBcRrDBf1jhTtJ7DyjOJhX_Zej3FjlcGak7MK8,44
|
|
10
10
|
renard/pipeline/corefs/corefs.py,sha256=nzYT6S9ify3FlgGB3FSDpAhs2UQYgW9c3CL2GRYzTms,11508
|
|
11
11
|
renard/pipeline/graph_extraction.py,sha256=n0T_nzNGiwE9bDubpPknHe7bbDhJ4ndnqmoMmyfbeWg,19468
|
|
@@ -29,7 +29,7 @@ renard/resources/pronouns/pronouns.py,sha256=YJ8hM6H8QHrF2Xx6O5blqc-Sqe1D1YFL0sR
|
|
|
29
29
|
renard/resources/titles/__init__.py,sha256=Jcg4B7stsWiAaXbFgNl_L3ICtCQmFe9bo3YjdkVL50w,45
|
|
30
30
|
renard/resources/titles/titles.py,sha256=GsFccVJuTkgDWiAqWZpFd2R9pGvFKQZBOk4RWWuWDkw,968
|
|
31
31
|
renard/utils.py,sha256=8J3swFqSi4YqhgYNXvttJ0s-DmJbl_yEYri6JpGEWH8,2340
|
|
32
|
-
renard_pipeline-0.4.
|
|
33
|
-
renard_pipeline-0.4.
|
|
34
|
-
renard_pipeline-0.4.
|
|
35
|
-
renard_pipeline-0.4.
|
|
32
|
+
renard_pipeline-0.4.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
|
|
33
|
+
renard_pipeline-0.4.1.dist-info/METADATA,sha256=KgpnPAR6BtLS4RNjsxIBWqUygUcoRdJfkqHigzZMSqU,3697
|
|
34
|
+
renard_pipeline-0.4.1.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
|
|
35
|
+
renard_pipeline-0.4.1.dist-info/RECORD,,
|
|
File without changes
|