renard-pipeline 0.4.0__py3-none-any.whl → 0.4.2__py3-none-any.whl

renard/pipeline/character_unification.py

@@ -159,6 +159,7 @@ class GraphRulesCharacterUnifier(PipelineStep):
         min_appearances: int = 0,
         additional_hypocorisms: Optional[List[Tuple[str, List[str]]]] = None,
         link_corefs_mentions: bool = False,
+        ignore_lone_titles: Optional[Set[str]] = None,
     ) -> None:
         """
         :param min_appearances: minimum number of appearances of a
@@ -173,10 +174,14 @@ class GraphRulesCharacterUnifier(PipelineStep):
             extract a lot of spurious links.  However, linking by
             coref is sometimes the only way to resolve a character
             alias.
+        :param ignore_lone_titles: a set of titles to ignore when
+            they stand on their own.  This avoids extracting false
+            positives characters such as 'Mr.' or 'Miss'.
         """
         self.min_appearances = min_appearances
         self.additional_hypocorisms = additional_hypocorisms
         self.link_corefs_mentions = link_corefs_mentions
+        self.ignore_lone_titles = ignore_lone_titles or set()
 
         super().__init__()
 
@@ -197,11 +202,16 @@ class GraphRulesCharacterUnifier(PipelineStep):
         import networkx as nx
 
         mentions = [m for m in entities if m.tag == "PER"]
-        mentions_str = [" ".join(m.tokens) for m in mentions]
+        mentions_str = set(
+            filter(
+                lambda m: not m in self.ignore_lone_titles,
+                map(lambda m: " ".join(m.tokens), mentions),
+            )
+        )
 
         # * create a graph where each node is a mention detected by NER
         G = nx.Graph()
-        for mention_str in set(mentions_str):
+        for mention_str in mentions_str:
             G.add_node(mention_str)
 
         # * HumanName local configuration - dependant on language

renard/pipeline/core.py

@@ -50,6 +50,13 @@ class Mention:
         self_dict["end_idx"] = self.end_idx + shift
         return self.__class__(**self_dict)
 
+    def __eq__(self, other: Mention) -> bool:
+        return (
+            self.tokens == other.tokens
+            and self.start_idx == other.start_idx
+            and self.end_idx == other.end_idx
+        )
+
     def __hash__(self) -> int:
         return hash(tuple(self.tokens) + (self.start_idx, self.end_idx))
 

{renard_pipeline-0.4.0.dist-info → renard_pipeline-0.4.2.dist-info}/METADATA

@@ -1,7 +1,8 @@
 Metadata-Version: 2.1
 Name: renard-pipeline
-Version: 0.4.0
+Version: 0.4.2
 Summary: Relationships Extraction from NARrative Documents
+Home-page: https://github.com/CompNet/Renard
 License: GPL-3.0-only
 Author: Arthur Amalvy
 Author-email: arthur.amalvy@univ-avignon.fr
@@ -31,6 +32,8 @@ Requires-Dist: tibert (>=0.3.0,<0.4.0)
 Requires-Dist: torch (>=2.0.0,!=2.0.1)
 Requires-Dist: tqdm (>=4.62.3,<5.0.0)
 Requires-Dist: transformers (>=4.36.0,<5.0.0)
+Project-URL: Documentation, https://compnet.github.io/Renard/
+Project-URL: Repository, https://github.com/CompNet/Renard
 Description-Content-Type: text/markdown
 
 # Renard
@@ -46,6 +49,8 @@ You can install the latest version using pip:
 
 > pip install renard-pipeline
 
+Currently, Renard supports Python 3.8, 3.9 and 3.10.
+
 
 # Documentation
 
@@ -56,7 +61,32 @@ If you need local documentation, it can be generated using `Sphinx`. From the `d
 
 # Tutorial
 
-`renard_tutorial.py` 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`).
+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:
+
+```python
+from renard.pipeline import Pipeline
+from renard.pipeline.tokenization import NLTKTokenizer
+from renard.pipeline.ner import NLTKNamedEntityRecognizer
+from renard.pipeline.character_unification import GraphRulesCharacterUnifier
+from renard.pipeline.graph_extraction import CoOccurrencesGraphExtractor
+
+with open("./my_doc.txt") as f:
+	text = f.read()
+
+pipeline = Pipeline(
+	[
+		NLTKTokenizer(),
+		NLTKNamedEntityRecognizer(),
+		GraphRulesCharacterUnifier(min_appearance=10),
+		CoOccurrencesGraphExtractor(co_occurrences_dist=25)
+	]
+)
+
+out = pipeline(text)
+```
+
+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`).
+
 
 
 # Running tests 

{renard_pipeline-0.4.0.dist-info → renard_pipeline-0.4.2.dist-info}/RECORD

@@ -3,9 +3,9 @@ renard/graph_utils.py,sha256=5jwky9JgJ-WMVHfeaiXkAAQwEfhR2BFSrWhck1Qmpgo,5812
 renard/ner_utils.py,sha256=jN1AQkaV0Kx-Bc0oc3SYBEmSUuKPBbzXqByOlaqH62k,11263
 renard/nltk_utils.py,sha256=mUJiwMrEDZV4Fla7WuMR-hA_OC2ZIwSXgW_0Ew18VSo,977
 renard/pipeline/__init__.py,sha256=8Yim2mmny8YGvM7N5-na5zK-C9UDxUb77K9ml-VirUA,35
-renard/pipeline/character_unification.py,sha256=GcnC8UYqn1RBOGVhYS9LVcTNqpxm9YoT-lPsE3vodek,14818
+renard/pipeline/character_unification.py,sha256=GJvPKw2zSMi0RpLLVlKsu7ewpxkrdxytND9PLxolbP4,15252
 renard/pipeline/characters_extraction.py,sha256=NzF8H9X19diW6rqwS5ERrRku7rFueO3S077H5C6kb7I,363
-renard/pipeline/core.py,sha256=Xw6AUQkqasBu2b1uCqAs4Pn_vLrZd1mDsP9TepuudFo,22360
+renard/pipeline/core.py,sha256=luKNUTCDtZfwKzxVIaImyIMwFFvIknfT1LdQtongj24,22570
 renard/pipeline/corefs/__init__.py,sha256=9c9AaXBcRrDBf1jhTtJ7DyjOJhX_Zej3FjlcGak7MK8,44
 renard/pipeline/corefs/corefs.py,sha256=nzYT6S9ify3FlgGB3FSDpAhs2UQYgW9c3CL2GRYzTms,11508
 renard/pipeline/graph_extraction.py,sha256=n0T_nzNGiwE9bDubpPknHe7bbDhJ4ndnqmoMmyfbeWg,19468
@@ -29,7 +29,7 @@ renard/resources/pronouns/pronouns.py,sha256=YJ8hM6H8QHrF2Xx6O5blqc-Sqe1D1YFL0sR
 renard/resources/titles/__init__.py,sha256=Jcg4B7stsWiAaXbFgNl_L3ICtCQmFe9bo3YjdkVL50w,45
 renard/resources/titles/titles.py,sha256=GsFccVJuTkgDWiAqWZpFd2R9pGvFKQZBOk4RWWuWDkw,968
 renard/utils.py,sha256=8J3swFqSi4YqhgYNXvttJ0s-DmJbl_yEYri6JpGEWH8,2340
-renard_pipeline-0.4.0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-renard_pipeline-0.4.0.dist-info/METADATA,sha256=LcFmKE9KkONguzTVGueOvPBiaavH98D8xFZKjYFQkLI,2681
-renard_pipeline-0.4.0.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
-renard_pipeline-0.4.0.dist-info/RECORD,,
+renard_pipeline-0.4.2.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+renard_pipeline-0.4.2.dist-info/METADATA,sha256=R1ZbG6Mdk1B5Zk73QSKB-lZu7rDnvWKe3M5JiDqPFxM,3697
+renard_pipeline-0.4.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+renard_pipeline-0.4.2.dist-info/RECORD,,

{renard_pipeline-0.4.0.dist-info → renard_pipeline-0.4.2.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.6.1
+Generator: poetry-core 1.9.0
 Root-Is-Purelib: true
 Tag: py3-none-any