renard-pipeline 0.6.0__tar.gz → 0.6.2__tar.gz

{renard_pipeline-0.6.0 → renard_pipeline-0.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: renard-pipeline
-Version: 0.6.0
+Version: 0.6.2
 Summary: Relationships Extraction from NARrative Documents
 Home-page: https://github.com/CompNet/Renard
 License: GPL-3.0-only
@@ -52,7 +52,7 @@ You can install the latest version using pip:
 
 > pip install renard-pipeline
 
-Currently, Renard supports Python 3.8, 3.9 and 3.10.
+Currently, Renard supports Python>=3.8,<=3.11
 
 
 # Documentation

{renard_pipeline-0.6.0 → renard_pipeline-0.6.2}/README.md

@@ -13,7 +13,7 @@ You can install the latest version using pip:
 
 > pip install renard-pipeline
 
-Currently, Renard supports Python 3.8, 3.9 and 3.10.
+Currently, Renard supports Python>=3.8,<=3.11
 
 
 # Documentation

{renard_pipeline-0.6.0 → renard_pipeline-0.6.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "renard-pipeline"
-version = "0.6.0"
+version = "0.6.2"
 description = "Relationships Extraction from NARrative Documents"
 authors = ["Arthur Amalvy <arthur.amalvy@univ-avignon.fr>"]
 license = "GPL-3.0-only"

{renard_pipeline-0.6.0 → renard_pipeline-0.6.2}/renard/graph_utils.py

@@ -124,6 +124,15 @@ def dynamic_graph_to_gephi_graph(graphs: List[nx.Graph]) -> nx.Graph:
     G = nx.Graph()
 
     for H_i, H in enumerate(graphs):
+
+        # update node attributes
+        for u in H.nodes:
+            G.add_node(u)
+            for key, value in H.nodes[u].items():
+                # format : (VALUE, START, END)
+                series = G.nodes[u].get(key, [])
+                G.nodes[u][key] = series + [(value, H_i, H_i + 1)]
+
         for u, v in H.edges:
             # create a new edge between two characters if it doesn't
             # exist yet

{renard_pipeline-0.6.0 → renard_pipeline-0.6.2}/renard/pipeline/graph_extraction.py

@@ -306,8 +306,11 @@ class CoOccurrencesGraphExtractor(PipelineStep):
 
         # * Construct graph from co-occurence matrix
         G = nx.Graph()
-        for character, _ in mentions:
-            G.add_node(character)
+        for character, mention in mentions:
+            # NOTE: we add an 'entity_type' attribute. This is useful
+            # when using the 'additional_ner_classes' option, to
+            # differentiate between different entity types.
+            G.add_node(character, entity_type=mention.tag)
 
         for i, (char1, mention1) in enumerate(mentions):
             for j, (char2, mention2) in enumerate(mentions):

{renard_pipeline-0.6.0 → renard_pipeline-0.6.2}/renard/pipeline/tokenization.py

@@ -37,6 +37,7 @@ class NLTKTokenizer(PipelineStep):
 
     def __init__(self):
         nltk.download("punkt", quiet=True)
+        nltk.download("punkt_tab", quiet=True)
         self.word_tokenizer = None
         self.sent_tokenizer = None
         super().__init__()