Update modules/text_analysis/semantic_analysis.py

modules/text_analysis/semantic_analysis.py

@@ -6,8 +6,6 @@ import matplotlib.pyplot as plt
 from collections import Counter
 from collections import defaultdict
 
-# Remove the global nlp model loading
-
 # Define colors for grammatical categories
 POS_COLORS = {
     'ADJ': '#FFA07A',    # Light Salmon
@@ -215,9 +213,39 @@ def visualize_semantic_relations(doc, lang):
 
     return fig
 
+############################################################################################################################################
+def identify_and_contextualize_entities(doc, lang):
+    entities = []
+    for ent in doc.ents:
+        # Obtener el contexto (3 palabras antes y después de la entidad)
+        start = max(0, ent.start - 3)
+        end = min(len(doc), ent.end + 3)
+        context = doc[start:end].text
+        
+        entities.append({
+            'text': ent.text,
+            'label': ent.label_,
+            'start': ent.start,
+            'end': ent.end,
+            'context': context
+        })
+    
+    # Identificar conceptos clave (usando sustantivos y verbos más frecuentes)
+    word_freq = Counter([token.lemma_.lower() for token in doc if token.pos_ in ['NOUN', 'VERB'] and not token.is_stop])
+    key_concepts = word_freq.most_common(10)  # Top 10 conceptos clave
+    
+    return entities, key_concepts
+
+
 ############################################################################################################################################
 def perform_semantic_analysis(text, nlp, lang):
     doc = nlp(text)
+
+    # Identificar entidades y conceptos clave
+    entities, key_concepts = identify_and_contextualize_entities(doc, lang)
+
+    # Visualizar relaciones semánticas
+    relations_graph = visualize_semantic_relations(doc, lang)
     
     # Imprimir entidades para depuración
     print(f"Entidades encontradas ({lang}):")
@@ -225,6 +253,10 @@ def perform_semantic_analysis(text, nlp, lang):
         print(f"{ent.text} - {ent.label_}")
     
     relations_graph = visualize_semantic_relations(doc, lang)
-    return relations_graph  # Ahora solo devuelve un único gráfico
+    return {
+        'entities': entities,
+        'key_concepts': key_concepts,
+        'relations_graph': relations_graph
+    }
 
-__all__ = ['visualize_semantic_relations', 'create_semantic_graph', 'POS_COLORS', 'POS_TRANSLATIONS']    
+__all__ = ['visualize_semantic_relations', 'create_semantic_graph', 'POS_COLORS', 'POS_TRANSLATIONS', 'identify_and_contextualize_entities']