Update modules/text_analysis/semantic_analysis.py

modules/text_analysis/semantic_analysis.py

@@ -68,33 +68,36 @@ def identify_key_concepts(doc, top_n=10):
     word_freq = Counter([token.lemma_.lower() for token in doc if token.pos_ in ['NOUN', 'VERB', 'ADJ'] and not token.is_stop])
     return word_freq.most_common(top_n)
 
-def create_concept_graph(text, concepts):
-    vectorizer = TfidfVectorizer()
-    tfidf_matrix = vectorizer.fit_transform([text])
-    concept_vectors = vectorizer.transform([c[0] for c in concepts])
-    similarity_matrix = cosine_similarity(concept_vectors, concept_vectors)
-
+def create_concept_graph(doc, key_concepts):
     G = nx.Graph()
-    for i, (concept, weight) in enumerate(concepts):
-        G.add_node(concept, weight=weight)
-        for j in range(i+1, len(concepts)):
-            if similarity_matrix[i][j] > 0.1:
-                G.add_edge(concept, concepts[j][0], weight=similarity_matrix[i][j])
-
+    
+    # Añadir nodos
+    for concept, freq in key_concepts:
+        G.add_node(concept, weight=freq)
+    
+    # Añadir aristas basadas en la co-ocurrencia en oraciones
+    for sent in doc.sents:
+        sent_concepts = [token.lemma_.lower() for token in sent if token.lemma_.lower() in dict(key_concepts)]
+        for i, concept1 in enumerate(sent_concepts):
+            for concept2 in sent_concepts[i+1:]:
+                if G.has_edge(concept1, concept2):
+                    G[concept1][concept2]['weight'] += 1
+                else:
+                    G.add_edge(concept1, concept2, weight=1)
+    
     return G
 
 def visualize_concept_graph(G, lang):
-    fig, ax = plt.subplots(figsize=(15, 10))
+    fig, ax = plt.subplots(figsize=(12, 8))
     pos = nx.spring_layout(G, k=0.5, iterations=50)
     
     node_sizes = [G.nodes[node]['weight'] * 100 for node in G.nodes()]
     nx.draw_networkx_nodes(G, pos, node_size=node_sizes, node_color='lightblue', alpha=0.8, ax=ax)
     nx.draw_networkx_labels(G, pos, font_size=10, font_weight="bold", ax=ax)
-    nx.draw_networkx_edges(G, pos, width=1, alpha=0.5, ax=ax)
     
-    edge_labels = nx.get_edge_attributes(G, 'weight')
-    nx.draw_networkx_edge_labels(G, pos, edge_labels=edge_labels, font_size=8, ax=ax)
-
+    edge_weights = [G[u][v]['weight'] for u, v in G.edges()]
+    nx.draw_networkx_edges(G, pos, width=edge_weights, alpha=0.5, ax=ax)
+    
     title = {
         'es': "Relaciones entre Conceptos Clave",
         'en': "Key Concept Relations",
@@ -102,18 +105,18 @@ def visualize_concept_graph(G, lang):
     }
     ax.set_title(title[lang], fontsize=16)
     ax.axis('off')
-
+    
     plt.tight_layout()
     return fig
 
 def perform_semantic_analysis(text, nlp, lang):
     doc = nlp(text)
-
+    
     # Identificar conceptos clave
     key_concepts = identify_key_concepts(doc)
-
+    
     # Crear y visualizar grafo de conceptos
-    concept_graph = create_concept_graph(text, key_concepts)
+    concept_graph = create_concept_graph(doc, key_concepts)
     relations_graph = visualize_concept_graph(concept_graph, lang)
     
     return {