Update modules/semantic_analysis.py

modules/semantic_analysis.py

@@ -119,10 +119,12 @@ def visualize_context_graph(doc, lang):
 
     # Add edges
     for sent in doc.sents:
-        sent_entities = [ent.text for ent in sent.ents if ent.text in G.nodes()]
-        for i in range(len(sent_entities)):
-            for j in range(i+1, len(sent_entities)):
-                G.add_edge(sent_entities[i], sent_entities[j])
+        sent_entities = [ent for ent in sent.ents if ent.text in G.nodes()]
+        person = next((ent for ent in sent_entities if ent.label_ == "PER"), None)
+        if person:
+            for ent in sent_entities:
+                if ent != person:
+                    G.add_edge(person.text, ent.text)
 
     # Visualize
     plt.figure(figsize=(20, 15))
@@ -137,7 +139,7 @@ def visualize_context_graph(doc, lang):
     legend_elements = [plt.Rectangle((0,0),1,1,fc=color, edgecolor='none') for color in color_map.values()]
     plt.legend(legend_elements, color_map.keys(), loc='upper left', bbox_to_anchor=(1, 1))
 
-    plt.title("Análisis de Contexto" if lang == 'es' else "Context Analysis" if lang == 'en' else "Analyse de Contexte", fontsize=20)
+    plt.title("Análisis del Contexto" if lang == 'es' else "Context Analysis" if lang == 'en' else "Analyse du Contexte", fontsize=20)
     plt.axis('off')
 
     return plt
@@ -160,27 +162,36 @@ def create_semantic_graph(doc, lang):
     return G, pos_counts
 
 def visualize_semantic_relations(doc, lang):
-    G, pos_counts = create_semantic_graph(doc, lang)
+    G = nx.Graph()
+    word_freq = Counter(token.text.lower() for token in doc if token.pos_ not in ['PUNCT', 'SPACE'])
+    top_words = [word for word, _ in word_freq.most_common(20)]  # Top 20 most frequent words
+
+    for token in doc:
+        if token.text.lower() in top_words:
+            G.add_node(token.text, pos=token.pos_)
+
+    for token in doc:
+        if token.text.lower() in top_words and token.head.text.lower() in top_words:
+            G.add_edge(token.text, token.head.text, label=token.dep_)
 
     plt.figure(figsize=(24, 18))
     pos = nx.spring_layout(G, k=0.9, iterations=50)
 
-    node_colors = [G.nodes[node].get('color', '#CCCCCC') for node in G.nodes()]
-    node_sizes = [G.nodes[node].get('size', 100) for node in G.nodes()]
+    node_colors = [POS_COLORS.get(G.nodes[node]['pos'], '#CCCCCC') for node in G.nodes()]
 
-    nx.draw(G, pos, node_color=node_colors, node_size=node_sizes, with_labels=True, 
-            font_size=8, font_weight='bold', arrows=True, arrowsize=20, width=2, edge_color='gray')
+    nx.draw(G, pos, node_color=node_colors, with_labels=True, 
+            font_size=10, font_weight='bold', arrows=True, arrowsize=20, width=2, edge_color='gray')
 
     edge_labels = nx.get_edge_attributes(G, 'label')
     nx.draw_networkx_edge_labels(G, pos, edge_labels=edge_labels, font_size=8)
 
-    plt.title("Análisis de Relaciones Semánticas" if lang == 'es' else "Semantic Relations Analysis" if lang == 'en' else "Analyse des Relations Sémantiques",
+    plt.title("Relaciones Semánticas Relevantes" if lang == 'es' else "Relevant Semantic Relations" if lang == 'en' else "Relations Sémantiques Pertinentes",
               fontsize=20, fontweight='bold')
     plt.axis('off')
 
-    legend_elements = [plt.Rectangle((0,0),1,1, facecolor=color, edgecolor='none', 
-                       label=f"{POS_TRANSLATIONS[lang].get(pos, pos)} ({pos_counts.get(pos, 0)})")
-                       for pos, color in POS_COLORS.items() if pos in pos_counts]
+    legend_elements = [plt.Rectangle((0,0),1,1, facecolor=POS_COLORS.get(pos, '#CCCCCC'), edgecolor='none', 
+                       label=f"{POS_TRANSLATIONS[lang].get(pos, pos)}")
+                       for pos in set(nx.get_node_attributes(G, 'pos').values())]
     plt.legend(handles=legend_elements, loc='center left', bbox_to_anchor=(1, 0.5), fontsize=12)
 
     return plt