AIdeaText commited on
Commit
7e9e0ee
·
verified ·
1 Parent(s): 38f352f

Update modules/semantic/semantic_analysis.py

Browse files
modules/semantic/semantic_analysis.py CHANGED
@@ -94,7 +94,7 @@ def fig_to_bytes(fig):
94
  return None
95
 
96
  ###########################################################
97
- def perform_semantic_analysis(text, nlp, lang_code):
98
  """
99
  Realiza el análisis semántico completo del texto.
100
  """
@@ -428,6 +428,7 @@ def create_topic_graph(topics, doc):
428
  G.add_edge(topic1, topic2, weight=weight)
429
  return G
430
 
 
431
  def visualize_topic_graph(G, lang_code):
432
  fig, ax = plt.subplots(figsize=(12, 8))
433
  pos = nx.spring_layout(G)
@@ -447,6 +448,7 @@ def generate_summary(doc, lang_code):
447
  summary = sentences[:3] # Toma las primeras 3 oraciones como resumen
448
  return " ".join([sent.text for sent in summary])
449
 
 
450
  def extract_entities(doc, lang_code):
451
  entities = defaultdict(list)
452
  for ent in doc.ents:
@@ -454,6 +456,7 @@ def extract_entities(doc, lang_code):
454
  entities[ent.label_].append(ent.text)
455
  return dict(entities)
456
 
 
457
  def analyze_sentiment(doc, lang_code):
458
  positive_words = sum(1 for token in doc if token.sentiment > 0)
459
  negative_words = sum(1 for token in doc if token.sentiment < 0)
@@ -465,12 +468,15 @@ def analyze_sentiment(doc, lang_code):
465
  else:
466
  return "Neutral"
467
 
 
468
  def extract_topics(doc, lang_code):
469
  vectorizer = TfidfVectorizer(stop_words='english', max_features=5)
470
  tfidf_matrix = vectorizer.fit_transform([doc.text])
471
  feature_names = vectorizer.get_feature_names_out()
472
  return list(feature_names)
473
 
 
 
474
  # Asegúrate de que todas las funciones necesarias estén exportadas
475
  __all__ = [
476
  'perform_semantic_analysis',
 
94
  return None
95
 
96
  ###########################################################
97
+ def perform_semantic_analysis(text, nlp, lang_code, semantic_t):
98
  """
99
  Realiza el análisis semántico completo del texto.
100
  """
 
428
  G.add_edge(topic1, topic2, weight=weight)
429
  return G
430
 
431
+ ##################################################
432
  def visualize_topic_graph(G, lang_code):
433
  fig, ax = plt.subplots(figsize=(12, 8))
434
  pos = nx.spring_layout(G)
 
448
  summary = sentences[:3] # Toma las primeras 3 oraciones como resumen
449
  return " ".join([sent.text for sent in summary])
450
 
451
+ ##################################################
452
  def extract_entities(doc, lang_code):
453
  entities = defaultdict(list)
454
  for ent in doc.ents:
 
456
  entities[ent.label_].append(ent.text)
457
  return dict(entities)
458
 
459
+ ##################################################
460
  def analyze_sentiment(doc, lang_code):
461
  positive_words = sum(1 for token in doc if token.sentiment > 0)
462
  negative_words = sum(1 for token in doc if token.sentiment < 0)
 
468
  else:
469
  return "Neutral"
470
 
471
+ ##################################################
472
  def extract_topics(doc, lang_code):
473
  vectorizer = TfidfVectorizer(stop_words='english', max_features=5)
474
  tfidf_matrix = vectorizer.fit_transform([doc.text])
475
  feature_names = vectorizer.get_feature_names_out()
476
  return list(feature_names)
477
 
478
+
479
+ ##################################################
480
  # Asegúrate de que todas las funciones necesarias estén exportadas
481
  __all__ = [
482
  'perform_semantic_analysis',