Update modules/studentact/current_situation_analysis.py

modules/studentact/current_situation_analysis.py

@@ -98,13 +98,17 @@ def analyze_cohesion(doc):
 
 def analyze_structure(doc):
     """Analiza la complejidad estructural"""
-    root_distances = []
-    for token in doc:
-        if token.dep_ == 'ROOT':
-            depths = get_dependency_depths(token)
-            root_distances.extend(depths)
-    avg_depth = sum(root_distances) / len(root_distances) if root_distances else 0
-    return normalize_score(avg_depth, optimal_depth=3)
+    try:
+        root_distances = []
+        for token in doc:
+            if token.dep_ == 'ROOT':
+                depths = get_dependency_depths(token)
+                root_distances.extend(depths)
+        avg_depth = sum(root_distances) / len(root_distances) if root_distances else 0
+        return normalize_score(avg_depth, optimal_depth=3)  # Usando optimal_depth en lugar de optimal_value
+    except Exception as e:
+        logger.error(f"Error en analyze_structure: {str(e)}")
+        return 0.0
 
 
 # Funciones auxiliares de análisis
@@ -115,7 +119,8 @@ def get_dependency_depths(token, depth=0):
         depths.extend(get_dependency_depths(child, depth + 1))
     return depths
 
-def normalize_score(value, optimal_value=1.0, range_factor=2.0, optimal_length=None, optimal_connections=None):
+def normalize_score(value, optimal_value=1.0, range_factor=2.0, optimal_length=None, 
+                   optimal_connections=None, optimal_depth=None):
     """
     Normaliza un valor a una escala de 0-1.
     
@@ -125,23 +130,25 @@ def normalize_score(value, optimal_value=1.0, range_factor=2.0, optimal_length=N
         range_factor: Factor para ajustar el rango
         optimal_length: Longitud óptima (opcional)
         optimal_connections: Número óptimo de conexiones (opcional)
+        optimal_depth: Profundidad óptima de estructura (opcional)
     
     Returns:
         float: Valor normalizado entre 0 y 1
     """
     try:
-        if optimal_connections is not None:
-            # Usar optimal_connections si está definido
+        if optimal_depth is not None:
+            diff = abs(value - optimal_depth)
+            max_diff = optimal_depth * range_factor
+            return 1.0 - min(diff / max_diff, 1.0)
+        elif optimal_connections is not None:
             diff = abs(value - optimal_connections)
             max_diff = optimal_connections * range_factor
             return 1.0 - min(diff / max_diff, 1.0)
         elif optimal_length is not None:
-            # Usar optimal_length si está definido
             diff = abs(value - optimal_length)
             max_diff = optimal_length * range_factor
             return 1.0 - min(diff / max_diff, 1.0)
         else:
-            # Usar optimal_value por defecto
             diff = abs(value - optimal_value)
             max_diff = optimal_value * range_factor
             return 1.0 - min(diff / max_diff, 1.0)
@@ -299,21 +306,16 @@ def create_syntax_complexity_graph(doc):
 
 
 def create_cohesion_heatmap(doc):
-    """
-    Genera un mapa de calor que muestra la cohesión entre párrafos/oraciones.
-    """
+    """Genera un mapa de calor que muestra la cohesión entre párrafos/oraciones."""
     try:
-        # Dividir en oraciones
         sentences = list(doc.sents)
         n_sentences = len(sentences)
         
         if n_sentences < 2:
             return None
             
-        # Crear matriz de similitud
         similarity_matrix = np.zeros((n_sentences, n_sentences))
         
-        # Calcular similitud entre pares de oraciones 
         for i in range(n_sentences):
             for j in range(n_sentences):
                 sent1_lemmas = {token.lemma_ for token in sentences[i] 
@@ -322,8 +324,8 @@ def create_cohesion_heatmap(doc):
                               if token.is_alpha and not token.is_stop}
                 
                 if sent1_lemmas and sent2_lemmas:
-                    intersection = len(sent1_lemmas & sent2_words)
-                    union = len(sent1_lemmas | sent2_words)
+                    intersection = len(sent1_lemmas & sent2_lemmas)  # Corregido aquí
+                    union = len(sent1_lemmas | sent2_lemmas)  # Y aquí
                     similarity_matrix[i, j] = intersection / union if union > 0 else 0
         
         # Crear visualización