Spaces:
Sleeping
Sleeping
Create semantic_analysis_BackUp_18-5-2025.py
Browse files
modules/text_analysis/semantic_analysis_BackUp_18-5-2025.py
ADDED
@@ -0,0 +1,475 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# modules/text_analysis/semantic_analysis.py
|
2 |
+
|
3 |
+
# 1. Importaciones estándar del sistema
|
4 |
+
import logging
|
5 |
+
import io
|
6 |
+
import base64
|
7 |
+
from collections import Counter, defaultdict
|
8 |
+
|
9 |
+
# 2. Importaciones de terceros
|
10 |
+
import streamlit as st
|
11 |
+
import spacy
|
12 |
+
import networkx as nx
|
13 |
+
import matplotlib.pyplot as plt
|
14 |
+
from sklearn.feature_extraction.text import TfidfVectorizer
|
15 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
16 |
+
|
17 |
+
# Solo configurar si no hay handlers ya configurados
|
18 |
+
logger = logging.getLogger(__name__)
|
19 |
+
|
20 |
+
# 4. Importaciones locales
|
21 |
+
from .stopwords import (
|
22 |
+
process_text,
|
23 |
+
clean_text,
|
24 |
+
get_custom_stopwords,
|
25 |
+
get_stopwords_for_spacy
|
26 |
+
)
|
27 |
+
|
28 |
+
|
29 |
+
# Define colors for grammatical categories
|
30 |
+
POS_COLORS = {
|
31 |
+
'ADJ': '#FFA07A', 'ADP': '#98FB98', 'ADV': '#87CEFA', 'AUX': '#DDA0DD',
|
32 |
+
'CCONJ': '#F0E68C', 'DET': '#FFB6C1', 'INTJ': '#FF6347', 'NOUN': '#90EE90',
|
33 |
+
'NUM': '#FAFAD2', 'PART': '#D3D3D3', 'PRON': '#FFA500', 'PROPN': '#20B2AA',
|
34 |
+
'SCONJ': '#DEB887', 'SYM': '#7B68EE', 'VERB': '#FF69B4', 'X': '#A9A9A9',
|
35 |
+
}
|
36 |
+
|
37 |
+
POS_TRANSLATIONS = {
|
38 |
+
'es': {
|
39 |
+
'ADJ': 'Adjetivo', 'ADP': 'Preposición', 'ADV': 'Adverbio', 'AUX': 'Auxiliar',
|
40 |
+
'CCONJ': 'Conjunción Coordinante', 'DET': 'Determinante', 'INTJ': 'Interjección',
|
41 |
+
'NOUN': 'Sustantivo', 'NUM': 'Número', 'PART': 'Partícula', 'PRON': 'Pronombre',
|
42 |
+
'PROPN': 'Nombre Propio', 'SCONJ': 'Conjunción Subordinante', 'SYM': 'Símbolo',
|
43 |
+
'VERB': 'Verbo', 'X': 'Otro',
|
44 |
+
},
|
45 |
+
'en': {
|
46 |
+
'ADJ': 'Adjective', 'ADP': 'Preposition', 'ADV': 'Adverb', 'AUX': 'Auxiliary',
|
47 |
+
'CCONJ': 'Coordinating Conjunction', 'DET': 'Determiner', 'INTJ': 'Interjection',
|
48 |
+
'NOUN': 'Noun', 'NUM': 'Number', 'PART': 'Particle', 'PRON': 'Pronoun',
|
49 |
+
'PROPN': 'Proper Noun', 'SCONJ': 'Subordinating Conjunction', 'SYM': 'Symbol',
|
50 |
+
'VERB': 'Verb', 'X': 'Other',
|
51 |
+
},
|
52 |
+
'fr': {
|
53 |
+
'ADJ': 'Adjectif', 'ADP': 'Préposition', 'ADV': 'Adverbe', 'AUX': 'Auxiliaire',
|
54 |
+
'CCONJ': 'Conjonction de Coordination', 'DET': 'Déterminant', 'INTJ': 'Interjection',
|
55 |
+
'NOUN': 'Nom', 'NUM': 'Nombre', 'PART': 'Particule', 'PRON': 'Pronom',
|
56 |
+
'PROPN': 'Nom Propre', 'SCONJ': 'Conjonction de Subordination', 'SYM': 'Symbole',
|
57 |
+
'VERB': 'Verbe', 'X': 'Autre',
|
58 |
+
}
|
59 |
+
}
|
60 |
+
|
61 |
+
ENTITY_LABELS = {
|
62 |
+
'es': {
|
63 |
+
"Personas": "lightblue",
|
64 |
+
"Lugares": "lightcoral",
|
65 |
+
"Inventos": "lightgreen",
|
66 |
+
"Fechas": "lightyellow",
|
67 |
+
"Conceptos": "lightpink"
|
68 |
+
},
|
69 |
+
'en': {
|
70 |
+
"People": "lightblue",
|
71 |
+
"Places": "lightcoral",
|
72 |
+
"Inventions": "lightgreen",
|
73 |
+
"Dates": "lightyellow",
|
74 |
+
"Concepts": "lightpink"
|
75 |
+
},
|
76 |
+
'fr': {
|
77 |
+
"Personnes": "lightblue",
|
78 |
+
"Lieux": "lightcoral",
|
79 |
+
"Inventions": "lightgreen",
|
80 |
+
"Dates": "lightyellow",
|
81 |
+
"Concepts": "lightpink"
|
82 |
+
}
|
83 |
+
}
|
84 |
+
|
85 |
+
###########################################################
|
86 |
+
def fig_to_bytes(fig):
|
87 |
+
"""Convierte una figura de matplotlib a bytes."""
|
88 |
+
try:
|
89 |
+
buf = io.BytesIO()
|
90 |
+
fig.savefig(buf, format='png', dpi=300, bbox_inches='tight')
|
91 |
+
buf.seek(0)
|
92 |
+
return buf.getvalue()
|
93 |
+
except Exception as e:
|
94 |
+
logger.error(f"Error en fig_to_bytes: {str(e)}")
|
95 |
+
return None
|
96 |
+
|
97 |
+
###########################################################
|
98 |
+
def perform_semantic_analysis(text, nlp, lang_code):
|
99 |
+
"""
|
100 |
+
Realiza el análisis semántico completo del texto.
|
101 |
+
"""
|
102 |
+
if not text or not nlp or not lang_code:
|
103 |
+
logger.error("Parámetros inválidos para el análisis semántico")
|
104 |
+
return {
|
105 |
+
'success': False,
|
106 |
+
'error': 'Parámetros inválidos'
|
107 |
+
}
|
108 |
+
|
109 |
+
try:
|
110 |
+
logger.info(f"Starting semantic analysis for language: {lang_code}")
|
111 |
+
|
112 |
+
# Procesar texto y remover stopwords
|
113 |
+
doc = nlp(text)
|
114 |
+
if not doc:
|
115 |
+
logger.error("Error al procesar el texto con spaCy")
|
116 |
+
return {
|
117 |
+
'success': False,
|
118 |
+
'error': 'Error al procesar el texto'
|
119 |
+
}
|
120 |
+
|
121 |
+
# Identificar conceptos clave
|
122 |
+
logger.info("Identificando conceptos clave...")
|
123 |
+
stopwords = get_custom_stopwords(lang_code)
|
124 |
+
key_concepts = identify_key_concepts(doc, stopwords=stopwords)
|
125 |
+
|
126 |
+
if not key_concepts:
|
127 |
+
logger.warning("No se identificaron conceptos clave")
|
128 |
+
return {
|
129 |
+
'success': False,
|
130 |
+
'error': 'No se pudieron identificar conceptos clave'
|
131 |
+
}
|
132 |
+
|
133 |
+
# Crear grafo de conceptos
|
134 |
+
logger.info(f"Creando grafo de conceptos con {len(key_concepts)} conceptos...")
|
135 |
+
concept_graph = create_concept_graph(doc, key_concepts)
|
136 |
+
|
137 |
+
if not concept_graph.nodes():
|
138 |
+
logger.warning("Se creó un grafo vacío")
|
139 |
+
return {
|
140 |
+
'success': False,
|
141 |
+
'error': 'No se pudo crear el grafo de conceptos'
|
142 |
+
}
|
143 |
+
|
144 |
+
# Visualizar grafo
|
145 |
+
logger.info("Visualizando grafo...")
|
146 |
+
plt.clf() # Limpiar figura actual
|
147 |
+
concept_graph_fig = visualize_concept_graph(concept_graph, lang_code)
|
148 |
+
|
149 |
+
# Convertir a bytes
|
150 |
+
logger.info("Convirtiendo grafo a bytes...")
|
151 |
+
graph_bytes = fig_to_bytes(concept_graph_fig)
|
152 |
+
|
153 |
+
if not graph_bytes:
|
154 |
+
logger.error("Error al convertir grafo a bytes")
|
155 |
+
return {
|
156 |
+
'success': False,
|
157 |
+
'error': 'Error al generar visualización'
|
158 |
+
}
|
159 |
+
|
160 |
+
# Limpiar recursos
|
161 |
+
plt.close(concept_graph_fig)
|
162 |
+
plt.close('all')
|
163 |
+
|
164 |
+
result = {
|
165 |
+
'success': True,
|
166 |
+
'key_concepts': key_concepts,
|
167 |
+
'concept_graph': graph_bytes
|
168 |
+
}
|
169 |
+
|
170 |
+
logger.info("Análisis semántico completado exitosamente")
|
171 |
+
return result
|
172 |
+
|
173 |
+
except Exception as e:
|
174 |
+
logger.error(f"Error in perform_semantic_analysis: {str(e)}")
|
175 |
+
plt.close('all') # Asegurarse de limpiar recursos
|
176 |
+
return {
|
177 |
+
'success': False,
|
178 |
+
'error': str(e)
|
179 |
+
}
|
180 |
+
finally:
|
181 |
+
plt.close('all') # Asegurar limpieza incluso si hay error
|
182 |
+
|
183 |
+
############################################################
|
184 |
+
|
185 |
+
def identify_key_concepts(doc, stopwords, min_freq=2, min_length=3):
|
186 |
+
"""
|
187 |
+
Identifica conceptos clave en el texto, excluyendo entidades nombradas.
|
188 |
+
Args:
|
189 |
+
doc: Documento procesado por spaCy
|
190 |
+
stopwords: Lista de stopwords
|
191 |
+
min_freq: Frecuencia mínima para considerar un concepto
|
192 |
+
min_length: Longitud mínima del concepto
|
193 |
+
Returns:
|
194 |
+
List[Tuple[str, int]]: Lista de tuplas (concepto, frecuencia)
|
195 |
+
"""
|
196 |
+
try:
|
197 |
+
word_freq = Counter()
|
198 |
+
|
199 |
+
# Crear conjunto de tokens que son parte de entidades
|
200 |
+
entity_tokens = set()
|
201 |
+
for ent in doc.ents:
|
202 |
+
entity_tokens.update(token.i for token in ent)
|
203 |
+
|
204 |
+
# Procesar tokens
|
205 |
+
for token in doc:
|
206 |
+
# Verificar si el token no es parte de una entidad nombrada
|
207 |
+
if (token.i not in entity_tokens and # No es parte de una entidad
|
208 |
+
token.lemma_.lower() not in stopwords and # No es stopword
|
209 |
+
len(token.lemma_) >= min_length and # Longitud mínima
|
210 |
+
token.is_alpha and # Es alfabético
|
211 |
+
not token.is_punct and # No es puntuación
|
212 |
+
not token.like_num and # No es número
|
213 |
+
not token.is_space and # No es espacio
|
214 |
+
not token.is_stop and # No es stopword de spaCy
|
215 |
+
not token.pos_ == 'PROPN' and # No es nombre propio
|
216 |
+
not token.pos_ == 'SYM' and # No es símbolo
|
217 |
+
not token.pos_ == 'NUM' and # No es número
|
218 |
+
not token.pos_ == 'X'): # No es otro
|
219 |
+
|
220 |
+
# Convertir a minúsculas y añadir al contador
|
221 |
+
word_freq[token.lemma_.lower()] += 1
|
222 |
+
|
223 |
+
# Filtrar conceptos por frecuencia mínima y ordenar por frecuencia
|
224 |
+
concepts = [(word, freq) for word, freq in word_freq.items()
|
225 |
+
if freq >= min_freq]
|
226 |
+
concepts.sort(key=lambda x: x[1], reverse=True)
|
227 |
+
|
228 |
+
logger.info(f"Identified {len(concepts)} key concepts after excluding entities")
|
229 |
+
return concepts[:10]
|
230 |
+
|
231 |
+
except Exception as e:
|
232 |
+
logger.error(f"Error en identify_key_concepts: {str(e)}")
|
233 |
+
return []
|
234 |
+
|
235 |
+
########################################################################
|
236 |
+
|
237 |
+
def create_concept_graph(doc, key_concepts):
|
238 |
+
"""
|
239 |
+
Crea un grafo de relaciones entre conceptos, ignorando entidades.
|
240 |
+
Args:
|
241 |
+
doc: Documento procesado por spaCy
|
242 |
+
key_concepts: Lista de tuplas (concepto, frecuencia)
|
243 |
+
Returns:
|
244 |
+
nx.Graph: Grafo de conceptos
|
245 |
+
"""
|
246 |
+
try:
|
247 |
+
G = nx.Graph()
|
248 |
+
|
249 |
+
# Crear un conjunto de conceptos clave para búsqueda rápida
|
250 |
+
concept_words = {concept[0].lower() for concept in key_concepts}
|
251 |
+
|
252 |
+
# Crear conjunto de tokens que son parte de entidades
|
253 |
+
entity_tokens = set()
|
254 |
+
for ent in doc.ents:
|
255 |
+
entity_tokens.update(token.i for token in ent)
|
256 |
+
|
257 |
+
# Añadir nodos al grafo
|
258 |
+
for concept, freq in key_concepts:
|
259 |
+
G.add_node(concept.lower(), weight=freq)
|
260 |
+
|
261 |
+
# Analizar cada oración
|
262 |
+
for sent in doc.sents:
|
263 |
+
# Obtener conceptos en la oración actual, excluyendo entidades
|
264 |
+
current_concepts = []
|
265 |
+
for token in sent:
|
266 |
+
if (token.i not in entity_tokens and
|
267 |
+
token.lemma_.lower() in concept_words):
|
268 |
+
current_concepts.append(token.lemma_.lower())
|
269 |
+
|
270 |
+
# Crear conexiones entre conceptos en la misma oración
|
271 |
+
for i, concept1 in enumerate(current_concepts):
|
272 |
+
for concept2 in current_concepts[i+1:]:
|
273 |
+
if concept1 != concept2:
|
274 |
+
if G.has_edge(concept1, concept2):
|
275 |
+
G[concept1][concept2]['weight'] += 1
|
276 |
+
else:
|
277 |
+
G.add_edge(concept1, concept2, weight=1)
|
278 |
+
|
279 |
+
return G
|
280 |
+
|
281 |
+
except Exception as e:
|
282 |
+
logger.error(f"Error en create_concept_graph: {str(e)}")
|
283 |
+
return nx.Graph()
|
284 |
+
|
285 |
+
###############################################################################
|
286 |
+
|
287 |
+
def visualize_concept_graph(G, lang_code):
|
288 |
+
try:
|
289 |
+
# 1. Diccionario de traducciones
|
290 |
+
GRAPH_LABELS = {
|
291 |
+
'es': {
|
292 |
+
'concept_network': 'Relaciones entre conceptos clave',
|
293 |
+
'concept_centrality': 'Centralidad de conceptos clave'
|
294 |
+
},
|
295 |
+
'en': {
|
296 |
+
'concept_network': 'Relationships between key concepts',
|
297 |
+
'concept_centrality': 'Concept centrality'
|
298 |
+
},
|
299 |
+
'fr': {
|
300 |
+
'concept_network': 'Relations entre concepts clés',
|
301 |
+
'concept_centrality': 'Centralité des concepts'
|
302 |
+
},
|
303 |
+
'pt': {
|
304 |
+
'concept_network': 'Relações entre conceitos-chave',
|
305 |
+
'concept_centrality': 'Centralidade dos conceitos'
|
306 |
+
}
|
307 |
+
}
|
308 |
+
|
309 |
+
# 2. Obtener traducciones (inglés por defecto)
|
310 |
+
translations = GRAPH_LABELS.get(lang_code, GRAPH_LABELS['en'])
|
311 |
+
|
312 |
+
# Configuración de la figura
|
313 |
+
fig, ax = plt.subplots(figsize=(15, 10))
|
314 |
+
|
315 |
+
if not G.nodes():
|
316 |
+
logger.warning("Grafo vacío, retornando figura vacía")
|
317 |
+
return fig
|
318 |
+
|
319 |
+
# Convertir a grafo dirigido para flechas
|
320 |
+
DG = nx.DiGraph(G)
|
321 |
+
centrality = nx.degree_centrality(G)
|
322 |
+
|
323 |
+
# Layout consistente
|
324 |
+
pos = nx.spring_layout(DG, k=2, iterations=50, seed=42)
|
325 |
+
|
326 |
+
# Escalado de elementos visuales
|
327 |
+
num_nodes = len(DG.nodes())
|
328 |
+
scale_factor = 1000 if num_nodes < 10 else 500 if num_nodes < 20 else 200
|
329 |
+
node_sizes = [DG.nodes[node].get('weight', 1) * scale_factor for node in DG.nodes()]
|
330 |
+
edge_widths = [DG[u][v].get('weight', 1) for u, v in DG.edges()]
|
331 |
+
node_colors = [plt.cm.viridis(centrality[node]) for node in DG.nodes()]
|
332 |
+
|
333 |
+
# Dibujar elementos del grafo
|
334 |
+
nx.draw_networkx_nodes(
|
335 |
+
DG, pos,
|
336 |
+
node_size=node_sizes,
|
337 |
+
node_color=node_colors,
|
338 |
+
alpha=0.7,
|
339 |
+
ax=ax
|
340 |
+
)
|
341 |
+
|
342 |
+
nx.draw_networkx_edges(
|
343 |
+
DG, pos,
|
344 |
+
width=edge_widths,
|
345 |
+
alpha=0.6,
|
346 |
+
edge_color='gray',
|
347 |
+
arrows=True,
|
348 |
+
arrowsize=20,
|
349 |
+
arrowstyle='->',
|
350 |
+
connectionstyle='arc3,rad=0.2',
|
351 |
+
ax=ax
|
352 |
+
)
|
353 |
+
|
354 |
+
# Etiquetas de nodos
|
355 |
+
font_size = 12 if num_nodes < 10 else 10 if num_nodes < 20 else 8
|
356 |
+
nx.draw_networkx_labels(
|
357 |
+
DG, pos,
|
358 |
+
font_size=font_size,
|
359 |
+
font_weight='bold',
|
360 |
+
bbox=dict(facecolor='white', edgecolor='none', alpha=0.7),
|
361 |
+
ax=ax
|
362 |
+
)
|
363 |
+
|
364 |
+
# Barra de color (centralidad)
|
365 |
+
sm = plt.cm.ScalarMappable(
|
366 |
+
cmap=plt.cm.viridis,
|
367 |
+
norm=plt.Normalize(vmin=0, vmax=1)
|
368 |
+
)
|
369 |
+
sm.set_array([])
|
370 |
+
plt.colorbar(sm, ax=ax, label=translations['concept_centrality'])
|
371 |
+
|
372 |
+
# Título del gráfico
|
373 |
+
plt.title(translations['concept_network'], pad=20, fontsize=14)
|
374 |
+
ax.set_axis_off()
|
375 |
+
plt.tight_layout()
|
376 |
+
|
377 |
+
return fig
|
378 |
+
|
379 |
+
except Exception as e:
|
380 |
+
logger.error(f"Error en visualize_concept_graph: {str(e)}")
|
381 |
+
return plt.figure()
|
382 |
+
|
383 |
+
########################################################################
|
384 |
+
def create_entity_graph(entities):
|
385 |
+
G = nx.Graph()
|
386 |
+
for entity_type, entity_list in entities.items():
|
387 |
+
for entity in entity_list:
|
388 |
+
G.add_node(entity, type=entity_type)
|
389 |
+
for i, entity1 in enumerate(entity_list):
|
390 |
+
for entity2 in entity_list[i+1:]:
|
391 |
+
G.add_edge(entity1, entity2)
|
392 |
+
return G
|
393 |
+
|
394 |
+
|
395 |
+
#############################################################
|
396 |
+
def visualize_entity_graph(G, lang_code):
|
397 |
+
fig, ax = plt.subplots(figsize=(12, 8))
|
398 |
+
pos = nx.spring_layout(G)
|
399 |
+
for entity_type, color in ENTITY_LABELS[lang_code].items():
|
400 |
+
node_list = [node for node, data in G.nodes(data=True) if data['type'] == entity_type]
|
401 |
+
nx.draw_networkx_nodes(G, pos, nodelist=node_list, node_color=color, node_size=500, alpha=0.8, ax=ax)
|
402 |
+
nx.draw_networkx_edges(G, pos, width=1, alpha=0.5, ax=ax)
|
403 |
+
nx.draw_networkx_labels(G, pos, font_size=8, font_weight="bold", ax=ax)
|
404 |
+
ax.set_title(f"Relaciones entre Entidades ({lang_code})", fontsize=16)
|
405 |
+
ax.axis('off')
|
406 |
+
plt.tight_layout()
|
407 |
+
return fig
|
408 |
+
|
409 |
+
|
410 |
+
#################################################################################
|
411 |
+
def create_topic_graph(topics, doc):
|
412 |
+
G = nx.Graph()
|
413 |
+
for topic in topics:
|
414 |
+
G.add_node(topic, weight=doc.text.count(topic))
|
415 |
+
for i, topic1 in enumerate(topics):
|
416 |
+
for topic2 in topics[i+1:]:
|
417 |
+
weight = sum(1 for sent in doc.sents if topic1 in sent.text and topic2 in sent.text)
|
418 |
+
if weight > 0:
|
419 |
+
G.add_edge(topic1, topic2, weight=weight)
|
420 |
+
return G
|
421 |
+
|
422 |
+
def visualize_topic_graph(G, lang_code):
|
423 |
+
fig, ax = plt.subplots(figsize=(12, 8))
|
424 |
+
pos = nx.spring_layout(G)
|
425 |
+
node_sizes = [G.nodes[node]['weight'] * 100 for node in G.nodes()]
|
426 |
+
nx.draw_networkx_nodes(G, pos, node_size=node_sizes, node_color='lightgreen', alpha=0.8, ax=ax)
|
427 |
+
nx.draw_networkx_labels(G, pos, font_size=10, font_weight="bold", ax=ax)
|
428 |
+
edge_weights = [G[u][v]['weight'] for u, v in G.edges()]
|
429 |
+
nx.draw_networkx_edges(G, pos, width=edge_weights, alpha=0.5, ax=ax)
|
430 |
+
ax.set_title(f"Relaciones entre Temas ({lang_code})", fontsize=16)
|
431 |
+
ax.axis('off')
|
432 |
+
plt.tight_layout()
|
433 |
+
return fig
|
434 |
+
|
435 |
+
###########################################################################################
|
436 |
+
def generate_summary(doc, lang_code):
|
437 |
+
sentences = list(doc.sents)
|
438 |
+
summary = sentences[:3] # Toma las primeras 3 oraciones como resumen
|
439 |
+
return " ".join([sent.text for sent in summary])
|
440 |
+
|
441 |
+
def extract_entities(doc, lang_code):
|
442 |
+
entities = defaultdict(list)
|
443 |
+
for ent in doc.ents:
|
444 |
+
if ent.label_ in ENTITY_LABELS[lang_code]:
|
445 |
+
entities[ent.label_].append(ent.text)
|
446 |
+
return dict(entities)
|
447 |
+
|
448 |
+
def analyze_sentiment(doc, lang_code):
|
449 |
+
positive_words = sum(1 for token in doc if token.sentiment > 0)
|
450 |
+
negative_words = sum(1 for token in doc if token.sentiment < 0)
|
451 |
+
total_words = len(doc)
|
452 |
+
if positive_words > negative_words:
|
453 |
+
return "Positivo"
|
454 |
+
elif negative_words > positive_words:
|
455 |
+
return "Negativo"
|
456 |
+
else:
|
457 |
+
return "Neutral"
|
458 |
+
|
459 |
+
def extract_topics(doc, lang_code):
|
460 |
+
vectorizer = TfidfVectorizer(stop_words='english', max_features=5)
|
461 |
+
tfidf_matrix = vectorizer.fit_transform([doc.text])
|
462 |
+
feature_names = vectorizer.get_feature_names_out()
|
463 |
+
return list(feature_names)
|
464 |
+
|
465 |
+
# Asegúrate de que todas las funciones necesarias estén exportadas
|
466 |
+
__all__ = [
|
467 |
+
'perform_semantic_analysis',
|
468 |
+
'identify_key_concepts',
|
469 |
+
'create_concept_graph',
|
470 |
+
'visualize_concept_graph',
|
471 |
+
'fig_to_bytes', # Faltaba esta coma
|
472 |
+
'ENTITY_LABELS',
|
473 |
+
'POS_COLORS',
|
474 |
+
'POS_TRANSLATIONS'
|
475 |
+
]
|