Spaces:
Sleeping
Sleeping
Delete modules/text_analysis/semantic_analysis.py
Browse files
modules/text_analysis/semantic_analysis.py
DELETED
@@ -1,486 +0,0 @@
|
|
1 |
-
# modules/text_analysis/semantic_analysis.py
|
2 |
-
|
3 |
-
# 1. Importaciones est谩ndar 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': 'Preposici贸n', 'ADV': 'Adverbio', 'AUX': 'Auxiliar',
|
40 |
-
'CCONJ': 'Conjunci贸n Coordinante', 'DET': 'Determinante', 'INTJ': 'Interjecci贸n',
|
41 |
-
'NOUN': 'Sustantivo', 'NUM': 'N煤mero', 'PART': 'Part铆cula', 'PRON': 'Pronombre',
|
42 |
-
'PROPN': 'Nombre Propio', 'SCONJ': 'Conjunci贸n Subordinante', 'SYM': 'S铆mbolo',
|
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': 'Pr茅position', 'ADV': 'Adverbe', 'AUX': 'Auxiliaire',
|
54 |
-
'CCONJ': 'Conjonction de Coordination', 'DET': 'D茅terminant', '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, semantic_t):
|
99 |
-
"""
|
100 |
-
Realiza el an谩lisis sem谩ntico completo del texto.
|
101 |
-
"""
|
102 |
-
if not text or not nlp or not lang_code:
|
103 |
-
logger.error("Par谩metros inv谩lidos para el an谩lisis sem谩ntico")
|
104 |
-
return {
|
105 |
-
'success': False,
|
106 |
-
'error': 'Par谩metros inv谩lidos'
|
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 cre贸 un grafo vac铆o")
|
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 |
-
|
148 |
-
concept_graph_fig = visualize_concept_graph(concept_graph, lang_code, semantic_t)
|
149 |
-
|
150 |
-
# Convertir a bytes
|
151 |
-
logger.info("Convirtiendo grafo a bytes...")
|
152 |
-
graph_bytes = fig_to_bytes(concept_graph_fig)
|
153 |
-
|
154 |
-
if not graph_bytes:
|
155 |
-
logger.error("Error al convertir grafo a bytes")
|
156 |
-
return {
|
157 |
-
'success': False,
|
158 |
-
'error': 'Error al generar visualizaci贸n'
|
159 |
-
}
|
160 |
-
|
161 |
-
# Limpiar recursos
|
162 |
-
plt.close(concept_graph_fig)
|
163 |
-
plt.close('all')
|
164 |
-
|
165 |
-
result = {
|
166 |
-
'success': True,
|
167 |
-
'key_concepts': key_concepts,
|
168 |
-
'concept_graph': graph_bytes
|
169 |
-
}
|
170 |
-
|
171 |
-
logger.info("An谩lisis sem谩ntico completado exitosamente")
|
172 |
-
return result
|
173 |
-
|
174 |
-
except Exception as e:
|
175 |
-
logger.error(f"Error in perform_semantic_analysis: {str(e)}")
|
176 |
-
plt.close('all') # Asegurarse de limpiar recursos
|
177 |
-
return {
|
178 |
-
'success': False,
|
179 |
-
'error': str(e)
|
180 |
-
}
|
181 |
-
finally:
|
182 |
-
plt.close('all') # Asegurar limpieza incluso si hay error
|
183 |
-
|
184 |
-
############################################################
|
185 |
-
|
186 |
-
def identify_key_concepts(doc, stopwords, min_freq=2, min_length=3):
|
187 |
-
"""
|
188 |
-
Identifica conceptos clave en el texto, excluyendo entidades nombradas.
|
189 |
-
Args:
|
190 |
-
doc: Documento procesado por spaCy
|
191 |
-
stopwords: Lista de stopwords
|
192 |
-
min_freq: Frecuencia m铆nima para considerar un concepto
|
193 |
-
min_length: Longitud m铆nima del concepto
|
194 |
-
Returns:
|
195 |
-
List[Tuple[str, int]]: Lista de tuplas (concepto, frecuencia)
|
196 |
-
"""
|
197 |
-
try:
|
198 |
-
word_freq = Counter()
|
199 |
-
|
200 |
-
# Crear conjunto de tokens que son parte de entidades
|
201 |
-
entity_tokens = set()
|
202 |
-
for ent in doc.ents:
|
203 |
-
entity_tokens.update(token.i for token in ent)
|
204 |
-
|
205 |
-
# Procesar tokens
|
206 |
-
for token in doc:
|
207 |
-
# Verificar si el token no es parte de una entidad nombrada
|
208 |
-
if (token.i not in entity_tokens and # No es parte de una entidad
|
209 |
-
token.lemma_.lower() not in stopwords and # No es stopword
|
210 |
-
len(token.lemma_) >= min_length and # Longitud m铆nima
|
211 |
-
token.is_alpha and # Es alfab茅tico
|
212 |
-
not token.is_punct and # No es puntuaci贸n
|
213 |
-
not token.like_num and # No es n煤mero
|
214 |
-
not token.is_space and # No es espacio
|
215 |
-
not token.is_stop and # No es stopword de spaCy
|
216 |
-
not token.pos_ == 'PROPN' and # No es nombre propio
|
217 |
-
not token.pos_ == 'SYM' and # No es s铆mbolo
|
218 |
-
not token.pos_ == 'NUM' and # No es n煤mero
|
219 |
-
not token.pos_ == 'X'): # No es otro
|
220 |
-
|
221 |
-
# Convertir a min煤sculas y a帽adir al contador
|
222 |
-
word_freq[token.lemma_.lower()] += 1
|
223 |
-
|
224 |
-
# Filtrar conceptos por frecuencia m铆nima y ordenar por frecuencia
|
225 |
-
concepts = [(word, freq) for word, freq in word_freq.items()
|
226 |
-
if freq >= min_freq]
|
227 |
-
concepts.sort(key=lambda x: x[1], reverse=True)
|
228 |
-
|
229 |
-
logger.info(f"Identified {len(concepts)} key concepts after excluding entities")
|
230 |
-
return concepts[:10]
|
231 |
-
|
232 |
-
except Exception as e:
|
233 |
-
logger.error(f"Error en identify_key_concepts: {str(e)}")
|
234 |
-
return []
|
235 |
-
|
236 |
-
########################################################################
|
237 |
-
|
238 |
-
def create_concept_graph(doc, key_concepts):
|
239 |
-
"""
|
240 |
-
Crea un grafo de relaciones entre conceptos, ignorando entidades.
|
241 |
-
Args:
|
242 |
-
doc: Documento procesado por spaCy
|
243 |
-
key_concepts: Lista de tuplas (concepto, frecuencia)
|
244 |
-
Returns:
|
245 |
-
nx.Graph: Grafo de conceptos
|
246 |
-
"""
|
247 |
-
try:
|
248 |
-
G = nx.Graph()
|
249 |
-
|
250 |
-
# Crear un conjunto de conceptos clave para b煤squeda r谩pida
|
251 |
-
concept_words = {concept[0].lower() for concept in key_concepts}
|
252 |
-
|
253 |
-
# Crear conjunto de tokens que son parte de entidades
|
254 |
-
entity_tokens = set()
|
255 |
-
for ent in doc.ents:
|
256 |
-
entity_tokens.update(token.i for token in ent)
|
257 |
-
|
258 |
-
# A帽adir nodos al grafo
|
259 |
-
for concept, freq in key_concepts:
|
260 |
-
G.add_node(concept.lower(), weight=freq)
|
261 |
-
|
262 |
-
# Analizar cada oraci贸n
|
263 |
-
for sent in doc.sents:
|
264 |
-
# Obtener conceptos en la oraci贸n actual, excluyendo entidades
|
265 |
-
current_concepts = []
|
266 |
-
for token in sent:
|
267 |
-
if (token.i not in entity_tokens and
|
268 |
-
token.lemma_.lower() in concept_words):
|
269 |
-
current_concepts.append(token.lemma_.lower())
|
270 |
-
|
271 |
-
# Crear conexiones entre conceptos en la misma oraci贸n
|
272 |
-
for i, concept1 in enumerate(current_concepts):
|
273 |
-
for concept2 in current_concepts[i+1:]:
|
274 |
-
if concept1 != concept2:
|
275 |
-
if G.has_edge(concept1, concept2):
|
276 |
-
G[concept1][concept2]['weight'] += 1
|
277 |
-
else:
|
278 |
-
G.add_edge(concept1, concept2, weight=1)
|
279 |
-
|
280 |
-
return G
|
281 |
-
|
282 |
-
except Exception as e:
|
283 |
-
logger.error(f"Error en create_concept_graph: {str(e)}")
|
284 |
-
return nx.Graph()
|
285 |
-
|
286 |
-
###############################################################################
|
287 |
-
|
288 |
-
def visualize_concept_graph(G, lang_code, semantic_t):
|
289 |
-
"""
|
290 |
-
Visualiza el grafo de conceptos con layout consistente.
|
291 |
-
Args:
|
292 |
-
G: networkx.Graph - Grafo de conceptos
|
293 |
-
lang_code: str - C贸digo del idioma
|
294 |
-
Returns:
|
295 |
-
matplotlib.figure.Figure - Figura del grafo
|
296 |
-
"""
|
297 |
-
try:
|
298 |
-
# Crear nueva figura con mayor tama帽o y definir los ejes expl铆citamente
|
299 |
-
fig, ax = plt.subplots(figsize=(15, 10))
|
300 |
-
|
301 |
-
if not G.nodes():
|
302 |
-
logger.warning("Grafo vac铆o, retornando figura vac铆a")
|
303 |
-
return fig
|
304 |
-
|
305 |
-
# Convertir grafo no dirigido a dirigido para mostrar flechas
|
306 |
-
DG = nx.DiGraph(G)
|
307 |
-
|
308 |
-
# Calcular centralidad de los nodos para el color
|
309 |
-
centrality = nx.degree_centrality(G)
|
310 |
-
|
311 |
-
# Establecer semilla para reproducibilidad
|
312 |
-
seed = 42
|
313 |
-
|
314 |
-
# Calcular layout con par谩metros fijos
|
315 |
-
pos = nx.spring_layout(
|
316 |
-
DG,
|
317 |
-
k=2, # Distancia ideal entre nodos
|
318 |
-
iterations=50, # N煤mero de iteraciones
|
319 |
-
seed=seed # Semilla fija para reproducibilidad
|
320 |
-
)
|
321 |
-
|
322 |
-
# Calcular factor de escala basado en n煤mero de nodos
|
323 |
-
num_nodes = len(DG.nodes())
|
324 |
-
scale_factor = 1000 if num_nodes < 10 else 500 if num_nodes < 20 else 200
|
325 |
-
|
326 |
-
# Obtener pesos ajustados
|
327 |
-
node_weights = [DG.nodes[node].get('weight', 1) * scale_factor for node in DG.nodes()]
|
328 |
-
edge_weights = [DG[u][v].get('weight', 1) for u, v in DG.edges()]
|
329 |
-
|
330 |
-
# Crear mapa de colores basado en centralidad
|
331 |
-
node_colors = [plt.cm.viridis(centrality[node]) for node in DG.nodes()]
|
332 |
-
|
333 |
-
# Dibujar nodos
|
334 |
-
nodes = nx.draw_networkx_nodes(
|
335 |
-
DG,
|
336 |
-
pos,
|
337 |
-
node_size=node_weights,
|
338 |
-
node_color=node_colors,
|
339 |
-
alpha=0.7,
|
340 |
-
ax=ax
|
341 |
-
)
|
342 |
-
|
343 |
-
# Dibujar aristas con flechas
|
344 |
-
edges = nx.draw_networkx_edges(
|
345 |
-
DG,
|
346 |
-
pos,
|
347 |
-
width=edge_weights,
|
348 |
-
alpha=0.6,
|
349 |
-
edge_color='gray',
|
350 |
-
arrows=True,
|
351 |
-
arrowsize=20,
|
352 |
-
arrowstyle='->',
|
353 |
-
connectionstyle='arc3,rad=0.2',
|
354 |
-
ax=ax
|
355 |
-
)
|
356 |
-
|
357 |
-
# Ajustar tama帽o de fuente seg煤n n煤mero de nodos
|
358 |
-
font_size = 12 if num_nodes < 10 else 10 if num_nodes < 20 else 8
|
359 |
-
|
360 |
-
# Dibujar etiquetas con fondo blanco para mejor legibilidad
|
361 |
-
labels = nx.draw_networkx_labels(
|
362 |
-
DG,
|
363 |
-
pos,
|
364 |
-
font_size=font_size,
|
365 |
-
font_weight='bold',
|
366 |
-
bbox=dict(
|
367 |
-
facecolor='white',
|
368 |
-
edgecolor='none',
|
369 |
-
alpha=0.7
|
370 |
-
),
|
371 |
-
ax=ax
|
372 |
-
)
|
373 |
-
|
374 |
-
# A帽adir leyenda de centralidad
|
375 |
-
sm = plt.cm.ScalarMappable(
|
376 |
-
cmap=plt.cm.viridis,
|
377 |
-
norm=plt.Normalize(vmin=0, vmax=1)
|
378 |
-
)
|
379 |
-
sm.set_array([])
|
380 |
-
plt.colorbar(sm, ax=ax, label=semantic_t.get('concept_centrality', 'Centralidad de los conceptos clave'))
|
381 |
-
|
382 |
-
plt.title(semantic_t.get('concept_network', 'Relaciones entre los conceptos clave'), pad=20, fontsize=14)
|
383 |
-
ax.set_axis_off()
|
384 |
-
|
385 |
-
# Ajustar el layout para que la barra de color no se superponga
|
386 |
-
plt.tight_layout()
|
387 |
-
|
388 |
-
return fig
|
389 |
-
|
390 |
-
except Exception as e:
|
391 |
-
logger.error(f"Error en visualize_concept_graph: {str(e)}")
|
392 |
-
return plt.figure() # Retornar figura vac铆a en caso de error
|
393 |
-
|
394 |
-
########################################################################
|
395 |
-
def create_entity_graph(entities):
|
396 |
-
G = nx.Graph()
|
397 |
-
for entity_type, entity_list in entities.items():
|
398 |
-
for entity in entity_list:
|
399 |
-
G.add_node(entity, type=entity_type)
|
400 |
-
for i, entity1 in enumerate(entity_list):
|
401 |
-
for entity2 in entity_list[i+1:]:
|
402 |
-
G.add_edge(entity1, entity2)
|
403 |
-
return G
|
404 |
-
|
405 |
-
|
406 |
-
#############################################################
|
407 |
-
def visualize_entity_graph(G, lang_code):
|
408 |
-
fig, ax = plt.subplots(figsize=(12, 8))
|
409 |
-
pos = nx.spring_layout(G)
|
410 |
-
for entity_type, color in ENTITY_LABELS[lang_code].items():
|
411 |
-
node_list = [node for node, data in G.nodes(data=True) if data['type'] == entity_type]
|
412 |
-
nx.draw_networkx_nodes(G, pos, nodelist=node_list, node_color=color, node_size=500, alpha=0.8, ax=ax)
|
413 |
-
nx.draw_networkx_edges(G, pos, width=1, alpha=0.5, ax=ax)
|
414 |
-
nx.draw_networkx_labels(G, pos, font_size=8, font_weight="bold", ax=ax)
|
415 |
-
ax.set_title(f"Relaciones entre Entidades ({lang_code})", fontsize=16)
|
416 |
-
ax.axis('off')
|
417 |
-
plt.tight_layout()
|
418 |
-
return fig
|
419 |
-
|
420 |
-
|
421 |
-
#################################################################################
|
422 |
-
def create_topic_graph(topics, doc):
|
423 |
-
G = nx.Graph()
|
424 |
-
for topic in topics:
|
425 |
-
G.add_node(topic, weight=doc.text.count(topic))
|
426 |
-
for i, topic1 in enumerate(topics):
|
427 |
-
for topic2 in topics[i+1:]:
|
428 |
-
weight = sum(1 for sent in doc.sents if topic1 in sent.text and topic2 in sent.text)
|
429 |
-
if weight > 0:
|
430 |
-
G.add_edge(topic1, topic2, weight=weight)
|
431 |
-
return G
|
432 |
-
|
433 |
-
def visualize_topic_graph(G, lang_code):
|
434 |
-
fig, ax = plt.subplots(figsize=(12, 8))
|
435 |
-
pos = nx.spring_layout(G)
|
436 |
-
node_sizes = [G.nodes[node]['weight'] * 100 for node in G.nodes()]
|
437 |
-
nx.draw_networkx_nodes(G, pos, node_size=node_sizes, node_color='lightgreen', alpha=0.8, ax=ax)
|
438 |
-
nx.draw_networkx_labels(G, pos, font_size=10, font_weight="bold", ax=ax)
|
439 |
-
edge_weights = [G[u][v]['weight'] for u, v in G.edges()]
|
440 |
-
nx.draw_networkx_edges(G, pos, width=edge_weights, alpha=0.5, ax=ax)
|
441 |
-
ax.set_title(f"Relaciones entre Temas ({lang_code})", fontsize=16)
|
442 |
-
ax.axis('off')
|
443 |
-
plt.tight_layout()
|
444 |
-
return fig
|
445 |
-
|
446 |
-
###########################################################################################
|
447 |
-
def generate_summary(doc, lang_code):
|
448 |
-
sentences = list(doc.sents)
|
449 |
-
summary = sentences[:3] # Toma las primeras 3 oraciones como resumen
|
450 |
-
return " ".join([sent.text for sent in summary])
|
451 |
-
|
452 |
-
def extract_entities(doc, lang_code):
|
453 |
-
entities = defaultdict(list)
|
454 |
-
for ent in doc.ents:
|
455 |
-
if ent.label_ in ENTITY_LABELS[lang_code]:
|
456 |
-
entities[ent.label_].append(ent.text)
|
457 |
-
return dict(entities)
|
458 |
-
|
459 |
-
def analyze_sentiment(doc, lang_code):
|
460 |
-
positive_words = sum(1 for token in doc if token.sentiment > 0)
|
461 |
-
negative_words = sum(1 for token in doc if token.sentiment < 0)
|
462 |
-
total_words = len(doc)
|
463 |
-
if positive_words > negative_words:
|
464 |
-
return "Positivo"
|
465 |
-
elif negative_words > positive_words:
|
466 |
-
return "Negativo"
|
467 |
-
else:
|
468 |
-
return "Neutral"
|
469 |
-
|
470 |
-
def extract_topics(doc, lang_code):
|
471 |
-
vectorizer = TfidfVectorizer(stop_words='english', max_features=5)
|
472 |
-
tfidf_matrix = vectorizer.fit_transform([doc.text])
|
473 |
-
feature_names = vectorizer.get_feature_names_out()
|
474 |
-
return list(feature_names)
|
475 |
-
|
476 |
-
# Aseg煤rate de que todas las funciones necesarias est茅n exportadas
|
477 |
-
__all__ = [
|
478 |
-
'perform_semantic_analysis',
|
479 |
-
'identify_key_concepts',
|
480 |
-
'create_concept_graph',
|
481 |
-
'visualize_concept_graph',
|
482 |
-
'fig_to_bytes', # Faltaba esta coma
|
483 |
-
'ENTITY_LABELS',
|
484 |
-
'POS_COLORS',
|
485 |
-
'POS_TRANSLATIONS'
|
486 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|