Update modules/text_analysis/discourse_analysis.py
Browse files
modules/text_analysis/discourse_analysis.py
CHANGED
@@ -8,6 +8,10 @@ import matplotlib.pyplot as plt
|
|
8 |
import pandas as pd
|
9 |
import numpy as np
|
10 |
import logging
|
|
|
|
|
|
|
|
|
11 |
|
12 |
logger = logging.getLogger(__name__)
|
13 |
|
@@ -23,6 +27,7 @@ from .stopwords import (
|
|
23 |
get_stopwords_for_spacy
|
24 |
)
|
25 |
|
|
|
26 |
#####################
|
27 |
# Define colors for grammatical categories
|
28 |
POS_COLORS = {
|
@@ -80,6 +85,27 @@ ENTITY_LABELS = {
|
|
80 |
}
|
81 |
}
|
82 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
83 |
|
84 |
#################
|
85 |
def compare_semantic_analysis(text1, text2, nlp, lang):
|
@@ -161,9 +187,17 @@ def create_concept_table(key_concepts):
|
|
161 |
|
162 |
|
163 |
##########################################################
|
|
|
164 |
def perform_discourse_analysis(text1, text2, nlp, lang):
|
165 |
"""
|
166 |
Realiza el análisis completo del discurso
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
167 |
"""
|
168 |
try:
|
169 |
logger.info("Iniciando análisis del discurso...")
|
@@ -174,27 +208,33 @@ def perform_discourse_analysis(text1, text2, nlp, lang):
|
|
174 |
|
175 |
if not nlp:
|
176 |
raise ValueError("Modelo de lenguaje no inicializado")
|
177 |
-
|
178 |
# Realizar análisis comparativo
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
|
|
|
|
|
|
|
|
|
|
186 |
|
187 |
# Crear tablas de resultados
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
|
195 |
result = {
|
196 |
-
'graph1':
|
197 |
-
'graph2':
|
|
|
198 |
'key_concepts1': key_concepts1,
|
199 |
'key_concepts2': key_concepts2,
|
200 |
'table1': table1,
|
@@ -202,17 +242,21 @@ def perform_discourse_analysis(text1, text2, nlp, lang):
|
|
202 |
'success': True
|
203 |
}
|
204 |
|
205 |
-
logger.info("Análisis del discurso completado
|
206 |
return result
|
207 |
|
208 |
except Exception as e:
|
209 |
logger.error(f"Error en perform_discourse_analysis: {str(e)}")
|
|
|
|
|
210 |
return {
|
211 |
'success': False,
|
212 |
'error': str(e)
|
213 |
}
|
214 |
finally:
|
215 |
-
|
|
|
|
|
216 |
|
217 |
#################################################################
|
218 |
def create_concept_table(key_concepts):
|
|
|
8 |
import pandas as pd
|
9 |
import numpy as np
|
10 |
import logging
|
11 |
+
import io
|
12 |
+
import base64
|
13 |
+
from collections import Counter, defaultdict
|
14 |
+
|
15 |
|
16 |
logger = logging.getLogger(__name__)
|
17 |
|
|
|
27 |
get_stopwords_for_spacy
|
28 |
)
|
29 |
|
30 |
+
|
31 |
#####################
|
32 |
# Define colors for grammatical categories
|
33 |
POS_COLORS = {
|
|
|
85 |
}
|
86 |
}
|
87 |
|
88 |
+
#################
|
89 |
+
def fig_to_bytes(fig):
|
90 |
+
"""
|
91 |
+
Convierte una figura de matplotlib a bytes en formato PNG.
|
92 |
+
|
93 |
+
Args:
|
94 |
+
fig: Figura de matplotlib
|
95 |
+
|
96 |
+
Returns:
|
97 |
+
bytes: Representación en bytes de la figura en formato PNG
|
98 |
+
"""
|
99 |
+
try:
|
100 |
+
import io
|
101 |
+
buf = io.BytesIO()
|
102 |
+
fig.savefig(buf, format='png', dpi=100, bbox_inches='tight')
|
103 |
+
buf.seek(0)
|
104 |
+
return buf.getvalue()
|
105 |
+
except Exception as e:
|
106 |
+
logger.error(f"Error al convertir figura a bytes: {str(e)}")
|
107 |
+
return None
|
108 |
+
|
109 |
|
110 |
#################
|
111 |
def compare_semantic_analysis(text1, text2, nlp, lang):
|
|
|
187 |
|
188 |
|
189 |
##########################################################
|
190 |
+
|
191 |
def perform_discourse_analysis(text1, text2, nlp, lang):
|
192 |
"""
|
193 |
Realiza el análisis completo del discurso
|
194 |
+
Args:
|
195 |
+
text1: Primer texto a analizar
|
196 |
+
text2: Segundo texto a analizar
|
197 |
+
nlp: Modelo de spaCy cargado
|
198 |
+
lang: Código de idioma
|
199 |
+
Returns:
|
200 |
+
dict: Resultados del análisis con gráficos convertidos a bytes
|
201 |
"""
|
202 |
try:
|
203 |
logger.info("Iniciando análisis del discurso...")
|
|
|
208 |
|
209 |
if not nlp:
|
210 |
raise ValueError("Modelo de lenguaje no inicializado")
|
211 |
+
|
212 |
# Realizar análisis comparativo
|
213 |
+
fig1, fig2, key_concepts1, key_concepts2 = compare_semantic_analysis(
|
214 |
+
text1, text2, nlp, lang
|
215 |
+
)
|
216 |
+
|
217 |
+
logger.info("Análisis comparativo completado, convirtiendo figuras a bytes...")
|
218 |
+
|
219 |
+
# Convertir figuras a bytes para almacenamiento
|
220 |
+
graph1_bytes = fig_to_bytes(fig1)
|
221 |
+
graph2_bytes = fig_to_bytes(fig2)
|
222 |
+
|
223 |
+
logger.info(f"Figura 1 convertida a {len(graph1_bytes) if graph1_bytes else 0} bytes")
|
224 |
+
logger.info(f"Figura 2 convertida a {len(graph2_bytes) if graph2_bytes else 0} bytes")
|
225 |
|
226 |
# Crear tablas de resultados
|
227 |
+
table1 = create_concept_table(key_concepts1)
|
228 |
+
table2 = create_concept_table(key_concepts2)
|
229 |
+
|
230 |
+
# Cerrar figuras para liberar memoria
|
231 |
+
plt.close(fig1)
|
232 |
+
plt.close(fig2)
|
233 |
|
234 |
result = {
|
235 |
+
'graph1': graph1_bytes, # Bytes en lugar de figura
|
236 |
+
'graph2': graph2_bytes, # Bytes en lugar de figura
|
237 |
+
'combined_graph': None, # No hay gráfico combinado por ahora
|
238 |
'key_concepts1': key_concepts1,
|
239 |
'key_concepts2': key_concepts2,
|
240 |
'table1': table1,
|
|
|
242 |
'success': True
|
243 |
}
|
244 |
|
245 |
+
logger.info("Análisis del discurso completado y listo para almacenamiento")
|
246 |
return result
|
247 |
|
248 |
except Exception as e:
|
249 |
logger.error(f"Error en perform_discourse_analysis: {str(e)}")
|
250 |
+
# Asegurar limpieza de recursos
|
251 |
+
plt.close('all')
|
252 |
return {
|
253 |
'success': False,
|
254 |
'error': str(e)
|
255 |
}
|
256 |
finally:
|
257 |
+
# Asegurar limpieza en todos los casos
|
258 |
+
plt.close('all')
|
259 |
+
|
260 |
|
261 |
#################################################################
|
262 |
def create_concept_table(key_concepts):
|