Spaces:
Running
Running
Update modules/text_analysis/discourse_analysis.py
Browse files
modules/text_analysis/discourse_analysis.py
CHANGED
|
@@ -8,30 +8,31 @@ 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 |
|
|
|
|
| 14 |
from .semantic_analysis import (
|
| 15 |
create_concept_graph,
|
| 16 |
visualize_concept_graph,
|
| 17 |
identify_key_concepts
|
| 18 |
)
|
| 19 |
|
|
|
|
| 20 |
from .stopwords import (
|
| 21 |
get_custom_stopwords,
|
| 22 |
process_text,
|
| 23 |
get_stopwords_for_spacy
|
| 24 |
)
|
| 25 |
|
| 26 |
-
#####################
|
| 27 |
-
# Define colors for grammatical categories
|
| 28 |
-
POS_COLORS = {
|
| 29 |
-
'ADJ': '#FFA07A', 'ADP': '#98FB98', 'ADV': '#87CEFA', 'AUX': '#DDA0DD',
|
| 30 |
-
'CCONJ': '#F0E68C', 'DET': '#FFB6C1', 'INTJ': '#FF6347', 'NOUN': '#90EE90',
|
| 31 |
-
'NUM': '#FAFAD2', 'PART': '#D3D3D3', 'PRON': '#FFA500', 'PROPN': '#20B2AA',
|
| 32 |
-
'SCONJ': '#DEB887', 'SYM': '#7B68EE', 'VERB': '#FF69B4', 'X': '#A9A9A9',
|
| 33 |
-
}
|
| 34 |
|
|
|
|
| 35 |
POS_TRANSLATIONS = {
|
| 36 |
'es': {
|
| 37 |
'ADJ': 'Adjetivo', 'ADP': 'Preposición', 'ADV': 'Adverbio', 'AUX': 'Auxiliar',
|
|
@@ -53,6 +54,13 @@ POS_TRANSLATIONS = {
|
|
| 53 |
'NOUN': 'Nom', 'NUM': 'Nombre', 'PART': 'Particule', 'PRON': 'Pronom',
|
| 54 |
'PROPN': 'Nom Propre', 'SCONJ': 'Conjonction de Subordination', 'SYM': 'Symbole',
|
| 55 |
'VERB': 'Verbe', 'X': 'Autre',
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
}
|
| 57 |
}
|
| 58 |
|
|
@@ -77,10 +85,29 @@ ENTITY_LABELS = {
|
|
| 77 |
"Inventions": "lightgreen",
|
| 78 |
"Dates": "lightyellow",
|
| 79 |
"Concepts": "lightpink"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
}
|
| 81 |
}
|
| 82 |
|
|
|
|
| 83 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
#################
|
| 85 |
def compare_semantic_analysis(text1, text2, nlp, lang):
|
| 86 |
"""
|
|
@@ -161,9 +188,17 @@ 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...")
|
|
@@ -174,98 +209,59 @@ 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 |
-
try:
|
| 180 |
-
fig1, fig2, key_concepts1, key_concepts2 = compare_semantic_analysis(
|
| 181 |
-
text1, text2, nlp, lang
|
| 182 |
-
)
|
| 183 |
-
except Exception as e:
|
| 184 |
-
logger.error(f"Error en el análisis comparativo: {str(e)}")
|
| 185 |
-
raise
|
| 186 |
-
|
| 187 |
-
# Crear tablas de resultados
|
| 188 |
-
try:
|
| 189 |
-
table1 = create_concept_table(key_concepts1)
|
| 190 |
-
table2 = create_concept_table(key_concepts2)
|
| 191 |
-
except Exception as e:
|
| 192 |
-
logger.error(f"Error creando tablas de conceptos: {str(e)}")
|
| 193 |
-
raise
|
| 194 |
-
|
| 195 |
-
result = {
|
| 196 |
-
'graph1': fig1,
|
| 197 |
-
'graph2': fig2,
|
| 198 |
-
'key_concepts1': key_concepts1,
|
| 199 |
-
'key_concepts2': key_concepts2,
|
| 200 |
-
'table1': table1,
|
| 201 |
-
'table2': table2,
|
| 202 |
-
'success': True
|
| 203 |
-
}
|
| 204 |
|
| 205 |
-
logger.info("Análisis del discurso completado exitosamente")
|
| 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 |
-
plt.close('all') # Asegurar limpieza en todos los casos
|
| 216 |
-
|
| 217 |
-
#################################################################
|
| 218 |
-
def create_concept_table(key_concepts):
|
| 219 |
-
"""
|
| 220 |
-
Crea una tabla de conceptos clave con sus frecuencias
|
| 221 |
-
Args:
|
| 222 |
-
key_concepts: Lista de tuplas (concepto, frecuencia)
|
| 223 |
-
Returns:
|
| 224 |
-
pandas.DataFrame: Tabla formateada de conceptos
|
| 225 |
-
"""
|
| 226 |
-
try:
|
| 227 |
-
df = pd.DataFrame(key_concepts, columns=['Concepto', 'Frecuencia'])
|
| 228 |
-
df['Frecuencia'] = df['Frecuencia'].round(2)
|
| 229 |
-
return df
|
| 230 |
-
except Exception as e:
|
| 231 |
-
logger.error(f"Error en create_concept_table: {str(e)}")
|
| 232 |
-
raise
|
| 233 |
-
|
| 234 |
-
#################
|
| 235 |
-
def perform_discourse_analysis(text1, text2, nlp, lang):
|
| 236 |
-
"""
|
| 237 |
-
Realiza el análisis completo del discurso
|
| 238 |
-
Args:
|
| 239 |
-
text1: Primer texto a analizar
|
| 240 |
-
text2: Segundo texto a analizar
|
| 241 |
-
nlp: Modelo de spaCy cargado
|
| 242 |
-
lang: Código de idioma
|
| 243 |
-
Returns:
|
| 244 |
-
dict: Resultados del análisis
|
| 245 |
-
"""
|
| 246 |
-
try:
|
| 247 |
# Realizar análisis comparativo
|
| 248 |
fig1, fig2, key_concepts1, key_concepts2 = compare_semantic_analysis(
|
| 249 |
text1, text2, nlp, lang
|
| 250 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 251 |
|
| 252 |
# Crear tablas de resultados
|
| 253 |
table1 = create_concept_table(key_concepts1)
|
| 254 |
table2 = create_concept_table(key_concepts2)
|
| 255 |
|
| 256 |
-
|
| 257 |
-
|
| 258 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 259 |
'key_concepts1': key_concepts1,
|
| 260 |
'key_concepts2': key_concepts2,
|
| 261 |
'table1': table1,
|
| 262 |
'table2': table2,
|
| 263 |
'success': True
|
| 264 |
}
|
|
|
|
|
|
|
|
|
|
| 265 |
|
| 266 |
except Exception as e:
|
| 267 |
logger.error(f"Error en perform_discourse_analysis: {str(e)}")
|
|
|
|
|
|
|
| 268 |
return {
|
| 269 |
'success': False,
|
| 270 |
'error': str(e)
|
| 271 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
import logging
|
| 15 |
+
|
| 16 |
|
| 17 |
+
logging.basicConfig(level=logging.INFO)
|
| 18 |
logger = logging.getLogger(__name__)
|
| 19 |
|
| 20 |
+
|
| 21 |
from .semantic_analysis import (
|
| 22 |
create_concept_graph,
|
| 23 |
visualize_concept_graph,
|
| 24 |
identify_key_concepts
|
| 25 |
)
|
| 26 |
|
| 27 |
+
|
| 28 |
from .stopwords import (
|
| 29 |
get_custom_stopwords,
|
| 30 |
process_text,
|
| 31 |
get_stopwords_for_spacy
|
| 32 |
)
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
+
#####################
|
| 36 |
POS_TRANSLATIONS = {
|
| 37 |
'es': {
|
| 38 |
'ADJ': 'Adjetivo', 'ADP': 'Preposición', 'ADV': 'Adverbio', 'AUX': 'Auxiliar',
|
|
|
|
| 54 |
'NOUN': 'Nom', 'NUM': 'Nombre', 'PART': 'Particule', 'PRON': 'Pronom',
|
| 55 |
'PROPN': 'Nom Propre', 'SCONJ': 'Conjonction de Subordination', 'SYM': 'Symbole',
|
| 56 |
'VERB': 'Verbe', 'X': 'Autre',
|
| 57 |
+
},
|
| 58 |
+
'pt': {
|
| 59 |
+
'ADJ': 'Adjetivo', 'ADP': 'Preposição', 'ADV': 'Advérbio', 'AUX': 'Auxiliar',
|
| 60 |
+
'CCONJ': 'Conjunção Coordenativa', 'DET': 'Determinante', 'INTJ': 'Interjeição',
|
| 61 |
+
'NOUN': 'Substantivo', 'NUM': 'Número', 'PART': 'Partícula', 'PRON': 'Pronome',
|
| 62 |
+
'PROPN': 'Nome Próprio', 'SCONJ': 'Conjunção Subordinativa', 'SYM': 'Símbolo',
|
| 63 |
+
'VERB': 'Verbo', 'X': 'Outro',
|
| 64 |
}
|
| 65 |
}
|
| 66 |
|
|
|
|
| 85 |
"Inventions": "lightgreen",
|
| 86 |
"Dates": "lightyellow",
|
| 87 |
"Concepts": "lightpink"
|
| 88 |
+
},
|
| 89 |
+
'pt': {
|
| 90 |
+
"Pessoas": "lightblue",
|
| 91 |
+
"Lugares": "lightcoral",
|
| 92 |
+
"Invenções": "lightgreen",
|
| 93 |
+
"Datas": "lightyellow",
|
| 94 |
+
"Conceitos": "lightpink"
|
| 95 |
}
|
| 96 |
}
|
| 97 |
|
| 98 |
+
#################
|
| 99 |
|
| 100 |
+
def fig_to_bytes(fig, dpi=100):
|
| 101 |
+
"""Convierte una figura de matplotlib a bytes."""
|
| 102 |
+
try:
|
| 103 |
+
buf = io.BytesIO()
|
| 104 |
+
fig.savefig(buf, format='png', dpi=dpi, bbox_inches='tight') # Sin compression
|
| 105 |
+
buf.seek(0)
|
| 106 |
+
return buf.getvalue()
|
| 107 |
+
except Exception as e:
|
| 108 |
+
logger.error(f"Error en fig_to_bytes: {str(e)}")
|
| 109 |
+
return None
|
| 110 |
+
|
| 111 |
#################
|
| 112 |
def compare_semantic_analysis(text1, text2, nlp, lang):
|
| 113 |
"""
|
|
|
|
| 188 |
|
| 189 |
|
| 190 |
##########################################################
|
| 191 |
+
|
| 192 |
def perform_discourse_analysis(text1, text2, nlp, lang):
|
| 193 |
"""
|
| 194 |
Realiza el análisis completo del discurso
|
| 195 |
+
Args:
|
| 196 |
+
text1: Primer texto a analizar
|
| 197 |
+
text2: Segundo texto a analizar
|
| 198 |
+
nlp: Modelo de spaCy cargado
|
| 199 |
+
lang: Código de idioma
|
| 200 |
+
Returns:
|
| 201 |
+
dict: Resultados del análisis con gráficos convertidos a bytes
|
| 202 |
"""
|
| 203 |
try:
|
| 204 |
logger.info("Iniciando análisis del discurso...")
|
|
|
|
| 209 |
|
| 210 |
if not nlp:
|
| 211 |
raise ValueError("Modelo de lenguaje no inicializado")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 212 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 213 |
# Realizar análisis comparativo
|
| 214 |
fig1, fig2, key_concepts1, key_concepts2 = compare_semantic_analysis(
|
| 215 |
text1, text2, nlp, lang
|
| 216 |
)
|
| 217 |
+
|
| 218 |
+
logger.info("Análisis comparativo completado, convirtiendo figuras a bytes...")
|
| 219 |
+
|
| 220 |
+
# Convertir figuras a bytes para almacenamiento
|
| 221 |
+
graph1_bytes = fig_to_bytes(fig1)
|
| 222 |
+
graph2_bytes = fig_to_bytes(fig2)
|
| 223 |
+
|
| 224 |
+
logger.info(f"Figura 1 convertida a {len(graph1_bytes) if graph1_bytes else 0} bytes")
|
| 225 |
+
logger.info(f"Figura 2 convertida a {len(graph2_bytes) if graph2_bytes else 0} bytes")
|
| 226 |
+
|
| 227 |
+
# Verificar que las conversiones fueron exitosas antes de continuar
|
| 228 |
+
if not graph1_bytes or not graph2_bytes:
|
| 229 |
+
logger.error("Error al convertir figuras a bytes - obteniendo 0 bytes")
|
| 230 |
+
# Opción 1: Devolver error
|
| 231 |
+
raise ValueError("No se pudieron convertir las figuras a bytes")
|
| 232 |
|
| 233 |
# Crear tablas de resultados
|
| 234 |
table1 = create_concept_table(key_concepts1)
|
| 235 |
table2 = create_concept_table(key_concepts2)
|
| 236 |
|
| 237 |
+
# Cerrar figuras para liberar memoria
|
| 238 |
+
plt.close(fig1)
|
| 239 |
+
plt.close(fig2)
|
| 240 |
+
|
| 241 |
+
result = {
|
| 242 |
+
'graph1': graph1_bytes, # Bytes en lugar de figura
|
| 243 |
+
'graph2': graph2_bytes, # Bytes en lugar de figura
|
| 244 |
+
'combined_graph': None, # No hay gráfico combinado por ahora
|
| 245 |
'key_concepts1': key_concepts1,
|
| 246 |
'key_concepts2': key_concepts2,
|
| 247 |
'table1': table1,
|
| 248 |
'table2': table2,
|
| 249 |
'success': True
|
| 250 |
}
|
| 251 |
+
|
| 252 |
+
logger.info("Análisis del discurso completado y listo para almacenamiento")
|
| 253 |
+
return result
|
| 254 |
|
| 255 |
except Exception as e:
|
| 256 |
logger.error(f"Error en perform_discourse_analysis: {str(e)}")
|
| 257 |
+
# Asegurar limpieza de recursos
|
| 258 |
+
plt.close('all')
|
| 259 |
return {
|
| 260 |
'success': False,
|
| 261 |
'error': str(e)
|
| 262 |
+
}
|
| 263 |
+
finally:
|
| 264 |
+
# Asegurar limpieza en todos los casos
|
| 265 |
+
plt.close('all')
|
| 266 |
+
|
| 267 |
+
#################################################################
|