Merge branch #AIdeaText/test' into 'AIdeaText/test2'
Browse files- app.py +7 -0
- modules/database/database.py +61 -49
- modules/text_analysis/discourse_analysis.py +3 -2
- modules/text_analysis/semantic_analysis.py +4 -4
- modules/ui/ui.py +386 -226
- modules/ui/ui_rest1.py +1145 -0
- requirements.txt +1 -0
app.py
CHANGED
@@ -115,6 +115,13 @@ def logged_in_interface():
|
|
115 |
if 'current_lang' not in st.session_state:
|
116 |
st.session_state.current_lang = 'es' # Idioma por defecto
|
117 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
118 |
# Crear un contenedor para la barra superior
|
119 |
with st.container():
|
120 |
# Usar más columnas para un mejor control del espacio
|
|
|
115 |
if 'current_lang' not in st.session_state:
|
116 |
st.session_state.current_lang = 'es' # Idioma por defecto
|
117 |
|
118 |
+
if 'morphosyntax_result' not in st.session_state:
|
119 |
+
st.session_state.morphosyntax_result = None
|
120 |
+
if 'semantic_result' not in st.session_state:
|
121 |
+
st.session_state.semantic_result = None
|
122 |
+
if 'discourse_result' not in st.session_state:
|
123 |
+
st.session_state.discourse_result = None
|
124 |
+
|
125 |
# Crear un contenedor para la barra superior
|
126 |
with st.container():
|
127 |
# Usar más columnas para un mejor control del espacio
|
modules/database/database.py
CHANGED
@@ -7,13 +7,15 @@ from pymongo import MongoClient
|
|
7 |
import certifi
|
8 |
from datetime import datetime
|
9 |
import io
|
|
|
10 |
import base64
|
11 |
import matplotlib.pyplot as plt
|
12 |
from matplotlib.figure import Figure
|
13 |
import bcrypt
|
14 |
print(f"Bcrypt version: {bcrypt.__version__}")
|
15 |
import uuid
|
16 |
-
|
|
|
17 |
logging.basicConfig(level=logging.DEBUG)
|
18 |
logger = logging.getLogger(__name__)
|
19 |
|
@@ -254,87 +256,93 @@ def store_morphosyntax_result(username, text, repeated_words, arc_diagrams, pos_
|
|
254 |
################################################################################################################
|
255 |
def store_semantic_result(username, text, analysis_result):
|
256 |
if analysis_collection is None:
|
257 |
-
|
258 |
return False
|
259 |
-
|
260 |
try:
|
|
|
|
|
|
|
261 |
# Convertir el gráfico a imagen base64
|
262 |
-
buf =
|
263 |
analysis_result['relations_graph'].savefig(buf, format='png')
|
264 |
buf.seek(0)
|
265 |
img_str = base64.b64encode(buf.getvalue()).decode('utf-8')
|
266 |
-
|
267 |
-
# Convertir los conceptos clave a una lista de tuplas
|
268 |
-
key_concepts = [(concept, float(frequency)) for concept, frequency in analysis_result['key_concepts']]
|
269 |
-
|
270 |
analysis_document = {
|
271 |
'username': username,
|
272 |
'timestamp': datetime.utcnow(),
|
273 |
-
'text': text,
|
274 |
'key_concepts': key_concepts,
|
275 |
-
'
|
276 |
'analysis_type': 'semantic'
|
277 |
}
|
278 |
-
|
279 |
result = analysis_collection.insert_one(analysis_document)
|
280 |
-
|
281 |
-
logger.info(f"Longitud de la imagen guardada: {len(img_str)}")
|
282 |
return True
|
283 |
except Exception as e:
|
284 |
-
|
285 |
return False
|
286 |
|
287 |
###############################################################################################################
|
288 |
|
289 |
def store_discourse_analysis_result(username, text1, text2, analysis_result):
|
|
|
|
|
|
|
|
|
290 |
try:
|
291 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
292 |
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(20, 10))
|
293 |
-
|
294 |
-
# Añadir la primera imagen
|
295 |
-
ax1.imshow(analysis_result['graph1'].canvas.renderer.buffer_rgba())
|
296 |
-
ax1.set_title("Documento 1: Relaciones Conceptuales")
|
297 |
ax1.axis('off')
|
298 |
-
|
299 |
-
|
300 |
-
ax2.imshow(analysis_result['graph2'].canvas.renderer.buffer_rgba())
|
301 |
-
ax2.set_title("Documento 2: Relaciones Conceptuales")
|
302 |
ax2.axis('off')
|
303 |
-
|
304 |
-
|
305 |
-
|
306 |
-
|
307 |
-
|
308 |
-
|
309 |
-
fig.savefig(buf, format='png')
|
310 |
-
buf.seek(0)
|
311 |
-
img_str = base64.b64encode(buf.getvalue()).decode('utf-8')
|
312 |
-
|
313 |
-
# Cerrar las figuras para liberar memoria
|
314 |
plt.close(fig)
|
315 |
-
plt.close(analysis_result['graph1'])
|
316 |
-
plt.close(analysis_result['graph2'])
|
317 |
|
318 |
# Convertir los conceptos clave a listas de tuplas
|
319 |
-
key_concepts1 = [(concept, float(frequency)) for concept, frequency in analysis_result['
|
320 |
-
key_concepts2 = [(concept, float(frequency)) for concept, frequency in analysis_result['
|
321 |
|
|
|
322 |
analysis_document = {
|
323 |
'username': username,
|
324 |
'timestamp': datetime.utcnow(),
|
325 |
-
'text1': text1,
|
326 |
-
'text2': text2,
|
327 |
-
'
|
|
|
|
|
328 |
'key_concepts1': key_concepts1,
|
329 |
'key_concepts2': key_concepts2,
|
330 |
'analysis_type': 'discourse'
|
331 |
}
|
332 |
|
|
|
333 |
result = analysis_collection.insert_one(analysis_document)
|
334 |
-
|
335 |
return True
|
336 |
except Exception as e:
|
337 |
-
|
|
|
|
|
338 |
return False
|
339 |
|
340 |
###############################################################################################################
|
@@ -361,7 +369,6 @@ def get_student_data(username):
|
|
361 |
if analysis_collection is None or chat_collection is None:
|
362 |
logger.error("La conexión a MongoDB no está inicializada")
|
363 |
return None
|
364 |
-
|
365 |
formatted_data = {
|
366 |
"username": username,
|
367 |
"entries": [],
|
@@ -371,7 +378,6 @@ def get_student_data(username):
|
|
371 |
"discourse_analyses": [],
|
372 |
"chat_history": []
|
373 |
}
|
374 |
-
|
375 |
try:
|
376 |
logger.info(f"Buscando datos de análisis para el usuario: {username}")
|
377 |
cursor = analysis_collection.find({"username": username})
|
@@ -379,12 +385,12 @@ def get_student_data(username):
|
|
379 |
for entry in cursor:
|
380 |
formatted_entry = {
|
381 |
"timestamp": entry.get("timestamp", datetime.utcnow()),
|
382 |
-
"text": entry.get("text", ""),
|
383 |
"analysis_type": entry.get("analysis_type", "morphosyntax")
|
384 |
}
|
385 |
|
386 |
if formatted_entry["analysis_type"] == "morphosyntax":
|
387 |
formatted_entry.update({
|
|
|
388 |
"word_count": entry.get("word_count", {}),
|
389 |
"arc_diagrams": entry.get("arc_diagrams", [])
|
390 |
})
|
@@ -392,17 +398,24 @@ def get_student_data(username):
|
|
392 |
formatted_data["word_count"][category] = formatted_data["word_count"].get(category, 0) + count
|
393 |
|
394 |
elif formatted_entry["analysis_type"] == "semantic":
|
395 |
-
formatted_entry
|
|
|
|
|
|
|
396 |
formatted_data["semantic_analyses"].append(formatted_entry)
|
397 |
|
398 |
elif formatted_entry["analysis_type"] == "discourse":
|
399 |
formatted_entry.update({
|
400 |
"text1": entry.get("text1", ""),
|
401 |
"text2": entry.get("text2", ""),
|
|
|
|
|
|
|
|
|
402 |
"combined_graph": entry.get("combined_graph", "")
|
403 |
})
|
404 |
formatted_data["discourse_analyses"].append(formatted_entry)
|
405 |
-
|
406 |
formatted_data["entries"].append(formatted_entry)
|
407 |
|
408 |
formatted_data["entries_count"] = len(formatted_data["entries"])
|
@@ -428,6 +441,5 @@ def get_student_data(username):
|
|
428 |
|
429 |
except Exception as e:
|
430 |
logger.error(f"Error al obtener historial de chat del estudiante {username}: {str(e)}")
|
431 |
-
|
432 |
logger.info(f"Datos formateados para {username}: {formatted_data}")
|
433 |
return formatted_data
|
|
|
7 |
import certifi
|
8 |
from datetime import datetime
|
9 |
import io
|
10 |
+
from io import BytesIO
|
11 |
import base64
|
12 |
import matplotlib.pyplot as plt
|
13 |
from matplotlib.figure import Figure
|
14 |
import bcrypt
|
15 |
print(f"Bcrypt version: {bcrypt.__version__}")
|
16 |
import uuid
|
17 |
+
import plotly.graph_objects as go # Para manejar el diagrama de Sankey
|
18 |
+
import numpy as np # Puede ser necesario para algunas operaciones
|
19 |
logging.basicConfig(level=logging.DEBUG)
|
20 |
logger = logging.getLogger(__name__)
|
21 |
|
|
|
256 |
################################################################################################################
|
257 |
def store_semantic_result(username, text, analysis_result):
|
258 |
if analysis_collection is None:
|
259 |
+
print("La conexión a MongoDB no está inicializada")
|
260 |
return False
|
|
|
261 |
try:
|
262 |
+
# Convertir los conceptos clave a una lista de tuplas
|
263 |
+
key_concepts = [(concept, float(frequency)) for concept, frequency in analysis_result['key_concepts']]
|
264 |
+
|
265 |
# Convertir el gráfico a imagen base64
|
266 |
+
buf = BytesIO()
|
267 |
analysis_result['relations_graph'].savefig(buf, format='png')
|
268 |
buf.seek(0)
|
269 |
img_str = base64.b64encode(buf.getvalue()).decode('utf-8')
|
270 |
+
|
|
|
|
|
|
|
271 |
analysis_document = {
|
272 |
'username': username,
|
273 |
'timestamp': datetime.utcnow(),
|
|
|
274 |
'key_concepts': key_concepts,
|
275 |
+
'graph': img_str,
|
276 |
'analysis_type': 'semantic'
|
277 |
}
|
278 |
+
|
279 |
result = analysis_collection.insert_one(analysis_document)
|
280 |
+
print(f"Análisis semántico guardado con ID: {result.inserted_id} para el usuario: {username}")
|
|
|
281 |
return True
|
282 |
except Exception as e:
|
283 |
+
print(f"Error al guardar el análisis semántico para el usuario {username}: {str(e)}")
|
284 |
return False
|
285 |
|
286 |
###############################################################################################################
|
287 |
|
288 |
def store_discourse_analysis_result(username, text1, text2, analysis_result):
|
289 |
+
if analysis_collection is None:
|
290 |
+
print("La conexión a MongoDB no está inicializada")
|
291 |
+
return False
|
292 |
+
|
293 |
try:
|
294 |
+
# Convertir los grafos individuales a imágenes base64
|
295 |
+
buf1 = BytesIO()
|
296 |
+
analysis_result['graph1'].savefig(buf1, format='png')
|
297 |
+
buf1.seek(0)
|
298 |
+
img_str1 = base64.b64encode(buf1.getvalue()).decode('utf-8')
|
299 |
+
|
300 |
+
buf2 = BytesIO()
|
301 |
+
analysis_result['graph2'].savefig(buf2, format='png')
|
302 |
+
buf2.seek(0)
|
303 |
+
img_str2 = base64.b64encode(buf2.getvalue()).decode('utf-8')
|
304 |
+
|
305 |
+
# Crear una imagen combinada
|
306 |
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(20, 10))
|
307 |
+
ax1.imshow(plt.imread(BytesIO(base64.b64decode(img_str1))))
|
|
|
|
|
|
|
308 |
ax1.axis('off')
|
309 |
+
ax1.set_title("Documento 1: Relaciones Conceptuales")
|
310 |
+
ax2.imshow(plt.imread(BytesIO(base64.b64decode(img_str2))))
|
|
|
|
|
311 |
ax2.axis('off')
|
312 |
+
ax2.set_title("Documento 2: Relaciones Conceptuales")
|
313 |
+
|
314 |
+
buf_combined = BytesIO()
|
315 |
+
fig.savefig(buf_combined, format='png')
|
316 |
+
buf_combined.seek(0)
|
317 |
+
img_str_combined = base64.b64encode(buf_combined.getvalue()).decode('utf-8')
|
|
|
|
|
|
|
|
|
|
|
318 |
plt.close(fig)
|
|
|
|
|
319 |
|
320 |
# Convertir los conceptos clave a listas de tuplas
|
321 |
+
key_concepts1 = [(concept, float(frequency)) for concept, frequency in analysis_result['key_concepts1']]
|
322 |
+
key_concepts2 = [(concept, float(frequency)) for concept, frequency in analysis_result['key_concepts2']]
|
323 |
|
324 |
+
# Crear el documento para guardar
|
325 |
analysis_document = {
|
326 |
'username': username,
|
327 |
'timestamp': datetime.utcnow(),
|
328 |
+
#'text1': text1,
|
329 |
+
#'text2': text2,
|
330 |
+
'graph1': img_str1,
|
331 |
+
'graph2': img_str2,
|
332 |
+
'combined_graph': img_str_combined,
|
333 |
'key_concepts1': key_concepts1,
|
334 |
'key_concepts2': key_concepts2,
|
335 |
'analysis_type': 'discourse'
|
336 |
}
|
337 |
|
338 |
+
# Insertar el documento en la base de datos
|
339 |
result = analysis_collection.insert_one(analysis_document)
|
340 |
+
print(f"Análisis discursivo guardado con ID: {result.inserted_id} para el usuario: {username}")
|
341 |
return True
|
342 |
except Exception as e:
|
343 |
+
print(f"Error al guardar el análisis discursivo para el usuario {username}: {str(e)}")
|
344 |
+
print(f"Tipo de excepción: {type(e).__name__}")
|
345 |
+
print(f"Detalles de la excepción: {e.args}")
|
346 |
return False
|
347 |
|
348 |
###############################################################################################################
|
|
|
369 |
if analysis_collection is None or chat_collection is None:
|
370 |
logger.error("La conexión a MongoDB no está inicializada")
|
371 |
return None
|
|
|
372 |
formatted_data = {
|
373 |
"username": username,
|
374 |
"entries": [],
|
|
|
378 |
"discourse_analyses": [],
|
379 |
"chat_history": []
|
380 |
}
|
|
|
381 |
try:
|
382 |
logger.info(f"Buscando datos de análisis para el usuario: {username}")
|
383 |
cursor = analysis_collection.find({"username": username})
|
|
|
385 |
for entry in cursor:
|
386 |
formatted_entry = {
|
387 |
"timestamp": entry.get("timestamp", datetime.utcnow()),
|
|
|
388 |
"analysis_type": entry.get("analysis_type", "morphosyntax")
|
389 |
}
|
390 |
|
391 |
if formatted_entry["analysis_type"] == "morphosyntax":
|
392 |
formatted_entry.update({
|
393 |
+
"text": entry.get("text", ""),
|
394 |
"word_count": entry.get("word_count", {}),
|
395 |
"arc_diagrams": entry.get("arc_diagrams", [])
|
396 |
})
|
|
|
398 |
formatted_data["word_count"][category] = formatted_data["word_count"].get(category, 0) + count
|
399 |
|
400 |
elif formatted_entry["analysis_type"] == "semantic":
|
401 |
+
formatted_entry.update({
|
402 |
+
"key_concepts": entry.get("key_concepts", []),
|
403 |
+
"graph": entry.get("graph", "")
|
404 |
+
})
|
405 |
formatted_data["semantic_analyses"].append(formatted_entry)
|
406 |
|
407 |
elif formatted_entry["analysis_type"] == "discourse":
|
408 |
formatted_entry.update({
|
409 |
"text1": entry.get("text1", ""),
|
410 |
"text2": entry.get("text2", ""),
|
411 |
+
"key_concepts1": entry.get("key_concepts1", []),
|
412 |
+
"key_concepts2": entry.get("key_concepts2", []),
|
413 |
+
"graph1": entry.get("graph1", ""),
|
414 |
+
"graph2": entry.get("graph2", ""),
|
415 |
"combined_graph": entry.get("combined_graph", "")
|
416 |
})
|
417 |
formatted_data["discourse_analyses"].append(formatted_entry)
|
418 |
+
|
419 |
formatted_data["entries"].append(formatted_entry)
|
420 |
|
421 |
formatted_data["entries_count"] = len(formatted_data["entries"])
|
|
|
441 |
|
442 |
except Exception as e:
|
443 |
logger.error(f"Error al obtener historial de chat del estudiante {username}: {str(e)}")
|
|
|
444 |
logger.info(f"Datos formateados para {username}: {formatted_data}")
|
445 |
return formatted_data
|
modules/text_analysis/discourse_analysis.py
CHANGED
@@ -3,6 +3,7 @@ import spacy
|
|
3 |
import networkx as nx
|
4 |
import matplotlib.pyplot as plt
|
5 |
import pandas as pd
|
|
|
6 |
from .semantic_analysis import (
|
7 |
create_concept_graph,
|
8 |
visualize_concept_graph,
|
@@ -49,8 +50,8 @@ def perform_discourse_analysis(text1, text2, nlp, lang):
|
|
49 |
return {
|
50 |
'graph1': graph1,
|
51 |
'graph2': graph2,
|
52 |
-
'
|
53 |
-
'
|
54 |
}
|
55 |
|
56 |
def display_discourse_analysis_results(analysis_result, lang_code):
|
|
|
3 |
import networkx as nx
|
4 |
import matplotlib.pyplot as plt
|
5 |
import pandas as pd
|
6 |
+
import numpy as np
|
7 |
from .semantic_analysis import (
|
8 |
create_concept_graph,
|
9 |
visualize_concept_graph,
|
|
|
50 |
return {
|
51 |
'graph1': graph1,
|
52 |
'graph2': graph2,
|
53 |
+
'key_concepts1': key_concepts1,
|
54 |
+
'key_concepts2': key_concepts2
|
55 |
}
|
56 |
|
57 |
def display_discourse_analysis_results(analysis_result, lang_code):
|
modules/text_analysis/semantic_analysis.py
CHANGED
@@ -63,10 +63,10 @@ ENTITY_LABELS = {
|
|
63 |
}
|
64 |
}
|
65 |
|
66 |
-
def identify_key_concepts(doc
|
67 |
-
|
68 |
-
|
69 |
-
return
|
70 |
|
71 |
def create_concept_graph(doc, key_concepts):
|
72 |
G = nx.Graph()
|
|
|
63 |
}
|
64 |
}
|
65 |
|
66 |
+
def identify_key_concepts(doc):
|
67 |
+
word_freq = Counter([token.lemma_.lower() for token in doc if token.pos_ in ['NOUN', 'VERB'] and not token.is_stop])
|
68 |
+
key_concepts = word_freq.most_common(10) # Top 10 conceptos clave
|
69 |
+
return [(concept, float(freq)) for concept, freq in key_concepts] # Asegurarse de que las frecuencias sean float
|
70 |
|
71 |
def create_concept_graph(doc, key_concepts):
|
72 |
G = nx.Graph()
|
modules/ui/ui.py
CHANGED
@@ -5,12 +5,15 @@ import io
|
|
5 |
from io import BytesIO
|
6 |
import base64
|
7 |
import matplotlib.pyplot as plt
|
|
|
8 |
import pandas as pd
|
|
|
9 |
import time
|
10 |
from datetime import datetime
|
11 |
from streamlit_player import st_player # Necesitarás instalar esta librería: pip install streamlit-player
|
12 |
from spacy import displacy
|
13 |
import logging
|
|
|
14 |
|
15 |
######################################################
|
16 |
# Configuración del logger
|
@@ -207,7 +210,7 @@ def display_videos_and_info():
|
|
207 |
st.header("Videos: pitch, demos, entrevistas, otros")
|
208 |
|
209 |
videos = {
|
210 |
-
"
|
211 |
"Presentación fundación Ser Maaestro": "https://www.youtube.com/watch?v=imc4TI1q164",
|
212 |
"Pitch IFE Explora": "https://www.youtube.com/watch?v=Fqi4Di_Rj_s",
|
213 |
"Entrevista Dr. Guillermo Ruíz": "https://www.youtube.com/watch?v=_ch8cRja3oc",
|
@@ -364,59 +367,58 @@ def display_student_progress(username, lang_code='es'):
|
|
364 |
##########################################################
|
365 |
with st.expander("Histórico de Análisis Semánticos"):
|
366 |
semantic_entries = [entry for entry in student_data['entries'] if entry['analysis_type'] == 'semantic']
|
367 |
-
st.write(f"Número total de entradas semánticas: {len(semantic_entries)}")
|
368 |
for entry in semantic_entries:
|
369 |
st.subheader(f"Análisis del {entry['timestamp']}")
|
370 |
-
st.write(f"Archivo analizado: {entry.get('filename', 'Nombre no disponible')}")
|
371 |
-
st.write(f"Claves disponibles en esta entrada: {', '.join(entry.keys())}")
|
372 |
|
373 |
-
#
|
374 |
-
if '
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
375 |
try:
|
376 |
-
|
377 |
-
st.image(
|
378 |
except Exception as e:
|
379 |
-
st.error(f"No se pudo mostrar
|
380 |
-
st.write("Datos de la imagen (para depuración):")
|
381 |
-
st.write(entry['network_diagram'][:100] + "...")
|
382 |
-
else:
|
383 |
-
logger.warning(f"No se encontró 'relations_graph' en la entrada: {entry.keys()}")
|
384 |
-
st.write("No se encontró el gráfico para este análisis.")
|
385 |
|
386 |
##########################################################
|
387 |
with st.expander("Histórico de Análisis Discursivos"):
|
388 |
discourse_entries = [entry for entry in student_data['entries'] if entry['analysis_type'] == 'discourse']
|
389 |
for entry in discourse_entries:
|
390 |
st.subheader(f"Análisis del {entry['timestamp']}")
|
391 |
-
|
392 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
393 |
|
394 |
try:
|
395 |
-
|
396 |
-
if 'graph1' in entry and 'graph2' in entry:
|
397 |
-
img1 = Image.open(BytesIO(base64.b64decode(entry['graph1'])))
|
398 |
-
img2 = Image.open(BytesIO(base64.b64decode(entry['graph2'])))
|
399 |
-
|
400 |
-
# Crear una nueva imagen combinada
|
401 |
-
total_width = img1.width + img2.width
|
402 |
-
max_height = max(img1.height, img2.height)
|
403 |
-
combined_img = Image.new('RGB', (total_width, max_height))
|
404 |
-
|
405 |
-
# Pegar las dos imágenes lado a lado
|
406 |
-
combined_img.paste(img1, (0, 0))
|
407 |
-
combined_img.paste(img2, (img1.width, 0))
|
408 |
-
|
409 |
-
# Convertir la imagen combinada a bytes
|
410 |
-
buffered = BytesIO()
|
411 |
-
combined_img.save(buffered, format="PNG")
|
412 |
-
img_str = base64.b64encode(buffered.getvalue()).decode()
|
413 |
-
|
414 |
-
# Mostrar la imagen combinada
|
415 |
-
st.image(f"data:image/png;base64,{img_str}")
|
416 |
-
elif 'combined_graph' in entry:
|
417 |
-
# Si ya existe una imagen combinada, mostrarla directamente
|
418 |
img_bytes = base64.b64decode(entry['combined_graph'])
|
419 |
st.image(img_bytes)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
420 |
else:
|
421 |
st.write("No se encontraron gráficos para este análisis.")
|
422 |
except Exception as e:
|
@@ -428,7 +430,6 @@ def display_student_progress(username, lang_code='es'):
|
|
428 |
st.write("Graph 2:", entry['graph2'][:100] + "...")
|
429 |
if 'combined_graph' in entry:
|
430 |
st.write("Combined Graph:", entry['combined_graph'][:100] + "...")
|
431 |
-
|
432 |
|
433 |
##########################################################
|
434 |
with st.expander("Histórico de Conversaciones con el ChatBot"):
|
@@ -467,6 +468,8 @@ def display_morphosyntax_analysis_interface(nlp_models, lang_code):
|
|
467 |
'success_message': "Análisis guardado correctamente.",
|
468 |
'error_message': "Hubo un problema al guardar el análisis. Por favor, inténtelo de nuevo.",
|
469 |
'warning_message': "Por favor, ingrese un texto para analizar.",
|
|
|
|
|
470 |
'pos_analysis': "Análisis de categorías gramaticales",
|
471 |
'morphological_analysis': "Análisis morfológico",
|
472 |
'sentence_structure': "Estructura de oraciones",
|
@@ -501,6 +504,8 @@ def display_morphosyntax_analysis_interface(nlp_models, lang_code):
|
|
501 |
'success_message': "Analysis saved successfully.",
|
502 |
'error_message': "There was a problem saving the analysis. Please try again.",
|
503 |
'warning_message': "Please enter a text to analyze.",
|
|
|
|
|
504 |
'pos_analysis': "Part of Speech Analysis",
|
505 |
'morphological_analysis': "Morphological Analysis",
|
506 |
'sentence_structure': "Sentence Structure",
|
@@ -535,6 +540,8 @@ def display_morphosyntax_analysis_interface(nlp_models, lang_code):
|
|
535 |
'success_message': "Analyse enregistrée avec succès.",
|
536 |
'error_message': "Un problème est survenu lors de l'enregistrement de l'analyse. Veuillez réessayer.",
|
537 |
'warning_message': "Veuillez entrer un texte à analyser.",
|
|
|
|
|
538 |
'pos_analysis': "Analyse des parties du discours",
|
539 |
'morphological_analysis': "Analyse morphologique",
|
540 |
'sentence_structure': "Structure des phrases",
|
@@ -580,181 +587,202 @@ def display_morphosyntax_analysis_interface(nlp_models, lang_code):
|
|
580 |
# Análisis morfosintáctico avanzado
|
581 |
advanced_analysis = perform_advanced_morphosyntactic_analysis(current_input, nlp_models[lang_code])
|
582 |
|
583 |
-
#
|
584 |
-
st.
|
585 |
-
|
586 |
-
|
587 |
-
|
588 |
-
|
589 |
-
|
590 |
-
st.
|
591 |
-
|
592 |
-
#
|
593 |
-
|
594 |
-
|
595 |
-
|
596 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
597 |
|
598 |
-
#
|
599 |
-
|
600 |
-
for i, sent_analysis in enumerate(advanced_analysis['sentence_structure']):
|
601 |
-
sentence_str = (
|
602 |
-
f"**{t['sentence']} {i+1}** "
|
603 |
-
f"{t['root']}: {sent_analysis['root']} ({sent_analysis['root_pos']}) -- "
|
604 |
-
f"{t['subjects']}: {', '.join(sent_analysis['subjects'])} -- "
|
605 |
-
f"{t['objects']}: {', '.join(sent_analysis['objects'])} -- "
|
606 |
-
f"{t['verbs']}: {', '.join(sent_analysis['verbs'])}"
|
607 |
-
)
|
608 |
-
st.markdown(sentence_str)
|
609 |
-
|
610 |
-
# Mostrar análisis de categorías gramaticales # Mostrar análisis morfológico
|
611 |
-
# Mostrar análisis de categorías gramaticales # Mostrar análisis morfológico
|
612 |
-
col1, col2 = st.columns(2)
|
613 |
|
614 |
-
|
615 |
-
|
616 |
-
|
617 |
-
|
618 |
-
|
619 |
-
|
620 |
-
|
621 |
-
# Renombrar las columnas para mayor claridad
|
622 |
-
pos_df = pos_df.rename(columns={
|
623 |
-
'pos': t['grammatical_category'],
|
624 |
-
'count': t['count'],
|
625 |
-
'percentage': t['percentage'],
|
626 |
-
'examples': t['examples']
|
627 |
-
})
|
628 |
-
|
629 |
-
# Mostrar el dataframe
|
630 |
-
st.dataframe(pos_df)
|
631 |
|
632 |
-
|
633 |
-
|
634 |
-
|
635 |
-
|
636 |
-
|
637 |
-
|
638 |
-
|
639 |
-
|
640 |
-
|
641 |
-
|
642 |
-
|
643 |
-
|
644 |
-
|
645 |
-
|
646 |
-
|
647 |
-
|
648 |
-
|
649 |
-
|
650 |
-
|
651 |
-
|
652 |
-
|
653 |
-
|
654 |
-
|
655 |
-
|
656 |
-
|
657 |
-
|
658 |
-
|
659 |
-
|
660 |
-
|
661 |
-
|
662 |
-
|
663 |
-
|
664 |
-
|
665 |
-
|
666 |
-
|
667 |
-
|
668 |
-
|
669 |
-
|
670 |
-
|
671 |
-
|
672 |
-
|
673 |
-
|
674 |
-
|
675 |
-
|
676 |
-
|
677 |
-
|
678 |
-
|
679 |
-
|
680 |
-
|
681 |
-
|
682 |
-
|
683 |
-
|
684 |
-
|
685 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
686 |
}
|
687 |
-
|
688 |
-
|
689 |
-
|
690 |
-
|
691 |
-
morph_translations = {
|
692 |
-
'es': {
|
693 |
-
'Gender': 'Género', 'Number': 'Número', 'Case': 'Caso', 'Definite': 'Definido',
|
694 |
-
'PronType': 'Tipo de Pronombre', 'Person': 'Persona', 'Mood': 'Modo',
|
695 |
-
'Tense': 'Tiempo', 'VerbForm': 'Forma Verbal', 'Voice': 'Voz',
|
696 |
-
'Fem': 'Femenino', 'Masc': 'Masculino', 'Sing': 'Singular', 'Plur': 'Plural',
|
697 |
-
'Ind': 'Indicativo', 'Sub': 'Subjuntivo', 'Imp': 'Imperativo', 'Inf': 'Infinitivo',
|
698 |
-
'Part': 'Participio', 'Ger': 'Gerundio', 'Pres': 'Presente', 'Past': 'Pasado',
|
699 |
-
'Fut': 'Futuro', 'Perf': 'Perfecto', 'Imp': 'Imperfecto'
|
700 |
-
},
|
701 |
-
'en': {
|
702 |
-
'Gender': 'Gender', 'Number': 'Number', 'Case': 'Case', 'Definite': 'Definite', 'PronType': 'Pronoun Type', 'Person': 'Person',
|
703 |
-
'Mood': 'Mood', 'Tense': 'Tense', 'VerbForm': 'Verb Form', 'Voice': 'Voice',
|
704 |
-
'Fem': 'Feminine', 'Masc': 'Masculine', 'Sing': 'Singular', 'Plur': 'Plural', 'Ind': 'Indicative',
|
705 |
-
'Sub': 'Subjunctive', 'Imp': 'Imperative', 'Inf': 'Infinitive', 'Part': 'Participle',
|
706 |
-
'Ger': 'Gerund', 'Pres': 'Present', 'Past': 'Past', 'Fut': 'Future', 'Perf': 'Perfect', 'Imp': 'Imperfect'
|
707 |
-
},
|
708 |
-
'fr': {
|
709 |
-
'Gender': 'Genre', 'Number': 'Nombre', 'Case': 'Cas', 'Definite': 'Défini', 'PronType': 'Type de Pronom',
|
710 |
-
'Person': 'Personne', 'Mood': 'Mode', 'Tense': 'Temps', 'VerbForm': 'Forme Verbale', 'Voice': 'Voix',
|
711 |
-
'Fem': 'Féminin', 'Masc': 'Masculin', 'Sing': 'Singulier', 'Plur': 'Pluriel', 'Ind': 'Indicatif',
|
712 |
-
'Sub': 'Subjonctif', 'Imp': 'Impératif', 'Inf': 'Infinitif', 'Part': 'Participe',
|
713 |
-
'Ger': 'Gérondif', 'Pres': 'Présent', 'Past': 'Passé', 'Fut': 'Futur', 'Perf': 'Parfait', 'Imp': 'Imparfait'
|
714 |
-
}
|
715 |
-
}
|
716 |
-
for key, value in morph_translations[lang_code].items():
|
717 |
-
morph_string = morph_string.replace(key, value)
|
718 |
-
return morph_string
|
719 |
-
|
720 |
-
morph_df[t['morphology']] = morph_df[t['morphology']].apply(lambda x: translate_morph(x, lang_code))
|
721 |
-
|
722 |
-
# Seleccionar y ordenar las columnas a mostrar
|
723 |
-
columns_to_display = [t['word'], t['lemma'], t['grammatical_category'], t['dependency'], t['morphology']]
|
724 |
-
columns_to_display = [col for col in columns_to_display if col in morph_df.columns]
|
725 |
-
|
726 |
-
# Mostrar el DataFrame
|
727 |
-
st.dataframe(morph_df[columns_to_display])
|
728 |
-
|
729 |
-
# Mostrar diagramas de arco (código existente)
|
730 |
-
with st.expander(t['arc_diagram'], expanded=True):
|
731 |
-
sentences = list(doc.sents)
|
732 |
-
arc_diagrams = []
|
733 |
-
for i, sent in enumerate(sentences):
|
734 |
-
st.subheader(f"{t['sentence']} {i+1}")
|
735 |
-
html = displacy.render(sent, style="dep", options={"distance": 100})
|
736 |
-
html = html.replace('height="375"', 'height="200"')
|
737 |
-
html = re.sub(r'<svg[^>]*>', lambda m: m.group(0).replace('height="450"', 'height="300"'), html)
|
738 |
-
html = re.sub(r'<g [^>]*transform="translate\((\d+),(\d+)\)"', lambda m: f'<g transform="translate({m.group(1)},50)"', html)
|
739 |
-
st.write(html, unsafe_allow_html=True)
|
740 |
-
arc_diagrams.append(html)
|
741 |
|
742 |
-
|
743 |
-
|
744 |
-
|
745 |
-
|
746 |
-
|
747 |
-
|
748 |
-
|
749 |
-
|
750 |
-
|
751 |
-
|
752 |
-
|
753 |
-
|
754 |
-
|
755 |
-
|
756 |
-
|
757 |
-
|
|
|
|
|
|
|
|
|
|
|
758 |
|
759 |
###############################################################################################################
|
760 |
def display_semantic_analysis_interface(nlp_models, lang_code):
|
@@ -770,7 +798,9 @@ def display_semantic_analysis_interface(nlp_models, lang_code):
|
|
770 |
'key_concepts': "Conceptos Clave",
|
771 |
'success_message': "Análisis semántico guardado correctamente.",
|
772 |
'error_message': "Hubo un problema al guardar el análisis semántico. Por favor, inténtelo de nuevo.",
|
773 |
-
'warning_message': "Por favor, ingrese un texto o cargue un archivo para analizar."
|
|
|
|
|
774 |
},
|
775 |
'en': {
|
776 |
'title': "AIdeaText - Semantic Analysis",
|
@@ -783,7 +813,9 @@ def display_semantic_analysis_interface(nlp_models, lang_code):
|
|
783 |
'key_concepts': "Key Concepts",
|
784 |
'success_message': "Semantic analysis saved successfully.",
|
785 |
'error_message': "There was a problem saving the semantic analysis. Please try again.",
|
786 |
-
'warning_message': "Please enter a text or upload a file to analyze."
|
|
|
|
|
787 |
},
|
788 |
'fr': {
|
789 |
'title': "AIdeaText - Analyse sémantique",
|
@@ -796,7 +828,9 @@ def display_semantic_analysis_interface(nlp_models, lang_code):
|
|
796 |
'key_concepts': "Concepts Clés",
|
797 |
'success_message': "Analyse sémantique enregistrée avec succès.",
|
798 |
'error_message': "Un problème est survenu lors de l'enregistrement de l'analyse sémantique. Veuillez réessayer.",
|
799 |
-
'warning_message': "Veuillez entrer un texte ou télécharger un fichier à analyser."
|
|
|
|
|
800 |
}
|
801 |
}
|
802 |
|
@@ -824,14 +858,11 @@ def display_semantic_analysis_interface(nlp_models, lang_code):
|
|
824 |
# Realizar el análisis
|
825 |
analysis_result = perform_semantic_analysis(text_content, nlp_models[lang_code], lang_code)
|
826 |
|
827 |
-
#
|
828 |
-
|
829 |
-
concept_text = " | ".join([f"{concept} ({frequency:.2f})" for concept, frequency in analysis_result['key_concepts']])
|
830 |
-
st.write(concept_text)
|
831 |
|
832 |
-
# Mostrar
|
833 |
-
|
834 |
-
st.pyplot(analysis_result['relations_graph'])
|
835 |
|
836 |
# Guardar el resultado del análisis
|
837 |
if store_semantic_result(st.session_state.username, text_content, analysis_result):
|
@@ -840,6 +871,29 @@ def display_semantic_analysis_interface(nlp_models, lang_code):
|
|
840 |
st.error(t['error_message'])
|
841 |
else:
|
842 |
st.warning(t['warning_message'])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
843 |
##################################################################################################
|
844 |
def display_discourse_analysis_interface(nlp_models, lang_code):
|
845 |
translations = {
|
@@ -851,7 +905,13 @@ def display_discourse_analysis_interface(nlp_models, lang_code):
|
|
851 |
'comparison': "Comparación de Relaciones Semánticas",
|
852 |
'success_message': "Análisis del discurso guardado correctamente.",
|
853 |
'error_message': "Hubo un problema al guardar el análisis del discurso. Por favor, inténtelo de nuevo.",
|
854 |
-
'warning_message': "Por favor, cargue ambos archivos para analizar."
|
|
|
|
|
|
|
|
|
|
|
|
|
855 |
},
|
856 |
'en': {
|
857 |
'title': "AIdeaText - Discourse Analysis",
|
@@ -861,7 +921,13 @@ def display_discourse_analysis_interface(nlp_models, lang_code):
|
|
861 |
'comparison': "Comparison of Semantic Relations",
|
862 |
'success_message': "Discourse analysis saved successfully.",
|
863 |
'error_message': "There was a problem saving the discourse analysis. Please try again.",
|
864 |
-
'warning_message': "Please upload both files to analyze."
|
|
|
|
|
|
|
|
|
|
|
|
|
865 |
},
|
866 |
'fr': {
|
867 |
'title': "AIdeaText - Analyse du discours",
|
@@ -871,7 +937,13 @@ def display_discourse_analysis_interface(nlp_models, lang_code):
|
|
871 |
'comparison': "Comparaison des Relations Sémantiques",
|
872 |
'success_message': "Analyse du discours enregistrée avec succès.",
|
873 |
'error_message': "Un problème est survenu lors de l'enregistrement de l'analyse du discours. Veuillez réessayer.",
|
874 |
-
'warning_message': "Veuillez télécharger les deux fichiers à analyser."
|
|
|
|
|
|
|
|
|
|
|
|
|
875 |
}
|
876 |
}
|
877 |
|
@@ -879,10 +951,8 @@ def display_discourse_analysis_interface(nlp_models, lang_code):
|
|
879 |
st.header(t['title'])
|
880 |
|
881 |
col1, col2 = st.columns(2)
|
882 |
-
|
883 |
with col1:
|
884 |
uploaded_file1 = st.file_uploader(t['file_uploader1'], type=['txt'])
|
885 |
-
|
886 |
with col2:
|
887 |
uploaded_file2 = st.file_uploader(t['file_uploader2'], type=['txt'])
|
888 |
|
@@ -894,8 +964,11 @@ def display_discourse_analysis_interface(nlp_models, lang_code):
|
|
894 |
# Realizar el análisis
|
895 |
analysis_result = perform_discourse_analysis(text_content1, text_content2, nlp_models[lang_code], lang_code)
|
896 |
|
|
|
|
|
|
|
897 |
# Mostrar los resultados del análisis
|
898 |
-
|
899 |
|
900 |
# Guardar el resultado del análisis
|
901 |
if store_discourse_analysis_result(st.session_state.username, text_content1, text_content2, analysis_result):
|
@@ -904,6 +977,93 @@ def display_discourse_analysis_interface(nlp_models, lang_code):
|
|
904 |
st.error(t['error_message'])
|
905 |
else:
|
906 |
st.warning(t['warning_message'])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
907 |
|
908 |
##################################################################################################
|
909 |
#def display_saved_discourse_analysis(analysis_data):
|
|
|
5 |
from io import BytesIO
|
6 |
import base64
|
7 |
import matplotlib.pyplot as plt
|
8 |
+
import plotly.graph_objects as go
|
9 |
import pandas as pd
|
10 |
+
import numpy as np
|
11 |
import time
|
12 |
from datetime import datetime
|
13 |
from streamlit_player import st_player # Necesitarás instalar esta librería: pip install streamlit-player
|
14 |
from spacy import displacy
|
15 |
import logging
|
16 |
+
import random
|
17 |
|
18 |
######################################################
|
19 |
# Configuración del logger
|
|
|
210 |
st.header("Videos: pitch, demos, entrevistas, otros")
|
211 |
|
212 |
videos = {
|
213 |
+
"Presentación en PyCon Colombia, Medellín, 2024": "https://www.youtube.com/watch?v=Jn545-IKx5Q",
|
214 |
"Presentación fundación Ser Maaestro": "https://www.youtube.com/watch?v=imc4TI1q164",
|
215 |
"Pitch IFE Explora": "https://www.youtube.com/watch?v=Fqi4Di_Rj_s",
|
216 |
"Entrevista Dr. Guillermo Ruíz": "https://www.youtube.com/watch?v=_ch8cRja3oc",
|
|
|
367 |
##########################################################
|
368 |
with st.expander("Histórico de Análisis Semánticos"):
|
369 |
semantic_entries = [entry for entry in student_data['entries'] if entry['analysis_type'] == 'semantic']
|
|
|
370 |
for entry in semantic_entries:
|
371 |
st.subheader(f"Análisis del {entry['timestamp']}")
|
|
|
|
|
372 |
|
373 |
+
# Mostrar conceptos clave
|
374 |
+
if 'key_concepts' in entry:
|
375 |
+
st.write("Conceptos clave:")
|
376 |
+
concepts_str = " | ".join([f"{concept} ({frequency:.2f})" for concept, frequency in entry['key_concepts']])
|
377 |
+
#st.write("Conceptos clave:")
|
378 |
+
#st.write(concepts_str)
|
379 |
+
st.markdown(f"<div style='background-color: #f0f2f6; padding: 10px; border-radius: 5px;'>{concepts_str}</div>", unsafe_allow_html=True)
|
380 |
+
|
381 |
+
# Mostrar gráfico
|
382 |
+
if 'graph' in entry:
|
383 |
try:
|
384 |
+
img_bytes = base64.b64decode(entry['graph'])
|
385 |
+
st.image(img_bytes, caption="Gráfico de relaciones conceptuales")
|
386 |
except Exception as e:
|
387 |
+
st.error(f"No se pudo mostrar el gráfico: {str(e)}")
|
|
|
|
|
|
|
|
|
|
|
388 |
|
389 |
##########################################################
|
390 |
with st.expander("Histórico de Análisis Discursivos"):
|
391 |
discourse_entries = [entry for entry in student_data['entries'] if entry['analysis_type'] == 'discourse']
|
392 |
for entry in discourse_entries:
|
393 |
st.subheader(f"Análisis del {entry['timestamp']}")
|
394 |
+
|
395 |
+
# Mostrar conceptos clave para ambos documentos
|
396 |
+
if 'key_concepts1' in entry:
|
397 |
+
concepts_str1 = " | ".join([f"{concept} ({frequency:.2f})" for concept, frequency in entry['key_concepts1']])
|
398 |
+
st.write("Conceptos clave del documento 1:")
|
399 |
+
#st.write(concepts_str1)
|
400 |
+
st.markdown(f"<div style='background-color: #f0f2f6; padding: 10px; border-radius: 5px;'>{concepts_str1}</div>", unsafe_allow_html=True)
|
401 |
+
|
402 |
+
if 'key_concepts2' in entry:
|
403 |
+
concepts_str2 = " | ".join([f"{concept} ({frequency:.2f})" for concept, frequency in entry['key_concepts2']])
|
404 |
+
st.write("Conceptos clave del documento 2:")
|
405 |
+
#st.write(concepts_str2)
|
406 |
+
st.markdown(f"<div style='background-color: #f0f2f6; padding: 10px; border-radius: 5px;'>{concepts_str2}</div>", unsafe_allow_html=True)
|
407 |
|
408 |
try:
|
409 |
+
if 'combined_graph' in entry and entry['combined_graph']:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
410 |
img_bytes = base64.b64decode(entry['combined_graph'])
|
411 |
st.image(img_bytes)
|
412 |
+
elif 'graph1' in entry and 'graph2' in entry:
|
413 |
+
col1, col2 = st.columns(2)
|
414 |
+
with col1:
|
415 |
+
if entry['graph1']:
|
416 |
+
img_bytes1 = base64.b64decode(entry['graph1'])
|
417 |
+
st.image(img_bytes1)
|
418 |
+
with col2:
|
419 |
+
if entry['graph2']:
|
420 |
+
img_bytes2 = base64.b64decode(entry['graph2'])
|
421 |
+
st.image(img_bytes2)
|
422 |
else:
|
423 |
st.write("No se encontraron gráficos para este análisis.")
|
424 |
except Exception as e:
|
|
|
430 |
st.write("Graph 2:", entry['graph2'][:100] + "...")
|
431 |
if 'combined_graph' in entry:
|
432 |
st.write("Combined Graph:", entry['combined_graph'][:100] + "...")
|
|
|
433 |
|
434 |
##########################################################
|
435 |
with st.expander("Histórico de Conversaciones con el ChatBot"):
|
|
|
468 |
'success_message': "Análisis guardado correctamente.",
|
469 |
'error_message': "Hubo un problema al guardar el análisis. Por favor, inténtelo de nuevo.",
|
470 |
'warning_message': "Por favor, ingrese un texto para analizar.",
|
471 |
+
'initial_message': "Ingrese un texto y presione 'Analizar texto' para comenzar.",
|
472 |
+
'no_results': "No hay resultados disponibles. Por favor, realice un análisis primero.",
|
473 |
'pos_analysis': "Análisis de categorías gramaticales",
|
474 |
'morphological_analysis': "Análisis morfológico",
|
475 |
'sentence_structure': "Estructura de oraciones",
|
|
|
504 |
'success_message': "Analysis saved successfully.",
|
505 |
'error_message': "There was a problem saving the analysis. Please try again.",
|
506 |
'warning_message': "Please enter a text to analyze.",
|
507 |
+
'initial_message': "Enter a text and press 'Analyze text' to start.",
|
508 |
+
'no_results': "No results available. Please perform an analysis first.",
|
509 |
'pos_analysis': "Part of Speech Analysis",
|
510 |
'morphological_analysis': "Morphological Analysis",
|
511 |
'sentence_structure': "Sentence Structure",
|
|
|
540 |
'success_message': "Analyse enregistrée avec succès.",
|
541 |
'error_message': "Un problème est survenu lors de l'enregistrement de l'analyse. Veuillez réessayer.",
|
542 |
'warning_message': "Veuillez entrer un texte à analyser.",
|
543 |
+
'initial_message': "Entrez un texte et appuyez sur 'Analyser le texte' pour commencer.",
|
544 |
+
'no_results': "Aucun résultat disponible. Veuillez d'abord effectuer une analyse.",
|
545 |
'pos_analysis': "Analyse des parties du discours",
|
546 |
'morphological_analysis': "Analyse morphologique",
|
547 |
'sentence_structure': "Structure des phrases",
|
|
|
587 |
# Análisis morfosintáctico avanzado
|
588 |
advanced_analysis = perform_advanced_morphosyntactic_analysis(current_input, nlp_models[lang_code])
|
589 |
|
590 |
+
# Guardar el resultado en el estado de la sesión
|
591 |
+
st.session_state.morphosyntax_result = {
|
592 |
+
'doc': doc,
|
593 |
+
'advanced_analysis': advanced_analysis
|
594 |
+
}
|
595 |
+
|
596 |
+
# Mostrar resultados
|
597 |
+
display_morphosyntax_results(st.session_state.morphosyntax_result, lang_code, t)
|
598 |
+
|
599 |
+
# Guardar resultados
|
600 |
+
if store_morphosyntax_result(
|
601 |
+
st.session_state.username,
|
602 |
+
current_input,
|
603 |
+
get_repeated_words_colors(doc),
|
604 |
+
advanced_analysis['arc_diagram'],
|
605 |
+
advanced_analysis['pos_analysis'],
|
606 |
+
advanced_analysis['morphological_analysis'],
|
607 |
+
advanced_analysis['sentence_structure']
|
608 |
+
):
|
609 |
+
st.success(t['success_message'])
|
610 |
+
else:
|
611 |
+
st.error(t['error_message'])
|
612 |
+
else:
|
613 |
+
st.warning(t['warning_message'])
|
614 |
+
elif 'morphosyntax_result' in st.session_state and st.session_state.morphosyntax_result is not None:
|
615 |
+
|
616 |
+
# Si hay un resultado guardado, mostrarlo
|
617 |
+
display_morphosyntax_results(st.session_state.morphosyntax_result, lang_code, t)
|
618 |
+
else:
|
619 |
+
st.info(t['initial_message']) # Añade esta traducción a tu diccionario
|
620 |
+
|
621 |
+
def display_morphosyntax_results(result, lang_code, t):
|
622 |
+
if result is None:
|
623 |
+
st.warning(t['no_results']) # Añade esta traducción a tu diccionario
|
624 |
+
return
|
625 |
+
|
626 |
+
doc = result['doc']
|
627 |
+
advanced_analysis = result['advanced_analysis']
|
628 |
+
|
629 |
+
# Mostrar leyenda (código existente)
|
630 |
+
st.markdown(f"##### {t['legend']}")
|
631 |
+
legend_html = "<div style='display: flex; flex-wrap: wrap;'>"
|
632 |
+
for pos, color in POS_COLORS.items():
|
633 |
+
if pos in POS_TRANSLATIONS[lang_code]:
|
634 |
+
legend_html += f"<div style='margin-right: 10px;'><span style='background-color: {color}; padding: 2px 5px;'>{POS_TRANSLATIONS[lang_code][pos]}</span></div>"
|
635 |
+
legend_html += "</div>"
|
636 |
+
st.markdown(legend_html, unsafe_allow_html=True)
|
637 |
+
|
638 |
+
# Mostrar análisis de palabras repetidas (código existente)
|
639 |
+
word_colors = get_repeated_words_colors(doc)
|
640 |
+
with st.expander(t['repeated_words'], expanded=True):
|
641 |
+
highlighted_text = highlight_repeated_words(doc, word_colors)
|
642 |
+
st.markdown(highlighted_text, unsafe_allow_html=True)
|
643 |
+
|
644 |
+
# Mostrar estructura de oraciones
|
645 |
+
with st.expander(t['sentence_structure'], expanded=True):
|
646 |
+
for i, sent_analysis in enumerate(advanced_analysis['sentence_structure']):
|
647 |
+
sentence_str = (
|
648 |
+
f"**{t['sentence']} {i+1}** "
|
649 |
+
f"{t['root']}: {sent_analysis['root']} ({sent_analysis['root_pos']}) -- "
|
650 |
+
f"{t['subjects']}: {', '.join(sent_analysis['subjects'])} -- "
|
651 |
+
f"{t['objects']}: {', '.join(sent_analysis['objects'])} -- "
|
652 |
+
f"{t['verbs']}: {', '.join(sent_analysis['verbs'])}"
|
653 |
+
)
|
654 |
+
st.markdown(sentence_str)
|
655 |
+
|
656 |
+
# Mostrar análisis de categorías gramaticales # Mostrar análisis morfológico
|
657 |
+
col1, col2 = st.columns(2)
|
658 |
+
|
659 |
+
with col1:
|
660 |
+
with st.expander(t['pos_analysis'], expanded=True):
|
661 |
+
pos_df = pd.DataFrame(advanced_analysis['pos_analysis'])
|
662 |
|
663 |
+
# Traducir las etiquetas POS a sus nombres en el idioma seleccionado
|
664 |
+
pos_df['pos'] = pos_df['pos'].map(lambda x: POS_TRANSLATIONS[lang_code].get(x, x))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
665 |
|
666 |
+
# Renombrar las columnas para mayor claridad
|
667 |
+
pos_df = pos_df.rename(columns={
|
668 |
+
'pos': t['grammatical_category'],
|
669 |
+
'count': t['count'],
|
670 |
+
'percentage': t['percentage'],
|
671 |
+
'examples': t['examples']
|
672 |
+
})
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
673 |
|
674 |
+
# Mostrar el dataframe
|
675 |
+
st.dataframe(pos_df)
|
676 |
+
|
677 |
+
with col2:
|
678 |
+
with st.expander(t['morphological_analysis'], expanded=True):
|
679 |
+
morph_df = pd.DataFrame(advanced_analysis['morphological_analysis'])
|
680 |
+
|
681 |
+
# Definir el mapeo de columnas
|
682 |
+
column_mapping = {
|
683 |
+
'text': t['word'],
|
684 |
+
'lemma': t['lemma'],
|
685 |
+
'pos': t['grammatical_category'],
|
686 |
+
'dep': t['dependency'],
|
687 |
+
'morph': t['morphology']
|
688 |
+
}
|
689 |
+
|
690 |
+
# Renombrar las columnas existentes
|
691 |
+
morph_df = morph_df.rename(columns={col: new_name for col, new_name in column_mapping.items() if col in morph_df.columns})
|
692 |
+
|
693 |
+
# Traducir las categorías gramaticales
|
694 |
+
morph_df[t['grammatical_category']] = morph_df[t['grammatical_category']].map(lambda x: POS_TRANSLATIONS[lang_code].get(x, x))
|
695 |
+
|
696 |
+
# Traducir las dependencias
|
697 |
+
dep_translations = {
|
698 |
+
'es': {
|
699 |
+
'ROOT': 'RAÍZ', 'nsubj': 'sujeto nominal', 'obj': 'objeto', 'iobj': 'objeto indirecto',
|
700 |
+
'csubj': 'sujeto clausal', 'ccomp': 'complemento clausal', 'xcomp': 'complemento clausal abierto',
|
701 |
+
'obl': 'oblicuo', 'vocative': 'vocativo', 'expl': 'expletivo', 'dislocated': 'dislocado',
|
702 |
+
'advcl': 'cláusula adverbial', 'advmod': 'modificador adverbial', 'discourse': 'discurso',
|
703 |
+
'aux': 'auxiliar', 'cop': 'cópula', 'mark': 'marcador', 'nmod': 'modificador nominal',
|
704 |
+
'appos': 'aposición', 'nummod': 'modificador numeral', 'acl': 'cláusula adjetiva',
|
705 |
+
'amod': 'modificador adjetival', 'det': 'determinante', 'clf': 'clasificador',
|
706 |
+
'case': 'caso', 'conj': 'conjunción', 'cc': 'coordinante', 'fixed': 'fijo',
|
707 |
+
'flat': 'plano', 'compound': 'compuesto', 'list': 'lista', 'parataxis': 'parataxis',
|
708 |
+
'orphan': 'huérfano', 'goeswith': 'va con', 'reparandum': 'reparación', 'punct': 'puntuación'
|
709 |
+
},
|
710 |
+
'en': {
|
711 |
+
'ROOT': 'ROOT', 'nsubj': 'nominal subject', 'obj': 'object',
|
712 |
+
'iobj': 'indirect object', 'csubj': 'clausal subject', 'ccomp': 'clausal complement', 'xcomp': 'open clausal complement',
|
713 |
+
'obl': 'oblique', 'vocative': 'vocative', 'expl': 'expletive', 'dislocated': 'dislocated', 'advcl': 'adverbial clause modifier',
|
714 |
+
'advmod': 'adverbial modifier', 'discourse': 'discourse element', 'aux': 'auxiliary', 'cop': 'copula', 'mark': 'marker',
|
715 |
+
'nmod': 'nominal modifier', 'appos': 'appositional modifier', 'nummod': 'numeric modifier', 'acl': 'clausal modifier of noun',
|
716 |
+
'amod': 'adjectival modifier', 'det': 'determiner', 'clf': 'classifier', 'case': 'case marking',
|
717 |
+
'conj': 'conjunct', 'cc': 'coordinating conjunction', 'fixed': 'fixed multiword expression',
|
718 |
+
'flat': 'flat multiword expression', 'compound': 'compound', 'list': 'list', 'parataxis': 'parataxis', 'orphan': 'orphan',
|
719 |
+
'goeswith': 'goes with', 'reparandum': 'reparandum', 'punct': 'punctuation'
|
720 |
+
},
|
721 |
+
'fr': {
|
722 |
+
'ROOT': 'RACINE', 'nsubj': 'sujet nominal', 'obj': 'objet', 'iobj': 'objet indirect',
|
723 |
+
'csubj': 'sujet phrastique', 'ccomp': 'complément phrastique', 'xcomp': 'complément phrastique ouvert', 'obl': 'oblique',
|
724 |
+
'vocative': 'vocatif', 'expl': 'explétif', 'dislocated': 'disloqué', 'advcl': 'clause adverbiale', 'advmod': 'modifieur adverbial',
|
725 |
+
'discourse': 'élément de discours', 'aux': 'auxiliaire', 'cop': 'copule', 'mark': 'marqueur', 'nmod': 'modifieur nominal',
|
726 |
+
'appos': 'apposition', 'nummod': 'modifieur numéral', 'acl': 'clause relative', 'amod': 'modifieur adjectival', 'det': 'déterminant',
|
727 |
+
'clf': 'classificateur', 'case': 'marqueur de cas', 'conj': 'conjonction', 'cc': 'coordination', 'fixed': 'expression figée',
|
728 |
+
'flat': 'construction plate', 'compound': 'composé', 'list': 'liste', 'parataxis': 'parataxe', 'orphan': 'orphelin',
|
729 |
+
'goeswith': 'va avec', 'reparandum': 'réparation', 'punct': 'ponctuation'
|
730 |
+
}
|
731 |
+
}
|
732 |
+
morph_df[t['dependency']] = morph_df[t['dependency']].map(lambda x: dep_translations[lang_code].get(x, x))
|
733 |
+
|
734 |
+
# Traducir la morfología
|
735 |
+
def translate_morph(morph_string, lang_code):
|
736 |
+
morph_translations = {
|
737 |
+
'es': {
|
738 |
+
'Gender': 'Género', 'Number': 'Número', 'Case': 'Caso', 'Definite': 'Definido',
|
739 |
+
'PronType': 'Tipo de Pronombre', 'Person': 'Persona', 'Mood': 'Modo',
|
740 |
+
'Tense': 'Tiempo', 'VerbForm': 'Forma Verbal', 'Voice': 'Voz',
|
741 |
+
'Fem': 'Femenino', 'Masc': 'Masculino', 'Sing': 'Singular', 'Plur': 'Plural',
|
742 |
+
'Ind': 'Indicativo', 'Sub': 'Subjuntivo', 'Imp': 'Imperativo', 'Inf': 'Infinitivo',
|
743 |
+
'Part': 'Participio', 'Ger': 'Gerundio', 'Pres': 'Presente', 'Past': 'Pasado',
|
744 |
+
'Fut': 'Futuro', 'Perf': 'Perfecto', 'Imp': 'Imperfecto'
|
745 |
+
},
|
746 |
+
'en': {
|
747 |
+
'Gender': 'Gender', 'Number': 'Number', 'Case': 'Case', 'Definite': 'Definite', 'PronType': 'Pronoun Type', 'Person': 'Person',
|
748 |
+
'Mood': 'Mood', 'Tense': 'Tense', 'VerbForm': 'Verb Form', 'Voice': 'Voice',
|
749 |
+
'Fem': 'Feminine', 'Masc': 'Masculine', 'Sing': 'Singular', 'Plur': 'Plural', 'Ind': 'Indicative',
|
750 |
+
'Sub': 'Subjunctive', 'Imp': 'Imperative', 'Inf': 'Infinitive', 'Part': 'Participle',
|
751 |
+
'Ger': 'Gerund', 'Pres': 'Present', 'Past': 'Past', 'Fut': 'Future', 'Perf': 'Perfect', 'Imp': 'Imperfect'
|
752 |
+
},
|
753 |
+
'fr': {
|
754 |
+
'Gender': 'Genre', 'Number': 'Nombre', 'Case': 'Cas', 'Definite': 'Défini', 'PronType': 'Type de Pronom',
|
755 |
+
'Person': 'Personne', 'Mood': 'Mode', 'Tense': 'Temps', 'VerbForm': 'Forme Verbale', 'Voice': 'Voix',
|
756 |
+
'Fem': 'Féminin', 'Masc': 'Masculin', 'Sing': 'Singulier', 'Plur': 'Pluriel', 'Ind': 'Indicatif',
|
757 |
+
'Sub': 'Subjonctif', 'Imp': 'Impératif', 'Inf': 'Infinitif', 'Part': 'Participe',
|
758 |
+
'Ger': 'Gérondif', 'Pres': 'Présent', 'Past': 'Passé', 'Fut': 'Futur', 'Perf': 'Parfait', 'Imp': 'Imparfait'
|
759 |
}
|
760 |
+
}
|
761 |
+
for key, value in morph_translations[lang_code].items():
|
762 |
+
morph_string = morph_string.replace(key, value)
|
763 |
+
return morph_string
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
764 |
|
765 |
+
morph_df[t['morphology']] = morph_df[t['morphology']].apply(lambda x: translate_morph(x, lang_code))
|
766 |
+
|
767 |
+
# Seleccionar y ordenar las columnas a mostrar
|
768 |
+
columns_to_display = [t['word'], t['lemma'], t['grammatical_category'], t['dependency'], t['morphology']]
|
769 |
+
columns_to_display = [col for col in columns_to_display if col in morph_df.columns]
|
770 |
+
|
771 |
+
# Mostrar el DataFrame
|
772 |
+
st.dataframe(morph_df[columns_to_display])
|
773 |
+
|
774 |
+
# Mostrar diagramas de arco (código existente)
|
775 |
+
with st.expander(t['arc_diagram'], expanded=True):
|
776 |
+
sentences = list(doc.sents)
|
777 |
+
arc_diagrams = []
|
778 |
+
for i, sent in enumerate(sentences):
|
779 |
+
st.subheader(f"{t['sentence']} {i+1}")
|
780 |
+
html = displacy.render(sent, style="dep", options={"distance": 100})
|
781 |
+
html = html.replace('height="375"', 'height="200"')
|
782 |
+
html = re.sub(r'<svg[^>]*>', lambda m: m.group(0).replace('height="450"', 'height="300"'), html)
|
783 |
+
html = re.sub(r'<g [^>]*transform="translate\((\d+),(\d+)\)"', lambda m: f'<g transform="translate({m.group(1)},50)"', html)
|
784 |
+
st.write(html, unsafe_allow_html=True)
|
785 |
+
arc_diagrams.append(html)
|
786 |
|
787 |
###############################################################################################################
|
788 |
def display_semantic_analysis_interface(nlp_models, lang_code):
|
|
|
798 |
'key_concepts': "Conceptos Clave",
|
799 |
'success_message': "Análisis semántico guardado correctamente.",
|
800 |
'error_message': "Hubo un problema al guardar el análisis semántico. Por favor, inténtelo de nuevo.",
|
801 |
+
'warning_message': "Por favor, ingrese un texto o cargue un archivo para analizar.",
|
802 |
+
'initial_message': "Ingrese un texto y presione 'Analizar texto' para comenzar.",
|
803 |
+
'no_results': "No hay resultados disponibles. Por favor, realice un análisis primero."
|
804 |
},
|
805 |
'en': {
|
806 |
'title': "AIdeaText - Semantic Analysis",
|
|
|
813 |
'key_concepts': "Key Concepts",
|
814 |
'success_message': "Semantic analysis saved successfully.",
|
815 |
'error_message': "There was a problem saving the semantic analysis. Please try again.",
|
816 |
+
'warning_message': "Please enter a text or upload a file to analyze.",
|
817 |
+
'initial_message': "Enter a text and press 'Analyze text' to start.",
|
818 |
+
'no_results': "No results available. Please perform an analysis first."
|
819 |
},
|
820 |
'fr': {
|
821 |
'title': "AIdeaText - Analyse sémantique",
|
|
|
828 |
'key_concepts': "Concepts Clés",
|
829 |
'success_message': "Analyse sémantique enregistrée avec succès.",
|
830 |
'error_message': "Un problème est survenu lors de l'enregistrement de l'analyse sémantique. Veuillez réessayer.",
|
831 |
+
'warning_message': "Veuillez entrer un texte ou télécharger un fichier à analyser.",
|
832 |
+
'initial_message': "Entrez un texte et appuyez sur 'Analyser le texte' pour commencer.",
|
833 |
+
'no_results': "Aucun résultat disponible. Veuillez d'abord effectuer une analyse."
|
834 |
}
|
835 |
}
|
836 |
|
|
|
858 |
# Realizar el análisis
|
859 |
analysis_result = perform_semantic_analysis(text_content, nlp_models[lang_code], lang_code)
|
860 |
|
861 |
+
# Guardar el resultado en el estado de la sesión
|
862 |
+
st.session_state.semantic_result = analysis_result
|
|
|
|
|
863 |
|
864 |
+
# Mostrar resultados
|
865 |
+
display_semantic_results(st.session_state.semantic_result, lang_code, t)
|
|
|
866 |
|
867 |
# Guardar el resultado del análisis
|
868 |
if store_semantic_result(st.session_state.username, text_content, analysis_result):
|
|
|
871 |
st.error(t['error_message'])
|
872 |
else:
|
873 |
st.warning(t['warning_message'])
|
874 |
+
|
875 |
+
elif 'semantic_result' in st.session_state:
|
876 |
+
|
877 |
+
# Si hay un resultado guardado, mostrarlo
|
878 |
+
display_semantic_results(st.session_state.semantic_result, lang_code, t)
|
879 |
+
|
880 |
+
else:
|
881 |
+
st.info(t['initial_message']) # Asegúrate de que 'initial_message' esté en tus traducciones
|
882 |
+
|
883 |
+
def display_semantic_results(result, lang_code, t):
|
884 |
+
if result is None:
|
885 |
+
st.warning(t['no_results']) # Asegúrate de que 'no_results' esté en tus traducciones
|
886 |
+
return
|
887 |
+
|
888 |
+
# Mostrar conceptos clave
|
889 |
+
with st.expander(t['key_concepts'], expanded=True):
|
890 |
+
concept_text = " | ".join([f"{concept} ({frequency:.2f})" for concept, frequency in result['key_concepts']])
|
891 |
+
st.write(concept_text)
|
892 |
+
|
893 |
+
# Mostrar el gráfico de relaciones conceptuales
|
894 |
+
with st.expander(t['conceptual_relations'], expanded=True):
|
895 |
+
st.pyplot(result['relations_graph'])
|
896 |
+
|
897 |
##################################################################################################
|
898 |
def display_discourse_analysis_interface(nlp_models, lang_code):
|
899 |
translations = {
|
|
|
905 |
'comparison': "Comparación de Relaciones Semánticas",
|
906 |
'success_message': "Análisis del discurso guardado correctamente.",
|
907 |
'error_message': "Hubo un problema al guardar el análisis del discurso. Por favor, inténtelo de nuevo.",
|
908 |
+
'warning_message': "Por favor, cargue ambos archivos para analizar.",
|
909 |
+
'initial_message': "Ingrese un texto y presione 'Analizar texto' para comenzar.",
|
910 |
+
'no_results': "No hay resultados disponibles. Por favor, realice un análisis primero.",
|
911 |
+
'key_concepts': "Conceptos Clave",
|
912 |
+
'graph_not_available': "El gráfico no está disponible.",
|
913 |
+
'concepts_not_available': "Los conceptos clave no están disponibles.",
|
914 |
+
'comparison_not_available': "La comparación no está disponible."
|
915 |
},
|
916 |
'en': {
|
917 |
'title': "AIdeaText - Discourse Analysis",
|
|
|
921 |
'comparison': "Comparison of Semantic Relations",
|
922 |
'success_message': "Discourse analysis saved successfully.",
|
923 |
'error_message': "There was a problem saving the discourse analysis. Please try again.",
|
924 |
+
'warning_message': "Please upload both files to analyze.",
|
925 |
+
'initial_message': "Enter a text and press 'Analyze text' to start.",
|
926 |
+
'no_results': "No results available. Please perform an analysis first.",
|
927 |
+
'key_concepts': "Key Concepts",
|
928 |
+
'graph_not_available': "The graph is not available.",
|
929 |
+
'concepts_not_available': "Key concepts are not available.",
|
930 |
+
'comparison_not_available': "The comparison is not available."
|
931 |
},
|
932 |
'fr': {
|
933 |
'title': "AIdeaText - Analyse du discours",
|
|
|
937 |
'comparison': "Comparaison des Relations Sémantiques",
|
938 |
'success_message': "Analyse du discours enregistrée avec succès.",
|
939 |
'error_message': "Un problème est survenu lors de l'enregistrement de l'analyse du discours. Veuillez réessayer.",
|
940 |
+
'warning_message': "Veuillez télécharger les deux fichiers à analyser.",
|
941 |
+
'initial_message': "Entrez un texte et appuyez sur 'Analyser le texte' pour commencer.",
|
942 |
+
'no_results': "Aucun résultat disponible. Veuillez d'abord effectuer une analyse.",
|
943 |
+
'key_concepts': "Concepts Clés",
|
944 |
+
'graph_not_available': "Le graphique n'est pas disponible.",
|
945 |
+
'concepts_not_available': "Les concepts clés ne sont pas disponibles.",
|
946 |
+
'comparison_not_available': "La comparaison n'est pas disponible."
|
947 |
}
|
948 |
}
|
949 |
|
|
|
951 |
st.header(t['title'])
|
952 |
|
953 |
col1, col2 = st.columns(2)
|
|
|
954 |
with col1:
|
955 |
uploaded_file1 = st.file_uploader(t['file_uploader1'], type=['txt'])
|
|
|
956 |
with col2:
|
957 |
uploaded_file2 = st.file_uploader(t['file_uploader2'], type=['txt'])
|
958 |
|
|
|
964 |
# Realizar el análisis
|
965 |
analysis_result = perform_discourse_analysis(text_content1, text_content2, nlp_models[lang_code], lang_code)
|
966 |
|
967 |
+
# Guardar el resultado en el estado de la sesión
|
968 |
+
st.session_state.discourse_result = analysis_result
|
969 |
+
|
970 |
# Mostrar los resultados del análisis
|
971 |
+
display_discourse_results(st.session_state.discourse_result, lang_code, t)
|
972 |
|
973 |
# Guardar el resultado del análisis
|
974 |
if store_discourse_analysis_result(st.session_state.username, text_content1, text_content2, analysis_result):
|
|
|
977 |
st.error(t['error_message'])
|
978 |
else:
|
979 |
st.warning(t['warning_message'])
|
980 |
+
elif 'discourse_result' in st.session_state and st.session_state.discourse_result is not None:
|
981 |
+
# Si hay un resultado guardado, mostrarlo
|
982 |
+
display_discourse_results(st.session_state.discourse_result, lang_code, t)
|
983 |
+
else:
|
984 |
+
st.info(t['initial_message']) # Asegúrate de que 'initial_message' esté en tus traducciones
|
985 |
+
|
986 |
+
#################################################
|
987 |
+
|
988 |
+
def display_discourse_results(result, lang_code, t):
|
989 |
+
if result is None:
|
990 |
+
st.warning(t.get('no_results', "No hay resultados disponibles."))
|
991 |
+
return
|
992 |
+
|
993 |
+
col1, col2 = st.columns(2)
|
994 |
+
|
995 |
+
with col1:
|
996 |
+
with st.expander(t.get('file_uploader1', "Documento 1"), expanded=True):
|
997 |
+
st.subheader(t.get('key_concepts', "Conceptos Clave"))
|
998 |
+
if 'key_concepts1' in result:
|
999 |
+
df1 = pd.DataFrame(result['key_concepts1'], columns=['Concepto', 'Frecuencia'])
|
1000 |
+
df1['Frecuencia'] = df1['Frecuencia'].round(2)
|
1001 |
+
st.table(df1)
|
1002 |
+
else:
|
1003 |
+
st.warning(t.get('concepts_not_available', "Los conceptos clave no están disponibles."))
|
1004 |
+
|
1005 |
+
if 'graph1' in result:
|
1006 |
+
st.pyplot(result['graph1'])
|
1007 |
+
else:
|
1008 |
+
st.warning(t.get('graph_not_available', "El gráfico no está disponible."))
|
1009 |
+
|
1010 |
+
with col2:
|
1011 |
+
with st.expander(t.get('file_uploader2', "Documento 2"), expanded=True):
|
1012 |
+
st.subheader(t.get('key_concepts', "Conceptos Clave"))
|
1013 |
+
if 'key_concepts2' in result:
|
1014 |
+
df2 = pd.DataFrame(result['key_concepts2'], columns=['Concepto', 'Frecuencia'])
|
1015 |
+
df2['Frecuencia'] = df2['Frecuencia'].round(2)
|
1016 |
+
st.table(df2)
|
1017 |
+
else:
|
1018 |
+
st.warning(t.get('concepts_not_available', "Los conceptos clave no están disponibles."))
|
1019 |
+
|
1020 |
+
if 'graph2' in result:
|
1021 |
+
st.pyplot(result['graph2'])
|
1022 |
+
else:
|
1023 |
+
st.warning(t.get('graph_not_available', "El gráfico no está disponible."))
|
1024 |
+
|
1025 |
+
# Relación de conceptos entre ambos documentos (Diagrama de Sankey)
|
1026 |
+
st.subheader(t.get('comparison', "Relación de conceptos entre ambos documentos"))
|
1027 |
+
if 'key_concepts1' in result and 'key_concepts2' in result:
|
1028 |
+
df1 = pd.DataFrame(result['key_concepts1'], columns=['Concepto', 'Frecuencia'])
|
1029 |
+
df2 = pd.DataFrame(result['key_concepts2'], columns=['Concepto', 'Frecuencia'])
|
1030 |
+
|
1031 |
+
# Crear una lista de todos los conceptos únicos
|
1032 |
+
all_concepts = list(set(df1['Concepto'].tolist() + df2['Concepto'].tolist()))
|
1033 |
+
|
1034 |
+
# Crear un diccionario de colores para cada concepto
|
1035 |
+
color_scale = [f'rgb({random.randint(50,255)},{random.randint(50,255)},{random.randint(50,255)})' for _ in range(len(all_concepts))]
|
1036 |
+
color_map = dict(zip(all_concepts, color_scale))
|
1037 |
+
|
1038 |
+
# Crear el diagrama de Sankey
|
1039 |
+
source = [0] * len(df1) + list(range(2, 2 + len(df1)))
|
1040 |
+
target = list(range(2, 2 + len(df1))) + [1] * len(df2)
|
1041 |
+
value = list(df1['Frecuencia']) + list(df2['Frecuencia'])
|
1042 |
+
|
1043 |
+
node_colors = ['blue', 'red'] + [color_map[concept] for concept in df1['Concepto']] + [color_map[concept] for concept in df2['Concepto']]
|
1044 |
+
link_colors = [color_map[concept] for concept in df1['Concepto']] + [color_map[concept] for concept in df2['Concepto']]
|
1045 |
+
|
1046 |
+
fig = go.Figure(data=[go.Sankey(
|
1047 |
+
node = dict(
|
1048 |
+
pad = 15,
|
1049 |
+
thickness = 20,
|
1050 |
+
line = dict(color = "black", width = 0.5),
|
1051 |
+
label = [t.get('file_uploader1', "Documento 1"), t.get('file_uploader2', "Documento 2")] + list(df1['Concepto']) + list(df2['Concepto']),
|
1052 |
+
color = node_colors
|
1053 |
+
),
|
1054 |
+
link = dict(
|
1055 |
+
source = source,
|
1056 |
+
target = target,
|
1057 |
+
value = value,
|
1058 |
+
color = link_colors
|
1059 |
+
))])
|
1060 |
+
|
1061 |
+
fig.update_layout(title_text="Relación de conceptos entre documentos", font_size=10)
|
1062 |
+
st.plotly_chart(fig, use_container_width=True)
|
1063 |
+
else:
|
1064 |
+
st.warning(t.get('comparison_not_available', "La comparación no está disponible."))
|
1065 |
+
|
1066 |
+
# Aquí puedes agregar el código para mostrar los gráficos si es necesario
|
1067 |
|
1068 |
##################################################################################################
|
1069 |
#def display_saved_discourse_analysis(analysis_data):
|
modules/ui/ui_rest1.py
ADDED
@@ -0,0 +1,1145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Importaciones generales
|
2 |
+
import streamlit as st
|
3 |
+
import re
|
4 |
+
import io
|
5 |
+
from io import BytesIO
|
6 |
+
import base64
|
7 |
+
import matplotlib.pyplot as plt
|
8 |
+
import pandas as pd
|
9 |
+
import numpy as np
|
10 |
+
import time
|
11 |
+
from datetime import datetime
|
12 |
+
from streamlit_player import st_player # Necesitarás instalar esta librería: pip install streamlit-player
|
13 |
+
from spacy import displacy
|
14 |
+
import logging
|
15 |
+
|
16 |
+
######################################################
|
17 |
+
# Configuración del logger
|
18 |
+
logging.basicConfig(level=logging.INFO)
|
19 |
+
logger = logging.getLogger(__name__)
|
20 |
+
|
21 |
+
######################################################
|
22 |
+
# Importaciones locales
|
23 |
+
from ..email.email import send_email_notification
|
24 |
+
|
25 |
+
######################################################
|
26 |
+
# Importaciones locales de autenticación y base de datos
|
27 |
+
from ..auth.auth import (
|
28 |
+
authenticate_user,
|
29 |
+
register_user
|
30 |
+
)
|
31 |
+
|
32 |
+
######################################################
|
33 |
+
from ..database.database import (
|
34 |
+
get_student_data,
|
35 |
+
store_application_request,
|
36 |
+
store_morphosyntax_result,
|
37 |
+
store_semantic_result,
|
38 |
+
store_discourse_analysis_result,
|
39 |
+
store_chat_history,
|
40 |
+
create_admin_user,
|
41 |
+
create_student_user,
|
42 |
+
store_user_feedback
|
43 |
+
)
|
44 |
+
|
45 |
+
######################################################
|
46 |
+
# Importaciones locales de uiadmin
|
47 |
+
from ..admin.admin_ui import admin_page
|
48 |
+
|
49 |
+
######################################################
|
50 |
+
# Importaciones locales funciones de análisis
|
51 |
+
from ..text_analysis.morpho_analysis import (
|
52 |
+
generate_arc_diagram,
|
53 |
+
get_repeated_words_colors,
|
54 |
+
highlight_repeated_words,
|
55 |
+
POS_COLORS,
|
56 |
+
POS_TRANSLATIONS,
|
57 |
+
perform_advanced_morphosyntactic_analysis
|
58 |
+
)
|
59 |
+
|
60 |
+
######################################################
|
61 |
+
from ..text_analysis.semantic_analysis import (
|
62 |
+
#visualize_semantic_relations,
|
63 |
+
perform_semantic_analysis,
|
64 |
+
create_concept_graph,
|
65 |
+
visualize_concept_graph
|
66 |
+
)
|
67 |
+
|
68 |
+
######################################################
|
69 |
+
from ..text_analysis.discourse_analysis import (
|
70 |
+
perform_discourse_analysis,
|
71 |
+
display_discourse_analysis_results
|
72 |
+
)
|
73 |
+
|
74 |
+
######################################################
|
75 |
+
from ..chatbot.chatbot import (
|
76 |
+
initialize_chatbot,
|
77 |
+
get_chatbot_response
|
78 |
+
)
|
79 |
+
|
80 |
+
##################################################################################################
|
81 |
+
def initialize_session_state():
|
82 |
+
if 'initialized' not in st.session_state:
|
83 |
+
st.session_state.clear()
|
84 |
+
st.session_state.initialized = True
|
85 |
+
st.session_state.logged_in = False
|
86 |
+
st.session_state.page = 'login'
|
87 |
+
st.session_state.username = None
|
88 |
+
st.session_state.role = None
|
89 |
+
|
90 |
+
##################################################################################################
|
91 |
+
def main():
|
92 |
+
initialize_session_state()
|
93 |
+
|
94 |
+
print(f"Página actual: {st.session_state.page}")
|
95 |
+
print(f"Rol del usuario: {st.session_state.role}")
|
96 |
+
|
97 |
+
if st.session_state.page == 'login':
|
98 |
+
login_register_page()
|
99 |
+
elif st.session_state.page == 'admin':
|
100 |
+
print("Intentando mostrar página de admin")
|
101 |
+
admin_page()
|
102 |
+
elif st.session_state.page == 'user':
|
103 |
+
user_page()
|
104 |
+
else:
|
105 |
+
print(f"Página no reconocida: {st.session_state.page}")
|
106 |
+
|
107 |
+
print(f"Estado final de la sesión: {st.session_state}")
|
108 |
+
|
109 |
+
##################################################################################################
|
110 |
+
def login_register_page():
|
111 |
+
st.title("AIdeaText")
|
112 |
+
|
113 |
+
left_column, right_column = st.columns([1, 3])
|
114 |
+
|
115 |
+
with left_column:
|
116 |
+
tab1, tab2 = st.tabs(["Iniciar Sesión", "Registrarse"])
|
117 |
+
|
118 |
+
with tab1:
|
119 |
+
login_form()
|
120 |
+
|
121 |
+
with tab2:
|
122 |
+
register_form()
|
123 |
+
|
124 |
+
with right_column:
|
125 |
+
display_videos_and_info()
|
126 |
+
|
127 |
+
##################################################################################################
|
128 |
+
|
129 |
+
def login_form():
|
130 |
+
username = st.text_input("Correo electrónico", key="login_username")
|
131 |
+
password = st.text_input("Contraseña", type="password", key="login_password")
|
132 |
+
|
133 |
+
if st.button("Iniciar Sesión", key="login_button"):
|
134 |
+
success, role = authenticate_user(username, password)
|
135 |
+
if success:
|
136 |
+
st.session_state.logged_in = True
|
137 |
+
st.session_state.username = username
|
138 |
+
st.session_state.role = role
|
139 |
+
st.session_state.page = 'admin' if role == 'Administrador' else 'user'
|
140 |
+
print(f"Inicio de sesión exitoso. Usuario: {username}, Rol: {role}")
|
141 |
+
print(f"Estado de sesión después de login: {st.session_state}")
|
142 |
+
st.rerun()
|
143 |
+
else:
|
144 |
+
st.error("Credenciales incorrectas")
|
145 |
+
|
146 |
+
##################################################################################################
|
147 |
+
def admin_page():
|
148 |
+
st.title("Panel de Administración")
|
149 |
+
st.write(f"Bienvenida, {st.session_state.username}")
|
150 |
+
|
151 |
+
st.header("Crear Nuevo Usuario Estudiante")
|
152 |
+
new_username = st.text_input("Correo electrónico del nuevo usuario", key="admin_new_username")
|
153 |
+
new_password = st.text_input("Contraseña", type="password", key="admin_new_password")
|
154 |
+
if st.button("Crear Usuario", key="admin_create_user"):
|
155 |
+
if create_student_user(new_username, new_password):
|
156 |
+
st.success(f"Usuario estudiante {new_username} creado exitosamente")
|
157 |
+
else:
|
158 |
+
st.error("Error al crear el usuario estudiante")
|
159 |
+
|
160 |
+
# Aquí puedes añadir más funcionalidades para el panel de administración
|
161 |
+
|
162 |
+
##################################################################################################
|
163 |
+
def user_page():
|
164 |
+
# Asumimos que el idioma seleccionado está almacenado en st.session_state.lang_code
|
165 |
+
# Si no está definido, usamos 'es' como valor predeterminado
|
166 |
+
lang_code = st.session_state.get('lang_code', 'es')
|
167 |
+
|
168 |
+
translations = {
|
169 |
+
'es': {
|
170 |
+
'welcome': "Bienvenido a AIdeaText",
|
171 |
+
'hello': "Hola",
|
172 |
+
'tabs': ["Análisis Morfosintáctico", "Análisis Semántico", "Análisis del Discurso", "Chat", "Mi Progreso", "Formulario de Retroalimentación"]
|
173 |
+
},
|
174 |
+
'en': {
|
175 |
+
'welcome': "Welcome to AIdeaText",
|
176 |
+
'hello': "Hello",
|
177 |
+
'tabs': ["Morphosyntactic Analysis", "Semantic Analysis", "Discourse Analysis", "Chat", "My Progress", "Feedback Form"]
|
178 |
+
},
|
179 |
+
'fr': {
|
180 |
+
'welcome': "Bienvenue à AIdeaText",
|
181 |
+
'hello': "Bonjour",
|
182 |
+
'tabs': ["Analyse Morphosyntaxique", "Analyse Sémantique", "Analyse du Discours", "Chat", "Mon Progrès", "Formulaire de Rétroaction"]
|
183 |
+
}
|
184 |
+
}
|
185 |
+
|
186 |
+
t = translations[lang_code]
|
187 |
+
|
188 |
+
st.title(t['welcome'])
|
189 |
+
st.write(f"{t['hello']}, {st.session_state.username}")
|
190 |
+
|
191 |
+
tabs = st.tabs(t['tabs'])
|
192 |
+
|
193 |
+
with tabs[0]:
|
194 |
+
display_morphosyntax_analysis_interface(nlp_models, lang_code)
|
195 |
+
with tabs[1]:
|
196 |
+
display_semantic_analysis_interface(nlp_models, lang_code)
|
197 |
+
with tabs[2]:
|
198 |
+
display_discourse_analysis_interface(nlp_models, lang_code)
|
199 |
+
with tabs[3]:
|
200 |
+
display_chatbot_interface(lang_code)
|
201 |
+
with tabs[4]:
|
202 |
+
display_student_progress(st.session_state.username, lang_code)
|
203 |
+
with tabs[5]:
|
204 |
+
display_feedback_form(lang_code)
|
205 |
+
|
206 |
+
##################################################################################################
|
207 |
+
def display_videos_and_info():
|
208 |
+
st.header("Videos: pitch, demos, entrevistas, otros")
|
209 |
+
|
210 |
+
videos = {
|
211 |
+
"Intro AideaText": "https://www.youtube.com/watch?v=UA-md1VxaRc",
|
212 |
+
"Presentación fundación Ser Maaestro": "https://www.youtube.com/watch?v=imc4TI1q164",
|
213 |
+
"Pitch IFE Explora": "https://www.youtube.com/watch?v=Fqi4Di_Rj_s",
|
214 |
+
"Entrevista Dr. Guillermo Ruíz": "https://www.youtube.com/watch?v=_ch8cRja3oc",
|
215 |
+
"Demo versión desktop": "https://www.youtube.com/watch?v=nP6eXbog-ZY"
|
216 |
+
}
|
217 |
+
|
218 |
+
selected_title = st.selectbox("Selecciona un video tutorial:", list(videos.keys()))
|
219 |
+
|
220 |
+
if selected_title in videos:
|
221 |
+
try:
|
222 |
+
st_player(videos[selected_title])
|
223 |
+
except Exception as e:
|
224 |
+
st.error(f"Error al cargar el video: {str(e)}")
|
225 |
+
|
226 |
+
st.markdown("""
|
227 |
+
## Novedades de la versión actual
|
228 |
+
- Nueva función de análisis semántico
|
229 |
+
- Soporte para múltiples idiomas
|
230 |
+
- Interfaz mejorada para una mejor experiencia de usuario
|
231 |
+
""")
|
232 |
+
|
233 |
+
##################################################################################################
|
234 |
+
def register_form():
|
235 |
+
st.header("Solicitar prueba de la aplicación")
|
236 |
+
|
237 |
+
name = st.text_input("Nombre completo")
|
238 |
+
email = st.text_input("Correo electrónico institucional")
|
239 |
+
institution = st.text_input("Institución")
|
240 |
+
role = st.selectbox("Rol", ["Estudiante", "Profesor", "Investigador", "Otro"])
|
241 |
+
reason = st.text_area("¿Por qué estás interesado en probar AIdeaText?")
|
242 |
+
|
243 |
+
if st.button("Enviar solicitud"):
|
244 |
+
logger.info(f"Attempting to submit application for {email}")
|
245 |
+
logger.debug(f"Form data: name={name}, email={email}, institution={institution}, role={role}, reason={reason}")
|
246 |
+
|
247 |
+
if not name or not email or not institution or not reason:
|
248 |
+
logger.warning("Incomplete form submission")
|
249 |
+
st.error("Por favor, completa todos los campos.")
|
250 |
+
elif not is_institutional_email(email):
|
251 |
+
logger.warning(f"Non-institutional email used: {email}")
|
252 |
+
st.error("Por favor, utiliza un correo electrónico institucional.")
|
253 |
+
else:
|
254 |
+
logger.info(f"Attempting to store application for {email}")
|
255 |
+
success = store_application_request(name, email, institution, role, reason)
|
256 |
+
if success:
|
257 |
+
st.success("Tu solicitud ha sido enviada. Te contactaremos pronto.")
|
258 |
+
logger.info(f"Application request stored successfully for {email}")
|
259 |
+
else:
|
260 |
+
st.error("Hubo un problema al enviar tu solicitud. Por favor, intenta de nuevo más tarde.")
|
261 |
+
logger.error(f"Failed to store application request for {email}")
|
262 |
+
|
263 |
+
################################################################################
|
264 |
+
def display_feedback_form(lang_code):
|
265 |
+
logging.info(f"display_feedback_form called with lang_code: {lang_code}")
|
266 |
+
translations = {
|
267 |
+
'es': {
|
268 |
+
'title': "Formulario de Retroalimentación",
|
269 |
+
'name': "Nombre",
|
270 |
+
'email': "Correo electrónico",
|
271 |
+
'feedback': "Tu retroalimentación",
|
272 |
+
'submit': "Enviar",
|
273 |
+
'success': "¡Gracias por tu retroalimentación!",
|
274 |
+
'error': "Hubo un problema al enviar el formulario. Por favor, intenta de nuevo."
|
275 |
+
},
|
276 |
+
'en': {
|
277 |
+
'title': "Feedback Form",
|
278 |
+
'name': "Name",
|
279 |
+
'email': "Email",
|
280 |
+
'feedback': "Your feedback",
|
281 |
+
'submit': "Submit",
|
282 |
+
'success': "Thank you for your feedback!",
|
283 |
+
'error': "There was a problem submitting the form. Please try again."
|
284 |
+
},
|
285 |
+
'fr': {
|
286 |
+
'title': "Formulaire de Rétroaction",
|
287 |
+
'name': "Nom",
|
288 |
+
'email': "Adresse e-mail",
|
289 |
+
'feedback': "Votre rétroaction",
|
290 |
+
'submit': "Envoyer",
|
291 |
+
'success': "Merci pour votre rétroaction !",
|
292 |
+
'error': "Un problème est survenu lors de l'envoi du formulaire. Veuillez réessayer."
|
293 |
+
}
|
294 |
+
}
|
295 |
+
|
296 |
+
t = translations[lang_code]
|
297 |
+
|
298 |
+
st.header(t['title'])
|
299 |
+
|
300 |
+
name = st.text_input(t['name'])
|
301 |
+
email = st.text_input(t['email'])
|
302 |
+
feedback = st.text_area(t['feedback'])
|
303 |
+
|
304 |
+
if st.button(t['submit']):
|
305 |
+
if name and email and feedback:
|
306 |
+
if store_user_feedback(st.session_state.username, name, email, feedback):
|
307 |
+
st.success(t['success'])
|
308 |
+
else:
|
309 |
+
st.error(t['error'])
|
310 |
+
else:
|
311 |
+
st.warning("Por favor, completa todos los campos.")
|
312 |
+
|
313 |
+
################################################################################
|
314 |
+
def is_institutional_email(email):
|
315 |
+
forbidden_domains = ['gmail.com', 'hotmail.com', 'yahoo.com', 'outlook.com']
|
316 |
+
return not any(domain in email.lower() for domain in forbidden_domains)
|
317 |
+
################################################################################
|
318 |
+
|
319 |
+
def display_student_progress(username, lang_code='es'):
|
320 |
+
student_data = get_student_data(username)
|
321 |
+
|
322 |
+
if student_data is None or len(student_data['entries']) == 0:
|
323 |
+
st.warning("No se encontraron datos para este estudiante.")
|
324 |
+
st.info("Intenta realizar algunos análisis de texto primero.")
|
325 |
+
return
|
326 |
+
|
327 |
+
st.title(f"Progreso de {username}")
|
328 |
+
|
329 |
+
with st.expander("Resumen de Actividades y Progreso", expanded=True):
|
330 |
+
# Resumen de actividades
|
331 |
+
total_entries = len(student_data['entries'])
|
332 |
+
st.write(f"Total de análisis realizados: {total_entries}")
|
333 |
+
|
334 |
+
# Gráfico de tipos de análisis
|
335 |
+
analysis_types = [entry['analysis_type'] for entry in student_data['entries']]
|
336 |
+
analysis_counts = pd.Series(analysis_types).value_counts()
|
337 |
+
|
338 |
+
fig, ax = plt.subplots()
|
339 |
+
analysis_counts.plot(kind='bar', ax=ax)
|
340 |
+
ax.set_title("Tipos de análisis realizados")
|
341 |
+
ax.set_xlabel("Tipo de análisis")
|
342 |
+
ax.set_ylabel("Cantidad")
|
343 |
+
st.pyplot(fig)
|
344 |
+
|
345 |
+
# Progreso a lo largo del tiempo
|
346 |
+
dates = [datetime.fromisoformat(entry['timestamp']) for entry in student_data['entries']]
|
347 |
+
analysis_counts = pd.Series(dates).value_counts().sort_index()
|
348 |
+
|
349 |
+
fig, ax = plt.subplots()
|
350 |
+
analysis_counts.plot(kind='line', ax=ax)
|
351 |
+
ax.set_title("Análisis realizados a lo largo del tiempo")
|
352 |
+
ax.set_xlabel("Fecha")
|
353 |
+
ax.set_ylabel("Cantidad de análisis")
|
354 |
+
st.pyplot(fig)
|
355 |
+
|
356 |
+
##########################################################
|
357 |
+
with st.expander("Histórico de Análisis Morfosintácticos"):
|
358 |
+
morphosyntax_entries = [entry for entry in student_data['entries'] if entry['analysis_type'] == 'morphosyntax']
|
359 |
+
for entry in morphosyntax_entries:
|
360 |
+
st.subheader(f"Análisis del {entry['timestamp']}")
|
361 |
+
if entry['arc_diagrams']:
|
362 |
+
st.write(entry['arc_diagrams'][0], unsafe_allow_html=True)
|
363 |
+
|
364 |
+
|
365 |
+
##########################################################
|
366 |
+
with st.expander("Histórico de Análisis Semánticos"):
|
367 |
+
semantic_entries = [entry for entry in student_data['entries'] if entry['analysis_type'] == 'semantic']
|
368 |
+
st.write(f"Número total de entradas semánticas: {len(semantic_entries)}")
|
369 |
+
for entry in semantic_entries:
|
370 |
+
st.subheader(f"Análisis del {entry['timestamp']}")
|
371 |
+
st.write(f"Archivo analizado: {entry.get('filename', 'Nombre no disponible')}")
|
372 |
+
st.write(f"Claves disponibles en esta entrada: {', '.join(entry.keys())}")
|
373 |
+
|
374 |
+
# Verificar si 'relations_graph' está en entry antes de intentar acceder
|
375 |
+
if 'network_diagram' in entry:
|
376 |
+
try:
|
377 |
+
logger.info(f"Longitud de la imagen recuperada: {len(entry['network_diagram'])}")
|
378 |
+
st.image(f"data:image/png;base64,{entry['network_diagram']}")
|
379 |
+
except Exception as e:
|
380 |
+
st.error(f"No se pudo mostrar la imagen: {str(e)}")
|
381 |
+
st.write("Datos de la imagen (para depuración):")
|
382 |
+
st.write(entry['network_diagram'][:100] + "...")
|
383 |
+
else:
|
384 |
+
logger.warning(f"No se encontró 'relations_graph' en la entrada: {entry.keys()}")
|
385 |
+
st.write("No se encontró el gráfico para este análisis.")
|
386 |
+
|
387 |
+
##########################################################
|
388 |
+
with st.expander("Histórico de Análisis Discursivos"):
|
389 |
+
discourse_entries = [entry for entry in student_data['entries'] if entry['analysis_type'] == 'discourse']
|
390 |
+
for entry in discourse_entries:
|
391 |
+
st.subheader(f"Análisis del {entry['timestamp']}")
|
392 |
+
st.write(f"Archivo patrón: {entry.get('filename1', 'Nombre no disponible')}")
|
393 |
+
st.write(f"Archivo comparado: {entry.get('filename2', 'Nombre no disponible')}")
|
394 |
+
|
395 |
+
try:
|
396 |
+
# Intentar obtener y combinar las dos imágenes
|
397 |
+
if 'graph1' in entry and 'graph2' in entry:
|
398 |
+
img1 = Image.open(BytesIO(base64.b64decode(entry['graph1'])))
|
399 |
+
img2 = Image.open(BytesIO(base64.b64decode(entry['graph2'])))
|
400 |
+
|
401 |
+
# Crear una nueva imagen combinada
|
402 |
+
total_width = img1.width + img2.width
|
403 |
+
max_height = max(img1.height, img2.height)
|
404 |
+
combined_img = Image.new('RGB', (total_width, max_height))
|
405 |
+
|
406 |
+
# Pegar las dos imágenes lado a lado
|
407 |
+
combined_img.paste(img1, (0, 0))
|
408 |
+
combined_img.paste(img2, (img1.width, 0))
|
409 |
+
|
410 |
+
# Convertir la imagen combinada a bytes
|
411 |
+
buffered = BytesIO()
|
412 |
+
combined_img.save(buffered, format="PNG")
|
413 |
+
img_str = base64.b64encode(buffered.getvalue()).decode()
|
414 |
+
|
415 |
+
# Mostrar la imagen combinada
|
416 |
+
st.image(f"data:image/png;base64,{img_str}")
|
417 |
+
elif 'combined_graph' in entry:
|
418 |
+
# Si ya existe una imagen combinada, mostrarla directamente
|
419 |
+
img_bytes = base64.b64decode(entry['combined_graph'])
|
420 |
+
st.image(img_bytes)
|
421 |
+
else:
|
422 |
+
st.write("No se encontraron gráficos para este análisis.")
|
423 |
+
except Exception as e:
|
424 |
+
st.error(f"No se pudieron mostrar los gráficos: {str(e)}")
|
425 |
+
st.write("Datos de los gráficos (para depuración):")
|
426 |
+
if 'graph1' in entry:
|
427 |
+
st.write("Graph 1:", entry['graph1'][:100] + "...")
|
428 |
+
if 'graph2' in entry:
|
429 |
+
st.write("Graph 2:", entry['graph2'][:100] + "...")
|
430 |
+
if 'combined_graph' in entry:
|
431 |
+
st.write("Combined Graph:", entry['combined_graph'][:100] + "...")
|
432 |
+
|
433 |
+
|
434 |
+
##########################################################
|
435 |
+
with st.expander("Histórico de Conversaciones con el ChatBot"):
|
436 |
+
if 'chat_history' in student_data:
|
437 |
+
for i, chat in enumerate(student_data['chat_history']):
|
438 |
+
st.subheader(f"Conversación {i+1} - {chat['timestamp']}")
|
439 |
+
for message in chat['messages']:
|
440 |
+
if message['role'] == 'user':
|
441 |
+
st.write("Usuario: " + message['content'])
|
442 |
+
else:
|
443 |
+
st.write("Asistente: " + message['content'])
|
444 |
+
st.write("---")
|
445 |
+
else:
|
446 |
+
st.write("No se encontraron conversaciones con el ChatBot.")
|
447 |
+
|
448 |
+
# Añadir logs para depuración
|
449 |
+
if st.checkbox("Mostrar datos de depuración"):
|
450 |
+
st.write("Datos del estudiante (para depuración):")
|
451 |
+
st.json(student_data)
|
452 |
+
|
453 |
+
##################################################################################################
|
454 |
+
def display_morphosyntax_analysis_interface(nlp_models, lang_code):
|
455 |
+
translations = {
|
456 |
+
'es': {
|
457 |
+
'title': "AIdeaText - Análisis morfológico y sintáctico",
|
458 |
+
'input_label': "Ingrese un texto para analizar (máximo 5,000 palabras",
|
459 |
+
'input_placeholder': "Esta funcionalidad le ayudará con dos competencias:\n"
|
460 |
+
"[1] \"Escribe diversos tipos de textos en su lengua materna\"\n"
|
461 |
+
"[2] \"Lee diversos tipos de textos escritos en su lengua materna\"\n\n"
|
462 |
+
"Ingrese su texto aquí para analizar...",
|
463 |
+
'analyze_button': "Analizar texto",
|
464 |
+
'repeated_words': "Palabras repetidas",
|
465 |
+
'legend': "Leyenda: Categorías gramaticales",
|
466 |
+
'arc_diagram': "An��lisis sintáctico: Diagrama de arco",
|
467 |
+
'sentence': "Oración",
|
468 |
+
'success_message': "Análisis guardado correctamente.",
|
469 |
+
'error_message': "Hubo un problema al guardar el análisis. Por favor, inténtelo de nuevo.",
|
470 |
+
'warning_message': "Por favor, ingrese un texto para analizar.",
|
471 |
+
'initial_message': "Ingrese un texto y presione 'Analizar texto' para comenzar.",
|
472 |
+
'no_results': "No hay resultados disponibles. Por favor, realice un análisis primero.",
|
473 |
+
'pos_analysis': "Análisis de categorías gramaticales",
|
474 |
+
'morphological_analysis': "Análisis morfológico",
|
475 |
+
'sentence_structure': "Estructura de oraciones",
|
476 |
+
'word': "Palabra",
|
477 |
+
'count': "Cantidad",
|
478 |
+
'percentage': "Porcentaje",
|
479 |
+
'examples': "Ejemplos",
|
480 |
+
'lemma': "Lema",
|
481 |
+
'tag': "Etiqueta",
|
482 |
+
'dep': "Dependencia",
|
483 |
+
'morph': "Morfología",
|
484 |
+
'root': "Raíz",
|
485 |
+
'subjects': "Sujetos",
|
486 |
+
'objects': "Objetos",
|
487 |
+
'verbs': "Verbos",
|
488 |
+
'grammatical_category': "Categoría gramatical",
|
489 |
+
'dependency': "Dependencia",
|
490 |
+
'morphology': "Morfología"
|
491 |
+
},
|
492 |
+
'en': {
|
493 |
+
'title': "AIdeaText - Morphological and Syntactic Analysis",
|
494 |
+
'input_label': "Enter a text to analyze (max 5,000 words):",
|
495 |
+
'input_placeholder': "This functionality will help you with two competencies:\n"
|
496 |
+
"[1] \"Write various types of texts in your native language\"\n"
|
497 |
+
"[2] \"Read various types of written texts in your native language\"\n\n"
|
498 |
+
"Enter your text here to analyze...",
|
499 |
+
'analyze_button': "Analyze text",
|
500 |
+
'repeated_words': "Repeated words",
|
501 |
+
'legend': "Legend: Grammatical categories",
|
502 |
+
'arc_diagram': "Syntactic analysis: Arc diagram",
|
503 |
+
'sentence': "Sentence",
|
504 |
+
'success_message': "Analysis saved successfully.",
|
505 |
+
'error_message': "There was a problem saving the analysis. Please try again.",
|
506 |
+
'warning_message': "Please enter a text to analyze.",
|
507 |
+
'initial_message': "Enter a text and press 'Analyze text' to start.",
|
508 |
+
'no_results': "No results available. Please perform an analysis first.",
|
509 |
+
'pos_analysis': "Part of Speech Analysis",
|
510 |
+
'morphological_analysis': "Morphological Analysis",
|
511 |
+
'sentence_structure': "Sentence Structure",
|
512 |
+
'word': "Word",
|
513 |
+
'count': "Count",
|
514 |
+
'percentage': "Percentage",
|
515 |
+
'examples': "Examples",
|
516 |
+
'lemma': "Lemma",
|
517 |
+
'tag': "Tag",
|
518 |
+
'dep': "Dependency",
|
519 |
+
'morph': "Morphology",
|
520 |
+
'root': "Root",
|
521 |
+
'subjects': "Subjects",
|
522 |
+
'objects': "Objects",
|
523 |
+
'verbs': "Verbs",
|
524 |
+
'grammatical_category': "Grammatical category",
|
525 |
+
'dependency': "Dependency",
|
526 |
+
'morphology': "Morphology"
|
527 |
+
},
|
528 |
+
'fr': {
|
529 |
+
'title': "AIdeaText - Analyse morphologique et syntaxique",
|
530 |
+
'input_label': "Entrez un texte à analyser (max 5 000 mots) :",
|
531 |
+
'input_placeholder': "Cette fonctionnalité vous aidera avec deux compétences :\n"
|
532 |
+
"[1] \"Écrire divers types de textes dans votre langue maternelle\"\n"
|
533 |
+
"[2] \"Lire divers types de textes écrits dans votre langue maternelle\"\n\n"
|
534 |
+
"Entrez votre texte ici pour l'analyser...",
|
535 |
+
'analyze_button': "Analyser le texte",
|
536 |
+
'repeated_words': "Mots répétés",
|
537 |
+
'legend': "Légende : Catégories grammaticales",
|
538 |
+
'arc_diagram': "Analyse syntaxique : Diagramme en arc",
|
539 |
+
'sentence': "Phrase",
|
540 |
+
'success_message': "Analyse enregistrée avec succès.",
|
541 |
+
'error_message': "Un problème est survenu lors de l'enregistrement de l'analyse. Veuillez réessayer.",
|
542 |
+
'warning_message': "Veuillez entrer un texte à analyser.",
|
543 |
+
'initial_message': "Entrez un texte et appuyez sur 'Analyser le texte' pour commencer.",
|
544 |
+
'no_results': "Aucun résultat disponible. Veuillez d'abord effectuer une analyse.",
|
545 |
+
'pos_analysis': "Analyse des parties du discours",
|
546 |
+
'morphological_analysis': "Analyse morphologique",
|
547 |
+
'sentence_structure': "Structure des phrases",
|
548 |
+
'word': "Mot",
|
549 |
+
'count': "Nombre",
|
550 |
+
'percentage': "Pourcentage",
|
551 |
+
'examples': "Exemples",
|
552 |
+
'lemma': "Lemme",
|
553 |
+
'tag': "Étiquette",
|
554 |
+
'dep': "Dépendance",
|
555 |
+
'morph': "Morphologie",
|
556 |
+
'root': "Racine",
|
557 |
+
'subjects': "Sujets",
|
558 |
+
'objects': "Objets",
|
559 |
+
'verbs': "Verbes",
|
560 |
+
'grammatical_category': "Catégorie grammaticale",
|
561 |
+
'dependency': "Dépendance",
|
562 |
+
'morphology': "Morphologie"
|
563 |
+
}
|
564 |
+
}
|
565 |
+
|
566 |
+
t = translations[lang_code]
|
567 |
+
|
568 |
+
input_key = f"morphosyntax_input_{lang_code}"
|
569 |
+
|
570 |
+
if input_key not in st.session_state:
|
571 |
+
st.session_state[input_key] = ""
|
572 |
+
|
573 |
+
sentence_input = st.text_area(
|
574 |
+
t['input_label'],
|
575 |
+
height=150,
|
576 |
+
placeholder=t['input_placeholder'],
|
577 |
+
value=st.session_state[input_key],
|
578 |
+
key=f"text_area_{lang_code}",
|
579 |
+
on_change=lambda: setattr(st.session_state, input_key, st.session_state[f"text_area_{lang_code}"])
|
580 |
+
)
|
581 |
+
|
582 |
+
if st.button(t['analyze_button'], key=f"analyze_button_{lang_code}"):
|
583 |
+
current_input = st.session_state[input_key]
|
584 |
+
if current_input:
|
585 |
+
doc = nlp_models[lang_code](current_input)
|
586 |
+
|
587 |
+
# Análisis morfosintáctico avanzado
|
588 |
+
advanced_analysis = perform_advanced_morphosyntactic_analysis(current_input, nlp_models[lang_code])
|
589 |
+
|
590 |
+
# Guardar el resultado en el estado de la sesión
|
591 |
+
st.session_state.morphosyntax_result = {
|
592 |
+
'doc': doc,
|
593 |
+
'advanced_analysis': advanced_analysis
|
594 |
+
}
|
595 |
+
|
596 |
+
# Mostrar resultados
|
597 |
+
display_morphosyntax_results(st.session_state.morphosyntax_result, lang_code, t)
|
598 |
+
|
599 |
+
# Guardar resultados
|
600 |
+
if store_morphosyntax_result(
|
601 |
+
st.session_state.username,
|
602 |
+
current_input,
|
603 |
+
get_repeated_words_colors(doc),
|
604 |
+
advanced_analysis['arc_diagram'],
|
605 |
+
advanced_analysis['pos_analysis'],
|
606 |
+
advanced_analysis['morphological_analysis'],
|
607 |
+
advanced_analysis['sentence_structure']
|
608 |
+
):
|
609 |
+
st.success(t['success_message'])
|
610 |
+
else:
|
611 |
+
st.error(t['error_message'])
|
612 |
+
else:
|
613 |
+
st.warning(t['warning_message'])
|
614 |
+
elif 'morphosyntax_result' in st.session_state and st.session_state.morphosyntax_result is not None:
|
615 |
+
|
616 |
+
# Si hay un resultado guardado, mostrarlo
|
617 |
+
display_morphosyntax_results(st.session_state.morphosyntax_result, lang_code, t)
|
618 |
+
else:
|
619 |
+
st.info(t['initial_message']) # Añade esta traducción a tu diccionario
|
620 |
+
|
621 |
+
def display_morphosyntax_results(result, lang_code, t):
|
622 |
+
if result is None:
|
623 |
+
st.warning(t['no_results']) # Añade esta traducción a tu diccionario
|
624 |
+
return
|
625 |
+
|
626 |
+
doc = result['doc']
|
627 |
+
advanced_analysis = result['advanced_analysis']
|
628 |
+
|
629 |
+
# Mostrar leyenda (código existente)
|
630 |
+
st.markdown(f"##### {t['legend']}")
|
631 |
+
legend_html = "<div style='display: flex; flex-wrap: wrap;'>"
|
632 |
+
for pos, color in POS_COLORS.items():
|
633 |
+
if pos in POS_TRANSLATIONS[lang_code]:
|
634 |
+
legend_html += f"<div style='margin-right: 10px;'><span style='background-color: {color}; padding: 2px 5px;'>{POS_TRANSLATIONS[lang_code][pos]}</span></div>"
|
635 |
+
legend_html += "</div>"
|
636 |
+
st.markdown(legend_html, unsafe_allow_html=True)
|
637 |
+
|
638 |
+
# Mostrar análisis de palabras repetidas (código existente)
|
639 |
+
word_colors = get_repeated_words_colors(doc)
|
640 |
+
with st.expander(t['repeated_words'], expanded=True):
|
641 |
+
highlighted_text = highlight_repeated_words(doc, word_colors)
|
642 |
+
st.markdown(highlighted_text, unsafe_allow_html=True)
|
643 |
+
|
644 |
+
# Mostrar estructura de oraciones
|
645 |
+
with st.expander(t['sentence_structure'], expanded=True):
|
646 |
+
for i, sent_analysis in enumerate(advanced_analysis['sentence_structure']):
|
647 |
+
sentence_str = (
|
648 |
+
f"**{t['sentence']} {i+1}** "
|
649 |
+
f"{t['root']}: {sent_analysis['root']} ({sent_analysis['root_pos']}) -- "
|
650 |
+
f"{t['subjects']}: {', '.join(sent_analysis['subjects'])} -- "
|
651 |
+
f"{t['objects']}: {', '.join(sent_analysis['objects'])} -- "
|
652 |
+
f"{t['verbs']}: {', '.join(sent_analysis['verbs'])}"
|
653 |
+
)
|
654 |
+
st.markdown(sentence_str)
|
655 |
+
|
656 |
+
# Mostrar análisis de categorías gramaticales # Mostrar análisis morfológico
|
657 |
+
col1, col2 = st.columns(2)
|
658 |
+
|
659 |
+
with col1:
|
660 |
+
with st.expander(t['pos_analysis'], expanded=True):
|
661 |
+
pos_df = pd.DataFrame(advanced_analysis['pos_analysis'])
|
662 |
+
|
663 |
+
# Traducir las etiquetas POS a sus nombres en el idioma seleccionado
|
664 |
+
pos_df['pos'] = pos_df['pos'].map(lambda x: POS_TRANSLATIONS[lang_code].get(x, x))
|
665 |
+
|
666 |
+
# Renombrar las columnas para mayor claridad
|
667 |
+
pos_df = pos_df.rename(columns={
|
668 |
+
'pos': t['grammatical_category'],
|
669 |
+
'count': t['count'],
|
670 |
+
'percentage': t['percentage'],
|
671 |
+
'examples': t['examples']
|
672 |
+
})
|
673 |
+
|
674 |
+
# Mostrar el dataframe
|
675 |
+
st.dataframe(pos_df)
|
676 |
+
|
677 |
+
with col2:
|
678 |
+
with st.expander(t['morphological_analysis'], expanded=True):
|
679 |
+
morph_df = pd.DataFrame(advanced_analysis['morphological_analysis'])
|
680 |
+
|
681 |
+
# Definir el mapeo de columnas
|
682 |
+
column_mapping = {
|
683 |
+
'text': t['word'],
|
684 |
+
'lemma': t['lemma'],
|
685 |
+
'pos': t['grammatical_category'],
|
686 |
+
'dep': t['dependency'],
|
687 |
+
'morph': t['morphology']
|
688 |
+
}
|
689 |
+
|
690 |
+
# Renombrar las columnas existentes
|
691 |
+
morph_df = morph_df.rename(columns={col: new_name for col, new_name in column_mapping.items() if col in morph_df.columns})
|
692 |
+
|
693 |
+
# Traducir las categorías gramaticales
|
694 |
+
morph_df[t['grammatical_category']] = morph_df[t['grammatical_category']].map(lambda x: POS_TRANSLATIONS[lang_code].get(x, x))
|
695 |
+
|
696 |
+
# Traducir las dependencias
|
697 |
+
dep_translations = {
|
698 |
+
'es': {
|
699 |
+
'ROOT': 'RAÍZ', 'nsubj': 'sujeto nominal', 'obj': 'objeto', 'iobj': 'objeto indirecto',
|
700 |
+
'csubj': 'sujeto clausal', 'ccomp': 'complemento clausal', 'xcomp': 'complemento clausal abierto',
|
701 |
+
'obl': 'oblicuo', 'vocative': 'vocativo', 'expl': 'expletivo', 'dislocated': 'dislocado',
|
702 |
+
'advcl': 'cláusula adverbial', 'advmod': 'modificador adverbial', 'discourse': 'discurso',
|
703 |
+
'aux': 'auxiliar', 'cop': 'cópula', 'mark': 'marcador', 'nmod': 'modificador nominal',
|
704 |
+
'appos': 'aposición', 'nummod': 'modificador numeral', 'acl': 'cláusula adjetiva',
|
705 |
+
'amod': 'modificador adjetival', 'det': 'determinante', 'clf': 'clasificador',
|
706 |
+
'case': 'caso', 'conj': 'conjunción', 'cc': 'coordinante', 'fixed': 'fijo',
|
707 |
+
'flat': 'plano', 'compound': 'compuesto', 'list': 'lista', 'parataxis': 'parataxis',
|
708 |
+
'orphan': 'huérfano', 'goeswith': 'va con', 'reparandum': 'reparación', 'punct': 'puntuación'
|
709 |
+
},
|
710 |
+
'en': {
|
711 |
+
'ROOT': 'ROOT', 'nsubj': 'nominal subject', 'obj': 'object',
|
712 |
+
'iobj': 'indirect object', 'csubj': 'clausal subject', 'ccomp': 'clausal complement', 'xcomp': 'open clausal complement',
|
713 |
+
'obl': 'oblique', 'vocative': 'vocative', 'expl': 'expletive', 'dislocated': 'dislocated', 'advcl': 'adverbial clause modifier',
|
714 |
+
'advmod': 'adverbial modifier', 'discourse': 'discourse element', 'aux': 'auxiliary', 'cop': 'copula', 'mark': 'marker',
|
715 |
+
'nmod': 'nominal modifier', 'appos': 'appositional modifier', 'nummod': 'numeric modifier', 'acl': 'clausal modifier of noun',
|
716 |
+
'amod': 'adjectival modifier', 'det': 'determiner', 'clf': 'classifier', 'case': 'case marking',
|
717 |
+
'conj': 'conjunct', 'cc': 'coordinating conjunction', 'fixed': 'fixed multiword expression',
|
718 |
+
'flat': 'flat multiword expression', 'compound': 'compound', 'list': 'list', 'parataxis': 'parataxis', 'orphan': 'orphan',
|
719 |
+
'goeswith': 'goes with', 'reparandum': 'reparandum', 'punct': 'punctuation'
|
720 |
+
},
|
721 |
+
'fr': {
|
722 |
+
'ROOT': 'RACINE', 'nsubj': 'sujet nominal', 'obj': 'objet', 'iobj': 'objet indirect',
|
723 |
+
'csubj': 'sujet phrastique', 'ccomp': 'complément phrastique', 'xcomp': 'complément phrastique ouvert', 'obl': 'oblique',
|
724 |
+
'vocative': 'vocatif', 'expl': 'explétif', 'dislocated': 'disloqué', 'advcl': 'clause adverbiale', 'advmod': 'modifieur adverbial',
|
725 |
+
'discourse': 'élément de discours', 'aux': 'auxiliaire', 'cop': 'copule', 'mark': 'marqueur', 'nmod': 'modifieur nominal',
|
726 |
+
'appos': 'apposition', 'nummod': 'modifieur numéral', 'acl': 'clause relative', 'amod': 'modifieur adjectival', 'det': 'déterminant',
|
727 |
+
'clf': 'classificateur', 'case': 'marqueur de cas', 'conj': 'conjonction', 'cc': 'coordination', 'fixed': 'expression figée',
|
728 |
+
'flat': 'construction plate', 'compound': 'composé', 'list': 'liste', 'parataxis': 'parataxe', 'orphan': 'orphelin',
|
729 |
+
'goeswith': 'va avec', 'reparandum': 'réparation', 'punct': 'ponctuation'
|
730 |
+
}
|
731 |
+
}
|
732 |
+
morph_df[t['dependency']] = morph_df[t['dependency']].map(lambda x: dep_translations[lang_code].get(x, x))
|
733 |
+
|
734 |
+
# Traducir la morfología
|
735 |
+
def translate_morph(morph_string, lang_code):
|
736 |
+
morph_translations = {
|
737 |
+
'es': {
|
738 |
+
'Gender': 'Género', 'Number': 'Número', 'Case': 'Caso', 'Definite': 'Definido',
|
739 |
+
'PronType': 'Tipo de Pronombre', 'Person': 'Persona', 'Mood': 'Modo',
|
740 |
+
'Tense': 'Tiempo', 'VerbForm': 'Forma Verbal', 'Voice': 'Voz',
|
741 |
+
'Fem': 'Femenino', 'Masc': 'Masculino', 'Sing': 'Singular', 'Plur': 'Plural',
|
742 |
+
'Ind': 'Indicativo', 'Sub': 'Subjuntivo', 'Imp': 'Imperativo', 'Inf': 'Infinitivo',
|
743 |
+
'Part': 'Participio', 'Ger': 'Gerundio', 'Pres': 'Presente', 'Past': 'Pasado',
|
744 |
+
'Fut': 'Futuro', 'Perf': 'Perfecto', 'Imp': 'Imperfecto'
|
745 |
+
},
|
746 |
+
'en': {
|
747 |
+
'Gender': 'Gender', 'Number': 'Number', 'Case': 'Case', 'Definite': 'Definite', 'PronType': 'Pronoun Type', 'Person': 'Person',
|
748 |
+
'Mood': 'Mood', 'Tense': 'Tense', 'VerbForm': 'Verb Form', 'Voice': 'Voice',
|
749 |
+
'Fem': 'Feminine', 'Masc': 'Masculine', 'Sing': 'Singular', 'Plur': 'Plural', 'Ind': 'Indicative',
|
750 |
+
'Sub': 'Subjunctive', 'Imp': 'Imperative', 'Inf': 'Infinitive', 'Part': 'Participle',
|
751 |
+
'Ger': 'Gerund', 'Pres': 'Present', 'Past': 'Past', 'Fut': 'Future', 'Perf': 'Perfect', 'Imp': 'Imperfect'
|
752 |
+
},
|
753 |
+
'fr': {
|
754 |
+
'Gender': 'Genre', 'Number': 'Nombre', 'Case': 'Cas', 'Definite': 'Défini', 'PronType': 'Type de Pronom',
|
755 |
+
'Person': 'Personne', 'Mood': 'Mode', 'Tense': 'Temps', 'VerbForm': 'Forme Verbale', 'Voice': 'Voix',
|
756 |
+
'Fem': 'Féminin', 'Masc': 'Masculin', 'Sing': 'Singulier', 'Plur': 'Pluriel', 'Ind': 'Indicatif',
|
757 |
+
'Sub': 'Subjonctif', 'Imp': 'Impératif', 'Inf': 'Infinitif', 'Part': 'Participe',
|
758 |
+
'Ger': 'Gérondif', 'Pres': 'Présent', 'Past': 'Passé', 'Fut': 'Futur', 'Perf': 'Parfait', 'Imp': 'Imparfait'
|
759 |
+
}
|
760 |
+
}
|
761 |
+
for key, value in morph_translations[lang_code].items():
|
762 |
+
morph_string = morph_string.replace(key, value)
|
763 |
+
return morph_string
|
764 |
+
|
765 |
+
morph_df[t['morphology']] = morph_df[t['morphology']].apply(lambda x: translate_morph(x, lang_code))
|
766 |
+
|
767 |
+
# Seleccionar y ordenar las columnas a mostrar
|
768 |
+
columns_to_display = [t['word'], t['lemma'], t['grammatical_category'], t['dependency'], t['morphology']]
|
769 |
+
columns_to_display = [col for col in columns_to_display if col in morph_df.columns]
|
770 |
+
|
771 |
+
# Mostrar el DataFrame
|
772 |
+
st.dataframe(morph_df[columns_to_display])
|
773 |
+
|
774 |
+
# Mostrar diagramas de arco (código existente)
|
775 |
+
with st.expander(t['arc_diagram'], expanded=True):
|
776 |
+
sentences = list(doc.sents)
|
777 |
+
arc_diagrams = []
|
778 |
+
for i, sent in enumerate(sentences):
|
779 |
+
st.subheader(f"{t['sentence']} {i+1}")
|
780 |
+
html = displacy.render(sent, style="dep", options={"distance": 100})
|
781 |
+
html = html.replace('height="375"', 'height="200"')
|
782 |
+
html = re.sub(r'<svg[^>]*>', lambda m: m.group(0).replace('height="450"', 'height="300"'), html)
|
783 |
+
html = re.sub(r'<g [^>]*transform="translate\((\d+),(\d+)\)"', lambda m: f'<g transform="translate({m.group(1)},50)"', html)
|
784 |
+
st.write(html, unsafe_allow_html=True)
|
785 |
+
arc_diagrams.append(html)
|
786 |
+
|
787 |
+
###############################################################################################################
|
788 |
+
def display_semantic_analysis_interface(nlp_models, lang_code):
|
789 |
+
translations = {
|
790 |
+
'es': {
|
791 |
+
'title': "AIdeaText - Análisis semántico",
|
792 |
+
'text_input_label': "Ingrese un texto para analizar (máx. 5,000 palabras):",
|
793 |
+
'text_input_placeholder': "El objetivo de esta aplicación es que mejore sus habilidades de redacción...",
|
794 |
+
'file_uploader': "O cargue un archivo de texto",
|
795 |
+
'analyze_button': "Analizar texto",
|
796 |
+
'conceptual_relations': "Relaciones Conceptuales",
|
797 |
+
'identified_entities': "Entidades Identificadas",
|
798 |
+
'key_concepts': "Conceptos Clave",
|
799 |
+
'success_message': "Análisis semántico guardado correctamente.",
|
800 |
+
'error_message': "Hubo un problema al guardar el análisis semántico. Por favor, inténtelo de nuevo.",
|
801 |
+
'warning_message': "Por favor, ingrese un texto o cargue un archivo para analizar.",
|
802 |
+
'initial_message': "Ingrese un texto y presione 'Analizar texto' para comenzar.",
|
803 |
+
'no_results': "No hay resultados disponibles. Por favor, realice un análisis primero."
|
804 |
+
},
|
805 |
+
'en': {
|
806 |
+
'title': "AIdeaText - Semantic Analysis",
|
807 |
+
'text_input_label': "Enter a text to analyze (max. 5,000 words):",
|
808 |
+
'text_input_placeholder': "The goal of this application is to improve your writing skills...",
|
809 |
+
'file_uploader': "Or upload a text file",
|
810 |
+
'analyze_button': "Analyze text",
|
811 |
+
'conceptual_relations': "Conceptual Relations",
|
812 |
+
'identified_entities': "Identified Entities",
|
813 |
+
'key_concepts': "Key Concepts",
|
814 |
+
'success_message': "Semantic analysis saved successfully.",
|
815 |
+
'error_message': "There was a problem saving the semantic analysis. Please try again.",
|
816 |
+
'warning_message': "Please enter a text or upload a file to analyze.",
|
817 |
+
'initial_message': "Enter a text and press 'Analyze text' to start.",
|
818 |
+
'no_results': "No results available. Please perform an analysis first."
|
819 |
+
},
|
820 |
+
'fr': {
|
821 |
+
'title': "AIdeaText - Analyse sémantique",
|
822 |
+
'text_input_label': "Entrez un texte à analyser (max. 5 000 mots) :",
|
823 |
+
'text_input_placeholder': "L'objectif de cette application est d'améliorer vos compétences en rédaction...",
|
824 |
+
'file_uploader': "Ou téléchargez un fichier texte",
|
825 |
+
'analyze_button': "Analyser le texte",
|
826 |
+
'conceptual_relations': "Relations Conceptuelles",
|
827 |
+
'identified_entities': "Entités Identifiées",
|
828 |
+
'key_concepts': "Concepts Clés",
|
829 |
+
'success_message': "Analyse sémantique enregistrée avec succès.",
|
830 |
+
'error_message': "Un problème est survenu lors de l'enregistrement de l'analyse sémantique. Veuillez réessayer.",
|
831 |
+
'warning_message': "Veuillez entrer un texte ou télécharger un fichier à analyser.",
|
832 |
+
'initial_message': "Entrez un texte et appuyez sur 'Analyser le texte' pour commencer.",
|
833 |
+
'no_results': "Aucun résultat disponible. Veuillez d'abord effectuer une analyse."
|
834 |
+
}
|
835 |
+
}
|
836 |
+
|
837 |
+
t = translations[lang_code]
|
838 |
+
|
839 |
+
st.header(t['title'])
|
840 |
+
|
841 |
+
# Opción para introducir texto
|
842 |
+
text_input = st.text_area(
|
843 |
+
t['text_input_label'],
|
844 |
+
height=150,
|
845 |
+
placeholder=t['text_input_placeholder'],
|
846 |
+
)
|
847 |
+
|
848 |
+
# Opción para cargar archivo
|
849 |
+
uploaded_file = st.file_uploader(t['file_uploader'], type=['txt'])
|
850 |
+
|
851 |
+
if st.button(t['analyze_button']):
|
852 |
+
if text_input or uploaded_file is not None:
|
853 |
+
if uploaded_file:
|
854 |
+
text_content = uploaded_file.getvalue().decode('utf-8')
|
855 |
+
else:
|
856 |
+
text_content = text_input
|
857 |
+
|
858 |
+
# Realizar el análisis
|
859 |
+
analysis_result = perform_semantic_analysis(text_content, nlp_models[lang_code], lang_code)
|
860 |
+
|
861 |
+
# Guardar el resultado en el estado de la sesión
|
862 |
+
st.session_state.semantic_result = analysis_result
|
863 |
+
|
864 |
+
# Mostrar resultados
|
865 |
+
display_semantic_results(st.session_state.semantic_result, lang_code, t)
|
866 |
+
|
867 |
+
# Guardar el resultado del análisis
|
868 |
+
if store_semantic_result(st.session_state.username, text_content, analysis_result):
|
869 |
+
st.success(t['success_message'])
|
870 |
+
else:
|
871 |
+
st.error(t['error_message'])
|
872 |
+
else:
|
873 |
+
st.warning(t['warning_message'])
|
874 |
+
|
875 |
+
elif 'semantic_result' in st.session_state:
|
876 |
+
|
877 |
+
# Si hay un resultado guardado, mostrarlo
|
878 |
+
display_semantic_results(st.session_state.semantic_result, lang_code, t)
|
879 |
+
|
880 |
+
else:
|
881 |
+
st.info(t['initial_message']) # Asegúrate de que 'initial_message' esté en tus traducciones
|
882 |
+
|
883 |
+
def display_semantic_results(result, lang_code, t):
|
884 |
+
if result is None:
|
885 |
+
st.warning(t['no_results']) # Asegúrate de que 'no_results' esté en tus traducciones
|
886 |
+
return
|
887 |
+
|
888 |
+
# Mostrar conceptos clave
|
889 |
+
with st.expander(t['key_concepts'], expanded=True):
|
890 |
+
concept_text = " | ".join([f"{concept} ({frequency:.2f})" for concept, frequency in result['key_concepts']])
|
891 |
+
st.write(concept_text)
|
892 |
+
|
893 |
+
# Mostrar el gráfico de relaciones conceptuales
|
894 |
+
with st.expander(t['conceptual_relations'], expanded=True):
|
895 |
+
st.pyplot(result['relations_graph'])
|
896 |
+
|
897 |
+
##################################################################################################
|
898 |
+
def display_discourse_analysis_interface(nlp_models, lang_code):
|
899 |
+
translations = {
|
900 |
+
'es': {
|
901 |
+
'title': "AIdeaText - Análisis del discurso",
|
902 |
+
'file_uploader1': "Cargar archivo de texto 1 (Patrón)",
|
903 |
+
'file_uploader2': "Cargar archivo de texto 2 (Comparación)",
|
904 |
+
'analyze_button': "Analizar textos",
|
905 |
+
'comparison': "Comparación de Relaciones Semánticas",
|
906 |
+
'success_message': "Análisis del discurso guardado correctamente.",
|
907 |
+
'error_message': "Hubo un problema al guardar el análisis del discurso. Por favor, inténtelo de nuevo.",
|
908 |
+
'warning_message': "Por favor, cargue ambos archivos para analizar.",
|
909 |
+
'initial_message': "Ingrese un texto y presione 'Analizar texto' para comenzar.",
|
910 |
+
'no_results': "No hay resultados disponibles. Por favor, realice un análisis primero.",
|
911 |
+
'key_concepts': "Conceptos Clave",
|
912 |
+
'graph_not_available': "El gráfico no está disponible.",
|
913 |
+
'concepts_not_available': "Los conceptos clave no están disponibles.",
|
914 |
+
'comparison_not_available': "La comparación no está disponible."
|
915 |
+
},
|
916 |
+
'en': {
|
917 |
+
'title': "AIdeaText - Discourse Analysis",
|
918 |
+
'file_uploader1': "Upload text file 1 (Pattern)",
|
919 |
+
'file_uploader2': "Upload text file 2 (Comparison)",
|
920 |
+
'analyze_button': "Analyze texts",
|
921 |
+
'comparison': "Comparison of Semantic Relations",
|
922 |
+
'success_message': "Discourse analysis saved successfully.",
|
923 |
+
'error_message': "There was a problem saving the discourse analysis. Please try again.",
|
924 |
+
'warning_message': "Please upload both files to analyze.",
|
925 |
+
'initial_message': "Enter a text and press 'Analyze text' to start.",
|
926 |
+
'no_results': "No results available. Please perform an analysis first.",
|
927 |
+
'key_concepts': "Key Concepts",
|
928 |
+
'graph_not_available': "The graph is not available.",
|
929 |
+
'concepts_not_available': "Key concepts are not available.",
|
930 |
+
'comparison_not_available': "The comparison is not available."
|
931 |
+
},
|
932 |
+
'fr': {
|
933 |
+
'title': "AIdeaText - Analyse du discours",
|
934 |
+
'file_uploader1': "Télécharger le fichier texte 1 (Modèle)",
|
935 |
+
'file_uploader2': "Télécharger le fichier texte 2 (Comparaison)",
|
936 |
+
'analyze_button': "Analyser les textes",
|
937 |
+
'comparison': "Comparaison des Relations Sémantiques",
|
938 |
+
'success_message': "Analyse du discours enregistrée avec succès.",
|
939 |
+
'error_message': "Un problème est survenu lors de l'enregistrement de l'analyse du discours. Veuillez réessayer.",
|
940 |
+
'warning_message': "Veuillez télécharger les deux fichiers à analyser.",
|
941 |
+
'initial_message': "Entrez un texte et appuyez sur 'Analyser le texte' pour commencer.",
|
942 |
+
'no_results': "Aucun résultat disponible. Veuillez d'abord effectuer une analyse.",
|
943 |
+
'key_concepts': "Concepts Clés",
|
944 |
+
'graph_not_available': "Le graphique n'est pas disponible.",
|
945 |
+
'concepts_not_available': "Les concepts clés ne sont pas disponibles.",
|
946 |
+
'comparison_not_available': "La comparaison n'est pas disponible."
|
947 |
+
}
|
948 |
+
}
|
949 |
+
|
950 |
+
t = translations[lang_code]
|
951 |
+
st.header(t['title'])
|
952 |
+
|
953 |
+
col1, col2 = st.columns(2)
|
954 |
+
with col1:
|
955 |
+
uploaded_file1 = st.file_uploader(t['file_uploader1'], type=['txt'])
|
956 |
+
with col2:
|
957 |
+
uploaded_file2 = st.file_uploader(t['file_uploader2'], type=['txt'])
|
958 |
+
|
959 |
+
if st.button(t['analyze_button']):
|
960 |
+
if uploaded_file1 is not None and uploaded_file2 is not None:
|
961 |
+
text_content1 = uploaded_file1.getvalue().decode('utf-8')
|
962 |
+
text_content2 = uploaded_file2.getvalue().decode('utf-8')
|
963 |
+
|
964 |
+
# Realizar el análisis
|
965 |
+
analysis_result = perform_discourse_analysis(text_content1, text_content2, nlp_models[lang_code], lang_code)
|
966 |
+
|
967 |
+
# Guardar el resultado en el estado de la sesión
|
968 |
+
st.session_state.discourse_result = analysis_result
|
969 |
+
|
970 |
+
# Mostrar los resultados del análisis
|
971 |
+
display_discourse_results(st.session_state.discourse_result, lang_code, t)
|
972 |
+
|
973 |
+
# Guardar el resultado del análisis
|
974 |
+
if store_discourse_analysis_result(st.session_state.username, text_content1, text_content2, analysis_result):
|
975 |
+
st.success(t['success_message'])
|
976 |
+
else:
|
977 |
+
st.error(t['error_message'])
|
978 |
+
else:
|
979 |
+
st.warning(t['warning_message'])
|
980 |
+
elif 'discourse_result' in st.session_state and st.session_state.discourse_result is not None:
|
981 |
+
# Si hay un resultado guardado, mostrarlo
|
982 |
+
display_discourse_results(st.session_state.discourse_result, lang_code, t)
|
983 |
+
else:
|
984 |
+
st.info(t['initial_message']) # Asegúrate de que 'initial_message' esté en tus traducciones
|
985 |
+
|
986 |
+
#################################################
|
987 |
+
def display_discourse_results(result, lang_code, t):
|
988 |
+
if result is None:
|
989 |
+
st.warning(t.get('no_results', "No hay resultados disponibles."))
|
990 |
+
return
|
991 |
+
|
992 |
+
def clean_and_convert(value):
|
993 |
+
if isinstance(value, (int, float)):
|
994 |
+
return float(value)
|
995 |
+
elif isinstance(value, str):
|
996 |
+
try:
|
997 |
+
return float(value.replace(',', '.'))
|
998 |
+
except ValueError:
|
999 |
+
return 0.0
|
1000 |
+
return 0.0
|
1001 |
+
|
1002 |
+
def process_key_concepts(key_concepts):
|
1003 |
+
df = pd.DataFrame(key_concepts, columns=['Concepto', 'Frecuencia'])
|
1004 |
+
df['Frecuencia'] = df['Frecuencia'].apply(clean_and_convert)
|
1005 |
+
return df
|
1006 |
+
|
1007 |
+
col1, col2 = st.columns(2)
|
1008 |
+
|
1009 |
+
with col1:
|
1010 |
+
with st.expander(t.get('file_uploader1', "Documento 1"), expanded=True):
|
1011 |
+
if 'graph1' in result:
|
1012 |
+
st.pyplot(result['graph1'])
|
1013 |
+
else:
|
1014 |
+
st.warning(t.get('graph_not_available', "El gráfico no está disponible."))
|
1015 |
+
st.subheader(t.get('key_concepts', "Conceptos Clave"))
|
1016 |
+
if 'key_concepts1' in result:
|
1017 |
+
df1 = process_key_concepts(result['key_concepts1'])
|
1018 |
+
st.table(df1)
|
1019 |
+
else:
|
1020 |
+
st.warning(t.get('concepts_not_available', "Los conceptos clave no están disponibles."))
|
1021 |
+
|
1022 |
+
with col2:
|
1023 |
+
with st.expander(t.get('file_uploader2', "Documento 2"), expanded=True):
|
1024 |
+
if 'graph2' in result:
|
1025 |
+
st.pyplot(result['graph2'])
|
1026 |
+
else:
|
1027 |
+
st.warning(t.get('graph_not_available', "El gráfico no está disponible."))
|
1028 |
+
st.subheader(t.get('key_concepts', "Conceptos Clave"))
|
1029 |
+
if 'key_concepts2' in result:
|
1030 |
+
df2 = process_key_concepts(result['key_concepts2'])
|
1031 |
+
st.table(df2)
|
1032 |
+
else:
|
1033 |
+
st.warning(t.get('concepts_not_available', "Los conceptos clave no están disponibles."))
|
1034 |
+
|
1035 |
+
# Comparación de conceptos clave
|
1036 |
+
st.subheader(t.get('comparison', "Comparación de conceptos entre ambos documentos"))
|
1037 |
+
if 'key_concepts1' in result and 'key_concepts2' in result:
|
1038 |
+
df1 = process_key_concepts(result['key_concepts1']).set_index('Concepto')
|
1039 |
+
df2 = process_key_concepts(result['key_concepts2']).set_index('Concepto')
|
1040 |
+
|
1041 |
+
df_comparison = pd.concat([df1, df2], axis=1, keys=[t.get('file_uploader1', "Documento 1"), t.get('file_uploader2', "Documento 2")])
|
1042 |
+
df_comparison = df_comparison.fillna(0.0)
|
1043 |
+
|
1044 |
+
# Asegurarse de que todas las columnas sean float
|
1045 |
+
for col in df_comparison.columns:
|
1046 |
+
df_comparison[col] = df_comparison[col].astype(float)
|
1047 |
+
|
1048 |
+
# Mostrar la tabla de comparación
|
1049 |
+
try:
|
1050 |
+
st.dataframe(df_comparison.style.format("{:.2f}"), width=1000)
|
1051 |
+
except Exception as e:
|
1052 |
+
st.error(f"Error al mostrar el DataFrame: {str(e)}")
|
1053 |
+
st.write("DataFrame sin formato:")
|
1054 |
+
st.write(df_comparison)
|
1055 |
+
else:
|
1056 |
+
st.warning(t.get('comparison_not_available', "La comparación no está disponible."))
|
1057 |
+
|
1058 |
+
# Aquí puedes agregar el código para mostrar los gráficos si es necesario
|
1059 |
+
|
1060 |
+
##################################################################################################
|
1061 |
+
#def display_saved_discourse_analysis(analysis_data):
|
1062 |
+
# img_bytes = base64.b64decode(analysis_data['combined_graph'])
|
1063 |
+
# img = plt.imread(io.BytesIO(img_bytes), format='png')
|
1064 |
+
|
1065 |
+
# st.image(img, use_column_width=True)
|
1066 |
+
# st.write("Texto del documento patrón:")
|
1067 |
+
# st.write(analysis_data['text1'])
|
1068 |
+
# st.write("Texto del documento comparado:")
|
1069 |
+
# st.write(analysis_data['text2'])
|
1070 |
+
|
1071 |
+
##################################################################################################
|
1072 |
+
def display_chatbot_interface(lang_code):
|
1073 |
+
translations = {
|
1074 |
+
'es': {
|
1075 |
+
'title': "Expertos en Vacaciones",
|
1076 |
+
'input_placeholder': "Escribe tu mensaje aquí...",
|
1077 |
+
'initial_message': "¡Hola! ¿Cómo podemos ayudarte?"
|
1078 |
+
},
|
1079 |
+
'en': {
|
1080 |
+
'title': "Vacation Experts",
|
1081 |
+
'input_placeholder': "Type your message here...",
|
1082 |
+
'initial_message': "Hi! How can we help you?"
|
1083 |
+
},
|
1084 |
+
'fr': {
|
1085 |
+
'title': "Experts en Vacances",
|
1086 |
+
'input_placeholder': "Écrivez votre message ici...",
|
1087 |
+
'initial_message': "Bonjour! Comment pouvons-nous vous aider?"
|
1088 |
+
}
|
1089 |
+
}
|
1090 |
+
t = translations[lang_code]
|
1091 |
+
st.title(t['title'])
|
1092 |
+
|
1093 |
+
if 'chatbot' not in st.session_state:
|
1094 |
+
st.session_state.chatbot = initialize_chatbot()
|
1095 |
+
if 'messages' not in st.session_state:
|
1096 |
+
st.session_state.messages = [{"role": "assistant", "content": t['initial_message']}]
|
1097 |
+
|
1098 |
+
# Contenedor principal para el chat
|
1099 |
+
chat_container = st.container()
|
1100 |
+
|
1101 |
+
# Mostrar mensajes existentes
|
1102 |
+
with chat_container:
|
1103 |
+
for message in st.session_state.messages:
|
1104 |
+
with st.chat_message(message["role"]):
|
1105 |
+
st.markdown(message["content"])
|
1106 |
+
|
1107 |
+
# Área de entrada del usuario
|
1108 |
+
user_input = st.chat_input(t['input_placeholder'])
|
1109 |
+
|
1110 |
+
if user_input:
|
1111 |
+
# Agregar mensaje del usuario
|
1112 |
+
st.session_state.messages.append({"role": "user", "content": user_input})
|
1113 |
+
|
1114 |
+
# Mostrar mensaje del usuario
|
1115 |
+
with chat_container:
|
1116 |
+
with st.chat_message("user"):
|
1117 |
+
st.markdown(user_input)
|
1118 |
+
|
1119 |
+
# Generar respuesta del chatbot
|
1120 |
+
with chat_container:
|
1121 |
+
with st.chat_message("assistant"):
|
1122 |
+
message_placeholder = st.empty()
|
1123 |
+
full_response = ""
|
1124 |
+
for chunk in get_chatbot_response(st.session_state.chatbot, user_input, lang_code):
|
1125 |
+
full_response += chunk
|
1126 |
+
message_placeholder.markdown(full_response + "▌")
|
1127 |
+
message_placeholder.markdown(full_response)
|
1128 |
+
|
1129 |
+
# Agregar respuesta del asistente a los mensajes
|
1130 |
+
st.session_state.messages.append({"role": "assistant", "content": full_response})
|
1131 |
+
|
1132 |
+
# Guardar la conversación en la base de datos
|
1133 |
+
try:
|
1134 |
+
store_chat_history(st.session_state.username, st.session_state.messages)
|
1135 |
+
st.success("Conversación guardada exitosamente")
|
1136 |
+
except Exception as e:
|
1137 |
+
st.error(f"Error al guardar la conversación: {str(e)}")
|
1138 |
+
logger.error(f"Error al guardar el historial de chat para {st.session_state.username}: {str(e)}")
|
1139 |
+
|
1140 |
+
# Scroll al final del chat
|
1141 |
+
st.markdown('<script>window.scrollTo(0,document.body.scrollHeight);</script>', unsafe_allow_html=True)
|
1142 |
+
|
1143 |
+
######################################################
|
1144 |
+
if __name__ == "__main__":
|
1145 |
+
main()
|
requirements.txt
CHANGED
@@ -9,6 +9,7 @@ https://huggingface.co/spacy/fr_core_news_lg/resolve/main/fr_core_news_lg-any-py
|
|
9 |
numpy
|
10 |
networkx
|
11 |
matplotlib
|
|
|
12 |
pydantic
|
13 |
pandas
|
14 |
pymssql
|
|
|
9 |
numpy
|
10 |
networkx
|
11 |
matplotlib
|
12 |
+
plotly
|
13 |
pydantic
|
14 |
pandas
|
15 |
pymssql
|