Upload 3 files
Browse files
modules/studentact/current_situation_analysis.py
CHANGED
@@ -1,1008 +1,1009 @@
|
|
1 |
-
#v3/modules/studentact/current_situation_analysis.py
|
2 |
-
|
3 |
-
import streamlit as st
|
4 |
-
import matplotlib.pyplot as plt
|
5 |
-
import networkx as nx
|
6 |
-
import seaborn as sns
|
7 |
-
from collections import Counter
|
8 |
-
from itertools import combinations
|
9 |
-
import numpy as np
|
10 |
-
import matplotlib.patches as patches
|
11 |
-
import logging
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
logging.
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
logging.
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
#
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
#
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
#
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
#
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
'
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
'
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
'
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
'
|
108 |
-
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
|
128 |
-
|
129 |
-
'
|
130 |
-
'
|
131 |
-
'
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
-
|
144 |
-
|
145 |
-
|
146 |
-
|
147 |
-
|
148 |
-
|
149 |
-
|
150 |
-
|
151 |
-
|
152 |
-
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
|
158 |
-
|
159 |
-
|
160 |
-
|
161 |
-
|
162 |
-
|
163 |
-
|
164 |
-
'
|
165 |
-
'
|
166 |
-
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
212 |
-
|
213 |
-
'
|
214 |
-
'
|
215 |
-
'
|
216 |
-
|
217 |
-
|
218 |
-
|
219 |
-
|
220 |
-
weights['
|
221 |
-
weights['
|
222 |
-
weights['
|
223 |
-
|
224 |
-
|
225 |
-
|
226 |
-
|
227 |
-
'
|
228 |
-
'
|
229 |
-
'
|
230 |
-
'
|
231 |
-
'
|
232 |
-
'
|
233 |
-
|
234 |
-
|
235 |
-
|
236 |
-
|
237 |
-
|
238 |
-
|
239 |
-
-
|
240 |
-
-
|
241 |
-
-
|
242 |
-
-
|
243 |
-
|
244 |
-
|
245 |
-
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
|
250 |
-
|
251 |
-
|
252 |
-
|
253 |
-
|
254 |
-
|
255 |
-
|
256 |
-
|
257 |
-
|
258 |
-
|
259 |
-
|
260 |
-
|
261 |
-
|
262 |
-
|
263 |
-
|
264 |
-
|
265 |
-
|
266 |
-
|
267 |
-
|
268 |
-
|
269 |
-
|
270 |
-
|
271 |
-
|
272 |
-
|
273 |
-
|
274 |
-
|
275 |
-
|
276 |
-
|
277 |
-
|
278 |
-
|
279 |
-
|
280 |
-
|
281 |
-
|
282 |
-
'
|
283 |
-
'
|
284 |
-
'
|
285 |
-
|
286 |
-
|
287 |
-
|
288 |
-
|
289 |
-
'
|
290 |
-
'
|
291 |
-
'
|
292 |
-
|
293 |
-
|
294 |
-
|
295 |
-
|
296 |
-
|
297 |
-
|
298 |
-
|
299 |
-
|
300 |
-
'
|
301 |
-
|
302 |
-
|
303 |
-
|
304 |
-
|
305 |
-
|
306 |
-
|
307 |
-
|
308 |
-
|
309 |
-
|
310 |
-
|
311 |
-
|
312 |
-
|
313 |
-
|
314 |
-
sentences
|
315 |
-
|
316 |
-
|
317 |
-
|
318 |
-
|
319 |
-
|
320 |
-
|
321 |
-
|
322 |
-
|
323 |
-
|
324 |
-
|
325 |
-
|
326 |
-
|
327 |
-
|
328 |
-
|
329 |
-
|
330 |
-
|
331 |
-
|
332 |
-
|
333 |
-
|
334 |
-
|
335 |
-
|
336 |
-
|
337 |
-
|
338 |
-
|
339 |
-
|
340 |
-
|
341 |
-
|
342 |
-
'
|
343 |
-
'
|
344 |
-
|
345 |
-
|
346 |
-
|
347 |
-
|
348 |
-
|
349 |
-
token.
|
350 |
-
|
351 |
-
|
352 |
-
|
353 |
-
|
354 |
-
|
355 |
-
|
356 |
-
|
357 |
-
|
358 |
-
|
359 |
-
|
360 |
-
|
361 |
-
|
362 |
-
|
363 |
-
|
364 |
-
|
365 |
-
|
366 |
-
'
|
367 |
-
|
368 |
-
|
369 |
-
|
370 |
-
|
371 |
-
weights['
|
372 |
-
|
373 |
-
|
374 |
-
|
375 |
-
|
376 |
-
|
377 |
-
|
378 |
-
- Conexiones
|
379 |
-
-
|
380 |
-
-
|
381 |
-
-
|
382 |
-
-
|
383 |
-
|
384 |
-
|
385 |
-
|
386 |
-
|
387 |
-
|
388 |
-
|
389 |
-
|
390 |
-
|
391 |
-
|
392 |
-
|
393 |
-
|
394 |
-
|
395 |
-
|
396 |
-
|
397 |
-
|
398 |
-
|
399 |
-
|
400 |
-
|
401 |
-
result
|
402 |
-
|
403 |
-
|
404 |
-
|
405 |
-
|
406 |
-
|
407 |
-
|
408 |
-
|
409 |
-
|
410 |
-
|
411 |
-
|
412 |
-
|
413 |
-
|
414 |
-
|
415 |
-
|
416 |
-
|
417 |
-
|
418 |
-
|
419 |
-
|
420 |
-
|
421 |
-
|
422 |
-
|
423 |
-
|
424 |
-
|
425 |
-
|
426 |
-
-
|
427 |
-
-
|
428 |
-
|
429 |
-
|
430 |
-
|
431 |
-
|
432 |
-
|
433 |
-
|
434 |
-
|
435 |
-
|
436 |
-
'
|
437 |
-
'
|
438 |
-
|
439 |
-
|
440 |
-
|
441 |
-
|
442 |
-
|
443 |
-
|
444 |
-
|
445 |
-
#
|
446 |
-
'
|
447 |
-
'
|
448 |
-
'
|
449 |
-
|
450 |
-
|
451 |
-
#
|
452 |
-
'
|
453 |
-
'
|
454 |
-
|
455 |
-
|
456 |
-
#
|
457 |
-
'
|
458 |
-
'
|
459 |
-
'
|
460 |
-
|
461 |
-
|
462 |
-
#
|
463 |
-
'
|
464 |
-
'
|
465 |
-
|
466 |
-
|
467 |
-
#
|
468 |
-
'
|
469 |
-
'
|
470 |
-
|
471 |
-
|
472 |
-
|
473 |
-
|
474 |
-
|
475 |
-
'
|
476 |
-
'
|
477 |
-
|
478 |
-
|
479 |
-
|
480 |
-
|
481 |
-
|
482 |
-
|
483 |
-
|
484 |
-
|
485 |
-
|
486 |
-
|
487 |
-
|
488 |
-
|
489 |
-
|
490 |
-
|
491 |
-
|
492 |
-
|
493 |
-
|
494 |
-
|
495 |
-
current_result['
|
496 |
-
current_result['
|
497 |
-
|
498 |
-
|
499 |
-
|
500 |
-
|
501 |
-
|
502 |
-
|
503 |
-
|
504 |
-
|
505 |
-
|
506 |
-
|
507 |
-
|
508 |
-
|
509 |
-
|
510 |
-
|
511 |
-
|
512 |
-
|
513 |
-
|
514 |
-
|
515 |
-
|
516 |
-
|
517 |
-
|
518 |
-
|
519 |
-
|
520 |
-
|
521 |
-
|
522 |
-
|
523 |
-
|
524 |
-
|
525 |
-
|
526 |
-
|
527 |
-
|
528 |
-
|
529 |
-
|
530 |
-
|
531 |
-
|
532 |
-
|
533 |
-
|
534 |
-
|
535 |
-
|
536 |
-
|
537 |
-
|
538 |
-
|
539 |
-
|
540 |
-
|
541 |
-
|
542 |
-
|
543 |
-
|
544 |
-
|
545 |
-
'
|
546 |
-
'
|
547 |
-
|
548 |
-
|
549 |
-
|
550 |
-
'
|
551 |
-
'
|
552 |
-
|
553 |
-
|
554 |
-
|
555 |
-
'
|
556 |
-
'
|
557 |
-
|
558 |
-
|
559 |
-
|
560 |
-
'
|
561 |
-
'
|
562 |
-
|
563 |
-
|
564 |
-
|
565 |
-
|
566 |
-
|
567 |
-
|
568 |
-
|
569 |
-
|
570 |
-
|
571 |
-
|
572 |
-
|
573 |
-
|
574 |
-
|
575 |
-
|
576 |
-
|
577 |
-
|
578 |
-
'
|
579 |
-
'
|
580 |
-
|
581 |
-
|
582 |
-
|
583 |
-
|
584 |
-
|
585 |
-
|
586 |
-
|
587 |
-
|
588 |
-
|
589 |
-
|
590 |
-
|
591 |
-
|
592 |
-
|
593 |
-
|
594 |
-
|
595 |
-
|
596 |
-
|
597 |
-
|
598 |
-
|
599 |
-
|
600 |
-
#
|
601 |
-
|
602 |
-
|
603 |
-
|
604 |
-
|
605 |
-
|
606 |
-
|
607 |
-
|
608 |
-
|
609 |
-
|
610 |
-
|
611 |
-
|
612 |
-
|
613 |
-
|
614 |
-
|
615 |
-
|
616 |
-
|
617 |
-
|
618 |
-
|
619 |
-
|
620 |
-
|
621 |
-
|
622 |
-
|
623 |
-
#########################################################################
|
624 |
-
|
625 |
-
def generate_recommendations(metrics, text_type, lang_code='es'):
|
626 |
-
"""
|
627 |
-
Genera recomendaciones personalizadas basadas en las métricas del texto y el tipo de texto.
|
628 |
-
|
629 |
-
Args:
|
630 |
-
metrics: Diccionario con las métricas analizadas
|
631 |
-
text_type: Tipo de texto ('academic_article', 'student_essay', 'general_communication')
|
632 |
-
lang_code: Código del idioma para las recomendaciones (es, en,
|
633 |
-
|
634 |
-
Returns:
|
635 |
-
dict: Recomendaciones organizadas por categoría en el idioma correspondiente
|
636 |
-
"""
|
637 |
-
try:
|
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 |
-
|
692 |
-
|
693 |
-
|
694 |
-
|
695 |
-
|
696 |
-
|
697 |
-
|
698 |
-
|
699 |
-
|
700 |
-
|
701 |
-
|
702 |
-
|
703 |
-
|
704 |
-
|
705 |
-
|
706 |
-
|
707 |
-
|
708 |
-
|
709 |
-
|
710 |
-
|
711 |
-
|
712 |
-
|
713 |
-
|
714 |
-
|
715 |
-
|
716 |
-
|
717 |
-
'
|
718 |
-
'
|
719 |
-
'
|
720 |
-
'
|
721 |
-
|
722 |
-
|
723 |
-
|
724 |
-
'
|
725 |
-
'
|
726 |
-
'
|
727 |
-
'
|
728 |
-
|
729 |
-
|
730 |
-
|
731 |
-
|
732 |
-
|
733 |
-
|
734 |
-
|
735 |
-
|
736 |
-
|
737 |
-
|
738 |
-
|
739 |
-
'
|
740 |
-
'
|
741 |
-
'
|
742 |
-
|
743 |
-
|
744 |
-
'
|
745 |
-
|
746 |
-
|
747 |
-
'
|
748 |
-
'
|
749 |
-
|
750 |
-
|
751 |
-
'
|
752 |
-
|
753 |
-
|
754 |
-
'
|
755 |
-
'
|
756 |
-
'
|
757 |
-
|
758 |
-
|
759 |
-
|
760 |
-
|
761 |
-
|
762 |
-
|
763 |
-
'
|
764 |
-
|
765 |
-
|
766 |
-
|
767 |
-
'
|
768 |
-
'
|
769 |
-
},
|
770 |
-
'dimension_names': {
|
771 |
-
'vocabulary': '
|
772 |
-
'structure': '
|
773 |
-
'cohesion': '
|
774 |
-
'clarity': '
|
775 |
-
'general': '
|
776 |
-
},
|
777 |
-
'ui_text': {
|
778 |
-
'priority_intro': "
|
779 |
-
'detailed_recommendations': "
|
780 |
-
'save_button': "
|
781 |
-
'save_success': "
|
782 |
-
'save_error': "
|
783 |
-
'area_priority': "Área
|
784 |
-
}
|
785 |
-
}
|
786 |
-
|
787 |
-
|
788 |
-
|
789 |
-
|
790 |
-
|
791 |
-
|
792 |
-
|
793 |
-
|
794 |
-
|
795 |
-
|
796 |
-
|
797 |
-
|
798 |
-
|
799 |
-
|
800 |
-
|
801 |
-
|
802 |
-
|
803 |
-
|
804 |
-
|
805 |
-
|
806 |
-
|
807 |
-
|
808 |
-
|
809 |
-
|
810 |
-
|
811 |
-
|
812 |
-
|
813 |
-
|
814 |
-
|
815 |
-
|
816 |
-
|
817 |
-
|
818 |
-
|
819 |
-
|
820 |
-
fig
|
821 |
-
|
822 |
-
|
823 |
-
|
824 |
-
|
825 |
-
|
826 |
-
|
827 |
-
|
828 |
-
|
829 |
-
|
830 |
-
|
831 |
-
|
832 |
-
|
833 |
-
|
834 |
-
|
835 |
-
|
836 |
-
|
837 |
-
|
838 |
-
|
839 |
-
def create_vocabulary_network(doc):
|
840 |
-
"""
|
841 |
-
Genera el grafo de red de vocabulario.
|
842 |
-
"""
|
843 |
-
G = nx.Graph()
|
844 |
-
|
845 |
-
# Crear nodos para palabras significativas
|
846 |
-
words = [token.text.lower() for token in doc if token.is_alpha and not token.is_stop]
|
847 |
-
word_freq = Counter(words)
|
848 |
-
|
849 |
-
# Añadir nodos con tamaño basado en frecuencia
|
850 |
-
for word, freq in word_freq.items():
|
851 |
-
G.add_node(word, size=freq)
|
852 |
-
|
853 |
-
# Crear conexiones basadas en co-ocurrencia
|
854 |
-
window_size = 5
|
855 |
-
for i in range(len(words) - window_size):
|
856 |
-
window = words[i:i+window_size]
|
857 |
-
for w1, w2 in combinations(set(window), 2):
|
858 |
-
if G.has_edge(w1, w2):
|
859 |
-
G[w1][w2]['weight'] += 1
|
860 |
-
else:
|
861 |
-
G.add_edge(w1, w2, weight=1)
|
862 |
-
|
863 |
-
# Crear visualización
|
864 |
-
fig, ax = plt.subplots(figsize=(12, 8))
|
865 |
-
pos = nx.spring_layout(G)
|
866 |
-
|
867 |
-
# Dibujar nodos
|
868 |
-
nx.draw_networkx_nodes(G, pos,
|
869 |
-
node_size=[G.nodes[node]['size']*100 for node in G.nodes],
|
870 |
-
node_color='lightblue',
|
871 |
-
alpha=0.7)
|
872 |
-
|
873 |
-
# Dibujar conexiones
|
874 |
-
nx.draw_networkx_edges(G, pos,
|
875 |
-
width=[G[u][v]['weight']*0.5 for u,v in G.edges],
|
876 |
-
alpha=0.5)
|
877 |
-
|
878 |
-
# Añadir etiquetas
|
879 |
-
nx.draw_networkx_labels(G, pos)
|
880 |
-
|
881 |
-
plt.title("Red de Vocabulario")
|
882 |
-
plt.axis('off')
|
883 |
-
return fig
|
884 |
-
|
885 |
-
|
886 |
-
|
887 |
-
|
888 |
-
|
889 |
-
|
890 |
-
|
891 |
-
|
892 |
-
|
893 |
-
|
894 |
-
|
895 |
-
|
896 |
-
|
897 |
-
|
898 |
-
|
899 |
-
|
900 |
-
|
901 |
-
|
902 |
-
|
903 |
-
|
904 |
-
|
905 |
-
|
906 |
-
|
907 |
-
|
908 |
-
|
909 |
-
|
910 |
-
|
911 |
-
|
912 |
-
plt.
|
913 |
-
|
914 |
-
|
915 |
-
|
916 |
-
|
917 |
-
|
918 |
-
|
919 |
-
|
920 |
-
|
921 |
-
|
922 |
-
|
923 |
-
|
924 |
-
|
925 |
-
|
926 |
-
|
927 |
-
|
928 |
-
|
929 |
-
|
930 |
-
|
931 |
-
|
932 |
-
|
933 |
-
|
934 |
-
|
935 |
-
|
936 |
-
|
937 |
-
|
938 |
-
|
939 |
-
|
940 |
-
|
941 |
-
|
942 |
-
|
943 |
-
|
944 |
-
|
945 |
-
|
946 |
-
|
947 |
-
|
948 |
-
|
949 |
-
|
950 |
-
|
951 |
-
|
952 |
-
|
953 |
-
|
954 |
-
plt.
|
955 |
-
plt.
|
956 |
-
plt.
|
957 |
-
|
958 |
-
|
959 |
-
|
960 |
-
|
961 |
-
|
962 |
-
|
963 |
-
|
964 |
-
|
965 |
-
|
966 |
-
|
967 |
-
|
968 |
-
|
969 |
-
|
970 |
-
|
971 |
-
|
972 |
-
|
973 |
-
|
974 |
-
|
975 |
-
|
976 |
-
|
977 |
-
|
978 |
-
|
979 |
-
|
980 |
-
|
981 |
-
|
982 |
-
|
983 |
-
|
984 |
-
|
985 |
-
|
986 |
-
|
987 |
-
|
988 |
-
|
989 |
-
|
990 |
-
|
991 |
-
|
992 |
-
|
993 |
-
|
994 |
-
|
995 |
-
|
996 |
-
|
997 |
-
|
998 |
-
|
999 |
-
|
1000 |
-
plt.
|
1001 |
-
plt.
|
1002 |
-
|
1003 |
-
|
1004 |
-
|
1005 |
-
|
1006 |
-
|
1007 |
-
|
1008 |
-
|
|
|
|
1 |
+
#v3/modules/studentact/current_situation_analysis.py
|
2 |
+
|
3 |
+
import streamlit as st
|
4 |
+
import matplotlib.pyplot as plt
|
5 |
+
import networkx as nx
|
6 |
+
import seaborn as sns
|
7 |
+
from collections import Counter
|
8 |
+
from itertools import combinations
|
9 |
+
import numpy as np
|
10 |
+
import matplotlib.patches as patches
|
11 |
+
import logging
|
12 |
+
|
13 |
+
|
14 |
+
# 2. Configuración básica del logging
|
15 |
+
logging.basicConfig(
|
16 |
+
level=logging.INFO,
|
17 |
+
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
|
18 |
+
handlers=[
|
19 |
+
logging.StreamHandler(),
|
20 |
+
logging.FileHandler('app.log')
|
21 |
+
]
|
22 |
+
)
|
23 |
+
|
24 |
+
# 3. Obtener el logger específico para este módulo
|
25 |
+
logger = logging.getLogger(__name__)
|
26 |
+
|
27 |
+
#########################################################################
|
28 |
+
|
29 |
+
def correlate_metrics(scores):
|
30 |
+
"""
|
31 |
+
Ajusta los scores para mantener correlaciones lógicas entre métricas.
|
32 |
+
|
33 |
+
Args:
|
34 |
+
scores: dict con scores iniciales de vocabulario, estructura, cohesión y claridad
|
35 |
+
|
36 |
+
Returns:
|
37 |
+
dict con scores ajustados
|
38 |
+
"""
|
39 |
+
try:
|
40 |
+
# 1. Correlación estructura-cohesión
|
41 |
+
# La cohesión no puede ser menor que estructura * 0.7
|
42 |
+
min_cohesion = scores['structure']['normalized_score'] * 0.7
|
43 |
+
if scores['cohesion']['normalized_score'] < min_cohesion:
|
44 |
+
scores['cohesion']['normalized_score'] = min_cohesion
|
45 |
+
|
46 |
+
# 2. Correlación vocabulario-cohesión
|
47 |
+
# La cohesión léxica depende del vocabulario
|
48 |
+
vocab_influence = scores['vocabulary']['normalized_score'] * 0.6
|
49 |
+
scores['cohesion']['normalized_score'] = max(
|
50 |
+
scores['cohesion']['normalized_score'],
|
51 |
+
vocab_influence
|
52 |
+
)
|
53 |
+
|
54 |
+
# 3. Correlación cohesión-claridad
|
55 |
+
# La claridad no puede superar cohesión * 1.2
|
56 |
+
max_clarity = scores['cohesion']['normalized_score'] * 1.2
|
57 |
+
if scores['clarity']['normalized_score'] > max_clarity:
|
58 |
+
scores['clarity']['normalized_score'] = max_clarity
|
59 |
+
|
60 |
+
# 4. Correlación estructura-claridad
|
61 |
+
# La claridad no puede superar estructura * 1.1
|
62 |
+
struct_max_clarity = scores['structure']['normalized_score'] * 1.1
|
63 |
+
scores['clarity']['normalized_score'] = min(
|
64 |
+
scores['clarity']['normalized_score'],
|
65 |
+
struct_max_clarity
|
66 |
+
)
|
67 |
+
|
68 |
+
# Normalizar todos los scores entre 0 y 1
|
69 |
+
for metric in scores:
|
70 |
+
scores[metric]['normalized_score'] = max(0.0, min(1.0, scores[metric]['normalized_score']))
|
71 |
+
|
72 |
+
return scores
|
73 |
+
|
74 |
+
except Exception as e:
|
75 |
+
logger.error(f"Error en correlate_metrics: {str(e)}")
|
76 |
+
return scores
|
77 |
+
|
78 |
+
##########################################################################
|
79 |
+
|
80 |
+
def analyze_text_dimensions(doc):
|
81 |
+
"""
|
82 |
+
Analiza las dimensiones principales del texto manteniendo correlaciones lógicas.
|
83 |
+
"""
|
84 |
+
try:
|
85 |
+
# Obtener scores iniciales
|
86 |
+
vocab_score, vocab_details = analyze_vocabulary_diversity(doc)
|
87 |
+
struct_score = analyze_structure(doc)
|
88 |
+
cohesion_score = analyze_cohesion(doc)
|
89 |
+
clarity_score, clarity_details = analyze_clarity(doc)
|
90 |
+
|
91 |
+
# Crear diccionario de scores inicial
|
92 |
+
scores = {
|
93 |
+
'vocabulary': {
|
94 |
+
'normalized_score': vocab_score,
|
95 |
+
'details': vocab_details
|
96 |
+
},
|
97 |
+
'structure': {
|
98 |
+
'normalized_score': struct_score,
|
99 |
+
'details': None
|
100 |
+
},
|
101 |
+
'cohesion': {
|
102 |
+
'normalized_score': cohesion_score,
|
103 |
+
'details': None
|
104 |
+
},
|
105 |
+
'clarity': {
|
106 |
+
'normalized_score': clarity_score,
|
107 |
+
'details': clarity_details
|
108 |
+
}
|
109 |
+
}
|
110 |
+
|
111 |
+
# Ajustar correlaciones entre métricas
|
112 |
+
adjusted_scores = correlate_metrics(scores)
|
113 |
+
|
114 |
+
# Logging para diagnóstico
|
115 |
+
logger.info(f"""
|
116 |
+
Scores originales vs ajustados:
|
117 |
+
Vocabulario: {vocab_score:.2f} -> {adjusted_scores['vocabulary']['normalized_score']:.2f}
|
118 |
+
Estructura: {struct_score:.2f} -> {adjusted_scores['structure']['normalized_score']:.2f}
|
119 |
+
Cohesión: {cohesion_score:.2f} -> {adjusted_scores['cohesion']['normalized_score']:.2f}
|
120 |
+
Claridad: {clarity_score:.2f} -> {adjusted_scores['clarity']['normalized_score']:.2f}
|
121 |
+
""")
|
122 |
+
|
123 |
+
return adjusted_scores
|
124 |
+
|
125 |
+
except Exception as e:
|
126 |
+
logger.error(f"Error en analyze_text_dimensions: {str(e)}")
|
127 |
+
return {
|
128 |
+
'vocabulary': {'normalized_score': 0.0, 'details': {}},
|
129 |
+
'structure': {'normalized_score': 0.0, 'details': {}},
|
130 |
+
'cohesion': {'normalized_score': 0.0, 'details': {}},
|
131 |
+
'clarity': {'normalized_score': 0.0, 'details': {}}
|
132 |
+
}
|
133 |
+
|
134 |
+
|
135 |
+
|
136 |
+
#############################################################################################
|
137 |
+
|
138 |
+
def analyze_clarity(doc):
|
139 |
+
"""
|
140 |
+
Analiza la claridad del texto considerando múltiples factores.
|
141 |
+
"""
|
142 |
+
try:
|
143 |
+
sentences = list(doc.sents)
|
144 |
+
if not sentences:
|
145 |
+
return 0.0, {}
|
146 |
+
|
147 |
+
# 1. Longitud de oraciones
|
148 |
+
sentence_lengths = [len(sent) for sent in sentences]
|
149 |
+
avg_length = sum(sentence_lengths) / len(sentences)
|
150 |
+
|
151 |
+
# Normalizar usando los umbrales definidos para clarity
|
152 |
+
length_score = normalize_score(
|
153 |
+
value=avg_length,
|
154 |
+
metric_type='clarity',
|
155 |
+
optimal_length=20, # Una oración ideal tiene ~20 palabras
|
156 |
+
min_threshold=0.60, # Consistente con METRIC_THRESHOLDS
|
157 |
+
target_threshold=0.75 # Consistente con METRIC_THRESHOLDS
|
158 |
+
)
|
159 |
+
|
160 |
+
# 2. Análisis de conectores
|
161 |
+
connector_count = 0
|
162 |
+
connector_weights = {
|
163 |
+
'CCONJ': 1.0, # Coordinantes
|
164 |
+
'SCONJ': 1.2, # Subordinantes
|
165 |
+
'ADV': 0.8 # Adverbios conectivos
|
166 |
+
}
|
167 |
+
|
168 |
+
for token in doc:
|
169 |
+
if token.pos_ in connector_weights and token.dep_ in ['cc', 'mark', 'advmod']:
|
170 |
+
connector_count += connector_weights[token.pos_]
|
171 |
+
|
172 |
+
# Normalizar conectores por oración
|
173 |
+
connectors_per_sentence = connector_count / len(sentences) if sentences else 0
|
174 |
+
connector_score = normalize_score(
|
175 |
+
value=connectors_per_sentence,
|
176 |
+
metric_type='clarity',
|
177 |
+
optimal_connections=1.5, # ~1.5 conectores por oración es óptimo
|
178 |
+
min_threshold=0.60,
|
179 |
+
target_threshold=0.75
|
180 |
+
)
|
181 |
+
|
182 |
+
# 3. Complejidad estructural
|
183 |
+
clause_count = 0
|
184 |
+
for sent in sentences:
|
185 |
+
verbs = [token for token in sent if token.pos_ == 'VERB']
|
186 |
+
clause_count += len(verbs)
|
187 |
+
|
188 |
+
complexity_raw = clause_count / len(sentences) if sentences else 0
|
189 |
+
complexity_score = normalize_score(
|
190 |
+
value=complexity_raw,
|
191 |
+
metric_type='clarity',
|
192 |
+
optimal_depth=2.0, # ~2 cláusulas por oración es óptimo
|
193 |
+
min_threshold=0.60,
|
194 |
+
target_threshold=0.75
|
195 |
+
)
|
196 |
+
|
197 |
+
# 4. Densidad léxica
|
198 |
+
content_words = len([token for token in doc if token.pos_ in ['NOUN', 'VERB', 'ADJ', 'ADV']])
|
199 |
+
total_words = len([token for token in doc if token.is_alpha])
|
200 |
+
density = content_words / total_words if total_words > 0 else 0
|
201 |
+
|
202 |
+
density_score = normalize_score(
|
203 |
+
value=density,
|
204 |
+
metric_type='clarity',
|
205 |
+
optimal_connections=0.6, # 60% de palabras de contenido es óptimo
|
206 |
+
min_threshold=0.60,
|
207 |
+
target_threshold=0.75
|
208 |
+
)
|
209 |
+
|
210 |
+
# Score final ponderado
|
211 |
+
weights = {
|
212 |
+
'length': 0.3,
|
213 |
+
'connectors': 0.3,
|
214 |
+
'complexity': 0.2,
|
215 |
+
'density': 0.2
|
216 |
+
}
|
217 |
+
|
218 |
+
clarity_score = (
|
219 |
+
weights['length'] * length_score +
|
220 |
+
weights['connectors'] * connector_score +
|
221 |
+
weights['complexity'] * complexity_score +
|
222 |
+
weights['density'] * density_score
|
223 |
+
)
|
224 |
+
|
225 |
+
details = {
|
226 |
+
'length_score': length_score,
|
227 |
+
'connector_score': connector_score,
|
228 |
+
'complexity_score': complexity_score,
|
229 |
+
'density_score': density_score,
|
230 |
+
'avg_sentence_length': avg_length,
|
231 |
+
'connectors_per_sentence': connectors_per_sentence,
|
232 |
+
'density': density
|
233 |
+
}
|
234 |
+
|
235 |
+
# Agregar logging para diagnóstico
|
236 |
+
logger.info(f"""
|
237 |
+
Scores de Claridad:
|
238 |
+
- Longitud: {length_score:.2f} (avg={avg_length:.1f} palabras)
|
239 |
+
- Conectores: {connector_score:.2f} (avg={connectors_per_sentence:.1f} por oración)
|
240 |
+
- Complejidad: {complexity_score:.2f} (avg={complexity_raw:.1f} cláusulas)
|
241 |
+
- Densidad: {density_score:.2f} ({density*100:.1f}% palabras de contenido)
|
242 |
+
- Score Final: {clarity_score:.2f}
|
243 |
+
""")
|
244 |
+
|
245 |
+
return clarity_score, details
|
246 |
+
|
247 |
+
except Exception as e:
|
248 |
+
logger.error(f"Error en analyze_clarity: {str(e)}")
|
249 |
+
return 0.0, {}
|
250 |
+
|
251 |
+
#########################################################################
|
252 |
+
def analyze_vocabulary_diversity(doc):
|
253 |
+
"""Análisis mejorado de la diversidad y calidad del vocabulario"""
|
254 |
+
try:
|
255 |
+
# 1. Análisis básico de diversidad
|
256 |
+
unique_lemmas = {token.lemma_ for token in doc if token.is_alpha}
|
257 |
+
total_words = len([token for token in doc if token.is_alpha])
|
258 |
+
basic_diversity = len(unique_lemmas) / total_words if total_words > 0 else 0
|
259 |
+
|
260 |
+
# 2. Análisis de registro
|
261 |
+
academic_words = 0
|
262 |
+
narrative_words = 0
|
263 |
+
technical_terms = 0
|
264 |
+
|
265 |
+
# Clasificar palabras por registro
|
266 |
+
for token in doc:
|
267 |
+
if token.is_alpha:
|
268 |
+
# Detectar términos académicos/técnicos
|
269 |
+
if token.pos_ in ['NOUN', 'VERB', 'ADJ']:
|
270 |
+
if any(parent.pos_ == 'NOUN' for parent in token.ancestors):
|
271 |
+
technical_terms += 1
|
272 |
+
# Detectar palabras narrativas
|
273 |
+
if token.pos_ in ['VERB', 'ADV'] and token.dep_ in ['ROOT', 'advcl']:
|
274 |
+
narrative_words += 1
|
275 |
+
|
276 |
+
# 3. Análisis de complejidad sintáctica
|
277 |
+
avg_sentence_length = sum(len(sent) for sent in doc.sents) / len(list(doc.sents))
|
278 |
+
|
279 |
+
# 4. Calcular score ponderado
|
280 |
+
weights = {
|
281 |
+
'diversity': 0.3,
|
282 |
+
'technical': 0.3,
|
283 |
+
'narrative': 0.2,
|
284 |
+
'complexity': 0.2
|
285 |
+
}
|
286 |
+
|
287 |
+
scores = {
|
288 |
+
'diversity': basic_diversity,
|
289 |
+
'technical': technical_terms / total_words if total_words > 0 else 0,
|
290 |
+
'narrative': narrative_words / total_words if total_words > 0 else 0,
|
291 |
+
'complexity': min(1.0, avg_sentence_length / 20) # Normalizado a 20 palabras
|
292 |
+
}
|
293 |
+
|
294 |
+
# Score final ponderado
|
295 |
+
final_score = sum(weights[key] * scores[key] for key in weights)
|
296 |
+
|
297 |
+
# Información adicional para diagnóstico
|
298 |
+
details = {
|
299 |
+
'text_type': 'narrative' if scores['narrative'] > scores['technical'] else 'academic',
|
300 |
+
'scores': scores
|
301 |
+
}
|
302 |
+
|
303 |
+
return final_score, details
|
304 |
+
|
305 |
+
except Exception as e:
|
306 |
+
logger.error(f"Error en analyze_vocabulary_diversity: {str(e)}")
|
307 |
+
return 0.0, {}
|
308 |
+
|
309 |
+
#########################################################################
|
310 |
+
def analyze_cohesion(doc):
|
311 |
+
"""Analiza la cohesión textual"""
|
312 |
+
try:
|
313 |
+
sentences = list(doc.sents)
|
314 |
+
if len(sentences) < 2:
|
315 |
+
logger.warning("Texto demasiado corto para análisis de cohesión")
|
316 |
+
return 0.0
|
317 |
+
|
318 |
+
# 1. Análisis de conexiones léxicas
|
319 |
+
lexical_connections = 0
|
320 |
+
total_possible_connections = 0
|
321 |
+
|
322 |
+
for i in range(len(sentences)-1):
|
323 |
+
# Obtener lemmas significativos (no stopwords)
|
324 |
+
sent1_words = {token.lemma_ for token in sentences[i]
|
325 |
+
if token.is_alpha and not token.is_stop}
|
326 |
+
sent2_words = {token.lemma_ for token in sentences[i+1]
|
327 |
+
if token.is_alpha and not token.is_stop}
|
328 |
+
|
329 |
+
if sent1_words and sent2_words: # Verificar que ambos conjuntos no estén vacíos
|
330 |
+
intersection = len(sent1_words.intersection(sent2_words))
|
331 |
+
total_possible = min(len(sent1_words), len(sent2_words))
|
332 |
+
|
333 |
+
if total_possible > 0:
|
334 |
+
lexical_score = intersection / total_possible
|
335 |
+
lexical_connections += lexical_score
|
336 |
+
total_possible_connections += 1
|
337 |
+
|
338 |
+
# 2. Análisis de conectores
|
339 |
+
connector_count = 0
|
340 |
+
connector_types = {
|
341 |
+
'CCONJ': 1.0, # Coordinantes
|
342 |
+
'SCONJ': 1.2, # Subordinantes
|
343 |
+
'ADV': 0.8 # Adverbios conectivos
|
344 |
+
}
|
345 |
+
|
346 |
+
for token in doc:
|
347 |
+
if (token.pos_ in connector_types and
|
348 |
+
token.dep_ in ['cc', 'mark', 'advmod'] and
|
349 |
+
not token.is_stop):
|
350 |
+
connector_count += connector_types[token.pos_]
|
351 |
+
|
352 |
+
# 3. Cálculo de scores normalizados
|
353 |
+
if total_possible_connections > 0:
|
354 |
+
lexical_cohesion = lexical_connections / total_possible_connections
|
355 |
+
else:
|
356 |
+
lexical_cohesion = 0
|
357 |
+
|
358 |
+
if len(sentences) > 1:
|
359 |
+
connector_cohesion = min(1.0, connector_count / (len(sentences) - 1))
|
360 |
+
else:
|
361 |
+
connector_cohesion = 0
|
362 |
+
|
363 |
+
# 4. Score final ponderado
|
364 |
+
weights = {
|
365 |
+
'lexical': 0.7,
|
366 |
+
'connectors': 0.3
|
367 |
+
}
|
368 |
+
|
369 |
+
cohesion_score = (
|
370 |
+
weights['lexical'] * lexical_cohesion +
|
371 |
+
weights['connectors'] * connector_cohesion
|
372 |
+
)
|
373 |
+
|
374 |
+
# 5. Logging para diagnóstico
|
375 |
+
logger.info(f"""
|
376 |
+
Análisis de Cohesión:
|
377 |
+
- Conexiones léxicas encontradas: {lexical_connections}
|
378 |
+
- Conexiones posibles: {total_possible_connections}
|
379 |
+
- Lexical cohesion score: {lexical_cohesion}
|
380 |
+
- Conectores encontrados: {connector_count}
|
381 |
+
- Connector cohesion score: {connector_cohesion}
|
382 |
+
- Score final: {cohesion_score}
|
383 |
+
""")
|
384 |
+
|
385 |
+
return cohesion_score
|
386 |
+
|
387 |
+
except Exception as e:
|
388 |
+
logger.error(f"Error en analyze_cohesion: {str(e)}")
|
389 |
+
return 0.0
|
390 |
+
|
391 |
+
#########################################################################
|
392 |
+
def analyze_structure(doc):
|
393 |
+
try:
|
394 |
+
if len(doc) == 0:
|
395 |
+
return 0.0
|
396 |
+
|
397 |
+
structure_scores = []
|
398 |
+
for token in doc:
|
399 |
+
if token.dep_ == 'ROOT':
|
400 |
+
result = get_dependency_depths(token)
|
401 |
+
structure_scores.append(result['final_score'])
|
402 |
+
|
403 |
+
if not structure_scores:
|
404 |
+
return 0.0
|
405 |
+
|
406 |
+
return min(1.0, sum(structure_scores) / len(structure_scores))
|
407 |
+
|
408 |
+
except Exception as e:
|
409 |
+
logger.error(f"Error en analyze_structure: {str(e)}")
|
410 |
+
return 0.0
|
411 |
+
|
412 |
+
#########################################################################
|
413 |
+
# Funciones auxiliares de análisis
|
414 |
+
def get_dependency_depths(token, depth=0, analyzed_tokens=None):
|
415 |
+
"""
|
416 |
+
Analiza la profundidad y calidad de las relaciones de dependencia.
|
417 |
+
|
418 |
+
Args:
|
419 |
+
token: Token a analizar
|
420 |
+
depth: Profundidad actual en el árbol
|
421 |
+
analyzed_tokens: Set para evitar ciclos en el análisis
|
422 |
+
|
423 |
+
Returns:
|
424 |
+
dict: Información detallada sobre las dependencias
|
425 |
+
- depths: Lista de profundidades
|
426 |
+
- relations: Diccionario con tipos de relaciones encontradas
|
427 |
+
- complexity_score: Puntuación de complejidad
|
428 |
+
"""
|
429 |
+
if analyzed_tokens is None:
|
430 |
+
analyzed_tokens = set()
|
431 |
+
|
432 |
+
# Evitar ciclos
|
433 |
+
if token.i in analyzed_tokens:
|
434 |
+
return {
|
435 |
+
'depths': [],
|
436 |
+
'relations': {},
|
437 |
+
'complexity_score': 0
|
438 |
+
}
|
439 |
+
|
440 |
+
analyzed_tokens.add(token.i)
|
441 |
+
|
442 |
+
# Pesos para diferentes tipos de dependencias
|
443 |
+
dependency_weights = {
|
444 |
+
# Dependencias principales
|
445 |
+
'nsubj': 1.2, # Sujeto nominal
|
446 |
+
'obj': 1.1, # Objeto directo
|
447 |
+
'iobj': 1.1, # Objeto indirecto
|
448 |
+
'ROOT': 1.3, # Raíz
|
449 |
+
|
450 |
+
# Modificadores
|
451 |
+
'amod': 0.8, # Modificador adjetival
|
452 |
+
'advmod': 0.8, # Modificador adverbial
|
453 |
+
'nmod': 0.9, # Modificador nominal
|
454 |
+
|
455 |
+
# Estructuras complejas
|
456 |
+
'csubj': 1.4, # Cláusula como sujeto
|
457 |
+
'ccomp': 1.3, # Complemento clausal
|
458 |
+
'xcomp': 1.2, # Complemento clausal abierto
|
459 |
+
'advcl': 1.2, # Cláusula adverbial
|
460 |
+
|
461 |
+
# Coordinación y subordinación
|
462 |
+
'conj': 1.1, # Conjunción
|
463 |
+
'cc': 0.7, # Coordinación
|
464 |
+
'mark': 0.8, # Marcador
|
465 |
+
|
466 |
+
# Otros
|
467 |
+
'det': 0.5, # Determinante
|
468 |
+
'case': 0.5, # Caso
|
469 |
+
'punct': 0.1 # Puntuación
|
470 |
+
}
|
471 |
+
|
472 |
+
# Inicializar resultados
|
473 |
+
current_result = {
|
474 |
+
'depths': [depth],
|
475 |
+
'relations': {token.dep_: 1},
|
476 |
+
'complexity_score': dependency_weights.get(token.dep_, 0.5) * (depth + 1)
|
477 |
+
}
|
478 |
+
|
479 |
+
# Analizar hijos recursivamente
|
480 |
+
for child in token.children:
|
481 |
+
child_result = get_dependency_depths(child, depth + 1, analyzed_tokens)
|
482 |
+
|
483 |
+
# Combinar profundidades
|
484 |
+
current_result['depths'].extend(child_result['depths'])
|
485 |
+
|
486 |
+
# Combinar relaciones
|
487 |
+
for rel, count in child_result['relations'].items():
|
488 |
+
current_result['relations'][rel] = current_result['relations'].get(rel, 0) + count
|
489 |
+
|
490 |
+
# Acumular score de complejidad
|
491 |
+
current_result['complexity_score'] += child_result['complexity_score']
|
492 |
+
|
493 |
+
# Calcular métricas adicionales
|
494 |
+
current_result['max_depth'] = max(current_result['depths'])
|
495 |
+
current_result['avg_depth'] = sum(current_result['depths']) / len(current_result['depths'])
|
496 |
+
current_result['relation_diversity'] = len(current_result['relations'])
|
497 |
+
|
498 |
+
# Calcular score ponderado por tipo de estructura
|
499 |
+
structure_bonus = 0
|
500 |
+
|
501 |
+
# Bonus por estructuras complejas
|
502 |
+
if 'csubj' in current_result['relations'] or 'ccomp' in current_result['relations']:
|
503 |
+
structure_bonus += 0.3
|
504 |
+
|
505 |
+
# Bonus por coordinación balanceada
|
506 |
+
if 'conj' in current_result['relations'] and 'cc' in current_result['relations']:
|
507 |
+
structure_bonus += 0.2
|
508 |
+
|
509 |
+
# Bonus por modificación rica
|
510 |
+
if len(set(['amod', 'advmod', 'nmod']) & set(current_result['relations'])) >= 2:
|
511 |
+
structure_bonus += 0.2
|
512 |
+
|
513 |
+
current_result['final_score'] = (
|
514 |
+
current_result['complexity_score'] * (1 + structure_bonus)
|
515 |
+
)
|
516 |
+
|
517 |
+
return current_result
|
518 |
+
|
519 |
+
#########################################################################
|
520 |
+
def normalize_score(value, metric_type,
|
521 |
+
min_threshold=0.0, target_threshold=1.0,
|
522 |
+
range_factor=2.0, optimal_length=None,
|
523 |
+
optimal_connections=None, optimal_depth=None):
|
524 |
+
"""
|
525 |
+
Normaliza un valor considerando umbrales específicos por tipo de métrica.
|
526 |
+
|
527 |
+
Args:
|
528 |
+
value: Valor a normalizar
|
529 |
+
metric_type: Tipo de métrica ('vocabulary', 'structure', 'cohesion', 'clarity')
|
530 |
+
min_threshold: Valor mínimo aceptable
|
531 |
+
target_threshold: Valor objetivo
|
532 |
+
range_factor: Factor para ajustar el rango
|
533 |
+
optimal_length: Longitud óptima (opcional)
|
534 |
+
optimal_connections: Número óptimo de conexiones (opcional)
|
535 |
+
optimal_depth: Profundidad óptima de estructura (opcional)
|
536 |
+
|
537 |
+
Returns:
|
538 |
+
float: Valor normalizado entre 0 y 1
|
539 |
+
"""
|
540 |
+
try:
|
541 |
+
# Definir umbrales por tipo de métrica
|
542 |
+
METRIC_THRESHOLDS = {
|
543 |
+
'vocabulary': {
|
544 |
+
'min': 0.60,
|
545 |
+
'target': 0.75,
|
546 |
+
'range_factor': 1.5
|
547 |
+
},
|
548 |
+
'structure': {
|
549 |
+
'min': 0.65,
|
550 |
+
'target': 0.80,
|
551 |
+
'range_factor': 1.8
|
552 |
+
},
|
553 |
+
'cohesion': {
|
554 |
+
'min': 0.55,
|
555 |
+
'target': 0.70,
|
556 |
+
'range_factor': 1.6
|
557 |
+
},
|
558 |
+
'clarity': {
|
559 |
+
'min': 0.60,
|
560 |
+
'target': 0.75,
|
561 |
+
'range_factor': 1.7
|
562 |
+
}
|
563 |
+
}
|
564 |
+
|
565 |
+
# Validar valores negativos o cero
|
566 |
+
if value < 0:
|
567 |
+
logger.warning(f"Valor negativo recibido: {value}")
|
568 |
+
return 0.0
|
569 |
+
|
570 |
+
# Manejar caso donde el valor es cero
|
571 |
+
if value == 0:
|
572 |
+
logger.warning("Valor cero recibido")
|
573 |
+
return 0.0
|
574 |
+
|
575 |
+
# Obtener umbrales específicos para el tipo de métrica
|
576 |
+
thresholds = METRIC_THRESHOLDS.get(metric_type, {
|
577 |
+
'min': min_threshold,
|
578 |
+
'target': target_threshold,
|
579 |
+
'range_factor': range_factor
|
580 |
+
})
|
581 |
+
|
582 |
+
# Identificar el valor de referencia a usar
|
583 |
+
if optimal_depth is not None:
|
584 |
+
reference = optimal_depth
|
585 |
+
elif optimal_connections is not None:
|
586 |
+
reference = optimal_connections
|
587 |
+
elif optimal_length is not None:
|
588 |
+
reference = optimal_length
|
589 |
+
else:
|
590 |
+
reference = thresholds['target']
|
591 |
+
|
592 |
+
# Validar valor de referencia
|
593 |
+
if reference <= 0:
|
594 |
+
logger.warning(f"Valor de referencia inválido: {reference}")
|
595 |
+
return 0.0
|
596 |
+
|
597 |
+
# Calcular score basado en umbrales
|
598 |
+
if value < thresholds['min']:
|
599 |
+
# Valor por debajo del mínimo
|
600 |
+
score = (value / thresholds['min']) * 0.5 # Máximo 0.5 para valores bajo el mínimo
|
601 |
+
elif value < thresholds['target']:
|
602 |
+
# Valor entre mínimo y objetivo
|
603 |
+
range_size = thresholds['target'] - thresholds['min']
|
604 |
+
progress = (value - thresholds['min']) / range_size
|
605 |
+
score = 0.5 + (progress * 0.5) # Escala entre 0.5 y 1.0
|
606 |
+
else:
|
607 |
+
# Valor alcanza o supera el objetivo
|
608 |
+
score = 1.0
|
609 |
+
|
610 |
+
# Penalizar valores muy por encima del objetivo
|
611 |
+
if value > (thresholds['target'] * thresholds['range_factor']):
|
612 |
+
excess = (value - thresholds['target']) / (thresholds['target'] * thresholds['range_factor'])
|
613 |
+
score = max(0.7, 1.0 - excess) # No bajar de 0.7 para valores altos
|
614 |
+
|
615 |
+
# Asegurar que el resultado esté entre 0 y 1
|
616 |
+
return max(0.0, min(1.0, score))
|
617 |
+
|
618 |
+
except Exception as e:
|
619 |
+
logger.error(f"Error en normalize_score: {str(e)}")
|
620 |
+
return 0.0
|
621 |
+
|
622 |
+
#########################################################################
|
623 |
+
#########################################################################
|
624 |
+
|
625 |
+
def generate_recommendations(metrics, text_type, lang_code='es'):
|
626 |
+
"""
|
627 |
+
Genera recomendaciones personalizadas basadas en las métricas del texto y el tipo de texto.
|
628 |
+
|
629 |
+
Args:
|
630 |
+
metrics: Diccionario con las métricas analizadas
|
631 |
+
text_type: Tipo de texto ('academic_article', 'student_essay', 'general_communication')
|
632 |
+
lang_code: Código del idioma para las recomendaciones (es, en, uk)
|
633 |
+
|
634 |
+
Returns:
|
635 |
+
dict: Recomendaciones organizadas por categoría en el idioma correspondiente
|
636 |
+
"""
|
637 |
+
try:
|
638 |
+
# Añadir debug log para verificar el código de idioma recibido
|
639 |
+
logger.info(f"generate_recommendations llamado con idioma: {lang_code}")
|
640 |
+
|
641 |
+
# Comprobar que importamos RECOMMENDATIONS correctamente
|
642 |
+
logger.info(f"Idiomas disponibles en RECOMMENDATIONS: {list(RECOMMENDATIONS.keys())}")
|
643 |
+
|
644 |
+
# Obtener umbrales según el tipo de texto
|
645 |
+
thresholds = TEXT_TYPES[text_type]['thresholds']
|
646 |
+
|
647 |
+
# Verificar que el idioma esté soportado, usar español como respaldo
|
648 |
+
if lang_code not in RECOMMENDATIONS:
|
649 |
+
logger.warning(f"Idioma {lang_code} no soportado para recomendaciones, usando español")
|
650 |
+
lang_code = 'es'
|
651 |
+
|
652 |
+
# Obtener traducciones para el idioma seleccionado
|
653 |
+
translations = RECOMMENDATIONS[lang_code]
|
654 |
+
|
655 |
+
# Inicializar diccionario de recomendaciones
|
656 |
+
recommendations = {
|
657 |
+
'vocabulary': [],
|
658 |
+
'structure': [],
|
659 |
+
'cohesion': [],
|
660 |
+
'clarity': [],
|
661 |
+
'specific': [],
|
662 |
+
'priority': {
|
663 |
+
'area': 'general',
|
664 |
+
'tips': []
|
665 |
+
},
|
666 |
+
'text_type_name': translations['text_types'][text_type],
|
667 |
+
'dimension_names': translations['dimension_names'],
|
668 |
+
'ui_text': {
|
669 |
+
'priority_intro': translations['priority_intro'],
|
670 |
+
'detailed_recommendations': translations['detailed_recommendations'],
|
671 |
+
'save_button': translations['save_button'],
|
672 |
+
'save_success': translations['save_success'],
|
673 |
+
'save_error': translations['save_error'],
|
674 |
+
'area_priority': translations['area_priority']
|
675 |
+
}
|
676 |
+
}
|
677 |
+
|
678 |
+
# Determinar nivel para cada dimensión y asignar recomendaciones
|
679 |
+
dimensions = ['vocabulary', 'structure', 'cohesion', 'clarity']
|
680 |
+
scores = {}
|
681 |
+
|
682 |
+
for dim in dimensions:
|
683 |
+
score = metrics[dim]['normalized_score']
|
684 |
+
scores[dim] = score
|
685 |
+
|
686 |
+
# Determinar nivel (bajo, medio, alto)
|
687 |
+
if score < thresholds[dim]['min']:
|
688 |
+
level = 'low'
|
689 |
+
elif score < thresholds[dim]['target']:
|
690 |
+
level = 'medium'
|
691 |
+
else:
|
692 |
+
level = 'high'
|
693 |
+
|
694 |
+
# Asignar recomendaciones para ese nivel
|
695 |
+
recommendations[dim] = translations[dim][level]
|
696 |
+
|
697 |
+
# Asignar recomendaciones específicas por tipo de texto
|
698 |
+
recommendations['specific'] = translations[text_type]
|
699 |
+
|
700 |
+
# Determinar área prioritaria (la que tiene menor puntuación)
|
701 |
+
priority_dimension = min(scores, key=scores.get)
|
702 |
+
recommendations['priority']['area'] = priority_dimension
|
703 |
+
recommendations['priority']['tips'] = recommendations[priority_dimension]
|
704 |
+
|
705 |
+
logger.info(f"Generadas recomendaciones en {lang_code} para texto tipo {text_type}")
|
706 |
+
return recommendations
|
707 |
+
|
708 |
+
except Exception as e:
|
709 |
+
logger.error(f"Error en generate_recommendations: {str(e)}")
|
710 |
+
|
711 |
+
# Utilizar un enfoque basado en el idioma actual en lugar de casos codificados
|
712 |
+
# Esto permite manejar ucraniano y cualquier otro idioma futuro
|
713 |
+
fallback_translations = {
|
714 |
+
'en': {
|
715 |
+
'basic_recommendations': {
|
716 |
+
'vocabulary': ["Try enriching your vocabulary"],
|
717 |
+
'structure': ["Work on the structure of your sentences"],
|
718 |
+
'cohesion': ["Improve the connection between your ideas"],
|
719 |
+
'clarity': ["Try to express your ideas more clearly"],
|
720 |
+
'specific': ["Adapt your text according to its purpose"],
|
721 |
+
},
|
722 |
+
'dimension_names': {
|
723 |
+
'vocabulary': 'Vocabulary',
|
724 |
+
'structure': 'Structure',
|
725 |
+
'cohesion': 'Cohesion',
|
726 |
+
'clarity': 'Clarity',
|
727 |
+
'general': 'General'
|
728 |
+
},
|
729 |
+
'ui_text': {
|
730 |
+
'priority_intro': "This is where you should focus your efforts.",
|
731 |
+
'detailed_recommendations': "Detailed recommendations",
|
732 |
+
'save_button': "Save analysis",
|
733 |
+
'save_success': "Analysis saved successfully",
|
734 |
+
'save_error': "Error saving analysis",
|
735 |
+
'area_priority': "Priority area"
|
736 |
+
}
|
737 |
+
},
|
738 |
+
'uk': {
|
739 |
+
'basic_recommendations': {
|
740 |
+
'vocabulary': ["Розширте свій словниковий запас"],
|
741 |
+
'structure': ["Покращіть структуру ваших речень"],
|
742 |
+
'cohesion': ["Покращіть зв'язок між вашими ідеями"],
|
743 |
+
'clarity': ["Висловлюйте свої ідеї ясніше"],
|
744 |
+
'specific': ["Адаптуйте свій текст відповідно до його мети"],
|
745 |
+
},
|
746 |
+
'dimension_names': {
|
747 |
+
'vocabulary': 'Словниковий запас',
|
748 |
+
'structure': 'Структура',
|
749 |
+
'cohesion': 'Зв\'язність',
|
750 |
+
'clarity': 'Ясність',
|
751 |
+
'general': 'Загальне'
|
752 |
+
},
|
753 |
+
'ui_text': {
|
754 |
+
'priority_intro': "Це область, де ви повинні зосередити свої зусилля.",
|
755 |
+
'detailed_recommendations': "Детальні рекомендації",
|
756 |
+
'save_button': "Зберегти аналіз",
|
757 |
+
'save_success': "Аналіз успішно збережено",
|
758 |
+
'save_error': "Помилка при збереженні аналізу",
|
759 |
+
'area_priority': "Пріоритетна область"
|
760 |
+
}
|
761 |
+
},
|
762 |
+
'es': {
|
763 |
+
'basic_recommendations': {
|
764 |
+
'vocabulary': ["Intenta enriquecer tu vocabulario"],
|
765 |
+
'structure': ["Trabaja en la estructura de tus oraciones"],
|
766 |
+
'cohesion': ["Mejora la conexión entre tus ideas"],
|
767 |
+
'clarity': ["Busca expresar tus ideas con mayor claridad"],
|
768 |
+
'specific': ["Adapta tu texto según su propósito"],
|
769 |
+
},
|
770 |
+
'dimension_names': {
|
771 |
+
'vocabulary': 'Vocabulario',
|
772 |
+
'structure': 'Estructura',
|
773 |
+
'cohesion': 'Cohesión',
|
774 |
+
'clarity': 'Claridad',
|
775 |
+
'general': 'General'
|
776 |
+
},
|
777 |
+
'ui_text': {
|
778 |
+
'priority_intro': "Esta es el área donde debes concentrar tus esfuerzos.",
|
779 |
+
'detailed_recommendations': "Recomendaciones detalladas",
|
780 |
+
'save_button': "Guardar análisis",
|
781 |
+
'save_success': "Análisis guardado con éxito",
|
782 |
+
'save_error': "Error al guardar el análisis",
|
783 |
+
'area_priority': "Área prioritaria"
|
784 |
+
}
|
785 |
+
}
|
786 |
+
}
|
787 |
+
|
788 |
+
# Usar el idioma actual si está disponible, o inglés, o español como última opción
|
789 |
+
current_lang = fallback_translations.get(lang_code,
|
790 |
+
fallback_translations.get('en',
|
791 |
+
fallback_translations['es']))
|
792 |
+
|
793 |
+
basic_recommendations = current_lang['basic_recommendations']
|
794 |
+
|
795 |
+
return {
|
796 |
+
'vocabulary': basic_recommendations['vocabulary'],
|
797 |
+
'structure': basic_recommendations['structure'],
|
798 |
+
'cohesion': basic_recommendations['cohesion'],
|
799 |
+
'clarity': basic_recommendations['clarity'],
|
800 |
+
'specific': basic_recommendations['specific'],
|
801 |
+
'priority': {
|
802 |
+
'area': 'general',
|
803 |
+
'tips': ["Busca retroalimentación específica de un tutor o profesor"]
|
804 |
+
},
|
805 |
+
'dimension_names': current_lang['dimension_names'],
|
806 |
+
'ui_text': current_lang['ui_text']
|
807 |
+
}
|
808 |
+
|
809 |
+
|
810 |
+
|
811 |
+
|
812 |
+
#########################################################################
|
813 |
+
#########################################################################
|
814 |
+
# Funciones de generación de gráficos
|
815 |
+
def generate_sentence_graphs(doc):
|
816 |
+
"""Genera visualizaciones de estructura de oraciones"""
|
817 |
+
fig, ax = plt.subplots(figsize=(10, 6))
|
818 |
+
# Implementar visualización
|
819 |
+
plt.close()
|
820 |
+
return fig
|
821 |
+
|
822 |
+
############################################################################
|
823 |
+
def generate_word_connections(doc):
|
824 |
+
"""Genera red de conexiones de palabras"""
|
825 |
+
fig, ax = plt.subplots(figsize=(10, 6))
|
826 |
+
# Implementar visualización
|
827 |
+
plt.close()
|
828 |
+
return fig
|
829 |
+
|
830 |
+
############################################################################
|
831 |
+
def generate_connection_paths(doc):
|
832 |
+
"""Genera patrones de conexión"""
|
833 |
+
fig, ax = plt.subplots(figsize=(10, 6))
|
834 |
+
# Implementar visualización
|
835 |
+
plt.close()
|
836 |
+
return fig
|
837 |
+
|
838 |
+
############################################################################
|
839 |
+
def create_vocabulary_network(doc):
|
840 |
+
"""
|
841 |
+
Genera el grafo de red de vocabulario.
|
842 |
+
"""
|
843 |
+
G = nx.Graph()
|
844 |
+
|
845 |
+
# Crear nodos para palabras significativas
|
846 |
+
words = [token.text.lower() for token in doc if token.is_alpha and not token.is_stop]
|
847 |
+
word_freq = Counter(words)
|
848 |
+
|
849 |
+
# Añadir nodos con tamaño basado en frecuencia
|
850 |
+
for word, freq in word_freq.items():
|
851 |
+
G.add_node(word, size=freq)
|
852 |
+
|
853 |
+
# Crear conexiones basadas en co-ocurrencia
|
854 |
+
window_size = 5
|
855 |
+
for i in range(len(words) - window_size):
|
856 |
+
window = words[i:i+window_size]
|
857 |
+
for w1, w2 in combinations(set(window), 2):
|
858 |
+
if G.has_edge(w1, w2):
|
859 |
+
G[w1][w2]['weight'] += 1
|
860 |
+
else:
|
861 |
+
G.add_edge(w1, w2, weight=1)
|
862 |
+
|
863 |
+
# Crear visualización
|
864 |
+
fig, ax = plt.subplots(figsize=(12, 8))
|
865 |
+
pos = nx.spring_layout(G)
|
866 |
+
|
867 |
+
# Dibujar nodos
|
868 |
+
nx.draw_networkx_nodes(G, pos,
|
869 |
+
node_size=[G.nodes[node]['size']*100 for node in G.nodes],
|
870 |
+
node_color='lightblue',
|
871 |
+
alpha=0.7)
|
872 |
+
|
873 |
+
# Dibujar conexiones
|
874 |
+
nx.draw_networkx_edges(G, pos,
|
875 |
+
width=[G[u][v]['weight']*0.5 for u,v in G.edges],
|
876 |
+
alpha=0.5)
|
877 |
+
|
878 |
+
# Añadir etiquetas
|
879 |
+
nx.draw_networkx_labels(G, pos)
|
880 |
+
|
881 |
+
plt.title("Red de Vocabulario")
|
882 |
+
plt.axis('off')
|
883 |
+
return fig
|
884 |
+
|
885 |
+
############################################################################
|
886 |
+
def create_syntax_complexity_graph(doc):
|
887 |
+
"""
|
888 |
+
Genera el diagrama de arco de complejidad sintáctica.
|
889 |
+
Muestra la estructura de dependencias con colores basados en la complejidad.
|
890 |
+
"""
|
891 |
+
try:
|
892 |
+
# Preparar datos para la visualización
|
893 |
+
sentences = list(doc.sents)
|
894 |
+
if not sentences:
|
895 |
+
return None
|
896 |
+
|
897 |
+
# Crear figura para el gráfico
|
898 |
+
fig, ax = plt.subplots(figsize=(12, len(sentences) * 2))
|
899 |
+
|
900 |
+
# Colores para diferentes niveles de profundidad
|
901 |
+
depth_colors = plt.cm.viridis(np.linspace(0, 1, 6))
|
902 |
+
|
903 |
+
y_offset = 0
|
904 |
+
max_x = 0
|
905 |
+
|
906 |
+
for sent in sentences:
|
907 |
+
words = [token.text for token in sent]
|
908 |
+
x_positions = range(len(words))
|
909 |
+
max_x = max(max_x, len(words))
|
910 |
+
|
911 |
+
# Dibujar palabras
|
912 |
+
plt.plot(x_positions, [y_offset] * len(words), 'k-', alpha=0.2)
|
913 |
+
plt.scatter(x_positions, [y_offset] * len(words), alpha=0)
|
914 |
+
|
915 |
+
# Añadir texto
|
916 |
+
for i, word in enumerate(words):
|
917 |
+
plt.annotate(word, (i, y_offset), xytext=(0, -10),
|
918 |
+
textcoords='offset points', ha='center')
|
919 |
+
|
920 |
+
# Dibujar arcos de dependencia
|
921 |
+
for token in sent:
|
922 |
+
if token.dep_ != "ROOT":
|
923 |
+
# Calcular profundidad de dependencia
|
924 |
+
depth = 0
|
925 |
+
current = token
|
926 |
+
while current.head != current:
|
927 |
+
depth += 1
|
928 |
+
current = current.head
|
929 |
+
|
930 |
+
# Determinar posiciones para el arco
|
931 |
+
start = token.i - sent[0].i
|
932 |
+
end = token.head.i - sent[0].i
|
933 |
+
|
934 |
+
# Altura del arco basada en la distancia entre palabras
|
935 |
+
height = 0.5 * abs(end - start)
|
936 |
+
|
937 |
+
# Color basado en la profundidad
|
938 |
+
color = depth_colors[min(depth, len(depth_colors)-1)]
|
939 |
+
|
940 |
+
# Crear arco
|
941 |
+
arc = patches.Arc((min(start, end) + abs(end - start)/2, y_offset),
|
942 |
+
width=abs(end - start),
|
943 |
+
height=height,
|
944 |
+
angle=0,
|
945 |
+
theta1=0,
|
946 |
+
theta2=180,
|
947 |
+
color=color,
|
948 |
+
alpha=0.6)
|
949 |
+
ax.add_patch(arc)
|
950 |
+
|
951 |
+
y_offset -= 2
|
952 |
+
|
953 |
+
# Configurar el gráfico
|
954 |
+
plt.xlim(-1, max_x)
|
955 |
+
plt.ylim(y_offset - 1, 1)
|
956 |
+
plt.axis('off')
|
957 |
+
plt.title("Complejidad Sintáctica")
|
958 |
+
|
959 |
+
return fig
|
960 |
+
|
961 |
+
except Exception as e:
|
962 |
+
logger.error(f"Error en create_syntax_complexity_graph: {str(e)}")
|
963 |
+
return None
|
964 |
+
|
965 |
+
############################################################################
|
966 |
+
def create_cohesion_heatmap(doc):
|
967 |
+
"""Genera un mapa de calor que muestra la cohesión entre párrafos/oraciones."""
|
968 |
+
try:
|
969 |
+
sentences = list(doc.sents)
|
970 |
+
n_sentences = len(sentences)
|
971 |
+
|
972 |
+
if n_sentences < 2:
|
973 |
+
return None
|
974 |
+
|
975 |
+
similarity_matrix = np.zeros((n_sentences, n_sentences))
|
976 |
+
|
977 |
+
for i in range(n_sentences):
|
978 |
+
for j in range(n_sentences):
|
979 |
+
sent1_lemmas = {token.lemma_ for token in sentences[i]
|
980 |
+
if token.is_alpha and not token.is_stop}
|
981 |
+
sent2_lemmas = {token.lemma_ for token in sentences[j]
|
982 |
+
if token.is_alpha and not token.is_stop}
|
983 |
+
|
984 |
+
if sent1_lemmas and sent2_lemmas:
|
985 |
+
intersection = len(sent1_lemmas & sent2_lemmas) # Corregido aquí
|
986 |
+
union = len(sent1_lemmas | sent2_lemmas) # Y aquí
|
987 |
+
similarity_matrix[i, j] = intersection / union if union > 0 else 0
|
988 |
+
|
989 |
+
# Crear visualización
|
990 |
+
fig, ax = plt.subplots(figsize=(10, 8))
|
991 |
+
|
992 |
+
sns.heatmap(similarity_matrix,
|
993 |
+
cmap='YlOrRd',
|
994 |
+
square=True,
|
995 |
+
xticklabels=False,
|
996 |
+
yticklabels=False,
|
997 |
+
cbar_kws={'label': 'Cohesión'},
|
998 |
+
ax=ax)
|
999 |
+
|
1000 |
+
plt.title("Mapa de Cohesión Textual")
|
1001 |
+
plt.xlabel("Oraciones")
|
1002 |
+
plt.ylabel("Oraciones")
|
1003 |
+
|
1004 |
+
plt.tight_layout()
|
1005 |
+
return fig
|
1006 |
+
|
1007 |
+
except Exception as e:
|
1008 |
+
logger.error(f"Error en create_cohesion_heatmap: {str(e)}")
|
1009 |
+
return None
|
modules/studentact/current_situation_interface.py
CHANGED
@@ -1,321 +1,436 @@
|
|
1 |
-
# modules/studentact/current_situation_interface.py
|
2 |
-
|
3 |
-
import streamlit as st
|
4 |
-
import logging
|
5 |
-
from ..utils.widget_utils import generate_unique_key
|
6 |
-
import matplotlib.pyplot as plt
|
7 |
-
import numpy as np
|
8 |
-
from ..database.current_situation_mongo_db import store_current_situation_result
|
9 |
-
|
10 |
-
# Importaciones locales
|
11 |
-
from translations import get_translations
|
12 |
-
|
13 |
-
# Importamos la función de recomendaciones personalizadas si existe
|
14 |
-
try:
|
15 |
-
from .claude_recommendations import display_personalized_recommendations
|
16 |
-
except ImportError:
|
17 |
-
# Si no existe el módulo, definimos una función placeholder
|
18 |
-
def display_personalized_recommendations(text, metrics, text_type, lang_code, t):
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
plt.rcParams['
|
41 |
-
plt.rcParams['axes.
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
'
|
53 |
-
'
|
54 |
-
'
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
'thresholds': {
|
60 |
-
'vocabulary': {'min': 0.60, 'target': 0.75},
|
61 |
-
'structure': {'min': 0.65, 'target': 0.80},
|
62 |
-
'cohesion': {'min': 0.55, 'target': 0.70},
|
63 |
-
'clarity': {'min': 0.60, 'target': 0.75}
|
64 |
-
}
|
65 |
-
},
|
66 |
-
'general_communication': {
|
67 |
-
'
|
68 |
-
|
69 |
-
'
|
70 |
-
'
|
71 |
-
'
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
def display_current_situation_interface(lang_code, nlp_models, t):
|
79 |
-
"""
|
80 |
-
Interfaz simplificada con gráfico de radar para visualizar métricas.
|
81 |
-
"""
|
82 |
-
#
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
if '
|
88 |
-
st.session_state.
|
89 |
-
if '
|
90 |
-
st.session_state.
|
91 |
-
if '
|
92 |
-
st.session_state.
|
93 |
-
if '
|
94 |
-
st.session_state.
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
-
|
144 |
-
|
145 |
-
|
146 |
-
|
147 |
-
|
148 |
-
|
149 |
-
|
150 |
-
|
151 |
-
|
152 |
-
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
|
158 |
-
|
159 |
-
|
160 |
-
|
161 |
-
|
162 |
-
|
163 |
-
|
164 |
-
|
165 |
-
|
166 |
-
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
)
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
212 |
-
|
213 |
-
'
|
214 |
-
'
|
215 |
-
|
216 |
-
|
217 |
-
|
218 |
-
|
219 |
-
|
220 |
-
|
221 |
-
|
222 |
-
|
223 |
-
|
224 |
-
|
225 |
-
|
226 |
-
|
227 |
-
|
228 |
-
|
229 |
-
|
230 |
-
|
231 |
-
|
232 |
-
|
233 |
-
|
234 |
-
|
235 |
-
|
236 |
-
|
237 |
-
|
238 |
-
|
239 |
-
|
240 |
-
|
241 |
-
|
242 |
-
|
243 |
-
|
244 |
-
|
245 |
-
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
|
250 |
-
|
251 |
-
|
252 |
-
|
253 |
-
|
254 |
-
|
255 |
-
|
256 |
-
|
257 |
-
|
258 |
-
|
259 |
-
|
260 |
-
|
261 |
-
|
262 |
-
|
263 |
-
|
264 |
-
|
265 |
-
|
266 |
-
|
267 |
-
|
268 |
-
|
269 |
-
|
270 |
-
|
271 |
-
|
272 |
-
|
273 |
-
|
274 |
-
|
275 |
-
|
276 |
-
|
277 |
-
|
278 |
-
|
279 |
-
|
280 |
-
|
281 |
-
|
282 |
-
|
283 |
-
|
284 |
-
|
285 |
-
|
286 |
-
|
287 |
-
|
288 |
-
|
289 |
-
|
290 |
-
|
291 |
-
|
292 |
-
|
293 |
-
|
294 |
-
|
295 |
-
|
296 |
-
|
297 |
-
|
298 |
-
|
299 |
-
|
300 |
-
|
301 |
-
|
302 |
-
|
303 |
-
|
304 |
-
|
305 |
-
|
306 |
-
|
307 |
-
|
308 |
-
|
309 |
-
|
310 |
-
|
311 |
-
|
312 |
-
|
313 |
-
|
314 |
-
|
315 |
-
|
316 |
-
|
317 |
-
|
318 |
-
|
319 |
-
|
320 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
321 |
st.error("Error al mostrar el gráfico")
|
|
|
1 |
+
# modules/studentact/current_situation_interface.py
|
2 |
+
|
3 |
+
import streamlit as st
|
4 |
+
import logging
|
5 |
+
from ..utils.widget_utils import generate_unique_key
|
6 |
+
import matplotlib.pyplot as plt
|
7 |
+
import numpy as np
|
8 |
+
from ..database.current_situation_mongo_db import store_current_situation_result
|
9 |
+
|
10 |
+
# Importaciones locales
|
11 |
+
from translations import get_translations
|
12 |
+
|
13 |
+
# Importamos la función de recomendaciones personalizadas si existe
|
14 |
+
try:
|
15 |
+
from .claude_recommendations import display_personalized_recommendations
|
16 |
+
except ImportError:
|
17 |
+
# Si no existe el módulo, definimos una función placeholder
|
18 |
+
def display_personalized_recommendations(text, metrics, text_type, lang_code, t):
|
19 |
+
# Obtener el mensaje de advertencia traducido si está disponible
|
20 |
+
warning = t.get('module_not_available', "Módulo de recomendaciones personalizadas no disponible. Por favor, contacte al administrador.")
|
21 |
+
st.warning(warning)
|
22 |
+
|
23 |
+
from .current_situation_analysis import (
|
24 |
+
analyze_text_dimensions,
|
25 |
+
analyze_clarity,
|
26 |
+
analyze_vocabulary_diversity,
|
27 |
+
analyze_cohesion,
|
28 |
+
analyze_structure,
|
29 |
+
get_dependency_depths,
|
30 |
+
normalize_score,
|
31 |
+
generate_sentence_graphs,
|
32 |
+
generate_word_connections,
|
33 |
+
generate_connection_paths,
|
34 |
+
create_vocabulary_network,
|
35 |
+
create_syntax_complexity_graph,
|
36 |
+
create_cohesion_heatmap
|
37 |
+
)
|
38 |
+
|
39 |
+
# Configuración del estilo de matplotlib para el gráfico de radar
|
40 |
+
plt.rcParams['font.family'] = 'sans-serif'
|
41 |
+
plt.rcParams['axes.grid'] = True
|
42 |
+
plt.rcParams['axes.spines.top'] = False
|
43 |
+
plt.rcParams['axes.spines.right'] = False
|
44 |
+
|
45 |
+
logger = logging.getLogger(__name__)
|
46 |
+
|
47 |
+
# Definición de tipos de texto con umbrales
|
48 |
+
TEXT_TYPES = {
|
49 |
+
'academic_article': {
|
50 |
+
# Los nombres se obtendrán de las traducciones
|
51 |
+
'thresholds': {
|
52 |
+
'vocabulary': {'min': 0.70, 'target': 0.85},
|
53 |
+
'structure': {'min': 0.75, 'target': 0.90},
|
54 |
+
'cohesion': {'min': 0.65, 'target': 0.80},
|
55 |
+
'clarity': {'min': 0.70, 'target': 0.85}
|
56 |
+
}
|
57 |
+
},
|
58 |
+
'student_essay': {
|
59 |
+
'thresholds': {
|
60 |
+
'vocabulary': {'min': 0.60, 'target': 0.75},
|
61 |
+
'structure': {'min': 0.65, 'target': 0.80},
|
62 |
+
'cohesion': {'min': 0.55, 'target': 0.70},
|
63 |
+
'clarity': {'min': 0.60, 'target': 0.75}
|
64 |
+
}
|
65 |
+
},
|
66 |
+
'general_communication': {
|
67 |
+
'thresholds': {
|
68 |
+
'vocabulary': {'min': 0.50, 'target': 0.65},
|
69 |
+
'structure': {'min': 0.55, 'target': 0.70},
|
70 |
+
'cohesion': {'min': 0.45, 'target': 0.60},
|
71 |
+
'clarity': {'min': 0.50, 'target': 0.65}
|
72 |
+
}
|
73 |
+
}
|
74 |
+
}
|
75 |
+
|
76 |
+
####################################################
|
77 |
+
####################################################
|
78 |
+
def display_current_situation_interface(lang_code, nlp_models, t):
|
79 |
+
"""
|
80 |
+
Interfaz simplificada con gráfico de radar para visualizar métricas.
|
81 |
+
"""
|
82 |
+
# Agregar logs para depuración
|
83 |
+
logger.info(f"Idioma: {lang_code}")
|
84 |
+
logger.info(f"Claves en t: {list(t.keys())}")
|
85 |
+
|
86 |
+
# Inicializar estados si no existen
|
87 |
+
if 'text_input' not in st.session_state:
|
88 |
+
st.session_state.text_input = ""
|
89 |
+
if 'text_area' not in st.session_state:
|
90 |
+
st.session_state.text_area = ""
|
91 |
+
if 'show_results' not in st.session_state:
|
92 |
+
st.session_state.show_results = False
|
93 |
+
if 'current_doc' not in st.session_state:
|
94 |
+
st.session_state.current_doc = None
|
95 |
+
if 'current_metrics' not in st.session_state:
|
96 |
+
st.session_state.current_metrics = None
|
97 |
+
if 'current_recommendations' not in st.session_state:
|
98 |
+
st.session_state.current_recommendations = None
|
99 |
+
|
100 |
+
try:
|
101 |
+
# Container principal con dos columnas
|
102 |
+
with st.container():
|
103 |
+
input_col, results_col = st.columns([1,2])
|
104 |
+
|
105 |
+
###############################################################################################
|
106 |
+
# CSS personalizado para que el formulario ocupe todo el alto disponible
|
107 |
+
st.markdown("""
|
108 |
+
<style>
|
109 |
+
/* Hacer que la columna tenga una altura definida */
|
110 |
+
[data-testid="column"] {
|
111 |
+
min-height: 900px;
|
112 |
+
height: 100vh; /* 100% del alto visible de la ventana */
|
113 |
+
}
|
114 |
+
|
115 |
+
/* Hacer que el formulario ocupe el espacio disponible en la columna */
|
116 |
+
.stForm {
|
117 |
+
height: calc(100% - 40px); /* Ajuste por márgenes y paddings */
|
118 |
+
display: flex;
|
119 |
+
flex-direction: column;
|
120 |
+
}
|
121 |
+
|
122 |
+
/* Hacer que el área de texto se expanda dentro del formulario */
|
123 |
+
.stForm .stTextArea {
|
124 |
+
flex: 1;
|
125 |
+
display: flex;
|
126 |
+
flex-direction: column;
|
127 |
+
}
|
128 |
+
|
129 |
+
/* El textarea en sí debe expandirse */
|
130 |
+
.stForm .stTextArea textarea {
|
131 |
+
flex: 1;
|
132 |
+
min-height: 750px !important;
|
133 |
+
}
|
134 |
+
</style>
|
135 |
+
""", unsafe_allow_html=True)
|
136 |
+
|
137 |
+
###############################################################################################
|
138 |
+
with input_col:
|
139 |
+
with st.form(key=f"text_input_form_{lang_code}"):
|
140 |
+
text_input = st.text_area(
|
141 |
+
t.get('input_prompt', "Escribe o pega tu texto aquí:"),
|
142 |
+
height=800,
|
143 |
+
key=f"text_area_{lang_code}",
|
144 |
+
value=st.session_state.text_input,
|
145 |
+
help=t.get('help', "Este texto será analizado para darte recomendaciones personalizadas")
|
146 |
+
)
|
147 |
+
|
148 |
+
submit_button = st.form_submit_button(
|
149 |
+
t.get('analyze_button', "Analizar mi escritura"),
|
150 |
+
type="primary",
|
151 |
+
use_container_width=True
|
152 |
+
)
|
153 |
+
|
154 |
+
if submit_button:
|
155 |
+
if text_input.strip():
|
156 |
+
st.session_state.text_input = text_input
|
157 |
+
|
158 |
+
#######################################################################
|
159 |
+
# Código para análisis...
|
160 |
+
try:
|
161 |
+
with st.spinner(t.get('processing', "Analizando...")): # Usando t.get directamente
|
162 |
+
doc = nlp_models[lang_code](text_input)
|
163 |
+
metrics = analyze_text_dimensions(doc)
|
164 |
+
|
165 |
+
storage_success = store_current_situation_result(
|
166 |
+
username=st.session_state.username,
|
167 |
+
text=text_input,
|
168 |
+
metrics=metrics,
|
169 |
+
feedback=None
|
170 |
+
)
|
171 |
+
|
172 |
+
if not storage_success:
|
173 |
+
logger.warning("No se pudo guardar el análisis en la base de datos")
|
174 |
+
|
175 |
+
st.session_state.current_doc = doc
|
176 |
+
st.session_state.current_metrics = metrics
|
177 |
+
st.session_state.show_results = True
|
178 |
+
|
179 |
+
except Exception as e:
|
180 |
+
logger.error(f"Error en análisis: {str(e)}")
|
181 |
+
st.error(t.get('analysis_error', "Error al analizar el texto")) # Usando t.get directamente
|
182 |
+
|
183 |
+
# Mostrar resultados en la columna derecha
|
184 |
+
with results_col:
|
185 |
+
if st.session_state.show_results and st.session_state.current_metrics is not None:
|
186 |
+
# Primero los radio buttons para tipo de texto - usando t.get directamente
|
187 |
+
st.markdown(f"### {t.get('text_type_header', 'Tipo de texto')}")
|
188 |
+
|
189 |
+
# Preparar opciones de tipos de texto con nombres traducidos
|
190 |
+
text_type_options = {}
|
191 |
+
for text_type_key in TEXT_TYPES.keys():
|
192 |
+
# Fallback a nombres genéricos si no hay traducción
|
193 |
+
default_names = {
|
194 |
+
'academic_article': 'Academic Article' if lang_code == 'en' else 'Артикул академічний' if lang_code == 'uk' else 'Artículo Académico',
|
195 |
+
'student_essay': 'Student Essay' if lang_code == 'en' else 'Студентське есе' if lang_code == 'uk' else 'Trabajo Universitario',
|
196 |
+
'general_communication': 'General Communication' if lang_code == 'en' else 'Загальна комунікація' if lang_code == 'uk' else 'Comunicación General'
|
197 |
+
}
|
198 |
+
text_type_options[text_type_key] = default_names.get(text_type_key, text_type_key)
|
199 |
+
|
200 |
+
text_type = st.radio(
|
201 |
+
label=t.get('text_type_header', "Tipo de texto"), # Usando t.get directamente
|
202 |
+
options=list(TEXT_TYPES.keys()),
|
203 |
+
format_func=lambda x: text_type_options.get(x, x),
|
204 |
+
horizontal=True,
|
205 |
+
key="text_type_radio",
|
206 |
+
label_visibility="collapsed",
|
207 |
+
help=t.get('text_type_help', "Selecciona el tipo de texto para ajustar los criterios de evaluación") # Usando t.get directamente
|
208 |
+
)
|
209 |
+
|
210 |
+
st.session_state.current_text_type = text_type
|
211 |
+
|
212 |
+
# Crear subtabs con nombres traducidos
|
213 |
+
diagnosis_tab = "Diagnosis" if lang_code == 'en' else "Діагностика" if lang_code == 'uk' else "Diagnóstico"
|
214 |
+
recommendations_tab = "Recommendations" if lang_code == 'en' else "Рекомендації" if lang_code == 'uk' else "Recomendaciones"
|
215 |
+
|
216 |
+
subtab1, subtab2 = st.tabs([diagnosis_tab, recommendations_tab])
|
217 |
+
|
218 |
+
# Mostrar resultados en el primer subtab
|
219 |
+
with subtab1:
|
220 |
+
display_diagnosis(
|
221 |
+
metrics=st.session_state.current_metrics,
|
222 |
+
text_type=text_type,
|
223 |
+
lang_code=lang_code,
|
224 |
+
t=t # Pasar t directamente, no current_situation_t
|
225 |
+
)
|
226 |
+
|
227 |
+
# Mostrar recomendaciones en el segundo subtab
|
228 |
+
with subtab2:
|
229 |
+
# Llamar directamente a la función de recomendaciones personalizadas
|
230 |
+
display_personalized_recommendations(
|
231 |
+
text=text_input,
|
232 |
+
metrics=st.session_state.current_metrics,
|
233 |
+
text_type=text_type,
|
234 |
+
lang_code=lang_code,
|
235 |
+
t=t
|
236 |
+
)
|
237 |
+
|
238 |
+
except Exception as e:
|
239 |
+
logger.error(f"Error en interfaz principal: {str(e)}")
|
240 |
+
st.error(t.get('error_interface', "Ocurrió un error al cargar la interfaz")) # Usando t.get directamente
|
241 |
+
|
242 |
+
#################################################################
|
243 |
+
#################################################################
|
244 |
+
def display_diagnosis(metrics, text_type=None, lang_code='es', t=None):
|
245 |
+
"""
|
246 |
+
Muestra los resultados del análisis: métricas verticalmente y gráfico radar.
|
247 |
+
"""
|
248 |
+
try:
|
249 |
+
# Asegurar que tenemos traducciones
|
250 |
+
if t is None:
|
251 |
+
t = {}
|
252 |
+
|
253 |
+
# Traducciones para títulos y etiquetas
|
254 |
+
dimension_labels = {
|
255 |
+
'es': {
|
256 |
+
'title': "Tipo de texto",
|
257 |
+
'vocabulary': "Vocabulario",
|
258 |
+
'structure': "Estructura",
|
259 |
+
'cohesion': "Cohesión",
|
260 |
+
'clarity': "Claridad",
|
261 |
+
'improvement': "⚠️ Por mejorar",
|
262 |
+
'acceptable': "📈 Aceptable",
|
263 |
+
'optimal': "✅ Óptimo",
|
264 |
+
'target': "Meta: {:.2f}"
|
265 |
+
},
|
266 |
+
'en': {
|
267 |
+
'title': "Text Type",
|
268 |
+
'vocabulary': "Vocabulary",
|
269 |
+
'structure': "Structure",
|
270 |
+
'cohesion': "Cohesion",
|
271 |
+
'clarity': "Clarity",
|
272 |
+
'improvement': "⚠️ Needs improvement",
|
273 |
+
'acceptable': "📈 Acceptable",
|
274 |
+
'optimal': "✅ Optimal",
|
275 |
+
'target': "Target: {:.2f}"
|
276 |
+
},
|
277 |
+
'uk': {
|
278 |
+
'title': "Тип тексту",
|
279 |
+
'vocabulary': "Словниковий запас",
|
280 |
+
'structure': "Структура",
|
281 |
+
'cohesion': "Зв'язність",
|
282 |
+
'clarity': "Ясність",
|
283 |
+
'improvement': "⚠️ Потребує покращення",
|
284 |
+
'acceptable': "📈 Прийнятно",
|
285 |
+
'optimal': "✅ Оптимально",
|
286 |
+
'target': "Ціль: {:.2f}"
|
287 |
+
}
|
288 |
+
}
|
289 |
+
|
290 |
+
# Obtener traducciones para el idioma actual, con fallback a español
|
291 |
+
labels = dimension_labels.get(lang_code, dimension_labels['es'])
|
292 |
+
|
293 |
+
# Usar valor por defecto si no se especifica tipo
|
294 |
+
text_type = text_type or 'student_essay'
|
295 |
+
|
296 |
+
# Obtener umbrales según el tipo de texto
|
297 |
+
thresholds = TEXT_TYPES[text_type]['thresholds']
|
298 |
+
|
299 |
+
# Crear dos columnas para las métricas y el gráfico
|
300 |
+
metrics_col, graph_col = st.columns([1, 1.5])
|
301 |
+
|
302 |
+
# Columna de métricas
|
303 |
+
with metrics_col:
|
304 |
+
metrics_config = [
|
305 |
+
{
|
306 |
+
'label': labels['vocabulary'],
|
307 |
+
'key': 'vocabulary',
|
308 |
+
'value': metrics['vocabulary']['normalized_score'],
|
309 |
+
'help': t.get('vocabulary_help', "Riqueza y variedad del vocabulario"),
|
310 |
+
'thresholds': thresholds['vocabulary']
|
311 |
+
},
|
312 |
+
{
|
313 |
+
'label': labels['structure'],
|
314 |
+
'key': 'structure',
|
315 |
+
'value': metrics['structure']['normalized_score'],
|
316 |
+
'help': t.get('structure_help', "Organización y complejidad de oraciones"),
|
317 |
+
'thresholds': thresholds['structure']
|
318 |
+
},
|
319 |
+
{
|
320 |
+
'label': labels['cohesion'],
|
321 |
+
'key': 'cohesion',
|
322 |
+
'value': metrics['cohesion']['normalized_score'],
|
323 |
+
'help': t.get('cohesion_help', "Conexión y fluidez entre ideas"),
|
324 |
+
'thresholds': thresholds['cohesion']
|
325 |
+
},
|
326 |
+
{
|
327 |
+
'label': labels['clarity'],
|
328 |
+
'key': 'clarity',
|
329 |
+
'value': metrics['clarity']['normalized_score'],
|
330 |
+
'help': t.get('clarity_help', "Facilidad de comprensión del texto"),
|
331 |
+
'thresholds': thresholds['clarity']
|
332 |
+
}
|
333 |
+
]
|
334 |
+
|
335 |
+
# Mostrar métricas con textos traducidos
|
336 |
+
for metric in metrics_config:
|
337 |
+
value = metric['value']
|
338 |
+
if value < metric['thresholds']['min']:
|
339 |
+
status = labels['improvement']
|
340 |
+
color = "inverse"
|
341 |
+
elif value < metric['thresholds']['target']:
|
342 |
+
status = labels['acceptable']
|
343 |
+
color = "off"
|
344 |
+
else:
|
345 |
+
status = labels['optimal']
|
346 |
+
color = "normal"
|
347 |
+
|
348 |
+
target_text = labels['target'].format(metric['thresholds']['target'])
|
349 |
+
|
350 |
+
st.metric(
|
351 |
+
metric['label'],
|
352 |
+
f"{value:.2f}",
|
353 |
+
f"{status} ({target_text})",
|
354 |
+
delta_color=color,
|
355 |
+
help=metric['help']
|
356 |
+
)
|
357 |
+
st.markdown("<div style='margin-bottom: 0.5rem;'></div>", unsafe_allow_html=True)
|
358 |
+
|
359 |
+
# Gráfico radar en la columna derecha
|
360 |
+
with graph_col:
|
361 |
+
display_radar_chart(metrics_config, thresholds, lang_code) # Pasar el parámetro lang_code
|
362 |
+
|
363 |
+
except Exception as e:
|
364 |
+
logger.error(f"Error mostrando resultados: {str(e)}")
|
365 |
+
st.error(t.get('error_results', "Error al mostrar los resultados"))
|
366 |
+
|
367 |
+
##################################################################
|
368 |
+
##################################################################
|
369 |
+
def display_radar_chart(metrics_config, thresholds, lang_code='es'):
|
370 |
+
"""
|
371 |
+
Muestra el gráfico radar con los resultados.
|
372 |
+
"""
|
373 |
+
try:
|
374 |
+
# Traducción de las etiquetas de leyenda según el idioma
|
375 |
+
legend_translations = {
|
376 |
+
'es': {'min': 'Mínimo', 'target': 'Meta', 'user': 'Tu escritura'},
|
377 |
+
'en': {'min': 'Minimum', 'target': 'Target', 'user': 'Your writing'},
|
378 |
+
'uk': {'min': 'Мінімум', 'target': 'Ціль', 'user': 'Ваш текст'}
|
379 |
+
}
|
380 |
+
|
381 |
+
# Usar español por defecto si el idioma no está soportado
|
382 |
+
translations = legend_translations.get(lang_code, legend_translations['es'])
|
383 |
+
|
384 |
+
# Preparar datos para el gráfico
|
385 |
+
categories = [m['label'] for m in metrics_config]
|
386 |
+
values_user = [m['value'] for m in metrics_config]
|
387 |
+
min_values = [m['thresholds']['min'] for m in metrics_config]
|
388 |
+
target_values = [m['thresholds']['target'] for m in metrics_config]
|
389 |
+
|
390 |
+
# Crear y configurar gráfico
|
391 |
+
fig = plt.figure(figsize=(8, 8))
|
392 |
+
ax = fig.add_subplot(111, projection='polar')
|
393 |
+
|
394 |
+
# Configurar radar
|
395 |
+
angles = [n / float(len(categories)) * 2 * np.pi for n in range(len(categories))]
|
396 |
+
angles += angles[:1]
|
397 |
+
values_user += values_user[:1]
|
398 |
+
min_values += min_values[:1]
|
399 |
+
target_values += target_values[:1]
|
400 |
+
|
401 |
+
# Configurar ejes
|
402 |
+
ax.set_xticks(angles[:-1])
|
403 |
+
ax.set_xticklabels(categories, fontsize=10)
|
404 |
+
circle_ticks = np.arange(0, 1.1, 0.2)
|
405 |
+
ax.set_yticks(circle_ticks)
|
406 |
+
ax.set_yticklabels([f'{tick:.1f}' for tick in circle_ticks], fontsize=8)
|
407 |
+
ax.set_ylim(0, 1)
|
408 |
+
|
409 |
+
# Dibujar áreas de umbrales con etiquetas traducidas
|
410 |
+
ax.plot(angles, min_values, '#e74c3c', linestyle='--', linewidth=1, label=translations['min'], alpha=0.5)
|
411 |
+
ax.plot(angles, target_values, '#2ecc71', linestyle='--', linewidth=1, label=translations['target'], alpha=0.5)
|
412 |
+
ax.fill_between(angles, target_values, [1]*len(angles), color='#2ecc71', alpha=0.1)
|
413 |
+
ax.fill_between(angles, [0]*len(angles), min_values, color='#e74c3c', alpha=0.1)
|
414 |
+
|
415 |
+
# Dibujar valores del usuario con etiqueta traducida
|
416 |
+
ax.plot(angles, values_user, '#3498db', linewidth=2, label=translations['user'])
|
417 |
+
ax.fill(angles, values_user, '#3498db', alpha=0.2)
|
418 |
+
|
419 |
+
# Ajustar leyenda
|
420 |
+
ax.legend(
|
421 |
+
loc='upper right',
|
422 |
+
bbox_to_anchor=(1.3, 1.1),
|
423 |
+
fontsize=10,
|
424 |
+
frameon=True,
|
425 |
+
facecolor='white',
|
426 |
+
edgecolor='none',
|
427 |
+
shadow=True
|
428 |
+
)
|
429 |
+
|
430 |
+
plt.tight_layout()
|
431 |
+
st.pyplot(fig)
|
432 |
+
plt.close()
|
433 |
+
|
434 |
+
except Exception as e:
|
435 |
+
logger.error(f"Error mostrando gráfico radar: {str(e)}")
|
436 |
st.error("Error al mostrar el gráfico")
|
modules/studentact/student_activities_v2.py
CHANGED
@@ -1,571 +1,576 @@
|
|
1 |
-
|
2 |
-
###modules/studentact/student_activities_v2.py
|
3 |
-
|
4 |
-
import streamlit as st
|
5 |
-
import re
|
6 |
-
import io
|
7 |
-
from io import BytesIO
|
8 |
-
import pandas as pd
|
9 |
-
import numpy as np
|
10 |
-
import time
|
11 |
-
import matplotlib.pyplot as plt
|
12 |
-
from datetime import datetime, timedelta
|
13 |
-
from spacy import displacy
|
14 |
-
import random
|
15 |
-
import base64
|
16 |
-
import seaborn as sns
|
17 |
-
import logging
|
18 |
-
|
19 |
-
# Importaciones de la base de datos
|
20 |
-
from ..database.morphosintax_mongo_db import get_student_morphosyntax_analysis
|
21 |
-
from ..database.semantic_mongo_db import get_student_semantic_analysis
|
22 |
-
from ..database.discourse_mongo_db import get_student_discourse_analysis
|
23 |
-
from ..database.chat_mongo_db import get_chat_history
|
24 |
-
from ..database.current_situation_mongo_db import get_current_situation_analysis
|
25 |
-
from ..database.claude_recommendations_mongo_db import get_claude_recommendations
|
26 |
-
|
27 |
-
# Importar la función generate_unique_key
|
28 |
-
from ..utils.widget_utils import generate_unique_key
|
29 |
-
|
30 |
-
logger = logging.getLogger(__name__)
|
31 |
-
|
32 |
-
###################################################################################
|
33 |
-
|
34 |
-
def display_student_activities(username: str, lang_code: str, t: dict):
|
35 |
-
"""
|
36 |
-
Muestra todas las actividades del estudiante
|
37 |
-
Args:
|
38 |
-
username: Nombre del estudiante
|
39 |
-
lang_code: Código del idioma
|
40 |
-
t: Diccionario de traducciones
|
41 |
-
"""
|
42 |
-
try:
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
t.get('
|
50 |
-
t.get('
|
51 |
-
t.get('
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
logger.
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
-
|
144 |
-
|
145 |
-
|
146 |
-
|
147 |
-
|
148 |
-
|
149 |
-
|
150 |
-
|
151 |
-
|
152 |
-
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
|
158 |
-
|
159 |
-
|
160 |
-
|
161 |
-
|
162 |
-
|
163 |
-
|
164 |
-
|
165 |
-
|
166 |
-
|
167 |
-
'
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
212 |
-
|
213 |
-
|
214 |
-
|
215 |
-
|
216 |
-
|
217 |
-
|
218 |
-
|
219 |
-
|
220 |
-
|
221 |
-
|
222 |
-
|
223 |
-
|
224 |
-
'
|
225 |
-
|
226 |
-
|
227 |
-
|
228 |
-
|
229 |
-
|
230 |
-
|
231 |
-
|
232 |
-
|
233 |
-
title += f" 🔄 (emparejados
|
234 |
-
|
235 |
-
|
236 |
-
|
237 |
-
|
238 |
-
|
239 |
-
|
240 |
-
|
241 |
-
|
242 |
-
|
243 |
-
|
244 |
-
|
245 |
-
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
|
250 |
-
|
251 |
-
|
252 |
-
|
253 |
-
|
254 |
-
|
255 |
-
|
256 |
-
|
257 |
-
|
258 |
-
|
259 |
-
|
260 |
-
|
261 |
-
|
262 |
-
|
263 |
-
|
264 |
-
|
265 |
-
|
266 |
-
|
267 |
-
|
268 |
-
|
269 |
-
|
270 |
-
|
271 |
-
|
272 |
-
|
273 |
-
|
274 |
-
|
275 |
-
|
276 |
-
|
277 |
-
|
278 |
-
|
279 |
-
score = metric_data['
|
280 |
-
elif '
|
281 |
-
score = metric_data['
|
282 |
-
|
283 |
-
|
284 |
-
|
285 |
-
|
286 |
-
|
287 |
-
|
288 |
-
|
289 |
-
|
290 |
-
|
291 |
-
|
292 |
-
|
293 |
-
|
294 |
-
|
295 |
-
|
296 |
-
|
297 |
-
|
298 |
-
|
299 |
-
|
300 |
-
|
301 |
-
|
302 |
-
|
303 |
-
|
304 |
-
|
305 |
-
|
306 |
-
|
307 |
-
|
308 |
-
|
309 |
-
|
310 |
-
|
311 |
-
|
312 |
-
|
313 |
-
|
314 |
-
|
315 |
-
|
316 |
-
|
317 |
-
|
318 |
-
|
319 |
-
|
320 |
-
|
321 |
-
|
322 |
-
|
323 |
-
|
324 |
-
|
325 |
-
|
326 |
-
|
327 |
-
|
328 |
-
|
329 |
-
|
330 |
-
|
331 |
-
|
332 |
-
|
333 |
-
|
334 |
-
|
335 |
-
|
336 |
-
|
337 |
-
|
338 |
-
|
339 |
-
|
340 |
-
|
341 |
-
|
342 |
-
|
343 |
-
|
344 |
-
|
345 |
-
|
346 |
-
|
347 |
-
|
348 |
-
|
349 |
-
|
350 |
-
|
351 |
-
|
352 |
-
|
353 |
-
|
354 |
-
|
355 |
-
|
356 |
-
|
357 |
-
|
358 |
-
|
359 |
-
|
360 |
-
|
361 |
-
|
362 |
-
|
363 |
-
|
364 |
-
|
365 |
-
|
366 |
-
|
367 |
-
|
368 |
-
|
369 |
-
|
370 |
-
|
371 |
-
|
372 |
-
|
373 |
-
|
374 |
-
|
375 |
-
|
376 |
-
|
377 |
-
|
378 |
-
|
379 |
-
|
380 |
-
|
381 |
-
|
382 |
-
|
383 |
-
|
384 |
-
|
385 |
-
|
386 |
-
|
387 |
-
|
388 |
-
|
389 |
-
|
390 |
-
|
391 |
-
|
392 |
-
|
393 |
-
|
394 |
-
|
395 |
-
|
396 |
-
|
397 |
-
|
398 |
-
|
399 |
-
|
400 |
-
|
401 |
-
|
402 |
-
|
403 |
-
|
404 |
-
|
405 |
-
|
406 |
-
|
407 |
-
|
408 |
-
|
409 |
-
|
410 |
-
|
411 |
-
|
412 |
-
|
413 |
-
|
414 |
-
|
415 |
-
|
416 |
-
|
417 |
-
|
418 |
-
|
419 |
-
|
420 |
-
|
421 |
-
|
422 |
-
|
423 |
-
|
424 |
-
|
425 |
-
|
426 |
-
|
427 |
-
|
428 |
-
|
429 |
-
|
430 |
-
|
431 |
-
|
432 |
-
|
433 |
-
|
434 |
-
|
435 |
-
|
436 |
-
|
437 |
-
|
438 |
-
|
439 |
-
|
440 |
-
|
441 |
-
|
442 |
-
|
443 |
-
|
444 |
-
|
445 |
-
|
446 |
-
|
447 |
-
|
448 |
-
|
449 |
-
|
450 |
-
|
451 |
-
|
452 |
-
|
453 |
-
|
454 |
-
|
455 |
-
|
456 |
-
|
457 |
-
|
458 |
-
|
459 |
-
|
460 |
-
|
461 |
-
|
462 |
-
|
463 |
-
|
464 |
-
|
465 |
-
|
466 |
-
|
467 |
-
|
468 |
-
|
469 |
-
|
470 |
-
|
471 |
-
|
472 |
-
|
473 |
-
|
474 |
-
|
475 |
-
|
476 |
-
|
477 |
-
|
478 |
-
|
479 |
-
|
480 |
-
|
481 |
-
|
482 |
-
|
483 |
-
|
484 |
-
|
485 |
-
|
486 |
-
|
487 |
-
|
488 |
-
|
489 |
-
|
490 |
-
|
491 |
-
|
492 |
-
|
493 |
-
|
494 |
-
|
495 |
-
|
496 |
-
|
497 |
-
|
498 |
-
|
499 |
-
|
500 |
-
|
501 |
-
|
502 |
-
|
503 |
-
|
504 |
-
|
505 |
-
|
506 |
-
|
507 |
-
|
508 |
-
|
509 |
-
|
510 |
-
|
511 |
-
|
512 |
-
|
513 |
-
|
514 |
-
|
515 |
-
|
516 |
-
|
517 |
-
|
518 |
-
|
519 |
-
|
520 |
-
|
521 |
-
|
522 |
-
|
523 |
-
|
524 |
-
|
525 |
-
|
526 |
-
|
527 |
-
|
528 |
-
|
529 |
-
|
530 |
-
|
531 |
-
|
532 |
-
|
533 |
-
|
534 |
-
|
535 |
-
|
536 |
-
|
537 |
-
|
538 |
-
|
539 |
-
|
540 |
-
|
541 |
-
|
542 |
-
|
543 |
-
|
544 |
-
#
|
545 |
-
st.
|
546 |
-
|
547 |
-
|
548 |
-
|
549 |
-
|
550 |
-
|
551 |
-
|
552 |
-
|
553 |
-
|
554 |
-
|
555 |
-
|
556 |
-
|
557 |
-
|
558 |
-
|
559 |
-
|
560 |
-
|
561 |
-
|
562 |
-
|
563 |
-
|
564 |
-
|
565 |
-
|
566 |
-
|
567 |
-
|
568 |
-
with
|
569 |
-
st.markdown(f"**{t.get('
|
570 |
-
|
571 |
-
st.dataframe(
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
##############
|
2 |
+
###modules/studentact/student_activities_v2.py
|
3 |
+
|
4 |
+
import streamlit as st
|
5 |
+
import re
|
6 |
+
import io
|
7 |
+
from io import BytesIO
|
8 |
+
import pandas as pd
|
9 |
+
import numpy as np
|
10 |
+
import time
|
11 |
+
import matplotlib.pyplot as plt
|
12 |
+
from datetime import datetime, timedelta
|
13 |
+
from spacy import displacy
|
14 |
+
import random
|
15 |
+
import base64
|
16 |
+
import seaborn as sns
|
17 |
+
import logging
|
18 |
+
|
19 |
+
# Importaciones de la base de datos
|
20 |
+
from ..database.morphosintax_mongo_db import get_student_morphosyntax_analysis
|
21 |
+
from ..database.semantic_mongo_db import get_student_semantic_analysis
|
22 |
+
from ..database.discourse_mongo_db import get_student_discourse_analysis
|
23 |
+
from ..database.chat_mongo_db import get_chat_history
|
24 |
+
from ..database.current_situation_mongo_db import get_current_situation_analysis
|
25 |
+
from ..database.claude_recommendations_mongo_db import get_claude_recommendations
|
26 |
+
|
27 |
+
# Importar la función generate_unique_key
|
28 |
+
from ..utils.widget_utils import generate_unique_key
|
29 |
+
|
30 |
+
logger = logging.getLogger(__name__)
|
31 |
+
|
32 |
+
###################################################################################
|
33 |
+
|
34 |
+
def display_student_activities(username: str, lang_code: str, t: dict):
|
35 |
+
"""
|
36 |
+
Muestra todas las actividades del estudiante
|
37 |
+
Args:
|
38 |
+
username: Nombre del estudiante
|
39 |
+
lang_code: Código del idioma
|
40 |
+
t: Diccionario de traducciones
|
41 |
+
"""
|
42 |
+
try:
|
43 |
+
# Cambiado de "Mis Actividades" a "Registro de mis actividades"
|
44 |
+
#st.header(t.get('activities_title', 'Registro de mis actividades'))
|
45 |
+
|
46 |
+
# Tabs para diferentes tipos de análisis
|
47 |
+
# Cambiado "Análisis del Discurso" a "Análisis comparado de textos"
|
48 |
+
tabs = st.tabs([
|
49 |
+
t.get('current_situation_activities', 'Registros de la función: Mi Situación Actual'),
|
50 |
+
t.get('morpho_activities', 'Registros de mis análisis morfosintácticos'),
|
51 |
+
t.get('semantic_activities', 'Registros de mis análisis semánticos'),
|
52 |
+
t.get('discourse_activities', 'Registros de mis análisis comparado de textos'),
|
53 |
+
t.get('chat_activities', 'Registros de mis conversaciones con el tutor virtual')
|
54 |
+
])
|
55 |
+
|
56 |
+
# Tab de Situación Actual
|
57 |
+
with tabs[0]:
|
58 |
+
display_current_situation_activities(username, t)
|
59 |
+
|
60 |
+
# Tab de Análisis Morfosintáctico
|
61 |
+
with tabs[1]:
|
62 |
+
display_morphosyntax_activities(username, t)
|
63 |
+
|
64 |
+
# Tab de Análisis Semántico
|
65 |
+
with tabs[2]:
|
66 |
+
display_semantic_activities(username, t)
|
67 |
+
|
68 |
+
# Tab de Análisis del Discurso (mantiene nombre interno pero UI muestra "Análisis comparado de textos")
|
69 |
+
with tabs[3]:
|
70 |
+
display_discourse_activities(username, t)
|
71 |
+
|
72 |
+
# Tab de Conversaciones del Chat
|
73 |
+
with tabs[4]:
|
74 |
+
display_chat_activities(username, t)
|
75 |
+
|
76 |
+
except Exception as e:
|
77 |
+
logger.error(f"Error mostrando actividades: {str(e)}")
|
78 |
+
st.error(t.get('error_loading_activities', 'Error al cargar las actividades'))
|
79 |
+
|
80 |
+
|
81 |
+
###############################################################################################
|
82 |
+
|
83 |
+
def display_current_situation_activities(username: str, t: dict):
|
84 |
+
"""
|
85 |
+
Muestra análisis de situación actual junto con las recomendaciones de Claude
|
86 |
+
unificando la información de ambas colecciones y emparejándolas por cercanía temporal.
|
87 |
+
"""
|
88 |
+
try:
|
89 |
+
# Recuperar datos de ambas colecciones
|
90 |
+
logger.info(f"Recuperando análisis de situación actual para {username}")
|
91 |
+
situation_analyses = get_current_situation_analysis(username, limit=10)
|
92 |
+
|
93 |
+
# Verificar si hay datos
|
94 |
+
if situation_analyses:
|
95 |
+
logger.info(f"Recuperados {len(situation_analyses)} análisis de situación")
|
96 |
+
# Depurar para ver la estructura de datos
|
97 |
+
for i, analysis in enumerate(situation_analyses):
|
98 |
+
logger.info(f"Análisis #{i+1}: Claves disponibles: {list(analysis.keys())}")
|
99 |
+
if 'metrics' in analysis:
|
100 |
+
logger.info(f"Métricas disponibles: {list(analysis['metrics'].keys())}")
|
101 |
+
else:
|
102 |
+
logger.warning("No se encontraron análisis de situación actual")
|
103 |
+
|
104 |
+
logger.info(f"Recuperando recomendaciones de Claude para {username}")
|
105 |
+
claude_recommendations = get_claude_recommendations(username)
|
106 |
+
|
107 |
+
if claude_recommendations:
|
108 |
+
logger.info(f"Recuperadas {len(claude_recommendations)} recomendaciones de Claude")
|
109 |
+
else:
|
110 |
+
logger.warning("No se encontraron recomendaciones de Claude")
|
111 |
+
|
112 |
+
# Verificar si hay algún tipo de análisis disponible
|
113 |
+
if not situation_analyses and not claude_recommendations:
|
114 |
+
logger.info("No se encontraron análisis de situación actual ni recomendaciones")
|
115 |
+
st.info(t.get('no_current_situation', 'No hay análisis de situación actual registrados'))
|
116 |
+
return
|
117 |
+
|
118 |
+
# Crear pares combinados emparejando diagnósticos y recomendaciones cercanos en tiempo
|
119 |
+
logger.info("Creando emparejamientos temporales de análisis")
|
120 |
+
|
121 |
+
# Convertir timestamps a objetos datetime para comparación
|
122 |
+
situation_times = []
|
123 |
+
for analysis in situation_analyses:
|
124 |
+
if 'timestamp' in analysis:
|
125 |
+
try:
|
126 |
+
timestamp_str = analysis['timestamp']
|
127 |
+
dt = datetime.fromisoformat(timestamp_str.replace('Z', '+00:00'))
|
128 |
+
situation_times.append((dt, analysis))
|
129 |
+
except Exception as e:
|
130 |
+
logger.error(f"Error parseando timestamp de situación: {str(e)}")
|
131 |
+
|
132 |
+
recommendation_times = []
|
133 |
+
for recommendation in claude_recommendations:
|
134 |
+
if 'timestamp' in recommendation:
|
135 |
+
try:
|
136 |
+
timestamp_str = recommendation['timestamp']
|
137 |
+
dt = datetime.fromisoformat(timestamp_str.replace('Z', '+00:00'))
|
138 |
+
recommendation_times.append((dt, recommendation))
|
139 |
+
except Exception as e:
|
140 |
+
logger.error(f"Error parseando timestamp de recomendación: {str(e)}")
|
141 |
+
|
142 |
+
# Ordenar por tiempo
|
143 |
+
situation_times.sort(key=lambda x: x[0], reverse=True)
|
144 |
+
recommendation_times.sort(key=lambda x: x[0], reverse=True)
|
145 |
+
|
146 |
+
# Crear pares combinados
|
147 |
+
combined_items = []
|
148 |
+
|
149 |
+
# Primero, procesar todas las situaciones encontrando la recomendación más cercana
|
150 |
+
for sit_time, situation in situation_times:
|
151 |
+
# Buscar la recomendación más cercana en tiempo
|
152 |
+
best_match = None
|
153 |
+
min_diff = timedelta(minutes=30) # Máxima diferencia de tiempo aceptable (30 minutos)
|
154 |
+
best_rec_time = None
|
155 |
+
|
156 |
+
for rec_time, recommendation in recommendation_times:
|
157 |
+
time_diff = abs(sit_time - rec_time)
|
158 |
+
if time_diff < min_diff:
|
159 |
+
min_diff = time_diff
|
160 |
+
best_match = recommendation
|
161 |
+
best_rec_time = rec_time
|
162 |
+
|
163 |
+
# Crear un elemento combinado
|
164 |
+
if best_match:
|
165 |
+
timestamp_key = sit_time.isoformat()
|
166 |
+
combined_items.append((timestamp_key, {
|
167 |
+
'situation': situation,
|
168 |
+
'recommendation': best_match,
|
169 |
+
'time_diff': min_diff.total_seconds()
|
170 |
+
}))
|
171 |
+
# Eliminar la recomendación usada para no reutilizarla
|
172 |
+
recommendation_times = [(t, r) for t, r in recommendation_times if t != best_rec_time]
|
173 |
+
logger.info(f"Emparejado: Diagnóstico {sit_time} con Recomendación {best_rec_time} (diferencia: {min_diff})")
|
174 |
+
else:
|
175 |
+
# Si no hay recomendación cercana, solo incluir la situación
|
176 |
+
timestamp_key = sit_time.isoformat()
|
177 |
+
combined_items.append((timestamp_key, {
|
178 |
+
'situation': situation
|
179 |
+
}))
|
180 |
+
logger.info(f"Sin emparejar: Diagnóstico {sit_time} sin recomendación cercana")
|
181 |
+
|
182 |
+
# Agregar recomendaciones restantes sin situación
|
183 |
+
for rec_time, recommendation in recommendation_times:
|
184 |
+
timestamp_key = rec_time.isoformat()
|
185 |
+
combined_items.append((timestamp_key, {
|
186 |
+
'recommendation': recommendation
|
187 |
+
}))
|
188 |
+
logger.info(f"Sin emparejar: Recomendación {rec_time} sin diagnóstico cercano")
|
189 |
+
|
190 |
+
# Ordenar por tiempo (más reciente primero)
|
191 |
+
combined_items.sort(key=lambda x: x[0], reverse=True)
|
192 |
+
|
193 |
+
logger.info(f"Procesando {len(combined_items)} elementos combinados")
|
194 |
+
|
195 |
+
# Mostrar cada par combinado
|
196 |
+
for i, (timestamp_key, analysis_pair) in enumerate(combined_items):
|
197 |
+
try:
|
198 |
+
# Obtener datos de situación y recomendación
|
199 |
+
situation_data = analysis_pair.get('situation', {})
|
200 |
+
recommendation_data = analysis_pair.get('recommendation', {})
|
201 |
+
time_diff = analysis_pair.get('time_diff')
|
202 |
+
|
203 |
+
# Si no hay ningún dato, continuar al siguiente
|
204 |
+
if not situation_data and not recommendation_data:
|
205 |
+
continue
|
206 |
+
|
207 |
+
# Determinar qué texto mostrar (priorizar el de la situación)
|
208 |
+
text_to_show = situation_data.get('text', recommendation_data.get('text', ''))
|
209 |
+
text_type = situation_data.get('text_type', recommendation_data.get('text_type', ''))
|
210 |
+
|
211 |
+
# Formatear fecha para mostrar
|
212 |
+
try:
|
213 |
+
# Usar timestamp del key que ya es un formato ISO
|
214 |
+
dt = datetime.fromisoformat(timestamp_key)
|
215 |
+
formatted_date = dt.strftime("%d/%m/%Y %H:%M:%S")
|
216 |
+
except Exception as date_error:
|
217 |
+
logger.error(f"Error formateando fecha: {str(date_error)}")
|
218 |
+
formatted_date = timestamp_key
|
219 |
+
|
220 |
+
# Determinar el título del expander
|
221 |
+
title = f"{t.get('analysis_date', 'Fecha')}: {formatted_date}"
|
222 |
+
if text_type:
|
223 |
+
text_type_display = {
|
224 |
+
'academic_article': t.get('academic_article', 'Artículo académico'),
|
225 |
+
'student_essay': t.get('student_essay', 'Trabajo universitario'),
|
226 |
+
'general_communication': t.get('general_communication', 'Comunicación general')
|
227 |
+
}.get(text_type, text_type)
|
228 |
+
title += f" - {text_type_display}"
|
229 |
+
|
230 |
+
# Añadir indicador de emparejamiento si existe
|
231 |
+
if time_diff is not None:
|
232 |
+
if time_diff < 60: # menos de un minuto
|
233 |
+
title += f" 🔄 (emparejados)"
|
234 |
+
else:
|
235 |
+
title += f" 🔄 (emparejados, diferencia: {int(time_diff//60)} min)"
|
236 |
+
|
237 |
+
# Usar un ID único para cada expander
|
238 |
+
expander_id = f"analysis_{i}_{timestamp_key.replace(':', '_')}"
|
239 |
+
|
240 |
+
# Mostrar el análisis en un expander
|
241 |
+
with st.expander(title, expanded=False):
|
242 |
+
# Mostrar texto analizado con key único
|
243 |
+
st.subheader(t.get('analyzed_text', 'Texto analizado'))
|
244 |
+
st.text_area(
|
245 |
+
"Text Content",
|
246 |
+
value=text_to_show,
|
247 |
+
height=100,
|
248 |
+
disabled=True,
|
249 |
+
label_visibility="collapsed",
|
250 |
+
key=f"text_area_{expander_id}"
|
251 |
+
)
|
252 |
+
|
253 |
+
# Crear tabs para separar diagnóstico y recomendaciones
|
254 |
+
diagnosis_tab, recommendations_tab = st.tabs([
|
255 |
+
t.get('diagnosis_tab', 'Diagnóstico'),
|
256 |
+
t.get('recommendations_tab', 'Recomendaciones')
|
257 |
+
])
|
258 |
+
|
259 |
+
# Tab de diagnóstico
|
260 |
+
with diagnosis_tab:
|
261 |
+
if situation_data and 'metrics' in situation_data:
|
262 |
+
metrics = situation_data['metrics']
|
263 |
+
|
264 |
+
# Dividir en dos columnas
|
265 |
+
col1, col2 = st.columns(2)
|
266 |
+
|
267 |
+
# Principales métricas en formato de tarjetas
|
268 |
+
with col1:
|
269 |
+
st.subheader(t.get('key_metrics', 'Métricas clave'))
|
270 |
+
|
271 |
+
# Mostrar cada métrica principal
|
272 |
+
for metric_name, metric_data in metrics.items():
|
273 |
+
try:
|
274 |
+
# Determinar la puntuación
|
275 |
+
score = None
|
276 |
+
if isinstance(metric_data, dict):
|
277 |
+
# Intentar diferentes nombres de campo
|
278 |
+
if 'normalized_score' in metric_data:
|
279 |
+
score = metric_data['normalized_score']
|
280 |
+
elif 'score' in metric_data:
|
281 |
+
score = metric_data['score']
|
282 |
+
elif 'value' in metric_data:
|
283 |
+
score = metric_data['value']
|
284 |
+
elif isinstance(metric_data, (int, float)):
|
285 |
+
score = metric_data
|
286 |
+
|
287 |
+
if score is not None:
|
288 |
+
# Asegurarse de que score es numérico
|
289 |
+
if isinstance(score, (int, float)):
|
290 |
+
# Determinar color y emoji basado en la puntuación
|
291 |
+
if score < 0.5:
|
292 |
+
emoji = "🔴"
|
293 |
+
color = "#ffcccc" # light red
|
294 |
+
elif score < 0.75:
|
295 |
+
emoji = "🟡"
|
296 |
+
color = "#ffffcc" # light yellow
|
297 |
+
else:
|
298 |
+
emoji = "🟢"
|
299 |
+
color = "#ccffcc" # light green
|
300 |
+
|
301 |
+
# Mostrar la métrica con estilo
|
302 |
+
st.markdown(f"""
|
303 |
+
<div style="background-color:{color}; padding:10px; border-radius:5px; margin-bottom:10px;">
|
304 |
+
<b>{emoji} {metric_name.capitalize()}:</b> {score:.2f}
|
305 |
+
</div>
|
306 |
+
""", unsafe_allow_html=True)
|
307 |
+
else:
|
308 |
+
# Si no es numérico, mostrar como texto
|
309 |
+
st.markdown(f"""
|
310 |
+
<div style="background-color:#f0f0f0; padding:10px; border-radius:5px; margin-bottom:10px;">
|
311 |
+
<b>ℹ️ {metric_name.capitalize()}:</b> {str(score)}
|
312 |
+
</div>
|
313 |
+
""", unsafe_allow_html=True)
|
314 |
+
except Exception as e:
|
315 |
+
logger.error(f"Error procesando métrica {metric_name}: {str(e)}")
|
316 |
+
|
317 |
+
# Mostrar detalles adicionales si están disponibles
|
318 |
+
with col2:
|
319 |
+
st.subheader(t.get('details', 'Detalles'))
|
320 |
+
|
321 |
+
# Para cada métrica, mostrar sus detalles si existen
|
322 |
+
for metric_name, metric_data in metrics.items():
|
323 |
+
try:
|
324 |
+
if isinstance(metric_data, dict):
|
325 |
+
# Mostrar detalles directamente o buscar en subcampos
|
326 |
+
details = None
|
327 |
+
if 'details' in metric_data and metric_data['details']:
|
328 |
+
details = metric_data['details']
|
329 |
+
else:
|
330 |
+
# Crear un diccionario con los detalles excluyendo 'normalized_score' y similares
|
331 |
+
details = {k: v for k, v in metric_data.items()
|
332 |
+
if k not in ['normalized_score', 'score', 'value']}
|
333 |
+
|
334 |
+
if details:
|
335 |
+
st.write(f"**{metric_name.capitalize()}**")
|
336 |
+
st.json(details, expanded=False)
|
337 |
+
except Exception as e:
|
338 |
+
logger.error(f"Error mostrando detalles de {metric_name}: {str(e)}")
|
339 |
+
else:
|
340 |
+
st.info(t.get('no_diagnosis', 'No hay datos de diagnóstico disponibles'))
|
341 |
+
|
342 |
+
# Tab de recomendaciones
|
343 |
+
with recommendations_tab:
|
344 |
+
if recommendation_data and 'recommendations' in recommendation_data:
|
345 |
+
st.markdown(f"""
|
346 |
+
<div style="padding: 20px; border-radius: 10px;
|
347 |
+
background-color: #f8f9fa; margin-bottom: 20px;">
|
348 |
+
{recommendation_data['recommendations']}
|
349 |
+
</div>
|
350 |
+
""", unsafe_allow_html=True)
|
351 |
+
elif recommendation_data and 'feedback' in recommendation_data:
|
352 |
+
st.markdown(f"""
|
353 |
+
<div style="padding: 20px; border-radius: 10px;
|
354 |
+
background-color: #f8f9fa; margin-bottom: 20px;">
|
355 |
+
{recommendation_data['feedback']}
|
356 |
+
</div>
|
357 |
+
""", unsafe_allow_html=True)
|
358 |
+
else:
|
359 |
+
st.info(t.get('no_recommendations', 'No hay recomendaciones disponibles'))
|
360 |
+
|
361 |
+
except Exception as e:
|
362 |
+
logger.error(f"Error procesando par de análisis: {str(e)}")
|
363 |
+
continue
|
364 |
+
|
365 |
+
except Exception as e:
|
366 |
+
logger.error(f"Error mostrando actividades de situación actual: {str(e)}")
|
367 |
+
st.error(t.get('error_current_situation', 'Error al mostrar análisis de situación actual'))
|
368 |
+
|
369 |
+
###############################################################################################
|
370 |
+
|
371 |
+
def display_morphosyntax_activities(username: str, t: dict):
|
372 |
+
"""Muestra actividades de análisis morfosintáctico"""
|
373 |
+
try:
|
374 |
+
analyses = get_student_morphosyntax_analysis(username)
|
375 |
+
if not analyses:
|
376 |
+
st.info(t.get('no_morpho_analyses', 'No hay análisis morfosintácticos registrados'))
|
377 |
+
return
|
378 |
+
|
379 |
+
for analysis in analyses:
|
380 |
+
with st.expander(
|
381 |
+
f"{t.get('analysis_date', 'Fecha')}: {analysis['timestamp']}",
|
382 |
+
expanded=False
|
383 |
+
):
|
384 |
+
st.text(f"{t.get('analyzed_text', 'Texto analizado')}:")
|
385 |
+
st.write(analysis['text'])
|
386 |
+
|
387 |
+
if 'arc_diagrams' in analysis:
|
388 |
+
st.subheader(t.get('syntactic_diagrams', 'Diagramas sintácticos'))
|
389 |
+
for diagram in analysis['arc_diagrams']:
|
390 |
+
st.write(diagram, unsafe_allow_html=True)
|
391 |
+
|
392 |
+
except Exception as e:
|
393 |
+
logger.error(f"Error mostrando análisis morfosintáctico: {str(e)}")
|
394 |
+
st.error(t.get('error_morpho', 'Error al mostrar análisis morfosintáctico'))
|
395 |
+
|
396 |
+
|
397 |
+
###############################################################################################
|
398 |
+
|
399 |
+
def display_semantic_activities(username: str, t: dict):
|
400 |
+
"""Muestra actividades de análisis semántico"""
|
401 |
+
try:
|
402 |
+
logger.info(f"Recuperando análisis semántico para {username}")
|
403 |
+
analyses = get_student_semantic_analysis(username)
|
404 |
+
|
405 |
+
if not analyses:
|
406 |
+
logger.info("No se encontraron análisis semánticos")
|
407 |
+
st.info(t.get('no_semantic_analyses', 'No hay análisis semánticos registrados'))
|
408 |
+
return
|
409 |
+
|
410 |
+
logger.info(f"Procesando {len(analyses)} análisis semánticos")
|
411 |
+
|
412 |
+
for analysis in analyses:
|
413 |
+
try:
|
414 |
+
# Verificar campos necesarios
|
415 |
+
if not all(key in analysis for key in ['timestamp', 'concept_graph']):
|
416 |
+
logger.warning(f"Análisis incompleto: {analysis.keys()}")
|
417 |
+
continue
|
418 |
+
|
419 |
+
# Formatear fecha
|
420 |
+
timestamp = datetime.fromisoformat(analysis['timestamp'].replace('Z', '+00:00'))
|
421 |
+
formatted_date = timestamp.strftime("%d/%m/%Y %H:%M:%S")
|
422 |
+
|
423 |
+
# Crear expander
|
424 |
+
with st.expander(f"{t.get('analysis_date', 'Fecha')}: {formatted_date}", expanded=False):
|
425 |
+
# Procesar y mostrar gráfico
|
426 |
+
if analysis.get('concept_graph'):
|
427 |
+
try:
|
428 |
+
# Convertir de base64 a bytes
|
429 |
+
logger.debug("Decodificando gráfico de conceptos")
|
430 |
+
image_data = analysis['concept_graph']
|
431 |
+
|
432 |
+
# Si el gráfico ya es bytes, usarlo directamente
|
433 |
+
if isinstance(image_data, bytes):
|
434 |
+
image_bytes = image_data
|
435 |
+
else:
|
436 |
+
# Si es string base64, decodificar
|
437 |
+
image_bytes = base64.b64decode(image_data)
|
438 |
+
|
439 |
+
logger.debug(f"Longitud de bytes de imagen: {len(image_bytes)}")
|
440 |
+
|
441 |
+
# Mostrar imagen
|
442 |
+
st.image(
|
443 |
+
image_bytes,
|
444 |
+
caption=t.get('concept_network', 'Red de Conceptos'),
|
445 |
+
use_column_width=True
|
446 |
+
)
|
447 |
+
logger.debug("Gráfico mostrado exitosamente")
|
448 |
+
|
449 |
+
except Exception as img_error:
|
450 |
+
logger.error(f"Error procesando gráfico: {str(img_error)}")
|
451 |
+
st.error(t.get('error_loading_graph', 'Error al cargar el gráfico'))
|
452 |
+
else:
|
453 |
+
st.info(t.get('no_graph', 'No hay visualización disponible'))
|
454 |
+
|
455 |
+
except Exception as e:
|
456 |
+
logger.error(f"Error procesando análisis individual: {str(e)}")
|
457 |
+
continue
|
458 |
+
|
459 |
+
except Exception as e:
|
460 |
+
logger.error(f"Error mostrando análisis semántico: {str(e)}")
|
461 |
+
st.error(t.get('error_semantic', 'Error al mostrar análisis semántico'))
|
462 |
+
|
463 |
+
|
464 |
+
###################################################################################################
|
465 |
+
def display_discourse_activities(username: str, t: dict):
|
466 |
+
"""Muestra actividades de análisis del discurso (mostrado como 'Análisis comparado de textos' en la UI)"""
|
467 |
+
try:
|
468 |
+
logger.info(f"Recuperando análisis del discurso para {username}")
|
469 |
+
analyses = get_student_discourse_analysis(username)
|
470 |
+
|
471 |
+
if not analyses:
|
472 |
+
logger.info("No se encontraron análisis del discurso")
|
473 |
+
# Usamos el término "análisis comparado de textos" en la UI
|
474 |
+
st.info(t.get('no_discourse_analyses', 'No hay análisis comparados de textos registrados'))
|
475 |
+
return
|
476 |
+
|
477 |
+
logger.info(f"Procesando {len(analyses)} análisis del discurso")
|
478 |
+
for analysis in analyses:
|
479 |
+
try:
|
480 |
+
# Verificar campos mínimos necesarios
|
481 |
+
if not all(key in analysis for key in ['timestamp', 'combined_graph']):
|
482 |
+
logger.warning(f"Análisis incompleto: {analysis.keys()}")
|
483 |
+
continue
|
484 |
+
|
485 |
+
# Formatear fecha
|
486 |
+
timestamp = datetime.fromisoformat(analysis['timestamp'].replace('Z', '+00:00'))
|
487 |
+
formatted_date = timestamp.strftime("%d/%m/%Y %H:%M:%S")
|
488 |
+
|
489 |
+
with st.expander(f"{t.get('analysis_date', 'Fecha')}: {formatted_date}", expanded=False):
|
490 |
+
if analysis['combined_graph']:
|
491 |
+
logger.debug("Decodificando gráfico combinado")
|
492 |
+
try:
|
493 |
+
image_bytes = base64.b64decode(analysis['combined_graph'])
|
494 |
+
st.image(image_bytes, use_column_width=True)
|
495 |
+
logger.debug("Gráfico mostrado exitosamente")
|
496 |
+
except Exception as img_error:
|
497 |
+
logger.error(f"Error decodificando imagen: {str(img_error)}")
|
498 |
+
st.error(t.get('error_loading_graph', 'Error al cargar el gráfico'))
|
499 |
+
else:
|
500 |
+
st.info(t.get('no_visualization', 'No hay visualización comparativa disponible'))
|
501 |
+
|
502 |
+
except Exception as e:
|
503 |
+
logger.error(f"Error procesando análisis individual: {str(e)}")
|
504 |
+
continue
|
505 |
+
|
506 |
+
except Exception as e:
|
507 |
+
logger.error(f"Error mostrando análisis del discurso: {str(e)}")
|
508 |
+
# Usamos el término "análisis comparado de textos" en la UI
|
509 |
+
st.error(t.get('error_discourse', 'Error al mostrar análisis comparado de textos'))
|
510 |
+
|
511 |
+
#################################################################################
|
512 |
+
def display_chat_activities(username: str, t: dict):
|
513 |
+
"""
|
514 |
+
Muestra historial de conversaciones del chat
|
515 |
+
"""
|
516 |
+
try:
|
517 |
+
# Obtener historial del chat
|
518 |
+
chat_history = get_chat_history(
|
519 |
+
username=username,
|
520 |
+
analysis_type='sidebar',
|
521 |
+
limit=50
|
522 |
+
)
|
523 |
+
|
524 |
+
if not chat_history:
|
525 |
+
st.info(t.get('no_chat_history', 'No hay conversaciones registradas'))
|
526 |
+
return
|
527 |
+
|
528 |
+
for chat in reversed(chat_history): # Mostrar las más recientes primero
|
529 |
+
try:
|
530 |
+
# Convertir timestamp a datetime para formato
|
531 |
+
timestamp = datetime.fromisoformat(chat['timestamp'].replace('Z', '+00:00'))
|
532 |
+
formatted_date = timestamp.strftime("%d/%m/%Y %H:%M:%S")
|
533 |
+
|
534 |
+
with st.expander(
|
535 |
+
f"{t.get('chat_date', 'Fecha de conversación')}: {formatted_date}",
|
536 |
+
expanded=False
|
537 |
+
):
|
538 |
+
if 'messages' in chat and chat['messages']:
|
539 |
+
# Mostrar cada mensaje en la conversación
|
540 |
+
for message in chat['messages']:
|
541 |
+
role = message.get('role', 'unknown')
|
542 |
+
content = message.get('content', '')
|
543 |
+
|
544 |
+
# Usar el componente de chat de Streamlit
|
545 |
+
with st.chat_message(role):
|
546 |
+
st.markdown(content)
|
547 |
+
|
548 |
+
# Agregar separador entre mensajes
|
549 |
+
st.divider()
|
550 |
+
else:
|
551 |
+
st.warning(t.get('invalid_chat_format', 'Formato de chat no válido'))
|
552 |
+
|
553 |
+
except Exception as e:
|
554 |
+
logger.error(f"Error mostrando conversación: {str(e)}")
|
555 |
+
continue
|
556 |
+
|
557 |
+
except Exception as e:
|
558 |
+
logger.error(f"Error mostrando historial del chat: {str(e)}")
|
559 |
+
st.error(t.get('error_chat', 'Error al mostrar historial del chat'))
|
560 |
+
|
561 |
+
#################################################################################
|
562 |
+
def display_discourse_comparison(analysis: dict, t: dict):
|
563 |
+
"""Muestra la comparación de análisis del discurso"""
|
564 |
+
# Cambiado para usar "textos comparados" en la UI
|
565 |
+
st.subheader(t.get('comparison_results', 'Resultados de la comparación'))
|
566 |
+
|
567 |
+
col1, col2 = st.columns(2)
|
568 |
+
with col1:
|
569 |
+
st.markdown(f"**{t.get('concepts_text_1', 'Conceptos Texto 1')}**")
|
570 |
+
df1 = pd.DataFrame(analysis['key_concepts1'])
|
571 |
+
st.dataframe(df1)
|
572 |
+
|
573 |
+
with col2:
|
574 |
+
st.markdown(f"**{t.get('concepts_text_2', 'Conceptos Texto 2')}**")
|
575 |
+
df2 = pd.DataFrame(analysis['key_concepts2'])
|
576 |
+
st.dataframe(df2)
|