陈俊杰 commited on
Commit
593bcd7
·
1 Parent(s): 59dfef8
Files changed (1) hide show
  1. app.py +44 -30
app.py CHANGED
@@ -268,11 +268,13 @@ elif page == "LeaderBoard":
268
  TeamId = ["baseline", "baseline", "baseline", "baseline",
269
  'ISLab', 'ISLab', 'ISLab', 'ISLab', 'ISLab',
270
  'default5', 'default5', 'default5', 'default5', 'PanguIR', 'PanguIR',
271
- 'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR']
 
272
  Methods = ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o",
273
  "llama3-1_baseline5", "llama3-1_baseline6", "llama3-1-baseline7", "llama3-2-baseline", 'lst',
274
- "baselinev02", "baselinev72r1", "baselinev70r1", "baselinev72r2", 'baselinev62r5', 'TestV1',
275
- 'bert-base-uncased', 'gpt35turbo', 'logisticRegression', 'paraphrase-MiniLM-L6-v2', 'gpt4omini', 'gpt35turbo_2', 'paraphrase-MiniLM-L6-v2_2']
 
276
 
277
  # teamId 唯一标识码
278
  DG = {
@@ -280,16 +282,19 @@ elif page == "LeaderBoard":
280
  "Methods": Methods,
281
  "Accuracy": [0.5806, 0.5483, 0.6001, 0.6472,
282
  0, 0, 0, 0, 0,
283
- 0.631700513538749, 0.7111356209150326, 0.6176633986928104, 0.735954715219421, 0.7093849206349206, 0.6348867880485528,
284
- 0.5073529411764706, 0.5104038281979459, 0.5405182072829132, 0.5156874416433239, 0.6264040616246499, 0.5916596638655462, 0.5352462651727359],
 
285
  "Kendall's Tau": [0.3243, 0.1739, 0.3042, 0.4167,
286
  0, 0, 0, 0, 0,
287
- 0.38961572200778516, 0.5285302196320519, 0.31022946186879186, 0.5974703857412484, 0.5272439906890581, 0.40761909231510957,
288
- 0.024753688574416864, 0.2838365040871617, 0.18291748486237186, 0.334110095650077, 0.3649231979007039, 0.36962615507144936, 0.3390221267002087],
 
289
  "Spearman": [0.3505, 0.1857, 0.3264, 0.4512,
290
  0, 0, 0, 0, 0,
291
- 0.4200280894403279, 0.5723981513727318, 0.3392536955889527, 0.6542301178956093, 0.5685750705840381, 0.4402924204817677,
292
- 0.02673703949665616, 0.3132279427962962, 0.19244600211698878, 0.3697144425033483, 0.3950674896604176, 0.4100512798963848, 0.3649670915627452]
 
293
  }
294
 
295
  df1 = pd.DataFrame(DG)
@@ -298,17 +303,20 @@ elif page == "LeaderBoard":
298
  "TeamId": TeamId,
299
  "Methods": Methods,
300
  "Accuracy": [0.5107, 0.5050, 0.5461, 0.5581,
301
- 0.5067545088210725, 0.4766805549971185, 0, 0, 0.5584336118817543,
302
- 0.570425718931911, 0.5518648601785212, 0.5162097017834246, 0.5757498972475753, 0.5593401842395651, 0.5964374394095756,
303
- 0.49544642857142857, 0.506452190525333, 0.5427970103511899, 0.5491338026438646, 0.5369645467836258, 0.5152763188608777, 0.5987781340606417],
 
304
  "Kendall's Tau": [0.1281, 0.0635, 0.2716, 0.3864,
305
- 0.18884532500063825, 0.31629653258509166, 0, 0, 0.32462654010615744,
306
- 0.42340286124586973, 0.42163723763190575, 0.3111422734769831, 0.46417209045053276, 0.36801116758496544, 0.401849214251255,
307
- 0.04074528095431955, 0.3533564092679483, 0.19204956587442087, 0.24122049643546917, 0.3596504785294933, 0.3790073087255008, 0.3163318559794785],
 
308
  "Spearman": [0.1352, 0.0667, 0.2867, 0.4157,
309
- 0.2033137543983765, 0.35189638758373964, 0, 0, 0.3512102704868184,
310
- 0.44950359766748854, 0.4567231163496956, 0.3284040387552273, 0.5061135134678696, 0.410623572297829, 0.426954606739183,
311
- 0.04302709609666947, 0.3758784332521168, 0.2019542748712654, 0.25105320709917717, 0.3877701221573462, 0.4023214969583063, 0.3321820359446316]
 
312
  }
313
  df2 = pd.DataFrame(TE)
314
 
@@ -317,16 +325,19 @@ elif page == "LeaderBoard":
317
  "Methods": Methods,
318
  "Accuracy": [0.6504, 0.6014, 0.7162, 0.7441,
319
  0.7518953983108395, 0.7870818213649097, 0.6187623875307698, 0.8003185213479332, 0.7575067640692641,
320
- 0.7477385992275697, 0.7969309163059164, 0.784410942407266, 0.769276748578219, 0.7542146782955607, 0.7510259634156693,
321
- 0.5, 0.7231299072659366, 0.5, 0.7348077412783295, 0.8138134230965111, 0.7332144979203802, 0.7434876336898395],
 
322
  "Kendall's Tau": [0.3957, 0.2688, 0.5092, 0.5001,
323
  0.5377072309689559, 0.5709963447418871, 0.30897221697376714, 0.6064826537169805, 0.5223946531394501,
324
- 0.49885108461595573, 0.5408319381088115, 0.566750311845092, 0.539144026776003, 0.5039030127649896, 0.5386493074453432,
325
- 0.0, 0.48911130738063485, 0.0, 0.5436010461720943, 0.5887748722478621, 0.4789688329587808, 0.5861077265910544],
 
326
  "Spearman": [0.4188, 0.2817, 0.5403, 0.5405,
327
  0.5830423197486431, 0.6276373633425562, 0.324348752437819, 0.6664032039425867, 0.5882831332644322,
328
- 0.5603311161969196, 0.5987990693735654, 0.6200483357955027, 0.6021636544977567, 0.5658023652256237, 0.5876006357077044,
329
- 0.0, 0.530151784406405, 0.0, 0.5767282714406644, 0.6419500299643864, 0.5122236499720725, 0.6186519937766083]
 
330
  }
331
  df3 = pd.DataFrame(SG)
332
 
@@ -335,16 +346,19 @@ elif page == "LeaderBoard":
335
  "Methods": Methods,
336
  "Accuracy": [0.5935, 0.5817, 0.7000, 0.7203,
337
  0, 0, 0, 0, 0,
338
- 0.7215900072150073, 0.7137157287157287, 0.7298538961038961, 0.7578841991341992, 0.742178932178932, 0.7073651695526694,
339
- 0.6365868506493507,0.5985240800865801, 0.5590909090909092, 0.6762518037518037, 0.7228891594516594, 0.6581060606060605, 0.6888884379509378],
 
340
  "Kendall's Tau": [0.2332, 0.2389, 0.4440, 0.4235,
341
  0, 0, 0, 0, 0,
342
- 0.49445393416475697, 0.40897219553585185, 0.39880657282887155, 0.4594680081243032, 0.44808795202384744, 0.41813010356097624,
343
- 0.402354630029616, 0.29538507694084404, 0.10735098173126541, 0.4077804758055409, 0.4513811364777995, 0.2592602240459282, 0.4761306657795843],
 
344
  "Spearman": [0.2443, 0.2492, 0.4630, 0.4511,
345
  0, 0, 0, 0, 0,
346
- 0.5214865171404164, 0.4479941149402397, 0.424528242404003, 0.49907660929552167, 0.48643423849581746, 0.4372807302544148,
347
- 0.41802883351668096, 0.31033689944001186, 0.1096152564140644, 0.43265604612874153, 0.467017116366382, 0.2701488394210608, 0.4983905928499312]
 
348
  }
349
  df4 = pd.DataFrame(NFQA)
350
 
 
268
  TeamId = ["baseline", "baseline", "baseline", "baseline",
269
  'ISLab', 'ISLab', 'ISLab', 'ISLab', 'ISLab',
270
  'default5', 'default5', 'default5', 'default5', 'PanguIR', 'PanguIR',
271
+ 'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR',
272
+ "UCLWI"]
273
  Methods = ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o",
274
  "llama3-1_baseline5", "llama3-1_baseline6", "llama3-1-baseline7", "llama3-2-baseline", 'lst',
275
+ "baselinev02", "baselinev72r1", "baselinev70r1", "baselinev72r2", 'baselinev62r5', 'TestV1', 'testV1R1', 'testV12R1',
276
+ 'bert-base-uncased', 'gpt35turbo', 'logisticRegression', 'paraphrase-MiniLM-L6-v2', 'gpt4omini', 'gpt35turbo_2', 'paraphrase-MiniLM-L6-v2_2',
277
+ 'SIMILAR']
278
 
279
  # teamId 唯一标识码
280
  DG = {
 
282
  "Methods": Methods,
283
  "Accuracy": [0.5806, 0.5483, 0.6001, 0.6472,
284
  0, 0, 0, 0, 0,
285
+ 0.631700513538749, 0.7111356209150326, 0.6176633986928104, 0.735954715219421, 0.7093849206349206, 0.6348867880485528, 0.6133998599439777, 0.6934360410830999,
286
+ 0.5073529411764706, 0.5104038281979459, 0.5405182072829132, 0.5156874416433239, 0.6264040616246499, 0.5916596638655462, 0.5352462651727359,
287
+ 0.7043767507002803],
288
  "Kendall's Tau": [0.3243, 0.1739, 0.3042, 0.4167,
289
  0, 0, 0, 0, 0,
290
+ 0.38961572200778516, 0.5285302196320519, 0.31022946186879186, 0.5974703857412484, 0.5272439906890581, 0.40761909231510957, 0.35041734579937367, 0.5327818707808725,
291
+ 0.024753688574416864, 0.2838365040871617, 0.18291748486237186, 0.334110095650077, 0.3649231979007039, 0.36962615507144936, 0.3390221267002087,
292
+ 0.49126402677015407],
293
  "Spearman": [0.3505, 0.1857, 0.3264, 0.4512,
294
  0, 0, 0, 0, 0,
295
+ 0.4200280894403279, 0.5723981513727318, 0.3392536955889527, 0.6542301178956093, 0.5685750705840381, 0.4402924204817677, 0.37471431129298743, 0.5698785682220627,
296
+ 0.02673703949665616, 0.3132279427962962, 0.19244600211698878, 0.3697144425033483, 0.3950674896604176, 0.4100512798963848, 0.3649670915627452,
297
+ 0.5526515752201003]
298
  }
299
 
300
  df1 = pd.DataFrame(DG)
 
303
  "TeamId": TeamId,
304
  "Methods": Methods,
305
  "Accuracy": [0.5107, 0.5050, 0.5461, 0.5581,
306
+ 0.5067545088210725, 0.4766805549971185, 0, 0, 0.5077891433686712,
307
+ 0.570425718931911, 0.5518648601785212, 0.5162097017834246, 0.5757498972475753, 0.5593401842395651, 0.5964374394095756, 0.595433174067075, 0.5562621306497081,
308
+ 0.49544642857142857, 0.506452190525333, 0.5427970103511899, 0.5491338026438646, 0.5369645467836258, 0.5152763188608777, 0.5987781340606417,
309
+ 0.5339643630578228 ],
310
  "Kendall's Tau": [0.1281, 0.0635, 0.2716, 0.3864,
311
+ 0.18884532500063825, 0.31629653258509166, 0, 0, 0.45638913031218103,
312
+ 0.42340286124586973, 0.42163723763190575, 0.3111422734769831, 0.46417209045053276, 0.36801116758496544, 0.401849214251255, 0.44079331049853776, 0.37969277595414264,
313
+ 0.04074528095431955, 0.3533564092679483, 0.19204956587442087, 0.24122049643546917, 0.3596504785294933, 0.3790073087255008, 0.3163318559794785,
314
+ 0.27579701426321535 ],
315
  "Spearman": [0.1352, 0.0667, 0.2867, 0.4157,
316
+ 0.2033137543983765, 0.35189638758373964, 0, 0, 0.5010143172417726,
317
+ 0.44950359766748854, 0.4567231163496956, 0.3284040387552273, 0.5061135134678696, 0.410623572297829, 0.426954606739183, 0.4672241864454845, 0.41131149381447807,
318
+ 0.04302709609666947, 0.3758784332521168, 0.2019542748712654, 0.25105320709917717, 0.3877701221573462, 0.4023214969583063, 0.3321820359446316,
319
+ 0.3018726579994679]
320
  }
321
  df2 = pd.DataFrame(TE)
322
 
 
325
  "Methods": Methods,
326
  "Accuracy": [0.6504, 0.6014, 0.7162, 0.7441,
327
  0.7518953983108395, 0.7870818213649097, 0.6187623875307698, 0.8003185213479332, 0.7575067640692641,
328
+ 0.7477385992275697, 0.7969309163059164, 0.784410942407266, 0.769276748578219, 0.7542146782955607, 0.7510259634156693, 0.7510259634156693, 0.7665198996265173,
329
+ 0.5, 0.7231299072659366, 0.5, 0.7348077412783295, 0.8138134230965111, 0.7332144979203802, 0.7434876336898395,
330
+ 0.7493895891690008 ],
331
  "Kendall's Tau": [0.3957, 0.2688, 0.5092, 0.5001,
332
  0.5377072309689559, 0.5709963447418871, 0.30897221697376714, 0.6064826537169805, 0.5223946531394501,
333
+ 0.49885108461595573, 0.5408319381088115, 0.566750311845092, 0.539144026776003, 0.5039030127649896, 0.5386493074453432, 0.5386493074453432, 0.5765178792723434,
334
+ 0.0, 0.48911130738063485, 0.0, 0.5436010461720943, 0.5887748722478621, 0.4789688329587808, 0.5861077265910544,
335
+ 0.6113656024437849 ],
336
  "Spearman": [0.4188, 0.2817, 0.5403, 0.5405,
337
  0.5830423197486431, 0.6276373633425562, 0.324348752437819, 0.6664032039425867, 0.5882831332644322,
338
+ 0.5603311161969196, 0.5987990693735654, 0.6200483357955027, 0.6021636544977567, 0.5658023652256237, 0.5876006357077044, 0.5876006357077044, 0.6234709658897817,
339
+ 0.0, 0.530151784406405, 0.0, 0.5767282714406644, 0.6419500299643864, 0.5122236499720725, 0.6186519937766083,
340
+ 0.6418110452596717]
341
  }
342
  df3 = pd.DataFrame(SG)
343
 
 
346
  "Methods": Methods,
347
  "Accuracy": [0.5935, 0.5817, 0.7000, 0.7203,
348
  0, 0, 0, 0, 0,
349
+ 0.7215900072150073, 0.7137157287157287, 0.7298538961038961, 0.7578841991341992, 0.742178932178932, 0.7073651695526694, 0.7193082611832613, 0.7093867243867243,
350
+ 0.6365868506493507,0.5985240800865801, 0.5590909090909092, 0.6762518037518037, 0.7228891594516594, 0.6581060606060605, 0.6888884379509378,
351
+ 0.6905248917748917 ],
352
  "Kendall's Tau": [0.2332, 0.2389, 0.4440, 0.4235,
353
  0, 0, 0, 0, 0,
354
+ 0.49445393416475697, 0.40897219553585185, 0.39880657282887155, 0.4594680081243032, 0.44808795202384744, 0.41813010356097624, 0.4246126194063706, 0.398517678125797,
355
+ 0.402354630029616, 0.29538507694084404, 0.10735098173126541, 0.4077804758055409, 0.4513811364777995, 0.2592602240459282, 0.4761306657795843,
356
+ 0.40895990193173554 ],
357
  "Spearman": [0.2443, 0.2492, 0.4630, 0.4511,
358
  0, 0, 0, 0, 0,
359
+ 0.5214865171404164, 0.4479941149402397, 0.424528242404003, 0.49907660929552167, 0.48643423849581746, 0.4372807302544148, 0.44649320842950174, 0.42834069279542086,
360
+ 0.41802883351668096, 0.31033689944001186, 0.1096152564140644, 0.43265604612874153, 0.467017116366382, 0.2701488394210608, 0.4983905928499312,
361
+ 0.4310971432243079]
362
  }
363
  df4 = pd.DataFrame(NFQA)
364