陈俊杰
commited on
Commit
·
4ccefa7
1
Parent(s):
c5475fc
0104
Browse files
app.py
CHANGED
@@ -267,11 +267,11 @@ elif page == "LeaderBoard":
|
|
267 |
|
268 |
TeamId = ["baseline", "baseline", "baseline", "baseline",
|
269 |
'ISLab', 'ISLab', 'ISLab', 'ISLab',
|
270 |
-
'default5', 'default5', 'default5', 'default5',
|
271 |
'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",
|
274 |
-
"baselinev02", "baselinev72r1", "baselinev70r1", "baselinev72r2",
|
275 |
'bert-base-uncased', 'gpt35turbo', 'logisticRegression', 'paraphrase-MiniLM-L6-v2']
|
276 |
|
277 |
# teamId 唯一标识码
|
@@ -280,15 +280,15 @@ elif page == "LeaderBoard":
|
|
280 |
"Methods": Methods,
|
281 |
"Accuracy": [0.5806, 0.5483, 0.6001, 0.6472,
|
282 |
0, 0, 0, 0,
|
283 |
-
0.631700513538749, 0.7111356209150326, 0.6176633986928104, 0.735954715219421,
|
284 |
0.5073529411764706, 0.5104038281979459, 0.5405182072829132, 0.5156874416433239],
|
285 |
"Kendall's Tau": [0.3243, 0.1739, 0.3042, 0.4167,
|
286 |
0, 0, 0, 0,
|
287 |
-
0.38961572200778516, 0.5285302196320519, 0.31022946186879186, 0.5974703857412484,
|
288 |
0.024753688574416864, 0.2838365040871617, 0.18291748486237186, 0.334110095650077],
|
289 |
"Spearman": [0.3505, 0.1857, 0.3264, 0.4512,
|
290 |
0, 0, 0, 0,
|
291 |
-
0.4200280894403279, 0.5723981513727318, 0.3392536955889527, 0.6542301178956093,
|
292 |
0.02673703949665616, 0.3132279427962962, 0.19244600211698878, 0.3697144425033483]
|
293 |
}
|
294 |
|
@@ -299,15 +299,15 @@ elif page == "LeaderBoard":
|
|
299 |
"Methods": Methods,
|
300 |
"Accuracy": [0.5107, 0.5050, 0.5461, 0.5581,
|
301 |
0.5067545088210725, 0.4766805549971185, 0, 0,
|
302 |
-
0.570425718931911, 0.5518648601785212, 0.5162097017834246, 0.5757498972475753,
|
303 |
0.49544642857142857, 0.506452190525333, 0.5427970103511899, 0.5491338026438646],
|
304 |
"Kendall's Tau": [0.1281, 0.0635, 0.2716, 0.3864,
|
305 |
0.18884532500063825, 0.31629653258509166, 0, 0,
|
306 |
-
0.42340286124586973, 0.42163723763190575, 0.3111422734769831, 0.46417209045053276,
|
307 |
0.04074528095431955, 0.3533564092679483, 0.19204956587442087, 0.24122049643546917],
|
308 |
"Spearman": [0.1352, 0.0667, 0.2867, 0.4157,
|
309 |
0.2033137543983765, 0.35189638758373964, 0, 0,
|
310 |
-
0.44950359766748854, 0.4567231163496956, 0.3284040387552273, 0.5061135134678696,
|
311 |
0.04302709609666947, 0.3758784332521168, 0.2019542748712654, 0.25105320709917717]
|
312 |
}
|
313 |
df2 = pd.DataFrame(TE)
|
@@ -317,15 +317,15 @@ 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,
|
320 |
-
0.7477385992275697, 0.7969309163059164, 0.784410942407266, 0.769276748578219,
|
321 |
0.5, 0.7231299072659366, 0.5, 0.7348077412783295],
|
322 |
"Kendall's Tau": [0.3957, 0.2688, 0.5092, 0.5001,
|
323 |
0.5377072309689559, 0.5709963447418871, 0.30897221697376714, 0.6064826537169805,
|
324 |
-
0.49885108461595573, 0.5408319381088115, 0.566750311845092, 0.539144026776003,
|
325 |
0.0, 0.48911130738063485, 0.0, 0.5436010461720943],
|
326 |
"Spearman": [0.4188, 0.2817, 0.5403, 0.5405,
|
327 |
0.5830423197486431, 0.6276373633425562, 0.324348752437819, 0.6664032039425867,
|
328 |
-
0.5603311161969196, 0.5987990693735654, 0.6200483357955027, 0.6021636544977567,
|
329 |
0.0, 0.530151784406405, 0.0, 0.5767282714406644]
|
330 |
}
|
331 |
df3 = pd.DataFrame(SG)
|
@@ -335,15 +335,15 @@ elif page == "LeaderBoard":
|
|
335 |
"Methods": Methods,
|
336 |
"Accuracy": [0.5935, 0.5817, 0.7000, 0.7203,
|
337 |
0, 0, 0, 0,
|
338 |
-
0.7215900072150073, 0.7137157287157287, 0.7298538961038961, 0.7578841991341992,
|
339 |
0.6365868506493507,0.5985240800865801, 0.5590909090909092, 0.6762518037518037],
|
340 |
"Kendall's Tau": [0.2332, 0.2389, 0.4440, 0.4235,
|
341 |
0, 0, 0, 0,
|
342 |
-
0.49445393416475697, 0.40897219553585185, 0.39880657282887155, 0.4594680081243032,
|
343 |
0.402354630029616, 0.29538507694084404, 0.10735098173126541, 0.4077804758055409],
|
344 |
"Spearman": [0.2443, 0.2492, 0.4630, 0.4511,
|
345 |
0, 0, 0, 0,
|
346 |
-
0.5214865171404164, 0.4479941149402397, 0.424528242404003, 0.49907660929552167,
|
347 |
0.41802883351668096, 0.31033689944001186, 0.1096152564140644, 0.43265604612874153]
|
348 |
}
|
349 |
df4 = pd.DataFrame(NFQA)
|
|
|
267 |
|
268 |
TeamId = ["baseline", "baseline", "baseline", "baseline",
|
269 |
'ISLab', 'ISLab', 'ISLab', 'ISLab',
|
270 |
+
'default5', 'default5', 'default5', 'default5', 'PanguIR'
|
271 |
'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",
|
274 |
+
"baselinev02", "baselinev72r1", "baselinev70r1", "baselinev72r2", 'baselinev62r5'
|
275 |
'bert-base-uncased', 'gpt35turbo', 'logisticRegression', 'paraphrase-MiniLM-L6-v2']
|
276 |
|
277 |
# teamId 唯一标识码
|
|
|
280 |
"Methods": Methods,
|
281 |
"Accuracy": [0.5806, 0.5483, 0.6001, 0.6472,
|
282 |
0, 0, 0, 0,
|
283 |
+
0.631700513538749, 0.7111356209150326, 0.6176633986928104, 0.735954715219421, 0.7093849206349206
|
284 |
0.5073529411764706, 0.5104038281979459, 0.5405182072829132, 0.5156874416433239],
|
285 |
"Kendall's Tau": [0.3243, 0.1739, 0.3042, 0.4167,
|
286 |
0, 0, 0, 0,
|
287 |
+
0.38961572200778516, 0.5285302196320519, 0.31022946186879186, 0.5974703857412484, 0.5272439906890581
|
288 |
0.024753688574416864, 0.2838365040871617, 0.18291748486237186, 0.334110095650077],
|
289 |
"Spearman": [0.3505, 0.1857, 0.3264, 0.4512,
|
290 |
0, 0, 0, 0,
|
291 |
+
0.4200280894403279, 0.5723981513727318, 0.3392536955889527, 0.6542301178956093, 0.5685750705840381
|
292 |
0.02673703949665616, 0.3132279427962962, 0.19244600211698878, 0.3697144425033483]
|
293 |
}
|
294 |
|
|
|
299 |
"Methods": Methods,
|
300 |
"Accuracy": [0.5107, 0.5050, 0.5461, 0.5581,
|
301 |
0.5067545088210725, 0.4766805549971185, 0, 0,
|
302 |
+
0.570425718931911, 0.5518648601785212, 0.5162097017834246, 0.5757498972475753, 0.5593401842395651
|
303 |
0.49544642857142857, 0.506452190525333, 0.5427970103511899, 0.5491338026438646],
|
304 |
"Kendall's Tau": [0.1281, 0.0635, 0.2716, 0.3864,
|
305 |
0.18884532500063825, 0.31629653258509166, 0, 0,
|
306 |
+
0.42340286124586973, 0.42163723763190575, 0.3111422734769831, 0.46417209045053276, 0.36801116758496544
|
307 |
0.04074528095431955, 0.3533564092679483, 0.19204956587442087, 0.24122049643546917],
|
308 |
"Spearman": [0.1352, 0.0667, 0.2867, 0.4157,
|
309 |
0.2033137543983765, 0.35189638758373964, 0, 0,
|
310 |
+
0.44950359766748854, 0.4567231163496956, 0.3284040387552273, 0.5061135134678696, 0.410623572297829
|
311 |
0.04302709609666947, 0.3758784332521168, 0.2019542748712654, 0.25105320709917717]
|
312 |
}
|
313 |
df2 = pd.DataFrame(TE)
|
|
|
317 |
"Methods": Methods,
|
318 |
"Accuracy": [0.6504, 0.6014, 0.7162, 0.7441,
|
319 |
0.7518953983108395, 0.7870818213649097, 0.6187623875307698, 0.8003185213479332,
|
320 |
+
0.7477385992275697, 0.7969309163059164, 0.784410942407266, 0.769276748578219, 0.7542146782955607
|
321 |
0.5, 0.7231299072659366, 0.5, 0.7348077412783295],
|
322 |
"Kendall's Tau": [0.3957, 0.2688, 0.5092, 0.5001,
|
323 |
0.5377072309689559, 0.5709963447418871, 0.30897221697376714, 0.6064826537169805,
|
324 |
+
0.49885108461595573, 0.5408319381088115, 0.566750311845092, 0.539144026776003, 0.5039030127649896
|
325 |
0.0, 0.48911130738063485, 0.0, 0.5436010461720943],
|
326 |
"Spearman": [0.4188, 0.2817, 0.5403, 0.5405,
|
327 |
0.5830423197486431, 0.6276373633425562, 0.324348752437819, 0.6664032039425867,
|
328 |
+
0.5603311161969196, 0.5987990693735654, 0.6200483357955027, 0.6021636544977567, 0.5658023652256237
|
329 |
0.0, 0.530151784406405, 0.0, 0.5767282714406644]
|
330 |
}
|
331 |
df3 = pd.DataFrame(SG)
|
|
|
335 |
"Methods": Methods,
|
336 |
"Accuracy": [0.5935, 0.5817, 0.7000, 0.7203,
|
337 |
0, 0, 0, 0,
|
338 |
+
0.7215900072150073, 0.7137157287157287, 0.7298538961038961, 0.7578841991341992, 0.742178932178932
|
339 |
0.6365868506493507,0.5985240800865801, 0.5590909090909092, 0.6762518037518037],
|
340 |
"Kendall's Tau": [0.2332, 0.2389, 0.4440, 0.4235,
|
341 |
0, 0, 0, 0,
|
342 |
+
0.49445393416475697, 0.40897219553585185, 0.39880657282887155, 0.4594680081243032, 0.44808795202384744
|
343 |
0.402354630029616, 0.29538507694084404, 0.10735098173126541, 0.4077804758055409],
|
344 |
"Spearman": [0.2443, 0.2492, 0.4630, 0.4511,
|
345 |
0, 0, 0, 0,
|
346 |
+
0.5214865171404164, 0.4479941149402397, 0.424528242404003, 0.49907660929552167, 0.48643423849581746
|
347 |
0.41802883351668096, 0.31033689944001186, 0.1096152564140644, 0.43265604612874153]
|
348 |
}
|
349 |
df4 = pd.DataFrame(NFQA)
|
test.py
CHANGED
@@ -3,7 +3,7 @@ import pandas as pd
|
|
3 |
TeamId = ["baseline", "baseline", "baseline", "baseline",
|
4 |
'ISLab', 'ISLab', 'ISLab', 'ISLab',
|
5 |
'default5', 'default5', 'default5', 'default5',
|
6 |
-
'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR']
|
7 |
Methods = ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o",
|
8 |
"llama3-1_baseline5", "llama3-1_baseline6", "llama3-1-baseline7", "llama3-2-baseline",
|
9 |
"baselinev02", "baselinev72r1", "baselinev70r1", "baselinev72r2",
|
|
|
3 |
TeamId = ["baseline", "baseline", "baseline", "baseline",
|
4 |
'ISLab', 'ISLab', 'ISLab', 'ISLab',
|
5 |
'default5', 'default5', 'default5', 'default5',
|
6 |
+
'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR']
|
7 |
Methods = ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o",
|
8 |
"llama3-1_baseline5", "llama3-1_baseline6", "llama3-1-baseline7", "llama3-2-baseline",
|
9 |
"baselinev02", "baselinev72r1", "baselinev70r1", "baselinev72r2",
|