AEOLLM / test.py
陈俊杰
0104
4ccefa7
import pandas as pd
TeamId = ["baseline", "baseline", "baseline", "baseline",
'ISLab', 'ISLab', 'ISLab', 'ISLab',
'default5', 'default5', 'default5', 'default5',
'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR']
Methods = ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o",
"llama3-1_baseline5", "llama3-1_baseline6", "llama3-1-baseline7", "llama3-2-baseline",
"baselinev02", "baselinev72r1", "baselinev70r1", "baselinev72r2",
'bert-base-uncased', 'gpt35turbo', 'logisticRegression', 'paraphrase-MiniLM-L6-v2']
DG = {
"TeamId": TeamId,
"Methods": Methods,
"Accuracy": [0.5806, 0.5483, 0.6001, 0.6472,
0, 0, 0, 0,
0.631700513538749, 0.7111356209150326, 0.6176633986928104, 0.735954715219421,
0.5073529411764706, 0.5104038281979459, 0.5405182072829132, 0.5156874416433239],
"Kendall's Tau": [0.3243, 0.1739, 0.3042, 0.4167,
0, 0, 0, 0,
0.38961572200778516, 0.5285302196320519, 0.31022946186879186, 0.5974703857412484,
0.024753688574416864, 0.2838365040871617, 0.18291748486237186, 0.334110095650077],
"Spearman": [0.3505, 0.1857, 0.3264, 0.4512,
0, 0, 0, 0,
0.4200280894403279, 0.5723981513727318, 0.3392536955889527, 0.6542301178956093,
0.02673703949665616, 0.3132279427962962, 0.19244600211698878, 0.3697144425033483]
}
for key, value in DG.items():
print(len(value))
df1 = pd.DataFrame(DG)
print(df1)