File size: 1,415 Bytes
09f141d
 
 
9b2d9e3
 
eb03344
70fab96
9b2d9e3
 
 
 
52e5d39
9b2d9e3
7d6719b
52e5d39
9b2d9e3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
170b68e
9b2d9e3
 
 
 
170b68e
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
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
import pandas as pd
import streamlit as st

st.set_page_config(
    page_title="JuStRank",
    page_icon="οΈπŸ§‘πŸ»β€βš–οΈ",
    # layout="wide",
    initial_sidebar_state="auto",
    menu_items=None,
)

st.title("πŸ§‘πŸ»β€βš–οΈ JuStRank: The Best Judges for Ranking Systems πŸ§‘πŸ»β€βš–οΈ")

url = "https://arxiv.org/pdf/2412.09569"
st.subheader("Check out our [Arxiv submission](%s) for more details" % url)

def prettify_judge_name(judge_name):
    pretty_judge = (judge_name[0].upper()+judge_name[1:]).replace("Gpt", "GPT")
    return pretty_judge


def format_digits(flt, num_digits=3):
    format_str = "{:."+str(num_digits-1)+"f}"
    format_str_zeroes = "{:."+str(num_digits)+"f}"
    return format_str_zeroes.format(flt)[1:] if (0 < flt < 1) else format_str.format(flt)


df = pd.read_csv("./best_judges_single_agg.csv")[["Judge Model", "Realization", "Ranking Agreement", "Decisiveness", "Bias"]]
df["Judge Model"] = df["Judge Model"].apply(prettify_judge_name)

styled_data = (
    df.style.background_gradient(subset=["Ranking Agreement"])
    .background_gradient(
        subset=["Ranking Agreement"],
        cmap="RdYlGn",
        vmin=0.5,
        vmax=0.9,
    )
    .format(subset=["Ranking Agreement", "Decisiveness", "Bias"], formatter=format_digits)
    .set_properties(**{"text-align": "center"})
)


st.dataframe(styled_data, use_container_width=True, height=800, hide_index=True)