Hugging Face's logo

Spaces:
nan
/
leaderboard
Runtime error

App Files Community
1
leaderboard
File size: 2,542 Bytes 
9c49811
 
 
f30cbcc
9c49811
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f30cbcc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9c49811
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f30cbcc
 
 
 
 
 
 
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
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
 
import pandas as pd
import pytest

from utils import filter_models, search_table, filter_queries, select_columns, update_table_long_doc


@pytest.fixture
def toy_df():
    return pd.DataFrame(
        {
            "Retrieval Model": [
                "bge-m3",
                "bge-m3",
                "jina-embeddings-v2-base",
                "jina-embeddings-v2-base"
            ],
            "Reranking Model": [
                "bge-reranker-v2-m3",
                "NoReranker",
                "bge-reranker-v2-m3",
                "NoReranker"
            ],
            "Average ⬆️": [0.6, 0.4, 0.3, 0.2],
            "wiki_en": [0.8, 0.7, 0.2, 0.1],
            "wiki_zh": [0.4, 0.1, 0.4, 0.3],
            "news_en": [0.8, 0.7, 0.2, 0.1],
            "news_zh": [0.4, 0.1, 0.4, 0.3],
        }
    )


@pytest.fixture
def toy_df_long_doc():
    return pd.DataFrame(
        {
            "Retrieval Model": [
                "bge-m3",
                "bge-m3",
                "jina-embeddings-v2-base",
                "jina-embeddings-v2-base"
            ],
            "Reranking Model": [
                "bge-reranker-v2-m3",
                "NoReranker",
                "bge-reranker-v2-m3",
                "NoReranker"
            ],
            "Average ⬆️": [0.6, 0.4, 0.3, 0.2],
            "law_en_lex_files_300k_400k": [0.4, 0.1, 0.4, 0.3],
            "law_en_lex_files_400k_500k": [0.8, 0.7, 0.2, 0.1],
            "law_en_lex_files_500k_600k": [0.8, 0.7, 0.2, 0.1],
            "law_en_lex_files_600k_700k": [0.4, 0.1, 0.4, 0.3],
        }
    )
def test_filter_models(toy_df):
    df_result = filter_models(toy_df, ["bge-reranker-v2-m3", ])
    assert len(df_result) == 2
    assert df_result.iloc[0]["Reranking Model"] == "bge-reranker-v2-m3"


def test_search_table(toy_df):
    df_result = search_table(toy_df, "jina")
    assert len(df_result) == 2
    assert df_result.iloc[0]["Retrieval Model"] == "jina-embeddings-v2-base"


def test_filter_queries(toy_df):
    df_result = filter_queries("jina", toy_df)
    assert len(df_result) == 2
    assert df_result.iloc[0]["Retrieval Model"] == "jina-embeddings-v2-base"


def test_select_columns(toy_df):
    df_result = select_columns(toy_df, ['news',], ['zh',])
    assert len(df_result.columns) == 4
    assert df_result['Average ⬆️'].equals(df_result['news_zh'])


def test_update_table_long_doc(toy_df_long_doc):
    df_result = update_table_long_doc(toy_df_long_doc, ['law',], ['en',], ["bge-reranker-v2-m3", ], "jina")
    print(df_result)