File size: 5,502 Bytes
25557b5
 
 
 
 
 
 
 
05c90f4
 
 
 
 
 
 
 
 
5b0b818
05c90f4
25557b5
 
 
 
c660995
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25557b5
 
05c90f4
c660995
25557b5
05c90f4
 
 
 
 
 
 
 
 
25557b5
e29ab28
05c90f4
e29ab28
 
05c90f4
 
 
 
 
 
 
 
 
e29ab28
 
 
25557b5
 
05c90f4
e29ab28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
05c90f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25557b5
 
e611814
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
05c90f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25557b5
e611814
 
05c90f4
 
e611814
 
 
05c90f4
 
e611814
 
 
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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
import json

import gradio as gr
import pandas as pd
from huggingface_hub import HfFileSystem


RESULTS_DATASET_ID = "datasets/open-llm-leaderboard/results"
EXCLUDED_KEYS =  {
    "pretty_env_info",
    "chat_template",
    "group_subtasks",
}
EXCLUDED_RESULTS_KEYS = {
    "leaderboard",
}
EXCLUDED_RESULTS_LEADERBOARDS_KEYS = {
    "alias",
}

fs = HfFileSystem()


def fetch_result_paths():
    paths = fs.glob(f"{RESULTS_DATASET_ID}/**/**/*.json")
    return paths


def filter_latest_result_path_per_model(paths):
    from collections import defaultdict

    d = defaultdict(list)
    for path in paths:
        model_id, _ = path[len(RESULTS_DATASET_ID) +1:].rsplit("/", 1)
        d[model_id].append(path)
    return {model_id: max(paths) for model_id, paths in d.items()}


def get_result_path_from_model(model_id, result_path_per_model):
    return result_path_per_model[model_id]


def load_data(result_path) -> pd.DataFrame:
    with fs.open(result_path, "r") as f:
        data = json.load(f)
    return data
    # model_name = data.get("model_name", "Model")
    # df = pd.json_normalize([data])
    # return df.iloc[0].rename_axis("Parameters").rename(model_name).to_frame()  # .reset_index()


def load_result(model_id):
    result_path = get_result_path_from_model(model_id, latest_result_path_per_model)
    data = load_data(result_path)
    model_name = data.get("model_name", "Model")
    df = to_dataframe_all(data)
    result = [
        to_vertical(df, model_name),
        to_vertical(to_dataframe_results(df), model_name)
    ]
    return result


def to_dataframe(data):
    return pd.DataFrame.from_records([data])


def to_vertical(df, model_name):
    df = df.iloc[0].rename_axis("Parameters").rename(model_name).to_frame()  # .reset_index()
    df.index = df.index.str.join(".")
    return df


def to_dataframe_all(data):
    df = pd.json_normalize([{key: value for key, value in data.items() if key not in EXCLUDED_KEYS}])
    # df.columns = df.columns.str.split(".")  # .split return a list instead of a tuple
    df.columns = list(map(lambda x: tuple(x.split(".")), df.columns))
    return df

#
# def to_dataframe_results(data):
#     dfs = {}
#     for key in data["results"]:
#         if key not in EXCLUDED_RESULTS_KEYS:  # key.startswith("leaderboard_"):
#             name = key[len("leaderboard_"):]
#             df = to_dataframe(
#                 {
#                     key: value
#                     for key, value in data["results"][key].items()
#                     if key not in EXCLUDED_RESULTS_LEADERBOARDS_KEYS
#                 }
#             )
#             # df.drop(columns=["alias"])
#             # df.columns = pd.MultiIndex.from_product([[name], df.columns])
#             df.columns = [f"{name}.{column}" for column in df.columns]
#             dfs[name] = df
#     return pd.concat(dfs.values(), axis="columns")


def to_dataframe_results(df):
    df = df.loc[:, df.columns.str[0] == "results"]
    df = df.loc[:, ~df.columns.str[1].isin(EXCLUDED_RESULTS_KEYS)]
    df = df.loc[:, ~df.columns.str[2].isin(EXCLUDED_RESULTS_LEADERBOARDS_KEYS)]
    return df


def concat_result_1(result_1, results):
    return pd.concat([result_1, results.iloc[:, [0, 2]].set_index("Parameters")], axis=1).reset_index()


def concat_result_2(result_2, results):
    return pd.concat([results.iloc[:, [0, 1]].set_index("Parameters"), result_2], axis=1).reset_index()


def render_result_1(model_id, *results):
    result = load_result(model_id)
    return [concat_result_1(*result_args) for result_args in zip(result, results)]


def render_result_2(model_id, *results):
    result = load_result(model_id)
    return [concat_result_2(*result_args) for result_args in zip(result, results)]


# if __name__ == "__main__":
latest_result_path_per_model = filter_latest_result_path_per_model(fetch_result_paths())

with gr.Blocks(fill_height=True) as demo:
    gr.HTML("<h1 style='text-align: center;'>Compare Results of the 🤗 Open LLM Leaderboard</h1>")
    gr.HTML("<h3 style='text-align: center;'>Select 2 results to load and compare</h3>")

    with gr.Row():
        with gr.Column():
            model_id_1 = gr.Dropdown(choices=list(latest_result_path_per_model.keys()), label="Results")
            load_btn_1 = gr.Button("Load")
        with gr.Column():
            model_id_2 = gr.Dropdown(choices=list(latest_result_path_per_model.keys()), label="Results")
            load_btn_2 = gr.Button("Load")

    with gr.Row():
        with gr.Tab("All"):
            compared_results_all = gr.Dataframe(
                label="Results",
                headers=["Parameters", "Model-1", "Model-2"],
                interactive=False,
                column_widths=["30%", "30%", "30%"],
                wrap=True,
            )
        with gr.Tab("Results"):
            compared_results_results = gr.Dataframe(
                label="Results",
                headers=["Parameters", "Model-1", "Model-2"],
                interactive=False,
                column_widths=["30%", "30%", "30%"],
                wrap=True,
            )

    load_btn_1.click(
        fn=render_result_1,
        inputs=[model_id_1, compared_results_all, compared_results_results],
        outputs=[compared_results_all, compared_results_results],
    )
    load_btn_2.click(
        fn=render_result_2,
        inputs=[model_id_2, compared_results_all, compared_results_results],
        outputs=[compared_results_all, compared_results_results],
    )

demo.launch()