Hugging Face's logo

Spaces:
kenken999
/
fastapi_django_main_live
Running on Zero

App Files Community
fastapi_django_main_live
File size: 4,820 Bytes 
3860419
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os

import datasets
import pandas as pd


_CITATION = """\
@article{hendryckstest2021,
  title={Measuring Massive Multitask Language Understanding},
  author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt},
  journal={Proceedings of the International Conference on Learning Representations (ICLR)},
  year={2021}
}
"""

_DESCRIPTION = """\
Measuring Massive Multitask Language Understanding by Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt (ICLR 2021).
"""

_HOMEPAGE = "https://github.com/hendrycks/test"

_LICENSE = "MIT"

_URL = "mmlu.zip"

task_list = [
    "high_school_european_history",
    "business_ethics",
    "clinical_knowledge",
    "medical_genetics",
    "high_school_us_history",
    "high_school_physics",
    "high_school_world_history",
    "virology",
    "high_school_microeconomics",
    "econometrics",
    "college_computer_science",
    "high_school_biology",
    "abstract_algebra",
    "professional_accounting",
    "philosophy",
    "professional_medicine",
    "nutrition",
    "global_facts",
    "machine_learning",
    "security_studies",
    "public_relations",
    "professional_psychology",
    "prehistory",
    "anatomy",
    "human_sexuality",
    "college_medicine",
    "high_school_government_and_politics",
    "college_chemistry",
    "logical_fallacies",
    "high_school_geography",
    "elementary_mathematics",
    "human_aging",
    "college_mathematics",
    "high_school_psychology",
    "formal_logic",
    "high_school_statistics",
    "international_law",
    "high_school_mathematics",
    "high_school_computer_science",
    "conceptual_physics",
    "miscellaneous",
    "high_school_chemistry",
    "marketing",
    "professional_law",
    "management",
    "college_physics",
    "jurisprudence",
    "world_religions",
    "sociology",
    "us_foreign_policy",
    "high_school_macroeconomics",
    "computer_security",
    "moral_scenarios",
    "moral_disputes",
    "electrical_engineering",
    "astronomy",
    "college_biology",
]


class MMLUConfig(datasets.BuilderConfig):
    def __init__(self, **kwargs):
        super().__init__(version=datasets.Version("1.0.0"), **kwargs)


class MMLU(datasets.GeneratorBasedBuilder):
    BUILDER_CONFIGS = [
        MMLUConfig(
            name=task_name,
        )
        for task_name in task_list
    ]

    def _info(self):
        features = datasets.Features(
            {
                "question": datasets.Value("string"),
                "A": datasets.Value("string"),
                "B": datasets.Value("string"),
                "C": datasets.Value("string"),
                "D": datasets.Value("string"),
                "answer": datasets.Value("string"),
            }
        )
        return datasets.DatasetInfo(
            description=_DESCRIPTION,
            features=features,
            homepage=_HOMEPAGE,
            license=_LICENSE,
            citation=_CITATION,
        )

    def _split_generators(self, dl_manager):
        data_dir = dl_manager.download_and_extract(_URL)
        task_name = self.config.name
        return [
            datasets.SplitGenerator(
                name=datasets.Split.TEST,
                gen_kwargs={
                    "filepath": os.path.join(data_dir, "data", "test", f"{task_name}_test.csv"),
                },
            ),
            datasets.SplitGenerator(
                name=datasets.Split.VALIDATION,
                gen_kwargs={
                    "filepath": os.path.join(data_dir, "data", "val", f"{task_name}_val.csv"),
                },
            ),
            datasets.SplitGenerator(
                name=datasets.Split.TRAIN,
                gen_kwargs={
                    "filepath": os.path.join(data_dir, "data", "dev", f"{task_name}_dev.csv"),
                },
            ),
        ]

    def _generate_examples(self, filepath):
        df = pd.read_csv(filepath)
        df.columns = ["question", "A", "B", "C", "D", "answer"]

        for i, instance in enumerate(df.to_dict(orient="records")):
            yield i, instance