File size: 5,178 Bytes
dbf7be3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# 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.
"""CodeBLEU metric."""

import evaluate
import datasets

#these were added to fix evaluate load of dependencies
from .bleu import corpus_bleu
from .utils import pad_sequence
from .weighted_ngram_match import ngrams
from .syntax_match import calc_syntax_match
from .parser_DFG import DFG_python
from .parser_utils import tree_to_token_index
from .dataflow_match import calc_dataflow_match

from .my_codebleu import calc_codebleu


# TODO: Add BibTeX citation
_CITATION = """\
@InProceedings{huggingface:module,
title = {CodeBLEU: A Metric for Evaluating Code Generation},
authors={Sedykh, Ivan},
year={2022}
}
"""

# TODO: Add description of the module here
_DESCRIPTION = """\
This new module is an adaptation of the original CodeBLEU metric from CodexGLUE benchmark 
for evaluating code generation.
"""


# TODO: Add description of the arguments of the module here
_KWARGS_DESCRIPTION = """
Calculates how good are predictions given some references, using certain scores
Args:
    predictions: list of predictions to score. Each predictions
        should be a string with tokens separated by spaces.
    references: list of lists of references. Each list 
        should contain len(predictions) items.
    lang: programming language in ['java','js','c_sharp','php','go','python','ruby']
    tokenizer: tokenizer function str -> List[str], Defaults to lambda s: s.split()
    params: str, weights for averaging(see CodeBLEU paper). 
        Defaults to equal weights "0.25,0.25,0.25,0.25".
Returns:
    CodeBLEU: resulting score,
    ngram_match_score: See paper CodeBLEU,
    weighted_ngram_match_score: See paper CodeBLEU,
    syntax_match_score: See paper CodeBLEU,
    dataflow_match_score: See paper CodeBLEU,
Examples:

    >>> codebleu = evaluate.load("my_new_module")
    >>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
    >>> print(results)
    {'accuracy': 1.0}
"""

# TODO: Define external resources urls if needed
# BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class codebleu(evaluate.Metric):
    """CodeBLEU metric from CodexGLUE"""

    def _info(self):
        # TODO: Specifies the evaluate.EvaluationModuleInfo object
        return evaluate.MetricInfo(
            # This is the description that will appear on the modules page.
            module_type="metric",
            description=_DESCRIPTION,
            citation=_CITATION,
            inputs_description=_KWARGS_DESCRIPTION,
            # This defines the format of each prediction and reference
            features=[
                datasets.Features(
                    {
                        "predictions": datasets.Value("string", id="sequence"),
                        "references": datasets.Sequence(datasets.Value("string", id="sequence"), id="references"),
                    }
                ),
                datasets.Features(
                    {
                        "predictions": datasets.Value("string", id="sequence"),
                        "references": datasets.Value("string", id="sequence"),
                    }
                ),                
            ],
            # Homepage of the module for documentation
            homepage="",
            # Additional links to the codebase or references
            codebase_urls=[],
            reference_urls=[
                "https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/code-to-code-trans/evaluator",
                "https://arxiv.org/abs/2009.10297",
            ],
        )

    def _download_and_prepare(self, dl_manager):
        """Optional: download external resources useful to compute the scores"""
        # TODO: Download external resources if needed
        # source CodeBLEU/parser/build.sh
        # print(dl_manager)
        self.kw_dir = dl_manager.download_and_extract("keywords.tar.gz")
        print("Downloaded keywords to", self.kw_dir)
        self.langso_dir = dl_manager.download("my-languages.so")
        print("Downloaded languages.so to", self.langso_dir)

    def _compute(self, predictions, references, lang = "python", tokenizer=None, params="0.25,0.25,0.25,0.25"):
        """Returns the scores"""
        res = calc_codebleu(
            predictions=predictions,
            references=references,
            lang=lang,
            tokenizer=tokenizer,
            params=params,
            kw_dir = self.kw_dir,
            langso_dir = self.langso_dir
        )
        return res