File size: 5,517 Bytes
71fa3d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e3694cd
 
71fa3d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a5ef0f
 
71fa3d3
0a5ef0f
71fa3d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c9a7298
 
71fa3d3
 
 
 
 
 
 
 
 
 
 
 
 
e3694cd
 
 
 
 
 
 
 
 
 
 
 
 
 
d5d2df0
71fa3d3
e3694cd
 
 
 
d5d2df0
 
 
 
 
 
e3694cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a5ef0f
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
# 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.
"""TODO: Add a description here."""

import string

import evaluate
import datasets


# TODO: Add BibTeX citation
_CITATION = """\
@InProceedings{huggingface:module,
title = {A great new module},
authors={huggingface, Inc.},
year={2020}
}
"""

# TODO: Add description of the module here
_DESCRIPTION = """\
This new module is designed to solve this great ML task and is crafted with a lot of care.
"""


# 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 reference for each prediction. Each
        reference should be a string with tokens separated by spaces.
Returns:
    accuracy: description of the first score,
    another_score: description of the second score,
Examples:
    Examples should be written in doctest format, and should illustrate how
    to use the function.

    >>> metric = evaluate.load("DarrenChensformer/eval_keyphrase")
    >>> results = metric.compute(references=[["Hello","World"]], predictions=[["hello","world"]])
    >>> print(results)
    {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'num_pred': 2.0, 'num_gold': 2.0}
"""

# 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 eval_keyphrase(evaluate.Metric):
    """TODO: Short description of my evaluation module."""

    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.Sequence(datasets.Value('string')),
                'references': datasets.Sequence(datasets.Value('string')),
            }),
            # Homepage of the module for documentation
            homepage="http://module.homepage",
            # Additional links to the codebase or references
            codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
            reference_urls=["http://path.to.reference.url/new_module"]
        )

    def _download_and_prepare(self, dl_manager):
        """Optional: download external resources useful to compute the scores"""
        # TODO: Download external resources if needed
        pass

    def _normalize_keyphrase(self, kp):

        def white_space_fix(text):
            return ' '.join(text.split())

        def remove_punc(text):
            exclude = set(string.punctuation)
            return ''.join(ch for ch in text if ch not in exclude)

        def lower(text):
            return text.lower()

        return white_space_fix(remove_punc(lower(kp)))

    def _compute(self, predictions, references, ignore_empty_label=True):
        """Returns the scores"""

        macro_metrics = {'precision': [], 'recall': [], 'f1': [], 'num_pred': [], 'num_gold': []}

        for targets, preds in zip(references, predictions):
            if ignore_empty_label:
                targets = [self._normalize_keyphrase(tmp_key).strip() for tmp_key in targets if len(self._normalize_keyphrase(tmp_key).strip()) != 0]
                preds = [self._normalize_keyphrase(tmp_key).strip() for tmp_key in preds if len(self._normalize_keyphrase(tmp_key).strip()) != 0]
            else:
                targets = [self._normalize_keyphrase(tmp_key).strip() for tmp_key in targets]
                preds = [self._normalize_keyphrase(tmp_key).strip() for tmp_key in preds]
            total_tgt_set = set(targets)
            total_preds = set(preds)
            if len(total_tgt_set) == 0: continue

            # get the total_correctly_matched indicators
            total_correctly_matched = len(total_preds & total_tgt_set)

            # macro metric calculating
            precision = total_correctly_matched / len(total_preds) if len(total_preds) else 0.0
            recall = total_correctly_matched / len(total_tgt_set)
            f1 = 2 * precision * recall / (precision + recall) if total_correctly_matched > 0 else 0.0
            macro_metrics['precision'].append(precision)
            macro_metrics['recall'].append(recall)
            macro_metrics['f1'].append(f1)
            macro_metrics['num_pred'].append(len(total_preds))
            macro_metrics['num_gold'].append(len(total_tgt_set))

        return { k: round(sum(v)/len(v), 4) for k, v in macro_metrics.items()}