File size: 4,568 Bytes
edc5524
 
 
 
 
 
 
 
 
 
 
 
 
 
5d8c50a
edc5524
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d8c50a
 
 
 
 
 
 
 
 
 
 
 
36ed57b
 
 
 
 
 
 
d38c9a3
5d8c50a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36ed57b
 
 
 
 
d38c9a3
5d8c50a
 
 
 
 
 
 
edc5524
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f15598c
 
edc5524
 
 
 
 
 
 
 
 
 
 
 
 
 
5d8c50a
 
ec79cc9
edc5524
5d8c50a
 
 
 
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
# 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."""
from typing import List

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.

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


def calculate_precision(
        predictions: List[List[str]],
        reference: List[List[str]]
) -> float:
    precision = 0
    count = 0

    for i, d in enumerate(reference):
        if len(d) == 0:
            continue

        predicted_titles = predictions[i]
        hits = 0
        for title in predicted_titles:
            if title in d:
                hits += 1

        if len(predicted_titles) != 0:
            precision += hits / len(predicted_titles)

        count += 1

    return precision / count


def calculate_recall(
        predictions: List[List[str]],
        reference: List[List[str]]
) -> float:
    recall = 0
    count = 0

    for i, d in enumerate(reference):
        if len(d) == 0:
            continue

        predicted_titles = predictions[i]
        hits = 0
        for title in predicted_titles:
            if title in d:
                hits += 1
        recall += hits / len(d)

        count += 1

    return recall / count


beta = 0.7


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class DocRetrieveMetrics(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 _compute(self, predictions, references):
        recall = calculate_recall(predictions, references)
        precision = calculate_precision(predictions, references)
        f_score = (1 + beta*beta) * precision * recall / (beta * beta*precision + recall)
        return {
            "f1": float(
                f_score
            )
        }