File size: 3,859 Bytes
b3f9eae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65fa5ba
 
b3f9eae
 
 
 
 
 
 
 
 
 
 
 
65fa5ba
b3f9eae
 
 
 
 
 
 
65fa5ba
 
b3f9eae
65fa5ba
 
 
b3f9eae
 
65fa5ba
 
b3f9eae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54a903b
 
b3f9eae
 
 
 
 
 
 
 
65fa5ba
f95c10c
65fa5ba
 
 
 
 
 
 
 
 
 
 
 
 
e1f597a
b3f9eae
 
 
 
c0f684d
 
b3f9eae
65fa5ba
 
c0f684d
65fa5ba
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
# 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 evaluate
import datasets
from collections import Counter
import numpy as np

# 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 module calculates the unigram precision, recall, and f1 score.
"""


# 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 list of int (token)
    references: list of list of int (tokens)
Returns:
    f1: the unigram f1 score.
    precision: the unigram accuracy.
    recall: the unigram recall.
Examples:

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



@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class unigram(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('int64')),
                'references': datasets.Sequence(datasets.Value('int64')),
            }),
            # 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 _prec_recall_f1_score(self, pred_items, gold_items):
        """
        Compute precision, recall and f1 given a set of gold and prediction items.
        :param pred_items: iterable of predicted values
        :param gold_items: iterable of gold values
        :return: tuple (p, r, f1) for precision, recall, f1
        """
        common = Counter(gold_items) & Counter(pred_items)
        num_same = sum(common.values())
        if num_same == 0:
            return 0, 0, 0
        precision = 1.0 * num_same / len(pred_items)
        recall = 1.0 * num_same / len(gold_items)
        f1 = (2 * precision * recall) / (precision + recall)
        return np.array([precision, recall, f1])

    def _compute(self, predictions, references):
        """Returns the scores"""
        # TODO: Compute the different scores of the module
        score = sum([self._prec_recall_f1_score(i, j) for i, j in zip(predictions, references)]) / float(len(predictions))
        
        return {
            "precision": score[0],
            "recall": score[1],
            "f1": score[2],    
        }