Spaces:
Running
Running
File size: 5,669 Bytes
241fc76 d428842 241fc76 d428842 241fc76 d428842 241fc76 d428842 241fc76 d428842 241fc76 d428842 241fc76 8fae68a 8d838e8 241fc76 8fae68a 241fc76 8fae68a 241fc76 8fae68a 241fc76 8fae68a 241fc76 8fae68a 241fc76 d428842 |
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 |
# 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.
"""Exact Match metric."""
import re
import string
import datasets
import numpy as np
import evaluate
_DESCRIPTION = """
Returns the rate at which the input predicted strings exactly match their references, ignoring any strings input as part of the regexes_to_ignore list.
"""
_KWARGS_DESCRIPTION = """
Args:
predictions: List of predicted texts.
references: List of reference texts.
regexes_to_ignore: List, defaults to None. Regex expressions of characters to
ignore when calculating the exact matches. Note: these regexes are removed
from the input data before the changes based on the options below (e.g. ignore_case,
ignore_punctuation, ignore_numbers) are applied.
ignore_case: Boolean, defaults to False. If true, turns everything
to lowercase so that capitalization differences are ignored.
ignore_punctuation: Boolean, defaults to False. If true, removes all punctuation before
comparing predictions and references.
ignore_numbers: Boolean, defaults to False. If true, removes all punctuation before
comparing predictions and references.
Returns:
exact_match: Dictionary containing exact_match rate. Possible values are between 0.0 and 1.0, inclusive.
Examples:
>>> exact_match = evaluate.load("exact_match")
>>> refs = ["the cat", "theater", "YELLING", "agent007"]
>>> preds = ["cat?", "theater", "yelling", "agent"]
>>> results = exact_match.compute(references=refs, predictions=preds)
>>> print(round(results["exact_match"], 2))
0.25
>>> exact_match = evaluate.load("exact_match")
>>> refs = ["the cat", "theater", "YELLING", "agent007"]
>>> preds = ["cat?", "theater", "yelling", "agent"]
>>> results = exact_match.compute(references=refs, predictions=preds, regexes_to_ignore=["the ", "yell"], ignore_case=True, ignore_punctuation=True)
>>> print(round(results["exact_match"], 2))
0.5
>>> exact_match = evaluate.load("exact_match")
>>> refs = ["the cat", "theater", "YELLING", "agent007"]
>>> preds = ["cat?", "theater", "yelling", "agent"]
>>> results = exact_match.compute(references=refs, predictions=preds, regexes_to_ignore=["the ", "yell", "YELL"], ignore_case=True, ignore_punctuation=True)
>>> print(round(results["exact_match"], 2))
0.75
>>> exact_match = evaluate.load("exact_match")
>>> refs = ["the cat", "theater", "YELLING", "agent007"]
>>> preds = ["cat?", "theater", "yelling", "agent"]
>>> results = exact_match.compute(references=refs, predictions=preds, regexes_to_ignore=["the ", "yell", "YELL"], ignore_case=True, ignore_punctuation=True, ignore_numbers=True)
>>> print(round(results["exact_match"], 2))
1.0
>>> exact_match = evaluate.load("exact_match")
>>> refs = ["The cat sat on the mat.", "Theaters are great.", "It's like comparing oranges and apples."]
>>> preds = ["The cat sat on the mat?", "Theaters are great.", "It's like comparing apples and oranges."]
>>> results = exact_match.compute(references=refs, predictions=preds)
>>> print(round(results["exact_match"], 2))
0.33
"""
_CITATION = """
"""
@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class ExactMatch(evaluate.Metric):
def _info(self):
return evaluate.MetricInfo(
description=_DESCRIPTION,
citation=_CITATION,
inputs_description=_KWARGS_DESCRIPTION,
features=datasets.Features(
{
"predictions": datasets.Value("string", id="sequence"),
"references": datasets.Value("string", id="sequence"),
}
),
reference_urls=[],
)
def _compute(
self,
predictions,
references,
regexes_to_ignore=None,
ignore_case=False,
ignore_punctuation=False,
ignore_numbers=False,
):
if regexes_to_ignore is not None:
for s in regexes_to_ignore:
predictions = np.array([re.sub(s, "", x) for x in predictions])
references = np.array([re.sub(s, "", x) for x in references])
else:
predictions = np.asarray(predictions)
references = np.asarray(references)
if ignore_case:
predictions = np.char.lower(predictions)
references = np.char.lower(references)
if ignore_punctuation:
repl_table = string.punctuation.maketrans("", "", string.punctuation)
predictions = np.char.translate(predictions, table=repl_table)
references = np.char.translate(references, table=repl_table)
if ignore_numbers:
repl_table = string.digits.maketrans("", "", string.digits)
predictions = np.char.translate(predictions, table=repl_table)
references = np.char.translate(references, table=repl_table)
score_list = predictions == references
return {"exact_match": np.mean(score_list)}
|