File size: 7,145 Bytes
0daf005 4d4c4d4 0daf005 4d4c4d4 0daf005 4d4c4d4 0daf005 4d4c4d4 0daf005 4d4c4d4 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 |
# 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
# 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/aciton_generation")
>>> results = metric.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"
class BaseEvaluater:
eps = 1e-8
def __call__(self, preds, labels):
return self._compute(preds, labels)
def _compute(self, preds, labels):
# calculate precision, recall, f1
tp, fp, fn = 0, 0, 0
for pred, label in zip(preds, labels):
tp += len(set(pred) & set(label))
fp += len(set(pred) - set(label))
fn += len(set(label) - set(pred))
precision = tp / (tp + fp + self.eps)
recall = tp / (tp + fn + self.eps)
f1 = 2 * precision * recall / (precision + recall)
return {
"precision": round(precision, 4),
"recall": round(recall, 4),
"f1": round(f1, 4)
}
class ClassEvaluater(BaseEvaluater):
def __init__(self, valid_labels=None):
self.valid_labels = valid_labels
def __call__(self, preds, labels):
preds = map(self.extract_class, preds)
labels = map(self.extract_class, labels)
# helper function to extract valid tags
preds = list(map(self.extract_valid, preds))
labels = list(map(self.extract_valid, labels))
return self._compute(preds, labels)
def extract_valid(self, tags):
# TODO: if valid_labels is None:
tags = list(filter(lambda tag: tag in self.valid_labels, tags))
return tags
def extract_class(self, tags):
tags = map(lambda tag: tag.replace("/ ", "/"), tags)
tags = list(map(self.batch_extract_class, tags))
# deduplicate
tags = list(dict.fromkeys(tags))
return tags
def batch_extract_class(self, tag):
# filter out invalid tags
tag = tag.split('/')
if len(tag)==3:
_class = '/'.join(tag[:2])
elif len(tag)==4:
_class = '/'.join(tag[:3])
elif len(tag)==1:
_class = ''
else:
_class = None
if _class in self.valid_labels:
return _class
else:
return ""
class PhraseEvaluater(BaseEvaluater):
def __init__(self, valid_labels=None):
self.valid_labels = valid_labels
def __call__(self, preds, labels):
preds = map(self.extract_phrase, preds)
labels = map(self.extract_phrase, labels)
return self._compute(preds, labels)
def extract_phrase(self, tags):
tags = map(lambda tag: tag.replace("/ ", "/"), tags)
tags = list(map(self.batch_extract_phrase, tags))
# deduplicate
tags = list(dict.fromkeys(tags))
return tags
def batch_extract_phrase(self, phrase):
# filter out invalid tags
tag = phrase.split('/')
if len(tag)==3:
_class = '/'.join(tag[:2])
elif len(tag)==4:
_class = '/'.join(tag[:3])
elif len(tag)==1:
_class = ''
else:
_class = None
if _class in self.valid_labels:
return phrase.replace(_class, '')
else:
return ""
@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class action_generation(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,
valid_labels=None, detailed_scores=False,
weights={"class": 0.8, "phrase": 0.2}
):
"""Returns the scores"""
weights = {"class": 0.8, "phrase": 0.2}
class_eval = ClassEvaluater(valid_labels)(predictions, references)
phrase_eval = PhraseEvaluater(valid_labels)(predictions, references)
weight_sum = {
key: round((class_eval[key] * weights["class"]) + (phrase_eval[key] * weights["phrase"]), 4)
for key in class_eval
}
if detailed_scores:
results = {
"class": class_eval,
"phrase": phrase_eval,
"weighted_sum": weight_sum
}
else:
results = weight_sum
return results
|