Spaces:
Build error
Build error
File size: 4,147 Bytes
f93a3d8 bfa7fa8 f93a3d8 bfa7fa8 f93a3d8 bfa7fa8 f93a3d8 bfa7fa8 |
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 |
# 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.
"""SEScore: a text generation evaluation metric"""
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 = """\
SEScore is an evaluation metric that trys to compute an overall score to measure text generation quality.
"""
# 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}
"""
# 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 SEScore(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.Value('int64'),
'references': 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 _download_and_prepare(self, dl_manager):
"""download SEScore checkpoints to compute the scores"""
# Download SEScore checkpoint
from comet import load_from_checkpoint
import gdown
import os
url = "https://drive.google.com/uc?id=1QgMP_Y4QCbvDMTeVacYt0J76OYvwWK9V&export=download&confirm=true"
output = 'sescore_download.gz'
gdown.download(url, output, quiet=False)
cmd = 'tar -xvf sescore_download.gz'
os.system(cmd)
self.scorer = load_from_checkpoint('sescore_download/zh_en/checkpoint/sescore_english.ckpt')
def _compute(self, sources, predictions, references, gpus=None, progress_bar=False):
if gpus is None:
gpus = 1 if torch.cuda.is_available() else 0
data = {"src": references, "mt": predictions}
data = [dict(zip(data, t)) for t in zip(*data.values())]
scores, mean_score = self.scorer.predict(data, gpus=gpus, progress_bar=progress_bar)
return {"mean_score": mean_score, "scores": scores}
|