Spaces:
Build error
Build error
File size: 6,012 Bytes
d101c72 00e1647 d101c72 00e1647 d101c72 |
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 |
# 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.
"""ISCO-08 Hierarchical Accuracy Measure."""
import evaluate
import datasets
import ham
import isco
# TODO: Add BibTeX citation
_CITATION = """
@article{scikit-learn,
title={Scikit-learn: Machine Learning in {P}ython},
author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
journal={Journal of Machine Learning Research},
volume={12},
pages={2825--2830},
year={2011}
}
"""
_DESCRIPTION = """
The ISCO-08 Hierarchical Accuracy Measure is an implementation of the measure described in [Functional Annotation of Genes Using Hierarchical Text Categorization](https://www.researchgate.net/publication/44046343_Functional_Annotation_of_Genes_Using_Hierarchical_Text_Categorization) (Kiritchenko, Svetlana and Famili, Fazel. 2005) and adapted for the ISCO-08 classification scheme by the International Labour Organization.
"""
_KWARGS_DESCRIPTION = """
Calculates hierarchical precision, hierarchical recall and hierarchical F1 given a list of reference codes and predicted codes from the ISCO-08 taxonomy by the International Labour Organization.
Args:
- references (List[str]): List of ISCO-08 reference codes. Each reference code should be a single token, 4-digit ISCO-08 code string.
- predictions (List[str]): List of machine predicted or human assigned ISCO-08 codes to score. Each prediction should be a single token, 4-digit ISCO-08 code string.
Returns:
- hierarchical_precision (`float` or `int`): Hierarchical precision score. Minimum possible value is 0. Maximum possible value is 1.0. A higher score means higher accuracy.
- hierarchical_recall: Hierarchical recall score. Minimum possible value is 0. Maximum possible value is 1.0. A higher score means higher accuracy.
- hierarchical_fmeasure: Hierarchical F1 score. Minimum possible value is 0. Maximum possible value is 1.0. A higher score means higher accuracy.
Examples:
Example 1
>>> hierarchical_accuracy_metric = evaluate.load("ham")
>>> results = ham.compute(reference=["1111", "1112", "1113", "1114"], predictions=["1111", "1113", "1120", "1211"])
>>> print(results)
{
'accuracy': 0.25,
'hierarchical_precision': 0.7142857142857143,
'hierarchical_recall': 0.5,
'hierarchical_fmeasure': 0.588235294117647
}
"""
# TODO: Define external resources urls if needed
ISCO_CSV_MIRROR_URL = (
"https://storage.googleapis.com/isco-public/tables/ISCO_structure.csv"
)
ILO_ISCO_CSV_URL = (
"https://www.ilo.org/ilostat-files/ISCO/newdocs-08-2021/ISCO-08/ISCO-08%20EN.csv"
)
@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class ISCO_Hierarchical_Accuracy(evaluate.Metric):
"""The ISCO-08 Hierarchical Accuracy Measure"""
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("string"),
"references": datasets.Value("string"),
}
),
# TODO: Homepage of the module for documentation
homepage="http://module.homepage",
# TODO: 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 external ISCO-08 csv file from the ILO website for creating the hierarchy dictionary."""
isco_csv = dl_manager.download_and_extract(ISCO_CSV_MIRROR_URL)
print(f"ISCO CSV file downloaded")
self.isco_hierarchy = isco.create_hierarchy_dict(isco_csv)
print("ISCO hierarchy dictionary created")
print(self.isco_hierarchy)
def _compute(self, predictions, references):
"""Returns the accuracy scores."""
# Convert the inputs to strings
predictions = [str(p) for p in predictions]
references = [str(r) for r in references]
# Calculate accuracy
accuracy = sum(i == j for i, j in zip(predictions, references)) / len(
predictions
)
print(f"Accuracy: {accuracy}")
# Calculate hierarchical precision, recall and f-measure
hierarchy = self.isco_hierarchy
hP, hR = ham.calculate_hierarchical_precision_recall(
references, predictions, hierarchy
)
hF = ham.hierarchical_f_measure(hP, hR)
print(
f"Hierarchical Precision: {hP}, Hierarchical Recall: {hR}, Hierarchical F-measure: {hF}"
)
return {
"accuracy": accuracy,
"hierarchical_precision": hP,
"hierarchical_recall": hR,
"hierarchical_fmeasure": hF,
}
|