m2.py

# 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
from datasets import Features, Sequence, Value
import pdb

from m2scorer import get_m2score, get_m2score_from_raw, load_m2

# 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.

    >>> 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 M2(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=Features({
                'predictions': Value(dtype='string'),
                'references': {
                    'source_sentence': Value(dtype='string'),
                    'edits': Sequence({
                        'from': Value(dtype='int32'),
                        'to': Value(dtype='int32'),
                        'text': [Value(dtype='string')],
                        'aid': Value(dtype='int32'),
                    }),
                },
            }),
            # 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):
        """Returns the scores"""
        gold_data = self._features_to_gold_data(references)
        # TODO: Compute the different scores of the module
        p, r, f = get_m2score(predictions, gold_data, tokenize=False, keep_gold=True)
        return {
            "f0.5": f,
            "precision": p,
            "recall": r,
        }

    def _features_to_gold_data(self, features):
        gold_data = []
        for entry in features:
            annotators = {}
            edits = entry['edits']
            for i in range(len(edits['from'])):
                edit = (edits['from'][i], edits['to'][i], edits['text'][i])
                if edits['aid'][i] not in annotators:
                    annotators[edits['aid'][i]] = []
                annotators[edits['aid'][i]].append(edit)
            gold_data.append( (entry['source_sentence'], annotators) )
        return gold_data

    def load_m2_file(self, fpath):
        data = load_m2(fpath)
        result = []
        for src_sent, edits_ in data:
            edits = []
            for aid, annotator_edits in edits_.items():
                if len(annotator_edits) == 0:
                    edits.append({'from': -1, 'to': -1, 'text': [''], 'aid': aid})
                for from_, to_, text_ in annotator_edits:
                    edits.append({'from': from_, 'to': to_, 'text': text_, 'aid': aid})
            result.append({
                'source_sentence': src_sent,
                'edits': edits,
            })
        return result