squad_tools.py

# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
#
# 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.

from __future__ import print_function
from collections import Counter
import string
import re
import json
import sys


def normalize_answer(s):
    """Lower text and remove punctuation, articles and extra whitespace."""
    def remove_articles(text):
        return re.sub(r'\b(a|an|the)\b', ' ', text)

    def white_space_fix(text):
        return ' '.join(text.split())

    def remove_punc(text):
        exclude = set(string.punctuation)
        return ''.join(ch for ch in text if ch not in exclude)

    def lower(text):
        return text.lower()

    return white_space_fix(remove_articles(remove_punc(lower(s))))


def f1_score(prediction, ground_truth):
    prediction_tokens = normalize_answer(prediction).split()
    ground_truth_tokens = normalize_answer(ground_truth).split()
    common = Counter(prediction_tokens) & Counter(ground_truth_tokens)
    num_same = sum(common.values())
    if num_same == 0:
        return 0
    precision = 1.0 * num_same / len(prediction_tokens)
    recall = 1.0 * num_same / len(ground_truth_tokens)
    f1 = (2 * precision * recall) / (precision + recall)
    return f1


def exact_match_score(prediction, ground_truth):
    return (normalize_answer(prediction) == normalize_answer(ground_truth))


def metric_max_over_ground_truths(metric_fn, prediction, ground_truths):
    scores_for_ground_truths = []
    for ground_truth in ground_truths:
        score = metric_fn(prediction, ground_truth)
        scores_for_ground_truths.append(score)
    return max(scores_for_ground_truths)


def evaluate(dataset, predictions, ignore_missing_qids=False):
    f1 = exact_match = total = 0
    for article in dataset:
        for paragraph in article['paragraphs']:
            for qa in paragraph['qas']:
                if qa['id'] not in predictions:
                    if not ignore_missing_qids:
                        message = 'Unanswered question ' + qa['id'] + \
                                  ' will receive score 0.'
                        print(message, file=sys.stderr)
                        total += 1
                    continue
                total += 1
                ground_truths = list(map(lambda x: x['text'], qa['answers']))
                prediction = predictions[qa['id']]
                exact_match += metric_max_over_ground_truths(
                    exact_match_score, prediction, ground_truths)
                f1 += metric_max_over_ground_truths(
                    f1_score, prediction, ground_truths)

    exact_match = 100.0 * exact_match / total
    f1 = 100.0 * f1 / total

    return {'exact_match': exact_match, 'f1': f1}





global_id = 0


def build_squad_input(question: str, contexts: [str]) -> dict:
    global global_id
    bert_input = {
        'data': [{
            'title': "intranet",
            'paragraphs': []  # Going to fill this one with the pages and question
        }],
        'version': "2.0"
    }

    for i in range(len(contexts)):
        context = contexts[i]
        global_id += 1
        id_ = global_id
        element = {
            'context': context,
            'qas': [{'question': question, 'id': id_, #'answers': [{'text': "", 'answer_start': 0}],
                     "is_impossible": True
                    }]
        }
        bert_input['data'][0]['paragraphs'].append(element)
    return bert_input