notebooks/squad_preprocessing.py

# Copyright (c) 2021 Graphcore Ltd. All rights reserved.
# Copyright 2020 The HuggingFace Team 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.
# The original code has been modified by Graphcore Ltd.

import collections

import numpy as np
import torch
from tqdm.auto import tqdm

from transformers import BertTokenizerFast, default_data_collator


max_seq_length = 384
doc_stride = 128
tokenizer = BertTokenizerFast.from_pretrained("bert-base-uncased")


# `prepare_train_features` comes unmodified from
# https://github.com/huggingface/transformers/blob/v4.9.1/examples/pytorch/question-answering/run_qa.py
def prepare_train_features(examples):
    # Tokenize our examples with truncation and padding, but keep the overflows using a stride. This results
    # in one example possible giving several features when a context is long, each of those features having a
    # context that overlaps a bit the context of the previous feature.
    pad_on_right = tokenizer.padding_side == "right"
    tokenized_examples = tokenizer(
        examples["question" if pad_on_right else "context"],
        examples["context" if pad_on_right else "question"],
        truncation="only_second" if pad_on_right else "only_first",
        max_length=max_seq_length,
        stride=doc_stride,
        return_overflowing_tokens=True,
        return_offsets_mapping=True,
        padding="max_length",
    )

    # Since one example might give us several features if it has a long context, we need a map from a feature to
    # its corresponding example. This key gives us just that.
    sample_mapping = tokenized_examples.pop("overflow_to_sample_mapping")
    # The offset mappings will give us a map from token to character position in the original context. This will
    # help us compute the start_positions and end_positions.
    offset_mapping = tokenized_examples.pop("offset_mapping")

    # Let's label those examples!
    tokenized_examples["start_positions"] = []
    tokenized_examples["end_positions"] = []

    for i, offsets in enumerate(offset_mapping):
        # We will label impossible answers with the index of the CLS token.
        input_ids = tokenized_examples["input_ids"][i]
        cls_index = input_ids.index(tokenizer.cls_token_id)

        # Grab the sequence corresponding to that example (to know what is the context and what is the question).
        sequence_ids = tokenized_examples.sequence_ids(i)

        # One example can give several spans, this is the index of the example containing this span of text.
        sample_index = sample_mapping[i]
        answers = examples["answers"][sample_index]
        # If no answers are given, set the cls_index as answer.
        if len(answers["answer_start"]) == 0:
            tokenized_examples["start_positions"].append(cls_index)
            tokenized_examples["end_positions"].append(cls_index)
        else:
            # Start/end character index of the answer in the text.
            start_char = answers["answer_start"][0]
            end_char = start_char + len(answers["text"][0])

            # Start token index of the current span in the text.
            token_start_index = 0
            while sequence_ids[token_start_index] != (1 if pad_on_right else 0):
                token_start_index += 1

            # End token index of the current span in the text.
            token_end_index = len(input_ids) - 1
            while sequence_ids[token_end_index] != (1 if pad_on_right else 0):
                token_end_index -= 1

            # Detect if the answer is out of the span (in which case this feature is labeled with the CLS index).
            if not (offsets[token_start_index][0] <= start_char and offsets[token_end_index][1] >= end_char):
                tokenized_examples["start_positions"].append(cls_index)
                tokenized_examples["end_positions"].append(cls_index)
            else:
                # Otherwise move the token_start_index and token_end_index to the two ends of the answer.
                # Note: we could go after the last offset if the answer is the last word (edge case).
                while token_start_index < len(offsets) and offsets[token_start_index][0] <= start_char:
                    token_start_index += 1
                tokenized_examples["start_positions"].append(token_start_index - 1)
                while offsets[token_end_index][1] >= end_char:
                    token_end_index -= 1
                tokenized_examples["end_positions"].append(token_end_index + 1)

    return tokenized_examples


# `prepare_validation_features` comes unmodified from
# https://github.com/huggingface/transformers/blob/master/examples/pytorch/question-answering/run_qa.py
def prepare_validation_features(examples):
    # Tokenize our examples with truncation and maybe padding, but keep the overflows using a stride. This results
    # in one example possible giving several features when a context is long, each of those features having a
    # context that overlaps a bit the context of the previous feature.
    pad_on_right = tokenizer.padding_side == "right"
    tokenized_examples = tokenizer(
        examples["question" if pad_on_right else "context"],
        examples["context" if pad_on_right else "question"],
        truncation="only_second" if pad_on_right else "only_first",
        max_length=max_seq_length,
        stride=doc_stride,
        return_overflowing_tokens=True,
        return_offsets_mapping=True,
        padding="max_length",
    )

    # Since one example might give us several features if it has a long context, we need a map from a feature to
    # its corresponding example. This key gives us just that.
    sample_mapping = tokenized_examples.pop("overflow_to_sample_mapping")

    # We keep the example_id that gave us this feature and we will store the offset mappings.
    tokenized_examples["example_id"] = []

    for i in range(len(tokenized_examples["input_ids"])):
        # Grab the sequence corresponding to that example (to know what is the context and what is the question).
        sequence_ids = tokenized_examples.sequence_ids(i)
        context_index = 1 if pad_on_right else 0

        # One example can give several spans, this is the index of the example containing this span of text.
        sample_index = sample_mapping[i]
        tokenized_examples["example_id"].append(examples["id"][sample_index])

        # Set to None the offset_mapping that are not part of the context so it's easy to determine if a token
        # position is part of the context or not.
        tokenized_examples["offset_mapping"][i] = [
            (o if sequence_ids[k] == context_index else None)
            for k, o in enumerate(tokenized_examples["offset_mapping"][i])
        ]

    return tokenized_examples


# `postprocess_qa_predictions` comes unmodified from
# https://github.com/huggingface/notebooks/blob/master/examples/question_answering.ipynb
def postprocess_qa_predictions(
    examples, features, raw_predictions, n_best_size=20, max_answer_length=30, squad_v2=False
):
    all_start_logits, all_end_logits = raw_predictions
    # Build a map example to its corresponding features.
    example_id_to_index = {k: i for i, k in enumerate(examples["id"])}
    features_per_example = collections.defaultdict(list)
    for i, feature in enumerate(features):
        features_per_example[example_id_to_index[feature["example_id"]]].append(i)

    # The dictionaries we have to fill.
    predictions = collections.OrderedDict()

    # Logging.
    print(f"Post-processing {len(examples)} example predictions split into {len(features)} features.")

    # Let's loop over all the examples!
    for example_index, example in enumerate(tqdm(examples)):
        # Those are the indices of the features associated to the current example.
        feature_indices = features_per_example[example_index]

        min_null_score = None  # Only used if squad_v2 is True.
        valid_answers = []

        context = example["context"]
        # Looping through all the features associated to the current example.
        for feature_index in feature_indices:
            # We grab the predictions of the model for this feature.
            start_logits = all_start_logits[feature_index]
            end_logits = all_end_logits[feature_index]
            # This is what will allow us to map some the positions in our logits to span of texts in the original
            # context.
            offset_mapping = features[feature_index]["offset_mapping"]

            # Update minimum null prediction.
            cls_index = features[feature_index]["input_ids"].index(tokenizer.cls_token_id)
            feature_null_score = start_logits[cls_index] + end_logits[cls_index]
            if min_null_score is None or min_null_score < feature_null_score:
                min_null_score = feature_null_score

            # Go through all possibilities for the `n_best_size` greater start and end logits.
            start_indexes = np.argsort(start_logits)[-1 : -n_best_size - 1 : -1].tolist()
            end_indexes = np.argsort(end_logits)[-1 : -n_best_size - 1 : -1].tolist()
            for start_index in start_indexes:
                for end_index in end_indexes:
                    # Don't consider out-of-scope answers, either because the indices are out of bounds or correspond
                    # to part of the input_ids that are not in the context.
                    if (
                        start_index >= len(offset_mapping)
                        or end_index >= len(offset_mapping)
                        or offset_mapping[start_index] is None
                        or offset_mapping[end_index] is None
                        or offset_mapping[start_index] == []
                        or offset_mapping[end_index] == []
                    ):
                        continue
                    # Don't consider answers with a length that is either < 0 or > max_answer_length.
                    if end_index < start_index or end_index - start_index + 1 > max_answer_length:
                        continue

                    start_char = offset_mapping[start_index][0]
                    end_char = offset_mapping[end_index][1]
                    valid_answers.append(
                        {
                            "score": start_logits[start_index] + end_logits[end_index],
                            "text": context[start_char:end_char],
                        }
                    )

        if len(valid_answers) > 0:
            best_answer = sorted(valid_answers, key=lambda x: x["score"], reverse=True)[0]
        else:
            # In the very rare edge case we have not a single non-null prediction, we create a fake prediction to avoid
            # failure.
            best_answer = {"text": "", "score": 0.0}

        # Let's pick our final answer: the best one or the null answer (only for squad_v2)
        if not squad_v2:
            predictions[example["id"]] = best_answer["text"]
        else:
            answer = best_answer["text"] if best_answer["score"] > min_null_score else ""
            predictions[example["id"]] = answer

    return predictions


class PadCollate:
    """
    Collate into a batch and pad the batch up to a fixed size.
    """

    def __init__(self, batch_size, padding_val_dict=None):
        self.batch_size = batch_size
        self.padding_val_dict = padding_val_dict

    def pad_tensor(self, x, val):
        pad_size = list(x.shape)
        pad_size[0] = self.batch_size - x.size(0)
        return torch.cat([x, val * torch.ones(*pad_size, dtype=x.dtype)], dim=0)

    def __call__(self, batch):
        size = len(batch)
        batch = default_data_collator(batch)
        if size < self.batch_size:
            for k in batch.keys():
                batch[k] = self.pad_tensor(batch[k], self.padding_val_dict[k])
        return batch