def prepare_qa_validation_features()

in src/autotrain/trainers/extractive_question_answering/utils.py [0:0]

• 25 lines of code
• 16 McCabe index (conditional complexity)

def prepare_qa_validation_features(examples, tokenizer, config):
    # Some of the questions have lots of whitespace on the left, which is not useful and will make the
    # truncation of the context fail (the tokenized question will take a lots of space). So we remove that
    # left whitespace
    pad_on_right = tokenizer.padding_side == "right"
    examples[config.question_column] = [q.lstrip() for q in examples[config.question_column]]

    # 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.
    tokenized_examples = tokenizer(
        examples[config.question_column if pad_on_right else config.text_column],
        examples[config.text_column if pad_on_right else config.question_column],
        truncation="only_second" if pad_on_right else "only_first",
        max_length=config.max_seq_length,
        stride=config.max_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")

    # For evaluation, we will need to convert our predictions to substrings of the context, so we keep the
    # corresponding example_id 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