utils_for_glue.py

# Copyright (c) Microsoft Corporation. 
# Licensed under the MIT license.
## The script is largely adapted from the huggingface transformers library.
""" GLUE processors and helpers """

import logging
import os
import csv
import sys
import copy
import json
from scipy.stats import pearsonr, spearmanr
from sklearn.metrics import matthews_corrcoef, f1_score

logger = logging.getLogger(__name__)


class InputExample(object):
    """
    A single training/test example for simple sequence classification.

    Args:
        guid: Unique id for the example.
        text_a: string. The untokenized text of the first sequence. For single
        sequence tasks, only this sequence must be specified.
        text_b: (Optional) string. The untokenized text of the second sequence.
        Only must be specified for sequence pair tasks.
        label: (Optional) string. The label of the example. This should be
        specified for train and dev examples, but not for test examples.
    """
    def __init__(self, guid, text_a, text_b=None, label=None):
        self.guid = guid
        self.text_a = text_a
        self.text_b = text_b
        self.label = label

    def __repr__(self):
        return str(self.to_json_string())

    def to_dict(self):
        """Serializes this instance to a Python dictionary."""
        output = copy.deepcopy(self.__dict__)
        return output

    def to_json_string(self):
        """Serializes this instance to a JSON string."""
        return json.dumps(self.to_dict(), indent=2, sort_keys=True) + "\n"


class InputFeatures(object):
    """
    A single set of features of data.

    Args:
        input_ids: Indices of input sequence tokens in the vocabulary.
        attention_mask: Mask to avoid performing attention on padding token indices.
            Mask values selected in ``[0, 1]``:
            Usually  ``1`` for tokens that are NOT MASKED, ``0`` for MASKED (padded) tokens.
        token_type_ids: Segment token indices to indicate first and second portions of the inputs.
        label: Label corresponding to the input
    """

    def __init__(self, input_ids, attention_mask=None, token_type_ids=None, label=None):
        self.input_ids = input_ids
        self.attention_mask = attention_mask
        self.token_type_ids = token_type_ids
        self.label = label

    def __repr__(self):
        return str(self.to_json_string())

    def to_dict(self):
        """Serializes this instance to a Python dictionary."""
        output = copy.deepcopy(self.__dict__)
        return output

    def to_json_string(self):
        """Serializes this instance to a JSON string."""
        return json.dumps(self.to_dict(), indent=2, sort_keys=True) + "\n"


class DataProcessor(object):
    """Base class for data converters for sequence classification data sets."""

    @classmethod
    def _read_tsv(cls, input_file, quotechar=None):
        """Reads a tab separated value file."""
        with open(input_file, "r", encoding="utf-8-sig") as f:
            reader = csv.reader(f, delimiter="\t", quotechar=quotechar)
            lines = []
            for line in reader:
                if sys.version_info[0] == 2:
                    line = list(unicode(cell, 'utf-8') for cell in line)
                lines.append(line)
            return lines

def glue_convert_examples_to_features(examples, tokenizer,
                                      max_length=512,
                                      task=None,
                                      label_list=None,
                                      output_mode=None,
                                      pad_on_left=False,
                                      pad_token_id=0,
                                      pad_token_segment_id=0,
                                      mask_padding_with_zero=True):
    """
    Loads a data file into a list of ``InputFeatures``

    Args:
        examples: List of ``InputExamples`` or ``tf.data.Dataset`` containing the examples.
        tokenizer: Instance of a tokenizer that will tokenize the examples
        max_length: Maximum example length
        task: GLUE task
        label_list: List of labels. Can be obtained from the processor using the ``processor.get_labels()`` method
        output_mode: String indicating the output mode. Either ``regression`` or ``classification``
        pad_on_left: If set to ``True``, the examples will be padded on the left rather than on the right (default)
        pad_token_id: Padding token id
        pad_token_segment_id: The segment ID for the padding token (It is usually 0, but can vary such as for XLNet where it is 4)
        mask_padding_with_zero: If set to ``True``, the attention mask will be filled by ``1`` for actual values
            and by ``0`` for padded values. If set to ``False``, inverts it (``1`` for padded values, ``0`` for
            actual values)

    Returns:
        If the ``examples`` input is a ``tf.data.Dataset``, will return a ``tf.data.Dataset``
        containing the task-specific features. If the input is a list of ``InputExamples``, will return
        a list of task-specific ``InputFeatures`` which can be fed to the model.

    """
    is_tf_dataset = False

    if task is not None:
        processor = glue_processors[task]()
        if label_list is None:
            label_list = processor.get_labels()
            logger.info("Using label list %s for task %s" % (label_list, task))
        if output_mode is None:
            output_mode = glue_output_modes[task]
            logger.info("Using output mode %s for task %s" % (output_mode, task))

    label_map = {label: i for i, label in enumerate(label_list)}

    features = []
    for (ex_index, example) in enumerate(examples):
        if ex_index % 10000 == 0:
            logger.info("Writing example %d" % (ex_index))
        if is_tf_dataset:
            example = processor.get_example_from_tensor_dict(example)
            example = processor.tfds_map(example)

        inputs = tokenizer.encode_plus(
            example.text_a,
            example.text_b,
            add_special_tokens=True,
            max_length=max_length,
        )
        input_ids = inputs["input_ids"]
        if "token_type_ids" in inputs:
            token_type_ids = inputs["token_type_ids"]
        else:
            token_type_ids = []

        # The mask has 1 for real tokens and 0 for padding tokens. Only real
        # tokens are attended to.
        attention_mask = [1 if mask_padding_with_zero else 0] * len(input_ids)

        # Zero-pad up to the sequence length.
        padding_length = max_length - len(input_ids)
        if pad_on_left:
            input_ids = ([pad_token_id] * padding_length) + input_ids
            attention_mask = ([0 if mask_padding_with_zero else 1] * padding_length) + attention_mask
            if len(token_type_ids) == 0:
                padding_length = max_length
            token_type_ids = ([pad_token_segment_id] * padding_length) + token_type_ids
        else:
            input_ids = input_ids + ([pad_token_id] * padding_length)
            attention_mask = attention_mask + ([0 if mask_padding_with_zero else 1] * padding_length)
            if len(token_type_ids) == 0:
                padding_length = max_length
            token_type_ids = token_type_ids + ([pad_token_segment_id] * padding_length)

        assert len(input_ids) == max_length, "Error with input length {} vs {}".format(len(input_ids), max_length)
        assert len(attention_mask) == max_length, "Error with input length {} vs {}".format(len(attention_mask), max_length)
        assert len(token_type_ids) == max_length, "Error with input length {} vs {}".format(len(token_type_ids), max_length)

        if output_mode == "classification":
            label = label_map[example.label]
        elif output_mode == "regression":
            label = float(example.label)
        else:
            raise KeyError(output_mode)

        if ex_index < 5:
            logger.info("*** Example ***")
            logger.info("guid: %s" % (example.guid))
            logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids]))
            # logger.info("input_tokens: %s" % " ".join(tokenizer.convert_ids_to_tokens(input_ids)))
            logger.info("attention_mask: %s" % " ".join([str(x) for x in attention_mask]))
            logger.info("token_type_ids: %s" % " ".join([str(x) for x in token_type_ids]))
            logger.info("label: %s (id = %d)" % (example.label, label))

        features.append(
                InputFeatures(input_ids=input_ids,
                              attention_mask=attention_mask,
                              token_type_ids=token_type_ids,
                              label=label))

    return features


class MrpcProcessor(DataProcessor):
    """Processor for the MRPC data set (GLUE version)."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """See base class."""
        return InputExample(tensor_dict['idx'].numpy(),
                            tensor_dict['sentence1'].numpy().decode('utf-8'),
                            tensor_dict['sentence2'].numpy().decode('utf-8'),
                            str(tensor_dict['label'].numpy()))

    def get_train_examples(self, data_dir):
        """See base class."""
        logger.info("LOOKING AT {}".format(os.path.join(data_dir, "train.tsv")))
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")

    def get_labels(self):
        """See base class."""
        return ["0", "1"]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            if i == 0:
                continue
            guid = "%s-%s" % (set_type, i)
            text_a = line[3]
            text_b = line[4]
            label = line[0]
            examples.append(
                InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
        return examples


class MnliProcessor(DataProcessor):
    """Processor for the MultiNLI data set (GLUE version)."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """See base class."""
        return InputExample(tensor_dict['idx'].numpy(),
                            tensor_dict['premise'].numpy().decode('utf-8'),
                            tensor_dict['hypothesis'].numpy().decode('utf-8'),
                            str(tensor_dict['label'].numpy()))

    def get_train_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev_matched.tsv")),
            "dev_matched")

    def get_labels(self):
        """See base class."""
        return ["contradiction", "entailment", "neutral"]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            if i == 0:
                continue
            guid = "%s-%s" % (set_type, line[0])
            text_a = line[8]
            text_b = line[9]
            label = line[-1]
            examples.append(
                InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
        return examples


class MnliMismatchedProcessor(MnliProcessor):
    """Processor for the MultiNLI Mismatched data set (GLUE version)."""

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev_mismatched.tsv")),
            "dev_matched")


class ColaProcessor(DataProcessor):
    """Processor for the CoLA data set (GLUE version)."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """See base class."""
        return InputExample(tensor_dict['idx'].numpy(),
                            tensor_dict['sentence'].numpy().decode('utf-8'),
                            None,
                            str(tensor_dict['label'].numpy()))

    def get_train_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")

    def get_labels(self):
        """See base class."""
        return ["0", "1"]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            guid = "%s-%s" % (set_type, i)
            text_a = line[3]
            label = line[1]
            examples.append(
                InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
        return examples


class Sst2Processor(DataProcessor):
    """Processor for the SST-2 data set (GLUE version)."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """See base class."""
        return InputExample(tensor_dict['idx'].numpy(),
                            tensor_dict['sentence'].numpy().decode('utf-8'),
                            None,
                            str(tensor_dict['label'].numpy()))

    def get_train_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")

    def get_labels(self):
        """See base class."""
        return ["0", "1"]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            if i == 0:
                continue
            guid = "%s-%s" % (set_type, i)
            text_a = line[0]
            label = line[1]
            examples.append(
                InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
        return examples


class StsbProcessor(DataProcessor):
    """Processor for the STS-B data set (GLUE version)."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """See base class."""
        return InputExample(tensor_dict['idx'].numpy(),
                            tensor_dict['sentence1'].numpy().decode('utf-8'),
                            tensor_dict['sentence2'].numpy().decode('utf-8'),
                            str(tensor_dict['label'].numpy()))

    def get_train_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")

    def get_labels(self):
        """See base class."""
        return [None]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            if i == 0:
                continue
            guid = "%s-%s" % (set_type, line[0])
            text_a = line[7]
            text_b = line[8]
            label = line[-1]
            examples.append(
                InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
        return examples


class QqpProcessor(DataProcessor):
    """Processor for the QQP data set (GLUE version)."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """See base class."""
        return InputExample(tensor_dict['idx'].numpy(),
                            tensor_dict['question1'].numpy().decode('utf-8'),
                            tensor_dict['question2'].numpy().decode('utf-8'),
                            str(tensor_dict['label'].numpy()))

    def get_train_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")

    def get_labels(self):
        """See base class."""
        return ["0", "1"]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            if i == 0:
                continue
            guid = "%s-%s" % (set_type, line[0])
            try:
                text_a = line[3]
                text_b = line[4]
                label = line[5]
            except IndexError:
                continue
            examples.append(
                InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
        return examples


class QnliProcessor(DataProcessor):
    """Processor for the QNLI data set (GLUE version)."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """See base class."""
        return InputExample(tensor_dict['idx'].numpy(),
                            tensor_dict['question'].numpy().decode('utf-8'),
                            tensor_dict['sentence'].numpy().decode('utf-8'),
                            str(tensor_dict['label'].numpy()))

    def get_train_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev.tsv")),
            "dev_matched")

    def get_labels(self):
        """See base class."""
        return ["entailment", "not_entailment"]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            if i == 0:
                continue
            guid = "%s-%s" % (set_type, line[0])
            text_a = line[1]
            text_b = line[2]
            label = line[-1]
            examples.append(
                InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
        return examples


class RteProcessor(DataProcessor):
    """Processor for the RTE data set (GLUE version)."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """See base class."""
        return InputExample(tensor_dict['idx'].numpy(),
                            tensor_dict['sentence1'].numpy().decode('utf-8'),
                            tensor_dict['sentence2'].numpy().decode('utf-8'),
                            str(tensor_dict['label'].numpy()))

    def get_train_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")

    def get_labels(self):
        """See base class."""
        return ["entailment", "not_entailment"]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            if i == 0:
                continue
            guid = "%s-%s" % (set_type, line[0])
            text_a = line[1]
            text_b = line[2]
            label = line[-1]
            examples.append(
                InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
        return examples


class WnliProcessor(DataProcessor):
    """Processor for the WNLI data set (GLUE version)."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """See base class."""
        return InputExample(tensor_dict['idx'].numpy(),
                            tensor_dict['sentence1'].numpy().decode('utf-8'),
                            tensor_dict['sentence2'].numpy().decode('utf-8'),
                            str(tensor_dict['label'].numpy()))

    def get_train_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(
            self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")

    def get_labels(self):
        """See base class."""
        return ["0", "1"]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            if i == 0:
                continue
            guid = "%s-%s" % (set_type, line[0])
            text_a = line[1]
            text_b = line[2]
            label = line[-1]
            examples.append(
                InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
        return examples

glue_tasks_num_labels = {
    "cola": 2,
    "mnli": 3,
    "mrpc": 2,
    "sst-2": 2,
    "sts-b": 1,
    "qqp": 2,
    "qnli": 2,
    "rte": 2,
    "wnli": 2,
}

glue_processors = {
    "cola": ColaProcessor,
    "mnli": MnliProcessor,
    "mnli-mm": MnliMismatchedProcessor,
    "mrpc": MrpcProcessor,
    "sst-2": Sst2Processor,
    "sts-b": StsbProcessor,
    "qqp": QqpProcessor,
    "qnli": QnliProcessor,
    "rte": RteProcessor,
    "wnli": WnliProcessor,
}

glue_output_modes = {
    "cola": "classification",
    "mnli": "classification",
    "mnli-mm": "classification",
    "mrpc": "classification",
    "sst-2": "classification",
    "sts-b": "regression",
    "qqp": "classification",
    "qnli": "classification",
    "rte": "classification",
    "wnli": "classification",
}

def simple_accuracy(preds, labels):
    return (preds == labels).mean()


def acc_and_f1(preds, labels):
    acc = simple_accuracy(preds, labels)
    f1 = f1_score(y_true=labels, y_pred=preds)
    return {
        "acc": acc,
        "f1": f1,
        "acc_and_f1": (acc + f1) / 2,
    }


def pearson_and_spearman(preds, labels):
    pearson_corr = pearsonr(preds, labels)[0]
    spearman_corr = spearmanr(preds, labels)[0]
    return {
        "pearson": pearson_corr,
        "spearmanr": spearman_corr,
        "corr": (pearson_corr + spearman_corr) / 2,
    }


def glue_compute_metrics(task_name, preds, labels):
    assert len(preds) == len(labels)
    if task_name == "cola":
        return {"mcc": matthews_corrcoef(labels, preds)}
    elif task_name == "sst-2":
        return {"acc": simple_accuracy(preds, labels)}
    elif task_name == "mrpc":
        return acc_and_f1(preds, labels)
    elif task_name == "sts-b":
        return pearson_and_spearman(preds, labels)
    elif task_name == "qqp":
        return acc_and_f1(preds, labels)
    elif task_name == "mnli":
        return {"acc": simple_accuracy(preds, labels)}
    elif task_name == "mnli-mm":
        return {"acc": simple_accuracy(preds, labels)}
    elif task_name == "qnli":
        return {"acc": simple_accuracy(preds, labels)}
    elif task_name == "rte":
        return {"acc": simple_accuracy(preds, labels)}
    elif task_name == "wnli":
        return {"acc": simple_accuracy(preds, labels)}
    else:
        raise KeyError(task_name)