glue_utils.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.
""" GLUE processors and helpers """

import logging
import os
import csv
import sys
import copy
import json

import pandas as pd

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, token_type_ids, label):
        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."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """Gets an example from a dict with tensorflow tensors
        Args:
            tensor_dict: Keys and values should match the corresponding Glue
                tensorflow_dataset examples.
        """
        raise NotImplementedError()

    def get_train_examples(self, data_dir):
        """Gets a collection of `InputExample`s for the train set."""
        raise NotImplementedError()

    def get_dev_examples(self, data_dir):
        """Gets a collection of `InputExample`s for the dev set."""
        raise NotImplementedError()

    def get_labels(self):
        """Gets the list of labels for this data set."""
        raise NotImplementedError()

    def tfds_map(self, example):
        """Some tensorflow_datasets datasets are not formatted the same way the GLUE datasets are. 
        This method converts examples to the correct format."""
        if len(self.get_labels()) > 1:
            example.label = self.get_labels()[int(example.label)]
        return example

    @classmethod
    def _read_tsv(cls, input_file, quotechar=None):
        """Reads a tab separated value file."""
        lines = []
        df = pd.read_csv(input_file, delimiter='\t')
        for item in df.iterrows():
            temp = []
            temp.append(item[1][0])
            temp.append(item[1][1])
            lines.append(temp)
        return lines


def glue_convert_examples_to_features(examples, tokenizer,
                                      max_length=256,
                                      task=None,
                                      label_list=None,
                                      output_mode=None,
                                      pad_on_left=False,
                                      pad_token=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: Padding token
        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.
    """
    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):

        inputs = tokenizer.encode_plus(
            example.text_a,
            example.text_b,
            add_special_tokens=True,
            max_length=max_length,
        )
        input_ids, token_type_ids = inputs["input_ids"], inputs["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] * padding_length) + input_ids
            attention_mask = ([0 if mask_padding_with_zero else 1] * padding_length) + attention_mask
            token_type_ids = ([pad_token_segment_id] * padding_length) + token_type_ids
        else:
            input_ids = input_ids + ([pad_token] * padding_length)
            attention_mask = attention_mask + ([0 if mask_padding_with_zero else 1] * padding_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)

        label = label_map[str(example.label)]
        
        features.append(
                InputFeatures(input_ids=input_ids,
                              attention_mask=attention_mask,
                              token_type_ids=token_type_ids,
                              label=label))
    return features


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 Sst5Processor(DataProcessor):
    """Processor for the SST-5 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 ["1", "2", "3", "4", "5"]

    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

glue_tasks_num_labels = {
    "sst-2": 2,
    "sst-5": 5,
}

glue_processors = {
    "sst-2": Sst2Processor,
    "sst-5": Sst5Processor,
}

glue_output_modes = {
    "sst-2": "classification",
    "sst-5": "classification",
}


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


def glue_compute_metrics(task_name, preds, labels):
    assert len(preds) == len(labels)
    if task_name == "sst-2":
        return {"acc": simple_accuracy(preds, labels)}
    elif task_name == "sst-5":
        return {"acc": simple_accuracy(preds, labels)}
    else:
        raise KeyError(task_name)