utils_hans.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.

import copy
import csv
import json
import sys


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, pairID=None):
        self.guid = guid
        self.text_a = text_a
        self.text_b = text_b
        self.label = label
        self.pairID = pairID

    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, pairID=None):
        self.input_ids = input_ids
        self.attention_mask = attention_mask
        self.token_type_ids = token_type_ids
        self.label = label
        self.pairID = pairID

    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()

    @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