Class ImdbProcessor

src/process_data.py:150–177

`IMDB `_ is a Movie Review Sentiment Classification dataset. we use dataset provided by `LOTClass `_

    

class ImdbProcessor(DataProcessor):
    """
    `IMDB <https://ai.stanford.edu/~ang/papers/acl11-WordVectorsSentimentAnalysis.pdf>`_ is a Movie Review Sentiment Classification dataset.

    we use dataset provided by `LOTClass <https://github.com/yumeng5/LOTClass>`_
    """

    def __init__(self):
        super().__init__()
        self.labels = ["negative", "positive"]

    def get_examples(self, data_dir, split):
        examples = []
        label_file = open(os.path.join(data_dir, "{}_labels.txt".format(split)), 'r') 
        labels = [int(x.strip()) for x in label_file.readlines()]
        with open(os.path.join(data_dir, '{}.txt'.format(split)),'r') as fin:
            for idx, line in enumerate(fin):
                text_a = line.strip()
                example = InputExample(guid=str(idx), text_a=text_a, label=int(labels[idx]))
                examples.append(example)
        return examples


    @staticmethod
    def get_test_labels_only(data_dir, dirname):
        label_file  = open(os.path.join(data_dir,dirname,"{}_labels.txt".format('test')),'r') 
        labels  = [int(x.strip()) for x in label_file.readlines()]
        return labels

class YahooProcessor(DataProcessor):
    """