def from_dict()

in table_bert/dataset.py [0:0]
56 lines of code
22 McCabe index (conditional complexity)

    def from_dict(cls, entry: Dict, tokenizer: Optional[BertTokenizer], suffix) -> 'Example':
        def _get_data_source():
            return 'wiki' if 'wiki' in entry['uuid'] else 'common_crawl'

        source = _get_data_source()

        header_entry = entry['header'] if source == 'wiki' else entry['table']['header']
        header = []
        column_data = []
        for col in header_entry:
            sample_value = col['sample_value']['value']
            if tokenizer:
                name_tokens = tokenizer.tokenize(col['name'])
            else: name_tokens = None
            column = Column(col['name'],
                            col['type'],
                            sample_value,
                            name_tokens=name_tokens)
            header.append(column)

        if source == 'wiki':
            for row in entry['data'][1:]:
                for col_id, (tag, cell_val) in enumerate(row):
                    if col_id >= len(column_data):
                        column_data.append([])

                    column_data[col_id].append(cell_val)
        else:
            for row in entry['table']['data']:
                for col_id, (cell_val) in enumerate(row):
                    if col_id >= len(column_data):
                        column_data.append([])

                    column_data[col_id].append(cell_val)

        context_before = []
        context_after = []

        if source == 'wiki':
            for para in entry['context_before']:
                for sent in para:
                    if tokenizer:
                        sent = tokenizer.tokenize(sent)

                    context_before.append(sent)

            caption = entry['caption']
            if caption:
                if tokenizer:
                    caption = tokenizer.tokenize(entry['caption'])

                context_before.append(caption)
        else:
            for sent in entry['context_before']:
                if tokenizer:
                    sent = tokenizer.tokenize(sent)
                context_before.append(sent)

            for sent in entry['context_after']:
                if tokenizer:
                    sent = tokenizer.tokenize(sent)
                context_after.append(sent)

        uuid = entry['uuid']

        return cls(uuid, header,
                   [context_before, context_after],
                   column_data=column_data,
                   source=source)