lexeme.py 文件源码

def misses_to_frame(parsed_lexemes: Iterable,
                    terms: Dict[str, str]=None) -> pd.DataFrame:
    if not terms:
        terms = {}
    miss_dict = collect_misses(parsed_lexemes)
    misses = []
    for miss in miss_dict:
        low_miss = miss.lower()
        miss_record = OrderedDict()
        miss_record['miss'] = low_miss
        miss_record['term'] = terms.get(low_miss, low_miss)
        miss_record['lexemes'] = ' '.join(miss_dict[miss])
        misses.append(miss_record)
    miss_frame = pd.DataFrame.from_records(
        misses, index='miss', columns=['miss', 'term', 'lexemes'])
    return miss_frame