convert.py 文件源码

def to_dataframe(lines, **kwargs):
    names = lines.readline().decode('utf-8').strip().split('\t')
    types = lines.readline().decode('utf-8').strip().split('\t')

    dtypes, parse_dates, converters = {}, [], {}
    for name, chtype in zip(names, types):
        dtype = CH2PD[chtype]
        if dtype == 'object':
            converters[name] = decode_escapes
        elif dtype.startswith('datetime'):
            parse_dates.append(name)
        else:
            dtypes[name] = dtype

    return pd.read_table(lines, header=None, names=names, dtype=dtypes,
                         parse_dates=parse_dates, converters=converters,
                         na_values=set(), keep_default_na=False, **kwargs)