notice_dag.py 文件源码

def filter_data(csv_file, start_day=28, end_day=90, interest=780, state=None, **kwargs):
    f = pd.read_csv(csv_file)
    f['sub_title'] = f['sub_title'].fillna('')
    candidate = []
    filter = Filter()
    filter.install_rule(lambda v: v['period'] <= datetime.timedelta(days=20) and v['benefit'] > 6, ok_stop=True, weight=5)
    filter.install_rule(lambda v: v['benefit'] >= 8 and v['period'] < datetime.timedelta(days=230))
    filter.install_rule(lambda v: not v['sub_title'].startswith('????'))
    for row in f.iterrows():
        idx, v = row
        money = money2float(v['money'])
        period = period2timedelta(v['period'])
        # remove percent sign(%)
        benefit = float(v['expected_benefit'][:-1])
        item = {
            'title': v['title'],
            'sub_title': v['sub_title'],
            'money': money,
            'period': period,
            'benefit': benefit,
        }
        if filter.check(item):
            candidate.append(item)
    return candidate