gen_feat.py 文件源码

def get_accumulate_brand_feat(start_date, end_date):
    feature = ['brand', 'brand_action_1_ratio', 'brand_action_2_ratio', 'brand_action_3_ratio',
               'brand_action_5_ratio', 'brand_action_6_ratio', 'brand_action_num']
    dump_path = './cache/brand_feat_accumulate_%s_%s.csv' %(start_date,end_date)
    if os._exists(dump_path):
        actions = pd.read_csv(dump_path)
    else:
        actions = get_actions(start_date,end_date)
        df = pd.get_dummies(actions['type'],prefix='action')
        actions = pd.concat([actions['brand'],df],axis=1)
        actions = actions.groupby(['brand'],as_index = False).sum()
        actions['brand_action_1_ratio'] = actions['action_4']/actions['action_1']
        actions['brand_action_2_ratio'] = actions['action_4']/actions['action_2']
        actions['brand_action_3_ratio'] = actions['action_4']/actions['action_3']

        actions['brand_action_5_ratio'] = actions['action_4']/actions['action_5']
        actions['brand_action_6_ratio'] = actions['action_4']/actions['action_6']
        actions['brand_action_num'] = actions['action_1'] + actions['action_2'] + actions['action_3'] + actions[
            'action_4'] + actions['action_5'] + actions['action_6']
        actions = actions[feature]
        actions.replace(np.inf, 9999)
        actions.to_csv(dump_path)
    return  actions
    pass