rov-offline/ad_users_data_update.py

import datetime
import pandas as pd
from utils import get_data_from_odps
from config import set_config
from log import Log
config_, _ = set_config()
log_ = Log()


def get_feature_data(project, table, features, now_date):
    """获取特征数据"""
    dt = datetime.datetime.strftime(now_date, '%Y%m%d')
    records = get_data_from_odps(date=dt, project=project, table=table)
    feature_data = []
    for record in records:
        item = {}
        for feature_name in features:
            item[feature_name] = record[feature_name]
        feature_data.append(item)
    feature_df = pd.DataFrame(feature_data)
    return feature_df


def predict_user_group_share_rate(now_date):
    """预估用户组对应的有广告时分享率"""
    # 获取用户组特征
    project = config_.ad_model_data['users_share_rate'].get('project')
    table = config_.ad_model_data['users_share_rate'].get('table')
    features = [
        'apptype',
        'group',
        'sharerate_all',
        'sharerate_ad'
    ]

    user_group_df = get_feature_data(project=project, table=table, features=features, now_date=now_date)
    user_group_df['sharerate_all'] = user_group_df['sharerate_all'].astype(float)
    user_group_df['sharerate_ad'] = user_group_df['sharerate_ad'].astype(float)
    # 获取有广告时所有用户组近30天的分享率
    ad_all_group_share_rate = user_group_df[user_group_df['group'] == 'allmids']['sharerate_ad']
    user_group_df = user_group_df[user_group_df['group'] != 'allmids']
    # 计算用户组有广告时分享率
    user_group_df['group_ad_share_rate'] = \
        user_group_df['sharerate_ad'] * float(ad_all_group_share_rate) / user_group_df['sharerate_all']
    return user_group_df


def predict_video_share_rate(now_date):
    """预估视频有广告时分享率"""
    # 获取视频特征
    project = config_.ad_model_data['videos_share_rate'].get('project')
    table = config_.ad_model_data['videos_share_rate'].get('table')
    features = [
        'apptype',
        'videoid',
        'sharerate_all',
        'sharerate_ad'
    ]

    video_df = get_feature_data(project=project, table=table, features=features, now_date=now_date)
    video_df['sharerate_all'] = video_df['sharerate_all'].astype(float)
    video_df['sharerate_ad'] = video_df['sharerate_ad'].astype(float)
    # 获取有广告时所有视频近30天的分享率
    ad_all_videos_share_rate = video_df[video_df['videoid'] == 'allvideos']['sharerate_ad']
    video_df = video_df[video_df['videoid'] != 'allvideos']
    # 计算视频有广告时分享率
    video_df['video_ad_share_rate'] = \
        video_df['sharerate_ad'] * float(ad_all_videos_share_rate) / video_df['sharerate_all']
    return video_df