rov-offline/ad_user_video_predict.py

import datetime
import pandas as pd
from odps import ODPS
from utils import data_check, get_feature_data, send_msg_to_feishu
from config import set_config
from log import Log
config_, _ = set_config()
log_ = Log()


def predict_user_group_share_rate(dt, app_type):
    """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, dt=dt)
    user_group_df['apptype'] = user_group_df['apptype'].astype(int)
    user_group_df = user_group_df[user_group_df['apptype'] == app_type]
    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'].values[0]
    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(dt, app_type):
    """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, dt=dt)
    video_df['apptype'] = video_df['apptype'].astype(int)
    video_df = video_df[video_df['apptype'] == app_type]
    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'].values[0]
    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


def predict_ad_group_video():
    app_type = config_.APP_TYPE['VLOG']
    now_date = datetime.datetime.today()
    dt = datetime.datetime.strftime(now_date, '%Y%m%d')
    user_group_df = predict_user_group_share_rate(dt=dt, app_type=app_type)
    video_df = predict_video_share_rate(dt=dt, app_type=app_type)
    print(f"user_group_df count = {len(user_group_df)}, \nvideo_df count = {len(video_df)}")
    predict_df = video_df
    for item in user_group_df:
        predict_df[item['group']] = predict_df['videoid'] * item['group_ad_share_rate']
    predict_df.to_csv('./data/ad_user_video_predict.csv')
    return predict_df


if __name__ == '__main__':
    predict_df = predict_ad_group_video()