rov-offline/whole_movies_update.py

import time
import datetime
import pandas as pd
import math
import random
from odps import ODPS
from threading import Timer
from get_data import get_data_from_odps
from db_helper import RedisHelper, MysqlHelper
from config import set_config
from log import Log
from utils import filter_video_status_with_applet_rec

config_, env = set_config()
log_ = Log()

features = [
    '视频id',
    '抓取时间',
    '进入黑名单时间',
    '站外播放量'
]


def h_data_check(project, table, now_date):
    """检查数据是否准备好"""
    odps = ODPS(
        access_id=config_.ODPS_CONFIG['ACCESSID'],
        secret_access_key=config_.ODPS_CONFIG['ACCESSKEY'],
        project=project,
        endpoint=config_.ODPS_CONFIG['ENDPOINT'],
        connect_timeout=3000,
        read_timeout=500000,
        pool_maxsize=1000,
        pool_connections=1000
    )

    try:
        dt = datetime.datetime.strftime(now_date, '%Y%m%d')
        sql = f'select * from {project}.{table} where dt = {dt}'
        with odps.execute_sql(sql=sql).open_reader() as reader:
            data_count = reader.count
    except Exception as e:
        data_count = 0
    return data_count


def get_feature_data(now_date, project, table):
    """获取特征数据"""
    dt = datetime.datetime.strftime(now_date, '%Y%m%d')
    # dt = '2022041310'
    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 video_rank(app_type, df, now_date):
    """
    对视频进行排序
    :param app_type:
    :param df:
    :param now_date:
    :return:
    """
    df = df.fillna(0)
    # 视频状态过滤
    log_.info(f'initial_df count = {len(df)}')
    video_ids = [int(video_id) for video_id in df['videoid']]
    df['videoid'] = df['videoid'].astype(int)
    df = df.drop_duplicates(['videoid'], keep=False)
    log_.info(f'df length = {len(df)}')

    # 获取待推荐
    filtered_result_6 = filter_video_status_with_applet_rec(video_ids=video_ids, applet_rec_status=-6)
    filtered_df_6 = df[df['videoid'].isin(filtered_result_6)]
    filtered_df_6 = filtered_df_6.sort_values(by=['站外播放量'], ascending=False)
    log_.info(f'filtered_df_6 count = {len(filtered_df_6)}')

    # 获取普通推荐
    filtered_result_1 = filter_video_status_with_applet_rec(video_ids=video_ids, applet_rec_status=1)
    filtered_df_1 = df[df['videoid'].isin(filtered_result_1)]
    filtered_df_1 = filtered_df_1.sort_values(by=['站外播放量'], ascending=False)
    log_.info(f'filtered_df_1 count = {len(filtered_df_1)}')

    # 排序合并,给定分数
    merge_df = filtered_df_1.append(filtered_df_6)
    merge_df = merge_df.drop_duplicates(['videoid'], keep=False)
    merge_videos = merge_df['videoid'].to_list()
    final_result = {}
    step = round(100 / len(merge_videos), 3)
    for i, video_id in enumerate(merge_videos):
        score = 100 - i * step
        final_result[int(video_id)] = score
    # 写入对应的redis
    # key_name = \
    #     f"{}{app_type}.{datetime.datetime.strftime(now_date, '%Y%m%d')}"
    # if len(final_result) > 0:
    #     redis_helper = RedisHelper()
    #     redis_helper.add_data_with_zset(key_name=key_name, data=final_result, expire_time=23 * 3600)


def rank_by_h(app_type, now_date, now_h, return_count_list, project, table):
    # 获取特征数据
    feature_df = get_feature_data(now_date=now_date, project=project, table=table)
    # rank
    for cnt in return_count_list:
        log_.info(f"return_count = {cnt}")
        video_rank(app_type=app_type, df=feature_df, now_date=now_date)
    # to-csv
    # score_filename = f"score_{app_type}_{datetime.datetime.strftime(now_date, '%Y%m%d%H')}.csv"
    # score_df.to_csv(f'./data/{score_filename}')