title_with_video/applications/match_algorithm/rank.py

"""
@author: luojunhui
"""
from datetime import datetime, timedelta

from applications.match_algorithm.title_similarity import jcd_title_similarity


def jac_score(d1, d2):
    """
    通过交并集来判断
    :param d1:
    :param d2:
    :return:
    """
    f1_keys = set(d1["key_words"])
    f2_keys = set(d2["key_words"])
    keys_union = f1_keys | f2_keys
    keys_intersection = f1_keys & f2_keys
    f1_search_keys = set(d1["search_keys"])
    f2_search_keys = set(d2["search_keys"])
    search_keys_union = f1_search_keys | f2_search_keys
    search_keys_intersection = f1_search_keys & f2_search_keys
    f1_extra_keys = set(d1["extra_keys"])
    f2_extra_keys = set(d2["extra_keys"])
    extra_keys_union = f1_extra_keys | f2_extra_keys
    extra_keys_intersection = f1_extra_keys & f2_extra_keys
    score_1 = len(keys_intersection) / len(keys_union)
    score_2 = len(search_keys_intersection) / len(search_keys_union)
    score_3 = len(extra_keys_intersection) / len(extra_keys_union)
    return score_1 * 0.4 + score_2 * 0.4 + score_3 * 0.2, d2['video_id']


def title_similarity_rank(content_title, recall_list):
    """

    :param content_title:
    :param recall_list:
    :return:
    """
    include_title_list = []
    for item in recall_list:
        video_info = item['result']
        platform = item['platform']
        if platform in ['dy_search', 'baidu_search']:
            title = video_info['title']
        elif platform in ['xg_search']:
            title = video_info['video_title']
        else:
            continue
        item['title'] = title
        item['score'] = jcd_title_similarity(content_title, title)
        include_title_list.append(item)
    sorted_list = sorted(include_title_list, key=lambda x: x['score'], reverse=True)
    return sorted_list


def rank_by_fission_info(db_client, config, content_id):
    """
    通过 content_id 对应的 oss 路径对应的裂变表现进行排序
    oss 数据每天凌晨 2 点更新
    :return:
    """
    FISSION_DETAIL_TABLE = config.fission_detail_table
    yesterday_str = (datetime.now() - timedelta(days=1)).strftime('%Y%m%d')
    sql = f"""
        SELECT 
            oss_name, fission_0_on_read
        FROM
            {FISSION_DETAIL_TABLE}
        WHERE content_id = '{content_id}' and dt = '{yesterday_str}'
        ORDER BY fission_0_on_read DESC;
    """
    result = db_client.select(sql)
    if result:
        oss_name_list = [i[0] for i in result]
        return oss_name_list
    else:
        return