rov-offline/export_24h_vid.py

import sys
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()

features = [
    'apptype',
    'videoid',
    'preview人数',  # 过去24h预曝光人数
    'view人数',  # 过去24h曝光人数
    'play人数',  # 过去24h播放人数
    'share人数',  # 过去24h分享人数
    '回流人数',  # 过去24h分享，过去24h回流人数
    'preview次数',  # 过去24h预曝光次数
    'view次数',  # 过去24h曝光次数
    'play次数',  # 过去24h播放次数
    'share次数',  # 过去24h分享次数
    'platform_return',
    'platform_preview',
    'platform_preview_total',
    'platform_show',
    'platform_show_total',
    'platform_view',
    'platform_view_total',
]


def get_feature_data(project, table, now_date):
    """获取特征数据"""
    # dt = datetime.datetime.strftime(now_date, '%Y%m%d%H')
    # dt = '2022041310'
    records = get_data_from_odps(date=now_date, 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


if __name__ == "__main__":
    project = config_.PROJECT_24H_APP_TYPE
    table = config_.TABLE_24H_APP_TYPE
    now_date = sys.argv[1]
    print("now date:", now_date)
    data = get_feature_data(project=project, table=table, now_date=now_date)
    data = data.fillna(0)
    data.to_csv(f"./data/24h_video_data_{now_date}.csv", index=False)
    print(f"data shape: {data.shape}")