import pandas as pd from datetime import datetime from utils import get_data_from_odps from config import set_config from log import Log config_, env = 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(now_date, now_h, project, table): """获取特征数据""" dt = datetime.strftime(now_date, '%Y%m%d%H') log_.info({'feature_dt': dt}) 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 main(): now_date = datetime.today() log_.info(f"now_date: {datetime.strftime(now_date, '%Y%m%d%H')}") project_24h = config_.PROJECT_24H_APP_TYPE table_24h = config_.TABLE_24H_APP_TYPE now_min = datetime.now().minute now_h = datetime.now().hour