rov-offline/ad_feature_process.py

import pandas as pd
from utils import get_data_from_odps

features = [
    'apptype',
    'videoid',
    'mid',
    'ad_mid',
    'mid_preview_count',
    'mid_view_count',
    'mid_view_count_pv',
    'mid_play_count',
    'mid_play_count_pv',
    'mid_share_count',
    'mid_share_count_pv',
    'mid_return_count',
    'mid_share_rate',
    'mid_return_rate',
    'video_preview_count_uv',
    'video_preview_count_pv',
    'video_view_count_uv',
    'video_view_count_pv',
    'video_play_count_uv',
    'video_play_count_pv',
    'video_share_count_uv',
    'video_share_count_pv',
    'video_return_count',
    'video_ctr_uv',
    'video_ctr_pv',
    'video_share_rate_uv',
    'video_share_rate_pv',
    'video_return_rate'
    'share_videoid'
]


def get_feature_data(project, table, features, dt):
    """获取特征数据"""
    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 daily_data_process(project, table, features, dt):
    feature_df = get_feature_data(project=project, table=table, features=features, dt=dt)
    feature_df['']
    pass