rov-offline/alg_growth_common.py

#! /usr/bin/env python
# -*- coding: utf-8 -*-
# vim:fenc=utf-8
#
# Copyright © 2024 StrayWarrior <i@straywarrior.com>

"""
Common functions for growth jobs
"""

UNSAFE_VIDEO_IDS = [14403867, 13696461, 13671819, 13587868, 13680796, 14050873,
                    26348326, 28623786]

def check_unsafe_video(df, force_replace=True):
    unsafe_video_condition = ','.join([str(x) for x in UNSAFE_VIDEO_IDS])
    unsafe_rows = df.query(f'video_id in ({unsafe_video_condition})')
    if len(unsafe_rows) > 0:
        print(unsafe_rows)
        if not force_replace:
            raise Exception("video unsafe")
        df.loc[unsafe_rows.index, 'video_id'] = 20463342

def filter_unsafe_video(df):
    unsafe_video_condition = ','.join([str(x) for x in UNSAFE_VIDEO_IDS])
    df = df.query(f'video_id not in ({unsafe_video_condition})')
    return df