rov-offline/cal_24h_score.py

# coding utf-8
import sys
import json
import math
import pandas as pd


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 data_group(data_path):
    """将数据按照videoid聚合（求和）"""
    f = open(data_path)
    index = 0
    data_dict = {}
    while True:
        line = f.readline()
        if not line:
            break
        if index == 0:
            index += 1
            continue
        index += 1
        items = line.strip().split(",")
        # print(items)
        if len(items) < len(features):
            continue
        video_id = items[1]
        if video_id not in data_dict:
            data_dict[video_id] = {'videoid': video_id}
            for i, feature in enumerate(features):
                if feature in ['apptype', 'videoid']:
                    continue
                data_dict[video_id][feature] = int(float(items[i]))
        else:
            for i, feature in enumerate(features):
                if feature in ['apptype', 'videoid']:
                    continue
                data_dict[video_id][feature] = data_dict[video_id][feature] + int(float(items[i]))
    f.close()
    data_list = [item for video_id, item in data_dict.items()]
    data_df = pd.DataFrame(data_list)
    return data_df


def cal_score(data_df):
    """计算score"""
    df = data_df.copy()
    # score1 = 回流/(view+10)
    df['24h_score1'] = df['回流人数'] / (df['view人数'] + 10)
    score_df = df[['videoid', '24h_score1']]
    # print(score_df)
    return score_df


if __name__ == "__main__":
    # 1.load data
    now_date = sys.argv[1]
    print(f"now_date: {now_date}")
    data_path = f"./data/24h_video_data_{now_date}.csv"
    data_df = data_group(data_path=data_path)
    print(f"data_df shape: {data_df.shape}")
    hour_score_path = f"./data/24h_score_{now_date}.csv"
    score_df = cal_score(data_df=data_df)
    score_df.to_csv(hour_score_path, index=False)
    print(f"score_df shape: {score_df.shape}")