LongArticlesJob/dev/task_analysis.py

"""
@author: luojunhui
"""
import json
import pandas as pd

with open("AccountInfo.json", encoding="utf-8") as f:
    account_base_info = json.loads(f.read())

new_d = {}
for key in account_base_info:
    value = account_base_info[key]
    name = value['accountName']
    position = value['position']
    read_avg = value['readAvg']
    new_key = "{}_{}".format(name, position)
    new_d[new_key] = read_avg


df = pd.read_excel("非实验数据.xlsx")
L = []
a = 0
b = 0
for line in df.values.tolist():
    dt = line[0]
    account_name = line[1]
    title = line[2]
    link = line[3]
    pos = line[4]
    read = line[5]
    avg_read = new_d.get("{}_{}".format(account_name, pos), 0)
    if avg_read:
        avg_times = read / avg_read
        if avg_times > 1.3:
            is_up = 1
            a += 1
        else:
            is_up = 0
            b += 1
        strategy = line[-7]
        # if "军事" in strategy or "历史" in strategy:
        #     ac_t = "实验"
        # else:
        ac_t = "对照"
        L.append([dt, account_name, title, link, pos, read, avg_read, avg_times, is_up, ac_t, strategy])
        print([dt, account_name, title, link, pos, read, avg_read, avg_times, is_up, ac_t, strategy])

print(b)
print(a)
print(a + b)
print(a / (a + b))
# out_df = pd.DataFrame(
#     L,
#     columns=['日期', '账号名称', '标题', '链接', '文章位置', '阅读量', '阅读均值', '阅读均值倍数', '是否晋升', '实验/对照', '冷启品类']
# )
#
# out_df.to_excel("result.xlsx", index=False)