n2 = len(df[df["上报时间"].dt.date == day]) # 当天案件总数
# 自行处理的案件总数
n3 = len(df_self)
# 分类统计
s = df.groupby("小类名称").count()["上报时间"]
s["案件总数"] = n1
s["当天案件总数"] = n2
s["自行处理案件总数"] = n3
s["日期"] = day
s["街道"] = area
s["原指标"] = gt
res[j] = s
j += 1
res.fillna(0, inplace=True)
return res.T
if __name__ == "__main__":
# source_file = '../queryResult_2019-09-10_145030_zs341.xlsx'
source_file = '../queryResult_2019-09-10_145030.npy'
gt_file = "../source_data/ZS321 - 环境问题指数.xlsx"
df2 = convert_to_new_dataframe(source_file,
gt_file,
write_path='../tmp_zs321')
df2.to_excel('../zs321_20190923.xlsx')
# regression
regression_test('../zs321_20190923.xlsx', 'zs321')
# TODO: 增加当天内完成案件的权重(比如自行处理案件因当天完成, 相比第二天完成的案件, 少了一晚上的执行分数)
w1 = 60 # 自行处理案件总数, 认为w1分钟为完成一个自行处理案件所需的平均时间
w2 = 0 # 其他案件总数, 不考评
w3 = 0 # 强制结案总数, 暂不考评(没有好的思路, 且强制结案会同时生成一个新的案件)
w4 = 0 # 立案耗时总长(分钟), 不考评
w5 = 1 # 计划内耗时总长(分钟)
w6 = -1 # 计划外耗时总长(分钟)
df['新评分'] = (df["自行处理案件总数"] * w1 + df["其他案件总数"] * w2 + df["强制结案总数"] * w3 +
df["立案耗时总长(分钟)"] * w4 + df["计划内耗时总长(分钟)"] * w5 +
df["计划外耗时总长(分钟)"] * w6) / 1000
return df
if __name__ == "__main__":
# source_file = '../queryResult_2019-09-10_145030.xlsx'
source_file = '../queryResult_2019-09-10_145030.npy'
gt_file = "../source_data/ZS222 - 处置效能指数.xlsx"
df2 = convert_to_new_dataframe(source_file,
gt_file,
write_path='../tmp_zs222')
df2.to_excel('../zs222_20190923.xlsx')
df3_file_path = '../zs222_20190923.xlsx'
df3 = cal_index(df3_file_path)
df3 = df3.drop('Unnamed: 0', 1)
df3.to_excel(df3_file_path)
# regression
regression_test('../zs222_20190923.xlsx')
s["按时完成"] = n1a
s["延期完成"] = n1b
s["当天案件总数"] = n2
s["自行处理案件总数"] = n3
s["日期"] = day
s["街道"] = area
s["原指标"] = gt
lst.append(s)
res = pd.concat(lst, axis=1, sort=False)
res.fillna(0, inplace=True)
res = res.T
# https://stackoverflow.com/questions/14507794/pandas-how-to-flatten-a-hierarchical-index-in-columns @Andy Hayden
res.columns = [' '.join(col).strip() for col in res.columns.values]
res.reset_index(inplace=True, drop=True)
return res
if __name__ == "__main__":
# source_file = '../queryResult_2019-09-10_145030_zs341.xlsx'
source_file = '../queryResult_2019-09-10_145030.npy'
gt_file = "../source_data/ZS341 - 服务需求指数.xlsx"
df2 = convert_to_new_dataframe(source_file,
gt_file,
write_path='../tmp_zs341')
df2.to_excel('../zs341_20190923.xlsx')
# regression
regression_test('../zs341_20190923.xlsx')