ibis 按周统计

 import ibis

import pandas as pd

from ibis import _

import ibis.selectors as s

ibis.options.interactive = True

def load_excel_to_ibis(excel_path):

    try:

        # 读取Excel文件

        df = pd.read_excel(excel_path)

       

        # 将所有object类型的列转换为字符串

        for col in df.select_dtypes(include=['object']).columns:

            df[col] = df[col].astype(str)

       

        # 转换为Ibis表格

        ibis_table = ibis.memtable(df)

        return ibis_table

   

    except Exception as e:

        print(f"错误: {str(e)}")

        return None

dq= load_excel_to_ibis("/mnt/c/users/xuefe/Downloads/百日咳分日发病.xlsx")

tj=(

    dq

    .mutate(时间=_.时间.cast('date'))

    .mutate(zhou=_.时间.week_of_year())

    .group_by(_.zhou)

    .aggregate(fabingshu=_.发病数.sum())

    .execute()

)

tj.to_excel('/mnt/c/users/xuefe/Downloads/zhoutj.xlsx',index=False)

# con=ibis.connect("duckdb://")

con=ibis.duckdb.connect(':memory:')

tmp = pd.read_csv('/mnt/c/users/xuefe/Downloads/报告卡2025-03-11+15_55_57.csv', encoding='gb18030')

brk = ibis.memtable(tmp)

print(ibis.__version__)

tmp2=(

    brk

    .mutate(年龄1=_.年龄.contains('岁'))

    .filter(_.年龄1==False)

    .execute()

)

tmp2=(

    brk

    .filter(_.年龄.contains('岁'))

    .execute()

)

tmp2 = (

    brk

    .filter(_.性别=='女')

    .execute()

)