【推荐】2019 Java 开发者跳槽指南.pdf(吐血整理) >>>
import pandas as pd
# 加载11月份数据
xs = pd.read_excel(r"C:\Users\滕玉龙\Desktop\采购单品汇总_华南.xlsx",sheet_name = "销售",header = 6)
xs
# 筛选出大分类名称为“水果”部门的全部记录
sg = xs[xs["大分类名称"] == "水果"]
sg
# 按商品名称对学生金额与销售数量作聚合求和运算
qh = sg.groupby(["商品名称"])["销售金额","销售数量"].sum()
qh
# 对销售金额字段按降序排列
pm = qh.sort_values(by = "销售金额",ascending = False)
pm
# 获取销售金额排名在前20的单品记录
q20 = pm.head(20)
q20
# 在桌面新建一个工作簿名为“水果”,工作单表名为“水果销售金额前20的单品”的excel电子表格,用来保存排序所得到的结果
q20.to_excel(excel_writer = r"C:\Users\滕玉龙\Desktop\水果.xlsx",sheet_name = "水果销售金额前20的单品")
# 加载10月份销售数据
import pandas as pd
October = pd.read_excel(r"C:\Users\滕玉龙\Desktop\采购单品汇总_华南 (10月份).xlsx",sheet_name = "销售",header = 6)
October
# 数据透视表
st = pd.pivot_table(October,index = "商品名称",values = ["销售金额","销售数量"],aggfunc = "sum")
st
# 将两表按“商品编号”作为公共字段来拼接结果
pj = pd.merge(q20,st,on = "商品名称")
pj
# 将拼接之后的结果输出冰保存
pj.to_excel(excel_writer = r"C:\Users\滕玉龙\Desktop\水果前20.xlsx",sheet_name = "水果销售金额前20的单品")
求同比环比就更简单了!我就懒得写了!
来源:oschina
链接:https://my.oschina.net/u/3750423/blog/3141901