Python在Excel中创建数据透视表的完整指南

pip install spire.xls.free

from spire.xls import *
from spire.xls.common import *
# 创建一个新的工作簿
workbook = Workbook()
sheet = workbook.Worksheets[0]
sheet.Name = "销售明细"
# 写入表头
headers = ["区域", "产品", "季度", "销售额", "订单数"]
for col, header in enumerate(headers, start=1):
    sheet.Range[1, col].Value = header
# 写入示例数据（区域、产品、季度、销售额、订单数）
sales_data = [
    ["华东", "激光打印机", "Q1", 182000, 42],
    ["华东", "激光打印机", "Q2", 154000, 35],
    ["华东", "扫描仪",     "Q1",  96000, 28],
    ["华东", "投影仪",     "Q1", 128000, 19],
    ["华北", "激光打印机", "Q1", 145000, 33],
    ["华北", "扫描仪",     "Q2",  88000, 24],
    ["华北", "投影仪",     "Q2", 117000, 17],
    ["华南", "激光打印机", "Q2", 166000, 38],
    ["华南", "扫描仪",     "Q1",  79000, 21],
    ["华南", "投影仪",     "Q1", 138000, 20],
    ["西南", "激光打印机", "Q2", 102000, 26],
    ["西南", "扫描仪",     "Q2",  61000, 15],
    ["西南", "投影仪",     "Q1",  86000, 12],
]
for row, data in enumerate(sales_data, start=2):
    for col, value in enumerate(data, start=1):
        if isinstance(value, (int, float)):
            sheet.Range[row, col].NumberValue = value
        else:
            sheet.Range[row, col].Value = value

# 基于 A1:E14 区域创建透视缓存
dataRange = sheet.Range["A1:E14"]
cache = workbook.PivotCaches.Add(dataRange)

# 新建工作表用于存放透视表
sheet2 = workbook.CreateEmptySheet()
sheet2.Name = "数据透视表"

# 创建透视表对象
pt = sheet2.PivotTables.Add("销售透视表", sheet2.Range["A1"], cache)

# 把字段拖入行区域（区域外层 → 产品内层）
pf_region = pt.PivotFields["区域"]
pf_region.Axis = AxisTypes.Row
pf_product = pt.PivotFields["产品"]
pf_product.Axis = AxisTypes.Row

# 把字段拖入数据区域
pt.DataFields.Add(pt.PivotFields["销售额"], "销售额汇总", SubtotalTypes.Sum)
pt.DataFields.Add(pt.PivotFields["订单数"], "订单数汇总", SubtotalTypes.Sum)

# 应用内置样式并触发计算
pt.BuiltInStyle = PivotBuiltInStyles.PivotStyleMedium12
pt.CalculateData()

workbook.SaveToFile("SalesPivot.xlsx", ExcelVersion.Version2016)
workbook.Dispose()
print("SalesPivot.xlsx 已生成")

from spire.xls import *
from spire.xls.common import *

workbook = Workbook()
workbook.LoadFromFile("SalesPivot.xlsx")
sheet = workbook.Worksheets["数据透视表"]
pt = sheet.PivotTables[0]

# 修改汇总方式
pt.DataFields[0].Subtotal = SubtotalTypes.Average   # 销售额 → 平均值
pt.DataFields[1].Subtotal = SubtotalTypes.Max       # 订单数 → 最大值

# 数据字段显示为列百分比（适用于销售额这一列）
pt.DataFields[0].ShowDataAs = PivotFieldFormatType.PercentageOfColumn

# 重新计算并保存
pt.CalculateData()
workbook.SaveToFile("SalesPivot_Modified.xlsx", ExcelVersion.Version2016)
workbook.Dispose()
print("SalesPivot_Modified.xlsx 已生成")

from spire.xls import *
from spire.xls.common import *

workbook = Workbook()
workbook.LoadFromFile("SalesPivot.xlsx")
sheet = workbook.Worksheets["数据透视表"]
pt = sheet.PivotTables[0]

# 切换到 Tabular 布局（行字段并排显示，附带显式小计行）
pt.Options.RowLayout = PivotTableLayoutType.Tabular

# 显示行列总计
pt.ShowRowGrand = True
pt.ShowColumnGrand = True

# 空值单元格显示为自定义字符串
pt.DisplayNullString = True
pt.NullString = "—"

# 报表筛选字段自上而下、再自左而右
pt.PageFieldOrder = PagesOrderType.DownThenOver

# 是否显示行小计（默认 True；设为 False 时小计行会被隐藏）
pt.ShowSubtotals = True

# 重新应用内置样式
pt.BuiltInStyle = PivotBuiltInStyles.PivotStyleLight10

pt.CalculateData()
workbook.SaveToFile("SalesPivot_Styled.xlsx", ExcelVersion.Version2016)
workbook.Dispose()

from spire.xls import *
from spire.xls.common import *

workbook = Workbook()
workbook.LoadFromFile("SalesPivot.xlsx")
sheet = workbook.Worksheets["数据透视表"]
pt = sheet.PivotTables[0]

# 1. 计算数据（展开/折叠前需先调用）
pt.CalculateData()

# 2. 折叠"华东"区域的产品明细行（仅显示华东合计）
pt.PivotFields["区域"].HideItemDetail("华东", True)

# 3. 展开"华北"区域的产品明细行
pt.PivotFields["区域"].HideItemDetail("华北", False)

# 4. 启用"打开文件时自动刷新"
pt.Cache.IsRefreshOnLoad = True

workbook.SaveToFile("SalesPivot_Refresh.xlsx", ExcelVersion.Version2016)
workbook.Dispose()