Python中openpyxl和pandas的使用示例详解

pip install openpyxl

pip install openpyxl[charts]

from openpyxl import Workbook
# 创建一个新工作簿
wb = Workbook()
# 获取活动的工作表
ws = wb.active
# 设置工作表标题
ws.title = "第一个工作表"
# 创建新的工作表
ws1 = wb.create_sheet("第二个工作表")  # 默认插入到最后
ws2 = wb.create_sheet("第三个工作表", 0)  # 插入到第一个位置
# 保存工作簿
wb.save("新工作簿.xlsx")

from openpyxl import load_workbook
# 打开一个已存在的工作簿
wb = load_workbook('example.xlsx')
# 获取所有工作表名称
print(wb.sheetnames)
# 通过名称获取工作表
ws = wb['Sheet1']
# 检查工作表是否存在
if 'Sheet1' in wb.sheetnames:
    print("Sheet1存在")

# 复制工作表
source = wb['Sheet1']
target = wb.copy_worksheet(source)
target.title = "Sheet1的副本"
# 删除工作表
del wb['Sheet1的副本']
# 遍历所有工作表
for sheet in wb:
    print(sheet.title)

# 获取单元格
cell = ws['A1']
# 写入值
ws['A1'] = "Hello"
ws['B1'] = "World"
# 使用单元格坐标
ws.cell(row=1, column=3, value="!")
# 读取值
print(ws['A1'].value)  # 输出: Hello
# 单元格坐标
print(cell.row, cell.column)  # 输出: 1, 1
print(cell.coordinate)  # 输出: A1

# 批量写入数据
for row in range(1, 6):
    for col in range(1, 5):
        ws.cell(row=row, column=col, value=f"R{row}C{col}")
# 批量读取数据
for row in ws.iter_rows(min_row=1, max_row=3, min_col=1, max_col=3):
    for cell in row:
        print(cell.value, end="\t")
    print()
# 使用values_only参数只获取值
for row in ws.iter_rows(values_only=True):
    print(row)

# 合并单元格
ws.merge_cells('A1:D1')
ws['A1'] = "合并的标题"
# 取消合并
ws.unmerge_cells('A1:D1')
# 设置行高和列宽
ws.row_dimensions[1].height = 30
ws.column_dimensions['A'].width = 20
# 隐藏行列
ws.column_dimensions['B'].hidden = True
ws.row_dimensions[2].hidden = True

from openpyxl.styles import Font, Color
# 设置字体
bold_font = Font(name='Arial', size=12, bold=True, italic=False, color='FF0000')
ws['A1'].font = bold_font
# 修改现有单元格字体
for row in ws.iter_rows(min_row=2, max_row=5):
    for cell in row:
        cell.font = Font(size=10, color=Color(rgb='0000FF'))

from openpyxl.styles import Alignment
# 设置对齐方式
center_aligned = Alignment(horizontal='center', vertical='center', wrap_text=True)
ws['A1'].alignment = center_aligned
# 应用到范围
for row in ws.iter_rows(min_row=1, max_row=10):
    for cell in row:
        cell.alignment = Alignment(horizontal='center')

from openpyxl.styles import Border, Side
# 定义边框样式
thin_border = Border(left=Side(style='thin'), 
                     right=Side(style='thin'),
                     top=Side(style='thin'),
                     bottom=Side(style='thin'))
# 应用边框
for row in ws.iter_rows(min_row=1, max_row=5):
    for cell in row:
        cell.border = thin_border

from openpyxl.styles import PatternFill, GradientFill
# 纯色填充
yellow_fill = PatternFill(start_color='FFFF00', end_color='FFFF00', fill_type='solid')
ws['A1'].fill = yellow_fill
# 渐变填充
gradient_fill = GradientFill(stop=('FFFFFF', '0000FF'))
ws['B1'].fill = gradient_fill

from openpyxl.styles import numbers
# 设置数字格式
ws['C1'].value = 3.1415926
ws['C1'].number_format = numbers.FORMAT_NUMBER_00  # 显示两位小数
# 自定义格式
ws['D1'].value = 0.85
ws['D1'].number_format = '0.00%'  # 显示为百分比

# 写入公式
ws['E1'] = '=SUM(A1:D1)'
ws['E2'] = '=AVERAGE(A2:D2)'
ws['E3'] = '=IF(A3>B3, "A大", "B大")'
# 读取公式
print(ws['E1'].value)  # 输出: =SUM(A1:D1)
# 计算数据
ws['F1'] = '结果'
ws['F2'] = '=E2*100'

from openpyxl.chart import BarChart, Reference
# 准备数据
for i in range(1, 6):
    ws[f'A{i}'] = i
    ws[f'B{i}'] = i*i
# 创建柱状图
chart = BarChart()
data = Reference(ws, min_col=2, min_row=1, max_row=5)
categories = Reference(ws, min_col=1, min_row=2, max_row=5)
chart.add_data(data, titles_from_data=True)
chart.set_categories(categories)
# 添加图表到工作表
ws.add_chart(chart, "D1")

from openpyxl.drawing.image import Image
# 插入图像
img = Image('logo.png')
ws.add_image(img, 'A10')
# 调整图像大小
img.width = 100
img.height = 100

from openpyxl.worksheet.datavalidation import DataValidation
# 创建数据验证
dv = DataValidation(type="list", formula1='"男,女"', allow_blank=True)
dv.add('A1:A10')  # 应用到A1:A10范围
ws.add_data_validation(dv)
# 数字范围验证
dv_num = DataValidation(type="whole", operator="between", formula1=1, formula2=100)
dv_num.error = "输入必须在1到100之间"
dv_num.add('B1:B10')
ws.add_data_validation(dv_num)

from openpyxl.formatting.rule import ColorScaleRule, FormulaRule
# 色阶条件格式
color_scale_rule = ColorScaleRule(start_type='min', start_color='FF0000',
                                 mid_type='percentile', mid_value=50, mid_color='FFFF00',
                                 end_type='max', end_color='00FF00')
ws.conditional_formatting.add('C1:C10', color_scale_rule)
# 公式条件格式
formula_rule = FormulaRule(formula=['ISBLANK(C1)'], stopIfTrue=True, font=Font(color='FF0000'))
ws.conditional_formatting.add('C1:C10', formula_rule)

# 保护工作表
ws.protection.sheet = True
ws.protection.password = 'password'
ws.protection.enable()
# 解锁特定单元格
for row in ws.iter_rows(min_row=1, max_row=5):
    for cell in row:
        cell.protection = Protection(locked=False)

# 冻结第一行和第一列
ws.freeze_panes = 'B2'
# 解冻
ws.freeze_panes = None

pip install pandas openpyxl xlrd

import pandas as pd
# 从字典创建
data = {
    '姓名': ['张三', '李四', '王五'],
    '年龄': [25, 30, 35],
    '城市': ['北京', '上海', '广州']
}
df = pd.DataFrame(data)
# 从列表创建
data = [
    {'姓名': '张三', '年龄': 25, '城市': '北京'},
    {'姓名': '李四', '年龄': 30, '城市': '上海'},
    {'姓名': '王五', '年龄': 35, '城市': '广州'}
]
df = pd.DataFrame(data)
# 显示DataFrame
print(df)

# 查看前几行
print(df.head(2))
# 查看后几行
print(df.tail(1))
# 查看形状
print(df.shape)  # 输出: (3, 3)
# 查看列名
print(df.columns)  # 输出: Index(['姓名', '年龄', '城市'], dtype='object')
# 查看索引
print(df.index)  # 输出: RangeIndex(start=0, stop=3, step=1)
# 查看数据类型
print(df.dtypes)

# 选择列
print(df['姓名'])  # 选择单列
print(df[['姓名', '年龄']])  # 选择多列
# 选择行
print(df.iloc[0])  # 通过位置选择
print(df.loc[0])  # 通过索引选择
print(df[1:3])  # 切片选择
# 条件选择
print(df[df['年龄'] > 28])
print(df[(df['年龄'] > 25) & (df['城市'] == '上海')])

# 添加列
df['性别'] = ['男', '女', '男']
# 修改值
df.loc[0, '年龄'] = 26
df['年龄'] = df['年龄'] + 1
# 删除列
df = df.drop('性别', axis=1)
# 删除行
df = df.drop(0, axis=0)

# 读取整个Excel文件
df = pd.read_excel('data.xlsx', sheet_name='Sheet1')
# 读取指定范围
df = pd.read_excel('data.xlsx', sheet_name='Sheet1', usecols='A:C', nrows=10)
# 读取多个工作表
with pd.ExcelFile('data.xlsx') as xls:
    df1 = pd.read_excel(xls, 'Sheet1')
    df2 = pd.read_excel(xls, 'Sheet2')
# 处理缺失值
df = pd.read_excel('data.xlsx', na_values=['NA', 'N/A', '缺失'])

# 写入单个DataFrame
df.to_excel('output.xlsx', sheet_name='数据', index=False)
# 写入多个DataFrame
with pd.ExcelWriter('output.xlsx') as writer:
    df1.to_excel(writer, sheet_name='Sheet1')
    df2.to_excel(writer, sheet_name='Sheet2')
# 追加模式写入
with pd.ExcelWriter('output.xlsx', mode='a') as writer:
    df3.to_excel(writer, sheet_name='Sheet3')
# 设置格式
df.to_excel('output.xlsx', 
            sheet_name='数据',
            index=False,
            float_format="%.2f",  # 浮点数格式
            freeze_panes=(1, 0))  # 冻结首行

# CSV文件
df.to_csv('data.csv', index=False)
df = pd.read_csv('data.csv')
# JSON
df.to_json('data.json', orient='records')
df = pd.read_json('data.json')
# SQL数据库
from sqlalchemy import create_engine
engine = create_engine('sqlite:///data.db')
df.to_sql('table_name', engine, if_exists='replace')
df = pd.read_sql('SELECT * FROM table_name', engine)

# 检测缺失值
print(df.isnull().sum())
# 删除缺失值
df_cleaned = df.dropna()  # 删除任何包含缺失值的行
df_cleaned = df.dropna(subset=['年龄'])  # 只删除年龄列有缺失的行
# 填充缺失值
df_filled = df.fillna(0)  # 用0填充
df_filled = df.fillna(df.mean())  # 用均值填充数值列
df_filled = df.fillna(method='ffill')  # 用前一个值填充

# 检测重复行
print(df.duplicated().sum())
# 删除重复行
df_unique = df.drop_duplicates()
# 基于某些列删除重复
df_unique = df.drop_duplicates(subset=['姓名', '城市'])

# 查看数据类型
print(df.dtypes)
# 转换数据类型
df['年龄'] = df['年龄'].astype('float64')
df['日期'] = pd.to_datetime(df['日期'])
# 分类数据
df['城市'] = df['城市'].astype('category')

# 字符串方法
df['姓名'] = df['姓名'].str.upper()  # 转为大写
df['城市'] = df['城市'].str.replace('京', '都')  # 替换
# 提取信息
df['姓氏'] = df['姓名'].str[0]  # 提取第一个字符
df['名字'] = df['姓名'].str[1:]  # 提取第二个字符之后
# 拆分列
df[['姓', '名']] = df['姓名'].str.split(expand=True)

# 解析日期
df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d')
# 提取日期部分
df['年'] = df['日期'].dt.year
df['月'] = df['日期'].dt.month
df['日'] = df['日期'].dt.day
df['星期'] = df['日期'].dt.day_name()
# 日期运算
df['年龄天数'] = (pd.to_datetime('today') - df['出生日期']).dt.days
df['年龄'] = df['年龄天数'] // 365

# 应用简单函数
df['年龄加10'] = df['年龄'].apply(lambda x: x + 10)
# 应用复杂函数
def age_group(age):
    if age < 20: return '少年'
    elif age < 40: return '青年'
    else: return '中年'
df['年龄段'] = df['年龄'].apply(age_group)
# 向量化操作
df['BMI'] = df['体重'] / (df['身高']/100)**2

# 基本分组
grouped = df.groupby('城市')
# 聚合函数
print(grouped['年龄'].mean())  # 每个城市的平均年龄
print(grouped.agg({'年龄': ['mean', 'min', 'max'], '收入': 'sum'}))
# 多级分组
grouped = df.groupby(['城市', '性别'])
print(grouped['年龄'].mean())

# 简单透视表
pivot = pd.pivot_table(df, values='年龄', index='城市', aggfunc='mean')
# 复杂透视表
pivot = pd.pivot_table(df, 
                      values=['年龄', '收入'],
                      index=['城市', '性别'],
                      columns=['教育程度'],
                      aggfunc={'年龄': 'mean', '收入': ['sum', 'count']},
                      fill_value=0,
                      margins=True)

# 合并两个DataFrame
df1 = pd.DataFrame({'key': ['A', 'B', 'C'], 'value': [1, 2, 3]})
df2 = pd.DataFrame({'key': ['A', 'B', 'D'], 'value': [4, 5, 6]})
# 内连接
pd.merge(df1, df2, on='key', how='inner')
# 左连接
pd.merge(df1, df2, on='key', how='left')
# 外连接
pd.merge(df1, df2, on='key', how='outer')
# 纵向合并
pd.concat([df1, df2], axis=0)

# 创建时间序列
date_rng = pd.date_range(start='1/1/2020', end='1/10/2020', freq='D')
df = pd.DataFrame(date_rng, columns=['date'])
df['data'] = np.random.randint(0,100,size=(len(date_rng)))
# 设置为索引
df = df.set_index('date')
# 重采样
df.resample('W').mean()  # 按周平均
df.resample('M').sum()  # 按月求和
# 滚动窗口
df.rolling(window=3).mean()  # 3天移动平均

# 描述性统计
print(df.describe())
# 相关性
print(df.corr())
# 协方差
print(df.cov())
# 唯一值计数
print(df['城市'].value_counts())
# 交叉表
pd.crosstab(df['城市'], df['性别'])

import matplotlib.pyplot as plt
# 线图
df.plot.line()
# 柱状图
df.plot.bar()
# 直方图
df['年龄'].plot.hist(bins=20)
# 箱线图
df.plot.box()
# 散点图
df.plot.scatter(x='年龄', y='收入')
plt.show()

from openpyxl import load_workbook
from openpyxl.utils.dataframe import dataframe_to_rows
# 创建DataFrame
df = pd.DataFrame({
    '产品': ['A', 'B', 'C', 'D'],
    '销量': [120, 150, 90, 200],
    '单价': [25.5, 32.0, 18.0, 40.5]
})
# 加载现有工作簿或创建新工作簿
try:
    wb = load_workbook('report.xlsx')
except FileNotFoundError:
    wb = Workbook()
# 选择或创建工作表
if '销售报告' in wb.sheetnames:
    ws = wb['销售报告']
else:
    ws = wb.create_sheet('销售报告')
# 清空现有内容
ws.delete_rows(1, ws.max_row)
# 写入DataFrame数据
for r in dataframe_to_rows(df, index=False, header=True):
    ws.append(r)
# 添加公式
ws['E1'] = '销售额'
for row in range(2, ws.max_row + 1):
    ws[f'E{row}'] = f'=B{row}*C{row}'
# 设置格式
header_font = Font(bold=True, color='FFFFFF')
header_fill = PatternFill(start_color='4F81BD', end_color='4F81BD', fill_type='solid')
for cell in ws[1]:
    cell.font = header_font
    cell.fill = header_fill
# 保存工作簿
wb.save('report.xlsx')

from openpyxl import load_workbook
# 加载工作簿
wb = load_workbook('data.xlsx')
ws = wb.active
# 将工作表数据转换为列表
data = []
for row in ws.iter_rows(values_only=True):
    data.append(row)
# 转换为DataFrame
df = pd.DataFrame(data[1:], columns=data[0])
# 处理数据
df['日期'] = pd.to_datetime(df['日期'])
df['销售额'] = df['数量'] * df['单价']
print(df.head())

import pandas as pd
from openpyxl import Workbook
from openpyxl.styles import Font, Alignment, Border, Side, PatternFill
from openpyxl.chart import BarChart, Reference
from openpyxl.drawing.image import Image
from datetime import datetime
# 1. 准备数据
sales_data = {
    '月份': ['1月', '2月', '3月', '4月', '5月', '6月'],
    '产品A': [1200, 1500, 1800, 2100, 2400, 2700],
    '产品B': [800, 950, 1100, 1250, 1400, 1550],
    '产品C': [500, 600, 700, 800, 900, 1000]
}
df = pd.DataFrame(sales_data)
# 2. 创建Excel工作簿
wb = Workbook()
ws = wb.active
ws.title = "销售报告"
# 3. 写入标题
ws['A1'] = "2023年上半年销售报告"
ws['A1'].font = Font(size=16, bold=True, name='微软雅黑')
ws.merge_cells('A1:D1')
# 4. 写入数据
# 写入列标题
columns = list(df.columns)
for col_num, column_title in enumerate(columns, 1):
    cell = ws.cell(row=3, column=col_num, value=column_title)
    cell.font = Font(bold=True)
    cell.alignment = Alignment(horizontal='center')
# 写入数据
for row_num, row_data in enumerate(df.values, 4):
    for col_num, cell_value in enumerate(row_data, 1):
        ws.cell(row=row_num, column=col_num, value=cell_value)
# 5. 添加汇总行
last_row = ws.max_row + 1
ws.cell(row=last_row, column=1, value="总计").font = Font(bold=True)
for col_num in range(2, 5):
    col_letter = chr(64 + col_num)
    ws.cell(row=last_row, column=col_num, 
           value=f"=SUM({col_letter}4:{col_letter}{last_row-1})")
# 6. 设置格式
# 设置边框
thin_border = Border(left=Side(style='thin'), 
                     right=Side(style='thin'),
                     top=Side(style='thin'),
                     bottom=Side(style='thin'))
for row in ws.iter_rows(min_row=3, max_row=last_row, min_col=1, max_col=4):
    for cell in row:
        cell.border = thin_border
        if cell.row > 3 and cell.column > 1:  # 数据单元格
            cell.number_format = '#,##0'
# 设置对齐
for row in ws.iter_rows(min_row=3, max_row=last_row, min_col=1, max_col=4):
    for cell in row:
        cell.alignment = Alignment(horizontal='center')
# 7. 创建图表
chart = BarChart()
chart.type = "col"
chart.style = 10
chart.title = "产品销售趋势"
chart.y_axis.title = "销售额"
chart.x_axis.title = "月份"
data = Reference(ws, min_col=2, max_col=4, min_row=3, max_row=last_row-1)
categories = Reference(ws, min_col=1, min_row=4, max_row=last_row-1)
chart.add_data(data, titles_from_data=True)
chart.set_categories(categories)
ws.add_chart(chart, "F3")
# 8. 添加页脚
footer_row = last_row + 2
ws.cell(row=footer_row, column=1, 
       value=f"报告生成时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
# 9. 调整列宽
ws.column_dimensions['A'].width = 12
ws.column_dimensions['B'].width = 12
ws.column_dimensions['C'].width = 12
ws.column_dimensions['D'].width = 12
# 10. 保存文件
filename = f"销售报告_{datetime.now().strftime('%Y%m%d')}.xlsx"
wb.save(filename)
print(f"报表已生成: {filename}")

from openpyxl import load_workbook
from openpyxl.utils.dataframe import dataframe_to_rows
import pandas as pd
# 1. 加载模板文件
template_path = 'report_template.xlsx'
wb = load_workbook(template_path)
ws = wb['Data']
# 2. 准备数据
data = {
    'Region': ['North', 'South', 'East', 'West'],
    'Q1': [1200, 1500, 1800, 900],
    'Q2': [1300, 1600, 1900, 950],
    'Q3': [1400, 1700, 2000, 1000],
    'Q4': [1500, 1800, 2100, 1050]
}
df = pd.DataFrame(data)
# 3. 清空模板中的数据区域 (保留格式)
for row in ws.iter_rows(min_row=3, max_row=100, min_col=1, max_col=6):
    for cell in row:
        cell.value = None
# 4. 写入新数据
for r_idx, row in enumerate(dataframe_to_rows(df, index=False, header=False), 3):
    for c_idx, value in enumerate(row, 1):
        ws.cell(row=r_idx, column=c_idx, value=value)
# 5. 更新公式 (假设模板中已有公式)
last_data_row = 3 + len(df) - 1
for row in range(3, last_data_row + 1):
    ws[f'F{row}'] = f'=SUM(B{row}:E{row})'
# 6. 更新汇总公式
ws['B20'] = f'=SUM(B3:B{last_data_row})'
ws['C20'] = f'=SUM(C3:C{last_data_row})'
ws['D20'] = f'=SUM(D3:D{last_data_row})'
ws['E20'] = f'=SUM(E3:E{last_data_row})'
ws['F20'] = f'=SUM(F3:F{last_data_row})'
# 7. 更新报告日期
ws['A1'] = f"销售报告 - {pd.Timestamp.today().strftime('%Y-%m-%d')}"
# 8. 保存新文件
output_path = 'quarterly_report.xlsx'
wb.save(output_path)
print(f"报告已生成: {output_path}")

wb = load_workbook('large_file.xlsx', read_only=True)

wb = Workbook(write_only=True)
ws = wb.create_sheet()
for row in data:
    ws.append(row)

wb = load_workbook('file.xlsx', data_only=False)
wb.calculation = False
# ... 写入公式 ...
wb.calculation = True
wb.save('file.xlsx')

del large_df
del wb

import pandas as pd
from openpyxl import load_workbook
from openpyxl.styles import Font, Alignment, numbers
from datetime import datetime
def generate_financial_report(input_path, output_path):
    # 1. 使用pandas读取和处理数据
    df = pd.read_excel(input_path, sheet_name='Transactions')
    # 数据清洗
    df = df.dropna(subset=['Amount'])
    df['Date'] = pd.to_datetime(df['Date'])
    df['Month'] = df['Date'].dt.to_period('M')
    # 分类汇总
    income = df[df['Type'] == 'Income'].groupby('Month')['Amount'].sum()
    expense = df[df['Type']