使用Python处理CSV和Excel文件的操作方法

Name,Age,Gender
Alice,25,Female
Bob,30,Male
Charlie,35,Male

import csv
 
# 打开 CSV 文件
with open('example.csv', mode='r') as file:
    reader = csv.reader(file)
    for row in reader:
        print(row)

import csv
 
# 数据准备
data = [['Name', 'Age', 'Gender'], ['Alice', 25, 'Female'], ['Bob', 30, 'Male']]
 
# 写入 CSV 文件
with open('output.csv', mode='w', newline='') as file:
    writer = csv.writer(file)
    writer.writerows(data)

import csv
 
# 读取 CSV 文件为字典
with open('example.csv', mode='r') as file:
    reader = csv.DictReader(file)
    for row in reader:
        print(row)
 
# 写入 CSV 文件为字典
data = [{'Name': 'Alice', 'Age': 25, 'Gender': 'Female'}, {'Name': 'Bob', 'Age': 30, 'Gender': 'Male'}]
with open('output.csv', mode='w', newline='') as file:
    fieldnames = ['Name', 'Age', 'Gender']
    writer = csv.DictWriter(file, fieldnames=fieldnames)
    writer.writeheader()
    writer.writerows(data)

import pandas as pd
 
# 读取 CSV 文件为 DataFrame
df = pd.read_csv('example.csv')
print(df)

import pandas as pd
 
# 数据准备
data = {'Name': ['Alice', 'Bob'], 'Age': [25, 30], 'Gender': ['Female', 'Male']}
df = pd.DataFrame(data)
 
# 写入 CSV 文件
df.to_csv('output.csv', index=False)

# 过滤年龄大于 30 的行
filtered_df = df[df['Age'] > 30]
print(filtered_df)
 
# 添加新列
df['Country'] = ['USA', 'UK']
print(df)

from openpyxl import load_workbook
 
# 加载 Excel 文件
wb = load_workbook('example.xlsx')
sheet = wb.active
 
# 读取单元格数据
for row in sheet.iter_rows(values_only=True):
    print(row)

from openpyxl import Workbook
 
# 创建一个新的 Excel 文件
wb = Workbook()
sheet = wb.active
 
# 写入数据
sheet['A1'] = 'Name'
sheet['A2'] = 'Alice'
sheet['B1'] = 'Age'
sheet['B2'] = 25
 
# 保存 Excel 文件
wb.save('output.xlsx')

from openpyxl.styles import Font, Color, Alignment
 
# 设置字体和对齐
sheet['A1'].font = Font(bold=True, color="FF0000")
sheet['A1'].alignment = Alignment(horizontal="center")
 
wb.save('styled_output.xlsx')

import xlrd
 
# 打开 Excel 文件
workbook = xlrd.open_workbook('example.xls')
sheet = workbook.sheet_by_index(0)
 
# 读取数据
for row in range(sheet.nrows):
    print(sheet.row_values(row))

import xlwt
 
# 创建 Excel 文件
workbook = xlwt.Workbook()
sheet = workbook.add_sheet('Sheet1')
 
# 写入数据
sheet.write(0, 0, 'Name')
sheet.write(0, 1, 'Age')
sheet.write(1, 0, 'Alice')
sheet.write(1, 1, 25)
 
# 保存 Excel 文件
workbook.save('output.xls')

import pandas as pd
 
# 读取 Excel 文件为 DataFrame
df = pd.read_excel('example.xlsx')
print(df)

import pandas as pd
 
# 数据准备
data = {'Name': ['Alice', 'Bob'], 'Age': [25, 30], 'Gender': ['Female', 'Male']}
df = pd.DataFrame(data)
 
# 写入 Excel 文件
df.to_excel('output.xlsx', index=False)

import pandas as pd
 
chunk_size = 10000
chunks = pd.read_csv('large_file.csv', chunksize=chunk_size)
for chunk in chunks:
    # 处理每一块数据
    print(chunk.head())

# 去除缺失值
df.dropna(inplace=True)
 
# 填充缺失值
df.fillna(0, inplace=True)
 
# 去除重复数据
df.drop_duplicates(inplace=True)

import os
import pandas as pd
 
for file in os.listdir('csv_files'):
    if file.endswith('.csv'):
        df = pd.read_csv(f'csv_files/{file}')
        # 处理文件
        df.to_csv(f'processed_{file}', index=False)

df = pd.read_csv('file.csv', encoding='utf-8')