csv怎么过滤数据_csv如何过滤数据

import csv

def filter_csv(input_file, output_file, condition):
    """
    从CSV文件中过滤数据。

    Args:
        input_file (str): 输入CSV文件的路径。
        output_file (str): 输出CSV文件的路径。
        condition (function): 用于过滤数据的函数，接受一个字典作为参数，返回True或False。
    """
    with open(input_file, 'r', newline='') as infile, \
            open(output_file, 'w', newline='') as outfile:

        reader = csv.DictReader(infile)
        writer = csv.DictWriter(outfile, fieldnames=reader.fieldnames)
        writer.writeheader() # 写入表头

        for row in reader:
            if condition(row):
                writer.writerow(row)

# 示例：只保留'age'大于30的行
def age_gt_30(row):
    try:
        return int(row['age']) > 30
    except ValueError:
        return False  # 处理'age'列为空或非数字的情况

# 使用示例
filter_csv('input.csv', 'output.csv', age_gt_30)

import csv

def process_large_csv(input_file, output_file, condition):
    with open(input_file, 'r', newline='') as infile, \
            open(output_file, 'w', newline='') as outfile:

        reader = csv.reader(infile)
        writer = csv.writer(outfile)

        header = next(reader) # 读取表头
        writer.writerow(header) # 写入表头

        for row in reader:
            # 将row转换为字典，方便使用列名进行条件判断
            row_dict = dict(zip(header, row))
            if condition(row_dict):
                writer.writerow(row)

# 示例：筛选'city'列为'New York'的行
def city_is_new_york(row):
    return row['city'] == 'New York'

process_large_csv('large_input.csv', 'large_output.csv', city_is_new_york)

import csv

def read_csv_with_encoding(file_path, encoding='utf-8'):
    try:
        with open(file_path, 'r', encoding=encoding, newline='') as csvfile:
            reader = csv.reader(csvfile)
            for row in reader:
                print(row)
    except UnicodeDecodeError:
        print(f"尝试使用 {encoding} 编码失败。")

# 尝试不同的编码
read_csv_with_encoding('your_file.csv', encoding='utf-8')
read_csv_with_encoding('your_file.csv', encoding='gbk')
read_csv_with_encoding('your_file.csv', encoding='latin-1')

import csv

def filter_csv_with_missing_values(input_file, output_file, condition):
    with open(input_file, 'r', newline='') as infile, \
            open(output_file, 'w', newline='') as outfile:

        reader = csv.DictReader(infile)
        writer = csv.DictWriter(outfile, fieldnames=reader.fieldnames)
        writer.writeheader()

        for row in reader:
            # 处理缺失值：将空字符串替换为None
            for key, value in row.items():
                if value == '':
                    row[key] = None
            if condition(row):
                writer.writerow(row)

# 示例：只保留'age'不为空的行
def age_is_not_null(row):
    return row['age'] is not None

filter_csv_with_missing_values('input_with_missing.csv', 'output_no_missing.csv', age_is_not_null)