import csv

# CSV 파일 읽기
with open('data.csv', 'r', encoding='utf-8') as file:
    reader = csv.reader(file)
    for row in reader:
        print(row)

# CSV 파일 쓰기
data = [
    ['이름', '나이', '도시'],
    ['John', '30', 'New York'],
    ['Alice', '25', 'London']
]

with open('output.csv', 'w', newline='', encoding='utf-8') as file:
    writer = csv.writer(file)
    writer.writerows(data)

# 딕셔너리 형태로 읽기
with open('data.csv', 'r', encoding='utf-8') as file:
    reader = csv.DictReader(file)
    for row in reader:
        print(f"이름: {row['이름']}, 나이: {row['나이']}")

# 딕셔너리 형태로 쓰기
data = [
    {'이름': 'John', '나이': '30', '도시': 'New York'},
    {'이름': 'Alice', '나이': '25', '도시': 'London'}
]

with open('output.csv', 'w', newline='', encoding='utf-8') as file:
    fieldnames = ['이름', '나이', '도시']
    writer = csv.DictWriter(file, fieldnames=fieldnames)
    writer.writeheader()
    writer.writerows(data)

# 커스텀 구분자 사용
with open('data.tsv', 'r', encoding='utf-8') as file:
    reader = csv.reader(file, delimiter='\t')
    for row in reader:
        print(row)

# 커스텀 따옴표 처리
csv.register_dialect('custom', 
    delimiter=';',
    quotechar='"',
    quoting=csv.QUOTE_MINIMAL,
    escapechar='\\'
)

with open('output.csv', 'w', newline='', encoding='utf-8') as file:
    writer = csv.writer(file, dialect='custom')
    writer.writerows(data)

def validate_row(row):
    try:
        # 나이 필드 검증
        age = int(row['나이'])
        if age < 0 or age > 150:
            raise ValueError("유효하지 않은 나이")
        
        # 이메일 필드 검증
        if '@' not in row['이메일']:
            raise ValueError("유효하지 않은 이메일")
        
        return True
    except Exception as e:
        print(f"검증 실패: {e}")
        return False

def process_csv(input_file, output_file):
    with open(input_file, 'r', encoding='utf-8') as infile:
        reader = csv.DictReader(infile)
        valid_rows = [row for row in reader if validate_row(row)]
        
    with open(output_file, 'w', newline='', encoding='utf-8') as outfile:
        writer = csv.DictWriter(outfile, fieldnames=reader.fieldnames)
        writer.writeheader()
        writer.writerows(valid_rows)

def process_large_csv(file_path, chunk_size=1000):
    with open(file_path, 'r', encoding='utf-8') as file:
        reader = csv.reader(file)
        header = next(reader)  # 헤더 읽기
        
        chunk = []
        for row in reader:
            chunk.append(row)
            
            if len(chunk) >= chunk_size:
                process_chunk(chunk)
                chunk = []
        
        # 남은 데이터 처리
        if chunk:
            process_chunk(chunk)

# 여러 CSV 파일 병합
def merge_csv_files(input_files, output_file):
    with open(output_file, 'w', newline='', encoding='utf-8') as outfile:
        for i, file_path in enumerate(input_files):
            with open(file_path, 'r', encoding='utf-8') as infile:
                reader = csv.reader(infile)
                
                # 첫 번째 파일의 헤더만 사용
                if i == 0:
                    header = next(reader)
                    writer = csv.writer(outfile)
                    writer.writerow(header)
                else:
                    next(reader)  # 헤더 건너뛰기
                
                # 데이터 복사
                for row in reader:
                    writer.writerow(row)

# CSV 파일 분할
def split_csv_file(input_file, output_prefix, rows_per_file=1000):
    with open(input_file, 'r', encoding='utf-8') as infile:
        reader = csv.reader(infile)
        header = next(reader)
        
        file_number = 1
        row_count = 0
        
        current_out_file = open(f"{output_prefix}_{file_number}.csv", 'w', newline='', encoding='utf-8')
        current_writer = csv.writer(current_out_file)
        current_writer.writerow(header)
        
        for row in reader:
            current_writer.writerow(row)
            row_count += 1
            
            if row_count >= rows_per_file:
                current_out_file.close()
                file_number += 1
                row_count = 0
                
                current_out_file = open(f"{output_prefix}_{file_number}.csv", 'w', newline='', encoding='utf-8')
                current_writer = csv.writer(current_out_file)
                current_writer.writerow(header)
        
        current_out_file.close()

import pandas as pd

# CSV 파일을 DataFrame으로 읽기
df = pd.read_csv('data.csv', encoding='utf-8')

# 데이터 탐색
print(df.head())  # 처음 5행 보기
print(df.describe())  # 기본 통계
print(df.columns)  # 열 이름

# 데이터 필터링 및 변환
filtered_df = df[df['나이'] > 25]
df['전체이름'] = df['성'] + ' ' + df['이름']

# 데이터 그룹화 및 집계
grouped = df.groupby('도시').agg({
    '나이': ['mean', 'min', 'max', 'count'],
    '급여': 'sum'
})

# CSV 파일로 저장
filtered_df.to_csv('filtered_data.csv', index=False, encoding='utf-8')