import csv

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

with open('data.csv', 'r', newline='', encoding='utf-8') as file:
    reader = csv.DictReader(file)
    for row in reader:
        print(row['name'], row['age'], row['city'])

import csv

data = [
    ["姓名", "年齡", "城市"],
    ["Alice", 25, "New York"],
    ["Bob", 30, "Los Angeles"],
    ["Charlie", 35, "Chicago"]
]

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

fieldnames = ['Name', 'Age', 'City']
data = [
    {'Name': 'Alice', 'Age': 24, 'City': 'New York'},
    {'Name': 'Bob', 'Age': 30, 'City': 'Los Angeles'}
]

極速分析

with open('output.csv', 'w', newline='', encoding='utf-8') as file:
    writer = csv.DictWriter(file, fieldnames=fieldnames)
    writer.writeheader()  # 寫入標(biāo)題行
    writer.writerows(data)

import pandas as pd

df = pd.read_csv('data.csv')
print(df.head())  # 查看前幾行數(shù)據(jù)

# 處理缺失值
df.fillna(0, inplace=True)  # 將所有缺失值替換為0
# 或者用特定列的平均值替換
df['column1'].fillna(df['column1'].mean(), inplace=True)

# 刪除含有缺失值的行
df.dropna(inplace=True)

# 數(shù)據(jù)類型轉(zhuǎn)換
df['age'] = df['age'].astype(int)

# 數(shù)據(jù)過濾
filtered_df = df[df['age'] > 30]  # 篩選年齡大于30的行

# 分組操作
grouped = df.groupby('city')['age'].mean()  # 按城市分組極速分析計(jì)算平均年齡

df.to_csv('output.csv', index=False)  # index=False表示不寫入行索引

# 分批寫入
for i in range(0, len(df), 1000):
    chunk = df[i:i+1000]
    chunk.to_csv(f'output_chunk_{i}.csv', index=False)
    
# 使用壓縮
df.to_csv('output.csv.gz', index=False, compression='gzip')

# 使用csv模塊逐行處理（內(nèi)存友好）
with open('large_data.csv', 'r') as file:
    reader = csv.reader(file)
    for極速分析 row in reader:
        process_row(row)  # 自定義處理函數(shù)

# 使用pandas分塊讀取
chunk_size = 10000
for chunk in pd.read_csv('large_data.csv', chunksize=chunk_size):
    process_chunk(chunk)  # 處理每個數(shù)據(jù)塊

# 讀取制表符分隔的文件
with open('data.ts極速分析v', 'r') as file:
    reader = csv.reader(file, delimiter='\t')
    for row in reader:
        print(row)

# 處理包含特殊字符的字段
with open('data.csv', 'w', newline='') as file:
    writer = csv.writer(file, quoting=csv.QUOTE_NONNUMERIC)  # 非數(shù)字字段加引號
    writer.writerow(['Text', 100, 'More "text"'])

# 手動指定數(shù)據(jù)類型以減少內(nèi)存使用和提高處理速度
dtypes = {
    'name': 'category',
    'age': 'int32',
    'salary': 'float32'
}
df = pd.read_csv('data.csv', dtype=dtypes)

# 在讀取時解析日期
df = pd.read_csv('data.csv', parse_dates=['birth_date'])

# 使用ciso8601快速解析日期時間
from ciso8601 import parse_datetime
date_string = "2023-10-01T12:00:00"
parsed_date = parse_datetime(date_string)

# 使用cython編譯關(guān)鍵代碼段
# 需要創(chuàng)建setup.py文件和編寫cython代碼

# 讀取UTF-8編碼的文件
with open('data.csv', 'r', encoding='utf-8') as file:
    reader = csv.reader(file)
    for row in reader:
        print(row)

# 讀取GBK編碼的文件（常見于中文環(huán)境）
with open('data.csv', 'r', encoding='gbk') as file:
    reader = csv.reader(file)
    for row in reader:
        print(row)

# 跳過錯誤行（使用pandas）
try:
    df = pd.read_csv('data.csv', error_bad_lines=False)
except Exception as e:
    print(f"Error: {e}")

# 使用靈活的分隔符和引號處理
import csv
with open('messy_data.csv', 'r') as file:
    # 嘗試多種分隔符
    dialects = csv.Sniffer().sniff(file.read(1024))
    file.seek(0)
    reader = csv.reader(file, delimiter=dialects.delimiter)
    for row in reader:
        print(row)