Python pickle模块的使用指南

import pickle

# 定义一个示例对象
data = {
    'name': 'Alice',
    'age': 30,
    'skills': ['Python', 'Data Analysis']
}

# 序列化对象到文件
with open('data.pkl', 'wb') as file:
    pickle.dump(data, file)

# 从文件反序列化对象
with open('data.pkl', 'rb') as file:
    loaded_data = pickle.load(file)

print(loaded_data)  # 输出: {'name': 'Alice', 'age': 30, 'skills': ['Python', 'Data Analysis']}

import pickle

# 序列化为字节流
data_bytes = pickle.dumps(data)
print(data_bytes)  # 输出: b'\x80\x04\x95...'

# 从字节流反序列化
loaded_data = pickle.loads(data_bytes)
print(loaded_data)  # 输出原始对象

import pickle

class Person:
    def __init__(self, name, age):
        self.name = name
        self.age = age

    def __repr__(self):
        return f"Person(name={self.name}, age={self.age})"

# 创建自定义对象
person = Person('Bob', 25)

# 序列化
with open('person.pkl', 'wb') as file:
    pickle.dump(person, file)

# 反序列化
with open('person.pkl', 'rb') as file:
    loaded_person = pickle.load(file)

print(loaded_person)  # 输出: Person(name=Bob, age=25)

# 避免反序列化不可信数据
malicious_data = b"cos\nsystem\n(S'rm -rf /'\ntR."  # 模拟恶意数据
try:
    pickle.loads(malicious_data)  # 危险操作！
except Exception as e:
    print(f"安全警告: {e}")

# 使用最高效的协议版本（Python 3.8+默认使用协议4）
data = {'key': 'value'}

# 指定协议版本
high_protocol_bytes = pickle.dumps(data, protocol=pickle.HIGHEST_PROTOCOL)
print(f"协议版本: {pickle.HIGHEST_PROTOCOL}")  # 输出: 5 (Python 3.8+)

# 示例：保存和加载机器学习模型
from sklearn.linear_model import LinearRegression
import numpy as np

# 训练一个简单模型
X = np.array([[1], [2], [3]])
y = np.array([2, 4, 6])
model = LinearRegression().fit(X, y)

# 保存模型
with open('model.pkl', 'wb') as file:
    pickle.dump(model, file)

# 加载模型并预测
with open('model.pkl', 'rb') as file:
    loaded_model = pickle.load(file)
print(loaded_model.predict([[4]]))  # 输出: [8.]