Python类型提示：类型注解实用指南

# 没有类型提示 - 这个函数期望什么？
def process_data(data, threshold, output):
    ...
 
# 有了类型提示 - 一目了然
def process_data(data: list[float], threshold: float, output: str) -> dict[str, float]:
    ...

# 基础变量注解
name: str = "Alice"
age: int = 30
height: float = 5.9
is_active: bool = True
raw_data: bytes = b"hello"
 
# 不带赋值的注解（仅声明）
username: str
count: int

def greet(name: str) -> str:
    return f"Hello, {name}!"
 
def calculate_average(numbers: list[float]) -> float:
    return sum(numbers) / len(numbers)
 
def save_record(record: dict[str, str], overwrite: bool = False) -> None:
    """不返回有意义的值的函数使用 -> None。"""
    ...

def parse_config(path: str, encoding: str = "utf-8") -> dict[str, str]:
    config: dict[str, str] = {}
    with open(path, encoding=encoding) as f:
        for line in f:
            key, _, value = line.partition("=")
            config[key.strip()] = value.strip()
    return config

# 列表
scores: list[int] = [95, 87, 92]
names: list[str] = ["Alice", "Bob"]
 
# 字典
user_ages: dict[str, int] = {"Alice": 30, "Bob": 25}
config: dict[str, list[str]] = {"servers": ["a.com", "b.com"]}
 
# 元组 - 固定长度且特定类型
point: tuple[float, float] = (3.14, 2.72)
record: tuple[str, int, bool] = ("Alice", 30, True)
 
# 可变长度元组（所有相同类型）
values: tuple[int, ...] = (1, 2, 3, 4, 5)
 
# 集合和冻结集合
tags: set[str] = {"python", "typing"}
constants: frozenset[int] = frozenset({1, 2, 3})

from typing import List, Dict, Tuple, Set, FrozenSet
 
scores: List[int] = [95, 87, 92]
user_ages: Dict[str, int] = {"Alice": 30}
point: Tuple[float, float] = (3.14, 2.72)
tags: Set[str] = {"python", "typing"}

# 矩阵：浮点数的列表的列表
matrix: list[list[float]] = [[1.0, 2.0], [3.0, 4.0]]
 
# 将用户映射到他们的分数列表
gradebook: dict[str, list[int]] = {
    "Alice": [95, 87, 92],
    "Bob": [78, 85, 90],
}
 
# 配置：嵌套字典
app_config: dict[str, dict[str, str | int]] = {
    "database": {"host": "localhost", "port": 5432},
    "cache": {"host": "redis.local", "port": 6379},
}

from typing import Optional
 
# 3.10之前的语法
def find_user(user_id: int) -> Optional[str]:
    """返回用户名，如果未找到则返回None。"""
    users = {1: "Alice", 2: "Bob"}
    return users.get(user_id)
 
# Python 3.10+语法（推荐）
def find_user(user_id: int) -> str | None:
    """返回用户名，如果未找到则返回None。"""
    users = {1: "Alice", 2: "Bob"}
    return users.get(user_id)

from typing import Union
 
# 3.10之前的语法
def format_value(value: Union[int, float, str]) -> str:
    return str(value)
 
# Python 3.10+语法（推荐）
def format_value(value: int | float | str) -> str:
    return str(value)
 
# 常见模式：接受多种输入格式
def load_data(source: str | Path) -> list[dict[str, str]]:
    path = Path(source) if isinstance(source, str) else source
    with open(path) as f:
        return json.load(f)

from typing import Any
 
def log_event(event: str, payload: Any) -> None:
    """接受任何负载类型 - 对通用日志记录很有用。"""
    print(f"[{event}] {payload}")
 
# Any与每种类型都兼容
log_event("click", {"x": 100, "y": 200})
log_event("error", 404)
log_event("message", "hello")

from typing import TypeVar
 
T = TypeVar("T")
 
def first_element(items: list[T]) -> T:
    """返回第一个元素，保留其类型。"""
    return items[0]
 
# 类型检查器推断正确的返回类型
name = first_element(["Alice", "Bob"])     # type: str
score = first_element([95, 87, 92])        # type: int
 
# 有界TypeVar - 限制为特定类型
Numeric = TypeVar("Numeric", int, float)
 
def add(a: Numeric, b: Numeric) -> Numeric:
    return a + b

from typing import TypeVar, Generic
 
T = TypeVar("T")
 
class Stack(Generic[T]):
    def __init__(self) -> None:
        self._items: list[T] = []
 
    def push(self, item: T) -> None:
        self._items.append(item)
 
    def pop(self) -> T:
        return self._items.pop()
 
    def peek(self) -> T:
        return self._items[-1]
 
    def is_empty(self) -> bool:
        return len(self._items) == 0
 
# 使用特定类型
int_stack: Stack[int] = Stack()
int_stack.push(42)
value: int = int_stack.pop()
 
str_stack: Stack[str] = Stack()
str_stack.push("hello")

from typing import Callable
 
# 接受回调的函数
def apply_operation(
    values: list[float],
    operation: Callable[[float], float]
) -> list[float]:
    return [operation(v) for v in values]
 
# 使用
import math
results = apply_operation([1.0, 4.0, 9.0], math.sqrt)
# results: [1.0, 2.0, 3.0]
 
# 更复杂的可调用签名
Comparator = Callable[[str, str], int]
EventHandler = Callable[[str, dict[str, str]], None]
 
def sort_with_comparator(
    items: list[str],
    compare: Comparator
) -> list[str]:
    import functools
    return sorted(items, key=functools.cmp_to_key(compare))

from typing import Literal
 
def set_log_level(level: Literal["DEBUG", "INFO", "WARNING", "ERROR"]) -> None:
    print(f"Log level set to {level}")
 
set_log_level("INFO")      # OK
set_log_level("VERBOSE")   # 类型错误：不是有效的字面量
 
# 对模式参数很有用
def read_file(
    path: str,
    mode: Literal["text", "binary"] = "text"
) -> str | bytes:
    if mode == "text":
        return open(path).read()
    return open(path, "rb").read()

from typing import TypedDict, NotRequired
 
class UserProfile(TypedDict):
    name: str
    email: str
    age: int
    bio: NotRequired[str]  # 可选键（Python 3.11+）
 
def display_user(user: UserProfile) -> str:
    return f"{user['name']} ({user['email']}), age {user['age']}"
 
# 类型检查器验证结构
user: UserProfile = {
    "name": "Alice",
    "email": "alice@example.com",
    "age": 30,
}
 
display_user(user)  # OK

from typing import Protocol, runtime_checkable
 
@runtime_checkable
class Drawable(Protocol):
    def draw(self, x: int, y: int) -> None: ...
 
class Circle:
    def draw(self, x: int, y: int) -> None:
        print(f"Drawing circle at ({x}, {y})")
 
class Square:
    def draw(self, x: int, y: int) -> None:
        print(f"Drawing square at ({x}, {y})")
 
def render(shape: Drawable, x: int, y: int) -> None:
    shape.draw(x, y)
 
# 两者都无需继承自Drawable即可工作
render(Circle(), 10, 20)
render(Square(), 30, 40)
 
# runtime_checkable启用isinstance检查
print(isinstance(Circle(), Drawable))  # True

from typing import TypeAlias
 
# 简单别名
UserId: TypeAlias = int
JsonDict: TypeAlias = dict[str, "JsonValue"]
JsonValue: TypeAlias = str | int | float | bool | None | list["JsonValue"] | JsonDict
 
# 复杂别名简化签名
Matrix: TypeAlias = list[list[float]]
Callback: TypeAlias = Callable[[str, int], bool]
Config: TypeAlias = dict[str, str | int | list[str]]
 
def transform_matrix(m: Matrix, factor: float) -> Matrix:
    return [[cell * factor for cell in row] for row in m]
 
# Python 3.12+使用type语句
# type Vector = list[float]

# 安装mypy
# pip install mypy
 
# 检查单个文件
# mypy script.py
 
# 检查整个项目
# mypy src/
 
# 使用特定Python版本检查
# mypy --python-version 3.10 src/

# pyproject.toml配置
# [tool.mypy]
# python_version = "3.10"
# warn_return_any = true
# warn_unused_configs = true
# disallow_untyped_defs = true
# check_untyped_defs = true
# no_implicit_optional = true
# strict_equality = true
 
# 按模块覆盖
# [[tool.mypy.overrides]]
# module = "third_party_lib.*"
# ignore_missing_imports = true

# 错误：不兼容的返回值类型（得到"Optional[str]"，期望"str"）
# 修复：处理None情况
def get_name(user_id: int) -> str:
    result = lookup(user_id)  # 返回 str | None
    if result is None:
        raise ValueError(f"User {user_id} not found")
    return result  # mypy知道result是str
 
# 错误："Optional[str]"的项"None"没有属性"upper"
# 修复：先缩小类型
def format_name(name: str | None) -> str:
    if name is not None:
        return name.upper()
    return "UNKNOWN"
 
# 错误：变量需要类型注解
# 修复：添加显式注解
items: list[str] = []  # 不只是：items = []
 
# 错误：赋值中的不兼容类型
# 修复：使用Union或更正类型
value: int | str = 42
value = "hello"  # 使用联合类型OK
 
# 必要时抑制特定错误
x = some_untyped_function()  # type: ignore[no-untyped-call]

from fastapi import FastAPI
from pydantic import BaseModel
 
app = FastAPI()
 
class UserCreate(BaseModel):
    name: str
    email: str
    age: int
    tags: list[str] = []
 
class UserResponse(BaseModel):
    id: int
    name: str
    email: str
 
@app.post("/users", response_model=UserResponse)
async def create_user(user: UserCreate) -> UserResponse:
    # FastAPI根据UserCreate验证请求体
    # 并将响应序列化为匹配UserResponse
    return UserResponse(id=1, name=user.name, email=user.email)

import pandas as pd
from typing import Any
 
# 基础DataFrame类型
def clean_dataframe(df: pd.DataFrame) -> pd.DataFrame:
    return df.dropna().reset_index(drop=True)
 
# 使用pandera进行模式验证
# pip install pandera
import pandera as pa
from pandera.typing import DataFrame, Series
 
class SalesSchema(pa.DataFrameModel):
    product: Series[str]
    quantity: Series[int] = pa.Field(ge=0)
    price: Series[float] = pa.Field(gt=0)
    date: Series[pd.Timestamp]
 
@pa.check_types
def process_sales(df: DataFrame[SalesSchema]) -> DataFrame[SalesSchema]:
    """类型检查的DataFrame处理。"""
    return df[df["quantity"] > 0]

# 错误：带类型提示的可变默认值
def bad_append(item: str, items: list[str] = []) -> list[str]:
    items.append(item)  # 共享的可变默认值！
    return items
 
# 修复：使用None作为默认值
def good_append(item: str, items: list[str] | None = None) -> list[str]:
    if items is None:
        items = []
    items.append(item)
    return items

from typing import TypedDict, Callable, TypeAlias
from pathlib import Path
import csv
 
# 使用TypedDict定义数据结构
class RawRecord(TypedDict):
    name: str
    value: str
    category: str
 
class ProcessedRecord(TypedDict):
    name: str
    value: float
    category: str
    normalized: float
 
# 转换函数的TypeAlias
Transform: TypeAlias = Callable[[list[ProcessedRecord]], list[ProcessedRecord]]
 
def load_csv(path: Path) -> list[RawRecord]:
    """加载CSV数据并返回类型化输出。"""
    records: list[RawRecord] = []
    with open(path) as f:
        reader = csv.DictReader(f)
        for row in reader:
            records.append(RawRecord(
                name=row["name"],
                value=row["value"],
                category=row["category"],
            ))
    return records
 
def parse_records(raw: list[RawRecord]) -> list[ProcessedRecord]:
    """将原始字符串记录转换为类型化记录。"""
    max_value = max(float(r["value"]) for r in raw) or 1.0
    return [
        ProcessedRecord(
            name=r["name"],
            value=float(r["value"]),
            category=r["category"],
            normalized=float(r["value"]) / max_value,
        )
        for r in raw
    ]
 
def filter_by_category(
    records: list[ProcessedRecord],
    category: str
) -> list[ProcessedRecord]:
    """过滤记录，输入和输出完全类型化。"""
    return [r for r in records if r["category"] == category]
 
def apply_transforms(
    records: list[ProcessedRecord],
    transforms: list[Transform]
) -> list[ProcessedRecord]:
    """应用一系列类型化的转换函数。"""
    result = records
    for transform in transforms:
        result = transform(result)
    return result
 
# 使用
raw = load_csv(Path("data.csv"))
processed = parse_records(raw)
filtered = filter_by_category(processed, "electronics")

import pandas as pd
import pygwalker as pyg
 
# 你的类型化管道产生干净、结构化的数据
data: list[ProcessedRecord] = parse_records(raw)
df = pd.DataFrame(data)
 
# PyGWalker将其渲染为交互式可视化
walker = pyg.walk(df)