Python推导式实战之一行代码实现复杂数据转换

squares = [x**2 for x in range(10) if x % 2 == 0]
print(squares)  # [0, 4, 16, 36, 64]

# 传统方式
squares = []
for x in range(10):
    if x % 2 == 0:
        squares.append(x**2)

{key_expr: value_expr for item in iterable if condition}

text = "hello"
char_positions = {char: idx for idx, char in enumerate(text)}
print(char_positions)  # {'h': 0, 'e': 1, 'l': 2, 'l': 3, 'o': 4}

unique_chars = {char.upper() for char in "hello world"}
print(unique_chars)  # {'H', 'E', 'L', 'O', 'W', 'R', 'D'}

users = [
    {"name": "Alice", "age": 25, "active": True},
    {"name": "Bob", "age": 30, "active": False},
    {"name": "Charlie", "age": 35, "active": True},
    {"name": "Diana", "age": 28, "active": True},
]

active_names_upper = [u["name"].upper() for u in users if u["active"] and u["age"] > 26]
print(active_names_upper)  # ['CHARLIE', 'DIANA']

scores = [
    ["Alice", 85, 90, 78],
    ["Bob", 92, 88, 95],
    ["Charlie", 76, 82, 79],
    ["Diana", 90, 94, 87],
]

avg_scores = sorted(
    [(name, sum(score_list[1:]) / len(score_list[1:])) for name, *scores in scores],
    key=lambda x: x[1], reverse=True
)
print(avg_scores)
# [('Diana', 90.33333333333333), ('Bob', 91.66666666666667), ('Alice', 84.33333333333333), ('Charlie', 79.0)]

matrix = [
    [1, 2, 3],
    [4, 5, 6],
    [7, 8, 9]
]

multiplied = [[x * 2 for x in row] for row in matrix]
print(multiplied)
# [[2, 4, 6], [8, 10, 12], [14, 16, 18]]

log_lines = [
    "INFO: User login successful - user=john, ip=192.168.1.1, time=2024-04-05T10:30:00",
    "ERROR: Database connection failed - user=alice, ip=10.0.0.5, time=2024-04-05T10:31:00",
    "WARNING: High memory usage - user=bob, ip=192.168.1.2, time=2024-04-05T10:32:00",
    "INFO: File uploaded - user=charlie, ip=10.0.0.3, time=2024-04-05T10:33:00",
]

error_users = [
    {"user": parts[0].split("=")[1], "ip": parts[1].split("=")[1]}
    for line in log_lines
    if line.startswith("ERROR")
    for parts in [line.split(" - ")[1:]]  # 拆分出 user=xxx, ip=xxx
    for part in parts
    if "=" in part
]

print(error_users)
# [{'user': 'alice', 'ip': '10.0.0.5'}]

names = ["alice", "bob", "charlie", "d", "eve"]

emails = [f"{name}@example.com" for name in names if len(name) >= 3]
print(emails)
# ['alice@example.com', 'charlie@example.com', 'eve@example.com']

email_status = {
    f"{name}@example.com": "valid" if len(name) >= 3 else "invalid"
    for name in names
}

print(email_status)
# {
#   'alice@example.com': 'valid',
#   'bob@example.com': 'invalid',
#   'charlie@example.com': 'valid',
#   'd@example.com': 'invalid',
#   'eve@example.com': 'valid'
# }

grades = [85, 92, 76, 98, 65, 88]

grade_labels = [
    "A" if score >= 90 else "B" if score >= 80 else "C" if score >= 70 else "F"
    for score in grades
]

print(grade_labels)  # ['B', 'A', 'C', 'A', 'F', 'B']

def format_name(name):
    return name.strip().title()

names = [" alice ", "bob", " CHARLIE "]

formatted = [format_name(n) for n in names]
print(formatted)  # ['Alice', 'Bob', 'Charlie']

import time

# 测试数据
data = list(range(100000))

# 方法1：推导式
start = time.time()
result1 = [x * 2 + 1 for x in data]
time1 = time.time() - start

# 方法2：传统循环
start = time.time()
result2 = []
for x in data:
    result2.append(x * 2 + 1)
time2 = time.time() - start

print(f"推导式耗时: {time1:.6f} 秒")
print(f"循环耗时: {time2:.6f} 秒")

# 不推荐：过于复杂
result = [x for x in [y for y in [z for z in range(10)] if z % 2 == 0] if x > 5]

# 推荐写法
even_nums = [x for x in range(10) if x % 2 == 0]
filtered_nums = [x for x in even_nums if x > 5]

# 错误：即使没有条件，也应考虑是否必要
[expensive_function(x) for x in data]  # 若 exp_func 很慢，会拖垮性能

[expensive_function(x) for x in data if x > 100]

# 危险！不要这样做
[print(x) for x in range(5)]  # 返回 [None, None, ...]，毫无意义

gen = (x**2 for x in range(10) if x % 2 == 0)
print(gen)  # <generator object <genexpr> at 0x...>

with open("large_file.txt") as f:
    lines = (line.strip() for line in f if line.strip())
    # 逐行处理，不加载整文件到内存

from functools import reduce

# 传统函数式
numbers = [1, 2, 3, 4, 5]
total = reduce(lambda a, b: a + b, filter(lambda x: x % 2 == 0, map(lambda x: x * 2, numbers)))

# 推导式等价写法
total = sum([x * 2 for x in numbers if x % 2 == 0])