Python filter()函数的使用方法和技巧(数据筛选的精密过滤器)

原始序列: [元素1, 元素2, 元素3, ...]
    ↓ filter(过滤函数)
过滤后序列: [元素1 if 函数(元素1)==True, 元素3 if 函数(元素3)==True, ...]

filter(function, iterable)

values = [0, 1, "", "hello", None, False, [], [1,2]]
truthy = list(filter(None, values))
print(truthy)  # 输出: [1, 'hello', [1, 2]]

# 过滤出可调用的对象
items = [1, str, len, "hello", dict]
callables = list(filter(callable, items))
print(callables)  # 输出: [<class 'str'>, <built-in function len>, <class 'dict'>]

def is_positive(x):
    return x > 0
numbers = [-2, -1, 0, 1, 2]
positives = list(filter(is_positive, numbers))
print(positives)  # 输出: [1, 2]

# 过滤偶数
numbers = [1, 2, 3, 4, 5, 6]
evens = list(filter(lambda x: x % 2 == 0, numbers))
print(evens)  # 输出: [2, 4, 6]
# 过滤包含特定字符的字符串
words = ["apple", "banana", "cherry", "date"]
a_words = list(filter(lambda w: 'a' in w, words))
print(a_words)  # 输出: ['apple', 'banana', 'date']

# 过滤3-7之间的偶数
numbers = range(10)
filtered = list(filter(lambda x: x%2==0 and 3<=x<=7, numbers))
print(filtered)  # 输出: [4, 6]

# 过滤字典列表
students = [
    {"name": "Alice", "score": 85},
    {"name": "Bob", "score": 58},
    {"name": "Charlie", "score": 92}
]
passed = list(filter(lambda s: s["score"] >= 60, students))
print(passed)
# 输出: [{'name': 'Alice', 'score': 85}, {'name': 'Charlie', 'score': 92}]

from itertools import filterfalse
# 获取不满足条件的元素（filter的反向操作）
numbers = [1, 2, 3, 4, 5]
odds = list(filterfalse(lambda x: x % 2 == 0, numbers))
print(odds)  # 输出: [1, 3, 5]

# filter对象是迭代器，节省内存
big_data = range(10**6)
filtered = filter(lambda x: x % 1000 == 0, big_data)
print(next(filtered))  # 输出: 0
print(next(filtered))  # 输出: 1000

# filter版本
evens_filter = list(filter(lambda x: x%2==0, range(1000)))
# 列表推导式版本
evens_lc = [x for x in range(1000) if x%2==0]

# 使用filter更清晰
valid_emails = list(filter(lambda x: '@' in x, email_list))
# 使用列表推导式更清晰
squares = [x**2 for x in numbers if x > 0 and x%2==0]

f = filter(lambda x: x>0, [-1, 0, 1])
print(list(f))  # 输出: [1]

f = filter(lambda x: x>0, [-1, 0, 1])
list(f)  # [1]
list(f)  # []

list(filter(lambda x: x-1, [0, 1, 2]))  # 输出: [2] (因为0-1=-1→True, 1-1=0→False)

list(filter(None, []))  # 输出: []

# 清洗混合类型数据
mixed_data = [1, "a", 0, "", None, [], [1,2], {"a":1}]
cleaned = list(filter(lambda x: isinstance(x, (int, float)) and x != 0, mixed_data))
print(cleaned)  # 输出: [1]

# 过滤出文本中的长单词
with open("text.txt") as f:
    long_words = list(filter(lambda w: len(w) > 5, f.read().split()))
print(long_words)

# 过滤出有效实验数据
import math
data = [1.2, -0.5, 3.1, float('nan'), 4.8, float('inf')]
valid = list(filter(lambda x: math.isfinite(x) and x > 0, data))
print(valid)  # 输出: [1.2, 3.1, 4.8]

# 不佳做法：先转换再过滤
result = list(filter(lambda x: x>10, map(lambda x: x**2, big_data)))
# 优化做法：先过滤再转换
result = list(map(lambda x: x**2, filter(lambda x: x>3, big_data)))

# 替代filter的方案
filtered = (x for x in big_data if x % 2 == 0)

# 不佳做法：重复计算
result = filter(lambda x: x > threshold and expensive_check(x), data)
# 优化做法
result = filter(lambda x: x > threshold, data)
result = filter(expensive_check, result)