@2 Python 数据结构与算法

Python 有序字典

from collections import OrderedDict
 
d = OrderedDict()
d['foo'] = 1
d['bar'] = 2
d['spam'] = 3

OrderedDict  内部维护着一个根据键插入顺序排序的双向链表。每次当一个新的元素插入进来的时候，它会被放到链表的尾部。对于一个已经存在的键的重复赋值不会改变键的顺序。

非重复 & 保序的迭代器

def dedupe(items):
    seen = set()
    for item in items:
        if item not in seen:
            yield item
            seen.add(item)
 
>>> a = [1, 5, 2, 1, 9, 1, 5, 10]
>>> list(dedupe(a))
[1, 5, 2, 9, 10]
>>>

Python 切片

1.11 命名切片 — python3-cookbook 3.0.0 文档

Python Counter

words = [
    'look', 'into', 'my', 'eyes', 'look', 'into', 'my', 'eyes',
    'the', 'eyes', 'the', 'eyes', 'the', 'eyes', 'not', 'around', 'the',
    'eyes', "don't", 'look', 'around', 'the', 'eyes', 'look', 'into',
    'my', 'eyes', "you're", 'under'
]
from collections import Counter
word_counts = Counter(words)
# 出现频率最高的3个单词
top_three = word_counts.most_common(3)
print(top_three)
# Outputs [('eyes', 8), ('the', 5), ('look', 4)]
 
>>> word_counts['not']
1
>>> word_counts['eyes']
8
>>> word_counts.update(morewords)
>>> a = Counter(words)
>>> b = Counter(morewords)
>>> a
Counter({'eyes': 8, 'the': 5, 'look': 4, 'into': 3, 'my': 3, 'around': 2,
"you're": 1, "don't": 1, 'under': 1, 'not': 1})
>>> b
Counter({'eyes': 1, 'looking': 1, 'are': 1, 'in': 1, 'not': 1, 'you': 1,
'my': 1, 'why': 1})
>>> # Combine counts
>>> c = a + b
>>> c
Counter({'eyes': 9, 'the': 5, 'look': 4, 'my': 4, 'into': 3, 'not': 2,
'around': 2, "you're": 1, "don't": 1, 'in': 1, 'why': 1,
'looking': 1, 'are': 1, 'under': 1, 'you': 1})
>>> # Subtract counts
>>> d = a - b
>>> d
Counter({'eyes': 7, 'the': 5, 'look': 4, 'into': 3, 'my': 2, 'around': 2,
"you're": 1, "don't": 1, 'under': 1})
>>>

Python 通过关键字排序字典

rows = [
    {'fname': 'Brian', 'lname': 'Jones', 'uid': 1003},
    {'fname': 'David', 'lname': 'Beazley', 'uid': 1002},
    {'fname': 'John', 'lname': 'Cleese', 'uid': 1001},
    {'fname': 'Big', 'lname': 'Jones', 'uid': 1004}
]
 
from operator import itemgetter
rows_by_fname = sorted(rows, key=itemgetter('fname'))
print(rows_by_fname)
# [{'fname': 'Big', 'uid': 1004, 'lname': 'Jones'},
# {'fname': 'Brian', 'uid': 1003, 'lname': 'Jones'},
# {'fname': 'David', 'uid': 1002, 'lname': 'Beazley'},
# {'fname': 'John', 'uid': 1001, 'lname': 'Cleese'}]
 
rows_by_lfname = sorted(rows, key=itemgetter('lname','fname'))