Python中collections模块的基本使用教程

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# __author__ = \'liao gao xiang\'

\"\"\"
保留最后n个元素
\"\"\"
from collections import deque


def search(file, pattern, history=5):
 previous_lines = deque(maxlen=history)
 for l in file:
 if pattern in l:
  yield l, previous_lines # 使用yield表达式的生成器函数，将搜索过程的代码和搜索结果的代码解耦
 previous_lines.append(l)


with open(b\'file.txt\', mode=\'r\', encoding=\'utf-8\') as f:
 for line, prevlines in search(f, \'Python\', 5):
 for pline in prevlines:
  print(pline, end=\'\')
 print(line, end=\'\')

d = deque()
d.append(1)
d.append(\"2\")
print(len(d))
print(d[0], d[1])
d.extendleft([0])
print(d)
d.extend([6, 7, 8])
print(d)

d2 = deque(\'12345\')
print(len(d2))
d2.popleft()
print(d2)
d2.pop()
print(d2)

# 在队列两端插入或删除元素时间复杂度都是 O(1) ，区别于列表，在列表的开头插入或删除元素的时间复杂度为 O(N)
d3 = deque(maxlen=2)
d3.append(1)
d3.append(2)
print(d3)
d3.append(3)
print(d3)

class deque( ):
 \"\"\"
 deque([iterable[, maxlen]]) --> deque  
 
 A list-like sequence optimized for data accesses near its endpoints.
 \"\"\"
 def append(self, *args, **kwargs): # real signature unknown
 \"\"\" Add an element to the right side of the deque. \"\"\"
 pass

 def appendleft(self, *args, **kwargs): # real signature unknown
 \"\"\" Add an element to the left side of the deque. \"\"\"
 pass

 def clear(self, *args, **kwargs): # real signature unknown
 \"\"\" Remove all elements from the deque. \"\"\"
 pass

 def copy(self, *args, **kwargs): # real signature unknown
 \"\"\" Return a shallow copy of a deque. \"\"\"
 pass

 def count(self, value): # real signature unknown; restored from __doc__
 \"\"\" D.count(value) -> integer -- return number of occurrences of value \"\"\"
 return 0

 def extend(self, *args, **kwargs): # real signature unknown
 \"\"\" Extend the right side of the deque with elements from the iterable \"\"\"
 pass

 def extendleft(self, *args, **kwargs): # real signature unknown
 \"\"\" Extend the left side of the deque with elements from the iterable \"\"\"
 pass

 def index(self, value, start=None, stop=None): # real signature unknown; restored from __doc__
 \"\"\"
 D.index(value, [start, [stop]]) -> integer -- return first index of value.
 Raises ValueError if the value is not present.
 \"\"\"
 return 0

 def insert(self, index, p_ ): # real signature unknown; restored from __doc__
 \"\"\" D.insert(index,  ) -- insert   before index \"\"\"
 pass

 def pop(self, *args, **kwargs): # real signature unknown
 \"\"\" Remove and return the rightmost element. \"\"\"
 pass

 def popleft(self, *args, **kwargs): # real signature unknown
 \"\"\" Remove and return the leftmost element. \"\"\"
 pass

 def remove(self, value): # real signature unknown; restored from __doc__
 \"\"\" D.remove(value) -- remove first occurrence of value. \"\"\"
 pass

 def reverse(self): # real signature unknown; restored from __doc__
 \"\"\" D.reverse() -- reverse *IN PLACE* \"\"\"
 pass

 def rotate(self, *args, **kwargs): # real signature unknown
 \"\"\" Rotate the deque n steps to the right (default n=1). If n is negative, rotates left. \"\"\"
 pass

d = {}
for key, value in pairs:
 if key not in d:
 d[key] = []
 d[key].append(value)

d = defaultdict(list)
for key, value in pairs:
 d[key].append(value)

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# __author__ = \'liao gao xiang\'

# 字典中的键映射多个值
from collections import defaultdict

d = defaultdict(list)
print(d)
d[\'a\'].append([1, 2, 3])
d[\'b\'].append(2)
d[\'c\'].append(3)

print(d)

d = defaultdict(set)
print(d)
d[\'a\'].add(1)
d[\'a\'].add(2)
d[\'b\'].add(4)

print(d)

from collections import namedtuple

websites = [
 (\'Sohu\', \'http://www.sohu.com/\', u\'张朝阳\'),
 (\'Sina\', \'http://www.sina.com.cn/\', u\'王志东\'),
 (\'163\', \'http://www.163.com/\', u\'丁磊\')
]

Website = namedtuple(\'Website\', [\'name\', \'url\', \'founder\'])

for website in websites:
 website = Website._make(website)
 print website


# 输出结果:
Website(name=\'Sohu\', url=\'http://www.sohu.com/\', founder=u\'\\u5f20\\u671d\\u9633\')
Website(name=\'Sina\', url=\'http://www.sina.com.cn/\', founder=u\'\\u738b\\u5fd7\\u4e1c\')
Website(name=\'163\', url=\'http://www.163.com/\', founder=u\'\\u4e01\\u78ca\')

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# __author__ = \'liao gao xiang\'

from collections import 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\'
]

word_counts = Counter(words)

# 出现频率最高的三个单词
top_three = word_counts.most_common(3)
print(top_three)
# Outputs [(\'eyes\', 8), (\'the\', 5), (\'look\', 4)]
print(word_counts[\'eyes\'])

morewords = [\'why\', \'are\', \'you\', \'not\', \'looking\', \'in\', \'my\', \'eyes\']

# 如果你想手动增加计数，可以简单的用加法：
for word in morewords:
 print(word)
 word_counts[word] += 1
print(word_counts[\'eyes\'])

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# __author__ = \'liao gao xiang\'

from collections import OrderedDict

d = OrderedDict()
d[\'foo\'] = 1
d[\'bar\'] = 2
d[\'spam\'] = 3
d[\'grok\'] = 4
# d[\'bar\'] = 22 #对于一个已经存在的键，重复赋值不会改变键的顺序
for key in d:
 print(key, d[key])

print(d)

import json

print(json.dumps(d))

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# __author__ = \'liao gao xiang\'

from collections import ChainMap
from itertools import chain

# 不同集合上元素的迭代
a = [1, 2, 3, 4]
b = (\'x\', \'y\', \'z\')
c = {1, \'a\'}

# 方法一，使用chain
for i in chain(a, b, c):
 print(i)
print(\'--------------\')
# 方法二，使用chainmap
for j in ChainMap(a, b, c):
 print(j)

# 这两种均为节省内存，效率更高的迭代方式

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# __author__ = \'liao gao xiang\'

# 合并多个字典和映射
a = {\'x\': 1, \'z\': 3}
b = {\'y\': 2, \'z\': 4}
# 现在假设你必须在两个字典中执行查找操作
# (比如先从 a 中找，如果找不到再在 b 中找)。
# 一个非常简单的解决方案就是使用collections模块中的ChainMap类
from collections import ChainMap

c = ChainMap(a, b)

print(c)
a[\'x\'] = 11 # 使用ChainMap时，原字典做了更新，这种更新会合并到新的字典中去

print(c) # 按顺序合并两个字典
print(c[\'x\'])
print(c[\'y\'])
print(c[\'z\'])

# 对于字典的更新或删除操作影响的总是列中的第一个字典。
c[\'z\'] = 10
c[\'w\'] = 40
del c[\'x\']
print(a)
# del c[\'y\']将出现报错

# ChainMap对于编程语言中的作用范围变量（比如globals,locals等）
# 是非常有用的。事实上，有一些方法可以使它变得简单：
values = ChainMap() # 默认会创建一个空字典
print(\'\\t\', values)
values[\'x\'] = 1
values = values.new_child() # 添加一个空字典
values[\'x\'] = 2
values = values.new_child()
values[\'x\'] = 30
# values = values.new_child()
print(values, values[\'x\']) # values[\'x\']输出最后一次添加的值
values = values.parents # 删除上一次添加的字典
print(values[\'x\'])
values = values.parents
print(values)

a = {\'x\': 1, \'y\': 2}
b = {\'y\': 2, \'z\': 3}
merge = dict(b)
merge.update(a)
print(merge[\'x\'], merge[\'y\'], merge[\'z\'])
a[\'x\'] = 11
print(merge[\'x\'])