Python CookBook总结
保留最后N 个元素
使用deque(maxlen=N) 构造函数会新建一个固定大小的队列。当新的元素加入并且这个队列已满的时候，最老的元素会自动被移除掉。
from collections import deque
def search(lines, pattern, history=5):
previous_lines = deque(maxlen=history)
for li in lines:
if pattern in li:
yield li, previous_lines
previous_lines.append(li)
怎样从一个集合中获得最大或者最小的N 个元素列表？
import heapq
nums = [1, 8, 2, 23, 7, -4, 18, 23, 42, 37, 2]
print(heapq.nlargest(3, nums)) # Prints [42, 37, 23]
print(heapq.nsmallest(3, nums)) # Prints [-4, 1, 2]
portfolio = [
{'name': 'IBM', 'shares': 100, 'price': 91.1},
{'name': 'AAPL', 'shares': 50, 'price': 543.22},
{'name': 'FB', 'shares': 200, 'price': 21.09},
{'name': 'HPQ', 'shares': 35, 'price': 31.75},
{'name': 'YHOO', 'shares': 45, 'price': 16.35},
{'name': 'ACME', 'shares': 75, 'price': 115.65}
]
cheap = heapq.nsmallest(3, portfolio, key=lambda s: s['price'])
expensive = heapq.nlargest(3, portfolio, key=lambda s: s['price'])
怎样实现一个键对应多个值的字典(也叫multidict )？
from collections import defaultdict
d = defaultdict(list)
d['a'].append(1)
d['a'].append(2)
d['b'].append(4)
d = defaultdict(set)
d['a'].add(1)
d['a'].add(2)
d['b'].add(4)
d = defaultdict(list)
for key, value in pairs:
d[key].append(value)
字典排序，你想创建一个字典，并且在迭代或序列化这个字典的时候能够控制元素的顺序。
from collections import OrderedDict
def ordered_dict():
d = OrderedDict()
d['foo'] = 1
d['bar'] = 2
d['spam'] = 3
d['grok'] = 4
# Outputs "foo 1", "bar 2", "spam 3", "grok 4"
for key in d:
print(key, d[key])
字典运算，怎样在数据字典中执行一些计算操作(比如求最小值、最大值、排序等等)？
prices = {
'ACME': 45.23,
'AAPL': 612.78,
'IBM': 205.55,
'HPQ': 37.20,
'FB': 10.75
}
#为了对字典值执行计算操作，通常需要使用zip() 函数先将键和值
#反转过来。比如，下面是查找最小和最大股票价格和股票值的代码：
min_price = min(zip(prices.values(), prices.keys()))
# min_price is (10.75, 'FB')
max_price = max(zip(prices.values(), prices.keys()))
# max_price is (612.78, 'AAPL')
prices_sorted = sorted(zip(prices.values(), prices.keys()))
# prices_sorted is [(10.75, 'FB'), (37.2, 'HPQ'),
# (45.23, 'ACME'), (205.55, 'IBM'),
# (612.78, 'AAPL')]
#注意:zip() 函数创建的是一个只能访问一次的迭代器
查找两字典的相同点
#python2.7需将列表加上set()转为集合
a = {'x' : 1,'y' : 2,'z' : 3}
b = {'w' : 10,'x' : 11,'y' : 2}
# Find keys in common
a.keys() & b.keys() # { 'x', 'y' }
# Find keys in a that are not in b
a.keys() - b.keys() # { 'z' }
# Find (key,value) pairs in common
a.items() & b.items() # { ('y', 2) }
#这些操作也可以用于修改或者过滤字典元素。比如，假如你
#想以现有字典构造一个排除几个指定键的新字典。下面利用字典推导来实现这样的需求：
# Make a new dictionary with certain keys removed
c = {key:a[key] for key in a.keys() - {'z', 'w'}}
# c is {'x': 1, 'y': 2}
命名切片
#内置的slice() 函数创建了一个切片对象
>>> a = slice(5, 50, 2)
>>> a.start
5
>>> a.stop
50
>>> a.step
2
record = '....................100 .......513.25 ..........'
SHARES = slice(20, 23)
PRICE = slice(31, 37)
cost = int(record[SHARES]) * float(record[PRICE])
#你还能通过调用切片的indices(size) 方法将它映射到一个确定大小的序
#列上，这个方法返回一个三元组(start, stop, step) ，所有值都会
#被合适的缩小以满足边界限制，从而使用的时候避免出现IndexError 异常
>>> s = 'HelloWorld'
>>> a.indices(len(s))
(5, 10, 2)
>>> for i in range(*a.indices(len(s))):
... print(s[i])
序列中出现次数最多的元素
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)]
#Counter 实例一个鲜为人知的特性是它们可以很容易的跟数学运算操作相结合。比如：
>>> 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})
>>>
通过某个关键字排序一个字典列表
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'))
rows_by_uid = sorted(rows, key=itemgetter('uid'))
print(rows_by_fname)
print(rows_by_uid)
#itemgetter() 有时候也可以用lambda 表达式代替
rows_by_fname = sorted(rows, key=lambda r: r['fname'])
rows_by_lfname = sorted(rows, key=lambda r: (r['lname'],r['fname']))
>>> min(rows, key=itemgetter('uid'))
{'fname': 'John', 'lname': 'Cleese', 'uid': 1001}
>>> max(rows, key=itemgetter('uid'))
{'fname': 'Big', 'lname': 'Jones', 'uid': 1004}
>>>
通过某个字段将记录分组
你有一个字典或者实例的序列，然后你想根据某个特定的字段比如date 来分组迭代访问。
#itertools.groupby() 函数对于这样的数据分组操作非常实用
rows = [
{'address': '5412 N CLARK', 'date': '07/01/2012'},
{'address': '5148 N CLARK', 'date': '07/04/2012'},
{'address': '5800 E 58TH', 'date': '07/02/2012'},
{'address': '2122 N CLARK', 'date': '07/03/2012'},
{'address': '5645 N RAVENSWOOD', 'date': '07/02/2012'},
{'address': '1060 W ADDISON', 'date': '07/02/2012'},
{'address': '4801 N BROADWAY', 'date': '07/01/2012'},
{'address': '1039 W GRANVILLE', 'date': '07/04/2012'},
]
from operator import itemgetter
from itertools import groupby
# Sort by the desired field first
rows.sort(key=itemgetter('date'))
# Iterate in groups
for date, items in groupby(rows, key=itemgetter('date')):
print(date)
for i in items:
print(' ', i)
运行结果：
07/01/2012
{'date': '07/01/2012', 'address': '5412 N CLARK'}
{'date': '07/01/2012', 'address': '4801 N BROADWAY'}
07/02/2012
{'date': '07/02/2012', 'address': '5800 E 58TH'}
{'date': '07/02/2012', 'address': '5645 N RAVENSWOOD'}
{'date': '07/02/2012', 'address': '1060 W ADDISON'}
07/03/2012
{'date': '07/03/2012', 'address': '2122 N CLARK'}
07/04/2012
{'date': '07/04/2012', 'address': '5148 N CLARK'}
{'date': '07/04/2012', 'address': '1039 W GRANVILLE'}
过滤序列元素
#最简单的过滤序列元素的方法就是使用列表推导。比如：
>>> mylist = [1, 4, -5, 10, -7, 2, 3, -1]
>>> [n for n in mylist if n > 0]
[1, 4, 10, 2, 3]
>>> [n for n in mylist if n < 0]
[-5, -7, -1]
>>>
#使用列表推导的一个潜在缺陷就是如果输入非常大的时候会产生一个非常大的结果集，占用大量内存。如果你对内存比较敏感，那么你可以使生成器表达式迭代产生过滤的元素。比如：
>>> pos = (n for n in mylist if n > 0)
>>> pos
at 0x1006a0eb0>
>>> for x in pos:
... print(x)
...
14
10
23
>>>
#filter函数
values = ['1', '2', '-3', '-', '4', 'N/A', '5']
def is_int(val):
try:
x = int(val)
return True
except ValueError:
return False
ivals = list(filter(is_int, values))
print(ivals)
# Outputs ['1', '2', '-3', '4', '5']
从字典中提取子集
prices = {
'ACME': 45.23,
'AAPL': 612.78,
'IBM': 205.55,
'HPQ': 37.20,
'FB': 10.75
}#
Make a dictionary of all prices over 200
p1 = {key: value for key, value in prices.items() if value > 200}
# Make a dictionary of tech stocks
tech_names = {'AAPL', 'IBM', 'HPQ', 'MSFT'}
p2 = {key: value for key, value in prices.items() if key in tech_names}
映射名称到序列元素
>>> from collections import namedtuple
>>> Subscriber = namedtuple('Subscriber', ['addr', 'joined'])
>>> sub = Subscriber('[email protected]', '2012-10-19')
>>> sub
Subscriber(addr='[email protected]', joined='2012-10-19')
>>> sub.addr
'[email protected]'
>>> sub.joined
'2012-10-19'
>>>
转换并同时计算数据,一个非常优雅的方式去结合数据计算与转换就是使用一个生成器表达式参数
nums = [1, 2, 3, 4, 5]
s = sum(x * x for x in nums)
# Determine if any .py files exist in a directory
import os
files = os.listdir('dirname')
if any(name.endswith('.py') for name in files):
print('There be python!')
else:
print('Sorry, no python.')
# Output a tuple as CSV
s = ('ACME', 50, 123.45)
print(','.join(str(x) for x in s))
# Data reduction across fields of a data structure
portfolio = [
{'name':'GOOG', 'shares': 50},
{'name':'YHOO', 'shares': 75},
{'name':'AOL', 'shares': 20},
{'name':'SCOX', 'shares': 65}
]
min_shares = min(s['shares'] for s in portfolio)
合并多个字典或映射
a = {'x': 1, 'z': 3 }
b = {'y': 2, 'z': 4 }
from collections import ChainMap
c = ChainMap(a,b)
print(c['x']) # Outputs 1 (from a)
print(c['y']) # Outputs 2 (from b)
print(c['z']) # Outputs 3 (from a)