Python3-cookbook- 笔记1 - 数据结构和算法-白红宇

元祖或者数组赋值

data = [ 'ACME', 50, 91.1, (2012, 12, 21) ]name , shares , price , (year,month,day) = dataprint(name , shares , price ,year,month,day)# ACME 50 91.1 2012 12 21复制代码

查找最大或者最小的N个元素

import heapqnums = [1, 8, 2, 23, 7, -4, 18, 23, 42, 37, 2]print(heapq.nlargest(3,nums)) # [42, 37, 23] print(heapq.nsmallest(3,nums)) # [-4, 1, 2]# 两个函数都能接受一个关键字参数，用于更复杂的数据结构中：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'])print(cheap)print(expensive)# [{'name': 'YHOO', 'shares': 45, 'price': 16.35}, {'name': 'FB', 'shares': 200, 'price': 21.09}, {'name': 'HPQ', 'shares': 35, 'price': 31.75}]# [{'name': 'AAPL', 'shares': 50, 'price': 543.22}, {'name': 'ACME', 'shares': 75, 'price': 115.65}, {'name': 'IBM', 'shares': 100, 'price': 91.1}]复制代码

下面的类利用 heapq 模块实现了一个简单的优先级队列

class PriorityQueue:	def __init__(self):		self._queue = []		self._index = 0	def push(self,item,priority):		heapq.heappush(self._queue,(-priority,self._index,item))		self._index += 1	def pop(self):		return heapq.heappop(self._queue)[-1]	def __len__(self):		return len(self._queue)	def pop_last(self,last):		return heapq.heappop(self._queue)[-last]class Item:	def __init__(self,name):		self.name = name	def __repr__(self):		return 'Item({!r})'.format(self.name)# 使用q = PriorityQueue()q.push(Item('foo'),1)q.push(Item('bar'),5)q.push(Item('spam'),4)q.push(Item('grok'),1)print(q.pop())print(q.pop())print(q.pop())print(q.pop())# Item('bar')# Item('spam')# Item('foo')# Item('grok')复制代码

字典排序

from collections import OrderedDictd = OrderedDict()d['a'] = 1d['b'] = 2d['c'] = 3for k in d:	print(k , d[k])# a 1# b 2# c 3复制代码

字典的运算

通常需要使用 zip() 函数先将键和值反转过来

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')]复制代码

命名切片

如果你的程序包含了大量无法直视的硬编码切片

record = '....................100 .......513.25 ..........'cost = int(record[20:23]) * float(record[31:37])SHARES = slice(20, 23)PRICE = slice(31, 37)cost = int(record[SHARES]) * float(record[PRICE])复制代码

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 Counterword_counts = Counter(words)# 出现频率最高的3个单词top_three = word_counts.most_common(3)print(top_three)# [('eyes', 8), ('the', 5), ('look', 4)]复制代码

通过某个关键字排序一个字典列表

from operator import itemgetterrows = [    {
   'fname': 'Brian', 'lname': 'Jones', 'uid': 1003},    {
   'fname': 'David', 'lname': 'Beazley', 'uid': 1002},    {
   'fname': 'John', 'lname': 'Cleese', 'uid': 1001},    {
   'fname': 'Big', 'lname': 'Jones', 'uid': 1004}]rows_by_fname = sorted(rows, key=itemgetter('fname'))rows_by_uid = sorted(rows, key=itemgetter('uid'))print(rows_by_fname)print(rows_by_uid)# [{'lname': 'Jones', 'uid': 1004, 'fname': 'Big'}, {'lname': 'Jones', 'uid': 1003, 'fname': 'Brian'}, {'lname': 'Beazley', 'uid': 1002, 'fname': 'David'}, {'lname': 'Cleese', 'uid': 1001, 'fname': 'John'}]# [{'lname': 'Cleese', 'uid': 1001, 'fname': 'John'}, {'lname': 'Beazley', 'uid': 1002, 'fname': 'David'}, {'lname': 'Jones', 'uid': 1003, 'fname': 'Brian'}, {'lname': 'Jones', 'uid': 1004, 'fname': 'Big'}]# itemgetter() 函数也支持多个 keys，比如下面的代码rows_by_lfname = sorted(rows, key=itemgetter('lname','fname'))print(rows_by_lfname)# [{'lname': 'Beazley', 'fname': 'David', 'uid': 1002}, {'lname': 'Cleese', 'fname': 'John', 'uid': 1001}, {'lname': 'Jones', 'fname': 'Big', 'uid': 1004}, {'lname': 'Jones', 'fname': 'Brian', 'uid': 1003}]复制代码

排序不支持原生比较的对象

from operator import attrgetterclass User:    def __init__(self, user_id):        self.user_id = user_id    def __repr__(self):        return 'User({})'.format(self.user_id)users = [User(23), User(3), User(99)]sorted(users, key=attrgetter('user_id'))复制代码

通过某个字段将记录分组

from operator import itemgetterfrom itertools import groupbyrows = [    {
   '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'},]# 现在假设你想在按 date 分组后的数据块上进行迭代。为了这样做，你首先需要按照指定的字段(这里就是 date )排序， 然后调用 itertools.groupby() 函数：# Sort by the desired field firstrows.sort(key=itemgetter('date'))for date, items in groupby(rows, key=itemgetter('date')):    print(date)    for i in items:        print(' ', i)# 07/01/2012#   {'address': '5412 N CLARK', 'date': '07/01/2012'}#   {'address': '4801 N BROADWAY', 'date': '07/01/2012'}# 07/02/2012#   {'address': '5800 E 58TH', 'date': '07/02/2012'}#   {'address': '5645 N RAVENSWOOD', 'date': '07/02/2012'}#   {'address': '1060 W ADDISON', 'date': '07/02/2012'}# 07/03/2012#   {'address': '2122 N CLARK', 'date': '07/03/2012'}# 07/04/2012#   {'address': '5148 N CLARK', 'date': '07/04/2012'}#   {'address': '1039 W GRANVILLE', 'date': '07/04/2012'}复制代码

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 200p1 = {key: value for key, value in prices.items() if value > 200}# Make a dictionary of tech stockstech_names = {
   'AAPL', 'IBM', 'HPQ', 'MSFT'}p2 = {key: value for key, value in prices.items() if key in tech_names}复制代码

映射名称到序列元素

from collections import namedtupleSubscriber = namedtuple('Subscriber', ['addr', 'joined'])sub = Subscriber('jonesy@example.com', '2012-10-19')print(sub.addr)print(sub.joined)复制代码