python cookbook学习笔记 -- DAY02

找出一个序列中出现次数最多的元素

代码片段

def countTest():
    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'
        ]
    print(Counter(words)) # Counter({'eyes': 8, 'the': 5, 'look': 4, 'into': 3, 'my': 3, 'around': 2, 'not': 1, "don't": 1, "you're": 1, 'under': 1})
    wordsCount = Counter(words)
    print("update:",wordsCount.update(words))
    print(wordsCount.most_common(3))
    print(wordsCount['eyes']) # 8

对象列表排序

代码片段

def dictListSorted():
    # 对象列表排序
    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}
        ]
    #[{'fname': 'Big', 'lname': 'Jones', 'uid': 1004}, 
    # {'fname': 'Brian', 'lname': 'Jones', 'uid': 1003}, 
    # {'fname': 'David', 'lname': 'Beazley', 'uid': 1002}, 
    # {'fname': 'John', 'lname': 'Cleese', 'uid': 1001}]
    print(sorted(rows,key = itemgetter('fname')))
    print(sorted(rows,key = lambda r:r['fname']))
    # [{'fname': 'John', 'lname': 'Cleese', 'uid': 1001}, 
    # {'fname': 'David', 'lname': 'Beazley', 'uid': 1002}, 
    # {'fname': 'Brian', 'lname': 'Jones', 'uid': 1003}, 
    # {'fname': 'Big', 'lname': 'Jones', 'uid': 1004}]
    print(sorted(rows,key = itemgetter('uid')))
    print(sorted(rows,key = lambda r:r['uid']))
    # [{'fname': 'Big', 'lname': 'Jones', 'uid': 1004},
    # {'fname': 'Brian', 'lname': 'Jones', 'uid': 1003},
    # {'fname': 'David', 'lname': 'Beazley', 'uid': 1002},
    # {'fname': 'John', 'lname': 'Cleese', 'uid': 1001}]
    print(sorted(rows,key = itemgetter('fname','uid')))
    print("min:",min(rows,key=itemgetter('fname'))) # min: {'fname': 'Big', 'lname': 'Jones', 'uid': 1004}
    print("max:",max(rows,key=itemgetter('uid'))) # max: {'fname': 'Big', 'lname': 'Jones', 'uid': 1004}

排序不支持比较的对象列表

代码片段

class User:
    def __init__(self,user_id):
        self.user_id = user_id
        
    def __repr__(self):
        return 'User({})'.format(self.user_id) # 重写比较方法
        
def sortNotCompare():
    users = [User(30),User(25),User(18)]
    print(users) # [User(30), User(25), User(18)]
    print(sorted(users,key = lambda u :u.user_id)) # [User(18), User(25), User(30)]
    print(sorted(users,key=attrgetter('user_id'))) # [User(18), User(25), User(30)]
    print(sorted(users,key=lambda k:k.user_id)) # [User(18), User(25), User(30)]
    print(min(users,key = attrgetter('user_id'))) # User(18)
    print(max(users,key= lambda k :k.user_id)) # User(30)

通过某个字段将记录分组

代码片段

def groupbyTest():
    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'},
        ]
    rows.sort(key = itemgetter('date')) # 先排序 sort直接操作了元数据

    for date,item in groupby(rows,key=itemgetter('date')):
        print(date)
        for i in item:
            print("",i)

可迭代对象筛选

def filterLogic(val): 
    if val>0: # 过滤器
        return True
    else:
        return False

def filterList():
    nums = [1,2,3,4,-4,8,-7,12,4,-9]
    filterList = [i for i in nums if i>0] # 内存占用较大
    print(filterList) # [1, 2, 3, 4, 8, 12, 4]
    filterList = filter(filterLogic,nums) # 过滤器，可迭代对象
    print(list(filterList)) # [1, 2, 3, 4, 8, 12, 4]


def compressList():
    addresses = [
        '5412 N CLARK',
        '5148 N CLARK',
        '5800 E 58TH',
        '2122 N CLARK',
        '5645 N RAVENSWOOD',
        '1060 W ADDISON',
        '4801 N BROADWAY',
        '1039 W GRANVILLE',
    ]
    counts = [ 0, 3, 10, 4, 1, 7, 6, 1]
    resultList = [n>5 for n in counts]

    # 这里的关键点在于先创建一个Boolean 序列，指示哪些元素复合条件。然后
    # compress() 函数根据这个序列去选择输出对应位置为True 的元素
    print(list(compress(addresses,resultList))) 

字典过滤

代码片段

def filterDict():
    prices = {
        'ACME': 45.23,
        'AAPL': 612.78,
        'IBM': 205.55,
        'HPQ': 37.20,
        'FB': 10.75
    }
    filterDic = {key:value for key,value in prices.items() if value>100}
    print(filterDic) # {'AAPL': 612.78, 'IBM': 205.55}
    tech_names = {'AAPL', 'IBM', 'HPQ', 'MSFT'}
    filterDic = {key: value for key, value in prices.items() if key in tech_names}
    print(filterDic) # {'AAPL': 612.78, 'IBM': 205.55, 'HPQ': 37.2}