3.1字典，集合，异常，函数，文件

#字典：键值对

#创建字典
empty_dict = {}
d1 = {'a':'some value','b':[1,2,3,4]}
d1

{'a': 'some value', 'b': [1, 2, 3, 4]}

#访问，插入，设定字典元素
d1[7] = 'an integer'
d1

{'a': 'some value', 'b': [1, 2, 3, 4], 7: 'an integer'}

d1['b'] 

[1, 2, 3, 4]

'b' in d1

True

d1[5] = 'some value'
d1

{'a': 'some value', 'b': [1, 2, 3, 4], 7: 'an integer', 5: 'some value'}

d1['dummy'] = 'another value'
d1

{'a': 'some value',
 'b': [1, 2, 3, 4],
 7: 'an integer',
 5: 'some value',
 'dummy': 'another value'}

del d1[5]
d1

{'a': 'some value',
 'b': [1, 2, 3, 4],
 7: 'an integer',
 'dummy': 'another value'}

ret = d1.pop('dummy')
ret

'another value'

list(d1.keys())

['a', 'b', 7]

list(d1.values())

['some value', [1, 2, 3, 4], 'an integer']

d1.update({'b':'foo','c':12})
d1

{'a': 'some value', 'b': 'foo', 7: 'an integer', 'c': 12}

#用序列创建字典
mapping = dict(zip(range(5),reversed(range(5))))
mapping

{0: 4, 1: 3, 2: 2, 3: 1, 4: 0}

#默认值
words = ['apple','bat','bar','atom','book']
by_letter = {}
for word in words:
    letter = word[0]
    if letter not in by_letter:
        by_letter[letter] = [word]
    else:
        by_letter[letter].append(word)
by_letter

{'a': ['apple', 'atom'], 'b': ['bat', 'bar', 'book']}

for word in words:
    letter = word[0]
    by_letter.setdefault(letter,[]).append(word)
by_letter

{'a': ['apple', 'atom', 'apple', 'atom', 'apple', 'atom'],
 'b': ['bat', 'bar', 'book', 'bat', 'bar', 'book', 'bat', 'bar', 'book']}

#有效的键类型
hash('string')#可哈希

-5063368329735123182

#集合
set([2,1,2,3,4,1])

{1, 2, 3, 4}

{2,1,1,2,3,4}

{1, 2, 3, 4}

a = {1,2,3,4,5}
b = {3,4,5,6,7}
a.union(b)

{1, 2, 3, 4, 5, 6, 7}

a|b

{1, 2, 3, 4, 5, 6, 7}

a.intersection(b)

{3, 4, 5}

a&b

{3, 4, 5}

#列表，集合和字典推导式
string = ['a','as','bat','car','dove','python']
[x.upper()for x in string if len(x)>2]

['BAT', 'CAR', 'DOVE', 'PYTHON']

#dict_comp = {key-expr : value-expr for value in collection if condition}
unique_lengths = {len(x)for x in string}
unique_lengths

{1, 2, 3, 4, 6}

loc_mapping = {val:index for index,val in enumerate(string)}
loc_mapping

{'a': 0, 'as': 1, 'bat': 2, 'car': 3, 'dove': 4, 'python': 5}

#嵌套列表推导式
all_data = [['John','Emily','Michael','Mary','Steven'],['Maria','Juan','Javier','Natalia','Pilar']]
result = [name for names in all_data for name in names
         if name.count('e')>=2]
result

['Steven']

some_tuples = [(1,2,3),(4,5,6),(7,8,9)]
flatted = [x for tup in some_tuples for x in tup]
flatted

[1, 2, 3, 4, 5, 6, 7, 8, 9]

#函数
#变量的命名空间，作用域，局部函数
#返回多个值
#函数也是对象

states = ['   Alabama ', 'Georgia!', 'Georgia', 'georgia', 'FlOrIda',
          'south   carolina##', 'West virginia?']

import re
def remove_punctuation(value):
    return re.sub('[!#?]','',value)
clean_ops = [str.strip,remove_punctuation,str.title]
def clean_string(strings,ops):
    result = []
    for value in strings:
        for function in ops:
            value = function(value)
        result.append(value)
    return result
clean_string(states,clean_ops)

['Alabama',
 'Georgia',
 'Georgia',
 'Georgia',
 'Florida',
 'South   Carolina',
 'West Virginia']

#匿名函数lambda
equiv_anon = lambda x:x*2
def apply_to_list(some_list,f):
    return [f(x) for x in some_list]
ints = [2,3,3,4,2,1]
apply_to_list(ints,lambda x:x*2)

[4, 6, 6, 8, 4, 2]

string =  ['foo', 'card', 'bar', 'aaaa', 'abab']
string.sort(key=lambda x:len(set(list(x))))
string

['aaaa', 'foo', 'abab', 'bar', 'card']

#柯里化：部分参数应用
def add_number(x,y):
    return x+y
add_five = lambda y:add_number(5,y)

#迭代器
some_dict = {'a':1,'b':2,'c':3}
for key in some_dict:
    print(key)

a
b
c

dict_iterator = iter(some_dict)
dict_iterator

<dict_keyiterator at 0x1a2dfdfe228>

list(dict_iterator)

['a', 'b', 'c']

#生成器
def squares(n=10):
    print('Generating squares from 1 to {0}'.format(n**2))
    for i in range(1,n+1):
        yield i**2
gen = squares()
gen

<generator object squares at 0x000001A2DFDBF750>

for x in gen:
    print(x,end=" ")

Generating squares from 1 to 100
1 4 9 16 25 36 49 64 81 100 

#生成器表达式
gen = (x**2for x in range(100))
gen

<generator object <genexpr> at 0x000001A2DFDBF930>

sum(x**2 for x in range(100))

328350

dict((i,i**2)for i in range(5))

{0: 0, 1: 1, 2: 4, 3: 9, 4: 16}

#itertools模块
import itertools
first_letter = lambda x :x[0]
names = ['Alan', 'Adam', 'Wes', 'Will', 'Albert', 'Steven']
for letter,names in itertools.groupby(names,first_letter):
    print(letter,list(names))

A ['Alan', 'Adam']
W ['Wes', 'Will']
A ['Albert']
S ['Steven']

#错误和异常处理
float('something')

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

<ipython-input-52-588ffff62dd7> in <module>()
      1 #错误和异常处理
----> 2 float('something')


ValueError: could not convert string to float: 'something'

def attempt_float(x):
    try:
        return float(x)
    except:
        return x
attempt_float('something')

'something'

float((1,2))

---------------------------------------------------------------------------

TypeError                                 Traceback (most recent call last)

<ipython-input-54-a101b3a3d6cd> in <module>()
----> 1 float((1,2))


TypeError: float() argument must be a string or a number, not 'tuple'

def attempt_float(x):
    try:
        return float(x)
    except (TypeError, ValueError):
        return x
attempt_float((1,2))

(1, 2)

#finally:无论try是否成功执行都执行的一段代码
#else：让只在try部分成功的情况下执行
try:
    write_to_file(f)
except:
    print('Failed')
else:
    print('Succeeded')
finally:
    f.close()

#文件和操作系统
path = 'example.txt'
f = open(path)   #默认只读模式

lines = [x.rstrip() for x in open(path)]
lines

['lzq', 'lfp', 'lkp', 'mjy']

f.close()#关闭文件，释放资源

with open(path)as f:           #with 在代码结束自动释放资源
    lines = [x.rstrip()for x in f]

f = open(path)
f.read(3)

'lzq'

f2 = open(path,'rb')3#二进制
f2.read(3)

b'lzq'

import sys
sys.getdefaultencoding()

'utf-8'

f.close()

f2.close()

#写入文件
with open('example.txt','w')as handle:
    handle.writelines(x for x in open(path) if len(x)>1)
with open('example.txt')as f:
    lines = f.readlines()
lines

[]

#文件的字节和Unicode
with open(path)as f:
    chars = f.read(3)
chars

'lzq'

 with open(path, 'rb') as f:
                data = f.read(3)
data

b'lzq'

data.decode('utf8')

'lzq'