py学习笔记（3）

元组

• 创建元组

tup1 = 1, 2, 3
print tup1

# 嵌套元组
tup2 = (1, 2, 3), (4, 5)
print tup2

(1, 2, 3)
((1, 2, 3), (4, 5))

• 转换为元组，list->tuple, string->tuple

l = [1, 2, 3]
print tuple(l)

str = 'Hello ChinaHadoop'
print tuple(str)

(1, 2, 3)
('H', 'e', 'l', 'l', 'o', ' ', 'C', 'h', 'i', 'n', 'a', 'H', 'a', 'd', 'o', 'o', 'p')

• 访问元组

tup3 = tuple(str)
print tup3[4]

o

• 合并元组

tup1 + tup2

(1, 2, 3, (1, 2, 3), (4, 5))

• 拆包

a, b, c = tup1
print b

2

# 函数返回多个值
def return_multiple():
    t = (1, 2, 3)
    return t

a, _, c = return_multiple()
print c

3

# 元组列表迭代
tuple_lst = [(1, 2), (3, 4), (5, 6)]
for x, y in tuple_lst:
    print x+y

3
7
11

• count 方法

tup3.count('o')

3

列表

• 创建列表

lst_1 = [1, 2, 3, 'a', 'b', (4, 5)]
print lst_1

lst_2 = range(1, 9)
print lst_2

[1, 2, 3, 'a', 'b', (4, 5)]
[1, 2, 3, 4, 5, 6, 7, 8]

• 转换为列表, tuple->list

lst_3 = list(tup3)
print lst_3

['H', 'e', 'l', 'l', 'o', ' ', 'C', 'h', 'i', 'n', 'a', 'H', 'a', 'd', 'o', 'o', 'p']

• 添加、移除元素

lst_4 = range(10)

# 末尾添加
lst_4.append(11)
print lst_4

# 指定位置插入
lst_4.insert(5, 12)
print lst_4

[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 11]
[0, 1, 2, 3, 4, 12, 5, 6, 7, 8, 9, 11]

# 删除指定位置的元素并返回
item = lst_4.pop(6)
print item
print lst_4

5
[0, 1, 2, 3, 4, 12, 6, 7, 8, 9, 11]

# 删除指定的值，注意12在这里是“值”不是“位置”
lst_4.remove(12)
print lst_4

[0, 1, 2, 3, 4, 6, 7, 8, 9, 11]

• 合并列表

lst_3 = lst_1 + lst_2
print lst_3

lst_1.extend(lst_2)
print lst_1

[1, 2, 3, 'a', 'b', (4, 5), 1, 2, 3, 4, 5, 6, 7, 8]
[1, 2, 3, 'a', 'b', (4, 5), 1, 2, 3, 4, 5, 6, 7, 8]

• 排序操作

import random
lst_5 = range(10)
random.shuffle(lst_5)
print lst_5

[7, 8, 5, 3, 2, 0, 4, 6, 9, 1]

lst_5.sort()
print lst_5

[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]

lst_6 = ['Welcome', 'to', 'Python', 'Data', 'Analysis', 'Course']
lst_6.sort()
print lst_6

['Analysis', 'Course', 'Data', 'Python', 'Welcome', 'to']

lst_6.sort(key = len, reverse=True)
print lst_6

['Analysis', 'Welcome', 'Course', 'Python', 'Data', 'to']

print lst_5
print lst_5[1:5]
print lst_5[5:]
print lst_5[:5]
print lst_5[-5:]
print lst_5[-5:-2]
print lst_5[::2]
print lst_5[::-1]

[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
[1, 2, 3, 4]
[5, 6, 7, 8, 9]
[0, 1, 2, 3, 4]
[5, 6, 7, 8, 9]
[5, 6, 7]
[0, 2, 4, 6, 8]
[9, 8, 7, 6, 5, 4, 3, 2, 1, 0]

字典 dict

• 创建字典

empty_dict = {}
dict1 = {'a': 1, 2: 'b', '3': [1, 2, 3]}
print empty_dict
print dict1

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

• 插入元素

dict1[4] = (4, 5)
print dict1

{'a': 1, 2: 'b', 4: (4, 5), '3': [1, 2, 3]}

• 删除元素

del dict1[2]
print dict1

{'a': 1, 4: (4, 5), '3': [1, 2, 3]}

a_value = dict1.pop('a')
print a_value
print dict1

1
{4: (4, 5), '3': [1, 2, 3]}

• 获取键、值列表

print dict1.keys()
print dict1.values()

[4, '3']
[(4, 5), [1, 2, 3]]

• 合并字典

dict2 = {4: 'new1', 5: 'news'}
dict1.update(dict2)
print dict1

{'3': [1, 2, 3], 4: 'new1', 5: 'news'}

• 通过多个列表创建字典

# 普通方法
dict_3 = {}
l1 = range(10)
l2 = list(reversed(range(10)))
for i1, i2 in zip(l1, l2):
    dict_3[i1] = i2
print dict_3

{0: 9, 1: 8, 2: 7, 3: 6, 4: 5, 5: 4, 6: 3, 7: 2, 8: 1, 9: 0}

dict_4 = dict(zip(l1, l2))
print dict_4

{0: 9, 1: 8, 2: 7, 3: 6, 4: 5, 5: 4, 6: 3, 7: 2, 8: 1, 9: 0}

hash函数

hash(12)

12

hash('test hash')

-520327859

hash((1, 2, 3))

-378539185

hash([1, 2, 3])

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

TypeError                                 Traceback (most recent call last)

<ipython-input-45-0b995650570c> in <module>()
----> 1 hash([1, 2, 3])


TypeError: unhashable type: 'list'

集合 set

a = set(range(10))
print a
b = set(range(5,15))
print b

set([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
set([5, 6, 7, 8, 9, 10, 11, 12, 13, 14])

• 并 交 差 异或

a | b

{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14}

a & b

{5, 6, 7, 8, 9}

a - b

{0, 1, 2, 3, 4}

a ^ b

{0, 1, 2, 3, 4, 10, 11, 12, 13, 14}

• 判断是否为子集、父集

a.issubset(b)

False

a.issuperset(b)

False

Python高阶函数

• 函数式编程

函数本身也可赋值给变量

import math
math.sqrt(25)

输出：
5.0

math.sqrt

输出：

fun = math.sqrt
fun

fun(10)

输出：

3.1622776601683795

将函数作为参数

def func_add(x, y, f):
    """
        functional addition
    """
    return f(x) + f(y)

print func_add(4, 25, math.sqrt)
print func_add(-4, 25, abs)

7.0
29

map/reduce

• map

x_2_lst = [x**2 for x in range(10)]
print x_2

x_sqrt_lst = map(math.sqrt, x_2)
print x_sqrt_lst

x_2_float_lst = map(float, x_2)
print x_2_float_lst

x_2_str_lst = map(str, x_2)
print x_2_str_lst

[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]
[0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0]
[0.0, 1.0, 4.0, 9.0, 16.0, 25.0, 36.0, 49.0, 64.0, 81.0]
['0', '1', '4', '9', '16', '25', '36', '49', '64', '81']

• reduce

str_lst = map(str, range(5)) # ['0', '1', ...]
print str_lst

def make_num(str1, str2):
    return int(str1) * 10 + int(str2)

result = reduce(make_num, str_lst)
print result

['0', '1', '2', '3', '4']
1234

关于map/reduce可以看廖雪峰的这个教程

规范字符串

name_lst = ['poNNY MA', 'rObIN li', 'steve JOBS', 'bILL gates']
standard_name_lst = map(str.title, name_lst)
print standard_name_lst

['Ponny Ma', 'Robin Li', 'Steve Jobs', 'Bill Gates']

filter

number_lst = range(-10, 10)

def is_negative(x):
    return x < 0

filtered_lst = filter(is_negative, number_lst)
print number_lst
print filtered_lst

[-10, -9, -8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
[-10, -9, -8, -7, -6, -5, -4, -3, -2, -1]

map reduce filter 与匿名函数

匿名函数：lambda
- 没有函数名
- 单条语句组成
- 语句执行的结果就是返回值
- 可用作sort的key的函数

• map与匿名函数

x_lst = range(10)
result_lst = map(lambda item : item**2 +item**3, x_lst) 

#相当于事先定义了一个平方加立方的函数，但是用匿名函数就看起来特别简洁

print x_lst
print result_lst

[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
[0, 2, 12, 36, 80, 150, 252, 392, 576, 810]

• reduce与匿名函数

x_lst = range(1, 5)
product = reduce(lambda x, y : x*y, x_lst)
#记住这里  reduce(func(x,y), lst) ,其中func必须有两个参数。每次计算结果和下一个元素做累积计算

print x_lst
print product

[1, 2, 3, 4]
24

• filter与匿名函数

number_lst = range(-10, 10)
filtered_lst = filter(lambda x : x<0, number_lst)
#filter(func, lst ), 将func作用于lst的每个元素，然后根据返回值是 TRUE还是FALSE 判断是保留还是丢弃该元素。
print number_lst
print filtered_lst

[-10, -9, -8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
[-10, -9, -8, -7, -6, -5, -4, -3, -2, -1]