Python Wiki

# 好的代码示例：
def calculate_sum(a, b):
    """计算两个数的和。

    Args:
        a: 第一个数。
        b: 第二个数。

    Returns:
        两个数的和。
    """
    return a + b

# 不推荐的代码示例：

def  calculateSum ( a,B ):
    # 计算 a 和 B 的和
    return a+B

# 导入整个 os 模块
import os

# 使用 os 模块的 getcwd 函数
current_directory = os.getcwd()
print(current_directory)

# 从 os 模块导入 getcwd 函数
from os import getcwd

# 直接使用 getcwd 函数
current_directory = getcwd()
print(current_directory)

# 为 os 模块指定别名
import os as my_os

# 使用别名调用 getcwd 函数
current_directory = my_os.getcwd()
print(current_directory)

# 获取用户输入的姓名
name = input("请输入您的姓名：")

# 使用 f-string 格式化输出问候语
print(f"您好，{name}！")

# 数值类型操作
a = 10
b = 3.14
c = a + b  # 加法
d = a - b  # 减法
e = a * b  # 乘法
f = a / b  # 除法
g = a // b  # 整除
h = a % b  # 取余
i = int(b)  # 类型转换，将浮点数转换为整数

# 字符串类型操作
name = "Alice"
greeting = "Hello, " + name + "!"  # 字符串拼接
message = f"欢迎 {name}！"  # f-string 格式化字符串

# 布尔类型操作
is_true = True
is_false = False
result1 = is_true and is_false  # 逻辑与
result2 = is_true or is_false   # 逻辑或
result3 = not is_true          # 逻辑非

# 常见的错误类型示例

# SyntaxError：语法错误
print("Hello, world!  # 缺少右括号

# NameError：未定义的变量

print(undefined_variable)

# TypeError：类型错误
print("Hello" + 123)

# 使用 try-except 语句处理异常

try:
    result = 10 / 0  # 可能引发 ZeroDivisionError
except ZeroDivisionError:
    print("除数不能为零！")

dir(int)

import sys
sys.version_info
sys.version
# => '3.7.1 (default, Dec 14 2018, 13:28:58)
#    [Clang 4.0.1 (tags/RELEASE_401/final)]

conda create -name myvenv python = 3.8

pip list

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple seaborn

;;使用--envs选项(-e)查看所有已创建的虚拟环境,在列出的虚拟环境中,使用星号(*)标识的是当前激活的虚拟环境.
conda info --envs

import os
os.system("ls")
os.system("ls -l") #more information
os.system("ls -F") #more information
os.system("dir")
os.remove #删除文件

import glob
glob.glob('*.py')

##查看文件编码方式
sys.getfilesystemencoding()
# => 'utf-8'

def test(x, y = 10):
    x += 100
    print(x, y)
test
# <function __main__.test(x, y=10)>
test.__code__
# <code object test at 0x11d9b15d0, file "<ipython-input-43-3d74f8241943>", line 1>
test.__code__.co_varnames # 参数及变量量名列列表。
# => ('x', 'y')
test.__code__.co_consts # 指令常量
# => (None, 100)
test.__defaults__ # 参数默认值
# => (10,)
test(1)
# => 101 10

year = int(input('请输入年份: '))
# 如果代码太长写成一行不便于阅读 可以使用\对代码进行折行
is_leap = year % 4 == 0 and year % 100 != 0 or \
          year % 400 == 0
print(is_leap)

x=2;y=3
x,y=y,x
x
# => 3
y
# => 2

with open('imagenet_classes.txt') as f:
    labels = [line.strip() for line in f.readlines()]

a = 3
assert(a>1)
print("断言成功，程序继续向下执行")

b = 4
assert(b>7)
# => Traceback (most recent call last):
#      File "<stdin>", line 1, in <module>
#    AssertionError
print("断言失败，程序报错")

x = 1
y = 2
assert x == y, "not equals"
# => Traceback (most recent call last):
#      File "<stdin>", line 1, in <module>
#    AssertionError: not equals

eval('[1,2,3]')
#> [1, 2, 3]
x = 7
eval('x**2')
# => 49

message = input("tell me something, and I will repeat it back to you:")
print(message)

import numpy as np
import pandas as pd
name = input("Please enter your name: ")
print("Hello, " + name + "!")

x = eval(input('Enter a number'))
print(x, type(x))

age = input("how old are you?")
age
21

import seaborn as sns
df = sns.load_dataset("titanic")
df["class"].unique()
# ['Third', 'First', 'Second']

import random
random.seed(1010)
random.randint(1, 100) # 生成一个[1,100]以内的随机整数
# => 78
random.choice([1,2,4,'word']) #随机选择一个数字
# => 2
random.sample(range(100), 5) # 随机生成5个100 以内不重复的数字
# => [68, 10, 52, 55, 21]
random.random() # 0-1 随机小数
# => 0.14252352294885373
random.shuffle([1, 2, 3, 4, 5]) # 随机打乱列表

import random
import numpy as np
values = [5, 10, 15, 20, 25]
random.shuffle(values)
print(values)
#[25, 20, 5, 15, 10]
np.random.normal(mu, sigma, n) #从正态分布中抽取数据
s = np.random.permutation(5) #随机生成一个[0 - 5]序列
# => array([3, 0, 1, 4, 2])
s[:3]
# => array([3, 1, 0])

print(bin(100))
# => 0b1100100

from time import time
t = time()
abbreviations = ['cf.', 'e.g.', 'ex.']
for i in range(10):
    for w in ('Mr.', 'hat', '.'):
        if w in abbreviations:
# if w[-1]=='.' and w in abbreviations:
            pass

def fib():
    a, b=0, 1
    while True:
        yield a
        a, b=b, a + b

from itertools import islice
list(islice(fib(), 5))
# => [0, 1, 1, 2, 3]

before=id(Y)
Y=Y+X
id(Y)==before
# False

Z = torch.zeros_like(Y)
print('id(Z):',id(Z))
Z[:] = X +Y
print('id(Z):', id(Z))
# id(Z): 140327634811696 id(Z): 140327634811696

a = torch.arange (3) . reshape((3, 1))
b= torch. arange(2) . reshape((1, 2))
a+b
# =>
# tensor([[0, 1],
#         [1, 2],
#         [2, 3]])

from math import sqrt
print ("Square root of 16 is", sqrt (16))

# my_script.py
if __name__ == "__main__":
    print("This script is being run directly, not imported.")
else:
    print("This script is being imported, not run directly.")

import pandas as pd
import numpy as np
df1 = pd.Series([1, np.nan, 2, None])
# => 0    1.0
#    1    NaN
#    2    2.0
#    3    NaN
#    dtype: float64
df1.isnull()
# => 0    False
#    1     True
#    2    False
#    3     True
#    dtype: bool
df1[df1.notnull()]
# => 0    1.0
#    2    2.0
#    dtype: float64

df1
# => 0    1.0
#    1    NaN
#    2    2.0
#    3    NaN
#    dtype: float64
df1.fillna(0)
# => 0    1.0
#    1    0.0
#    2    2.0
#    3    0.0
#    dtype: float64

housing.dropna(subset=['total_bedrooms']) #option 1 可以理解为删除缺失值
housing.drop('total_bedrooms', axis=1)  #删除一个特征
median = housing['total_bedrooms'].median()
housing['total_bedrooms'].fillna(median)

a = "Hi"
b = "Hi"
a == b
# => True
a is b
# => True

a1 = "I am using long string for testing"
a2 = "I am using long string for testing"
# => 'I am using long string for testing'
a1 == a2
# => True
a1 is a2
# => False

4 % 3
# 1

0^0
# => 0
0^1
# => 1
1^0
# => 1
1^1
# => 0
5^3
# => 6

current_num = 1
while current_num <= 5:
    print(current_num)
    current_num +=1

current_num
# => 6

import re
bt = 'bat|bet|bit'
m = re.match(bt, "bat")
m.group()
titles = '你好，hello, 世界'
pattern = re.compile(r'[\u4e00-\u9fa5]+')
results = pattern.findall(titles)
# => ['你好', '世界']

s = "小明年龄18岁 分数100"
res = re.search(r"\d+", s).group()
res = re.findall(r"\d+", s)
res = re.match("小明", s).group()

##不加group 匹配不到
res = re.match(r"\d+", s)

##分数不是字符串开头，匹配不到
res = re.match("分数", s).group()

s = "<a>哈哈</a><a>呵呵</a>"
import re
res1 = re.findall("<a>(.*)</a>", s)
# => ['哈哈</a><a>呵呵']
res2 = re.findall("<a>(.*?)</a>", s)
# => ['哈哈', '呵呵']

import re
anyend = '.end'
m = re.match(anyend, 'bend')
m.group()
# => 'bend'

s="Hello$@ Python3$"
import re
s1=re.sub("[^A-Za-z]","",s)
print (s1)
#Output:HelloPython

s = "A man, a plan, a canal: Panama"
import re
s = re.sub(r'[^A-Za-z0-9]', "", s)

s="Hello347 Python3$"
import re
s1=re.sub("[0-9]","",s)
print (s1)
#Output:Hello Python$

s="1-2$3%4 5a"
s1="".join(c for c in s if  c.isdecimal())
print (s1)
#Output:12345

l = [1, 2, 3]
l * 2
# => [1, 2, 3, 1, 2, 3]
2 * 'abc'
# 'abcabc'

line ='asdf fjjdk; afed, fjek'
import re
fields = re.split(r'[;,\s]\s*', line)
# => ['asdf', 'fjjdk', 'afed', 'fjek']
values = fields[::2]
delimiters = fields[1::2] + ['']

a = " heheheh "
a.strip()
# => 'heheheh'

filename = 'spam.txt'
filename.endswith('.txt')
# => True
filename.startswith('file:')
# => False
url = 'http://www.python.org'
url.startswith('http')
# => True

import os
filenames = os.listdir(".")
filenames[0:2]
[name for name in filenames if name.endswith(('.org'))] #展示以 org 结尾的文件名称
any(name.endswith('.py') for name in filenames) #判断目录下是否有py 文件

from fnmatch import fnmatch,  fnmatchcase
fnmatch('foo.txt', '*.txt')
fnmatch('foo.txt', '?oo.txt')
fnmatch('Dat45.csv', 'Dat[0-9]*')

text = 'yeah, but no'
text.replace('yeah', 'yep')
# => 'yep, but no'

##LabelBinarizer 类可以一次性完成两个转换
from sklearn.preprocessing import LabelBinarizer
encoder = LabelBinarizer()
housing_cat_1hot = encoder.fit_transform(housing_cat)
housing_cat_1hot

import re
line ='asdf fjdk;afed, fjek, asdf'
re.split(r'[;,\s]\s*', line)
# => ['asdf', 'fjdk', 'afed', 'fjek', 'asdf']

filename ='spam.txt'
filename.endswith('.txt') #判定结尾是否以确定的字符结尾
# => True
filename.startswith('file:')
# => False
url ='http://www.python.org'
url.startswith('http:')
# => True
import os
filenames =os.listdir('.')
filenames
[name for name in filenames if name.endswith('.org')]
any(name.endswith('.py') for name in filenames)
# => False

filename ='spam.txt'
filename[-4:] =='.txt'
# => True
url ='http://www.python.org'
url[:5] =='http:' or url[:6] =='https:' or url[:4] == 'ftp:'
# => True

import re
url ='http://www.python.org'
re.match('http:|https:|ftp:', url)

from fnmatch import fnmatch,fnmatchcase
fnmatch('foo.txt', '*.txt')
# => True
fnmatch('foo.txt', '?oo.txt')
# => True
fnmatch('Dat45.csv', 'Dat[0-9]*')
# => True
names =['Dat1.csv', 'Dat2.csv', 'config.ini']
[name for name in names if fnmatch(name, 'Dat*.csv')]
# => ['Dat1.csv', 'Dat2.csv']

fnmatchcase('foo.txt', '*.TXT')
# => False

text = 'yeah, but no, but yeah, but no, but yeah'
text == 'yeah'
# => False
#match at start or end
text.startswith('yeah')
# => True
text.endswith('not')
# => False
text.find('no')
# => 10

text1 = '11/27/2012'
text2 = 'Nov 27, 2012'
import re
if re.match(r'\d+/\d+/\d+', text1):
    print('yes')
else:
    print('no')
    # => yes

datepart =re.compile(r'\d+/\d+/\d+')
if datepart.match(text1):
    print('yes')
text ='Today is 11/27/2012, pycon srad 3/13/2013'
datepart.findall(text)
# => ['11/27/2012', '3/13/2013']
m =datepart.match('11/27/2012')
m
m.group()
m.group(0)
m.group(1)
m.group(2)
m.groups()
datepart.findall(text)
for month, day, year in datepart.findall(text):
    print('{}-{}-{}'.format(year, month, day))

for m in datepat.finditer(text):
    print(m.groups())

text = 'Yeah, but no, but Yeah'
text.replace('yeah', 'yep')
# => 'Yeah, but no, but Yeah'

text ='Today is 11/27/2012. Pycon starts 3/13/2013.'
import re
re.sub(r'(\d+)/(\d+)/(\d+)', r'\3-\1-\2', text)

import re
datepat =re.compile(r'(\d+)/(\d+)/(\d+)')
newtext, n= datepat.sub(r'\3-\1-\2', text)
newtext

text='Upper Python, lower python, mixed python'
re.findall('python', text, flags=re.IGNORECASE)
# => ['Python', 'python', 'python']
re.sub('python', 'snake', text, flags=re.IGNORECASE)
# => 'Upper snake, lower snake, mixed snake'

import re
str_pat =re.compile(r'\"(.*)"')
text1 ='Computer says "no."'
str_pat.findall(text1)
# => ['no.']
text2 ='Computer says "no." phone says "yes"'
str_pat.findall(text2)
# => ['no." phone says "yes']

str = '张三 美国 张 三 哈哈'
str.count('张三')

str = "HHHuuu"
print(str.upper())
# => HHHUUU
print(str.lower())
# => hhhuuu

str = 'hello world ha ha'
str.replace(" ", "")
list = str.split(" ")
"".join(list)
# => 'helloworldhaha'

titles = '你好，hello, 世界'
pattern = re.compile(r'[\u4e00-\u9fa5]+')
results = pattern.findall(titles)
# => ['你好', '世界']

text ='hello world'
text.ljust(20)
# => 'hello world         '
import re
text = 'hello world'
text.ljust(20)
# => 'hello world         '
text.rjust(20)
# => '         hello world'
text.center(20)
# => '    hello world     '
format(text, '>20')
# => '         hello world'
format(text, '<20')
# => 'hello world         '
format(text, '^20')
# => '    hello world     '
format(text, '=>20s')
# => '=========hello world'
format(text, '*^20s')
'{:>10s}{:>10s}'.format('hello', 'world')
# => '     hello     world'
x = 1.345
format(x, '>10')
# => '     1.345'
format(x, '^10.2f')
# => '   1.34   '
'%-20s' % text
# => 'hello world         '

parts = ['Is', 'chiao', 'not', 'chiago']
", ".join(parts)
# => 'Is, chiao, not, chiago'
''.join(parts)
# => 'Ischiaonotchiago'

a ='Is Chicago'
b ='Not Chicago'
a + ' ' +b
join = ['Is', '']
print(a + ':' + b)
print(a + ':' + b)

s = '{name} has {n} messages.'
s.format(name='Guidao', n=37)
# => 'Guidao has 37 messages.'

x = 10
y = 20
f"{x} + {y} = {x + y}"
# => '10 + 20 = 30'
"{} + {} = {}".format(x,y,x+y)
f"{type(x)}"
# => "<class 'int'>"

class User:
    def __init__(self, name, age):
        self.name = name
        self.age = age
    def __repr__(self):
        return f"{self.name} {self.age}"


users = [User(f"user{i}", i) for i in (3,1,0,2)]
users

a = 4.2
b = 2.1
a + b
# => 6.300000000000001
(a + b) == 6.3
# => False

from decimal import Decimal
a = Decimal('1.3')
b = Decimal('2.2')
a + b
# => Decimal('3.5')
print(a + b)
# => 3.5
(a + b) == Decimal('3.5')
# => True

from decimal import localcontext
a = Decimal('4.2')
b = Decimal('1.2')
print(a/b)

with localcontext() as ctx:
     ctx.prec = 3
     print(a/b)

nums = [1.23e+18, 1, -1.23e+18]
sum(nums)
# => 0.0
import math
math.fsum(nums)
# => 1.0

a = 'Hi'
b = 'Hi'
a is b
# => True
a == b
# => True
a1 = "I am lu"
b1 = 'I am lu'
a1 is b1
# => False
a1 == b1
# => True

x = 1234.34045
format(x, '0.2f')
# => '1234.34'
format(x, '> 10.1f')
# => '    1234.3'
format(x, '<10.1f')
# => '1234.3    '
format(x,',')
# => '1,234.34045'

'\n'
print(r'\n') #真的执行转行操作
# =>
print(r'hello')
# => hello

tup = 4, 5, 6
tup
# (4, 5, 6)
list(tup)
# => [4, 5, 6]

nested_tup = (4,5,6),(7,8)
nested_tup
# ((4, 5, 6), (7, 8))

tuple([4,0,2])
# (4, 0, 2)
tuple('string')
# ('s', 't', 'r', 'i', 'n', 'g')

tup = tuple(['foo', [1,2], True])
tup[1].append(3)
tup
# ('foo', [1, 2, 3], True)

(4,None,'foo') + (6,0) + ('bar',)
# (4, None, 'foo', 6, 0, 'bar')

('foo', 'bar')*4
# ('foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar')

tup = (4,5,6)
a,b,c=tup
b
# => 5

values = 1, 2, 3, 4, 5
a, b, *rest = values
rest
# => [3, 4, 5]

print(type(('ok')))
# => <class 'str'>
print(type(('ok', )))
# => <class 'tuple'>

nested = ((1,10,'python'),('data'))
nested
# => ((1, 10, 'python'), 'data')
type(nested)
# => <class 'tuple'>

nested = ((1,10,'python'),('data'))
type(nested)
# => <class 'tuple'>
nested[0]
# => (1, 10, 'python')
print(nested[0][0], nested[0][1], nested[0][2])
# => 1 10 python

t = ('ok',[1,2],True)
t[2] = False
# => Traceback (most recent call last):
#      File "<stdin>", line 1, in <module>
#      File "/path/to/example", line 1, in <module>
#        # -*- org-confirm-babel-evaluate: nil; -*-
#    TypeError: 'tuple' object does not support item assignment

tuple = ('a','b','c','d','e')
tuple[1:3]
# => ('b', 'c')
tuple[0] = 'A'
tuple = ('A',) + tuple[1:]
# => ('A', 'b', 'c', 'd', 'e')
tuple

t = ('a','b',['A','B'])
# => ('a', 'b', ['A', 'B'])
t[2][0] = 'X' #tuple 里的 list 对象本身仍可修改
# => 'X'
t[0] =  'C'
t
# => ('a', 'b', ['X', 'B'])

t[1].append(3)
t

t = (1,10.31,'python')
t.count('python')
# => 1
t.index(10.31)
# => 1

(1,10,'python') + ('data',11) + ('ok',)
# => (1, 10, 'python', 'data', 11, 'ok')
(1,10,'python') * 2
# => (1, 10, 'python', 1, 10, 'python')

t = (1,10,'python')
(a, b, c) = t
print(a,b,c)
# => 1 10 python

t = (1,10,('ok', 'python'))
(a,b,(c,d)) = t
print(a,b,c,d)
# => 1 10 ok python

p = (4, 5)
x, y, z =  p

t = 1,2,3,4,5
a,b,*rest,c = t
print(a,b,c)
# => 1 2 5
print(rest)
# => [3, 4]

data = ['a','b',23,1]
_,shares,price,_ = data
print(shares, price)

line = "nobody:*-2:-2:unpsdfdf:/sdsdsd"
uname,*filesd,hoer,sh = line.split(":")
uname
# => 'nobody'

record = ('as',50,12,(1,2,3))
name, *_,(*_,year) = record
year
# => 3

set(['I', 'you', 'he', 'I'])
# => {'you', 'he', 'I'}

set.difference(set(['a',2,'5']),set(['a',7]))
# => {2, '5'}
set.union(set(['a',2,'5']),set(['a',7]))
# => {2, '5', 7, 'a'}
set.intersection(set(['a',2,'5']),set(['a',7]))
# => {'a'}
a = [1, 2, 3, 4]
b = [4, 3, 5, 6]

[i for i in a if i in b]
set(a).intersection(set(b)) #交集
# => {3, 4}
set(a).union(set(b)) #并集
# => {1, 2, 3, 4, 5, 6}
set(a).difference(set(b))
# => {1, 2}

d1 = {'a':'some value', 'b':[1, 2, 3]}
d1
d1[7] = 'an integer'
d1
# => {'a': 'some value', 'b': [1, 2, 3], 7: 'an integer'}

from collections import OrderedDict
d = OrderedDict()

d['foo'] = 1
d['bar'] = 2
d['spam'] = 3
d['grok'] = 4

for key in d:
   print(key, d[key])
   # => foo 1
   #    bar 2
   #    spam 3
   #    grok 4

prices = {
'ACME': 45.23,
'AAPL': 612.78,
'IBM': 205.55,
'HPQ': 37.20,
'FB': 10.75
}
#make a dictionary of all price over 200
p1 = {key:value for key, value in prices.items() if value > 200}
# => {'AAPL': 612.78, 'IBM': 205.55}

#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}
# => {'AAPL': 612.78, 'IBM': 205.55, 'HPQ': 37.2}
p2 = {key:prices[key] for key in prices.keys() & tech_names}
# => {'IBM': 205.55, 'HPQ': 37.2, 'AAPL': 612.78}

from collections import defaultdict
d = defaultdict(list)
d['a'].append(1)
print(d)
# d = defaultdict(set)
# d['a'].add(1)

d = {}
d.setdefault('a', []).append(1)
d.setdefault('a', []).append(2)

from collections import deque
q = deque(maxlen=3)
q.append(1)
q.append(2)
q.append(3)
q.append(4)
q
# => deque([2, 3, 4], maxlen=3) #只保留最后3个元素
q.appendleft(4) #将元素加在左边
# =>
q.pop() #剔除最后一个元素
# => 3
q.popleft() #从左边开始剔除
# => 4

import heapq
nums = [1,8,2,12,23,1]
print(heapq.nlargest(3, nums))
# => [23, 12, 8]
print(heapq.nsmallest(3, nums))
# => [1, 1, 2]

portfolio = [
  {'name':'IBM', 'share':100, 'price':91.1},
  {'name':'aapl', 'share':50, 'price':2343.1}
]

heapq.nsmallest(1, portfolio, key = lambda s:s['price'])

d = {
  'a': [1, 2,3],
  'b': [4, 5]
}

d['a'].append(1)
d
# => {'a': [1, 2, 3, 1], 'b': [4, 5]}

prices = {'ACme': 45.23,'A':231.120,"sdfg":234}

min_price = min(zip(prices.values(), prices.keys()))
min_price
# => (45.23, 'ACme')
max_price = max(zip(prices.values(), prices.keys()))
max_price
# => (234, 'sdfg')
sort_price = sorted(zip(prices.values(), prices.keys()))
sort_price
# => [(45.23, 'ACme'), (231.12, 'A'), (234, 'sdfg')]

a = {'x':1, 'y':1, 'z':3}
b = {'w':2, "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()
# => set()

c = {key:a[key] for key in a.keys() - {'z', 'w'}}

def dedupe(items):
  seen = set()
  for item in items:
    if item not in seen:
      yield item
      seen.add(item)

a = [1, 5, 2, 1, 9]
list(dedupe(a))
# => [1, 5, 2, 9]

def dedupe(items, key=None):
    seen =  set()
    for item in items:
        val = item if key is None else key(item)
        if val not in seen:
            yield item
            seen.add(val)

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)
word_counts
# =>
# Counter({'eyes': 8, 'the': 5, 'look': 4, 'into': 3, 'my': 3, 'around':
# 2, 'not': 1, "don't": 1, "you're": 1, 'under': 1})
top_three =  word_counts.most_common(3)
# => [('eyes', 8), ('the', 5), ('look', 4)]

morewords =  ['my', 'look', 'b', 'c', 'b']
for word in morewords:
    word_counts[word] += 1

word_counts

word_counts.update(morewords)
a =  Counter(words)
b =  Counter(morewords)
#combine counts
c = a + b
c
#subtract counts
d = a - b
d

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
row_by_fname = sorted(rows,  key =itemgetter('fname'))
# =>
# [{'fname': 'Big', 'lname': 'Jones', 'uid': 1004},
#  {'fname': 'Brian', 'lname': 'Jones', 'uid': 1003},
#  {'fname': 'David', 'lname': 'Beazley', 'uid': 1002},
#  {'fname': 'John', 'lname': 'Cleese', 'uid': 1001}]
row_by_uid = sorted(rows,  key =itemgetter('uid'))
rows_by_lfname = sorted(rows, key = itemgetter('lname', 'fname'))
rows_by_lfname

rows_by_fname = sorted(rows, key=lambda x:x['fname'])
rows_by_lfname = sorted(rows, key=lambda x:(x['lname'], x['fname']))

min(rows,key=itemgetter('uid'))
max(rows,key=itemgetter('uid'))

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

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
rows.sort(key =  itemgetter('date')) #按照 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'}

mylist = [1,24,-5,10,-7]
[n for n in mylist if n > 0]
# => [1, 24, 10]
[n for n in mylist if n < 0]
# => [-5, -7]

pos =  (n for n in mylist if n > 0)
for i in pos:
    print(i)

values = ["1", "2", "-3", "-", "4", "N?A"]

def is_int(val):
    try:
        x = int(val)
        return True
    except ValueError:
        return False

ivals = list(filter(is_int,values))
ivals

mylist = [1,24,-5,10,-7]
[n if n > 0 else 0 for n in mylist]
# => [1, 24, 0, 10, 0]

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',
]
count = [0, 3, 10, 1,7, 6, 1]
from itertools import compress
more5 = [n > 5 for n in count]
more5
# => [False, False, True, False, True, True, False]
list(compress(addresses, more5))
# => ['5800 E 58TH', '1060 W ADDISON', '4801 N BROADWAY']

from collections import namedtuple
subscribe = namedtuple('subscribe',['addr', 'joined'])
sub = subscribe('user_at_example_dot_com', '2012-10-01')
sub
# => subscribe(addr='user_at_example_dot_com', joined='2012-10-01')
sub.addr
# => 'user_at_example_dot_com'
sub.joined
# => '2012-10-01'
len(sub)
# => 2
addr, joined=sub
addr
# => 'user_at_example_dot_com'
a, b=sub
a
# => 'user_at_example_dot_com'
from collections import namedtuple
stocks = namedtuple('stocks',['name', 'share', 'price'])
s = stocks('asb', 100,1003.55)
# => stocks(name='asb', share=100, price=1003.55)
s.share = 75
# => Traceback (most recent call last):
#      File "<stdin>", line 1, in <module>
#      File "/path/to/example", line 1, in <module>
#        # -*- org-confirm-babel-evaluate: nil; -*-
#    AttributeError: can't set attribute
s = s._replace(share=75)
# => stocks(name='asb', share=75, price=1003.55)

from collections import namedtuple

stock =namedtuple('stock',['name', 'share', 'price', 'date', 'time'])
stock_prototype = stock('', 1, 1, None, None)
def dict_to_stock(s):
  return stock_prototype._replace(**s)

a = {'name': 'asb','share':1, 'price':1003.55}
dict_to_stock(a)
# => stock(name='asb', share=1, price=1003.55, date=None, time=None)
b = {'name': 'b', 'share':1003.55, 'price':1003.55, 'date':'12/17/2016'}
dict_to_stock(b)
# => stock(name='b', share=1003.55, price=1003.55, date='12/17/2016', time=None)

nums =[1, 2, 3, 4, 5]
s = sum(x*x for x in nums)
# => 55

s =('acs', 50, 100.45)
print(','.join(str(x) for x in s))
# => acs,50,100.45

portfolio = [{'name': 'goog', 'share':50},
             {'name':'yhoo', 'share':100}]
portfolio
min_share = min(s['share'] for s in portfolio)
# => 50
# => acs,50,100.45

a ={'x':1, 'z':2}
b ={'y':1, 'z':2}
from collections import ChainMap
c =ChainMap(a, b)
c
# => ChainMap({'x': 1, 'z': 2}, {'y': 1, 'z': 2})
print(c['x'])
# => 1
print(c['z'])
# => 2
len(c)
# => 3
list(c.keys())
# => ['y', 'z', 'x']
list(c.values())
# => [1, 2, 1]
c['z'] =100
c['w'] =400
del c['x']
c
# => ChainMap({'z': 100, 'w': 400}, {'y': 1, 'z': 2})
a
# => {'z': 100, 'w': 400}
del c['y']
# => Traceback (most recent call last):
#      File "/path/to/example", line 970, in __delitem__
#        del self.maps[0][key]
#    KeyError: 'y'
#
#    During handling of the above exception, another exception occurred:
#
#    Traceback (most recent call last):
#      File "<stdin>", line 1, in <module>
#      File "/path/to/example", line 972, in __delitem__
#        raise KeyError('Key not found in the first mapping: {!r}'.format(key))
#    KeyError: "Key not found in the first mapping: 'y'"
values =ChainMap()
values['x'] = 1
#add a new mapping
values =values.new_child()
values['x'] = 2
values =values.new_child()
values['x'] = 3
values
# => ChainMap({'x': 3}, {'x': 2}, {'x': 1})
#discardlast mapping
values =values.parents
values['x']
values
# => ChainMap({'x': 2}, {'x': 1})

from collections import ChainMap
a ={'x':1, 'z':3}
b ={'y':2, 'z':4}
merged =dict(b)
merged.update(a)
merged
# => {'y': 2, 'z': 3, 'x': 1} #将z的值进行更新
##如果想保留z 值的话, 可以用chainmap 命令
a ={'x':1, 'z':3}
b ={'y':2, 'z':4}
merged = ChainMap(a, b)
merged['x']
# => 1
a['x'] = 42 #进行更新
merged['x']
# => 42

def f(x):
    return {
        'a': 1,
        'b': 2
    }.get(x, 9)    # 9 is default if x is not found

tup = ('foo', 'bar')
b_list = list(tup)
b_list
b_list[1] = 'peekaboo'
b_list
# => ['foo', 'peekaboo']

l = [1,10,'python']
l.append([4,3])
l
# =>
[1, 10, 'python', [4, 3]]
l.extend([4, 33])
l
# => [1, 10, 'python', [4, 3], 4, 33]
l.extend([1,2,'ok')
l
# => [1, 10, 'pyth, 1, 2, 'ok]

[4, None, 'foo'] + [7, 8, (2, 3)]
# => [4, None, 'foo', 7, 8, (2, 3)]

x = [4, None, 'foo']
x.extend([7, 8, (2, 3)])
x
# => [4, None, 'foo', 7, 8, (2, 3)]

li = ['a', 'b', 'c']
for i, e in enumerate(li):
    print("index:", i)
    print("element", e)
    # => index: 0
    #    element a
    #    index: 1
    #    element b
    #    index: 2
    #    element c

[1, 2] + [3, 4]
# => [1, 2, 3, 4]
[1, 2]*2
# => [1, 2, 1, 2]

len([1,2,3])
# => 3

colors = ['black', 'white']
sizes = ['S', 'M', 'L']
tshirts = [(color, size) for color in colors for size in sizes]
# [('black', 'S'), ('black', 'M'), ('black', 'L'), ('white', 'S'), ('white', 'M'), ('white', 'L')]

l = [10, 20, 30, 40]
l[::2]
# [10, 20]
l[0:3]
# [10, 20, 30]

s = 'bicycle'
s[::3] #间隔为3
# => 'bye'
s[1::3]
# => 'ic'
s[::-1]
# 'elcycib'
s[::-2]
# 'eccb'

l = list(range(10))
l
# [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
l[2:5] = [20, 30]
l
# [0, 1, 20, 30, 5, 6, 7, 8, 9]
del l[5:7]
l
l[3::2] = [11, 22]
l
# [0, 1, 20, 11, 5, 22, 9]
l[2:5] = 100
l[2:5] = [100]
l

import pandas as pd
data = pd.Series(['a', 'b', 'c'], index=[1, 3, 5])
data
# => 1    a
#    3    b
#    5    c
#    dtype: object
data[1] #第一个元素
# => 'a'
data[1:3] #第一个
# => 3    b
#    5    c
#    dtype: object
data.loc[1] #选择行
# => 'a'
data.loc[1:3]
# => 1    a
#    3    b
#    dtype: object

from itertools import chain
a = [1, 2, 3, 4]
b = ['x', 'y', 'z']
for x in chain(a, b):
    print(x)
# => 1
#    2
#    3
#    4
#    x
#    y
#    z

for x in a + b:
    print(x)

import heapq
a = [1, 4, 7, 10]
b = [2, 5, 6, 11]
for c in heapq.merge(a, b):
    print(c)
    # => 1
    #    2
    #    4
    #    5
    #    6
    #    7
    #    10
    #    11

[x for x in range(5)]
#> [0, 1, 2, 3, 4]

[x + 10 for x in range(10) if x % 2 == 0]
#> [10, 12, 14, 16, 18]

def test(data):
    print(type(data), data)

test({x for x in range(3)})
#> <class 'set'> {0, 1, 2}

[f"{x}{y}" for x in "abc" if x != "c"
           for y in range(3) if y != 0]
#> ['a1', 'a2', 'b1', 'b2']

symbols = '$¢£¥€¤'
beyond_ascii = [ord(s) for s in symbols if ord(s) >127]
# => [162, 163, 165, 8364, 164]
beyond_ascii = list(filter(lambda c: c > 127, map(ord, symbols)))
# => [162, 163, 165, 8364, 164]

{k:v for k,v in zip("abc", range(10, 13))}
#> {'a': 10, 'b': 11, 'c': 12}

{x for x in "abc"}
#> {'a', 'b', 'c'}

import enum
color = enum.Enum

def print_max(a, b):
    if a > b:
    print(a, 'is maximum')
elif a == b:
    print(a, 'is equal to', b)
else:
    print(b, 'is maximum')
print_max(3,4)

def demo(args_f, *args_v):
    print(args_f)
    for x in args_v:
        print(x)

demo('a','b','c')
# => a
#    b
#    c
demo('a', 'b')
# => a
#    b

def demo(**kwargs):
    for k,v in kwargs.items():
        print(k,v)

demo(name='njcx')
# => name njcx

def appendtest(newitem, lista=[]):
    print(id(lista))
    lista.append(newitem)
    print(id(lista))
    return lista

appendtest('a', ['b', 2, 4])
appendtest(1)

def appendtest(newitem, lista=None):
    if lista is None:
        lista = []
    lista.append(newitem)
    return lista

if age >=18:
    pass

[callable(obj) for obj in (abs, str, 13)]
# => [True, True, False]

x = 50
def func(x):
    print("x is", x)
    x = 2
    print('Changed local x to', x)

func(x)
# => x is 50
#    Changed local x to 2
print("x is still", x)
# => x is still 50

def say_hello():
    print('hello world')

say_hello()
# => hello world
x = 50
def func():
    global x

    print('x is', x)
    x = 2
    print('Changed global x to', x)

func()
# => x is 2
#    Changed global x to 2
print('Value of x is', x)
# => Value of x is 2
#如果不加上global
x = 50
def func():
    #global x
    print('x is', x)
    x = 2
    print('changed global x to', x)

func()
# => Traceback (most recent call last):
#      File "<stdin>", line 1, in <module>
#      File "/path/to/example", line 2, in func
#        #+PROPERTY: header-args :eval never-export
#    UnboundLocalError: local variable 'x' referenced before assignment

def func(a,b=5,c=10):
    print("a is", a, "and b is", b, "and c is", c)

func(3,7)
# => a is 3 and b is 7 and c is 10
func(25,c=7)
# => a is 25 and b is 5 and c is 7
func(c=50, a=100)
# => a is 100 and b is 5 and c is 50

def avg(first, *rest):
    return (first + sum(rest)) / (1 + len(rest))

# Sample use
avg(1, 2) # 1.5
avg(1, 2, 3, 4) # 2.5

def maximun(x, y):
  if x > y:
      return  x
  elif x == y:
      return "The numbers are equal"
  else:
      return y

print(maximun(2, 3))

def recv(maxsize, *, block):
   'Receives a message'
   pass

recv(1024, True) # TypeError
recv(1024, block=True) # Ok

import html

def make_element(name, value, **attrs):
    keyvals = [' %s="%s"' % item for item in attrs.items()]
    attr_str = ''.join(keyvals)
    element = '<{name}{attrs}>{value}</{name}>'.format(
                name=name,
                attrs=attr_str,
                value=html.escape(value))
    return element

# Example
# Creates '<item size="large" quantity="6">Albatross</item>'
make_element('item', 'Albatross', size='large', quantity=6)

# Creates '<p>&lt;spam&gt;</p>'
make_element('p', '<spam>')

def minimum(*values, clip=None):
   m = min(values)
   if clip is not None:
       m = clip if clip > m else m
   return m

minimum(1, 5, 2, -5, 10) # Returns -5
minimum(1, 5, 2, -5, 10, clip=0) # Returns 0

def add(x:int, y:int) -> int:
    return x + y

add(1,2)
#> 3

help(add)
#> Help on function add in module __main__:
#>
#> add(x: int, y: int) -> int

add.__annotations__
#> {'x': int, 'y': int, 'return': int}

def myfun():
    return 1,2,3

a, b, c = myfun()
a
#1
b
#2
c
#3

def spam(a, b = 42):
    print(a, b)

spam(1)
spam(1, 2)

_no_value = object()
def spam(a, b=_no_value):
    if b is _no_value:
        print('No b value supplied')

spam(1)
spam(1, 2)
spam(1,  None)


def spam(a,b=[]):
    print(b)
    return b

x = spam(1)
x.append(99)
spam(1)

from functools import partial
def spam(a, b, c, d):
    print(a, b, c, d)

s1 = partial(spam, 1)
s1
s1(2, 3, 4)
s2 = partial(spam, d = 42)
s2(1, 2, 3)
s2(4, 5, 5)
s3 = partial(spam, 1, 2, d = 42)
s3(3)
s3(4)
s3(5)

import functools
int2 = functools.partial(int, base=2)
int2('1000000')

def int2(x, base=2):
    return int(x, base)

def apply_async(func, args, *, callback):
    result = func(*args)
    callback(result)

def print_result(result):
    print('Got:', result)

def add(x,y):
    return x+y

apply_async(add, (2, 3), callback=print_result)
# Got: 5

def sample():
    n = 0
    def func():
        print('n=', n)
    def get_n():
        return n
    def set_n(value):
        nonlocal n
        n = value
    func.get_n = get_n
    func.set_n = set_n
    return func

f =sample()
f()
# n= 0
f.set_n(10)
f()
# n= 10
f.get_n()
# 10

def multiply():
    return (lambda x: i * x for i in range(4))

print([m(100) for m in multiply()])

def multiply():
    for i in range(4):
        yield lambda x: x * i

print([m(100) for m in multiply()])

from functools import partial
from operator import __mul__

def multiply():
    return [partial(__mul__, i) for i in range(4)]

print([m(100) for m in multiply()])

class myclass(object):
    def __init__(self):
        self.foo = 100

myinst = myclass()
isinstance(myinst, myclass)
# => True

type(1)
# => <class 'int'>
class A:
    pass
class B(A):
    pass
isinstance(A(), A)

type(df.weight[0])

class Base(object):
    def greet(self):
        print("hi, i am base")

class A(Base):
    def greet(self):
        Base.greet(self)
        print("hi, i am A")

a = A()
# => <__repl__.A object at 0x12018dcc0>
a.greet()
# => hi, i am base
#    hi, i am A

class Base(object):
    def __init__(self):
        print("enter Base")
        print("leave Base")

class A(Base):
    def __init__(self):
        print("enter A")
        Base.__init__(self) #调用父类的构造函数进行初始化
        print("leave A")

class B(Base):
    def __init__(self):
        print("enter B")
        Base.__init__(self) #调用父类的构造函数进行初始化
        print("leave B")

class C(A,B):
    def __init__(self):
        print("enter C")
        A.__init__(self) #调用父类A的构造函数进行初始化
        B.__init__(self) #调用父类B的构造函数进行初始化
        print("leave C")

c=C()
# => enter C
#    enter A
#    enter Base
#    leave Base
#    leave A
#    enter B
#    enter Base
#    leave Base
#    leave B
#    leave C

class Base(object):
    def __init__(self):
        print("enter Base")
        print("leave Base")


class A(Base):
    def __init__(self):
        print("enter A")
        super(A,self).__init__()
        print("leave A")

class B(Base):
    def __init__(self):
        print("enter B")
        super(B,self).__init__()
        print("leave B")

class C(A,B):
    def __init__(self):
        print("enter C")
        super(C,self).__init__()
        print("leave C")

c = C()
# => enter C
#    enter A
#    enter B
#    enter Base
#    leave Base
#    leave B
#    leave A
#    leave C
#    <__repl__.C object at 0x10898d3c8>
C.mro()
# => [__repl__.C, __repl__.A, __repl__.Base, __repl__.B, __repl__.Base, object]

super(type[, object-or-type])

class People:
    def __init__(self, name):
        self.name = name
    def say(self):
        print("我是人，名字为：", self.name)

class Animal:
    def __init__(self, food):
        self.food = food

    def display(self):
        print("我是动物，我吃", self.food)
#这里People, Animal 是父类
class Person(People, Animal):
    def __init__(self, name, food):
        super().__init__(name)
        Animal.__init__(self,food)

per = Person("zhangsan", "熟食")
per.say()
# => 我是人，名字为： zhangsan
per.display()
# => 我是动物，我吃 熟食

class FooParent(object):
    def __init__(self):
        self.parent = 'I\'m the parent.'
        print ('Parent')

    def bar(self,message):
        print ("%s from Parent" % message)

class FooChild(FooParent):
    def __init__(self):
        # super(FooChild,self) 首先找到 FooChild 的父类（就是类 FooParent），然后把类 FooChild 的对象转换为类 FooParent 的对象
        super(FooChild,self).__init__()
        print ('Child')

    def bar(self,message):
        super(FooChild, self).bar(message)
        print ('Child bar fuction')
        print (self.parent)

if __name__ == '__main__':
    fooChild = FooChild()
    fooChild.bar('HelloWorld')

class Bird:
    def __init__(self):
        self.hungry = True
    def eat(self):
        if self.hungry:
            print('sdd')
        else:
            print("no thx")

class SongBird(Bird):
    def __init__(self):
        super(SongBird,self).__init__()
        self.sound = 'sd'
    def sing(self):
        print(self.song())

sb = SongBird()
sb.sing()
sb.eat()

class Student(object):
    def __init__(self, name, score):
         self.name =name
         self.score = score

class Student(object):
    __slots__ = ('name', 'age')

s = Student()
s.name = 'Michael'
s.age = 25
s.score = 99
# => Traceback (most recent call last):
#      File "<stdin>", line 1, in <module>
#      File "/path/to/example", line 1, in <module>
#        # -*- org-confirm-babel-evaluate: nil; -*-
#    AttributeError: 'Student' object has no attribute 'score'

int('1234', base=8)

basket = ['apple', 'orange', 'apple']
set(basket)
#> {'apple', 'orange'}

list1 = [11,12,13,12,15]
[x for x in set(list1)]
# => [11, 12, 13, 15]