刚接触Python3版本的小伙伴们,编程时会对于Python中各种数据结构如:array、list、dict、set以及字符串str操作都不太熟悉。同时类似于Python网络编程、文件读取、数据库连接以及协程这些编程模板基本也都是固定的,本文便就这些方面进行总结,希望让大家进行Python3编程时能够更加的便捷,可以直接复制粘贴而不用每次都手敲了,好下面进入正题啦!
一、list各种操作
1、list和array之间相互转换及遍历
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from numpy import *
#python 中list和array之间的相互转换以及list和array的遍历
testList=[[1,2,3],[4,5,6]]
#将list转化成array
testArray=array(testList)
for i in range(testArray.shape[0]):
for j in range(testArray.shape[1]):
print(testArray[i,j],' ',end='')
print()
print()
#将array转化成list
toList=testArray.tolist()
for i in range(len(toList)):
for word in toList[i]:
print(word,' ',end='')
print()
2、查找返回list中出现次数最多的那个元素
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#查询list中出现次数最多的元素
def top(list):
s=set(list)
d={}
for i in s:
d[i]=list.count(i)
print('下面输出的是前k个字典:',end='')
print(d)
list1=[]
for i in d.values():
list1.append(i)
ma=max(list1)
key_max=get_keys(d,ma)
string=key_max[0]
return string
#get_keys实现已知dict的value返回key
def get_keys(d,value):
return [k for k,v in d.items() if v==value]
if __name__ == '__main__':
listTest=[1,1,1,2,2,3,4,5,5,6,6,6,6,6,7]
s=top(listTest)
print('出现次数最多的元素: ', s)
二、array各种操作
1、Python3中如何自定义结构化数组
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from numpy import *
import pandas as pd
#通过下面这种方式定义结构数组,自定义结构数组
dtypes={'name':'s32','age':'i','weight':'f'}
mydata=pd.DataFrame([['zhang',32,65.5],['wang',24,55.2]],columns=['name','age','weight'])
print(mydata)
t=mydata.shape
for i in mydata.columns:
print('')
for j in range(mydata.ndim):
print(' '+str(mydata[i][j]),end='')
2、array切片操作
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from numpy import *
a=arange(10)**3
for element in a.flat:
print(' %d' %element,end='')
print('')
for i in range(a.size):
print(' %d' %a[i],end='')
print('')
print(a[2:5]) #数组的切片处理
a[:6:2]=-1000 #省略的位置代表0
print(a)
m=a[: :-1] #将一维数组反转
print(m)
三、dict各种操作
1、如何根据dict字典的value反去除key
def get_keys(d,value):
return [k for k,v in d.items() if v==value]
2、dict中存取key、value各种函数使用
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import operator
a_dict={1:{'name':'Mary'},2:'python',3:'google','email':'qq.com'}
print(a_dict)
print(a_dict.items())
#字典的三个函数 keys()、values()、items()
print(a_dict.keys())
print(a_dict.values())
print(a_dict.items())
#两种遍历dict中key的方式
for k in a_dict.keys():
print(k)
for k in a_dict:
print(k)
print()
#两种遍历dict中value的方式
for v in a_dict.values():
print(v)
for k in a_dict.keys():
print(a_dict[k])
print()
#Python字典调用items()函数以列表返回可遍历的(键,值)元组数组
for k,v in a_dict.items():
print(str(k)+' : '+str(v))
for k in a_dict:
print(str(k)+' : '+str(a_dict[k]))
print()
#get函数的使用,用来取出dict的value的
for k in a_dict.keys():
print(a_dict.get(k))
print('字典的存储的数据量为: %d' %len(a_dict))
四、set各种操作
1、set声明操作集合和list之间转化
import numpy as np
import operator
#set中只存储key,不存储value,并且key不能够重复
#下面给出Python中声明set的方法
s1=set([])
while len(s1)!=5:
a=np.random.randint(0,10)
s1.add(a)
print(s1)
s2=set([])
for i in range(10):
s2.add(i)
print(s2)
#两个set进行相减操作
s3=s2-s1
print(s3)
#将set转化成list
list1=list(s1)
list2=list(s3)
for i in range(len(list1)):
print(list1[i])
for j in range(len(list2)):
print(list2[j])
五、字符串操作
1、Python中字符串相等判断
str1='csdn'
str2='csdn'
#Python中和Java不同,字符串相等直接使用‘==’
if str1==str2:
print('相等')
else:
print('不相等')
2、将文本中有效单词取出,过滤掉空格和其他符号
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import re
#在表示完整的文件路径需要在前面加 r
file_name = r'E:\python\Python_project\machine learning\bayes\email\ham\23.txt'
lines_count = 0
words_count = 0
chars_count = 0
words_dict = {}
lines_list = []
with open(file_name, 'r') as f:
print(f)
for line in f:
#print('line: ',line)
lines_count = lines_count + 1
chars_count = chars_count + len(line)
#这里的findall函数特殊
match = re.findall(r'[^a-zA-Z0-9]+', line)
#print('match: ',match)
for i in match:
# 只要英文单词,删掉其他字符
line = line.replace(i, ' ')
#split()返回的是 list
lines_list = line.split()
#下面的i表示的是单词,所以字典的key是单词,value是单词出现的次数
for i in lines_list:
if i not in words_dict:
words_dict[i] = 1
else:
words_dict[i] = words_dict[i] + 1
print('words_count is %d' %len(words_dict))
print('lines_count is %d' %lines_count)
print('chars_count is %d' %chars_count)
print(words_dict.keys())
print(words_dict.values())
for k,v in words_dict.items():
print(k,v)
六、json使用
1、Python对象和json对象相互转化
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import json
#python对象--->json对象 json.dumps(python对象)
#Python对象<---json对象 json.loads(json对象)
#下面是字典类型的对象和json对象之间的互相转化
d = dict(name='Bob', age=20, score=88)
data = json.dumps(d)
print('JSON Data is a str:', data)
reborn = json.loads(data)
print(reborn)
2、利用一个函数定制json序列化
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import json
#Python中类对象<--->json对象
#利用一个函数定制json序列化
class Student(object):
def __init__(self, name, age, score):
self.name = name
self.age = age
self.score = score
def __str__(self):
return 'Student object (%s, %s, %s)' % (self.name, self.age, self.score)
s = Student('Bob', 20, 88)
std_data = json.dumps(s, default=lambda obj: obj.__dict__)
print('Dump Student:', std_data)
rebuild = json.loads(std_data, object_hook=lambda d: Student(d['name'], d['age'], d['score']))
print(rebuild)
七、读取文件操作
1、一次性读取所有文件内容到内存:read()
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from datetime import datetime
#read函数对于文件过大时,会导致内存爆炸的!
with open('test1.txt','r') as f:
s=f.read()
print('open for read')
print(s)
2、每次读取一行文件内容:readline()
l=[]
try:
f=open('test2_data.txt','r')
s=f.readline()
#每次读取一行文件内容,循环读取
while len(s)!=0:
list1=[]
list1=s.split('\t')
#将读取的文件内容保存到list中
l.append(list1)
s=f.readline()
#print(l)
except:
if f:
f.close()
3、一次性读取所有文件内容但是按行返回list:readlines() 很好用
f=open('testSet.txt')
for line in f.readlines():
lineList=line.strip().split()
print(lineList)
4、向文件中写信息
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from datetime import datetime
with open('test.txt', 'w') as f:
f.write('今天是 ')
f.write(datetime.now().strftime('%Y-%m-%d'))
八、数据库操作
1、Python数据库的连接模板
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#导入mysql驱动
import mysql.connector
#连接mysql数据库
conn=mysql.connector.connect(user='root',password='',db='test')
cur=conn.cursor()
#查询多条记录
info=cur.fetchmany(5)
for ii in info:
print(ii)
#运行查询的另一种方式
cur.execute("select * from user")
values=cur.fetchall()
print(values)
#提交事务
conn.commit()
conn.close()
cur.close()
九、TCP网络通讯
1、服务器端server
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import socket,threading,time
def tcplink(socket,addr):
print('Accept new connection from %s:%s...' %addr)
sock.send(b'Welcome!')
while True:
data=sock.recv(1024)
time.sleep(1)
if not data or data.decode('utf-8')=='exit':
break
sock.send(('Hello,%s!' % data.decode('utf-8')).encode('utf-8'))
sock.close()
print('Connection from %s:%s closed' %addr)
if __name__=='__main__':
# 创建一个socket:
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
#监听窗口
#其中IP地址和端口号使用tuple的形式
s.bind(('127.0.0.1',9999))
#开始监听端口
s.listen(5)
print('waiting for connection...')
#永久循环接受客服端连接
while True:
#接受一个新连接
sock,addr=s.accept()
#创建新线程处理TCP连接
t = threading.Thread(target=tcplink, args=(sock, addr))
t.start()
2、客服端client
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import socket
# 创建一个socket:
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
#建立连接
s.connect(('127.0.0.1',9999))
#接受欢迎消息
print(s.recv(1024).decode('utf-8'))
for data in [b'Michael',b'Tracy',b'Sarah']:
s.send(data)
print(s.recv(1024).decode('utf-8'))
s.send(b'exit')
s.close()
十、Python协程async
1、Python中协程比使用多线程更高效
如是Python3.5及以上版本,代码如下:
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import asyncio
async def wget(host):
print('wget %s...' % host)
connect = asyncio.open_connection(host, 80)
reader,writer=await connect
header = 'GET / HTTP/1.0\r\nHost: %s\r\n\r\n' % host
writer.write(header.encode('utf-8'))
await writer.drain()
while True:
line=await reader.readline()
if line== b'\r\n':
break
print('%s header > %s' % (host, line.decode('utf-8').rstrip()))
writer.close()
loop = asyncio.get_event_loop()
tasks = [wget(host) for host in ['www.sina.com.cn', 'www.sohu.com', 'www.163.com']]
loop.run_until_complete(asyncio.wait(tasks))
loop.close()
如果是Python3.4的版本,代码如下:
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import asyncio
@asyncio.coroutine
def wget(host):
print('wget %s...' % host)
connect = asyncio.open_connection(host, 80)
reader, writer = yield from connect
header = 'GET / HTTP/1.0\r\nHost: %s\r\n\r\n' % host
writer.write(header.encode('utf-8'))
yield from writer.drain()
while True:
line = yield from reader.readline()
if line == b'\r\n':
break
print('%s header > %s' % (host, line.decode('utf-8').rstrip()))
# Ignore the body, close the socket
writer.close()
loop = asyncio.get_event_loop()
tasks = [wget(host) for host in ['www.sina.com.cn', 'www.sohu.com', 'www.163.com']]
loop.run_until_complete(asyncio.wait(tasks))
loop.close()
以上内容便是Python3.x常用数据结构和常用模板的总结,当然并不可能很全啦,后期如果有比较好的模板还会继续更新,小伙伴们如果有比较好的模板也欢迎添加分享!