python杂记

基础

print

camels = 42
water = 0.001

print("There are %d camelss"%(camels))

print("There are %d camels and also %g litres of water"%(2334343, 0.0011))

print("There are {} camels and {} litres of water".format(water, camels))

print("There are {cam} camels and {h20} litres of water".format(h20=water, cam=camels ))

var1 = "This will have {} dogs and {} cats"

print(var1.format(3, 4))

print(var1.format(100, 45))

F-Strings from python3.6

var2 = f"There are {camels} camels and {water} volume of water"
print(var2)

Try except

try:
    fin = open('worerererereerererds.txt')
    print("file was succesfully opened!!!")
except:
    print("hey dude, give a better filename")

a = 10 
b = 20

print(a+b)

pin = 90

try:
    print(pinx) # throws Name Error
    
except SyntaxError:
    print("succesfully caught the syntax error")

except NameError:
    print("hey now i am catching the name error")

else:
    pass

finally:

Turtle基础

新建turtle对象

import turtle
import math 
bob = turtle.Turtle()

画正方形

def rectangle(t,length):
  for i in range(4):
    t.fd(length)
    t.lt(90)

画圆形

def circle(t,r):
  n_of_edge=70
  circle_length = 2*math.pi*r
  angle = 360.0/n_of_edge
  length_of_edge = circle_length/n_of_edge
  for _ in range(int(n_of_edge)):
    t.fd(length_of_edge)
    t.lt(angle)

画圆弧

def arc(t,r):
  n_of_edge=700
  circle_length = 2*math.pi*r
  angle = 360.0/n_of_edge
  length_of_edge = circle_length/n_of_edge
  for _ in range(int(n_of_edge)/2):
    t.fd(length_of_edge)
    t.lt(angle)

进阶

Time 对象-打印（格式化输出）

class Time(object):
    def __init__(self,hour,minute,second):
        self.hour = hour
        self.minute = minute
        self.second = second
    def print_time(self):
        print("%.2d:%.2d:%.2d"%(self.hour,self.minute,self.second))

c = Time(111.233333,.233333,.233333)
c.print_time()

output: 111:00:00

关于对象的理解（每个object其实里面都内置一个字典）

假设说不要初始化函数

class Time(object):
#     def __init__(self,hour,minute,second):
#         self.hour = hour
#         self.minute = minute
#         self.second = second
    def print_time(self):
        print("%.2d:%.2d:%.2d"%(self.hour,self.minute,self.second))
    

此时：

c = Time(111.233333,.233333,.233333)
c.print_time()

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-24-a6174a4498c2> in <module>
----> 1 c = Time(111.233333,.233333,.233333)
      2 c.print_time()

TypeError: Time() takes no arguments

通过**.**可以直接给对象c中的字典赋值。

c.hour = 111
c.minute = 222
c.second = 99
c.print_time()

output: 
111:222:99

p1.__dict__

output: {'hour': 111, 'minute': 222, 'second': 99}

如何定义自己的包，导入包并运行包中的函数，调用包中的常量

新建一个文件my_own_add.py

var_1 = 250
var_2 = 360
def my_add(a,b):
	return a+b 

此时使用如下命令调用包中的一个函数my_add(a,b)和常量var_1,var_2

$ python3 
Python 3.7.3 (default, Mar  6 2020, 22:34:30) 
[Clang 11.0.3 (clang-1103.0.32.29)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> import my_own_add
>>> my_own_add.var_1
250
>>> my_own_add.var_2
360
>>> my_own_add.my_add(11111,22222)
33333

#直接指定要import这个函数，这样使用起来就不用加点
>>> from my_own_add import my_add
>>> my_add(222,333)
555

一些操作的源代码

读取txt 并进行分词：

如果说一个文件特别杂乱

f_txt = open("words.txt")
String_txt = f_txt.read()
import re
#Set stop words
# filter = ['the', 'a', 'an','and','of','in','The','to','s']
filter = []
String_txt = re.sub("[\n\s+\.\!\/_,$%^*(+\"\')]+|[+——()?【】“”！，。？、~@#￥%……&*:（）]+"," ",String_txt)
list_txt = String_txt.split(' ')

如果一个文件特别工整，比如这样

aa
aah
aahed
aahing
aahs
aal
aalii
aaliis

可以用：

#read the word list
f_txt = open("words.txt")
String_txt = f_txt.read()
# to lower_case
String_txt = String_txt.lower()


list_txt = String_txt.split('\n')

统计词频, 生成字典并且逆序排序，返回列表（因为字典没有顺序）：

def most_frequent(string_input):
    list_txt = string_input.split(' ')
    dict_count = {}
    for _ in list_txt:
        if _ not in filter:
#         print(_)
            dict_count[_] = 0
    for _ in list_txt:
         if _ not in filter:
#         print(_)
            dict_count[_] += 1
    dict_count_sorted = sorted(dict_count.items(), key=lambda item: item[1],reverse=True)    
#     print(dict_count)
    return (dict_count,dict_count_sorted)

从一个“根路径”开始，读取他所有的旗下的子路径，并打印出所有文件的地址：

dir_demo = '/Users/lianda_duan/Downloads/lab_4_assignment'
import os
file_path_list = []
def walk(dirname = dir_demo):
    for name in os.listdir(dirname):
        path = os.path.join(dirname, name)
        if os.path.isfile(path):
#             print(path)
            file_path_list.append(path)
        else:
            walk(path)
            
walk()
for _ in file_path_list:
    print(_)

从这些路径中，筛选mp3文件

file_path_list = [i  for i in file_path_list if str(i).split("/")[-1].split(".")[-1] == 'mp3']
for _ in file_path_list:
    print(_)

对文件内容一一二进制比对，返回一个字典说明比对结果

import filecmp
list_check = list(range(len(file_path_list)))
# list_check = 
# [i if i.split("/")[-1]=='mp3' for i in list_check]


dup_dic = {}
# initialize dic
for _ in [_.split("/")[-1] for _ in file_path_list]:
    dup_dic[_] = []
    
# print(dup_dic)

for index_file_path_be_compared in list_check:
#     if index_file_path_be_compared is not len(file_path_list)-2:
    for index_file_dest in list_check:
        if filecmp.cmp(file_path_list[index_file_path_be_compared], file_path_list[index_file_dest]):
            dup_dic[file_path_list[index_file_path_be_compared].split("/")[-1]].append(file_path_list[index_file_dest].split("/")[-1])
#                 list_check.pop(index_file_dest)
# print(filecmp.cmp(c_1, c_2))
# print(filecmp.cmp(c_1, c_3))
for _ in dup_dic.items():
    print(_,'\n')

获取当前python的工作路径

import sys
print(sys.executable)

例如所得的路径为：

/Users/lianda_duan/opt/anaconda3/bin/python

在工作路径安装新的包

如果想在这个路径下调用pip安装一个包，可以使用以下指令：

#Run terminal command to install wordcloud in current python working environment.
!/Users/lianda_duan/opt/anaconda3/bin/python -m pip install wordcloud

绘制词云图

from PIL import Image
from wordcloud import WordCloud
import matplotlib.pyplot as plt

#The higher the frequence, the larger front size the words will be in.

wc = WordCloud(background_color="yellow",width=3000,height=2000, max_words=200,relative_scaling=0.8,normalize_plurals=False).generate_from_frequencies(dictionary_for_word_cloud)
plt.imshow(wc)

其中：

dictionary_for_word_cloud

是一个字典。

写文件

fout = open("newFileMadeByMe.txt", mode='w')

fout.write("this is the first line")
fout.write("this is the first line")

Git 命令简明

将本地文件夹关联到远程仓库

1、（先进入项目文件夹）通过命令 git init 把这个目录变成git可以管理的仓库

git init

2、把文件添加到版本库中，使用命令 git add .添加到暂存区里面去，不要忘记后面的小数点“.”，意为添加文件夹下的所有文件

git add .

3、用命令 git commit告诉Git，把文件提交到仓库。引号内为提交说明

git commit -m 'first commit'

4、关联到远程库

git remote add origin 你的远程库地址
如：

git remote add origin https://github.com/githubusername/demo.git

5、获取远程库与本地同步合并（如果远程库不为空必须做这一步，否则后面的提交会失败）

git pull --rebase origin master

6、把本地库的内容推送到远程，使用 git push命令，实际上是把当前分支master推送到远程。执行此命令后会要求输入用户名、密码，验证通过后即开始上传。

git push -u origin master

*、状态查询命令

git status

git查看远程仓库地址命令

git remote -v

斐波那契数列

# 递归
def Fibonacci_Recursion_tool(n):
    if n <= 0:
        return 0
    elif n == 1:
        return 1
    else:
        return Fibonacci_Recursion_tool(n - 1) + Fibonacci_Recursion_tool(n - 2)
      
      
      
def Fibonacci_Recursion(n):
    result_list = []
    for i in range(1, n + 1): result_list.append(Fibonacci_Recursion_tool(i))
    return result_list

将远程仓库复制到本地

git clone https://github.com/inwk6312-summer2020/gwertfdfdty.git