自学训练营学习19群+1901100240+Day14的作业

exercises/1901100240/1001S02E04_control_flow.py

@@ -5,20 +5,8 @@
     for j in range(1,i+1):      # The column start from 1 to i
         print(i,'*',j,'=',i*j,end='\t')     # \t to make double blank
     print('')       # Start a new line for each row i
-
-for i in range(1,10):
-    for j in range(1,i+1):
-
-        print(i,'*',j,'=',i*j,end='\t')
-
-        print(i,'*',j,'=',i*j,end='  ')
-
-    print('')
-
-
 print('')
 
-
 # Print multiplication table without even numbers by using the while loop
 print('The Multiplication Table Without Even Number')
 
@@ -30,19 +18,4 @@
             print(i,'*',j,'=',i*j,end='\t')     # \t to make double blank
             j += 1
         print("")       # Start a new line for each odd row
-
-i=1;
-while i<10 :
-    if i%2!=0:
-        j=1;
-        while j<=i:
-            if j%2!=0:
-
-                print(i,'*',j,'=',i*j,end='\t')
-
-                print(i,'*',j,'=',i*j,end='  ')
-
-            j+=1
-        print("")
-
-    i+=1
+    i += 1

exercises/1901100240/README.md

@@ -1,2 +1,91 @@
-# hello-world
-The project that usually used as the first repository
+# 课程总结
+
+# Github
+除编译器之外的重要协作软件Github，其功能类似于编程版本的Google Doc，可以允许多人同时编程。
+对每段更改保有历史记录，可回溯任意更改，避免代码被覆盖，且可回溯任意版本。
+Github建立在分支架构之上，主分支负责程序主体，dev分支则可供个人修改使用。个人修改的程序可通过pull request请求并入主分支。此功能保证多人同时协作的同时，亦可以避免程序被个人错误更改。
+通过folk加入其他repository，通过clone下载到本地，通过commit讲更改提交到主分支，通过pull request将修改提交。
+
+# Python 编译器
+Anaconda-Navigator 综合了数个python编译器。
+Visual Studio Code适合快速编译python shell内容，界面视觉效果较好。Spyder适合做短代码测试，界面一般。
+Visual Studio Cose 和 Spyder 保存的代码可以自动同步，方便转换。
+在python shell中需要print将数值显示，否则默认隐藏。
+
+# Hello Word
+约定俗称的语言入门所编写的第一个程序。
+Print作为python输出，在python shell内不print的内容默认隐藏。
+print时以'/t'控制同行空格打印。
+print时以''换新的一行。
+
+# 结构类型
+有字典（dictionary），元组(tuple)，列表(list)等储存单位。
+元组和列表是以位置储存元素，位置0对应第一元素，位置1对应第二元素，构成元素和位置一一对应的关系。
+字典是以key和item进行一一对应。
+元组内部数据无法更改。
+字典用于统计数字较为方便。
+
+# 循环
+for loop 和 while loop是最常用的两种循环模式。
+for loop不仅可以进行数字循环，也可以进行列表中元素的循环。
+while loop可以通过 while True 不断循环直到达成条件break。
+break会跳出最内层的循环。
+当过多循环减慢速度时，可采用numpy替代。
+
+# try...except
+阻止程序进入error，可保证代码继续运行。
+可暂时忽略无效代码。
+配合try...except然后print，可进行debuging。
+
+# Debug
+bug可以双轴分为四象限：横轴为显性，隐性；纵轴为持续性，间歇性。
+隐性bug比显性bug危险，间歇性bug比持续性危险。
+显性bug程序会直接报错，易于发现；隐性bug程序不会报错，但输出结果与预期不符，更难发现。
+持续性bug每次运行都会出现，间歇性只会在特殊情况下出现。
+千年虫既为典型隐性间歇性bug。
+Debug过程，需要讲代码分为不同模块，检测不同模块结果，发现模块结果错误既修改之。
+修改单一模块后，仍需整体运行以保证输出正确。
+
+# 排序
+计算机编程的重要组成部分。
+不同的排序方式会产生巨大的速度差别。
+
+# 模块
+将已经编写好的代码作为模块保存，可以在其他程序中进行调用。
+调用所需时间较长。
+可使得程序简洁明了。
+
+# 画图
+画图逻辑与matlab相似。
+需要导入matplotlib包函数。
+处理速度相对较慢。
+matplotlib包本身不支持中文，故需要通过一下代码导入中文：
+    lt.rcParams['font.family'] = ['sans-serif']
+    plt.rcParams['font.sans-serif'] = ['SimHei']
+
+# yagmail
+可进行收发邮件，配合try..except使用，可保证在程序出错时迅速收到提醒。
+邮件发送前邮箱需要授权Pop/SMTP。
+授权后以授权码代替密码。
+getpass默认隐藏密码，输入不可见。
+yagmail.SMTP()中host需要输入，否则出现超时错误。
+
+# getpass
+可用于获取密码，其特点为密码会呈现不可见状态，以保护密码安全。
+
+# wxpy
+微信外链程序，可编写自动回复脚本。
+基于webweixin进行，有可能被微信web封号。
+
+# jieba
+中文分词包，其共嫩建立在内含的词典之上。
+可通过jieba进行词频统计。
+jieba输出为不可见的list形式。
+
+# 自学相关
+凡是知道方向，大部分问题都可通过搜索引擎解决。
+寻找方向是自学的关键。
+自定一个Project，以解决问题的形式进行学习，倒逼学习相关知识。
+自学可能产生回音室效应，产生自循环，也就是倾向于用已知知识解决新问题，因此需要时时与他人对比。
+部分问题已经有人做出更好解答，不可迷恋自身能力。
+相对于系统化学习，可能漏过部分基础，使得无知于某些高效解决方案。

exercises/1901100240/d09/mymodule/main.py

@@ -3,8 +3,15 @@
 import stats_word
 import json
 
+import os
+
+# Imput the tang300.json documents and transfer into form of [{dict},{dict},{dict}]
+with open('Documents/GitHub/selfteaching-python-camp/exercises/1901100240/d09/mymodule/tang300.json','r+',encoding = "utf-8") as f:
+
+
 # Imput the tang300.json documents and transfer into form of [{dict},{dict},{dict}]
 with open('/Users/yanning/Documents/GitHub/selfteaching-python-camp/exercises/1901100240/d09/mymodule/tang300.json','r+',encoding = "utf-8") as f:
+
     tang_load = json.load(f)
 
 # Create a empty string and use it as storage.
@@ -13,8 +20,16 @@
 for unit in tang_load:      # Unit will be each dictionary in the list
     for char in unit.values():      # Char will be each values of the dictionary in form ['values','values','values','values']
         for content in str(char):       # content will be each element in the list Char
+
+            if ord(content) > 256 and content not in "！“”#$%&‘’（）*+，-。/：；、……<=>？@[]［］《》^_`{|}~\n":     # Only count the Chinese characters without any symbol
+                tang_text += str(content)       # Store the string into the storage string tang_text
+
+# Doing the statistic of frequncy of each Chinese characters and make it a list
+print(stats_word.stats_text_cn(tang_text,100))
+
             if ord(content) > 256 and content not in "！“”#$%&‘’（）*+，-。/：；、……<=>？@[]《》^_`{|}~\n":     # Only count the Chinese characters without any symbol
                 tang_text += str(content)       # Store the string into the storage string tang_text
 
 # Doing the statistic of frequncy of each Chinese characters and make it a dictionary
 print(stats_word.stats_text(tang_text,100))
+

exercises/1901100240/d10/mymodule/main.py

@@ -0,0 +1,20 @@
+# This algorithm is to do the statistic of frequency of Chinese characters in tang300
+# Using the user-defined algrorithm 'stats_word' and package 'json'
+import stats_word
+import json
+
+# Imput the tang300.json documents and transfer into form of [{dict},{dict},{dict}]
+with open('/Users/yanning/Documents/GitHub/selfteaching-python-camp/exercises/1901100240/d10/mymodule/tang300.json','r+',encoding = "utf-8") as f:
+    tang_load = json.load(f)
+
+# Create a empty string and use it as storage.
+tang_text=""
+# Using loop to combine all dict.values() into the storage string
+for unit in tang_load:      # Unit will be each dictionary in the list
+    for char in unit.values():      # Char will be each values of the dictionary in form ['values','values','values','values']
+        for content in str(char):       # content will be each element in the list Char
+            if ord(content) > 256 and content not in "！“”#$%&‘’（）*+，-。/：；、……<=>？@[]［］《》^_`{|}~\n":     # Only count the Chinese characters without any symbol
+                tang_text += str(content)       # Store the string into the storage string tang_text
+
+# Doing the statistic of frequncy of each Chinese characters and make it a list
+print(stats_word.stats_text_cn(tang_text,20))

exercises/1901100240/d10/mymodule/stats_word.py

@@ -0,0 +1,48 @@
+# This algorithm return the statistic result of the text
+# It provide the frequency of every single words
+from collections import Counter
+import jieba
+
+# Define the function
+def stats_text_en(en_text,count):
+    try:
+        en_text = "".join(i for i in en_text if 65 <= ord(i) <= 90 or 97 <= ord(i) <= 122).replace("\n", " ")     # ord() returns ASCII or Unicode value, less than 256 will provide the English words
+        # Count the word use Counter
+        try:
+            en_count = Counter(en_text).most_common(count)         # Create an counter
+            return en_count # Return the counter as result
+        except TypeError:
+            print("Error! The second input of function stats_text_en should be the form of integer. The input now is in ", type(en_text)," type. Please retry and enter a integer")
+    except TypeError:
+        print("Error! The first input of function stats_text_en should be the form of string. The input now is in ", type(en_text)," type. Please retry and enter a string")
+
+# This algorithm return the statistic result of the text in Chinese
+# It provide the frequency of every Chinese word using algrothm jieba
+def stats_text_cn(cn_text,count):
+    try:
+        cn_text = "".join(j for j in cn_text if ord(j) > 256)        # ord() returns ASCII or Unicode value, greater than 256 will provide the Chinese Character
+        # Seprate the words in cn_text
+        cn_list=jieba.cut(cn_text,cut_all=False)
+        # Selected the words which length greater than two
+        cn_two_list=[]
+        for unit in cn_list:
+            if len(unit) >= 2:
+                cn_two_list.append(unit)
+        try:
+            cn_count = Counter(cn_two_list).most_common(count)         # Create an counter
+            return   cn_count   # Return the counter as result
+        except TypeError:
+            print("Error! The second input of function stats_text_cn should be the form of integer. The input now is in ", type(cn_text)," type. Please retry and enter a integer")
+    except TypeError:
+        print("Error! The first input of function stats_text_cn should be the form of string. The input now is in ", type(cn_text)," type. Please retry and enter a string")
+
+# This function uses the following encoding: utf-8
+# Return a list of strings with English and Chinese words seperatly
+def stats_text(string,count):
+    # Seperate the Chinese and English words into two strings by checking ASCII value
+    try:
+        en_text = "".join(i for i in string if ord(i) < 256).replace("\n", " ")     # ord() returns ASCII or Unicode value, less than 256 will provide the English words
+        cn_text = "".join(j for j in string if ord(j) > 256)        # ord() returns ASCII or Unicode value, greater than 256 will provide the Chinese Character
+        return [stats_text_en(en_text,count),stats_text_cn(cn_text,count)]
+    except TypeError:
+        print("Error! The first input of function stats_text should be the form of string. The input now is in ", type(string)," type. Please retry and enter a string")

exercises/1901100240/d11/mymodule/main.py

@@ -0,0 +1,28 @@
+# Import the 微信文章 from the webside
+import requests
+response=requests.get('https://mp.weixin.qq.com/s/pLmuGoc4bZrMNl7MSoWgiA')
+
+# Transer the 微信文章 to string type
+from pyquery import PyQuery
+document = PyQuery(response.text) 
+content = document('#js_content').text()
+
+# Make the satistic of the frequency of the word and output as a string
+import stats_word
+stats = stats_word.stats_text_cn(content,100)
+string=str('')      # Create a string to store the result
+for unit in stats:
+    # Control the spacing by adding two more space it the word is less than two
+    if len(unit[0]) <= 2:
+        string += "'" + unit[0] + "'的频率是:    " + str(unit[1]) + "\n"
+    elif len(unit[0]) == 3:
+        string += "'" + unit[0] + "'的频率是:  " + str(unit[1]) + "\n"
+
+# Send the result to the email
+import yagmail
+import getpass
+sender = input('输⼊入发件⼈人邮箱:')
+password = getpass.getpass('输⼊入发件⼈人邮箱密码(可复制粘贴):')       # The password typed will be invisible but will still work
+recipients = input('输⼊入收件⼈人邮箱:')
+yag=yagmail.SMTP(sender,password,host='smtp.sina.com')
+yag.send(to=recipients,subject='自学训练营学习19群+Ningziyun',contents=string)

exercises/1901100240/d11/mymodule/stats_word.py

@@ -0,0 +1,48 @@
+# This algorithm return the statistic result of the text
+# It provide the frequency of every single words
+from collections import Counter
+import jieba
+
+# Define the function
+def stats_text_en(en_text,count):
+    try:
+        en_text = "".join(i for i in en_text if 65 <= ord(i) <= 90 or 97 <= ord(i) <= 122).replace("\n", " ")     # ord() returns ASCII or Unicode value, less than 256 will provide the English words
+        # Count the word use Counter
+        try:
+            en_count = Counter(en_text).most_common(count)         # Create an counter
+            return en_count # Return the counter as result
+        except TypeError:
+            print("Error! The second input of function stats_text_en should be the form of integer. The input now is in ", type(en_text)," type. Please retry and enter a integer")
+    except TypeError:
+        print("Error! The first input of function stats_text_en should be the form of string. The input now is in ", type(en_text)," type. Please retry and enter a string")
+
+# This algorithm return the statistic result of the text in Chinese
+# It provide the frequency of every Chinese word using algrothm jieba
+def stats_text_cn(cn_text,count):
+    try:
+        cn_text = "".join(j for j in cn_text if ord(j) > 256)        # ord() returns ASCII or Unicode value, greater than 256 will provide the Chinese Character
+        # Seprate the words in cn_text
+        cn_list=jieba.cut(cn_text,cut_all=False)
+        # Selected the words which length greater than two
+        cn_two_list=[]
+        for unit in cn_list:
+            if len(unit) >= 2:
+                cn_two_list.append(unit)
+        try:
+            cn_count = Counter(cn_two_list).most_common(count)         # Create an counter
+            return   cn_count   # Return the counter as result
+        except TypeError:
+            print("Error! The second input of function stats_text_cn should be the form of integer. The input now is in ", type(cn_text)," type. Please retry and enter a integer")
+    except TypeError:
+        print("Error! The first input of function stats_text_cn should be the form of string. The input now is in ", type(cn_text)," type. Please retry and enter a string")
+
+# This function uses the following encoding: utf-8
+# Return a list of strings with English and Chinese words seperatly
+def stats_text(string,count):
+    # Seperate the Chinese and English words into two strings by checking ASCII value
+    try:
+        en_text = "".join(i for i in string if ord(i) < 256).replace("\n", " ")     # ord() returns ASCII or Unicode value, less than 256 will provide the English words
+        cn_text = "".join(j for j in string if ord(j) > 256)        # ord() returns ASCII or Unicode value, greater than 256 will provide the Chinese Character
+        return [stats_text_en(en_text,count),stats_text_cn(cn_text,count)]
+    except TypeError:
+        print("Error! The first input of function stats_text should be the form of string. The input now is in ", type(string)," type. Please retry and enter a string")

exercises/1901100240/d12/mymodule/main.py

@@ -0,0 +1,26 @@
+# Using wxpy to do the automatic reaply for sharing type
+from wxpy import *
+bot = Bot()
+Chats=bot.friends()
+# Doing the statistic for SHARING type
+@bot.register(Chats,SHARING)
+def print_statis(msg):
+    # Import the 微信文章 from the chat
+    import requests
+    response=requests.get(msg.url)
+    # Transer the 微信文章 to string type
+    from pyquery import PyQuery
+    document = PyQuery(response.text) 
+    content = document('#js_content').text()
+    # Make the satistic of the frequency of the word and output as a string
+    import stats_word
+    stats = stats_word.stats_text_cn(content,100)
+    string=str('')      # Create a string to store the result
+    for unit in stats:
+    # Control the spacing by adding two more space it the word is less than two
+        if len(unit[0]) <= 2:
+            string += "'" + unit[0] + "'的频率是:    " + str(unit[1]) + "\n"
+        elif len(unit[0]) == 3:
+            string += "'" + unit[0] + "'的频率是:  " + str(unit[1]) + "\n"
+    msg.reply(string)
+embed()

exercises/1901100240/d12/mymodule/stats_word.py

@@ -0,0 +1,48 @@
+# This algorithm return the statistic result of the text
+# It provide the frequency of every single words
+from collections import Counter
+import jieba
+
+# Define the function
+def stats_text_en(en_text,count):
+    try:
+        en_text = "".join(i for i in en_text if 65 <= ord(i) <= 90 or 97 <= ord(i) <= 122).replace("\n", " ")     # ord() returns ASCII or Unicode value, less than 256 will provide the English words
+        # Count the word use Counter
+        try:
+            en_count = Counter(en_text).most_common(count)         # Create an counter
+            return en_count # Return the counter as result
+        except TypeError:
+            print("Error! The second input of function stats_text_en should be the form of integer. The input now is in ", type(en_text)," type. Please retry and enter a integer")
+    except TypeError:
+        print("Error! The first input of function stats_text_en should be the form of string. The input now is in ", type(en_text)," type. Please retry and enter a string")
+
+# This algorithm return the statistic result of the text in Chinese
+# It provide the frequency of every Chinese word using algrothm jieba
+def stats_text_cn(cn_text,count):
+    try:
+        cn_text = "".join(j for j in cn_text if ord(j) > 256)        # ord() returns ASCII or Unicode value, greater than 256 will provide the Chinese Character
+        # Seprate the words in cn_text
+        cn_list=jieba.cut(cn_text,cut_all=False)
+        # Selected the words which length greater than two
+        cn_two_list=[]
+        for unit in cn_list:
+            if len(unit) >= 2:
+                cn_two_list.append(unit)
+        try:
+            cn_count = Counter(cn_two_list).most_common(count)         # Create an counter
+            return   cn_count   # Return the counter as result
+        except TypeError:
+            print("Error! The second input of function stats_text_cn should be the form of integer. The input now is in ", type(cn_text)," type. Please retry and enter a integer")
+    except TypeError:
+        print("Error! The first input of function stats_text_cn should be the form of string. The input now is in ", type(cn_text)," type. Please retry and enter a string")
+
+# This function uses the following encoding: utf-8
+# Return a list of strings with English and Chinese words seperatly
+def stats_text(string,count):
+    # Seperate the Chinese and English words into two strings by checking ASCII value
+    try:
+        en_text = "".join(i for i in string if ord(i) < 256).replace("\n", " ")     # ord() returns ASCII or Unicode value, less than 256 will provide the English words
+        cn_text = "".join(j for j in string if ord(j) > 256)        # ord() returns ASCII or Unicode value, greater than 256 will provide the Chinese Character
+        return [stats_text_en(en_text,count),stats_text_cn(cn_text,count)]
+    except TypeError:
+        print("Error! The first input of function stats_text should be the form of string. The input now is in ", type(string)," type. Please retry and enter a string")