自学训练营学习7群

exercises/1901050090/1001S02E05_array.py

@@ -0,0 +1,26 @@
+list_a=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
+sort_list=list_a[::-1]
+print('翻转后的数组',sort_list)
+
+join_str=''.join([str(i) for i in sort_list])
+
+print('数组拼接成字符串',join_str)
+
+cut_str=join_str[2:8]
+
+print('取第三个到第八个字符',cut_str)
+
+rev_str=cut_str[::-1]
+
+print('翻转后的字符串',rev_str)
+
+int_value=int(rev_str)
+
+print('转化为int类型',int_value)
+
+print('转化为 二进制',bin(int_value))
+
+print('转化为 八进制',oct(int_value))
+
+print('转化为 十六进制',hex(int_value))
+

exercises/1901050090/1001S02E05_stats_text.py

@@ -0,0 +1,44 @@
+text = ''' 
+The Zen of Python, by Tim Peters
+Beautiful is better than ugly. 
+Explicit is better than implicit.
+Simple is better than complex. 
+Complex is better than complicated. 
+Flat is better than nested. 
+Sparse is better than dense. 
+Readability counts. 
+Special cases aren't special enough to break the rules.
+Although practicality beats purity. 
+Errors should never pass silently. 
+Unless explicitly silenced. 
+In the face of ambxiguity, refuse the temptation to guess.
+There should be one-- and preferably only one --obvious way to do it. 
+Although that way may not be obvious at first unless you're Dutch. 
+Now is better than never. Although never is often better than *right* now. 
+If the implementation is hard to explain, it's a bad idea. If the implementation is easy to explain,
+it may be a good idea. Namespaces are one honking great idea -- let's do more of those!
+'''
+elements=text.split()
+
+words=[]
+
+symbols=',.*-!'
+
+for  element in elements:
+   for symbol in symbols:
+       element =element.replace(symbol,'')
+   if len(element):
+       words.append(element)
+
+print('正常的英文单词',words)
+
+counter={}
+
+word_set=set(words)
+
+for word in word_set:
+    counter[word] =words.count(word)
+print('单词出现的次数',counter)
+
+print('出现次数从大到小输出',sorted(counter.items(),key=lambda x:x[1],reverse=True))
+

exercises/1901050090/1001S02E05_string.py

@@ -0,0 +1,41 @@
+text = ''' 
+The Zen of Python, by Tim Peters
+Beautiful is better than ugly. 
+Explicit is better than implicit.
+Simple is better than complex. 
+Complex is better than complicated. 
+Flat is better than nested. 
+Sparse is better than dense. 
+Readability counts. 
+Special cases aren't special enough to break the rules.
+Although practicality beats purity. 
+Errors should never pass silently. 
+Unless explicitly silenced. 
+In the face of ambxiguity, refuse the temptation to guess.
+There should be one-- and preferably only one --obvious way to do it. 
+Although that way may not be obvious at first unless you're Dutch. 
+Now is better than never. Although never is often better than *right* now. 
+If the implementation is hard to explain, it's a bad idea. If the implementation is easy to explain,
+it may be a good idea. Namespaces are one honking great idea -- let's do more of those!
+'''
+text1=text.replace('better','worse')
+
+print('better替换为worse',text1)
+
+words=text1.split()
+filtered=[]
+for word in words:
+   if word.find('ea')<0:
+     filtered.append(word)
+print('将单词中的ea剔除',filtered)
+
+counter={}
+
+words_set=set(filtered)
+swapcase=[i.swapcase() for i in filtered]
+
+print('进行大小写翻转',swapcase)
+
+print('单词按照a--z升序排列',sorted(swapcase))
+
+

exercises/1901050090/1001S02E06_stats_word.py

@@ -0,0 +1,65 @@
+def stats_text_en(text):
+    elements=text.split()
+    words=[]
+    symbols=',.*-!'
+    for element in elements:
+        for symbol in symbols:
+            element =element.replace(symbol,'')
+        if len(element):
+           words.append(element)
+    counter={}
+    word_set=set(words)
+    for word in word_set:
+       counter[word] =words.count(word)
+    return sorted(counter.items(),key=lambda x:x[1],reverse=True)
+
+def stats_text_cn(text):
+    cn_characters=[]
+    for character in text:
+        if '\u4e00' <=character<='\u9fff':
+            cn_characters.append(character)
+    counter={}
+    cn_characters_set=set(cn_characters)
+    for character in cn_characters_set:
+        counter[character]=cn_characters.count(character)
+    return sorted(counter.items(),key=lambda x:x[1],reverse=True)
+
+en_text = ''' 
+The Zen of Python, by Tim Peters
+Beautiful is better than ugly. 
+Explicit is better than implicit.
+Simple is better than complex. 
+Complex is better than complicated. 
+Flat is better than nested. 
+Sparse is better than dense. 
+Readability counts. 
+Special cases aren't special enough to break the rules.
+Although practicality beats purity. 
+Errors should never pass silently. 
+Unless explicitly silenced. 
+In the face of ambxiguity, refuse the temptation to guess.
+There should be one-- and preferably only one --obvious way to do it. 
+Although that way may not be obvious at first unless you're Dutch. 
+Now is better than never. Although never is often better than *right* now. 
+If the implementation is hard to explain, it's a bad idea. If the implementation is easy to explain,
+it may be a good idea. Namespaces are one honking great idea -- let's do more of those!
+'''
+
+cn_text='''
+昨天上午，根据导航显示的“玉泉路1号”，
+我来到植物园北门的一处停车场附近，
+来回找了十来分钟都没找到“故居”。
+植物园内的指路牌，
+也没有任何蔡元培故居的标志或提示。
+询问停车场工作人员，一连问了五人，无论是“玉泉路1号”还是“蔡元培故居”，
+他们都摇头说不知道；又去问植物园门口小卖部里的阿姨，一位阿姨说：“故居没听说过，
+你要么往植物园公交站那里去看看，好像有两幢别墅洋房。
+'''
+
+#if __name__== '_main_':
+en_result=stats_text_en(en_text)
+cn_result=stats_text_cn(cn_text)
+print('统计参数中每个英文单词出现的次数',en_result)
+print('统计参数中每个中文汉字单词出现的次数',cn_result)
+
+

exercises/1901050090/d010/main.py

@@ -0,0 +1,29 @@
+from  mymodule import stats_word
+from os import path
+import json
+import logging
+
+logging.basicConfig(
+  format='文件名:%(filename)s|line:%(lineno)d|message:%(message)s',level=logging.DEBUG)
+
+def load_file():
+    file_path=path.join(path.dirname(path.abspath(__file__)),'tang300.json')
+    print('当前读取文件路径:',file_path)
+
+    with open (file_path,'r',encoding='utf-8') as f:
+         return f.read()
+
+def main():
+    try:
+        data=load_file()
+       # print(data)
+        logging.info(data[0])
+        data1=json.loads(data)
+        poems=''
+        for item in data1:
+            poems += item.get('contents','')
+        logging.info(stats_word.stats_text_cn(poems,100))
+    except Exception as e:
+        logging.exception(e)
+if  __name__ == "__main__":
+   main()

exercises/1901050090/d010/mymodule/stats_word.py

@@ -0,0 +1,39 @@
+from collections import Counter
+import jieba
+
+def stats_text_en(text,count):
+    if not isinstance(text,str):
+        raise ValueError('参数必须是str类型,输入的类型 %s' %type(text))
+    elements=text.split()
+    words=[]
+    symbols=',.*-!'
+    for element in elements:
+        for symbol in symbols:
+            element =element.replace(symbol,'')
+        if len(element):
+           words.append(element)
+    return Counter(words).most_common(count)
+
+def stats_text_cn(text,count):
+    if not isinstance(text,str):
+        raise ValueError('参数必须是str类型,输入的类型 %s' %type(text))
+    words=jieba.cut(text)
+    cn_characters=[]
+    for i in words:
+        if len(i)>1:
+            cn_characters.append(i)
+    return Counter(cn_characters).most_common(count)
+
+
+#if __name__== '_main_':
+def stats_text(text,count):
+    if not isinstance(text,str):
+        raise ValueError('参数必须是str类型,输入的类型 %s' %type(text))
+    en_result=stats_text_en(text,count)
+    cn_result=stats_text_cn(text,count)
+   #print('统计参数中每个英文单词出现的次数',en_result)
+   #print('统计参数中每个中文汉字单词出现的次数',cn_result)
+
+    return en_result + cn_result
+
+