Day 9 work(Student ID:PanChuang2019) 学习群14群

exercises/PanChuang2019/D08/main.py

@@ -22,9 +22,11 @@ def test_logger():
 
 
 if __name__=="__main__":
-    # stats_word.stats.text(1)
+
+    #stats_word.stats_text(1)
     test_traceback()
     test_logger()
 
 
+
 

exercises/PanChuang2019/D09/main.py

@@ -0,0 +1,40 @@
+from mymodule import stats_word
+from os import path
+import json
+import re
+import logging
+
+
+logging.basicConfig(
+    format='file:%(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('当前文件路径：',__file__,'\n读取文件路径:',file_path)
+    with open(file_path,'r',encoding='utf-8') as f:
+        return f.read()
+
+def merge_poems(data):
+    poems = ''
+    for item in data:
+        poems += item.get('contents','')
+    return poems
+
+def main():
+    try:
+        data=load_file()
+        logging.info(data[0])
+        poems = merge_poems(json.loads(data))
+        logging.info('result ==> %s',stats_word.stats_text_cn(poems,100))
+    except Exception as e:
+        logging.exception(e)
+
+
+if __name__=="__main__":
+    main()
+
+
+
+
+

exercises/PanChuang2019/D09/mymodule/stats_word.py

@@ -0,0 +1,27 @@
+from collections import Counter  
+
+def stats_text_en(text,count):
+    elements= text.split()
+    words=[]
+    symbols=',.*-!'
+    for element in elements:
+        for symbol in symbols:
+            element=element.replace(symbol,'')
+        if len(element) and element.isascii():
+            words.append(element)
+    return Counter(words).most_common(count)
+
+def stats_text_cn(text,count):
+    cn_characters=[]
+    for character in text:
+        if '\u4e00'<= character<='\u9fff':
+            cn_characters.append(character)
+    return Counter(cn_characters).most_common(count)
+
+#合并中文词频和英文词频的结果
+def stats_text(text,count):
+    if not isinstance(text,str):
+        raise ValueError('参数必须是str类型，输入类型%s' % type(text))
+    return stats_text_cn(text,count) + stats_text_en(text,count)
+
+

exercises/PanChuang2019/D10/main.py

@@ -0,0 +1,40 @@
+from mymodule import stats_word
+from os import path
+import json
+import re
+import logging
+
+
+logging.basicConfig(
+    format='file:%(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('当前文件路径：',__file__,'\n读取文件路径:',file_path)
+    with open(file_path,'r',encoding='utf-8') as f:
+        return f.read()
+
+def merge_poems(data):
+    poems = ''
+    for item in data:
+        poems += item.get('contents','')
+    return poems
+
+def main():
+    try:
+        data=load_file()
+        #logging.info(data[0])
+        poems = merge_poems(json.loads(data))
+        logging.info('result ==> %s',stats_word.stats_text_cn(poems,20))
+    except Exception as e:
+        logging.exception(e)
+
+
+if __name__=="__main__":
+    main()
+
+
+
+
+

exercises/PanChuang2019/D10/mymodule/stats_word.py

@@ -0,0 +1,29 @@
+from collections import Counter  
+import jieba
+
+def stats_text_en(text,count):
+    elements= text.split()
+    words=[]
+    symbols=',.*-!'
+    for element in elements:
+        for symbol in symbols:
+            element=element.replace(symbol,'')
+        if len(element) and element.isascii():
+            words.append(element)
+    return Counter(words).most_common(count)
+
+def stats_text_cn(text,count):
+    tmp=[]
+    words=jieba.cut(text)
+    for i in words:
+        if len(i)>=2:
+            tmp.append(i)
+    return Counter(tmp).most_common(count)
+
+#合并中文词频和英文词频的结果
+def stats_text(text,count):
+    if not isinstance(text,str):
+        raise ValueError('参数必须是str类型，输入类型%s' % type(text))
+    return stats_text_cn(text,count) + stats_text_en(text,count)
+
+