【1901100050】自学训练营学习13群 DAY10

exercises/1901100050/d08/main.py

@@ -15,7 +15,9 @@ def test_traceback():
 def test_logger():
     try:
         stats_word.stats_text(1)
-    except exception as e:
+
+    except Exception as e:
+
         # print('test_logger =>',e)
         logger.exception(e)
 

exercises/1901100050/d09/main.py

@@ -0,0 +1,35 @@
+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(date):
+    poems = ''
+    for item in date:
+        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/1901100050/d09/mymodule/stats_word.py

@@ -0,0 +1,34 @@
+from collections import Counter
+
+# 统计参数中每个英⽂单词出现的次数
+def stats_text_en(text, count):
+    elements = text.split()
+    words = []
+    symbols = ',.*-!'
+    for element in elements:
+        for symbol in symbols:
+            element = element.replace(symbol, '')
+        # 用 str 类型 的 isascii 方法判断是否是英文单词
+        if len(element) and element.isascii():
+            words.append(element)
+    return Counter(words).most_common(count)
+
+
+# 统计参数中每个中文汉字出现的次数
+def stats_text_cn(text, count):
+    cn_characters = []
+    for character in text:
+        # unicode 中 中文 字符的范围
+        if '\u4e00' <= character <= '\u9fff':
+            cn_characters.append(character)
+    return Counter(cn_characters).most_common(count)
+
+def stats_text(text):
+    '''
+    合并 英文词频 和 中文词频 的结果
+    '''
+    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_en(text, count) + stats_text_cn(text, count)
+
+

exercises/1901100050/d10/main.py

@@ -0,0 +1,33 @@
+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(date):
+    poems = ''
+    for item in date:
+        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/1901100050/d10/mymodule/stats_word.py

@@ -0,0 +1,35 @@
+from collections import Counter
+import jieba
+
+# 统计参数中每个英⽂单词出现的次数
+def stats_text_en(text, count):
+    elements = text.split()
+    words = []
+    symbols = ',.*-!'
+    for element in elements:
+        for symbol in symbols:
+            element = element.replace(symbol, '')
+        # 用 str 类型 的 isascii 方法判断是否是英文单词
+        if len(element) and element.isascii():
+            words.append(element)
+    return Counter(words).most_common(count)
+
+
+# 统计参数中每个中文汉字出现的次数
+def stats_text_cn(text, count):
+    words = jieba.cut(text)
+    tmp = []
+    for i in words:
+        if len(i) > 1:
+            tmp.append(i)
+    return Counter(tmp).most_common(count)
+
+def stats_text(text):
+    '''
+    合并 英文词频 和 中文词频 的结果
+    '''
+    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_en(text, count) + stats_text_cn(text, count)
+
+