课后作业3
- 学号:2017****07043
- 姓名:张淑慧
2) 程序分析
# filename: word_freq.py # 阅读注释,在所有pass处删除pass,添加代码 from string import punctuation def process_file(dst): # 读文件到缓冲区 try: # 打开文件 dkwj = open(dst,'r') except IOError as s: print (s) return None try: # 读文件到缓冲区 bvffer = dkwj.read() except: print ('Read File Error!') return None dkwj.close() return bvffer def process_buffer(bvffer): if bvffer: word_freq = {} # 下面添加处理缓冲区 bvffer代码,统计每个单词的频率,存放在字典word_freq bvffer = bvffer.lower() for i in '“‘!;,.?”[]': bvffer = bvffer.replace(i, " ") words = bvffer.strip().split() for word in words: word_freq[word] = word_freq.get(word, 0) + 1 return word_freq def output_result(word_freq): if word_freq: sorted_word_freq = sorted(word_freq.items(), key=lambda v: v[1], reverse=True) for item in sorted_word_freq[:10]: # 输出 Top 10 的单词 print(item) def main(): dst = "Gone_with_the_wind.txt" bvffer = process_file(dst) word_freq = process_buffer(bvffer) output_result(word_freq) if __name__ == "__main__": import argparse parser = argparse.ArgumentParser() parser.add_argument('dst') args = parser.parse_args() dst = args.dst bvffer = process_file(dst) word_freq = process_buffer(bvffer) output_result(word_freq)
词组频率统计代码
3) 性能分析结果及改进。
运行结果:
- 指出执行次数最多的代码
-
- 执行时间最长的代码
-
- 给出改进优化的方法以及你的改进代码
-
# filename: word_freq.py # 阅读注释,在所有pass处删除pass,添加代码 from string import punctuation def process_file(dst): # 读文件到缓冲区 try: # 打开文件 dkwj = open(dst,'r') except IOError as s: print (s) return None try: # 读文件到缓冲区 bvffer = dkwj.read() except: print ('Read File Error!') return None dkwj.close() return bvffer def process_buffer(bvffer): if bvffer: word_freq = {} # 下面添加处理缓冲区 bvffer代码,统计每个单词的频率,存放在字典word_freq bvffer = bvffer.lower() for i in '“‘!;,.?”[]': bvffer = bvffer.replace(i, " ") words = bvffer.strip().split() for word in words: word_freq[word] = word_freq.get(word, 0) + 1 return word_freq def output_result(word_freq): if word_freq: sorted_word_freq = sorted(word_freq.items(), key=lambda v: v[1], reverse=True) for item in sorted_word_freq[:10]: # 输出 Top 10 的单词 print(item) def main(): dst = "Gone_with_the_wind.txt" bvffer = process_file(dst) word_freq = process_buffer(bvffer) output_result(word_freq) if __name__ == "__main__": import argparse parser = argparse.ArgumentParser() parser.add_argument('dst') args = parser.parse_args() dst = args.dst bvffer = process_file(dst) word_freq = process_buffer(bvffer) output_result(word_freq)
4) 程序运行命令、运行结果截图以及改进后的程序运行命令及结果截图 。
5) 给出你对此次任务的总结与反思。
基本要求达成,改进后速度明显增快