forked from p46318075/CodePattern
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
53 lines
1.7 KiB
53 lines
1.7 KiB
# 引入停用词表和测试文件的路径
|
|
from cppy.cp_util import stopwordfilepath, testfilepath
|
|
|
|
# 准备停用词表
|
|
with open(stopwordfilepath, encoding='utf-8') as f:
|
|
stop_words = f.read().split(',')
|
|
for letter in 'abcdefghijklmnopqrstuvwxyz':
|
|
stop_words.append(letter)
|
|
|
|
|
|
# 读文件，逐行扫描文本，发现词，确定不是停用词，计数
|
|
word_freqs = []
|
|
for line in open( testfilepath, encoding='utf-8' ):
|
|
start_char = None
|
|
i = 0
|
|
for c in line:
|
|
if start_char is None:
|
|
if c.isalnum():
|
|
# 一个单词开始
|
|
start_char = i
|
|
else:
|
|
if not c.isalnum():
|
|
# 一个单词结束
|
|
found = False
|
|
word = line[start_char:i].lower()
|
|
# 跳过停用词
|
|
if word not in stop_words:
|
|
pair_index = 0
|
|
# 单词是否第一次出现
|
|
for pair in word_freqs:
|
|
if word == pair[0]:
|
|
pair[1] += 1
|
|
found = True
|
|
break
|
|
pair_index += 1
|
|
if not found:
|
|
word_freqs.append([word, 1])
|
|
# 重置开始标记
|
|
start_char = None
|
|
i += 1
|
|
|
|
# 使用冒泡排序对词频进行排序
|
|
n = len(word_freqs)
|
|
for i in range(n):
|
|
for j in range(0, n-i-1):
|
|
if word_freqs[j][1] < word_freqs[j+1][1]:
|
|
word_freqs[j], word_freqs[j+1] = word_freqs[j+1], word_freqs[j]
|
|
|
|
|
|
# 打印频率最高的前10个词
|
|
for tf in word_freqs[:10]:
|
|
print(tf[0], '-', tf[1])
|