从字频创建ARFF
我有一些代码，它给出了一个单词列表，其中包含它们在文本中出现的频率，我正在寻找它，以便代码将前10个单词自动转换为ARFF
@RELATION wordfrequencies
@ATTRIBUTE单词字符串
@ATTRIBUTE频率数字
和前10名作为数据及其频率。
我正在努力解决如何使用我当前的代码执行此操作
import re
import nltk
# Quran subset
filename = 'subsetQuran.txt'
# create list of lower case words
word_list = re.split('s+', file(filename).read().lower())
print 'Words in text:', len(word_list)
word_list2 = [w.strip() for w in word_list if w.strip() not in nltk.corpus.stopwords.words('english')]
# create dictionary of word:frequency pairs
freq_dic = {}
# punctuation and numbers to be removed
punctuation = re.compile(r'[-.?!,":;()|0-9]')
for word in word_list2:
# remove punctuation marks
word = punctuation.sub("", word)
# form dictionary
try:
freq_dic[word] += 1
except:
freq_dic[word] = 1
print '-'*30
print "sorted by highest frequency first:"
# create list of (val, key) tuple pairs
freq_list2 = [(val, key) for key, val in freq_dic.items()]
# sort by val or frequency
freq_list2.sort(reverse=True)
freq_list3 = list(freq_list2)
# display result
for freq, word in freq_list2:
print word, freq
f = open("wordfreq.txt", "w")
f.write( str(freq_list3) )
f.close()
没有找到相关结果
已邀请:
1 个回复
蓄荣糖些
import re import nltk from collections import defaultdict # Quran subset filename = 'subsetQuran.txt' # create list of lower case words word_list = open(filename).read().lower().split() print 'Words in text:', len(word_list) # remove stopwords word_list = [w for w in word_list if w not in nltk.corpus.stopwords.words('english')] # create dictionary of word:frequency pairs freq_dic = defaultdict(int) # punctuation and numbers to be removed punctuation = re.compile(r'[-.?!,":;()|0-9]') for word in word_list: # remove punctuation marks word = punctuation.sub("", word) # increment count for word freq_dic[word] += 1 print '-' * 30 print "sorted by highest frequency first:" # create list of (frequency, word) tuple pairs freq_list = [(freq, word) for word, freq in freq_dic.items()] # sort by descending frequency freq_list.sort(reverse=True) # display result for freq, word in freq_list: print word, freq # write ARFF file for 10 most common words f = open("wordfreq.txt", "w") f.write("@RELATION wordfrequenciesn") f.write("@ATTRIBUTE word stringn") f.write("@ATTRIBUTE frequency numericn") f.write("@DATAn") for freq, word in freq_list[ : 10]: f.write("'%s',%dn" % (word, freq)) f.close()