N-gram v2.0 part3

gistfile1.py

def longTermPriority(path, maxTermLength, minFreq):
    longTerms=[]          #長詞
    longTermsFreq=[]      #長詞+次數分配
    
    for i in range(maxTermLength,1,-1): ##字詞數由大至小
        text_list = cutSentence(path,longTerms)  #呼叫cutSentence function
        #print len(text_list)
        words_freq = ngram(text_list,i, minFreq) #呼叫 ngram function
        #print i

    
        for word_freq in words_freq:
            longTerms.append(word_freq[0])  #將跑出來的長詞加入 longTerms list 做為下次切割檔案的基礎
            #print word_freq[0]
            longTermsFreq.append(word_freq) #將長詞和次數加入另外一個list  分成兩個檔儲存的用意是減少迴圈次數
            #print word_freq
    
    return longTermsFreq