找不到Python、Stemmer

本文介绍了找不到Python、Stemmer的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！

问题描述

我从GitHub获得此代码，此代码将在64位Windows计算机上执行。

以下是我收到的错误：

回溯(最近一次调用)：文件"new.py"，第2行，中导入词干分析器

ModuleNotFoundError：没有名为‘stemmer’的模块

import math
import stemmer

def irange(sequence):
   return zip(range(len(sequence)), sequence)

class CosineScore(object):
    def __init__(self,all_docs):
      self.documents = all_docs #list all docs [doc1,doc2..]
       self.ndocs = len(all_docs)
    self.posting_list = {} #term frequency list, don't care about term position
     #term => {docId => freq}
       self.pstemmer = stemmer.PorterStemmer()

    self._term_indexer()

def _term_indexer(self):
    #Create term frequency dict
    #Run each word through stemmer
    for doc_id,document in irange(self.documents):
        for word in document.split(' '):
            s_word = self.pstemmer.stem(word)
            if self.posting_list.has_key(s_word):
                doc_id_mapping = self.posting_list[s_word]
                if doc_id_mapping.has_key(doc_id):
                    doc_id_mapping[doc_id] += 1
                else:
                    doc_id_mapping[doc_id] = 1
            else:
                self.posting_list[s_word] = {doc_id: 1}

def _term_frequency(self,term):
    if self.posting_list.has_key(term):
        return self.posting_list[term]
    else:
        return -1

def _listToString(self,arg):
    if isinstance(arg,basestring):
        return arg.split(' ')

def __qTermFrequency(self,term,bWords):
    count =0
    for i,bWordsObj in irange(bWords):
        if bWordsObj == term:
            count = count +1
    return count

def _docListWeights(self) :

    all_terms = self.posting_list.keys()
    doclist_weights = [0.0] * self.ndocs

    #for all terms in the corpus
    for i,term in irange(all_terms):
        #for all docs in corpus that contain this term
        docs = self.posting_list[term].keys()
        for j,doc_id in irange(docs):
            tf = self.posting_list[term][doc_id]
            tfSquared = (tf * tf)
            doclist_weights[doc_id] += tfSquared

        for k in range(self.ndocs):
            doclist_weights[k] = math.sqrt(doclist_weights[k])
    return doclist_weights

def compute(self,query,mIDF=0):
    '''
    dft - document term frequency
    idf - inverse document frequency
    wTQ - weights for each query term
    mIDF - max tf normalization
    '''

    scores = [0.0] * self.ndocs
    bWords = self._listToString(query)
    normalizationFactor = self._docListWeights()

    for qterm in bWords:
        term = self.pstemmer.stem(qterm)
        #calculate WT
        #dft =  __qTermFrequency(queryTerm,bWords)
        #wTQ = math.log10(int(N)/dft)

        term_posting_doclist = []
        if self._term_frequency(term) != -1:
            #Find all documents with this query term

            term_posting_doclist = self.posting_list[term].keys()
            #total_term_frequency_in_corpus = sum(self.posting_list[term].values())

            if(mIDF!=0):
                dft = mIDF
            else:
                dft = len(term_posting_doclist)

            _wTQ = float(self.ndocs)/float(dft)
            wTQ = math.log10(float(_wTQ)) #idf

        #cosinescore algorithm
        for doc_id in term_posting_doclist:
            if normalizationFactor[doc_id] != 0:
                #wFTD = termDocFrequencyList/ normalizationFactor(doc_id)
                wFTD = self.posting_list[term][doc_id] / float(normalizationFactor[doc_id])
            else:
                wFTD = 0.0

            scores[doc_id] +=  (wTQ * wFTD)
    return scores

if __name__ == "__main__":
    docs = [  "mallya","mallya mallya in hawaii", "sunil" ]
    q = "hawaii mallya"
    cs = CosineScore(docs)
    print (cs.compute(q))

Stemmer

找不到Python、Stemmer

问题描述

以下是我收到的错误：

ModuleNotFoundError：没有名为‘stemmer’的模块

推荐答案