找不到python、Stemmer

Question

我从github得到了这段代码，这段代码可以在64位的windows机器上执行。

下面是我得到的错误：

回溯(最近一次调用)：导入词干分析器中的文件"new.py"，第2行

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))

Answer 1

它很可能是nltk，您可以使用以下命令安装它：

pip install nltk

将import stemmer更改为import nltk.stem as stemmer

然后运行代码。请注意，此代码是Python2.7中的代码，如果您有Python3，则不会运行此代码

Answer 2

Stemmer是一个软件包，可以通过pip安装为PyStemmer。它只用在非常粗糙的"is real word“过滤器中。

pip install PyStemmer

现在这个版本可能还有其他一些问题。

Answer 3

使用：

pip install stemmer

在命令提示符下，如果该命令不起作用，请执行以下操作。

首先，手动从以下位置下载文本挖掘包：https://pypi.python.org/pypi/textmining/1.0

• Unzip it ( textmining-1.0

• type textmining-1.0.zip)您将在anconda提示符中获得一个名为C:\ProgramData\Anaconda3

• Copy

1. 的文件夹，然后查看此目录的活动环境位置:C：\ProgramData\Anaconda3
2. Copy paste unzipped -1.0 conda info in this directory
   1. 将该文件夹转换为python 3:为此，请将其粘贴到anaconda提示符中并运行

2to3 -- textmining-1.0

• After -dir= textmining-1.0_v3 -W -n目录将文件夹转换为python 3将textmining-1.0重命名为textmining-1.0_v3

最后，通过在anaconda提示符中键入以下代码来安装相同的程序

cd文本挖掘-1.0_v3

如下所示

C:\Users\user>cd文本挖掘-1.0_v3

键入以下代码python setup.py install

C:\Users\user \textmining-1.0_v3>python setup.py安装

现在，您将成功地消除error