python, Stemmer not found

Question

I got this code from github and this code will execute on windows machine 64 bit.

Here's the error I get:

Traceback (most recent call last): File "new.py", line 2, in import stemmer

ModuleNotFoundError: No module named 'stemmer'

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

Most probably it is nltk , you can install it using :

pip install nltk

change import stemmer to import nltk.stem as stemmer

And run the code. Please do take note this code is in Python 2.7 and will not run if u have Python3

Answer 2

Stemmer is a package that can be installed through pip as PyStemmer. It's only used in a very-rough "is real word" filter.

pip install PyStemmer

There might be a few other issues with this build right now.

Answer 3

Use:

pip install stemmer

in command prompt, if that is not working please follow as below.

---

1. First, manually download the text mining package from: https://pypi.python.org/pypi/textmining/1.0

2. Unzip it (unzip textmining-1.0.zip) you will get a folder with name textmining-1.0

3. type conda info in anconda prompt then see this directory active env location : C:\ProgramData\Anaconda3

4. Copy and paste unzipped textmining-1.0 folder in this directory

5. Convert the folder to python 3: to do this copy below code paste it in anaconda prompt and run

   2to3 --output-dir=textmining-1.0_v3 -W -n textmining-1.0
   

6. After converting the folder to python 3 RENAME the textmining-1.0 to textmining-1.0_v3

   Finally install the same by typing below code in anaconda prompt

   cd textmining-1.0_v3
   

   as below

   C:\Users\user>cd textmining-1.0_v3
   

   type this code python setup.py install as below

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

   Now succesfully you will get rid off error

Answer 4

In order to overcome the above problem in ubuntu, you need to install PyStemmer but it won't install directly,so firstly

install the gcc package:

sudo apt install gcc

Then:

Pip install PyStemmer

It worked for me ?