如何修复Porter词干分析器错误？

Question

我试图使用函数read txt file并通过单词进行标记化，包括标记化、删除空格、词干分析、收集字数、删除停止字，但是词干分析有问题，因为一些“s”和“r”被程序吞没了。 另外，哪个部分适合插入单词计数

import nltk
from nltk.tokenize import sent_tokenize, word_tokenize #split variable into words
from nltk.corpus import stopwords #stopwords
from nltk.stem import PorterStemmer #stem tools
from collections import defaultdict

#1)
def tokenizers(filename):
    #Read files
    file = open(filename, "r", encoding = "utf")
    lines = file.readline()
    file.close()
    #Set stop words and symbols (define symbols)
    stopWords = set(stopwords.words("english"))
    stopWords = stopWords.union(',','(",")','[","]','{","}','#','@','!',':',';','.','?')
    #Tokenize paragrah into words
    sentences = word_tokenize(lines)
    #Stem words, remove "s"
    ps = PorterStemmer()
    filterWords = [ps.stem(w) for w in sentences if not w in stopWords]
    return filterWords