[BUG] vectorizer.stop_words_ is not a property of the vectorizer

**Describe the bug**
While preprocessing the documents using the utils, I encounter a bug which says stop_words_ is not an attribute of CountVectorizer

**To Reproduce**
Steps to reproduce the behavior:
1. pip install the module / clone the repo
2. try to preprocess any documents

```

**Expected behavior**
a vocab and traindataset to return