View on GitHub


Starter code to solve real world text data problems. Includes: Gensim Word2Vec, phrase embeddings, Text Classification with Logistic Regression, word count with pyspark, simple text preprocessing, pre-trained embeddings and more.

In-depth usage examples of scikit’s CountVectorizer


Running the Notebook

  1. From the command line, first, clone this repo.
    git clone <this repo url>
  2. Next, switch to the CountVectorizer directory of this repo.
    cd  nlp-in-practice/CountVectorizer
  3. Then, run jupyter notebook
    jupyter notebook
  4. Select CountVectorizer.ipynb, and re-run the cells and re-use the code!