Using Python, implement the Cosine Similarity function between $2$ documents.

The dataset $20$ Newsgroups Dataset can be accessed by using Scikit library of

Python. This dataset is a collection of approximately $20,000$ newsgroup documents,

partitioned across $20$ different newsgroups. Your code should work with any pair from

the dataset.

As each document contains header, footer, and quotes, you may use the preprocessing

code you developed for the previous lab to have the document ready for the task.

To convert each of the documents to its vector form, you may use functions from the

same library.

Your input is the vectors of any $2$ documents from the dataset and your output should

be the cosine similarity between the documents.

The libraries you may need; Scikit, NLTK