Natural Language Processing the O.J. Simpson Trial Transcripts

This week you will be utilizing the Python 3rd Party Natural Language Tookit to analyze and extract information from the O.J. Simpson Trial Transcripts.

The Trial Transcripts are posted in this weeks module, you will be using these as your target natural language files.  Copy the Corpus zip file to the virtual desktop and unzip the contents.  

You will develop a script that will:

1) import the proper nltk libraries

2) Initialize the Corpus  

Provide a selection loop for the following

Print      the Corpus Length

Print      the number of word Tokens found

Print      the size of the vocabulary

Print      the occurrences of specific test words: GLOVE, GUN, BRONCO, BLOOD, GUILTY

• Print a      word concordance: using the same test words.
• Print      similarities: using the same test words
• Print a      word index: using the same test words
• Create      a Prettytable with each word and the number of occurrences
• Submit:
• 1) #comment the lines (someone that doesn know code) 
• 2) Your final Python script (.py file) 
• 3) a Transcript of your output

https://we.tl/t-AiVuhjNOTa     (link to corpus file and any helpful scripts)