Python

1. Creating the word dictionary [Coding only: save code as problem1.py ] The first step in building an n-gram model is to create a dictionary that maps words to java map or python dictionary (which well use to access the elements corresponding to that word in a vector or matrix of counts or probabilities). Youll create this dictionary from the given data files (Select one file for training purpose) for all unique words. Youll need to split the sentences (consider each line) into a list of words and convert each word to lowercase, before storing it to the dictionary.

For example, I have a text file abc.txt