rajdeep345 / nlpmooc

Code repository for the assignments for NLP MOOC - NPTEL 2017

NLP MOOC

Week 2 - Assignment

Download w2a.zip or the folder asg2 The required code-snippets for working on the Assignment 2 can be found at Assignment 2 work-sheet.ipynb.

Functions

• For questions 5,6,7 use the function levenshtein
• For question 6, modify the function levenshtein on the variable substitutions
• For question 8, use the function jaro_winkler. The function is defined in the file Edistance.py
• For questions 5 to 10, the function uniFreq is needed to calculate the count of unigrams in the corpus C₃
• For question 9, the function bigramFreq is needed to calculate the count of bigrams in the corpus C₃
• For question 10, use the code snippet given in the last cell

Files

• use unigram.csv for questions 5,6,7,8
• use bigrams.csv for questions 9,10