Natural Language Analysis with Ngrams

Goal of this project is to have a NLP tool that would give statistical analysis results based on Google Ngram data.

Furthermore, it is now just a NetBeans project without a final JAR.
Furthermore, there will be a github version for anyone who wishes to contribute.
In the future versions, user will be able to convert a single word to numerical data, to be able to compare two words and get the comparison data, and to be able to do the same for the sentences, paragraphs and documents.

I will JAR-it once I decide that it can be called a final release.

This project was made by creating a corpus from the Google Ngrams data for English Language, version 20120701.
EOWL list of English words was used to filter-out the words from Ngrams data.
For each year, per word, the data was added and calculated to describe the average appearance of a word per document for a given year.
Before using this program, you MUST download the corpus.