statisticallyWriting

This is a fun project that from a given text generate a new text based on the most common n-grams (n>=2) occurring in text.

License: MIT

The user can choose whether the grams should be word or character based.

Currently the code is only a starter; for obvious improvements (like not hard-coding everything) there will be issues.

Possible, more serious usage:

• What is the distribution of word length, when character n-grams are used?
• How cycles depend on the penalty factor of the code?