I am trying to automatically detect words from a string in python
Before:
["Absoluteadvantage", "Absorptioncosting", "Accreditedinvestor"]
After:
["Absolute Advantage", "Absorption Costing", "Accredited Investor"]
I understand that the accuracy will never be perfect but am looking for a method to seperate these strings of text into seperate words. I've tried using nltk's word_tokenize method to try and seperate these to no avail.