-
Getting raw text from JSON data
At this point we have the data of a whole chapter in a file containing a JSON structure divided by verses along with additional data. Now we will create some python functions to obtain the data in raw text that we can give to NLTK. import json def wholeChapter(chapter_dict): verses_text...
-
Getting data...not a small task
We need data: Text in proper English Available programmatically from python Lots of “articles” that can be processed later, more than 1000 according to the recommendations. Instead of going directly to books, let’s start testing with the Bible text because additionally to more or less fit the above requirements, it...
-
NLTK
This toolkit has a lot of implementations of code and resources that promise to make a lot easier the construction of NLP projects. Again, an independent Linux server seems ideal to handle all the NLP processes related to the implementation of the code of “Theophilus” (that’s the code-name for this...