Machine Learning/ Data Science -Parse Entire Bible instead of John

[JustinhSE]

Overview 🤔

We need to update the project to use the entire Bible for clustering instead of just 1 John. This will reduce the number of 0% similarity results.

Task 🔧

• Update the project to use the entire Bible for clustering to improve accuracy
• Reorganize the data storage for the Gutenberg Bible so that each book stores its own chapters, which in turn store their own scripture
• Modify the printing of the clusters to include the book name attached to the verse number (e.g., Matthew 5:38 instead of 5:38)
• Currently, we manually concatenate 1 John onto the verse, which needs to be removed

[rabelmervin]

Hi @JustinhSE , I'm interested in solving this issue. Could you please provide me the location of the project code.

[JustinhSE]

For sure @rabelmervin !

[JustinhSE]

@rabelmervin this is our Python app doing most of the work for this issue

[rabelmervin]

Hi sir @JustinhSE, I have seperated book name and content using indices I have researched but, I can't able seperate chapters could you please tell me the way to do it ?

[JustinhSE]

@rabelmervin can you send me your Jupyter notebook?

[rabelmervin]

@rabelmervin can you send me your Jupyter notebook? sure sir @JustinhSE https://colab.research.google.com/drive/14pA3UIGjorODH_kqJHs3rNAMTGzngMoO?usp=sharing

[unclebinary1001]

hi @JustinhSE , i am interested in this issue and I would like to collaborate with @rabelmervin seeing that this issue has several tasks in it. thank you for your consideration.

[JustinhSE]

@rabelmervin would you want to coauthor with @unclebinary1001 on this issue?

I am currently in midterm season so it may be hard for me to work immediately on this, however you 2 can work together and see if you can rework it?

[JustinhSE]

@rabelmervin can you send me your Jupyter notebook?

sure sir @JustinhSE https://colab.research.google.com/drive/14pA3UIGjorODH_kqJHs3rNAMTGzngMoO?usp=sharing

Try to first use the .ipynb notebook we derived the app from first and try working from their for a better sandbox

[rabelmervin]

@rabelmervin would you want to coauthor with @unclebinary1001 on this issue?

I am currently in midterm season so it may be hard for me to work immediately on this, however you 2 can work together and see if you can rework it?

Yeah sir @JustinhSE I'm really excited to collaborate with @unclebinary1001

[JustinhSE]

Great 🚀🚀🚀

Assigning you now @unclebinary1001

[JustinhSE]

nltk.download('gutenberg')
from nltk.corpus import gutenberg
bible = gutenberg.raw('bible-kjv.txt')

# split all of the books of the bible into an array
books = bible.split('\n\n\n\n\n')
print(books)```

This will help you both, this is from my original script of parsing the bible from the NLTK. Try this out and see how the book titles and chapters and verses are shown. (Hint: Within the string, it says 1:2 (whatever the verse says), so try to abstract those 2 verses and try to trim down the book titles to only Genesis for example and not the rest provided) @unclebinary1001 @rabelmervin 

[unclebinary1001]

Thank you for adding me to this task, @JustinhSE. I look forward to collaborating with you, @rabelmervin.

[rabelmervin]

Can we use this to access entire bible?

for i in range(len(books)): book = books[i] chapter = book.split('\n\n')

@JustinhSE , @unclebinary1001 could you please tell me how i can do like this (Matthew 5:38 instead of 5:38)

[JustinhSE]

So analyze how 5:38 is shown and how the book chapter is shown as well. Remember the books should be divided before you get to the chapters and verses

So what you could do is books[i] (title) then the verse output we currently have

[JustinhSE]

But the point of this issue is to reorganize how we are storing the Bible, instead maybe use a data structure that could do book -> chapters -> verses

[JustinhSE]

@rabelmervin look into this and instead use bible-kjv.text

https://www.nltk.org/book/ch02.html

[JustinhSE]

@rabelmervin @unclebinary1001 updates?

[rabelmervin]

Extremely apologize sir @JustinhSE I currently preparing for semester exams but, I'll definitely make pr within this week.

[JustinhSE]

Alright thanks @rabelmervin , updates @unclebinary1001 ?

[maskeensingh]

hi @JustinhSE i think i can contribute in this maybe alone or as well as with the @unclebinary1001 and @rabelmervin . I have a good knowledge about ML and I think i can do the task. I am late because i just got to know about hacktober fest. Please assign me also, maybe not whole if you want but a portion in this that is left uncovered by the persons whom you early assigned

[Namit2111]

Hi @maskeensingh not a lot of progress has been done in this issue, if you can discuss your approach in solving this or how you will move towards solving it we will assign it to you.

[maskeensingh]

ok @Namit2111 i will send you a detailed idea and workflow