Edit CHDModel.py I had from threading import activeCount, I don't remeber ever adding it, I'm thinking it might have been auto completed by accident or added using the quick fix feature??? I have no Idea. Anyways it does nothing so im removing it.

Just fixed up some comments that no longer apply and some other code

See merge request !8

added a bit more to read me

See merge request !7

This concludes the assignment

Report is finished, each report section is within the file and was written one...

See merge request !6

Report is finished, each report section is within the file and was written one at a time during development however, I'm not going to split it up for each individual push. (Again since I messed up and original code is in wrong repo).

This concludes the assignment

Main stage 4 done

See merge request !5

Added all the stuff from part 3

except for the categorical features I had type 1 and type 2

Instead of one hot encoding
I mapped each typing to a number and changed the columns values

I also dropped name and generation

Then I used leaky relu and early stopping
+ more epoch

While there wasnt overfitting present
the model now preforms better with the saved model getting 96% on testing

All coding done then I will push reports

Part 3 done

See merge request !4

made two csv files training and testing

binary encoded famhist
used z score to normalize numeric features

then for the model added a bunch of stuff to stop overfitting
leaky relu, L2, dropout, and early stopping

+ more epochs

NOTE: Saved model achieved 76%+ on testing for the bonus mark

Part 2 Done and Main stage 3

See merge request !3

Made a bar graph for special attack as I thought legendaries might have a much higher sp_attack on average

Made a better model
using L2, Batch normalization, dropout
overfitting has been reduced significantly,
Getting ~91-93% on testing

Big additions added pictures I tested with
As well as the different models
includes partial, complete, and complete95+
complete95+ is for the bonus

Main stage 2 Done

See merge request !2

made main2.py trained model on pokemon data, cleaned it fixing missing no secondary type.

The model preforms ok with ~82% on testing and ~90 on training, which probably indicates overfitting

Working_branch

reaches 95+

Also made a bonus model that achieves 98%+

data-cleaned is the usable data.
And I made 4 graphs instead of 3 since 2a and 2b are very similar

First commit - NOTE: I was stupid and didn't see that we needed to create a new repository. So I am moving everything here and recreating the git commits,pushes, pull etc.