Improved naive bayes model - Githubissues

DSCKGEC / learn-machine-learn

A one-stop repository for new-comers in Machine Learning and A.I.

MIT License

1 stars 4 forks source link

Improved naive bayes model #38

Closed srini047 closed 2 years ago

srini047 commented 2 years ago

Linked Issue

Closes: #7

Describe the changes you've made

I have improved the existing Naive Bayes model by 1% after analyzing the trend in the dataset.

Type of change

What sort of change have you made:

[ ] Bug fix (non-breaking change which fixes an issue)
[x] New feature (non-breaking change which adds functionality)
[ ] Code style update (formatting, local variables)
[ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
[ ] This change requires a documentation update

How Has This Been Tested?

Initially plotted the SNS Heat and Cluster Map.
Found that the Uniformity of cell size column is highly correlated which is causing the model to perform poorly.
After removing it can see a 1% betterment in the Naive Bayes Model and also a significant improvement in other models excluding the logistic regression model.

Checklist:

[x] My code follows the guidelines of this project.
[x] I have performed a self-review of my own code.
[x] I have commented my code, particularly wherever it was hard to understand.
[x] I have made corresponding changes to the documentation.
[x] My changes generate no new warnings.
[x] I have added tests that prove my fix is effective or that my feature works.
[x] Any dependent changes have been merged and published in downstream modules.

Screenshots

heat-map

cluster-map

srini047 commented 2 years ago

Original	Updated

It has actually improved the f1 score and accuracy. Now there is a change in the FN value. It has performed better in the test dataset rather than in the training dataset.

Also, my bad that I had made a PR with the wrong file since I had many files while trying to improve.