ilp-classification/preprocessing/ishwari

This merge request includes:

• Cleaned and standardized the dataset for ILP
• Dropped irrelevant and sparse features
• Discretized age and hours_per_week
• Performed basic EDA with key visualisations and observations

The dataset is now ready for .pl file generation and Aleph-based modelling.

requested review from @rm02120 and @ss05670

assigned to @in00270

approved this merge request

1. Hyphen in field columns/field values need to be replaced from hyphen to underscore.
2. income needs to be changed to less_equal_50k and greater_50k.
3. please check duplicated for the pre processed dataset and drop them.

All points have been addressed. Changes are committed and pushed.

added 1 commit

• b5d431df - Grouped native countries into regions and updated income labels

Compare with previous version

reset approvals from @ss05670 by pushing to the branch

added 1 commit

• 373aa834 - Removed duplicate rows from the dataset

Compare with previous version

added 1 commit

• 7e827533 - Complete preprocessing, added df.info()

Compare with previous version

approved this merge request

mentioned in commit 7a914fec

merged