Cleaning dataset

[mawada-sweis]

Cleaning the data by removing columns that are unnecessary, or contain a large amount of missing data. in addition to dealing with noisy or inconsistent data.

[mawada-sweis]

• ✅ Cleared direct missing data by removing any features with more than 75% missing data and filling the remaining features with their mode value.

• ✅ Cleaned indirect missing data by removing any features with more than 60% missing and filling the remaining features based on the type of feature; encoded features handled by encoding the label of the missing type; numeric features handled by replacing the label with a constant or mean value based on the type of missing. ❗The label features are not handled and will be handled during the transformation process.