To rectify this, you need to clean the data. You can do:
- Handle missing values i.e. null/nan values either by dropping or replacing their values with central tendency measures.
- Handle duplicate values by dropping them.
- Handle inconsistent data types i.e. converting the features to their correct types.
- Handle outliers, either by dropping them or performing some transformations on the data.
Comments
0 comments
Article is closed for comments.