Why is treating implicit sparse zeros as missing dangerous for SimpleImputer?
Classic MLLevel: IntermediateSparse missing markers
Why is treating implicit sparse zeros as missing dangerous for SimpleImputer?
Hints
- Separate absent entries from missing measurements.
- Estimate how many zeros would become nonzero.
Answer
Those zeros may denote genuine absence, and replacing them generally destroys sparsity. The documented sparse path requires an explicitly stored missing marker; zero-as-missing requires dense input.
Source and licence: scikit-learn 1.7.2 — impute · BSD-3-Clause · answer: Quantoros editorial