Scikit-learn enhancement proposals

This repository is for structured discussions about large modifications or additions to scikit-learn.

The discussions must create an “enhancement proposal”, similar Python enhancement proposal, that reflects the major arguments to keep in mind, the rational and usecases that are addressed, the problems and the major possible solution. It should be a summary of the key points that drive the decision, and ideally converge to a draft of an API or object to be implemented in scikit-learn.

The SLEPs are publicly available online on Read The Docs.

Accepted

• SLEP000: SLEP and its workflow
• SLEP006: Metadata Routing
• SLEP007: Feature names, their generation and the API
• SLEP009: Keyword-only arguments
• SLEP010: n_features_in_ attribute
• SLEP017: Clone Override Protocol with __sklearn_clone__
• SLEP018: Pandas Output for Transformers with set_output
• SLEP020: Simplifying Governance Changes

Under review

• SLEP017: Clone Override Protocol with __sklearn_clone__
• SLEP019: Governance Update - Recognizing Contributions Beyond Code

Delayed review

• 1. SLEP001: Transformers that modify their target
• 2. SLEP002: Dynamic pipelines
• 3. SLEP003: Consistent inspection for transformers

Rejected

• SLEP004: Data information
• SLEP012: InputArray
• SLEP013: n_features_out_ attribute
• SLEP014: Pandas In, Pandas Out
• SLEP015: Feature Names Propagation

Template

• SLEP Template and Instructions