Skip to main content
def AgentPredictorWorker.preprocess(self, data) [source]
Orchestrates the full transformation chain using the encoder states locked during fit. This eliminates training-serving skew by guaranteeing that production data is processed identically to training data.
Production data pipeline: raw→ML-ready.
  • GBM agents: cleaning only (raw features go directly to the model).
GLM agents**: cleaning→WOE encoding.

​
Parameters

data : pDF
Raw input DataFrame containing the original
(pre-WOE) feature columns.

​
Returns

pDF
ML-ready data, formatted exactly as the champion
model expects. Ready for transform.