experiment-breakout-bust

Automating feature engineering for fantasy baseball predictions involves running an experiment loop to diagnose model weaknesses, generate hypotheses, test candidate features, and log results. This Skill automates that entire iterative testing process for breakout-bust classifiers.

Testing and comparing features for a baseball breakout-bust model requires running automated experiments to evaluate different feature sets on the classifier. This Skill logs performance results to help you compare the accuracy of different engineered features.

Yes, you need Python and Astral UV installed in your environment to run this model testing for fantasy baseball. Execution requires the command `uv run fbm experiment` to initiate the automated feature engineering and diagnostic loop.

Generating hypotheses for breakout-bust predictions is best handled through an automated experiment loop that diagnoses model weaknesses and tests candidate features. This Skill systematically generates and validates hypotheses to improve prediction accuracy.

Yes, you can run breakout-bust predictions specifically for batters by passing the `--player-type batter` argument. The command `uv run fbm experiment --model breakout-bust --player-type batter` initiates the feature testing loop for that player type.