machine-learning-ops-ml-pipeline
Design and implement a complete ML pipeline for: $ARGUMENTS
Design and implement a complete ML pipeline for: $ARGUMENTS
Auto-generate features with encodings, scaling, polynomial features, and interaction terms for ML pipelines.
Use TabularPredictor.predict_proba with full argument guidance for classification probability outputs; depends on autogluon-tabularpredictor-fit and supports autogluon-tabularpredictor-calibrate-decision-threshold/set-decision-threshold.
Detail every TabularPredictor.fit argument, including presets, ensembling, resources, HPO, and deployment settings; depends on autogluon-tabularpredictor-class and feeds autogluon-tabularpredictor-fit-summary, predict-proba, calibrate-decision-threshold, set-model-best, save/load.
Set binary decision thresholds with TabularPredictor.set_decision_threshold and understand its single argument; depends on autogluon-tabularpredictor-calibrate-decision-threshold or autogluon-tabularpredictor-predict-proba for threshold selection.
Consolidated AutoGluon Tabular tutorial summary (essentials + how-it-works + in-depth), explaining the workflow and every highlighted argument; depends on autogluon-tabularpredictor-class and autogluon-tabularpredictor-fit, plus autogluon-tabularpredictor-calibrate-decision-threshold/set-decision-threshold for threshold tuning.
Calibrate binary classification decision thresholds with TabularPredictor.calibrate_decision_threshold, detailing every argument and trade-off; depends on autogluon-tabularpredictor-fit and pairs with autogluon-tabularpredictor-set-decision-threshold and autogluon-tabularpredictor-predict-proba.
Generate and interpret training summaries with TabularPredictor.fit_summary, detailing all arguments and outputs; depends on autogluon-tabularpredictor-fit and complements autogluon-tabularpredictor-set-model-best.
MLflow 3 GenAI evaluation for agent development. Use when (1) writing mlflow.genai.evaluate() code, (2) creating @scorer functions, (3) building evaluation datasets from traces, (4) using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), (5) analyzing traces for latency/errors/architecture, (6) optimizing agent context/prompts/token usage, (7) debugging evaluation failures. Covers the full eval workflow: trace analysis -> dataset building -> scorer creation -> evaluation execution.
Guide users through building comprehensive AI evaluation strategies using Evaluation-Driven Development (EDD)
Quick classifier training with automatic model selection, hyperparameter tuning, and comprehensive evaluation metrics.
Comprehensive LLM prompt engineering and optimization workflow that orchestrates expert analysis, advanced techniques, and multi-domain optimization using the integrated toolset. Handles everything from basic prompt improvement to complex multi-agent prompt orchestration.
Orchestrate multiple AI models (GLM, MiniMax, etc.) as workers using Pi Coding Agent with Claude as coordinator.
Core nnsight concepts for neural network interpretability. Use when setting up models, tracing activations, saving values, or making basic interventions on model internals.
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
Expert in vector spaces, matrices, linear transformations, eigenvalues, and applications to data science and machine learning
Save TabularPredictor artifacts with TabularPredictor.save, detailing all arguments and persistence behavior; depends on autogluon-tabularpredictor-fit and pairs with autogluon-tabularpredictor-load.
Explain ML model predictions using SHAP values, feature importance, and decision paths with visualizations.
Set the default prediction model with TabularPredictor.set_model_best, detailing all arguments and effects; depends on autogluon-tabularpredictor-fit and is often guided by autogluon-tabularpredictor-fit-summary or leaderboard outputs.
Load saved predictors with TabularPredictor.load, detailing all arguments and security/version implications; depends on autogluon-tabularpredictor-save and assumes a prior autogluon-tabularpredictor-fit.
Decode intermediate layer predictions using the Logit Lens technique. Use when analyzing what a model predicts at each layer, understanding information flow, or visualizing layer-wise processing.
Explain and configure AutoGluon’s TabularPredictor constructor, including all init arguments and their effects for tabular classification/regression; prerequisite for autogluon-tabularpredictor-fit, predict-proba, save/load, fit-summary, calibrate-decision-threshold, set-decision-threshold, and set-model-best.
Evaluator-Optimizer pattern knowledge for automatic iteration cycles. Implements Anthropic's agent architecture pattern for continuous improvement. Triggers: evaluator-optimizer, iteration pattern, 평가-최적화, 評価最適化, 评估优化
Use when asked to compare multiple ML models, perform cross-validation, evaluate metrics, or select the best model for a classification/regression task.