Sound ML without opening Python. The breezeml command trains, compares, audits, and deploys straight from your terminal, so it drops neatly into shell scripts and CI pipelines.
breezeml train data.csv --target churn [--out model.joblib] [--explain]Trains the auto-selected model on a CSV, prints its report, and saves it to disk. Add --explain to narrate every pipeline decision in plain English as it works.
In plain English: Train a model from a spreadsheet without writing any Python, straight from your terminal.
breezeml train data.csv --target churn --out model.joblib --explainbreezeml compare data.csv --target churnPrints a leaderboard of every built-in model ranked on the same cross-validation folds, so you can eyeball the winner before committing to one.
In plain English: Print a leaderboard of models from the command line before you commit to one.
breezeml compare data.csv --target churnbreezeml audit data.csv --target churnScans a CSV for leakage and data-quality problems and exits with status 1 on critical findings. That non-zero exit makes it a natural CI gate: wire it before training and a broken dataset fails the build instead of shipping a fantasy score.
In plain English: Scan a dataset for problems and fail the build if it finds any, perfect as a safety check in CI.
# fails the pipeline (exit 1) if the data is broken
breezeml audit data.csv --target churnbreezeml automl data.csv --target churn [--budget 120] [--out model.joblib]Budget-aware model search. Give it a time budget in seconds and it searches models and hyperparameters, then saves the best honest pipeline it found.
In plain English: Give it a time budget on the command line and it searches for the best model, then saves it.
breezeml automl data.csv --target churn --budget 120 --out best.joblibbreezeml deploy model.joblib --out api/ [--name breezeml-model]Turns a saved model into a complete FastAPI plus Docker serving directory, ready to run with uvicorn or build into an image.
In plain English: Turn a saved model into a runnable web service with one command.
breezeml deploy model.joblib --out api/ --name churn-apibreezeml card model.joblib --out MODEL_CARD.mdGenerates an honest Markdown model card from a saved model: data profile, metrics, decisions, and auto-detected caveats. Governance in one command.
In plain English: Generate the model's paperwork from the terminal in one line.
breezeml card model.joblib --out MODEL_CARD.mdbreezeml guidePrints the garden path: a friendly map of the whole library and a suggestion for what to reach for first, based on the kind of task you have.
In plain English: Not sure where to start? It prints a friendly map and suggests what to reach for first.
breezeml guidebreezeml zenWhen the work is done, rest. Prints the Zen of BreezeML: a calm pause at the end of an honest day of modeling.
In plain English: A calm sign-off for the end of an honest day of modeling.
breezeml zen