Export & deploy

Turn a trained model into something you can run anywhere. Zero lock-in.

export()

export(model, 'train.py') -> str

Writes a standalone scikit-learn script that reproduces your pipeline with no breezeml import. The ultimate no-lock-in guarantee.

In plain English: Writes a plain scikit-learn script that runs with no BreezeML at all. Delete us and your model still works.

Exampleruns locally after pip install

import breezeml

df = breezeml.datasets.iris()
model = breezeml.fit(df, "species")
breezeml.export(model, "train.py")

card(model, path=None) -> strRun here

Generates an honest Markdown model card: data profile, metrics, decisions, and auto-detected caveats. Governance made easy.

In plain English: Auto-writes the model's nutrition label: what it learned on, how it scores, and what to watch out for.

Try it yourself

Output

Press Run to execute this snippet.

deploy(model, out_dir='deployment') -> str

Emits a FastAPI app + Dockerfile + pinned requirements. Every deployed API ships /predict, /health and a live /drift endpoint.

In plain English: Generates a ready-to-run web service, container, and pinned setup, complete with a live drift monitor.

Exampleruns locally after pip install

import breezeml

breezeml.deploy(model, "api/")
# -> main.py, Dockerfile, requirements.txt, model.joblib

deploy.to_onnx(model, 'model.onnx')

Export to the ONNX open standard so your model runs in other languages and runtimes.

In plain English: Exports to an open format so the model can run in other languages and systems, not just Python.

Exampleruns locally after pip install

import breezeml

breezeml.deploy.to_onnx(model, "model.onnx")

automl(df, target, time_budget=60)

Give it a time budget and it searches models and hyperparameters for you, then returns the best honest pipeline.

In plain English: Give it a time limit and it hunts for the best model and settings for you, then hands back the honest winner.

Exampleruns locally after pip install

import breezeml

best = breezeml.automl(df, "target", time_budget=60)

track.log(model, report) · track.leaderboard() · blend(models)

Log every experiment to a local leaderboard, then blend your best models into an ensemble.

In plain English: Keeps a scoreboard of your experiments, then merges your best models into one stronger team.

Exampleruns locally after pip install

import breezeml

breezeml.track.log(model, report, name="run-1")
breezeml.track.leaderboard()