🔥 open-mlpipe
Production-level automated ML pipeline — from raw data to deployed model in one line.
Why open-mlpipe?¶
Every ML project starts the same way: load data, clean it, try 10 models, pick the best one. Hours wasted. Every. Single. Time.
open-mlpipe does it all in one line of Python:
One Line. Done.
# One line — full pipeline
ctx = run("dataset.csv", target="price")
# Access results
print(f"Best model: {ctx.best_model_name}")
print(f"Test R²: {ctx.metrics['test_r2']:.4f}")
Auto EDA
Column hygiene, quality assessment, distributions, statistical tests, VIF analysis — all automatic.
Feature Engineering
Missingness flags, interaction features, log transforms, datetime extraction — no manual work.
14+ Models
Ridge, XGBoost, LightGBM, RandomForest, Stacking, Voting — auto-selected and compared.
Optuna Tuning
Hyperparameter optimization with 18 model-specific search spaces — finds the best parameters.
SHAP Explainability
Global + local feature importance, dependence plots, waterfall explanations — understand your model.
Production Ready
Full inference pipeline saved — raw data → prediction with no manual preprocessing.
🚀 Get Started in 30 Seconds
Install
pip install open-mlpipe
Run
run("data.csv")
Results
ctx.best_model_name
Predict
model.predict(new)
🤖 Supported Models
Links¶
- Getting Started — Install and run your first pipeline
- Python API — Complete API documentation
- CLI Usage — Command-line interface
- YAML Config — Config-driven pipelines
- API Reference — Auto-generated from docstrings
- GitHub — Source code and issues