shankarpandala/lazypredict

Health v2 · maintenance only

Adoption not part of the score

3347 stars · 365 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Lazy Predict is a Python library that trains dozens of machine learning models with minimal code to quickly identify which algorithms perform best on a dataset, without any parameter tuning. It covers classification, regression, and time series forecasting, with optional GPU acceleration and MLflow experiment tracking.

Use cases

• quickly compare dozens of ML models on my dataset
• find the best classifier without tuning hyperparameters
• baseline all regression models with a few lines of code
• benchmark time series forecasting models automatically
• screen which algorithms are worth tuning for my problem
• run automated model selection for classification and regression

When to choose

• you need fast baselines across many models before investing in tuning
• you want a low-code way to screen classifiers, regressors, or forecasting models
• you want built-in experiment tracking, GPU acceleration, or seasonal detection for time series

When to avoid

• you need production-grade, fully tuned models rather than quick comparisons
• you require fine-grained control over each model's training pipeline
• your workflow depends on hyperparameter optimization, which Lazy Predict deliberately skips

Facets

library · maturity active

machine-learning data-science benchmarking machine-learning data-science time-series python cross-platform automl model-selection scikit-learn classification regression time-series-forecasting model-comparison low-code

Member repositories

For agents

markdown · JSON · MCP: product_card(name="shankarpandala/lazypredict")