FREEDOM251

Freedom251 › Predictive Analytics Software

PyCaret

Free plan Open source APILinuxMacSelf-hostedWebWindows

Visit PyCaret Alternatives Pricing

What PyCaret is

PyCaret is a free, open-source, low-code Python tool for automating machine-learning workflows. Its experiment APIs cover classification, regression, clustering, anomaly detection, and time-series forecasting. Users can fit experiments, compare and tune models, make predictions, and save or load results. Fitted outputs can be used as scikit-learn pipelines, with forecasting pipelines for time-series work. The engine installs from PyPI using `pip install pycaret`; Python 3.11, 3.12, and 3.13 are listed as supported. Forecasting, explainability, and dashboard dependencies are optional extras. The default workflow runs on CPU, while GPU-accelerated estimators are available if their required libraries are installed. An optional React dashboard and FastAPI backend can be self-hosted for multi-user and deployment workflows. Saved pipelines can be served behind FastAPI, and the optional PyCaret server has an HTTP prediction endpoint. The backend can be connected to existing authentication and is JWT-friendly. The FAQ directs questions to GitHub Discussions and bug reports to GitHub Issues. PyCaret is MIT-licensed, with no paid or enterprise plan stated.

Who it suits

PyCaret suits Python users automating model workflows across its supported machine-learning tasks. Its optional self-hosted dashboard and backend may suit teams working on multi-user or deployment workflows.

What it does well

  • Covers classification, regression, clustering, and more.
  • Supports model comparison, tuning, and prediction.
  • Fitted outputs can be portable pipelines.
  • Free and MIT-licensed.

What to know first

  • GPU estimators require relevant libraries.
  • Dashboard and other dependencies are optional extras.
  • The 4.0 release removes the 3.x module-level functional API.

Plans

PlanBilled and limitsPrice
PyCaretMIT-licensed open source; no paid tier or enterprise plan statedFree
PyCaret open-sourceNo paid tier · MIT open-source engine · self-hostedFree

As pycaret.org lists them, read 7 Oct 2026. The maker's own page has the final word.

Getting started

  1. Install the core engine from PyPI with `pip install pycaret`.
  2. Use Python 3.11, 3.12, or 3.13.
  3. Add optional forecasting, explainability, or dashboard dependencies if needed.
  4. Choose an experiment API for classification, regression, clustering, anomaly detection, or time-series forecasting.
  5. Fit and compare models, then tune them and make predictions.
  6. Save or load a model; use its pipeline for deployment if needed.

Verdict

PyCaret brings several machine-learning workflows into a low-code Python tool, with pipelines and optional serving components. Existing code using the 3.x module-level functional API may need to stay on 3.x; the FAQ recommends 4.0 for new work.

Questions

How much does PyCaret cost?

PyCaret is free and MIT-licensed. No paid or enterprise plan is stated.

What machine-learning tasks does PyCaret cover?

Its experiment APIs cover classification, regression, clustering, anomaly detection, and time-series forecasting.

Which Python versions are supported?

The installation page lists Python 3.11, 3.12, and 3.13.

Can PyCaret use a GPU?

The default path runs on CPU. GPU-accelerated estimators are available when the required libraries are installed.

Can I deploy a saved PyCaret model?

Yes. A saved pipeline can be served behind FastAPI, and the optional PyCaret server provides an HTTP prediction endpoint.

What should existing 3.x users know about version 4.0?

PyCaret 4.0 removes the 3.x module-level functional API. The FAQ advises pinning 3.x for existing code and using 4.0 for new work.

Facts from PyCaret's own pages

Anomaly detection
AnomalyExperiment uses pyod adapters including Isolation Forest, KNN, COPOD, ECOD, LOF, PCA, MCD, ABOD, CBLOF, HBOS, OCSVM, SOS, and SOD. · pycaret.org, 15 Oct 2026
Backend API
The optional pycaret-server backend is a FastAPI service with CRUD, run orchestration, WebSockets, pipeline deployment, and plot endpoints. · pycaret.org, 15 Oct 2026
Classification
ClassificationExperiment handles categorical targets and includes metrics such as accuracy, AUC, recall, precision, F1, kappa, and MCC. · pycaret.org, 15 Oct 2026
Clustering
ClusteringExperiment offers KMeans, affinity propagation, mean shift, spectral, hierarchical, DBSCAN, OPTICS, Birch, KMode, and HDBSCAN adapters. · pycaret.org, 15 Oct 2026
Company description
LinkedIn describes PyCaret as an open-source, low-code machine-learning library and a nonprofit software-development organization. · linkedin.com, 15 Oct 2026
Company location
LinkedIn lists Toronto, Canada as PyCaret's headquarters and primary location. · linkedin.com, 15 Oct 2026
Company size
LinkedIn lists PyCaret's company size as 11–50 employees. · linkedin.com, 15 Oct 2026
Compatibility break
Version 4.0 removes the 3.x module-level functional API and requires the new Experiment object-oriented API; mixing 3.x and 4.0 is unsupported. · pycaret.org, 15 Oct 2026
Compatibility limit
PyCaret 4.0 removes the 3.x module-level functional API, so the FAQ advises pinning 3.x for existing code and using 4.0 for new work. · pycaret.org, 7 Oct 2026
Current maturity
The GitHub repository labels the 4.0 line as work in progress and says the 3.x line is frozen at 3.4.0. · github.com, 15 Oct 2026
Dashboard
An optional React dashboard and FastAPI backend can be self-hosted for multi-user and deployment workflows. · pycaret.org, 7 Oct 2026
Deployment
Models can be saved as portable scikit-learn pipelines, served behind FastAPI, or deployed through the optional pycaret-server layer. · pycaret.org, 15 Oct 2026
Documentation depth
The official site includes concepts, tutorials, preprocessing references, function guides, FAQs, a cheat sheet, and generated API reference. · pycaret.org, 15 Oct 2026
Explainability and plots
The plotting modules expose diagnostic charts for classification, regression, features, clustering, anomalies, time series, and exploratory analysis. · pycaret.org, 15 Oct 2026
Forecasting
TimeSeriesExperiment is built on sktime and supports models such as ARIMA, AutoARIMA, exponential smoothing, ETS, Theta, STLF, Croston, and reduced-regressor adapters. · pycaret.org, 15 Oct 2026
Founded
LinkedIn lists PyCaret as founded in 2020. · linkedin.com, 15 Oct 2026
Hardware
The default path runs on CPU, and GPU-accelerated estimators are available when the relevant libraries are installed. · pycaret.org, 7 Oct 2026
Headquarters
Toronto, Canada · pycaret.org, 28 Sept 2026
Hyperparameter tuning
tune_model performs configurable iterative hyperparameter searches and returns tuned pipelines and parameters. · pycaret.org, 15 Oct 2026
Installation
The documented installation is pip install pycaret, with dashboard, explainability, and forecasting extras available. · pycaret.org, 15 Oct 2026
Integrations
PyCaret wraps or interoperates with scikit-learn, XGBoost, Microsoft LightGBM, spaCy, sktime, pyod, FastAPI, React, and Plotly. · linkedin.com, 15 Oct 2026
Known limitations
The 4.0 changelog lists incomplete plot rewrites, legacy internals still being replaced, and no Python 3.14 support. · pycaret.org, 15 Oct 2026
Licence
PyCaret 4.0 licenses the engine under MIT and the control-plane components under BUSL-1.1 with a later Apache-2.0 change date and an additional-use grant. · github.com, 15 Oct 2026
Limit: comparative performance
A 2023 healthcare study reported PyCaret accuracy below AutoGluon on several Cleveland, combined, and Hungarian dataset tests, with Hungarian unreduced accuracy around 68%. · scribd.com, 15 Oct 2026

Where PyCaret stands on Freedom251

Look at these too