# PyCaret

> An open-source, low-code machine learning library in Python that automates machine learning workflows.

PyCaret is an open-source, low-code machine learning library in Python that automates machine learning workflows. It serves as an end-to-end machine learning and model management tool that exponentially speeds up the experiment cycle and makes data scientists more productive. PyCaret is essentially a Python wrapper around several machine learning libraries and frameworks, such as scikit-learn, XGBoost, LightGBM, CatBoost, spaCy, Optuna, Hyperopt, Ray, and more.

- **Low-Code Approach**: Replace hundreds of lines of code with just a few lines, making experiments exponentially fast and efficient. Designed for both experienced data scientists and citizen data scientists who prefer simplified ML solutions.

- **Multiple ML Modules**: Supports classification, regression, time series forecasting, clustering, and anomaly detection through both Functional and Object-Oriented Programming APIs.

- **Deployment Ready**: All steps performed in an ML experiment can be reproduced using a pipeline that is reproducible and guaranteed for production. Pipelines can be saved in binary file format that is transferable across environments.

- **BI Integration**: Seamlessly integrates with environments supporting Python such as Microsoft Power BI, Tableau, Alteryx, and KNIME, allowing users to add machine learning capabilities to existing workflows.

- **GPU Training Support**: Train models on GPU by simply passing `use_gpu = True` in the setup function. Supports Extreme Gradient Boosting, CatBoost, Light Gradient Boosting Machine, and various scikit-learn models with cuML.

- **Intel Optimization Support**: Apply Intel optimizations for machine learning algorithms using the sklearnex engine to speed up workflows.

- **Flexible Installation**: Install via PyPi with optional dependencies for analysis, models, tuning, MLOps, parallel processing, and testing. Also available via Docker with pre-installed Jupyter notebook.

- **Data Preprocessing**: Built-in data preprocessing capabilities to prepare datasets for machine learning experiments.

To get started, install PyCaret using `pip install pycaret` and import the desired module. Use the `setup()` function to initialize the environment and `compare_models()` to automatically train and evaluate multiple models. The library provides extensive documentation, tutorials, and video resources for learning.

## Features
- Low-code machine learning automation
- Classification module
- Regression module
- Time series forecasting
- Clustering analysis
- Anomaly detection
- GPU training support
- Intel sklearnex optimization
- Deployment-ready pipelines
- BI tool integration (Power BI, Tableau, Alteryx, KNIME)
- Docker support
- Functional and OOP APIs
- Data preprocessing
- Model comparison and selection
- Hyperparameter tuning

## Integrations
scikit-learn, XGBoost, LightGBM, CatBoost, spaCy, Optuna, Hyperopt, Ray, Microsoft Power BI, Tableau, Alteryx, KNIME, Docker, AWS SageMaker, Gradio, Streamlit, cuML

## Platforms
WINDOWS, MACOS, LINUX, WEB, API, DEVELOPER_SDK

## Pricing
Open Source

## Version
3.0

## Links
- Website: https://pycaret.gitbook.io/docs
- Documentation: https://pycaret.readthedocs.io/en/latest/
- Repository: https://github.com/pycaret/pycaret
- EveryDev.ai: https://www.everydev.ai/tools/pycaret