PyCaret 2.1 is now available. Click here to see release notes. Documentation on the website is only updated for major releases. To see the latest documentation, Click Here


This page provides an overview of all the Modules available in PyCaret. A Module is a building block for creating experiments. Each module encapsulates specific machine learning algorithms and functions that are consistently used across different modules. For example, the create_model function trains and evaluates a model in all modules. Depending on the type of experiment, one of the six available modules must be imported into the environment. Learn more about how to import a module in notebook





Classify elements into groups and predict class labels which are discrete and unordered.

Common use-cases: Spam Detection, Predict Customer Churn, Predict Default, Disease Found / Not Found.


Predict continuous value by estimating the relationship between dependent and  independent variables.

Common use-cases: Predict Sales, Predict Stock Prices, Predict Quantity, Predict Cost.




Automatic grouping of similar objects into sets in a way that objects in same groups are more similar to each other than to those in other groups.

Common use-cases: Customer segmentation, pattern analysis

Association Rule Mining

Rule-based machine learning method for discovering interesting relations between variables in database.

Common use-cases: Market Basket Analysis.

Anomaly Detection

Identify and predict rare itemsevents or observations which raise suspicions by differing significantly from the majority of the data.

Common use-cases: Detect bank fraud, structural defect.

Natural Language Processing

Analyze textual data by creating topic models that finds hidden semantic structure in text documents.

Common use-cases: Document Classification, Document Tagging.