Need help with LightAutoML?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

176 Stars 16 Forks Other 87 Commits 6 Opened issues


LAMA - automatic model creation framework

Services available


Need anything else?

Contributors list

No Data

LightAutoML (LAMA) - automatic model creation framework

Slack PyPI - Downloads Read the Docs

LightAutoML (LAMA) project from Sberbank AI Lab AutoML group is the framework for automatic classification and regression model creation.

Current available tasks to solve: - binary classification - multiclass classification - regression

Currently we work with datasets, where each row is an object with its specific features and target. Multitable datasets and sequences are now under contruction :)

Note: for automatic creation of interpretable models we use

library made by our group as well.

Authors: Ryzhkov Alexander, Vakhrushev Anton, Simakov Dmitry, Bunakov Vasilii, Damdinov Rinchin, Shvets Pavel, Kirilin Alexander

LAMA video guides: - LAMA framework general overview, benchmarks and advantages for business (Ryzhkov Alexander) - LAMA practical guide - ML pipeline presets overview (Simakov Dmitry)


Installation via pip from PyPI

To install LAMA framework on your machine:

pip install lightautoml

Installation from sources with virtual environment creation

If you want to create a specific virtual environment for LAMA, you need to install

system package and run the following command, which creates
virtual env with LAMA inside:
To check this variant of installation and run all the demo scripts, use the command below:

Docs generation

To generate documentation for LAMA framework, you can use command below (it uses virtual env created on installation step from sources):


Builded official documentation for LightAutoML is available


Usage examples

To find out how to work with LightAutoML, we have several tutorials: 1.

Tutorial_1. Create your own pipeline.ipynb
- shows how to create your own pipeline from specified blocks: pipelines for feature generation and feature selection, ML algorithms, hyperparameter optimization etc. 2.
Tutorial_2. AutoML pipeline preset.ipynb
- shows how to use LightAutoML presets (both standalone and time utilized variants) for solving ML tasks on tabular data. Using presets you can solve binary classification, multiclass classification and regression tasks, changing the first argument in Task. 3.
Tutorial_3. Multiclass task.ipynb
- shows how to build ML pipeline for multiclass ML task by hand

Each tutorial has the step to enable Profiler and completes with Profiler run, which generates distribution for each function call time and shows it in interactive HTML report: the report show full time of run on its top and interactive tree of calls with percent of total time spent by the specific subtree.

Important 1: for production you have no need to use profiler (which increase work time and memory consomption), so please do not turn it on - it is in off state by default

Important 2: to take a look at this report after the run, please comment last line of demo with report deletion command.

For more examples, in

folder you can find different scenarios of LAMA usage: 1.
- building ML pipeline from blocks and fit + predict the pipeline itself. 2.
- several ML pipelines creation (using importances based cutoff feature selector) to build 2 level stacking using AutoML class 3.
- several ML pipelines creation (using iteartive feature selection algorithm) to build 2 level stacking using AutoML class 4.
- several ML pipelines creation (using combination of cutoff and iterative FS algos) to build 2 level stacking using AutoML class 5.
- creation of classification and regression tasks for AutoML with loss and evaluation metric setup 6.
- 2 level stacking using AutoML class with different algos on first level including LGBM, Linear and LinearL1 7.
- AutoML with nested CV usage 8.
- AutoML preset usage for tabular datasets (predefined structure of AutoML pipeline and simple interface for users without building from blocks) 9.
- creation pipelines from blocks to build AutoML, solving multiclass classification task 10.
- AutoML time utilization preset usage for tabular datasets (predefined structure of AutoML pipeline and simple interface for users without building from blocks) 11.
- creation pipelines from blocks (including CatBoost) to build AutoML , solving multiclass classification task 12.
- AutoML NLP preset usage for tabular datasets with text columns 13.
- AutoML tabular preset usage with custom validation scheme and multiprocessed inference

Questions / Issues / Suggestions

Write a message to us: - Alexander Ryzhkov (email: [email protected], telegram: @RyzhkovAlex) - Anton Vakhrushev (email: [email protected])

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.