Hypernets: A General Automated Machine Learning framework to simplify the development of End-to-end AutoML toolkits in specific domains.

Last update: Dec 23, 2022

Overview

Hypernets

We Are Hiring！

Dear folks, we are opening several precious positions based in Beijing both for professionals and interns avid in AutoML/NAS, please send your resume/cv to [email protected]. (Application deadline: TBD.)

Hypernets: A General Automated Machine Learning Framework

Hypernets is a general AutoML framework, based on which it can implement automatic optimization tools for various machine learning frameworks and libraries, including deep learning frameworks such as tensorflow, keras, pytorch, and machine learning libraries like sklearn, lightgbm, xgboost, etc. We introduced an abstract search space representation, taking into account the requirements of hyperparameter optimization and neural architecture search(NAS), making Hypernets a general framework that can adapt to various automated machine learning needs.

Overview

Conceptual Model

Illustration of the Search Space

Installation

Install Hypernets with pip command:

pip install hypernets

Optional, to run Hypernets in JupyterLab notebooks, install Hypernets and JupyterLab with command:

pip install hypernets[notebook]

Optional, to run Hypernets in distributed Dask cluster, install Hypernets with command:

pip install hypernets[dask]

Optional, to support dataset with simplified Chinese in feature generation, install jieba package before run Hypernets, or install Hypernets with command:

pip install hypernets[zhcn]

Optional, install all Hypernets components and dependencies with one command:

pip install hypernets[all]

Verify installation:

python -m hypernets.examples.smoke_testing

Hypernets related projects

HyperGBM: A full pipeline AutoML tool integrated various GBM models.
HyperDT/DeepTables: An AutoDL tool for tabular data.
HyperKeras: An AutoDL tool for Neural Architecture Search and Hyperparameter Optimization on Tensorflow and Keras.
Cooka: Lightweight interactive AutoML system.
Hypernets: A general automated machine learning framework.

Documents

Neural Architecture Search

DataCanvas

Hypernets is an open source project created by DataCanvas.

Comments

window pip fail.

ERROR: Complete output from command 'D:\Anaconda\Anaconda3\python.exe' -u -c 'import setuptools, tokenize;file='"'"'C:\Users\John\AppData\Local\Temp\pip-install-4hgmcjg1\python-geohash\setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' bdist_wheel -d 'C:\Users\John\AppData\Local\Temp\pip-wheel-gijlszf9' --python-tag cp37: ERROR: running bdist_wheel running build running build_py creating build creating build\lib.win-amd64-3.7 copying geohash.py -> build\lib.win-amd64-3.7 copying quadtree.py -> build\lib.win-amd64-3.7 copying jpgrid.py -> build\lib.win-amd64-3.7 copying jpiarea.py -> build\lib.win-amd64-3.7 running build_ext building '_geohash' extension error: Microsoft Visual C++ 14.0 is required. Get it with "Microsoft Visual C++ Build Tools": https://visualstudio.microsoft.com/downloads/

ERROR: Failed building wheel for python-geohash Running setup.py clean for python-geohash Failed to build python-geohash ERROR: spyder 3.3.6 requires pyqt5<5.13; python_version >= "3", which is not installed. ERROR: spyder 3.3.6 requires pyqtwebengine<5.13; python_version >= "3", which is not installed. ERROR: distributed 2021.11.1 has requirement dask==2021.11.1, but you'll have dask 2.1.0 which is incompatible. ERROR: woodwork 0.9.0 has requirement pandas>=1.3.0, but you'll have pandas 1.2.3 which is incompatible. ERROR: featuretools 1.2.0 has requirement dask[dataframe]>=2021.10.0, but you'll have dask 2.1.0 which is incompatible. ERROR: featuretools 1.2.0 has requirement pandas<2.0.0,>=1.3.0, but you'll have pandas 1.2.3 which is incompatible. Installing collected packages: psutil, pyyaml, tblib, distributed, woodwork, featuretools, python-geohash, hypernets Found existing installation: psutil 5.6.3 Uninstalling psutil-5.6.3: Successfully uninstalled psutil-5.6.3 Found existing installation: PyYAML 5.1.1 ERROR: Cannot uninstall 'PyYAML'. It is a distutils installed project and thus we cannot accurately determine which files belong to it which would lead to only a partial uninstall.
Installation

opened by zhangxjohn 2
dataset about dsutils

an error about "from hypernets.frameworks.ml.datasets import dsutils", I think it should be "from deeptables.datasets import dsutils".
bug

opened by ninanxiaoguai 2
A suggestion for GreedyEnsemble

On line 107 of voting's code, i.e. if self.ensemble_size <= 0: size = predictions.shape[1]

Is it possible to replace it with self.ensemble_size <= 0 or predictions.shape[1] < self.ensemble_size: size = predictions.shape[1]?

opened by zhangxjohn 1
scorer & calc_score
Please make sure that this is a feature request.

System information

Hypernets version (you are using):

Are you willing to contribute it (Yes/No):

Describe the feature and the current behavior/state. I found that the user-defined evaluation metric function could not be set in the hypernets experiment, and calc_score() contained few metrics, such as no mape.

Will this change the current api? How?

Any Other info.
opened by zhangxjohn 1
Bump url-parse from 1.5.1 to 1.5.3 in /hypernets/hn_widget/js
Bumps url-parse from 1.5.1 to 1.5.3.

Commits

ad44493 [dist] 1.5.3

c798461 [fix] Fix host parsing for file URLs (#210)

201034b [dist] 1.5.2

2d9ac2c [fix] Sanitize only special URLs (#209)

fb128af [fix] Use 'null' as origin for non special URLs

fed6d9e [fix] Add a leading slash only if the URL is special

94872e7 [fix] Do not incorrectly set the slashes property to true

81ab967 [fix] Ignore slashes after the protocol for special URLs

ee22050 [ci] Use GitHub Actions

d2979b5 [fix] Special case the file: protocol (#204)

Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot use these labels will set the current labels as the default for future PRs for this repo and language

@dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language

@dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language

@dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

You can disable automated security fix PRs for this repo from the Security Alerts page.

dependencies
opened by dependabot[bot] 1
Bump tar from 6.1.0 to 6.1.10 in /hypernets/hn_widget/js
Bumps tar from 6.1.0 to 6.1.10.

Commits

188badd 6.1.10

23312ce drop dirCache for symlink on all platforms

4f1f4a2 6.1.9

875a37e fix: prevent path escape using drive-relative paths

b6162c7 fix: reserve paths properly for unicode, windows

3aaf19b fix: prune dirCache properly for unicode, windows

6a9c51d 6.1.8

dfc5923 fix: skip extract if linkpath is stripped entirely

575a511 fix: reserve paths case-insensitively

d61628c 6.1.7

Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot use these labels will set the current labels as the default for future PRs for this repo and language

@dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language

@dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language

@dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

You can disable automated security fix PRs for this repo from the Security Alerts page.

dependencies
opened by dependabot[bot] 1
Bump tar from 6.1.0 to 6.1.5 in /hypernets/hn_widget/js
Bumps tar from 6.1.0 to 6.1.5.

Commits

bd4691c 6.1.5

d694c4f ci: test on node 16

84acbd3 fix(unpack): fix hang on large file on open() fail

97c46fc fix(unpack): always resume parsing after an entry error

488ab8c chore: WriteEntry cleaner write() handling

be89aaf WriteEntry backpressure

ba73f5e chore: track fs state on WriteEntry class, not in arguments

bf69383 6.1.4

06cbde5 Avoid an unlikely but theoretically possible redos

0b78386 6.1.3

Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot use these labels will set the current labels as the default for future PRs for this repo and language

@dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language

@dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language

@dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

You can disable automated security fix PRs for this repo from the Security Alerts page.

dependencies
opened by dependabot[bot] 1
Bump dns-packet from 1.3.1 to 1.3.4 in /js
Bumps dns-packet from 1.3.1 to 1.3.4.

Commits

ebdf849 1.3.4

ac57872 move all allocUnsafes to allocs for easier maintenance

c64c950 1.3.3

0598ba1 fix .. in encodingLength

010aedb 1.3.2

0d0d593 backport encodingLength fix to v1

See full diff in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot use these labels will set the current labels as the default for future PRs for this repo and language

@dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language

@dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language

@dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

You can disable automated security fix PRs for this repo from the Security Alerts page.

dependencies
opened by dependabot[bot] 0
Bump path-parse from 1.0.6 to 1.0.7 in /js
Bumps path-parse from 1.0.6 to 1.0.7.

Commits

See full diff in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot use these labels will set the current labels as the default for future PRs for this repo and language

@dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language

@dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language

@dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

You can disable automated security fix PRs for this repo from the Security Alerts page.

dependencies
opened by dependabot[bot] 0
Bump url-parse from 1.5.1 to 1.5.3 in /js
Bumps url-parse from 1.5.1 to 1.5.3.

Commits

ad44493 [dist] 1.5.3

c798461 [fix] Fix host parsing for file URLs (#210)

201034b [dist] 1.5.2

2d9ac2c [fix] Sanitize only special URLs (#209)

fb128af [fix] Use 'null' as origin for non special URLs

fed6d9e [fix] Add a leading slash only if the URL is special

94872e7 [fix] Do not incorrectly set the slashes property to true

81ab967 [fix] Ignore slashes after the protocol for special URLs

ee22050 [ci] Use GitHub Actions

d2979b5 [fix] Special case the file: protocol (#204)

Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot use these labels will set the current labels as the default for future PRs for this repo and language

@dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language

@dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language

@dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

You can disable automated security fix PRs for this repo from the Security Alerts page.

dependencies
opened by dependabot[bot] 0

Releases(0.2.5.7)

0.2.5.7(Nov 24, 2022)

Source code(tar.gz)
Source code(zip)
0.2.5.6(Oct 8, 2022)

Source code(tar.gz)
Source code(zip)
0.2.5.5(Sep 5, 2022)

Source code(tar.gz)
Source code(zip)
0.2.5.4(May 31, 2022)

Source code(tar.gz)
Source code(zip)
0.2.5.3(Mar 25, 2022)

Source code(tar.gz)
Source code(zip)
0.2.5.2(Mar 8, 2022)

Source code(tar.gz)
Source code(zip)
0.2.5.1(Mar 2, 2022)

Source code(tar.gz)
Source code(zip)
0.2.5(Feb 28, 2022)

Source code(tar.gz)
Source code(zip)
0.2.3.2(Dec 16, 2021)

Fix requirements
Source code(tar.gz)
Source code(zip)
0.2.3(Aug 20, 2021)

Source code(tar.gz)
Source code(zip)
0.1.8(Mar 4, 2021)

Source code(tar.gz)
Source code(zip)
0.1.7(Feb 4, 2021)

Source code(tar.gz)
Source code(zip)
0.1.5(Nov 30, 2020)

Source code(tar.gz)
Source code(zip)
0.1.3(Sep 27, 2020)

Source code(tar.gz)
Source code(zip)
0.1.2(Sep 2, 2020)

Source code(tar.gz)
Source code(zip)
0.1.1(Jun 24, 2020)

Source code(tar.gz)
Source code(zip)

Owner

DataCanvas

We love data science!

GitHub Repository https://hypernets.readthedocs.io/

A python library for Bayesian time series modeling

PyDLM Welcome to pydlm, a flexible time series modeling library for python. This library is based on the Bayesian dynamic linear model (Harrison and W

438 Dec 17, 2022

NumPy-based implementation of a multilayer perceptron (MLP)

My own NumPy-based implementation of a multilayer perceptron (MLP). Several of its components can be tuned and played with, such as layer depth and size, hidden and output layer activation functions,

1 Feb 10, 2022

Python/Sage Tool for deriving Scattering Matrices for WDF R-Adaptors

R-Solver A Python tools for deriving R-Type adaptors for Wave Digital Filters. This code is not quite production-ready. If you are interested in contr

8 Sep 19, 2022

Model Validation Toolkit is a collection of tools to assist with validating machine learning models prior to deploying them to production and monitoring them after deployment to production.

25 Dec 28, 2022

🌊 River is a Python library for online machine learning.

River is a Python library for online machine learning. It is the result of a merger between creme and scikit-multiflow. River's ambition is to be the go-to library for doing machine learning on strea

4k Jan 03, 2023

A simple and lightweight genetic algorithm for optimization of any machine learning model

geneticml This package contains a simple and lightweight genetic algorithm for optimization of any machine learning model. Installation Use pip to ins

8 Aug 10, 2022

Cryptocurrency price prediction and exceptions in python

Cryptocurrency price prediction and exceptions in python This is a coursework on foundations of computing module Through this coursework i worked on m

1 Nov 07, 2021

moDel Agnostic Language for Exploration and eXplanation

moDel Agnostic Language for Exploration and eXplanation Overview Unverified black box model is the path to the failure. Opaqueness leads to distrust.

1.2k Jan 04, 2023

Required for a machine learning pipeline data preprocessing and variable engineering script needs to be prepared

Feature-Engineering Required for a machine learning pipeline data preprocessing and variable engineering script needs to be prepared. When the dataset

5 Apr 21, 2022

Implementation of different ML Algorithms from scratch, written in Python 3.x

393 Nov 29, 2022

Open source time series library for Python

PyFlux PyFlux is an open source time series library for Python. The library has a good array of modern time series models, as well as a flexible array

2k Jan 02, 2023

This project impelemented for midterm of the Machine Learning #Zoomcamp #Alexey Grigorev

MLProject_01 This project impelemented for midterm of the Machine Learning #Zoomcamp #Alexey Grigorev Context Dataset English question data set file F

1 Dec 18, 2021

FLAML is a lightweight Python library that finds accurate machine learning models automatically, efficiently and economically

FLAML - Fast and Lightweight AutoML

2.2k Jan 09, 2023

GroundSeg Clustering Optimized Kdtree

ground seg and clustering based on kitti velodyne data, and a additional optimized kdtree for knn and radius nn search

2 Dec 02, 2021

This machine learning model was developed for House Prices

This machine learning model was developed for House Prices - Advanced Regression Techniques competition in Kaggle by using several machine learning models such as Random Forest, XGBoost and LightGBM.

1 Mar 02, 2022

Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch, and PySpark and can be used from pure Python code.

Petastorm Contents Petastorm Installation Generating a dataset Plain Python API Tensorflow API Pytorch API Spark Dataset Converter API Analyzing petas

1.6k Dec 31, 2022

Hypernets: A General Automated Machine Learning framework to simplify the development of End-to-end AutoML toolkits in specific domains.

Related tags

Overview

Hypernets

We Are Hiring！

Hypernets: A General Automated Machine Learning Framework

Overview

Conceptual Model

Illustration of the Search Space

Installation

Related Links

Hypernets related projects

Documents

Neural Architecture Search

DataCanvas

Comments

Releases(0.2.5.7)

0.2.5.7(Nov 24, 2022)

0.2.5.6(Oct 8, 2022)

0.2.5.5(Sep 5, 2022)

0.2.5.4(May 31, 2022)

0.2.5.3(Mar 25, 2022)

0.2.5.2(Mar 8, 2022)

0.2.5.1(Mar 2, 2022)

0.2.5(Feb 28, 2022)

0.2.3.2(Dec 16, 2021)

0.2.3(Aug 20, 2021)

0.1.8(Mar 4, 2021)

0.1.7(Feb 4, 2021)

0.1.5(Nov 30, 2020)

0.1.3(Sep 27, 2020)

0.1.2(Sep 2, 2020)

0.1.1(Jun 24, 2020)

Owner

DataCanvas

A python library for Bayesian time series modeling

NumPy-based implementation of a multilayer perceptron (MLP)

Python/Sage Tool for deriving Scattering Matrices for WDF R-Adaptors

Model Validation Toolkit is a collection of tools to assist with validating machine learning models prior to deploying them to production and monitoring them after deployment to production.

🌊 River is a Python library for online machine learning.

A simple and lightweight genetic algorithm for optimization of any machine learning model

Cryptocurrency price prediction and exceptions in python

moDel Agnostic Language for Exploration and eXplanation

Required for a machine learning pipeline data preprocessing and variable engineering script needs to be prepared

Implementation of different ML Algorithms from scratch, written in Python 3.x

Open source time series library for Python

This project impelemented for midterm of the Machine Learning #Zoomcamp #Alexey Grigorev

FLAML is a lightweight Python library that finds accurate machine learning models automatically, efficiently and economically

GroundSeg Clustering Optimized Kdtree

This machine learning model was developed for House Prices

Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch, and PySpark and can be used from pure Python code.

Predicting Keystrokes using an Audio Side-Channel Attack and Machine Learning

Fundamentals of Machine Learning

cuML - RAPIDS Machine Learning Library

Create large-scale ML-driven multiscale simulation ensembles to study the interactions