Skip to content

Jimlibo/AutoML-App

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

79 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AutoML-App

Python Streamlit Pycaret

General

An app that utilizes streamlit and pycaret to automate a machine learning pipeline. The web app contains several tabs, for data upload, data preprocessing, model training, model evaluation, and model deployment.

Setup

In order to get the app running, first you need to clone this repository. This can be done with the command:

git clone https://github.com/Jimlibo/AutoML-App.git

Automated Setup and Start (Linux)

If you are on Linux, you can start the app by running the following commands:

cd AutoML-App
./start-automl.sh

The above script, will check if you have docker installed, and if yes it will create a container to run the app. If docker is not found in your system, it will install the necessary dependencies and run the app locally, using streamlit.
To stop the app, you can run the command:

./stop-automl.sh

If you are using docker, and you also want to remove the container and the image that were created, use the parameter --remove-containers

Manual Setup and Start

If you are on Windows or Mac, you can install the necessary dependencies with the following commands:

cd AutoML-App
pip install -r Setup/requirements.txt
streamlit run app.py

To stop the app, you can press Ctrl+C in the terminal, or close the terminal window.

Usage

Once the app is running, you can go to http://localhost:8501/ to access it. You will be presented with the General tab, which contains a brief overview of the different functionalities and actions that are available. From the Import Dataset tab, you can upload a dataset in csv format. The datasets you upload will be saved inside the Datasets folder. In the Exploratory Data Analysis tab, you can get a summary of the dataset you uploaded, as well as some useful statistics. In the Create Model tab, you have the option to train a model on the specified dataset, and you can also download it from the Download Model tab. All the models you create will be saved inside the Models folder. In case you want to remove older datasets and models, you can click the 'Clear Datasets and Models' button. (Note: The 'Clear Datasets and Models' button will remove all the datasets and models that are saved in the folders mentioned above!)

License

Distributed under the MIT License. See LICENSE for more information.

About

An app that utilizes streamlit and pycaret to automate a machine learning pipeline

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors