Here we developed Flask web-based SLAMD app (jupyter-based: https://github.com/BAMcvoelker/SequentialLearningApp) that uses machine learning to speed up the experimental search for suitable materials.
pip install -r requirements.txt
before to run the requirement file, set up the enviroments.
We used Python Flask framework along with ML, JQ, HTML, CSS, and extra python pacakges.
conda create -n 'your_env_name' python
conda activatate 'your_env_name'
git clone https://github.com/ghezalahmad/SLAMD-Flask.git
In order to run the app, cd SLAMD-FLASK folder and type:
python app.py
Go to your browser and look for port : 127.0.0.1:5000
├───datasets
│ └───.ipynb_checkpoints
├───preprocessed
├───static
│ ├───css
│ └───js
├───templates
The app is separated into four primary pages, which are discussed below: "Upload," "Data Info," "Preprocessing" "Design Space Explorer," "Sequenital Learning" and "Materials Discovery".
In this page, user can clean their dataset and select their appropriate features from dataset.
