thermoverse 0.1.1

ML models for materials property thermodynamic prediction

Thermoverse

Thermoverse is a materials property prediction package for thermodynamics and mechanical behavior, with a polished local demo dashboard and a deploy-ready Streamlit interface.

Overview

• Sample-style Streamlit dashboard for exploring prediction files and one-row model prediction.
• Built for materials datasets and thermodynamic model outputs.
• Includes local launch helpers and deployment guidance for live demos.

Quick start

1. Create a Python virtual environment and activate it.
2. Install dependencies from requirements.txt:

cd "c:\Users\HassanTraders\Desktop\research find.py"
.\.venv\Scripts\python.exe -m pip install -r requirements.txt

3. Launch the demo locally:

.\app_launch.ps1

or

launch_streamlit.bat

4. Use the sidebar to switch between Home, Explore predictions, and Predict a sample.

Sample input

• sample_input.csv contains a one-row example you can upload into the Predict a sample view.

Deploy this demo to the web

This project is ready to deploy as a live demo on Streamlit Cloud or Hugging Face Spaces.

Streamlit Cloud

1. Push this repository to GitHub.
2. Create a new app on Streamlit Cloud.
3. Select your GitHub repo, branch, and set the app file to streamlit_app.py.
4. Use requirements.txt to install dependencies.

Hugging Face Spaces

1. Create a new Space using the Streamlit template.
2. Upload this repository or connect the GitHub repo.
3. Set the app entrypoint to streamlit_app.py.

Once deployed, you can link the live demo from your PyPI project page under project.urls.

PyPI upload notes

• Use upload_pypi.ps1 with a raw token value.
• upload_pypi.ps1 now accepts both raw and full pypi-... token forms.

cd "c:\Users\HassanTraders\Desktop\research find.py"
.\upload_pypi.ps1 <YOUR_TOKEN>

If you want to run Twine directly:

cd "c:\Users\HassanTraders\Desktop\research find.py"
.\.venv\Scripts\twine.exe upload dist\* -u __token__ -p pypi-<YOUR_TOKEN>

Files of interest

• app_streamlit.py — interactive dashboard for exploring outputs and making one-row predictions.
• streamlit_app.py — Streamlit Cloud / Spaces entrypoint for deployment.
• deploy_pypi.ps1 — PyPI upload helper that accepts raw or prefixed tokens.
• models/ — saved model pickles used by the dashboard.
• outputs/ — prediction CSV files the dashboard can preview.

How to publish to GitHub

1. Create a new repo on GitHub (choose a name like research-find).
2. From this folder run:

git init
git add .
git commit -m "Initial commit"
git branch -M main
git remote add origin https://github.com/your-username/repo-name.git
git push -u origin main

Replace your-username/repo-name.git with your repository URL.

If you want me to run these commands and push, give me the repository URL or let me know and I'll guide you through creating a PAT for authentication.

Model description

• Purpose: Build accurate, generalizable machine-learning predictors for thermodynamic and mechanical materials properties to accelerate screening and discovery.
• Data: Trained on curated datasets (Materials_Dataset_181600.csv, Materials_Dataset_50000.csv, Materials_Dataset_FIXED.csv).
• Model types: Ensemble models (XGBoost / CatBoost / RandomForest-style) trained per-property with cross-validation and ensembling.
• Inputs: Composition-based features and engineered descriptors produced by preprocessing scripts.
• Outputs: Per-property CSV predictions under outputs/ and evaluation summaries (R², RMSE) stored in outputs/ and models/.
• Usage: create a Python environment, install dependencies, then run training and evaluation scripts such as python train_181600_models.py.
• Notes: large model files and outputs are excluded via .gitignore. If datasets or model artifacts exceed GitHub file size limits (>100MB) enable Git LFS for those paths.