mineralML
We present mineralML (mineral classification using Machine Learning) for probabilistic classification of common igneous minerals. mineralML provides functions for calculating stoichiometries and crystallographic sites based on this classification, along with functions for handling mapped EDS data. Utilizing this package allows for the identification of misclassified mineral phases and poor-quality data. We streamline data processing and cleaning to allow for the rapid transition to usable data, improving the utility of data curated in these databases and furthering computing and modeling capabilities.
Documentation
Read the documentation for a run-through of the mineralML code.
Citation
If you use mineralML in your work, please cite this preprint. This package represents a significant time investment. Proper citation helps support continued development and academic recognition.
Shi, S., Wieser, P., Gordon, C., Toth, N., Antoshechkina, P.M., Gleeson, M., Lehnert, K., (2026) mineralML: Leveraging Machine Learning for Probabilistic Mineral Classification in Geochemical Databases", Earth ArXiv. doi:10.31223/X53J2M
@article{Shietal2026,
doi = {10.31223/X53J2M},
url = {https://doi.org/10.31223/X53J2M},
year = {2026},
author = {Shi, Sarah C and Wieser, Penny E and Gordon, Charlotte and Toth, Norbert and Antoshechkina, Paula M and Gleeson, Matthew LM and Lehnert, Kerstin},
title = {mineralML: Leveraging Machine Learning for Probabilistic Mineral Classification},
journal = {Earth ArXiv},
}
Run on the Cloud
Web app (no Python needed)
Open the mineralML web app at mineralml.streamlit.app. Upload a CSV or Excel file of oxide wt% (or type analyses in manually), get mineral classifications with prediction scores, and download an Excel workbook with one sheet per mineral plus stoichiometry sheets. The app sleeps after 12 hours without visitors; if you see a wake-up button, click it and wait ~30 seconds.
To run the app locally, see webapp/README.md.
Google Colab
If you do not have Python installed locally, run mineralML on Google Colab. The Cloud-based version runs rapidly, with test cases of >10,000 microanalyses classified within 4 seconds.
Run and Install Locally
Obtain a version of Python between 3.10 and 3.14 if you do not already have it installed. mineralML can be installed with one line. Open terminal and type the following:
pip install mineralML
Make sure that you keep up with the latest version of mineralML. To upgrade to the latest version of mineralML, open terminal and type the following:
pip install mineralML --upgrade
Metadata
Release files for mineralML 0.0.3.24
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mineralml-0.0.3.24.tar.gz | 2.2 MB | Without provenance | Details for mineralml-0.0.3.24.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mineralml-0.0.3.24-py3-none-any.whl | Python 3 | none | any | Details for mineralml-0.0.3.24-py3-none-any.whl |
Total release size: 4.3 MB
Release files / mineralml-0.0.3.24.tar.gz
| Download URL | mineralml-0.0.3.24.tar.gz |
|---|---|
| Size | 2.2 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
161edb42b04e2c5f15830e084e4835918983f049fda6c6eb82f7d1d37d12c2d5
|
|
BLAKE2b-256 checksum How to use checksums |
254126b3ac10f65d13ac9eeb8828fce60fee6fb9df4be4e95a971dd7c7045daa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Release files / mineralml-0.0.3.24-py3-none-any.whl
| Download URL | mineralml-0.0.3.24-py3-none-any.whl |
|---|---|
| Size | 2.2 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
df38f2292585fd7b372ab874a29eda966a32194ace1c8073c73881903f8a3893
|
|
BLAKE2b-256 checksum How to use checksums |
22fab4aa9fbc61f447c754b5f910564d0cd08449d1f4dce22439d8e01b16f529
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Security for mineralML 0.0.3.24
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.