A toolkit for visualizations in materials informatics
Project description
pymatviz
A toolkit for visualizations in materials informatics. Works with pymatgen.
Installation
pip install pymatviz
Elements
See pymatviz/elements.py.
Sunburst
See pymatviz/sunburst.py.
spacegroup_sunburst([65, 134, 225, ...]) |
spacegroup_sunburst([65, 134, 225, ...], show_values="percent") |
|---|---|
 |
 |
Structure
plot_structure_2d(pmg_struct) |
plot_structure_2d(pmg_struct, show_unit_cell=False, site_labels=False) |
|---|---|
 |
 |
Histograms
spacegroup_hist([65, 134, 225, ...]) |
spacegroup_hist([65, 134, 225, ...], show_counts=False) |
|---|---|
 |
 |
residual_hist(y_true, y_pred) |
true_pred_hist(y_true, y_pred, y_std) |
 |
 |
Parity Plots
See pymatviz/parity.py.
Uncertainty Calibration
See pymatviz/quantile.py.
qq_gaussian(y_true, y_pred, y_std) |
qq_gaussian(y_true, y_pred, y_std: dict) |
|---|---|
 |
 |
Ranking
See pymatviz/ranking.py.
err_decay(y_true, y_pred, y_std) |
err_decay(y_true, y_pred, y_std: dict) |
|---|---|
 |
 |
Cumulative Error and Residual
cum_err(preds, targets) |
cum_res(preds, targets) |
|---|---|
 |
 |
Classification Metrics
roc_curve(targets, proba_pos) |
precision_recall_curve(targets, proba_pos) |
|---|---|
 |
 |
Correlation
marchenko_pastur(corr_mat, gamma=ncols/nrows) |
marchenko_pastur(corr_mat_significant_eval, gamma=ncols/nrows) |
|---|---|
 |
 |
Migrating from ml-matrics to pymatviz
This library was renamed from ml-matrics to pymatviz between versions 0.3.0 and 0.4.0. To update existing Python files that import ml-matrics in place, run the following commands. On Linux:
find . -name '*.py' | xargs sed -i 's/^from ml_matrics import/from pymatviz import/g'
find . -name '*.py' | xargs sed -i 's/^from ml_matrics./from pymatviz./g'
find . -name '*.py' | xargs sed -i 's/^import ml_matrics/import pymatviz/g'
On Mac, replace sed -i with sed -i "".
Glossary
- Residual
y_res = y_true - y_pred: The difference between ground truth target and model prediction. - Error
y_err = abs(y_true - y_pred): Absolute error between target and model prediction. - Uncertainty
y_std: The model's estimate for its error, i.e. how much the model thinks its prediction can be trusted. (stdfor standard deviation.)
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pymatviz-0.4.0.tar.gz
(35.2 kB
view details)
File details
Details for the file pymatviz-0.4.0.tar.gz.
File metadata
- Download URL: pymatviz-0.4.0.tar.gz
- Upload date:
- Size: 35.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.8.0 pkginfo/1.8.2 readme-renderer/32.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.8 tqdm/4.63.0 importlib-metadata/4.11.2 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.8.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 3704dfb8d483f1df9fce5895828c964107cb7d140040c9a0cf3aba760d9b2fff |
|
| MD5 | b10a0c96b9c4243c6501f6b445454e68 |
|
| BLAKE2b-256 | 18d1eefecc276adf291b760b73fc37982c3ba01b15e7f6186ef3e603e4f512f3 |
