pip install pymatviz

See pymatviz/elements.py.

ptable_heatmap(compositions)	ptable_heatmap(compositions, log=True)
ptable_heatmap_ratio(comps_a, comps_b)	ptable_heatmap_ratio(comps_b, comps_a, log=True)
hist_elemental_prevalence(compositions)	hist_elemental_prevalence(compositions, log=True, bar_values='count')

See pymatviz/sunburst.py.

spacegroup_sunburst([65, 134, 225, ...])	spacegroup_sunburst([65, 134, 225, ...], show_values="percent")

See pymatviz/struct_vis.py.

plot_structure_2d(pmg_struct)	plot_structure_2d(pmg_struct, show_unit_cell=False, site_labels=False)

See pymatviz/histograms.py.

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)

See pymatviz/parity.py.

density_scatter(xs, ys, ...)	density_scatter_with_hist(xs, ys, ...)
density_hexbin(xs, ys, ...)	density_hexbin_with_hist(xs, ys, ...)
scatter_with_err_bar(xs, ys, yerr, ...)	residual_vs_actual(y_true, y_pred, ...)

See pymatviz/quantile.py.

qq_gaussian(y_true, y_pred, y_std)	qq_gaussian(y_true, y_pred, y_std: dict)

See pymatviz/ranking.py.

err_decay(y_true, y_pred, y_std)	err_decay(y_true, y_pred, y_std: dict)

See pymatviz/cumulative.py.

cum_err(preds, targets)	cum_res(preds, targets)

See pymatviz/relevance.py.

roc_curve(targets, proba_pos)	precision_recall_curve(targets, proba_pos)

See pymatviz/correlation.py.

marchenko_pastur(corr_mat, gamma=ncols/nrows)	marchenko_pastur(corr_mat_significant_eval, gamma=ncols/nrows)

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 "".

1. Residual y_res = y_true - y_pred: The difference between ground truth target and model prediction.
2. Error y_err = abs(y_true - y_pred): Absolute error between target and model prediction.
3. Uncertainty y_std: The model's estimate for its error, i.e. how much the model thinks its prediction can be trusted. (std for standard deviation.)