You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The primary way to use this benchmark is through the [PyPI Python package](https://pypi.org/project/matbench-discovery):
3
+
The recommended way to use this benchmark is through the [PyPI Python package](https://pypi.org/project/matbench-discovery):
9
4
10
5
```zsh
11
6
pip install matbench-discovery
12
7
```
13
8
9
+
## Usage
10
+
11
+
Here's an example script of how to download the training and test set files for training a new model, recording the results and submitting them via pull request to this benchmark:
12
+
13
+
```py
14
+
from matbench_discovery.data import load_train_test
1. `formula`: A compound's unreduced alphabetical formula
28
+
1. `n_sites`: Number of sites in the structure's unit cell
29
+
1. `volume`: Relaxed structure volume in cubic Angstrom
30
+
1. `uncorrected_energy`: Raw VASP-computed energy
31
+
1. `e_form_per_atom_wbm`: Original formation energy per atom from [WBM paper]
32
+
1. `e_hull_wbm`: Original energy above the convex hull in (eV/atom) from [WBM paper]
33
+
1. `bandgap_pbe`: PBE-level DFT band gap from [WBM paper]
34
+
1. `uncorrected_energy_from_cse`: Should be the same as `uncorrected_energy`. There are 2 cases where the absolute difference reported in the summary file and in the computed structure entries exceeds 0.1 eV (`wbm-2-3218`, `wbm-1-56320`) which we attribute to rounding errors.
35
+
1. `e_form_per_atom_mp2020_corrected`: Matbench Discovery takes these as ground truth for the formation energy. Includes MP2020 energy corrections (latest correction scheme at time of release).
36
+
1. `e_above_hull_mp2020_corrected_ppd_mp`: Energy above hull distances in eV/atom after applying the MP2020 correction scheme and with respect to the Materials Project convex hull. Matbench Discovery takes these as ground truth for material stability. Any value above 0 is assumed to be an unstable/metastable material.
37
+
<!-- TODO document remaining columns, or maybe drop them from df -->
38
+
39
+
## Direct Download
40
+
14
41
You can also download the data files directly:
15
42
16
43
1. [`2022-10-19-wbm-summary.csv`](https://github.com/janosh/matbench-discovery/raw/v1.0.0/data/wbm/2022-10-19-wbm-summary.csv) [[GitHub](https://github.com/janosh/matbench-discovery/blob/v1/data/wbm/2022-10-19-wbm-summary.csv)]: Computed material properties only, no structures. Available properties are VASP energy, formation energy, energy above the convex hull, volume, band gap, number of sites per unit cell, and more. e_form_per_atom and e_above_hull each have 3 separate columns for old, new and no Materials
@@ -21,6 +48,4 @@ You can also download the data files directly:
21
48
1. [`2022-09-18-ppd-mp.pkl.gz`](https://github.com/janosh/matbench-discovery/raw/v1.0.0/data/wbm/2022-09-18-ppd-mp.pkl.gz) [[GitHub](https://github.com/janosh/matbench-discovery/blob/v1/data/wbm/2022-09-18-ppd-mp.pkl.gz)]: [PatchedPhaseDiagram](https://pymatgen.org/pymatgen.analysis.phase_diagram.html#pymatgen.analysis.phase_diagram.PatchedPhaseDiagram) constructed from all MP ComputedStructureEntries
22
49
1. [`2022-09-19-mp-elemental-ref-energies.json`](https://github.com/janosh/matbench-discovery/raw/v1.0.0/data/wbm/2022-09-19-mp-elemental-ref-energies.json) [[GitHub](https://github.com/janosh/matbench-discovery/blob/v1/data/wbm/2022-09-19-mp-elemental-ref-energies.json)]: Minimum energy PDEntries for each element present in the Materials Project
0 commit comments