update email address, rename (fetch_process_wbm_dataset->compile_wbm_test_set).py

update site deps, set heading CSS text-wrap: balance;

Author: janosh

citation.cff

@@ -6,7 +6,7 @@ authors:
   - given-names: Janosh
     family-names: Riebesell
     affiliation: University of Cambridge, Lawrence Berkeley National Laboratory
-    email: janosh@lbl.gov
+    email: janosh.riebesell@gmail.gov
     orcid: https://orcid.org/0000-0001-5233-3462
     corresponding: true
     affil_key: 1, 2

data/wbm/fetch_process_wbm_dataset.py data/wbm/compile_wbm_test_set.py

@@ -16,7 +16,7 @@ Each iteration has varying numbers of materials which are counted by the 2nd int
 
 ## 🪓   Data Processing Steps
 
-The full set of processing steps used to curate the WBM test set from the raw data files (downloaded from [URLs listed below](#--links-to-wbm-files)) can be found in [`data/wbm/fetch_process_wbm_dataset.py`](https://github.com/janosh/matbench-discovery/blob/site/data/wbm/fetch_process_wbm_dataset.py). Processing steps taken:
+The full set of processing steps used to curate the WBM test set from the raw data files (downloaded from [URLs listed below](#--links-to-wbm-files)) can be found in [`data/wbm/compile_wbm_test_set.py`](https://github.com/janosh/matbench-discovery/blob/site/data/wbm/compile_wbm_test_set.py). Processing steps taken:
 
 - re-format material IDs: `step_1-0->wbm-1-1`, `step_1-1->wbm-1-2`, ...
 - correctly align initial structures to DFT-relaxed [`ComputedStructureEntries`](https://github.com/materialsproject/pymatgen/blob/02a4ca8aa0277b5f6db11f4de4fdbba129de70a5/pymatgen/entries/computed_entries.py#L536) (the initial structure files had 6 extra structures inserted towards the end of step 3 which had no corresponding IDs in the summary file)
@@ -31,7 +31,7 @@ The full set of processing steps used to curate the WBM test set from the raw da
 - apply the [`MaterialsProject2020Compatibility`](https://github.com/materialsproject/pymatgen/blob/02a4ca8aa0277b5f6db11f4de4fdbba129de70a5/pymatgen/entries/compatibility.py#L823) energy correction scheme to the formation energies
 - compute energy to the Materials Project convex hull constructed from all MP `ComputedStructureEntries` queried on 2023-02-07 ([database release 2021.05.13](https://docs.materialsproject.org/changes/database-versions#v2021.05.13))
 
-Invoking the script `python fetch_process_wbm_dataset.py` will auto-download and regenerate the WBM test set files from scratch. If you find
+Invoking the script `python compile_wbm_test_set.py` will auto-download and regenerate the WBM test set files from scratch. If you find
 
 - any questionable structures or data records in the released test set, or
 - inconsistencies between the files on GitHub vs the output of that script,

data/wbm/readme.md

@@ -125,7 +125,7 @@ def load(
         raise
 
     if Key.mat_id in df:
-        df = df.set_index(Key.mat_id)
+        df = df.set_index(Key.mat_id.value)
     if hydrate:
         for col in df:
             if not isinstance(df[col].iloc[0], dict):
@@ -270,4 +270,4 @@ def _on_not_found(self, key: str, path: str) -> None:  # type: ignore[override]
 
 
 df_wbm = load("wbm_summary")
-df_wbm[Key.mat_id] = df_wbm.index
+df_wbm[Key.mat_id.value] = df_wbm.index

matbench_discovery/data.py

@@ -15,7 +15,7 @@ authors:
     orcid: https://orcid.org/0000-0003-1974-028X
   - name: Janosh Riebesell
     affiliation: University of Cambridge, Lawrence Berkeley National Laboratory
-    email: janosh@lbl.gov
+    email: janosh.riebesell@gmail.gov
     orcid: https://orcid.org/0000-0001-5233-3462
   - name: Kevin Han
     affiliation: UC Berkeley

models/chgnet/metadata.yml

@@ -6,7 +6,7 @@ date_published: "2021-06-21"
 authors:
   - name: Janosh Riebesell
     affiliation: University of Cambridge, Lawrence Berkeley National Laboratory
-    email: janosh@lbl.gov
+    email: janosh.riebesell@gmail.gov
     orcid: https://orcid.org/0000-0001-5233-3462
   - name: Rhys Goodall
     affiliation: University of Cambridge

models/wrenformer/metadata.yml

@@ -27,6 +27,6 @@ Our results show that ML models have become robust enough to deploy them as tria
 
 We welcome contributions that add new models to the leaderboard through GitHub PRs. See the [contributing guide](https://janosh.github.io/matbench-discovery/contribute) for details.
 
-If you're interested in joining this work, feel free to [open a GitHub discussion](https://github.com/janosh/matbench-discovery/discussions) or [send an email](mailto:janosh@lbl.gov?subject=Collaborate%20on%20Matbench%20Discovery).
+If you're interested in joining this work, feel free to [open a GitHub discussion](https://github.com/janosh/matbench-discovery/discussions) or [send an email](mailto:janosh.riebesell@gmail.gov?subject=Collaborate%20on%20Matbench%20Discovery).
 
 For detailed results and analysis, check out the [preprint](https://janosh.github.io/matbench-discovery/preprint).

readme.md

@@ -32,17 +32,16 @@
 df_metrics.loc[train_size_col] = df_metrics_10k.loc[train_size_col] = ""
 for model in df_metrics:
     model_name = name_map.get(model, model)
-    if model_name not in MODEL_METADATA:
+    if not (model_data := MODEL_METADATA.get(model_name)):
         continue
-    n_structs = MODEL_METADATA[model_name]["training_set"]["n_structures"]
-    n_materials = MODEL_METADATA[model_name]["training_set"].get("n_materials")
+    n_structs = model_data["training_set"]["n_structures"]
+    n_structs_str = si_fmt(n_structs)
 
-    n_structs_fmt = si_fmt(n_structs)
-    if n_materials:
-        n_structs_fmt += f" <small>({si_fmt(n_materials)})</small>"
+    if n_materials := model_data["training_set"].get("n_materials"):
+        n_structs_str += f" <small>({si_fmt(n_materials)})</small>"
 
-    df_metrics.loc[train_size_col, model] = n_structs_fmt
-    df_metrics_10k.loc[train_size_col, model] = n_structs_fmt
+    df_metrics.loc[train_size_col, model] = n_structs_str
+    df_metrics_10k.loc[train_size_col, model] = n_structs_str
 
 
 # %% add dummy classifier results to df_metrics
@@ -183,7 +182,7 @@
         f"{SITE_FIGS}/metrics-table{label}.svelte",
         inline_props="class='roomy'",
         # draw dotted line between classification and regression metrics
-        styles=f"{col_selector} {{ border-left: 2px dotted white; }}{hide_scroll_bar}",
+        styles=f"{col_selector} {{ border-left: 1px solid white; }}{hide_scroll_bar}",
     )
     try:
         df_to_pdf(styler, f"{PDF_FIGS}/metrics-table{label}.pdf")

scripts/model_figs/make_metrics_tables.py

@@ -1,7 +1,7 @@
 {
   "name": "matbench-discovery",
   "description": "Benchmarking machine learning energy models for materials discovery.",
-  "author": "Janosh Riebesell <janosh@lbl.gov>",
+  "author": "Janosh Riebesell <janosh.riebesell@gmail.gov>",
   "homepage": "https://janosh.github.io/matbench-discovery",
   "repository": "https://github.com/janosh/matbench-discovery",
   "package": "https://pypi.org/project/matbench-discovery",
@@ -20,35 +20,35 @@
     "@iconify/svelte": "^3.1.6",
     "@rollup/plugin-yaml": "^4.1.2",
     "@sveltejs/adapter-static": "^3.0.1",
-    "@sveltejs/kit": "^2.3.2",
+    "@sveltejs/kit": "^2.4.1",
     "@sveltejs/vite-plugin-svelte": "^3.0.1",
-    "@typescript-eslint/eslint-plugin": "^6.18.1",
-    "@typescript-eslint/parser": "^6.18.1",
+    "@typescript-eslint/eslint-plugin": "^6.19.0",
+    "@typescript-eslint/parser": "^6.19.0",
     "d3-scale-chromatic": "^3.0.0",
     "elementari": "^0.2.3",
     "eslint": "^8.56.0",
     "eslint-plugin-svelte": "^2.35.1",
-    "hastscript": "^8.0.0",
+    "hastscript": "^9.0.0",
     "highlight.js": "^11.9.0",
     "js-yaml": "^4.1.0",
     "katex": "^0.16.9",
     "mdsvex": "^0.11.0",
-    "prettier": "^3.2.2",
+    "prettier": "^3.2.4",
     "prettier-plugin-svelte": "^3.1.2",
     "rehype-autolink-headings": "^7.1.0",
     "rehype-katex-svelte": "^1.2.0",
     "rehype-slug": "^6.0.0",
     "remark-math": "3.0.0",
-    "svelte": "^4.2.8",
+    "svelte": "^4.2.9",
     "svelte-check": "^3.6.3",
     "svelte-multiselect": "^10.2.0",
     "svelte-preprocess": "^5.1.3",
-    "svelte-toc": "^0.5.6",
+    "svelte-toc": "^0.5.7",
     "svelte-zoo": "^0.4.9",
     "svelte2tsx": "^0.7.0",
     "tslib": "^2.6.2",
     "typescript": "5.3.3",
-    "vite": "^5.0.11"
+    "vite": "^5.0.12"
   },
   "prettier": {
     "semi": false,

site/package.json

@@ -152,6 +152,9 @@ blockquote > :is(:first-child, :last-child) {
   margin: 0 auto;
 }
 
+:where(h1, h2, h3, h4, h5, h6, address) {
+  text-wrap: balance;
+}
 :where(h2, h3, h4, h5, h6) {
   scroll-margin-top: 50px;
   transition: 0.3s;

site/src/app.css

@@ -25,7 +25,7 @@
 <footer>
   <nav>
     <a href="{repository}/issues">Issues</a>
-    <a href="mailto:janosh@lbl.gov?subject=Matbench Discovery">Contact</a>
+    <a href="mailto:janosh.riebesell@gmail.gov?subject=Matbench Discovery">Contact</a>
     <a href="/changelog">Changelog</a>
     <button
       on:click={() => (show_tips = true)}

site/src/lib/Footer.svelte

@@ -63,8 +63,8 @@
   <h1>Leaderboard</h1>
 
   <p style="text-align: center;">
-    Sort models by stability classification metrics, by predicted convex hull distance
-    regressions metrics or by their tun time.
+    Sort models by different metrics (thermodynamic stability classification, convex hull
+    distance regressions or tun time).
   </p>
 
   <span>