make metrics-table sortable with svelte-zoo action

fix code in svelte.config.js for referencing figures in markdown with @fig:label syntax

add ruff config and move existing linter config from setup.cfg to pyproject.toml
replace isort black flake8 pyupgrade autoflake pydocstyle pre-commit hooks with ruff
update site deps

Author: janosh

.pre-commit-config.yaml

@@ -6,28 +6,17 @@ default_stages: [commit]
 default_install_hook_types: [pre-commit, commit-msg]
 
 repos:
-  - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.0.249
     hooks:
-      - id: isort
+      - id: ruff
+        args: [--fix]
 
   - repo: https://github.com/psf/black
     rev: 23.1.0
     hooks:
       - id: black
 
-  - repo: https://github.com/pycqa/flake8
-    rev: 6.0.0
-    hooks:
-      - id: flake8
-        additional_dependencies: [flake8-bugbear]
-
-  - repo: https://github.com/asottile/pyupgrade
-    rev: v3.3.1
-    hooks:
-      - id: pyupgrade
-        args: [--py39-plus]
-
   - repo: https://github.com/janosh/format-ipy-cells
     rev: v0.1.10
     hooks:
@@ -45,7 +34,7 @@ repos:
       - id: trailing-whitespace
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.991
+    rev: v1.0.1
     hooks:
       - id: mypy
         additional_dependencies: [types-pyyaml, types-requests]
@@ -57,11 +46,7 @@ repos:
         stages: [commit, commit-msg]
         exclude_types: [csv, json, svg]
         exclude: ^(.+references.yaml|site/src/figs/.+)$
-
-  - repo: https://github.com/PyCQA/autoflake
-    rev: v2.0.1
-    hooks:
-      - id: autoflake
+        args: [--ignore-words-list, "nd,te,fpr"]
 
   - repo: https://github.com/pre-commit/mirrors-prettier
     rev: v3.0.0-alpha.4
@@ -75,7 +60,7 @@ repos:
         exclude: ^(site/src/figs/.+\.svelte|data/wbm/20.+\..+|site/src/routes/.+\.(yml|yaml|json))$
 
   - repo: https://github.com/pre-commit/mirrors-eslint
-    rev: v8.33.0
+    rev: v8.34.0
     hooks:
       - id: eslint
         types: [file]
@@ -88,9 +73,3 @@ repos:
           - eslint-plugin-svelte3
           - "@typescript-eslint/eslint-plugin"
           - "@typescript-eslint/parser"
-
-  - repo: https://github.com/PyCQA/pydocstyle
-    rev: 6.3.0
-    hooks:
-      - id: pydocstyle
-        exclude: tests

data/wbm/fetch_process_wbm_dataset.py

@@ -322,7 +322,7 @@ def increment_wbm_material_id(wbm_id: str) -> str:
 
 df_summary.index = df_summary.index.map(increment_wbm_material_id)  # format IDs
 # drop materials with id='None' and missing initial structures
-df_summary = df_summary.drop(index=nan_init_structs_ids + ["None"])
+df_summary = df_summary.drop(index=[*nan_init_structs_ids, "None"])
 
 # the 8403 material IDs in step 3 with final number larger than any of the ones in
 # bad_struct_ids are now misaligned between df_summary and df_wbm

matbench_discovery/energy.py

@@ -87,7 +87,7 @@ def get_e_form_per_atom(
         entry: Entry | dict[str, float | str | Composition]: pymatgen Entry (PDEntry,
             ComputedEntry or ComputedStructureEntry) or dict with energy and composition
             keys to compute formation energy of.
-        elemental_ref_entries (dict[str, float], optional): Must be a covering set (for
+        elemental_ref_energies (dict[str, float], optional): Must be a covering set (for
             entry) of terminal reference energies, i.e. eV/atom of the lowest energy
             elemental phase for each element. Defaults to MP elemental reference
             energies as collected on 2022-09-19 get_elemental_ref_entries(). This was

matbench_discovery/metrics.py

@@ -55,8 +55,7 @@ def stable_metrics(
     each_pred: Sequence[float],
     stability_threshold: float = 0,
 ) -> dict[str, float]:
-    """
-    Get a dictionary of stability prediction metrics. Mostly binary classification
+    """Get a dictionary of stability prediction metrics. Mostly binary classification
     metrics, but also MAE, RMSE and R2.
 
     Args:

matbench_discovery/plots.py

@@ -314,10 +314,14 @@ def rolling_mae_vs_hull_dist(
         e_above_hull_errors (pd.DataFrame | dict[str, pd.Series]): Error in
             model-predicted distance to convex hull, i.e. actual hull distance minus
             predicted hull distance (in eV / atom).
+        df_rolling_err (pd.DataFrame, optional): Cached rolling MAE(s) as returned by
+            previous call to this function. Defaults to None.
+        df_err_std (pd.DataFrame, optional): Cached standard error in the mean of the
+            rolling MAE(s) as returned by prev. call to this function. Defaults to None.
         window (float, optional): Rolling MAE averaging window. Defaults to 0.02 (20
-        meV/atom) bin_width (float, optional): Density of line points (more points the
-        smaller).
-            Defaults to 0.002.
+            meV/atom)
+        bin_width (float, optional): Density of line points (more points the
+            smaller). Defaults to 0.002.
         x_lim (tuple[float, float], optional): x-axis range. Defaults to (-0.2, 0.3).
         y_lim (tuple[float, float], optional): y-axis range. Defaults to (0.0, 0.14).
         backend ('matplotlib' | 'plotly'], optional): Which plotting engine to use.
@@ -326,13 +330,17 @@ def rolling_mae_vs_hull_dist(
         just_plot_line (bool, optional): If True, plot only the rolling MAE, no shapes
             and annotations. Also won't plot the standard error in the mean. Defaults
             to False.
+        just_plot_lines (bool, optional): If True, plot only the rolling MAE, no shapes
+            and annotations. Also won't plot the standard error in the mean. Defaults
+            to False.
         with_sem (bool, optional): If True, plot the standard error of the mean as
             shaded area around the rolling MAE. Defaults to True.
         show_dft_acc (bool, optional): If True, change color of the triangle of peril's tip
             and annotate it with 'Corrected GGA Accuracy' at rolling MAE of 25 meV/atom.
             Defaults to False.
         show_dummy_mae (bool, optional): If True, plot a line at the dummy MAE of always
             predicting the target mean.
+        **kwargs: Additional keyword arguments to pass to df.plot().
 
     Returns:
         tuple[plt.Axes | go.Figure, pd.DataFrame, pd.DataFrame]: matplotlib Axes or

matbench_discovery/structure.py

@@ -8,10 +8,11 @@
 
 
 def perturb_structure(struct: Structure, gamma: float = 1.5) -> Structure:
-    """Perturb the atomic coordinates of a pymatgen structure
+    """Perturb the atomic coordinates of a pymatgen structure.
 
     Args:
         struct (Structure): pymatgen structure to be perturbed
+        gamma (float, optional): Weibull distribution parameter. Defaults to 1.5.
 
     Returns:
         Structure: Perturbed structure

models/voronoi/__init__.py

@@ -1,6 +1,5 @@
-"""
-Recreate the featurizer used by Ward et al. in
-https://journals.aps.org/prb/abstract/10.1103/PhysRevB.96.024104
+"""Recreate the featurizer used by Ward et al. in
+https://journals.aps.org/prb/abstract/10.1103/PhysRevB.96.024104.
 """
 
 import matminer.featurizers.composition as fc
@@ -30,7 +29,7 @@
     fs.StructuralHeterogeneity(),
 ]
 featurizer = MultipleFeaturizer(
-    structure_features + [*map(fs.StructureComposition, composition_features)]
+    [*structure_features, *map(fs.StructureComposition, composition_features)]
 )
 
 

pyproject.toml

@@ -0,0 +1,52 @@
+[tool.black]
+line-length = 95
+
+[tool.ruff]
+target-version = "py39"
+line-length = 95
+select = [
+  "B",   # flake8-bugbear
+  "C4",  # flake8-comprehensions
+  "D",   # pydocstyle
+  "E",   # pycodestyle
+  "F",   # pyflakes
+  "I",   # isort
+  "PLE", # pylint error
+  "PLW", # pylint warning
+  "Q",   # flake8-quotes
+  "RUF", # Ruff-specific rules
+  "SIM", # flake8-simplify
+  "TID", # tidy imports
+  "UP",  # pyupgrade
+  "W",   # pycodestyle
+  "YTT", # flake8-2020
+]
+ignore = [
+  "C408",    # Unnecessary dict call - rewrite as a literal
+  "D100",    # Missing docstring in public module
+  "D104",    # Missing docstring in public package
+  "D105",    # Missing docstring in magic method
+  "D107",    # Missing docstring in __init__
+  "D205",    # 1 blank line required between summary line and description
+  "E731",   # Do not assign a lambda expression, use a def
+]
+pydocstyle.convention = "google"
+isort.known-third-party = ["wandb"]
+
+[tool.ruff.per-file-ignores]
+"tests/*" = ["D"]
+
+[tool.mypy]
+check_untyped_defs = true
+disallow_untyped_defs = true
+disallow_any_generics = true
+disallow_incomplete_defs = true
+warn_redundant_casts = true
+warn_unused_ignores = true
+allow_redefinition = true
+no_namespace_packages = true
+no_implicit_optional = false
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-p no:warnings"

scripts/compile_metrics.py

@@ -148,7 +148,14 @@
 
 # %% export model metrics as styled HTML table
 # insert svelte {...props} forwarding to the table element
-html_table = styler.to_html().replace("<table", "<table {...$$props}")
+insert = """
+<script>
+  import { sortable } from 'svelte-zoo/actions'
+</script>
+
+<table use:sortable {...$$props}
+"""
+html_table = styler.to_html().replace("<table", insert)
 with open(f"{FIGS}/metrics-table.svelte", "w") as file:
     file.write(html_table)
 

scripts/make_api_docs.py

@@ -21,7 +21,8 @@
 
 # Tweak lazydocs's markdown output:
 for path in glob(f"{out_path}/*.md"):
-    text = open(path).read()
+    with open(path) as file:
+        text = file.read()
 
     # remove bold tags since they break inline code
     text = text.replace("<b>", "").replace("</b>", "")
@@ -31,4 +32,5 @@
         'src="https://img.shields.io/badge/-source-cccccc?style=flat-square"',
         'src="https://img.shields.io/badge/source-blue?style=flat" alt="source link"',
     )
-    open(path, "w").write(text)
+    with open(path, "w") as file:
+        file.write(text)

site/package.json

@@ -19,11 +19,11 @@
   "devDependencies": {
     "@iconify/svelte": "^3.1.0",
     "@rollup/plugin-yaml": "^4.0.1",
-    "@sveltejs/adapter-static": "^1.0.6",
-    "@sveltejs/kit": "^1.6.0",
+    "@sveltejs/adapter-static": "^2.0.1",
+    "@sveltejs/kit": "^1.8.3",
     "@sveltejs/vite-plugin-svelte": "^2.0.2",
-    "@typescript-eslint/eslint-plugin": "^5.52.0",
-    "@typescript-eslint/parser": "^5.52.0",
+    "@typescript-eslint/eslint-plugin": "^5.53.0",
+    "@typescript-eslint/parser": "^5.53.0",
     "elementari": "^0.1.0",
     "eslint": "^8.34.0",
     "eslint-plugin-svelte3": "^4.0.0",
@@ -41,11 +41,11 @@
     "svelte-multiselect": "^8.3.0",
     "svelte-preprocess": "^5.0.1",
     "svelte-toc": "^0.5.2",
-    "svelte-zoo": "^0.2.6",
+    "svelte-zoo": "^0.3.4",
     "svelte2tsx": "^0.6.1",
     "tslib": "^2.5.0",
     "typescript": "^4.9.5",
-    "vite": "^4.1.1"
+    "vite": "^4.1.3"
   },
   "keywords": [
     "materials discovery",