Merge branch 'main' into dependabot/pip/hdbscan-0.8.29

sparks-baird · Jul 8, 2023 · b22d11f · b22d11f
2 parents f1b7802 + 9dafd51
commit b22d11f
Show file tree

Hide file tree

Showing 21 changed files with 1,482 additions and 563 deletions.
diff --git a/.github/workflows/flit-install-test.yml b/.github/workflows/flit-install-test.yml
@@ -11,6 +11,8 @@ on:
     - "**"
     tags-ignore:
     - "*.*.*"
+  pull_request: # Run in every PR
+  workflow_dispatch: # Allow manually triggering the workflow
 
 jobs:
   pytest:

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -6,6 +6,6 @@ repos:
 #     -   id: end-of-file-fixer
 #     -   id: trailing-whitespace
 -   repo: https://github.com/psf/black
-    rev: 19.3b0
+    rev: 23.3.0
     hooks:
     -   id: black
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -94,7 +94,18 @@
 
 html_extra_path = ["googlea441f484329a8f75.html"]
 
-autodoc_mock_imports = ["numba", "torch", "pymatgen", "hdbscan"]
+autodoc_mock_imports = [
+    "numba",
+    "torch",
+    "pymatgen",
+    "hdbscan",
+    "matbench_genmetrics",
+    "matminer",
+    "tensorflow",
+    "megnet",
+    "m3gnet",
+    "umap",
+]
 
 # https://github.com/sphinx-doc/sphinx/issues/7000#issuecomment-677916705
 source_suffix = [".rst", ".md"]
diff --git a/docs/source/contributing.rst b/docs/source/contributing.rst
@@ -1,3 +1,5 @@
+Contributing
+============
 ```{include} ../../CONTRIBUTING.md
 :relative-images:
 ```
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -6,12 +6,12 @@
 Welcome to Chemically Novel Materials Discovery!
 ================================================
 
-This is the documentation for `mat_discover <https://github.com/sparks-baird/mat_discover>`_. Descending from Stochastic Clustering Variance Regression (DiSCoVeR) is a
-composition-based materials
-discovery algorithm. DiSCoVeR emphasizes exploring high-performance candidates in new chemical
+This is the documentation for `mat_discover <https://github.com/sparks-baird/mat_discover>`_. Descending from Stochastic Clustering Variance Regression (DiSCoVeR) is a materials
+discovery algorithm for composition- or structure-based materials. DiSCoVeR emphasizes exploring high-performance candidates in new chemical
 spaces as originally proposed by Baird, Diep, and Sparks (`Digital Discovery <https://dx.doi.org/10.1039/D1DD00028D>`_, `ChemRxiv <https://dx.doi.org/10.33774/chemrxiv-2021-5l2f8-v3>`_). The
 library :code:`mat_discover` provides a GPU-accelerated (and CPU-compatible) Python
-implementation and tools for analyzing the outputs. :code:`mat_discover` will "suggest your next experiment" using a custom training dataset of chemical formula and target
+implementation and tools for analyzing the outputs. :code:`mat_discover` will "suggest
+your next experiment" using a custom training dataset of chemical formula or structure and target
 properties and a custom validation set of potential candidates. All in just a few lines of code! `Get started learning about DiSCoVeR <https://mat-discover.readthedocs.io/en/latest/readme.html>`_.
 
 .. raw:: html
@@ -37,6 +37,7 @@ properties and a custom validation set of potential candidates. All in just a fe
    figures
    contributing
    modules
+   GitHub Source <https://github.com/sparks-baird/mat_discover>
 
 Indices and tables
 ==================

diff --git a/docs/source/readme.md b/docs/source/readme.md
@@ -34,7 +34,7 @@ working on an [implementation of composition-based Bayesian optimization
 using Ax](https://github.com/facebook/Ax/issues/727) (2021-12-10).
 
 For alternative "suggest next experiment" materials discovery tools,
-see the [Citrine Platform](https://citrination.com/) (free for non-commercial use), [CAMD](https://github.com/TRI-AMDD/CAMD) ([trihackathon2020 tutorial notebooks](https://github.com/TRI-AMDD/tri-hackathon-2020)), [PyChemia](https://github.com/MaterialsDiscovery/PyChemia),
+see the [Citrine Platform](https://citrination.com/) (proprietary), [ChemOS](https://chemos.io/) (proprietary), [Olympus](https://aspuru-guzik-group.github.io/olympus/), [CAMD](https://github.com/TRI-AMDD/CAMD) ([trihackathon2020 tutorial notebooks](https://github.com/TRI-AMDD/tri-hackathon-2020)), [PyChemia](https://github.com/MaterialsDiscovery/PyChemia),
 [Heteroscedastic-BO](https://github.com/Ryan-Rhys/Heteroscedastic-BO), and
 [thermo](https://github.com/janosh/thermo).
 

diff --git a/environment.yml b/environment.yml
@@ -12,7 +12,7 @@ dependencies:
   - pandas
   - pytorch >=1.9.0
   - plotly
-  - python >=3.7,<3.10
+  - python >=3.7
   - scipy
   - cudatoolkit <11.4
   - numba >=0.53.1
@@ -34,6 +34,8 @@ dependencies:
   - pip:
     # core:
     - ElM2D ==0.4.1
+    - matbench_genmetrics
+    - matbench
   # optional:
   - ipykernel
   - nbformat >=4.2.0

diff --git a/examples/crabnet_performance.py b/examples/crabnet_performance.py
@@ -4,6 +4,7 @@
 # TODO: incorporate CrabNet uncertainty into search
 """
 from crabnet.crabnet_ import CrabNet
+import pandas as pd
 
 # %% imports
 from tqdm import tqdm
@@ -82,7 +83,7 @@
         idx = perf_val_df.pred.idxmax()
         # idx = np.where(val_pred == max(val_pred))[0][0]
         move_row = perf_val_df.loc[idx]
-        perf_train_df.append(move_row)
+        perf_train_df = pd.concat((perf_train_df, move_row))
         perf_val_df = perf_val_df.drop(index=idx)
         next_experiments.append(move_row.to_dict())
     experiment = ad_experiments_metrics(

diff --git a/examples/structurally-aware-mat-discover-bare-bones.ipynb b/examples/structurally-aware-mat-discover-bare-bones.ipynb
@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "colab_type": "text",
@@ -11,6 +12,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "MMu_LzmX3LpF"
@@ -22,6 +24,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "L33XMjHe4QRS"
@@ -55,6 +58,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "e0mvzmq43JxT"
@@ -83,6 +87,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "WdMXy0Xe3U4L"
@@ -116,10 +121,11 @@
     "from m3gnet.models import M3GNet\n",
     "from m3gnet.trainers import Trainer\n",
     "from matbench.bench import MatbenchBenchmark\n",
-    "from matbench_genmetrics.utils.featurize import cdvae_cov_struct_fingerprints"
+    "from matbench_genmetrics.core.utils.featurize import cdvae_cov_struct_fingerprints"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "FJxouWga4x0o"
@@ -322,6 +328,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "S-MXvBpO3GTc"
@@ -378,6 +385,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "G0MkF2vC5ux7"
@@ -470,6 +478,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "GRY0BlXP3EUj"
@@ -577,6 +586,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "adO7u1h93CnD"
@@ -643,6 +653,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "JXcjLXuy2_m7"
@@ -794,6 +805,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "qQiTahYJ5-kC"
@@ -829,6 +841,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "92FfjLOt6AY5"