Add new default feature preset and updates for new matminer & pymatgen versions

.github/dependabot.yml

@@ -3,8 +3,15 @@ updates:
 - package-ecosystem: pip
   directory: "/"
   schedule:
-    interval: daily
+    interval: monthly
   open-pull-requests-limit: 10
   target-branch: master
   labels:
   - dependency_updates
+- package-ecosystem: github-actions
+  directory: "/"
+  schedule:
+    interval: monthly
+  target-branch: master
+  labels:
+    - CI

.github/workflows/ci.yml

@@ -11,17 +11,22 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 30
     steps:
-    - uses: actions/checkout@v1
+
+    - uses: actions/checkout@v3
+
     - name: Set up Python 3.8
-      uses: actions/setup-python@v1
+      uses: actions/setup-python@v4
       with:
         python-version: 3.8
+        cache: 'pip'
+        cache-dependency-path: |
+          **/requirements*.txt
 
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
         pip install -r requirements.txt
-        pip install --ignore-installed .[test,dev]
+        pip install .[test,dev]
 
     - name: Run pre-commit
       run: |
@@ -44,4 +49,4 @@ jobs:
     - name: Run tests with pytest
       run: |
         # run tests with pytest, reporting coverage and timings
-        py.test -rs -vvv  --durations=0 --cov=./modnet/
+        pytest -m "not slow" -rs -vvv  --durations=0 --cov=./modnet/

.gitignore

@@ -1,9 +1,12 @@
+### Custom
+modnet/data/
+.mypy_cache
+
 ### Python template
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
 *$py.class
-modnet/data/
 
 # Distribution / packaging
 build/

.pre-commit-config.yaml

@@ -18,7 +18,7 @@ repos:
     - id: check-symlinks
     - id: end-of-file-fixer
 
-  - repo: https://gitlab.com/pycqa/flake8
-    rev: '3.9.2'
+  - repo: https://github.com/pycqa/flake8
+    rev: '6.0.0'
     hooks:
     -   id: flake8

README.md

@@ -1,6 +1,6 @@
 # MODNet: Material Optimal Descriptor Network
 
-[![arXiv](https://img.shields.io/badge/arXiv-2004.14766-brightgreen)](https://arxiv.org/abs/2004.14766) [![Build Status](https://img.shields.io/github/workflow/status/ppdebreuck/modnet/Run%20tests?logo=github)](https://github.com/ppdebreuck/modnet/actions?query=branch%3Amaster+) [![Read the Docs](https://img.shields.io/readthedocs/modnet)](https://modnet.readthedocs.io/en/latest/)
+[![arXiv](https://img.shields.io/badge/arXiv-2004.14766-brightgreen)](https://arxiv.org/abs/2004.14766) [![Build Status](https://img.shields.io/github/actions/workflow/status/ppdebreuck/modnet/ci.yml?logo=github&branch=main)](https://github.com/ppdebreuck/modnet/actions?query=branch%3Amaster+) [![Read the Docs](https://img.shields.io/readthedocs/modnet)](https://modnet.readthedocs.io/en/latest/)
 
 <a name="introduction"></a>
 ## Introduction
@@ -47,14 +47,6 @@ Activate the environment:
 conda activate modnet
 ```
 
-Then, install pymatgen v2020.8.13 with conda, which will bundle several pre-built dependencies (e.g., numpy, scipy):
-
-```shell
-conda install -c conda-forge pymatgen=2020.8.13
-```
-
-(you could alternatively do this step with `pip install pymatgen==2020.8.13`).
-
 Finally, install MODNet from PyPI with `pip`:
 
 ```shell

docs/requirements.txt

@@ -1,3 +1,3 @@
-sphinx~=4.4
+sphinx~=5.3
 sphinx-rtd-theme~=1.0
 sphinxcontrib-napoleon~=0.7

modnet/__init__.py

@@ -1 +1 @@
-__version__ = "0.1.13"
+__version__ = "0.2.0~develop"

modnet/featurizers/featurizers.py

@@ -70,7 +70,7 @@ def featurize(self, df: pd.DataFrame) -> pd.DataFrame:
 
         Arguments:
             df: the input dataframe with a `"structure"` column
-                containing `pymatgen.Structure` objects.
+                containing pymatgen `Structure` objects.
 
         Returns:
             The featurized DataFrame.
@@ -137,7 +137,7 @@ def featurize_composition(self, df: pd.DataFrame) -> pd.DataFrame:
 
         Arguments:
             df: the input dataframe with a `"structure"` column
-                containing `pymatgen.Structure` objects.
+                containing pymatgen `Structure` objects.
 
         Returns:
             pandas.DataFrame: the decorated DataFrame, or an empty
@@ -184,7 +184,7 @@ def featurize_structure(self, df: pd.DataFrame) -> pd.DataFrame:
 
         Arguments:
             df: the input dataframe with a `"structure"` column
-                containing `pymatgen.Structure` objects.
+                containing pymatgen `Structure` objects.
 
         Returns:
             pandas.DataFrame: the decorated DataFrame.
@@ -206,7 +206,7 @@ def featurize_site(
 
         Arguments:
             df: the input dataframe with a `"structure"` column
-                containing `pymatgen.Structure` objects.
+                containing pymatgen `Structure` objects.
             aliases: optional dictionary to map matminer output column
                 names to new aliases, mostly used for
                 backwards-compatibility.

modnet/featurizers/presets/__init__.py

@@ -1,8 +1,20 @@
-__all__ = ("FEATURIZER_PRESETS",)
+__all__ = (
+    "FEATURIZER_PRESETS",
+    "DEFAULT_FEATURIZER",
+    "DEFAULT_COMPOSITION_ONLY_FEATURIZER",
+)
 
+from typing import Dict, Type
 from .debreuck_2020 import DeBreuck2020Featurizer, CompositionOnlyFeaturizer
+from .matminer_2023 import Matminer2023Featurizer, CompositionOnlyMatminer2023Featurizer
+from modnet.featurizers import MODFeaturizer
 
-FEATURIZER_PRESETS = {
+DEFAULT_FEATURIZER: str = "Matminer2023"
+DEFAULT_COMPOSITION_ONLY_FEATURIZER: str = "CompositionOnlyMatminer2023"
+
+FEATURIZER_PRESETS: Dict[str, Type[MODFeaturizer]] = {
     "DeBreuck2020": DeBreuck2020Featurizer,
     "CompositionOnly": CompositionOnlyFeaturizer,
+    "Matminer2023": Matminer2023Featurizer,
+    "CompositionOnlyMatminer2023": CompositionOnlyMatminer2023Featurizer,
 }

modnet/featurizers/presets/debreuck_2020.py

@@ -1,26 +1,59 @@
 """ This submodule contains the DeBreuck2020Featurizer class. """
 
 import numpy as np
-from pymatgen.core.periodic_table import Element
-from pymatgen.analysis.local_env import VoronoiNN
 import modnet.featurizers
 import contextlib
+import warnings
 
 
 class DeBreuck2020Featurizer(modnet.featurizers.MODFeaturizer):
-    """Featurizer presets used for the paper 'Machine learning
-    materials properties for small datasets' by Pierre-Paul De Breuck,
-    Geoffroy Hautier & Gian-Marco Rignanese, arXiv:2004.14766 (2020).
+    """Featurizer presets used for the paper
+
+        **Materials property prediction for limited datasets enabled
+        by feature selection and joint learning with MODNet**,
+        Pierre-Paul De Breuck, Geoffroy Hautier & Gian-Marco Rignanese
+        npj Comp. Mat. 7(1) 1-8 (2021)
+        10.1038/s41524-021-00552-2
 
     Uses most of the featurizers implemented by matminer at the time of
     writing with their default hyperparameters and presets.
 
     """
 
-    def __init__(self, fast_oxid=False):
-        super().__init__()
+    package_version_requirements = {"matminer": "==0.6.2"}
+
+    def __init__(self, fast_oxid: bool = False):
+        """Creates the featurizer and imports all featurizer functions.
+
+        Parameters:
+            fast_oxid: Whether to use the accelerated oxidation state parameters within
+                pymatgen when constructing features that constrain oxidation states such
+                that all sites with the same species in a structure will have the same
+                oxidation state (recommended if featurizing any structure
+                with large unit cells).
+
+        """
+        import matminer
+
+        if matminer.__version__ != self.package_version_requirements[
+            "matminer"
+        ].replace("==", ""):
+            warnings.warn(
+                f"The {self.__class__.__name__} preset was written for and tested only with matminer{self.package_version_requirements['matminer']}.\n"
+                "Newer versions of matminer will not work, and older versions may not be compatible with newer MODNet versions due to other conflicts.\n"
+                "To use this featurizer robustly, please install `modnet==0.1.13` with its pinned dependencies.\n\n"
+                "This preset will now be initialised without importing matminer featurizers to enable use with existing previously featurized data, "
+                "but attempts to perform further featurization will result in an error."
+            )
 
+        else:
+            super().__init__()
+            self.load_featurizers()
+            self.fast_oxid = fast_oxid
+
+    def load_featurizers(self):
         with contextlib.redirect_stdout(None):
+            from pymatgen.analysis.local_env import VoronoiNN
             from matminer.featurizers.composition import (
                 AtomicOrbitals,
                 AtomicPackingEfficiency,
@@ -117,13 +150,14 @@ def __init__(self, fast_oxid=False):
                 OPSiteFingerprint(),
                 VoronoiFingerprint(),
             )
-        self.fast_oxid = fast_oxid
 
     def featurize_composition(self, df):
         """Applies the preset composition featurizers to the input dataframe,
         renames some fields and cleans the output dataframe.
 
         """
+        from pymatgen.core.periodic_table import Element
+
         df = super().featurize_composition(df)
 
         _orbitals = {"s": 1, "p": 2, "d": 3, "f": 4}
@@ -151,18 +185,21 @@ def featurize_structure(self, df):
 
         df = super().featurize_structure(df)
 
-        dist = df["RadialDistributionFunction|radial distribution function"].iloc[0][
-            "distances"
-        ][:50]
-        for i, d in enumerate(dist):
-            _rdf_key = "RadialDistributionFunction|radial distribution function|d_{:.2f}".format(
-                d
-            )
-            df[_rdf_key] = df[
-                "RadialDistributionFunction|radial distribution function"
-            ].apply(lambda x: x["distribution"][i])
+        if "RadialDistributionFunction|radial distribution function" in df:
+            dist = df["RadialDistributionFunction|radial distribution function"].iloc[
+                0
+            ]["distances"][:50]
+            for i, d in enumerate(dist):
+                _rdf_key = "RadialDistributionFunction|radial distribution function|d_{:.2f}".format(
+                    d
+                )
+                df[_rdf_key] = df[
+                    "RadialDistributionFunction|radial distribution function"
+                ].apply(lambda x: x["distribution"][i])
 
-        df = df.drop("RadialDistributionFunction|radial distribution function", axis=1)
+            df = df.drop(
+                "RadialDistributionFunction|radial distribution function", axis=1
+            )
 
         _crystal_system = {
             "cubic": 1,
@@ -210,6 +247,20 @@ def featurize_site(self, df):
 
 
 class CompositionOnlyFeaturizer(DeBreuck2020Featurizer):
+    """This subclass simply disables structure and site-level features
+    from the main `DeBreuck2020Featurizer` class.
+
+        **Materials property prediction for limited datasets enabled
+        by feature selection and joint learning with MODNet**
+        Pierre-Paul De Breuck, Geoffroy Hautier & Gian-Marco Rignanese
+        npj Comp. Mat. 7(1) 1-8 (2021)
+        10.1038/s41524-021-00552-2
+
+    Uses most of the featurizers implemented by matminer at the time of
+    writing with their default hyperparameters and presets.
+
+    """
+
     def __init__(self):
         super().__init__()
         self.oxid_composition_featurizers = ()