Drop Python 3.8 and update other deps

.github/workflows/ci.yml

@@ -14,10 +14,10 @@ jobs:
 
     - uses: actions/checkout@v3
 
-    - name: Set up Python 3.8
+    - name: Set up Python 3.10
       uses: actions/setup-python@v4
       with:
-        python-version: '3.8'
+        python-version: '3.10'
 
     - name: Install pre-commit
       run: |
@@ -34,9 +34,9 @@ jobs:
     timeout-minutes: 30
     strategy:
       fail-fast: false
-      max-parallel: 3
+      max-parallel: 4
       matrix:
-        python-version: ['3.8', '3.9', '3.10']
+        python-version: ['3.9', '3.10']
 
     steps:
 

.pre-commit-config.yaml

@@ -1,15 +1,15 @@
 default_language_version:
-  python: python3.8
+  python: python3.10
 
 repos:
   - repo: https://github.com/ambv/black
-    rev: 22.3.0
+    rev: 24.3.0
     hooks:
     - id: black
       name: Blacken
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
+    rev: v4.5.0
     hooks:
     - id: check-added-large-files
       args: [--maxkb=1024]
@@ -19,6 +19,6 @@ repos:
     - id: end-of-file-fixer
 
   - repo: https://github.com/pycqa/flake8
-    rev: '6.0.0'
+    rev: '7.0.0'
     hooks:
     -   id: flake8

modnet/featurizers/featurizers.py

@@ -223,9 +223,9 @@ def featurize_composition(self, df: pd.DataFrame) -> pd.DataFrame:
                 df["integer_composition"] = [
                     Composition(
                         comp.get_integer_formula_and_factor(
-                            max_denominator=10
-                            if getattr(self, "fast_oxid", False)
-                            else 100
+                            max_denominator=(
+                                10 if getattr(self, "fast_oxid", False) else 100
+                            )
                         )[0]
                     )
                     for comp in df["composition"].values

modnet/hyper_opt/fit_genetic.py

@@ -438,9 +438,9 @@ def function_fitness(
         from modnet.matbench.benchmark import matbench_kfold_splits
         import os
 
-        os.environ[
-            "TF_CPP_MIN_LOG_LEVEL"
-        ] = "2"  # many models will be fitted => reduce output
+        os.environ["TF_CPP_MIN_LOG_LEVEL"] = (
+            "2"  # many models will be fitted => reduce output
+        )
 
         num_nested_folds = 5
         if nested:

modnet/models/ensemble.py

@@ -255,9 +255,9 @@ def fit_preset(
         from modnet.matbench.benchmark import matbench_kfold_splits
         import os
 
-        os.environ[
-            "TF_CPP_MIN_LOG_LEVEL"
-        ] = "2"  # many models will be fitted => reduce output
+        os.environ["TF_CPP_MIN_LOG_LEVEL"] = (
+            "2"  # many models will be fitted => reduce output
+        )
 
         if callbacks is None:
             es = tf.keras.callbacks.EarlyStopping(

modnet/models/vanilla.py

@@ -535,9 +535,9 @@ def fit_preset(
         from modnet.matbench.benchmark import matbench_kfold_splits
         import os
 
-        os.environ[
-            "TF_CPP_MIN_LOG_LEVEL"
-        ] = "2"  # many models will be fitted => reduce output
+        os.environ["TF_CPP_MIN_LOG_LEVEL"] = (
+            "2"  # many models will be fitted => reduce output
+        )
 
         if callbacks is None:
             es = tf.keras.callbacks.EarlyStopping(

modnet/preprocessing.py

@@ -924,15 +924,16 @@ def rebalance(self):
                 max_support = support.max()
                 for i in range(self.num_classes[targ]):
                     idxs = np.where(self.df_targets[targ].values == i)[0]
-                    sampled_x, sampled_y, sampled_struct = resample(
-                        self.df_featurized.iloc[idxs],
-                        self.df_targets.iloc[idxs],
-                        self.df_structure.iloc[idxs],
-                        n_samples=int(max_support - support[i]),
-                    )
-                    self.df_featurized = self.df_featurized.append(sampled_x)
-                    self.df_targets = self.df_targets.append(sampled_y)
-                    self.df_structure = self.df_structure.append(sampled_struct)
+                    if max_support - support[i] > 0:
+                        sampled_x, sampled_y, sampled_struct = resample(
+                            self.df_featurized.iloc[idxs],
+                            self.df_targets.iloc[idxs],
+                            self.df_structure.iloc[idxs],
+                            n_samples=int(max_support - support[i]),
+                        )
+                        self.df_featurized = self.df_featurized.append(sampled_x)
+                        self.df_targets = self.df_targets.append(sampled_y)
+                        self.df_structure = self.df_structure.append(sampled_struct)
 
     @property
     def structures(self) -> List[Union[Structure, CompositionContainer]]:

modnet/sklearn.py

@@ -24,7 +24,6 @@
   (see https://scikit-learn.org/stable/developers/develop.html#instantiation).
 """
 
-
 from sklearn.base import BaseEstimator
 from sklearn.base import RegressorMixin
 from sklearn.base import TransformerMixin

requirements.txt

@@ -3,5 +3,5 @@ pandas==1.5.2
 pymatgen==2023.7.20
 matminer==0.8.0
 numpy>=1.20
-scikit-learn==1.2.0
+scikit-learn==1.3.2
 ruamel.yaml~=0.17,<0.18  # Required until matminer updates

setup.py

@@ -13,8 +13,8 @@
 
 version = re.search('__version__ = "(.*)"', lines).group(1)
 
-tests_require = ("pytest>=6.0", "pytest-cov>=2.10", "flake8>=3.8")
-dev_require = ("pre-commit~=2.11",)
+tests_require = ("pytest~=8.0", "pytest-cov~=5.0", "flake8~=7.0")
+dev_require = ("pre-commit~=3.7",)
 
 setuptools.setup(
     name="modnet",
@@ -34,10 +34,10 @@
     install_requires=[
         "pandas~=1.5",
         "tensorflow~=2.10",
-        "pymatgen>=2022.9",
+        "pymatgen>=2023",
         "matminer~=0.8",
-        "numpy>=1.20",
-        "scikit-learn~=1.1",
+        "numpy>=1.24",
+        "scikit-learn~=1.3",
         "ruamel.yaml~=0.17,<0.18",  # Required until matminer updates
     ],
     tests_require=tests_require,
@@ -48,9 +48,7 @@
         "dev": dev_require,
     },
     classifiers=[
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3",
         "Intended Audience :: Science/Research",
         "Topic :: Scientific/Engineering :: Information Analysis",
         "Topic :: Scientific/Engineering :: Physics",
@@ -59,5 +57,5 @@
         "License :: OSI Approved :: MIT License",
         "Operating System :: OS Independent",
     ],
-    python_requires=">=3.8",
+    python_requires=">=3.9",
 )