Merge pull request JaGeo#331 from naik-aakash/update_calc_quality

Update calc quality and fingerprints usage

.github/workflows/python-package.yml

@@ -17,11 +17,11 @@ jobs:
 
       - uses: actions/setup-python@v4
         with:
-          python-version: "3.9"
+          python-version: "3.10"
           cache: pip
           cache-dependency-path: pyproject.toml
 
-      - uses: pre-commit/[email protected].0
+      - uses: pre-commit/[email protected].1
 
   test:
     runs-on: ubuntu-latest
@@ -31,7 +31,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.10", "3.11", "3.12"]
         split: [1, 2, 3, 4, 5, 6]
 
 
@@ -63,10 +63,12 @@ jobs:
         pytest --cov=lobsterpy --cov-report term-missing --cov-append --splits 6 --group ${{ matrix.split }} -vv --durations-path ./tests/test_data/.pytest-split-durations
 
     - name: Upload coverage
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
-        name: coverage-${{ matrix.split }}
-        path: .coverage
+        name: coverage-${{ matrix.split }}-${{ matrix.python-version }}
+        include-hidden-files: true
+        overwrite: false
+        path: ./.coverage
 
   coverage:
       needs: test
@@ -84,12 +86,12 @@ jobs:
 
         - name: Download coverage artifacts
           continue-on-error: true
-          uses: actions/download-artifact@v3
+          uses: actions/download-artifact@v4
 
         - name: Run coverage
           continue-on-error: true
           run: |
-            coverage combine coverage*/.coverage*
+            coverage combine coverage*/.coverage-*-3.10
             coverage report --show-missing
 
         - name: Upload coverage reports to Codecov

pyproject.toml

@@ -20,17 +20,16 @@ authors = [{ name = "Janine George", email = "[email protected]" }]
 version = "0.4.7"
 classifiers = [
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Development Status :: 5 - Production/Stable",
     "Intended Audience :: Science/Research",
     "Operating System :: OS Independent",
 ]
-requires-python = ">=3.9,<3.13"
+requires-python = ">=3.10,<3.13"
 dependencies = [
-     "pymatgen>=2024.5.1",
+     "pymatgen>=2024.9.10",
      "numpy<3.0.0",
      "typing",
 ]

src/lobsterpy/cohp/analyze.py

@@ -1693,18 +1693,18 @@ def get_lobster_calc_quality_summary(
                     max_e=max_e,
                     n_bins=n_bins,
                     normalize=True,
-                    type=orb.name,
+                    fp_type=orb.name,
                 )
                 fp_vasp_orb = dos_vasp.get_dos_fp(
                     min_e=min_e,
                     max_e=max_e,
                     n_bins=n_bins,
                     normalize=True,
-                    type=orb.name,
+                    fp_type=orb.name,
                 )
 
                 tani_orb = round(
-                    dos_vasp.get_dos_fp_similarity(fp_lobster_orb, fp_vasp_orb, tanimoto=True),
+                    dos_vasp.get_dos_fp_similarity(fp_lobster_orb, fp_vasp_orb, metric="tanimoto"),
                     4,
                 )
                 quality_dict["dos_comparisons"][f"tanimoto_orb_{orb.name}"] = tani_orb  # type: ignore
@@ -1714,17 +1714,17 @@ def get_lobster_calc_quality_summary(
                 max_e=max_e,
                 n_bins=n_bins,
                 normalize=True,
-                type="summed_pdos",
+                fp_type="summed_pdos",
             )
             fp_vasp = dos_vasp.get_dos_fp(
                 min_e=min_e,
                 max_e=max_e,
                 n_bins=n_bins,
                 normalize=True,
-                type="summed_pdos",
+                fp_type="summed_pdos",
             )
 
-            tanimoto_summed = round(dos_vasp.get_dos_fp_similarity(fp_lobster, fp_vasp, tanimoto=True), 4)
+            tanimoto_summed = round(dos_vasp.get_dos_fp_similarity(fp_lobster, fp_vasp, metric="tanimoto"), 4)
             quality_dict["dos_comparisons"]["tanimoto_summed"] = tanimoto_summed  # type: ignore
             quality_dict["dos_comparisons"]["e_range"] = [min_e, max_e]  # type: ignore
             quality_dict["dos_comparisons"]["n_bins"] = n_bins  # type: ignore

src/lobsterpy/featurize/core.py

@@ -1009,27 +1009,6 @@ def get_df(self, ids: str | None = None) -> pd.DataFrame:
         return df
 
 
-class DosFingerprint(NamedTuple):
-    """
-    Represents a Density of States (DOS) fingerprint.
-
-    This named tuple is used to store information related to the Density of States (DOS)
-    in a material. It includes the energies, densities, type, number of bins, and bin width.
-
-    :param energies: The energy values associated with the DOS.
-    :param densities: The corresponding density values for each energy.
-    :param type: The type of DOS fingerprint.
-    :param n_bins: The number of bins used in the fingerprint.
-    :param bin_width: The width of each bin in the DOS fingerprint.
-    """
-
-    energies: np.ndarray
-    densities: np.ndarray
-    type: str
-    n_bins: int
-    bin_width: float
-
-
 class FeaturizeDoscar:
     """
     Class to compute DOS moments and fingerprints from DOSCAR.lobster / DOSCAR.LSO.lobster.
@@ -1155,15 +1134,15 @@ def get_fingerprint_df(
             ids = Path(self.path_to_doscar).parent.name
             df = pd.DataFrame(index=[ids], columns=["DOS_FP"])
 
-        fp = self.dos.get_dos_fp(
-            type=fp_type,
+        dos_fp = self.dos.get_dos_fp(
+            fp_type=fp_type,
             normalize=normalize,
             n_bins=n_bins,
             binning=binning,
             max_e=self.e_range[-1] if self.e_range is not None else None,
             min_e=self.e_range[0] if self.e_range is not None else None,
-        )._asdict()
+        )
 
-        df.loc[ids, "DOS_FP"] = DosFingerprint(**fp)
+        df.loc[ids, "DOS_FP"] = dos_fp
 
         return df

tests/featurize/test_batch.py

@@ -8,8 +8,9 @@
     BatchStructureGraphs,
     BatchSummaryFeaturizer,
 )
-from lobsterpy.featurize.core import CoxxFingerprint, DosFingerprint
+from lobsterpy.featurize.core import CoxxFingerprint
 from pymatgen.analysis.graphs import StructureGraph
+from pymatgen.electronic_structure.dos import DosFingerprint
 
 CurrentDir = Path(__file__).absolute().parent
 TestDir = CurrentDir / "../"
@@ -576,7 +577,7 @@ def test_batch_dos_featurizer_non_lso(self):
 
         for dos_fp in df_fp["DOS_FP"]:
             assert isinstance(dos_fp, DosFingerprint)
-            assert dos_fp.type == "p"
+            assert dos_fp.fp_type == "p"
             assert dos_fp.n_bins == 100
 
     def test_batch_dos_featurizer_lso(self):
@@ -668,7 +669,7 @@ def test_batch_dos_featurizer_lso(self):
 
         for dos_fp in df_fp_lso["DOS_FP"]:
             assert isinstance(dos_fp, DosFingerprint)
-            assert dos_fp.type == "summed_pdos"
+            assert dos_fp.fp_type == "summed_pdos"
             assert dos_fp.n_bins == 256
 
 

tests/featurize/test_core.py

@@ -4,12 +4,12 @@
 import pandas as pd
 import pytest
 from lobsterpy.featurize.core import (
-    DosFingerprint,
     FeaturizeCharges,
     FeaturizeCOXX,
     FeaturizeDoscar,
     FeaturizeLobsterpy,
 )
+from pymatgen.electronic_structure.dos import DosFingerprint
 
 CurrentDir = Path(__file__).absolute().parent
 TestDir = CurrentDir / "../"