feat: Enable primitive cell for all Hashers

src/material_hasher/benchmark/run_disordered.py

@@ -13,8 +13,6 @@
 import yaml
 from pymatgen.core import Structure
 
-logger = logging.getLogger(__name__)
-
 from material_hasher.benchmark.disordered import (
     download_disordered_structures,
     get_classification_results_dissimilar,
@@ -25,6 +23,8 @@
 from material_hasher.similarity import SIMILARITY_MATCHERS
 from material_hasher.types import StructureEquivalenceChecker
 
+logger = logging.getLogger(__name__)
+
 STRUCTURE_CHECKERS = {**HASHERS, **SIMILARITY_MATCHERS}
 
 

src/material_hasher/benchmark/run_transformations.py

@@ -232,7 +232,11 @@ def hasher_sensitivity(
     else:
         raise ValueError("Unknown structure checker")
 
-    return matching_hashes / len(transformed_structures) if len(transformed_structures) > 0 else 0
+    return (
+        matching_hashes / len(transformed_structures)
+        if len(transformed_structures) > 0
+        else 0
+    )
 
 
 def mean_sensitivity(

src/material_hasher/benchmark/transformations.py

@@ -1,10 +1,9 @@
 # Copyright 2025 Entalpic
 import inspect
-import random
-from typing import Optional, Union
+from typing import Optional
 
 import numpy as np
-from pymatgen.core import Structure, SymmOp
+from pymatgen.core import Structure
 from pymatgen.symmetry.analyzer import SpacegroupAnalyzer
 
 ALL_TEST_CASES = [
@@ -16,10 +15,10 @@
 ]
 
 PARAMETERS = {
-    "gaussian_noise": {"sigma": np.logspace(0.0001, 0.5,15, base=0.0000001)},
-    "isometric_strain": {"pct": [1,1.05,1.1,1.2,1.5]},
-    "strain": {"sigma": np.logspace(0.001, 0.5,10, base=0.0000001)},
-    "translation": {"sigma": np.logspace(0.0001, 0.5,15, base=0.0000001)},
+    "gaussian_noise": {"sigma": np.logspace(0.0001, 0.5, 15, base=0.0000001)},
+    "isometric_strain": {"pct": [1, 1.05, 1.1, 1.2, 1.5]},
+    "strain": {"sigma": np.logspace(0.001, 0.5, 10, base=0.0000001)},
+    "translation": {"sigma": np.logspace(0.0001, 0.5, 15, base=0.0000001)},
     "symm_ops": {"structure_symmetries": ["all_symmetries_found"]},
 }
 

src/material_hasher/hasher/base.py

@@ -6,18 +6,51 @@
 from pymatgen.core import Structure
 
 from material_hasher.types import StructureEquivalenceChecker
+from material_hasher.utils import reduce_structure
 
 
 class HasherBase(ABC, StructureEquivalenceChecker):
-    """Abstract class for matching of the hashes between structures."""
+    """Abstract class for matching of the hashes between structures.
+
+    Parameters
+    ----------
+    primitive_reduction : bool, optional
+        Whether to reduce the structures to their primitive cells.
+        Defaults to False.
+    """
+
+    def __init__(self, primitive_reduction: bool = False):
+        self.primitive_reduction = primitive_reduction
 
-    @abstractmethod
     def get_material_hash(
         self,
         structure: Structure,
     ) -> str:
         """Returns a hash of the structure.
 
+        Parameters
+        ----------
+        structure : Structure
+            Structure to hash.
+
+        Returns
+        -------
+        str
+            Hash of the structure.
+        """
+        if self.primitive_reduction:
+            structure = reduce_structure(structure)
+        return self._get_material_hash(structure)
+
+    @abstractmethod
+    def _get_material_hash(
+        self,
+        structure: Structure,
+    ) -> str:
+        """Get the material hash of the structure.
+
+        Should be implemented by the subclass.
+
         Parameters
         ----------
         structure : Structure

src/material_hasher/hasher/bawl.py

@@ -55,12 +55,12 @@ def __init__(
         primitive_reduction: bool = False,
         shorten_hash: bool = False,
     ):
+        super().__init__(primitive_reduction=primitive_reduction)
         self.graphing_algorithm = graphing_algorithm
         self.bonding_algorithm = bonding_algorithm
         self.bonding_kwargs = bonding_kwargs
         self.include_composition = include_composition
         self.symmetry_labeling = symmetry_labeling
-        self.primitive_reduction = primitive_reduction
         self.shorten_hash = shorten_hash
 
     def get_bawl_materials_data(
@@ -92,7 +92,6 @@ def get_bawl_materials_data(
                 structure,
                 bonding_kwargs=self.bonding_kwargs,
                 bonding_algorithm=self.bonding_algorithm,
-                primitive_reduction=self.primitive_reduction,
             )
             data["bonding_graph_hash"] = get_weisfeiler_lehman_hash(graph)
         else:
@@ -121,7 +120,7 @@ def get_bawl_materials_data(
             data["composition"] = structure.composition.reduced_formula.replace(" ", "")
         return data
 
-    def get_material_hash(self, structure: Structure) -> str:
+    def _get_material_hash(self, structure: Structure) -> str:
         """Returns a hash of the structure.
 
         Parameters

src/material_hasher/hasher/example.py

@@ -10,10 +10,10 @@ class SimpleCompositionHasher(HasherBase):
     This is just a demo.
     """
 
-    def __init__(self) -> None:
-        pass
+    def __init__(self, primitive_reduction: bool = False) -> None:
+        super().__init__(primitive_reduction=primitive_reduction)
 
-    def get_material_hash(self, structure: Structure) -> str:
+    def _get_material_hash(self, structure: Structure) -> str:
         """Returns a hash of the structure.
 
         Parameters

src/material_hasher/hasher/pdd.py

@@ -9,13 +9,14 @@
 
 
 class PointwiseDistanceDistributionHasher(HasherBase):
-    def __init__(self, cutoff: float = 100.0):
+    def __init__(self, cutoff: float = 100.0, primitive_reduction: bool = False):
         """
         Initialize the PDD Generator.
 
         Parameters:
         cutoff (float): Cutoff distance for PDD calculation. Default is 100.
         """
+        super().__init__(primitive_reduction=primitive_reduction)
         self.cutoff = int(cutoff)  # Ensure cutoff is an integer
 
     def periodicset_from_structure(self, structure: Structure) -> PeriodicSet:
@@ -60,7 +61,7 @@ def periodicset_from_structure(self, structure: Structure) -> PeriodicSet:
             types=atomic_numbers,
         )
 
-    def get_material_hash(self, structure: Structure) -> str:
+    def _get_material_hash(self, structure: Structure) -> str:
         """
         Generate a hashed string for a single pymatgen structure based on its
         Point-wise Distance Distribution (PDD).
@@ -77,9 +78,7 @@ def get_material_hash(self, structure: Structure) -> str:
         """
         periodic_set = self.periodicset_from_structure(structure)
 
-        pdd = PDD(
-            periodic_set, int(self.cutoff), collapse=False
-        )
+        pdd = PDD(periodic_set, int(self.cutoff), collapse=False)
 
         # Round the PDD values to 4 decimal places for numerical stability and consistency.
         pdd = np.round(pdd, decimals=4)

src/material_hasher/hasher/slices.py

@@ -11,13 +11,14 @@
 
 
 class SLICESHasher(HasherBase):
-    def __init__(self):
+    def __init__(self, primitive_reduction: bool = False):
         """
         Initializes the SLICESHasher with the SLICES backend.
         """
+        super().__init__(primitive_reduction=primitive_reduction)
         self.backend = SLICES()
 
-    def get_material_hash(self, structure: Structure) -> str:
+    def _get_material_hash(self, structure: Structure) -> str:
         """
         Converts a pymatgen Structure to a SLICES string.
 
@@ -32,4 +33,3 @@ def get_material_hash(self, structure: Structure) -> str:
             The SLICES string representation of the structure.
         """
         return self.backend.structure2SLICES(structure)
-

src/material_hasher/hasher/utils/graph_structure.py

@@ -3,16 +3,12 @@
 from pymatgen.analysis.local_env import EconNN, NearNeighbors
 from pymatgen.core import Structure
 from networkx import Graph
-from moyopy import MoyoDataset
-from moyopy.interface import MoyoAdapter
-import warnings
 
 
 def get_structure_graph(
     structure: Structure,
     bonding_kwargs: dict = {},
     bonding_algorithm: NearNeighbors = EconNN,
-    primitive_reduction: bool = False,
 ) -> Graph:
     """Method to build networkx graph object based on
     bonding algorithm from Pymatgen Structure
@@ -27,18 +23,11 @@ class to build bonded structure. Defaults to EconNN.
     Returns:
         Graph: networkx Graph object
     """
-    assess_structure = (
-        MoyoAdapter.get_structure(
-            MoyoDataset(MoyoAdapter.from_structure(structure)).prim_std_cell
-        )
-        if primitive_reduction
-        else structure.copy()
-    )
     structure_graph = StructureGraph.with_local_env_strategy(
-        structure=assess_structure,
+        structure=structure,
         strategy=bonding_algorithm(**bonding_kwargs),
     )
-    for n, site in zip(range(len(assess_structure)), assess_structure):
+    for n, site in zip(range(len(structure)), structure):
         structure_graph.graph.nodes[n]["specie"] = site.specie.name
     for edge in structure_graph.graph.edges:
         structure_graph.graph.edges[edge]["voltage"] = structure_graph.graph.edges[

src/material_hasher/hasher/utils/symmetry.py

@@ -10,6 +10,7 @@
 
 logger = logging.getLogger(__name__)
 
+
 class MoyoSymmetry:
     """
     This is a wrapper around the functions of the Moyo library.
@@ -29,7 +30,10 @@ class MoyoSymmetry:
     """
 
     def __init__(
-        self, symprec: float | None = None, angle_tolerance: float | None = None, setting: str | None = None
+        self,
+        symprec: float | None = None,
+        angle_tolerance: float | None = None,
+        setting: str | None = None,
     ):
         self.symprec = symprec
         self.angle_tolerance = angle_tolerance
@@ -127,7 +131,9 @@ def __init__(self, aflow_executable: str = None):
                 f"the binary to be specified via {self.aflow_executable=}.\n"
             )
 
-    def get_symmetry_label(self, structure: Structure, tolerance: float = 0.1) -> str | None:
+    def get_symmetry_label(
+        self, structure: Structure, tolerance: float = 0.1
+    ) -> str | None:
         """
         Returns AFLOW label for a given structure
         Args:

src/material_hasher/similarity/base.py

@@ -6,12 +6,22 @@
 from pymatgen.core import Structure
 
 from material_hasher.types import StructureEquivalenceChecker
+from material_hasher.utils import reduce_structure
 
 
 class SimilarityMatcherBase(ABC, StructureEquivalenceChecker):
-    """Abstract class for similarity matching between structures."""
+    """Abstract class for similarity matching between structures.
+
+    Parameters
+    ----------
+    primitive_reduction : bool, optional
+        Whether to reduce the structures to their primitive cells.
+        Defaults to False.
+    """
+
+    def __init__(self, primitive_reduction: bool = False):
+        self.primitive_reduction = primitive_reduction
 
-    @abstractmethod
     def get_similarity_score(
         self, structure1: Structure, structure2: Structure
     ) -> float:
@@ -28,9 +38,32 @@ def get_similarity_score(
         float
             Similarity score between the two structures.
         """
-        pass
+        if self.primitive_reduction:
+            structure1 = reduce_structure(structure1)
+            structure2 = reduce_structure(structure2)
+        return self._get_similarity_score(structure1, structure2)
 
     @abstractmethod
+    def _get_similarity_score(
+        self, structure1: Structure, structure2: Structure
+    ) -> float:
+        """Returns a similarity score between two structures.
+
+        Should be implemented by the subclass.
+
+        Parameters
+        ----------
+        structure1 : Structure
+            First structure to compare.
+        structure2 : Structure
+
+        Returns
+        -------
+        float
+            Similarity score between the two structures.
+        """
+        pass
+
     def is_equivalent(
         self,
         structure1: Structure,
@@ -42,6 +75,40 @@ def is_equivalent(
         Uses a threshold to determine equivalence if provided and the algorithm
         does not have a built-in threshold.
 
+        Parameters
+        ----------
+        structure1 : Structure
+            First structure to compare.
+        structure2 : Structure
+            Second structure to compare.
+        threshold : float, optional
+            Threshold to determine similarity, by default None and the
+            algorithm's default threshold is used if it exists.
+
+        Returns
+        -------
+        bool
+            True if the two structures are similar, False otherwise.
+        """
+        if self.primitive_reduction:
+            structure1 = reduce_structure(structure1)
+            structure2 = reduce_structure(structure2)
+        return self._is_equivalent(structure1, structure2, threshold)
+
+    @abstractmethod
+    def _is_equivalent(
+        self,
+        structure1: Structure,
+        structure2: Structure,
+        threshold: Optional[float] = None,
+    ) -> bool:
+        """Returns True if the two structures are equivalent according to the
+        implemented algorithm.
+        Uses a threshold to determine equivalence if provided and the algorithm
+        does not have a built-in threshold.
+
+        Should be implemented by the subclass.
+
         Parameters
         ----------
         structure1 : Structure