Merge pull request #50 from nfragapane/main

[WIP] New data generation jobs

.github/workflows/python-package.yml

@@ -27,6 +27,7 @@ jobs:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
+        python -m pip cache purge
         python -m pip install --upgrade pip
         python -m pip install flake8 pytest pytest-mock pytest-split pytest-cov
         python -m pip install types-setuptools

autoplex/auto/phonons/flows.py

@@ -53,11 +53,11 @@ class CompleteDFTvsMLBenchmarkWorkflow(Maker):
         If True, will add randomly distorted structures for DFT calculation.
     add_rss_struct: bool.
         If True, will add RSS generated structures for DFT calculation.
-        n_struct: int.
+        n_structures: int.
         The total number of randomly displaced structures to be generated.
     phonon_displacement_maker: BaseVaspMaker
         Maker used to compute the forces for a supercell.
-    n_struct: int.
+    n_structures: int.
         The total number of randomly displaced structures to be generated.
     displacements: list[float]
         displacement distance for phonons
@@ -71,13 +71,15 @@ class CompleteDFTvsMLBenchmarkWorkflow(Maker):
     uc: bool.
         If True, will generate randomly distorted structures (unitcells)
         and add static computation jobs to the flow.
-    cell_factor_sequence: list[float]
+    volume_scale_factors: list[float]
         list of factors to resize cell parameters. Default is [0.975, 1.0, 1.025, 1.05].
-    std_dev: float
-        Standard deviation std_dev for normal distribution to draw numbers from
+    rattle_std: float
+        Standard deviation for normal distribution to draw numbers from
         to generate the rattled structures.
     supercell_matrix: Matrix3D or None
         The matrix to construct the supercell.
+    distort_type : int.
+        0- volume distortion, 1- angle distortion, 2- volume and angle distortion. Default=0.
     ml_models: list[str]
         list of the ML models to be used. Default is GAP.
     """
@@ -90,14 +92,15 @@ class CompleteDFTvsMLBenchmarkWorkflow(Maker):
     phonon_displacement_maker: BaseVaspMaker = field(
         default_factory=TightDFTStaticMaker
     )
-    n_struct: int = 1
+    n_structures: int = 1
     displacements: list[float] = field(default_factory=lambda: [0.01])
     min_length: int = 20
     symprec: float = 1e-4
     uc: bool = False
-    cell_factor_sequence: list[float] | None = None
-    std_dev: float = 0.01
+    volume_scale_factors: list[float] | None = None
+    rattle_std: float = 0.01
     supercell_matrix: Matrix3D | None = None
+    distort_type: int = 0
     ml_models: list[str] = field(default_factory=lambda: ["GAP"])
 
     def make(
@@ -108,7 +111,7 @@ def make(
         f_max: float = 40.0,
         pre_xyz_files: list[str] | None = None,
         pre_database_dir: str | None = None,
-        regularization: float = 0.1,
+        atom_wise_regularization_parameter: float = 0.1,
         f_min: float = 0.01,  # unit: eV Å-1
         atom_wise_regularization: bool = True,
         auto_delta: bool = True,
@@ -135,7 +138,7 @@ def make(
             names of the pre-database train xyz file and test xyz file.
         pre_database_dir:
             the pre-database directory.
-        regularization: float
+        atom_wise_regularization_parameter: float
             regularization value for the atom-wise force components.
         f_min: float
             minimal force cutoff value for atom-wise regularization.
@@ -161,11 +164,12 @@ def make(
                     structure,
                     mp_id,
                     self.phonon_displacement_maker,
-                    self.n_struct,
+                    self.n_structures,
                     self.uc,
-                    self.cell_factor_sequence,
-                    self.std_dev,
+                    self.volume_scale_factors,
+                    self.rattle_std,
                     self.supercell_matrix,
+                    self.distort_type,
                 )
                 flows.append(addDFTrand)
                 fit_input.update({mp_id: addDFTrand.output})
@@ -201,7 +205,7 @@ def make(
                 f_max=f_max,
                 pre_xyz_files=pre_xyz_files,
                 pre_database_dir=pre_database_dir,
-                regularization=regularization,
+                atomwise_regularization_param=atom_wise_regularization_parameter,
                 f_min=f_min,
                 atom_wise_regularization=atom_wise_regularization,
                 auto_delta=auto_delta,
@@ -313,11 +317,12 @@ def add_dft_random(
         structure: Structure,
         mp_id: str,
         phonon_displacement_maker: BaseVaspMaker,
-        n_struct: int = 1,
+        n_structures: int = 1,
         uc: bool = False,
-        cell_factor_sequence: list[float] | None = None,
-        std_dev: float = 0.01,
+        volume_custom_scale_factors: list[float] | None = None,
+        rattle_std: float = 0.01,
         supercell_matrix: Matrix3D | None = None,
+        distort_type: int = 0,
     ):
         """Add DFT phonon runs for randomly displaced structures.
 
@@ -329,28 +334,31 @@ def add_dft_random(
             materials project id
         phonon_displacement_maker: BaseVaspMaker
             Maker used to compute the forces for a supercell.
-        n_struct: int.
+        n_structures: int.
             The total number of randomly displaced structures to be generated.
         uc: bool.
             If True, will generate randomly distorted structures (unitcells)
             and add static computation jobs to the flow.
-        cell_factor_sequence: list[float]
+        volume_custom_scale_factors: list[float]
             list of factors to resize cell parameters.
-        std_dev: float
-            Standard deviation std_dev for normal distribution to draw numbers from
+        rattle_std: float
+            Standard deviation for normal distribution to draw numbers from
             to generate the rattled structures.
         supercell_matrix: Matrix3D or None
             The matrix to construct the supercell.
+        distort_type : int.
+            0- volume distortion, 1- angle distortion, 2- volume and angle distortion. Default=0.
         """
         additonal_dft_random = dft_random_gen_data(
             structure,
             mp_id,
             phonon_displacement_maker,
-            n_struct,
+            n_structures,
             uc,
-            cell_factor_sequence,
-            std_dev,
+            volume_custom_scale_factors,
+            rattle_std,
             supercell_matrix,
+            distort_type,
         )
         return Flow(
             additonal_dft_random,

autoplex/auto/phonons/jobs.py

@@ -237,11 +237,12 @@ def dft_random_gen_data(
     structure: Structure,
     mp_id,
     phonon_displacement_maker,
-    n_struct: int = 1,
+    n_structures: int = 1,
     uc: bool = False,
-    cell_factor_sequence: list[float] | None = None,
-    std_dev: float = 0.01,
+    volume_custom_scale_factors: list[float] | None = None,
+    rattle_std: float = 0.01,
     supercell_matrix: Matrix3D | None = None,
+    distort_type: int = 0,
 ):
     """
     Job to generate random structured DFT reference database to be used for fitting ML potentials.
@@ -254,31 +255,35 @@ def dft_random_gen_data(
         Maker used to compute the forces for a supercell.
     mp_id:
         materials project id
-    n_struct: int.
+    n_structures: int.
         The total number of randomly displaced structures to be generated.
     uc: bool.
         If True, will generate randomly distorted structures (unitcells)
         and add static computation jobs to the flow.
-    cell_factor_sequence: list[float]
+    volume_custom_scale_factors: list[float]
         list of factors to resize cell parameters.
-    std_dev: float
-        Standard deviation std_dev for normal distribution to draw numbers from to generate the rattled structures.
+    rattle_std: float.
+        Rattle amplitude (standard deviation in normal distribution).
+        Default=0.01.
     supercell_matrix: Matrix3D or None
         The matrix to construct the supercell.
+    distort_type : int.
+        0- volume distortion, 1- angle distortion, 2- volume and angle distortion. Default=0.
     """
     jobs = []
 
     random_datagen = RandomStructuresDataGenerator(
         name="RandomDataGen",
         phonon_displacement_maker=phonon_displacement_maker,
-        n_struct=n_struct,
+        n_structures=n_structures,
         uc=uc,
-        std_dev=std_dev,
+        rattle_std=rattle_std,
+        distort_type=distort_type,
     ).make(
         structure=structure,
         mp_id=mp_id,
         supercell_matrix=supercell_matrix,
-        cell_factor_sequence=cell_factor_sequence,
+        volume_custom_scale_factors=volume_custom_scale_factors,
     )
     jobs.append(random_datagen)
 

autoplex/data/common/flows.py

@@ -18,10 +18,10 @@
 
 from autoplex.data.common.jobs import (
     convert_to_extxyz,
+    generate_randomized_structures,
     get_supercell_job,
     plot_force_distribution,
 )
-from autoplex.data.phonons.jobs import generate_randomized_structures
 
 __all__ = ["GenerateTrainingDataForTesting"]
 
@@ -56,8 +56,8 @@ def make(
         train_structure_list: list[Structure],
         cell_factor_sequence: list[float] | None = None,
         potential_filename: str = "gap.xml",
-        n_struct: int = 50,
-        std_dev: float = 0.01,
+        n_structures: int = 50,
+        rattle_std: float = 0.01,
         relax_cell: bool = True,
         steps: int = 1000,
         supercell_matrix: Matrix3D | None = None,
@@ -78,10 +78,11 @@ def make(
             list of factor to resize cell parameters.
         potential_filename: str
             param_file_name for :obj:`quippy.potential.Potential()'`.
-        n_struct : int.
+        n_structures : int.
             Total number of randomly displaced structures to be generated.
-        std_dev: float
-            Standard deviation std_dev for normal distribution to draw numbers from to generate the rattled structures.
+        rattle_std: float.
+            Rattle amplitude (standard deviation in normal distribution).
+            Default=0.01.
         relax_cell : bool
             Whether to allow the cell shape/volume to change during relaxation.
         steps : int
@@ -126,10 +127,10 @@ def make(
 
             for cell_factor in cell_factor_sequence:
                 rand_struc_job = generate_randomized_structures(
-                    supercell.output,
-                    n_struct=n_struct,
-                    cell_factor_sequence=[cell_factor],
-                    std_dev=std_dev,
+                    structure=supercell.output,
+                    n_structures=n_structures,
+                    volume_custom_scale_factors=[cell_factor],
+                    rattle_std=rattle_std,
                 )
                 jobs.append(rand_struc_job)
                 static_conv_jobs = self.static_run_and_convert(