Merge pull request mala-project#637 from mala-project/redesign_lammps_compute_file

Make caching the descriptor calculation input files optional

Author: RandomDefaultUser

mala/common/parameters.py

@@ -446,10 +446,11 @@ class ParametersDescriptors(ParametersBase):
         mainly exists for debugging purposes. If the atomic density is instead
         used for model training itself, this parameter needs to be set.
 
-    lammps_compute_file : str
-        Path to a LAMMPS compute file for the bispectrum descriptor
-        calculation. MALA has its own collection of compute files which are
-        used by default. Setting this parameter is thus not necessarys for
+    custom_lammps_compute_file : str
+        Path to a LAMMPS compute file for the descriptor calculation.
+        MALA has its own collection of compute files which are
+        used by default, i.e., when this string is empty.
+        Setting this parameter is thus not necessarys for
         model training and inference, and it exists mainly for debugging
         purposes.
 
@@ -476,7 +477,7 @@ def __init__(self):
 
         # These affect all descriptors, at least as long all descriptors
         # use LAMMPS (which they currently do).
-        self.lammps_compute_file = ""
+        self.custom_lammps_compute_file = ""
         self.descriptors_contain_xyz = True
 
         # TODO: I would rather handle the parallelization info automatically
@@ -590,7 +591,7 @@ def _update_mpi(self, new_mpi):
 
         # There may have been a serial or parallel run before that is now
         # no longer valid.
-        self.lammps_compute_file = ""
+        self.custom_lammps_compute_file = ""
 
 
 class ParametersTargets(ParametersBase):

mala/descriptors/atomic_density.py

@@ -211,23 +211,26 @@ def __calculate_lammps(self, outdir, **kwargs):
 
         # For now the file is chosen automatically, because this is used
         # mostly under the hood anyway.
-        filepath = __file__.split("atomic_density")[0]
-        if self.parameters._configuration["mpi"]:
-            if self.parameters.use_z_splitting:
-                self.parameters.lammps_compute_file = os.path.join(
-                    filepath, "in.ggrid.python"
-                )
+        if self.parameters.custom_lammps_compute_file != "":
+            lammps_compute_file = self.parameters.custom_lammps_compute_file
+        else:
+            filepath = os.path.dirname(__file__)
+            if self.parameters._configuration["mpi"]:
+                if self.parameters.use_z_splitting:
+                    lammps_compute_file = os.path.join(
+                        filepath, "in.ggrid.python"
+                    )
+                else:
+                    lammps_compute_file = os.path.join(
+                        filepath, "in.ggrid_defaultproc.python"
+                    )
             else:
-                self.parameters.lammps_compute_file = os.path.join(
+                lammps_compute_file = os.path.join(
                     filepath, "in.ggrid_defaultproc.python"
                 )
-        else:
-            self.parameters.lammps_compute_file = os.path.join(
-                filepath, "in.ggrid_defaultproc.python"
-            )
 
         # Do the LAMMPS calculation and clean up.
-        lmp.file(self.parameters.lammps_compute_file)
+        lmp.file(lammps_compute_file)
 
         # Extract the data.
         nrows_ggrid = extract_compute_np(

mala/descriptors/bispectrum.py

@@ -229,24 +229,26 @@ def __calculate_lammps(self, outdir, **kwargs):
 
         # An empty string means that the user wants to use the standard input.
         # What that is differs depending on serial/parallel execution.
-        if self.parameters.lammps_compute_file == "":
-            filepath = __file__.split("bispectrum")[0]
+        # We also have to ensure that no input files from a different
+        # descriptor calculator gets used.
+        if self.parameters.custom_lammps_compute_file != "":
+            lammps_compute_file = self.parameters.custom_lammps_compute_file
+        else:
+            filepath = os.path.dirname(__file__)
             if self.parameters._configuration["mpi"]:
                 if self.parameters.use_z_splitting:
-                    self.parameters.lammps_compute_file = os.path.join(
+                    lammps_compute_file = os.path.join(
                         filepath, "in.bgridlocal.python"
                     )
                 else:
-                    self.parameters.lammps_compute_file = os.path.join(
+                    lammps_compute_file = os.path.join(
                         filepath, "in.bgridlocal_defaultproc.python"
                     )
             else:
-                self.parameters.lammps_compute_file = os.path.join(
-                    filepath, "in.bgrid.python"
-                )
+                lammps_compute_file = os.path.join(filepath, "in.bgrid.python")
 
         # Do the LAMMPS calculation and clean up.
-        lmp.file(self.parameters.lammps_compute_file)
+        lmp.file(lammps_compute_file)
         self.feature_size = self.__get_feature_size()
 
         # Extract data from LAMMPS calculation.

mala/descriptors/minterpy_descriptors.py

@@ -186,23 +186,28 @@ def _calculate(self, atoms, outdir, grid_dimensions, **kwargs):
 
             # For now the file is chosen automatically, because this is used
             # mostly under the hood anyway.
-            filepath = __file__.split("minterpy")[0]
-            if self.parameters._configuration["mpi"]:
-                raise Exception(
-                    "Minterpy descriptors cannot be calculated "
-                    "in parallel yet."
+            if self.parameters.custom_lammps_compute_file != "":
+                lammps_compute_file = (
+                    self.parameters.custom_lammps_compute_file
                 )
-                # if self.parameters.use_z_splitting:
-                #     runfile = os.path.join(filepath, "in.ggrid.python")
-                # else:
-                #     runfile = os.path.join(filepath, "in.ggrid_defaultproc.python")
             else:
-                self.parameters.lammps_compute_file = os.path.join(
-                    filepath, "in.ggrid_defaultproc.python"
-                )
+                filepath = os.path.dirname(__file__)
+                if self.parameters._configuration["mpi"]:
+                    raise Exception(
+                        "Minterpy descriptors cannot be calculated "
+                        "in parallel yet."
+                    )
+                    # if self.parameters.use_z_splitting:
+                    #     runfile = os.path.join(filepath, "in.ggrid.python")
+                    # else:
+                    #     runfile = os.path.join(filepath, "in.ggrid_defaultproc.python")
+                else:
+                    lammps_compute_file = os.path.join(
+                        filepath, "in.ggrid_defaultproc.python"
+                    )
 
             # Do the LAMMPS calculation and clean up.
-            lmp.file(self.parameters.lammps_compute_file)
+            lmp.file(lammps_compute_file)
 
             # Extract the data.
             nrows_ggrid = extract_compute_np(