Read descriptors from openPMD

examples/advanced/ex09_convert_numpy_openpmd.py

@@ -0,0 +1,24 @@
+import mala
+
+parameters = mala.Parameters()
+data_converter = mala.DataConverter(parameters)
+
+for snapshot in range(2):
+    data_converter.add_snapshot(
+        descriptor_input_type="openpmd",
+        descriptor_input_path="Be_shuffled{}.in.bp4".format(snapshot),
+        target_input_type=None,  # "openpmd",
+        target_input_path=None,  # "Be_shuffled{}.out.bp4".format(snapshot),
+        additional_info_input_type=None,
+        additional_info_input_path=None,
+        target_units=None,
+    )
+
+# data_handler.descriptor_calculator.write_to_openpmd_file("descriptor_*.bp")
+data_converter.convert_snapshots(
+    descriptor_save_path="./",
+    target_save_path="./",
+    additional_info_save_path="./",
+    naming_scheme="Be_snapshot*.bp",
+    descriptor_calculation_kwargs={"working_directory": "./"},
+)

examples/basic/ex03_preprocess_data.py

@@ -8,7 +8,7 @@
 
 """
 Shows how this framework can be used to preprocess
-data. Preprocessing here means converting raw DFT calculation output into 
+data. Preprocessing here means converting raw DFT calculation output into
 numpy arrays of the correct size. For the input data, this means descriptor
 calculation.
 

mala/common/physical_data.py

@@ -555,6 +555,11 @@ def write_to_openpmd_iteration(
                 atoms_openpmd["position"][str(atom)].unit_SI = 1.0e-10
                 atoms_openpmd["positionOffset"][str(atom)].unit_SI = 1.0e-10
 
+        if any(i == 0 for i in self.grid_dimensions) and not isinstance(
+            array, self.SkipArrayWriting
+        ):
+            self.grid_dimensions = array.shape[0:-1]
+
         dataset = (
             array.dataset
             if isinstance(array, self.SkipArrayWriting)
@@ -564,8 +569,12 @@ def write_to_openpmd_iteration(
         # Global feature sizes:
         feature_global_from = 0
         feature_global_to = self.feature_size
-        if feature_global_to == 0 and isinstance(array, self.SkipArrayWriting):
-            feature_global_to = array.feature_size
+        if feature_global_to == 0:
+            feature_global_to = (
+                array.feature_size
+                if isinstance(array, self.SkipArrayWriting)
+                else array.shape[-1]
+            )
 
         # First loop: Only metadata, write metadata equivalently across ranks
         for current_feature in range(feature_global_from, feature_global_to):

mala/datahandling/data_converter.py

@@ -10,8 +10,8 @@
 from mala.targets.target import Target
 from mala.version import __version__ as mala_version
 
-descriptor_input_types = ["espresso-out"]
-target_input_types = [".cube", ".xsf"]
+descriptor_input_types = ["espresso-out", "openpmd"]
+target_input_types = [".cube", ".xsf", "openpmd"]
 additional_info_input_types = ["espresso-out"]
 
 
@@ -546,6 +546,16 @@ def __convert_single_snapshot(
                     snapshot["input"], **descriptor_calculation_kwargs
                 )
             )
+            print(tmp_input)
+            print(tmp_input.shape)
+            print(local_size)
+
+        elif description["input"] == "openpmd":
+            tmp_input = self.descriptor_calculator.read_from_openpmd_file(
+                snapshot["input"]
+            )
+            print(tmp_input)
+            print(tmp_input.shape)
 
         elif description["input"] is None:
             # In this case, only the output is processed.
@@ -617,6 +627,9 @@ def __convert_single_snapshot(
                         snapshot["output"], **target_calculator_kwargs
                     )
 
+                elif description["output"] == "openpmd":
+                    raise RuntimeError("unimplemented!")
+
                 elif description["output"] is None:
                     # In this case, only the input is processed.
                     pass