Merge pull request #105 from pyscal/pack_calculations

Pack calculations

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.6.9
+current_version = 0.6.10
 commit = True
 tag = False
 

CITATION.cff

@@ -20,4 +20,4 @@ url: 'https://atomrdf.pyscal.org'
 license: "MIT"
 repository-code: https://github.com/pyscal/atomRDF
 type: software
-version: 0.6.9
+version: 0.6.10

atomrdf/graph.py

@@ -48,7 +48,7 @@
 from atomrdf.workflow.workflow import Workflow
 from atomrdf.sample import Sample
 
-from atomrdf.namespace import Namespace, CMSO, PLDO, PODO, ASMO
+from atomrdf.namespace import Namespace, CMSO, PLDO, PODO, ASMO, PROV
 
 # read element data file
 file_location = os.path.dirname(__file__).split("/")
@@ -804,7 +804,7 @@ def write(self, filename, format="json-ld"):
         with open(filename, "w") as fout:
             fout.write(self.graph.serialize(format=format))
 
-    def archive(self, package_name, format="turtle", compress=True):
+    def archive(self, package_name, format="turtle", compress=True, add_simulations=False):
         """
         Publish a dataset from graph including per atom quantities.
 
@@ -852,7 +852,7 @@ def archive(self, package_name, format="turtle", compress=True):
         os.mkdir(structure_store)
 
         # now go through each sample, and copy the file, at the same time fix the paths
-        for sample in self.samples:
+        for sample in self.sample_ids:
             filepath = self.value(URIRef(f"{sample}_Position"), CMSO.hasPath).toPython()
             shutil.copy(filepath, structure_store)
 
@@ -869,6 +869,20 @@ def archive(self, package_name, format="turtle", compress=True):
                         Literal(new_relpath, datatype=XSD.string),
                     )
                 )
+        #copy simulation files if needed
+        if add_simulations:
+            sim_store = f"{package_name}/simulation_store"
+            os.mkdir(sim_store)
+            activities = self.activity_ids
+            for activity in activities:
+                path = self.value(activity, CMSO.hasPath)
+                if path is not None:
+                    newpath = "/".join([sim_store, activity.toPython()])
+                    shutil.copytree(path, newpath)
+
+                    #remove old path
+                    self.remove((activity, CMSO.hasPath, None))
+                    self.add((activity, CMSO.hasPath, Literal(newpath, datatype=XSD.string)))
 
         triple_file = os.path.join(package_name, "triples")
         self.write(triple_file, format=format)
@@ -1086,6 +1100,14 @@ def samples(self):
             sample_objects.append(Sample(name, ids, self))
         return sample_objects
 
+    @property
+    def activity_ids(self):
+        """
+        Returns a list of all Samples in the graph
+        """
+
+        return [x[0] for x in self.triples((None, RDF.type, PROV.Activity))]
+
     def iterate_graph(self, item, create_new_graph=False):
         """
         Iterate through the graph starting from the given item.

atomrdf/visualize.py

@@ -43,6 +43,11 @@ def get_string_from_URI(x):
         if len(rawsplit) > 1:
             return "_".join(rawsplit), "BNode"
 
+    if "activity:" in raw:
+        rawsplit = raw.split(":")
+        if len(rawsplit) > 1:
+            return "_".join(rawsplit), "BNode"
+
     # just a normal url split now
     rawsplit = raw.split("/")
     if len(rawsplit) > 1:

atomrdf/workflow/pyiron.py

@@ -165,6 +165,7 @@ def process_murnaghan_job(job):
     murnaghan_dict['structure'] = get_structures(job)['structure']
     murnaghan_dict['sample'] = get_structures(job)['sample']
     murnaghan_dict['intermediate'] = False
+    murnaghan_dict['path'] = get_simulation_folder(job)
 
     #add the murnaghan method
     murnaghan_dict['method'] = "EquationOfState"
@@ -207,8 +208,12 @@ def process_lammps_job(job):
     method_dict['sample'] = structure_dict['sample']
     method_dict['outputs'] = output_dict
     method_dict['intermediate'] = False
+    method_dict['path'] = get_simulation_folder(job)
     return method_dict
 
+def get_simulation_folder(job):
+    return os.path.join(job.project.path, f'{job.name}_hdf5')
+
 def get_structures(job):
     initial_pyiron_structure = job.structure
     final_pyiron_structure = job.get_structure(frame=-1)
@@ -288,7 +293,7 @@ def lammps_identify_method(job):
     mdict["pressure"] = press
     mdict["dof"] = dof
     mdict["ensemble"] = ensemble
-    mdict["id"] = job.id
+    #mdict["id"] = job.id
 
     # now process potential
     inpdict = job.input.to_dict()

atomrdf/workflow/workflow.py

@@ -23,6 +23,7 @@
 import ast
 import uuid
 import importlib
+import uuid
 
 from atomrdf.structure import System
 
@@ -267,13 +268,15 @@ def _add_method(
 
         # add activity
         # ----------------------------------------------------------
-        main_id = job_dict['id']
-        activity = URIRef(f"activity_{main_id}")
+        main_id = uuid.uuid4()
+        main_id = f'activity:{main_id}'
+        job_dict['id'] = main_id
+        activity = URIRef(main_id)
         self.kg.add((activity, RDF.type, PROV.Activity))
 
         # add method
         # ----------------------------------------------------------
-        method = URIRef(f"method_{main_id}")
+        method = URIRef(f"{main_id}_method")
         if job_dict["method"] == "MolecularStatics":
             #TODO: Replace with ASMO.MolecularStatics
             self.kg.add((method, RDF.type, ASMO.MolecularDynamics))
@@ -300,6 +303,7 @@ def _add_method(
         # add that structure was generated
         #TODO: Move hasComputationalMethod here after EquationOfState is added
         self.kg.add((job_dict['sample']['final'], PROV.wasGeneratedBy, activity))
+        self.kg.add((activity, CMSO.hasPath, Literal(job_dict['path'], datatype=XSD.string)))
         self._add_inputs(job_dict, activity)
         self._add_outputs(job_dict, activity)
         self._add_software(job_dict, method)
@@ -393,7 +397,7 @@ def _add_md(self, job_dict, method, activity):
         # add temperature if needed
         if job_dict["temperature"] is not None:
             temperature = self.kg.create_node(
-                f"temperature_{main_id}", ASMO.InputParameter
+                f"{main_id}_temperature", ASMO.InputParameter
             )
             self.kg.add(
                 (temperature, RDFS.label, Literal("temperature", datatype=XSD.string))
@@ -412,7 +416,7 @@ def _add_md(self, job_dict, method, activity):
 
         if job_dict["pressure"] is not None:
             pressure = self.kg.create_node(
-                f"pressure_{main_id}", ASMO.InputParameter
+                f"{main_id}_pressure", ASMO.InputParameter
             )
             self.kg.add(
                 (pressure, RDFS.label, Literal("pressure", datatype=XSD.string))
@@ -430,7 +434,7 @@ def _add_md(self, job_dict, method, activity):
             )
 
         # potentials need to be mapped
-        potential = URIRef(f"potential_{main_id}")
+        potential = URIRef(f"{main_id}_potential")
         if "meam" in job_dict["potential"]["type"]:
             self.kg.add((potential, RDF.type, ASMO.ModifiedEmbeddedAtomModel))
         elif "eam" in job_dict["potential"]["type"]:

examples/workflow_examples/01_lammps_pyiron.ipynb

@@ -37,7 +37,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ff41537d7d5a411dad2041ebe785887e",
+       "model_id": "21fb303d02c64375a340d2958fb85147",
        "version_major": 2,
        "version_minor": 0
       },
@@ -60,7 +60,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "project = 'wf1a'\n",
+    "project = 'wf1c'\n",
     "pr = Project(project)"
    ]
   },
@@ -111,21 +111,21 @@
        "<!-- Generated by graphviz version 9.0.0 (20231125.0833)\n",
        " -->\n",
        "<!-- Pages: 1 -->\n",
-       "<svg width=\"232pt\" height=\"44pt\"\n",
-       " viewBox=\"0.00 0.00 231.75 44.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
+       "<svg width=\"230pt\" height=\"44pt\"\n",
+       " viewBox=\"0.00 0.00 230.25 44.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
        "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 40)\">\n",
-       "<polygon fill=\"white\" stroke=\"none\" points=\"-4,4 -4,-40 227.75,-40 227.75,4 -4,4\"/>\n",
-       "<!-- sample_4ff68114&#45;deac&#45;439a&#45;8540&#45;554d4a919e63 -->\n",
+       "<polygon fill=\"white\" stroke=\"none\" points=\"-4,4 -4,-40 226.25,-40 226.25,4 -4,4\"/>\n",
+       "<!-- sample_e91f804d&#45;5c09&#45;46dc&#45;8eef&#45;8a7a33b1c135 -->\n",
        "<g id=\"node1\" class=\"node\">\n",
-       "<title>sample_4ff68114&#45;deac&#45;439a&#45;8540&#45;554d4a919e63</title>\n",
-       "<polygon fill=\"#d9d9d9\" stroke=\"#d9d9d9\" points=\"223.75,-36 0,-36 0,0 223.75,0 223.75,-36\"/>\n",
-       "<text text-anchor=\"middle\" x=\"111.88\" y=\"-15.28\" font-family=\"Helvetica,sans-Serif\" font-size=\"8.00\">sample_4ff68114&#45;deac&#45;439a&#45;8540&#45;554d4a919e63</text>\n",
+       "<title>sample_e91f804d&#45;5c09&#45;46dc&#45;8eef&#45;8a7a33b1c135</title>\n",
+       "<polygon fill=\"#d9d9d9\" stroke=\"#d9d9d9\" points=\"222.25,-36 0,-36 0,0 222.25,0 222.25,-36\"/>\n",
+       "<text text-anchor=\"middle\" x=\"111.12\" y=\"-15.28\" font-family=\"Helvetica,sans-Serif\" font-size=\"8.00\">sample_e91f804d&#45;5c09&#45;46dc&#45;8eef&#45;8a7a33b1c135</text>\n",
        "</g>\n",
        "</g>\n",
        "</svg>\n"
       ],
       "text/plain": [
-       "<graphviz.graphs.Digraph at 0x7fb2d0b99310>"
+       "<graphviz.graphs.Digraph at 0x7f8373a835d0>"
       ]
      },
      "execution_count": 7,
@@ -187,7 +187,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The job j1 was saved and received the ID: 134\n"
+      "The job j1 was saved and received the ID: 154\n"
      ]
     }
    ],
@@ -197,14 +197,63 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "af64675d-2630-4e83-9b54-d83aa92f0df0",
    "metadata": {},
    "outputs": [],
    "source": [
     "kg.add_workflow(job, workflow_environment='pyiron')"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "b20c7a38-e530-44e4-a062-2c660052ba37",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "c4010a08",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'/mnt/c/Users/menon/Documents/repos/projects-iuc17/atomRDF/examples/workflow_examples/wf1c/j1_hdf5/j1'"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "os.path.join(job.project.path, f'{job.name}_hdf5', job.name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "6df3f9f7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ls: cannot access '/mnt/c/Users/menon/Documents/repos/projects-iuc17/atomRDF/examples/workflow_examples/wf1c/j1': No such file or directory\n"
+     ]
+    }
+   ],
+   "source": [
+    "! ls /mnt/c/Users/menon/Documents/repos/projects-iuc17/atomRDF/examples/workflow_examples/wf1c/j1"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 14,

setup.py

@@ -6,7 +6,7 @@
 
 setup(
     name='atomrdf',
-    version='0.6.9',
+    version='0.6.10',
     author='Abril Azocar Guzman, Sarath Menon',
     author_email='[email protected]',
     description='Ontology based structural manipulation and quering',