added schema for material fingerprint primary descriptors

example/job.json

@@ -1,9 +1,11 @@
 {
     "status": "pre-submission",
     "mode": "normal",
-    "_material": {
-        "...": "include(job/_material.json)"
-    },
+    "_materials": [
+        {
+            "...": "include(job/_material.json)"
+        }
+    ],
     "compute": {
         "...": "include(job/compute.json)"
     },

example/material/fingerprint.json

@@ -0,0 +1,8 @@
+{
+    "primary": {
+        "...": "include(fingerprint/primary.json)"
+    },
+    "secondary": {
+        "...": "include(characteristic.json)"
+    }
+}

example/material/fingerprint/primary.json

@@ -0,0 +1,85 @@
+{
+    "localEnvironment": {
+        "...": "include(primary/element_specific.json)"
+    },
+    "representation": {
+        "description": "structure representation.",
+        "$ref": "file:primary/compound_specific.json"
+    },
+    "valenceOrbitalOccupancy": {
+        "description": "s, p, d, and f orbital contribution to total valence electrons in the material ",
+        "$ref": "file:primary/compound_specific_array.json"
+    },
+    "elementSpinState": {
+        "type": "element-specific",
+        "subtype": "nominal",
+        "category": "electronic",
+        "elements": [
+            {
+                "name": "Si",
+                "value": "high"
+            },
+            {
+                "name": "O",
+                "value": "low"
+            }
+        ]
+    },
+    "pNorm": {
+        "type": "compound-specific",
+        "subtype": "numeric",
+        "category": "stoichiometric",
+        "data": [
+            {
+                "name": "p03",
+                "value": 0.693
+            },
+            {
+                "name": "p05",
+                "value": 0.671
+            },
+            {
+                "name": "p07",
+                "value": 0.667
+            },
+            {
+                "name": "p09",
+                "value": 0.667
+            }
+        ]
+    },
+    "elementalComposition": {
+        "type": "element-specific",
+        "subtype": "numeric",
+        "category": "stoichiometric",
+        "elements": [
+            {
+                "name": "Si",
+                "value": 0.33
+            },
+            {
+                "name": "O",
+                "value": 0.66
+            }
+        ]
+    },
+    "equilibrium": {
+        "type": "compound-specific",
+        "subtype": "nominal",
+        "category": "structural",
+        "value": "No"
+    },
+    "materialType": {
+        "type": "compound-specific",
+        "subtype": "nominal",
+        "category": "structural",
+        "value": "crystal"
+    },
+    "avgAtomVolume": {
+        "type": "compound-specific",
+        "subtype": "numeric",
+        "category": "structural",
+        "value": 0.039,
+        "units": "1/Ang^3"
+    }
+}

example/material/fingerprint/primary/_compound_data.json

@@ -0,0 +1,20 @@
+{
+    "data": [
+        {
+            "name": "s",
+            "value": 0.325
+        },
+        {
+            "name": "p",
+            "value": 0.625
+        },
+        {
+            "name": "d",
+            "value": 0.0
+        },
+        {
+            "name": "f",
+            "value": 0.0
+        }
+    ]
+}

example/material/fingerprint/primary/_element_data.json

@@ -0,0 +1,12 @@
+{
+    "elements": [
+        {
+            "name": "Si",
+            "value": "O"
+        },
+        {
+            "name": "O",
+            "value": "X"
+        }
+    ]
+}

example/material/fingerprint/primary/_primary.json

@@ -0,0 +1,5 @@
+{
+    "type": "compound-specific",
+    "subtype": "nominal",
+    "category": "structural"
+}

example/material/fingerprint/primary/compound_specific.json

@@ -0,0 +1,4 @@
+{
+    "...": "include(_primary.json)",
+    "value": "supercell"
+}

example/material/fingerprint/primary/compound_specific_array.json

@@ -0,0 +1,6 @@
+{
+    "type": "compound-specific",
+    "subtype": "numeric",
+    "category": "electronic",
+    "...": "include(_compound_data.json)"
+}

example/material/fingerprint/primary/element_specific.json

@@ -0,0 +1,6 @@
+{
+    "type": "element-specific",
+    "subtype": "nominal",
+    "category": "chemical",
+    "...": "include(_element_data.json)"
+}

example/material/structure/elements.json

@@ -0,0 +1,3 @@
+{
+    "...": "include(atomic_data.json)"
+}

example/material/structure/lattice_bravais.json

@@ -1,6 +1,6 @@
 {
-    "name": "lattice_bravais",
     "type": "CUB",
+    "name": "lattice_bravais",
     "a": 5.14,
     "b": 5.14,
     "c": 5.14,

schema/job.json

@@ -73,9 +73,12 @@
             "description": "Subset of the full information about the project that this job belongs to. Included for quick access in search.",
             "$ref": "file:job/_project.json"
         },
-        "_material": {
+        "_materials": {
             "description": "Subset of the full information about the materials used inside this job.",
-            "$ref": "file:job/_material.json"
+            "type": "array",
+            "items": {
+                "$ref": "file:job/_material.json"
+            }
         },
         "version": {
             "description": "Job's schema version. Used to distinct between different schemas.",

schema/material/fingerprint.json

@@ -0,0 +1,19 @@
+{
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "title": "material fingerprint schema",
+    "description": "collection of descriptors with information about materials structure, composition and characteristics required for performing advanced ML tasks",
+    "properties": {
+        "primary": {
+            "description": "descriptors related to structure, stoichiometry and physical reference data of materials. Calculated on-the-fly ",
+            "$ref": "file:fingerprint/primary.json"
+        },
+        "secondary": {
+            "description": "descriptors related to characteristics from simulations and/or experiments",
+            "$ref": "file:characteristic.json"
+        }
+    },
+    "required": [
+        "primary",
+        "secondary"
+    ]
+}

schema/material/fingerprint/primary.json

@@ -0,0 +1,43 @@
+{
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "title": "primary descriptors schema",
+    "description": "collection of stoichiometric, structural, physical, electronic and chemical",
+    "properties": {
+        "localEnvironment": {
+            "description": "atom type each element is bonded to",
+            "$ref": "file:primary/element_specific.json"
+        },
+        "elementSpinState": {
+            "description": "Spin state of each element. Spin state depends on oxidation state and electronic configuration. ",
+            "$ref": "file:primary/element_specific.json"
+        },
+        "valenceOrbitalOccupancy": {
+            "description": "contribution from s, p, d, and f of unique elements to total valence electrons in the material ",
+            "$ref": "file:primary/compound_specific_array.json"
+        },
+        "pNorm": {
+            "description": "values calculated using L-p norm upto p-dimensions",
+            "$ref": "file:primary/compound_specific_array.json"
+        },
+        "elementalComposition": {
+            "description": "elemental composition of the compound",
+            "$ref": "file:primary/element_specific.json"
+        },
+        "representation": {
+            "description": "structure representation.",
+            "$ref": "file:primary/compound_specific.json"
+        },
+        "equilibrium": {
+            "description": "Identifies a equilibrium structure.",
+            "$ref": "file:primary/compound_specific.json"
+        },
+        "materialType": {
+            "description": "structure representation.",
+            "$ref": "file:primary/compound_specific.json"
+        },
+        "avgAtomVolume": {
+            "description": "structure representation.",
+            "$ref": "file:primary/compound_specific.json"
+        }
+    }
+}

schema/material/fingerprint/primary/_compound_data.json

@@ -0,0 +1,29 @@
+{
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "title": "compound-specific descriptor array elements schema",
+    "description": "for p-norms and valence_orbital occupancy",
+    "properties": {
+        "name": {
+            "oneOf": [
+                {
+                    "description": "p-norms. Upto p99 allowed. Eg: p3",
+                    "type": "string",
+                    "pattern": "p[0-9]{2}"
+                },
+                {
+                    "description": "valence orbital occupancy - https://www.nature.com/article-assets/npg/npjcompumats/2016/npjcompumats201628/extref/npjcompumats201628-s1.pdf",
+                    "type": "string",
+                    "enum": [
+                        "s",
+                        "p",
+                        "d",
+                        "f"
+                    ]
+                }
+            ]
+        },
+        "value": {
+            "type": "number"
+        }
+    }
+}

schema/material/fingerprint/primary/_element_data.json

@@ -0,0 +1,40 @@
+{
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "title": "element-specific descriptors data schema",
+    "description": "element symbol and corresponding values.",
+    "properties": {
+        "name": {
+            "description": "element symbol. Eg: Si",
+            "type": "string"
+        },
+        "value": {
+            "oneOf": [
+                {
+                    "description": "elemental composition",
+                    "type": "number"
+                },
+                {
+                    "description": "element_spin_states. high and low spin states correspond to states with max number of unpaired electrons with same spin and maximum number of paired spins respectively.",
+                    "type": "string",
+                    "enum": [
+                        "high",
+                        "intermediate",
+                        "low"
+                    ]
+                },
+                {
+                    "description": "local environemnt. atom symbol to which element is bonded to. X means non-bonded or bonded to any atom other than the ones in the list",
+                    "type": "string",
+                    "enum": [
+                        "H",
+                        "O",
+                        "S",
+                        "F",
+                        "Cl",
+                        "X"
+                    ]
+                }
+            ]
+        }
+    }
+}

schema/material/fingerprint/primary/_primary.json

@@ -0,0 +1,32 @@
+{
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "title": "primary descriptor category schema",
+    "description": "type/subtype each primary descriptor belongs to",
+    "properties": {
+        "type": {
+            "type": "string",
+            "enum": [
+                "element-specific",
+                "compound-specific"
+            ]
+        },
+        "subtype": {
+            "description": "type of descriptor, whether it is a number or category",
+            "type": "string",
+            "enum": [
+                "numeric",
+                "nominal",
+                "ordinal"
+            ]
+        },
+        "category": {
+            "type": "string",
+            "enum": [
+                "chemical",
+                "stoichiometric",
+                "structural",
+                "electronic"
+            ]
+        }
+    }
+}