Add MLBuilder and MLDoc to record machine learning property predi…

…ctions (#806) * add pydantic models MLIPElasticityDoc, MLIPPhononDoc, MLIPEosDoc, MLIPRelaxationDoc for interatomic potential predictions * add class MLIPBuilder runs CHGNet and MEGNet over all structures in the materials store and with every matcalc PropCalc class * wip test_mlip_builder.py * MLIPBuilder add args model: Union[str, "Calculator"] and prop_kwargs: dict = None * update MLIPDoc with provenance just model name and package version for now * merge MLIPElasticityDoc MLIPPhononDoc MLIPEosDoc MLIPRelaxationDoc into MLIPDoc * run MLIPBuilder with chgnet and m3gnet in test_ml_ip_builder * deduplicate test_structures * remove magnetism_test_data fixture just adds verbosity * mv emmet-core/tests/test_structure{,_}metadata.py mv emmet-core/tests/test_molecule{,_}metadata.py * add test_mlip_doc * refactor MLIPDoc.__init__ * rename MLIPBuilder keyword calc_kwargs to model_kwargs * EOS->eos * test only one structure in test_mlip_doc() for speed * mv emmet-core/tests/test_{ml_potential.py,ml.py} and split chgnet and m3gnet into separate test functions * mv emmet-builders/emmet/builders/materials/{ml_potential,ml}.py emmet-core/emmet/core/{ml_potential,ml}.py convert numpy arrays to lists and fix doc str * fix typos compatability->compatibility * MLIPDoc add structure, calculator, version metadata fields * working MLIPDoc tests starting with test_mlip_doc_with_calc_as_(str|model) * setup.cfg add pytest option -p no:warnings set isort known_local_folder=emmet * fix names in MLIPDoc Attributes doc string section * fix MLIPBuilder provenance matcalc version model name model version * test_ml_ip_builder() 1st working version * ThermodynamicProperties.cv add alias heat_capacity * merge both MLIPDoc tests using @pytest.mark.parametrize * MLIPDoc rename field version to matcalc_version * MLIPBuilder add kwarg provenance for extra custom data * test_ml_ip_builder() parametrize model * add matcalc to emmet-core extras_require 'all' * fix test type hint Union[str, "Calculator"] * make all MLIPDoc fields optional * young_modulus add alias youngs_modulus * MLIPDoc inherit from ElasticityDoc add bulk_modulus and shear_modulus pydantic validators * fix emmet-core/tests/test_ml.py * update MLIPDoc doc string with correct elasticity types * map (bulk|shear)_modulus_vrh which matcalc returns to (bulk|shear)_modulus which ElasticityDoc expects * test prop_kwargs keyword of MLIPDoc * Automated dependency upgrades (#827) * update dependencies for emmet-api (ubuntu-latest/py3.10) * update dependencies for emmet-api (ubuntu-latest/py3.11) * update dependencies for emmet-api (ubuntu-latest/py3.8) * update dependencies for emmet-api (ubuntu-latest/py3.9) * update dependencies for emmet-builders (ubuntu-latest/py3.10) * update dependencies for emmet-builders (ubuntu-latest/py3.11) * update dependencies for emmet-builders (ubuntu-latest/py3.8) * update dependencies for emmet-builders (ubuntu-latest/py3.9) * update dependencies for emmet-core (ubuntu-latest/py3.10) * update dependencies for emmet-core (ubuntu-latest/py3.11) * update dependencies for emmet-core (ubuntu-latest/py3.8) * update dependencies for emmet-core (ubuntu-latest/py3.9) --------- Co-authored-by: github-actions <[email protected]> * rename MLIPBuilder to MLBuilder and MLIPDoc to MLDoc * Matcalc dep added to req files * Remove repeat req entry * Bump matcalc --------- Co-authored-by: Patrick Huck <[email protected]> Co-authored-by: github-actions <[email protected]> Co-authored-by: Jason Munro <[email protected]>
materialsproject · Sep 26, 2023 · ff4b452 · ff4b452
1 parent e4bb49f
commit ff4b452
Show file tree

Hide file tree

Showing 47 changed files with 526 additions and 306 deletions.
diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md
@@ -2608,7 +2608,7 @@
 - Working Thermo Builder [\#170](https://github.com/materialsproject/emmet/pull/170) ([jmmshn](https://github.com/jmmshn))
 - Add SCF gradient and Manual deprecation to VASP validation [\#169](https://github.com/materialsproject/emmet/pull/169) ([shyamd](https://github.com/shyamd))
 - Create MPID Type [\#167](https://github.com/materialsproject/emmet/pull/167) ([shyamd](https://github.com/shyamd))
-- Remove stubs in favor of monty pydantic compatability [\#165](https://github.com/materialsproject/emmet/pull/165) ([shyamd](https://github.com/shyamd))
+- Remove stubs in favor of monty pydantic compatibility [\#165](https://github.com/materialsproject/emmet/pull/165) ([shyamd](https://github.com/shyamd))
 - made structure grouper work with material\_ids [\#163](https://github.com/materialsproject/emmet/pull/163) ([jmmshn](https://github.com/jmmshn))
 - minor changes to get material builder working on non-production databases. [\#162](https://github.com/materialsproject/emmet/pull/162) ([jmmshn](https://github.com/jmmshn))
 - Electrode Doc [\#149](https://github.com/materialsproject/emmet/pull/149) ([jmmshn](https://github.com/jmmshn))

diff --git a/emmet-api/requirements/ubuntu-latest_py3.10.txt b/emmet-api/requirements/ubuntu-latest_py3.10.txt
@@ -138,7 +138,6 @@ monty==2023.9.25
     #   emmet-core
     #   maggma
     #   matminer
-    #   mp-api
     #   pymatgen
     #   robocrys
 mp-api==0.36.1
@@ -215,7 +214,6 @@ pymatgen==2023.9.10
     #   emmet-api (setup.py)
     #   emmet-core
     #   matminer
-    #   mp-api
     #   pymatgen-analysis-alloys
     #   pymatgen-analysis-diffusion
     #   robocrys
@@ -252,7 +250,6 @@ requests==2.31.0
     # via
     #   matminer
     #   mongogrant
-    #   mp-api
     #   pymatgen
 robocrys==0.2.8
     # via emmet-core
@@ -327,7 +324,6 @@ typing-extensions==4.8.0
     #   emmet-core
     #   fastapi
     #   inflect
-    #   mp-api
     #   pydantic
     #   pydash
     #   uvicorn

diff --git a/emmet-api/requirements/ubuntu-latest_py3.10_extras.txt b/emmet-api/requirements/ubuntu-latest_py3.10_extras.txt
@@ -217,7 +217,6 @@ monty==2023.9.25
     #   emmet-core
     #   maggma
     #   matminer
-    #   mp-api
     #   pymatgen
     #   robocrys
 mp-api==0.36.1
@@ -326,7 +325,6 @@ pymatgen==2023.9.10
     #   emmet-api (setup.py)
     #   emmet-core
     #   matminer
-    #   mp-api
     #   pymatgen-analysis-alloys
     #   pymatgen-analysis-diffusion
     #   robocrys
@@ -382,7 +380,6 @@ requests==2.31.0
     # via
     #   matminer
     #   mongogrant
-    #   mp-api
     #   pymatgen
 robocrys==0.2.8
     # via emmet-core
@@ -473,7 +470,6 @@ typing-extensions==4.8.0
     #   emmet-core
     #   fastapi
     #   inflect
-    #   mp-api
     #   mypy
     #   pydantic
     #   pydash

diff --git a/emmet-api/requirements/ubuntu-latest_py3.11.txt b/emmet-api/requirements/ubuntu-latest_py3.11.txt
@@ -134,7 +134,6 @@ monty==2023.9.25
     #   emmet-core
     #   maggma
     #   matminer
-    #   mp-api
     #   pymatgen
     #   robocrys
 mp-api==0.36.1
@@ -211,7 +210,6 @@ pymatgen==2023.9.10
     #   emmet-api (setup.py)
     #   emmet-core
     #   matminer
-    #   mp-api
     #   pymatgen-analysis-alloys
     #   pymatgen-analysis-diffusion
     #   robocrys
@@ -248,7 +246,6 @@ requests==2.31.0
     # via
     #   matminer
     #   mongogrant
-    #   mp-api
     #   pymatgen
 robocrys==0.2.8
     # via emmet-core
@@ -322,7 +319,6 @@ typing-extensions==4.8.0
     #   emmet-core
     #   fastapi
     #   inflect
-    #   mp-api
     #   pydantic
     #   pydash
 uncertainties==3.1.7

diff --git a/emmet-api/requirements/ubuntu-latest_py3.11_extras.txt b/emmet-api/requirements/ubuntu-latest_py3.11_extras.txt
@@ -212,7 +212,6 @@ monty==2023.9.25
     #   emmet-core
     #   maggma
     #   matminer
-    #   mp-api
     #   pymatgen
     #   robocrys
 mp-api==0.36.1
@@ -321,7 +320,6 @@ pymatgen==2023.9.10
     #   emmet-api (setup.py)
     #   emmet-core
     #   matminer
-    #   mp-api
     #   pymatgen-analysis-alloys
     #   pymatgen-analysis-diffusion
     #   robocrys
@@ -377,7 +375,6 @@ requests==2.31.0
     # via
     #   matminer
     #   mongogrant
-    #   mp-api
     #   pymatgen
 robocrys==0.2.8
     # via emmet-core
@@ -462,7 +459,6 @@ typing-extensions==4.8.0
     #   emmet-core
     #   fastapi
     #   inflect
-    #   mp-api
     #   mypy
     #   pydantic
     #   pydash

diff --git a/emmet-api/requirements/ubuntu-latest_py3.8.txt b/emmet-api/requirements/ubuntu-latest_py3.8.txt
@@ -48,7 +48,7 @@ click==8.1.7
     #   uvicorn-tschaume
 contourpy==1.1.1
     # via matplotlib
-cryptography==41.0.3
+cryptography==41.0.4
     # via paramiko
 cycler==0.11.0
     # via matplotlib
@@ -98,7 +98,7 @@ importlib-metadata==6.8.0
     # via
     #   flask
     #   opentelemetry-api
-importlib-resources==6.0.1
+importlib-resources==6.1.0
     # via
     #   jsonschema
     #   jsonschema-specifications
@@ -118,7 +118,7 @@ joblib==1.3.2
     #   pymatgen
     #   pymatgen-analysis-diffusion
     #   scikit-learn
-jsonschema==4.19.0
+jsonschema==4.19.1
     # via maggma
 jsonschema-specifications==2023.7.1
     # via jsonschema
@@ -152,7 +152,7 @@ mp-api==0.35.1
     # via pymatgen
 mpmath==1.3.0
     # via sympy
-msgpack==1.0.5
+msgpack==1.0.6
     # via
     #   maggma
     #   mp-api
@@ -278,7 +278,7 @@ ruamel-yaml-clib==0.2.7
     # via ruamel-yaml
 s3transfer==0.6.2
     # via boto3
-scikit-learn==1.3.0
+scikit-learn==1.3.1
     # via matminer
 scipy==1.10.1
     # via
@@ -359,7 +359,7 @@ wrapt==1.15.0
     # via deprecated
 xmltodict==0.13.0
     # via ddtrace
-zipp==3.16.2
+zipp==3.17.0
     # via
     #   importlib-metadata
     #   importlib-resources

diff --git a/emmet-api/requirements/ubuntu-latest_py3.8_extras.txt b/emmet-api/requirements/ubuntu-latest_py3.8_extras.txt
@@ -57,7 +57,7 @@ contourpy==1.1.1
     # via matplotlib
 coverage[toml]==7.3.1
     # via pytest-cov
-cryptography==41.0.3
+cryptography==41.0.4
     # via paramiko
 csscompressor==0.9.5
     # via mkdocs-minify-plugin
@@ -127,7 +127,7 @@ importlib-metadata==6.8.0
     #   mkdocs
     #   mkdocstrings
     #   opentelemetry-api
-importlib-resources==6.0.1
+importlib-resources==6.1.0
     # via
     #   jsonschema
     #   jsonschema-specifications
@@ -156,7 +156,7 @@ joblib==1.3.2
     #   scikit-learn
 jsmin==3.0.1
     # via mkdocs-minify-plugin
-jsonschema==4.19.0
+jsonschema==4.19.1
     # via maggma
 jsonschema-specifications==2023.7.1
     # via jsonschema
@@ -189,7 +189,7 @@ mccabe==0.7.0
     # via flake8
 mergedeep==1.3.4
     # via mkdocs
-mkdocs==1.5.2
+mkdocs==1.5.3
     # via
     #   emmet-api (setup.py)
     #   mkdocs-autorefs
@@ -206,7 +206,7 @@ mkdocs-markdownextradata-plugin==0.2.5
     # via emmet-api (setup.py)
 mkdocs-material==8.2.16
     # via emmet-api (setup.py)
-mkdocs-material-extensions==1.1.1
+mkdocs-material-extensions==1.2
     # via
     #   emmet-api (setup.py)
     #   mkdocs-material
@@ -234,7 +234,7 @@ mp-api==0.35.1
     # via pymatgen
 mpmath==1.3.0
     # via sympy
-msgpack==1.0.5
+msgpack==1.0.6
     # via
     #   maggma
     #   mp-api
@@ -411,7 +411,7 @@ ruamel-yaml-clib==0.2.7
     # via ruamel-yaml
 s3transfer==0.6.2
     # via boto3
-scikit-learn==1.3.0
+scikit-learn==1.3.1
     # via matminer
 scipy==1.10.1
     # via
@@ -472,7 +472,7 @@ tqdm==4.66.1
     #   maggma
     #   matminer
     #   pymatgen
-types-requests==2.31.0.2
+types-requests==2.31.0.5
     # via emmet-api (setup.py)
 types-setuptools==68.2.0.0
     # via emmet-api (setup.py)
@@ -518,7 +518,7 @@ wrapt==1.15.0
     # via deprecated
 xmltodict==0.13.0
     # via ddtrace
-zipp==3.16.2
+zipp==3.17.0
     # via
     #   importlib-metadata
     #   importlib-resources

diff --git a/emmet-api/requirements/ubuntu-latest_py3.9.txt b/emmet-api/requirements/ubuntu-latest_py3.9.txt
@@ -142,7 +142,6 @@ monty==2023.9.25
     #   emmet-core
     #   maggma
     #   matminer
-    #   mp-api
     #   pymatgen
     #   robocrys
 mp-api==0.36.1
@@ -219,7 +218,6 @@ pymatgen==2023.9.10
     #   emmet-api (setup.py)
     #   emmet-core
     #   matminer
-    #   mp-api
     #   pymatgen-analysis-alloys
     #   pymatgen-analysis-diffusion
     #   robocrys
@@ -256,7 +254,6 @@ requests==2.31.0
     # via
     #   matminer
     #   mongogrant
-    #   mp-api
     #   pymatgen
 robocrys==0.2.8
     # via emmet-core
@@ -333,7 +330,6 @@ typing-extensions==4.8.0
     #   emmet-core
     #   fastapi
     #   inflect
-    #   mp-api
     #   pydantic
     #   pydash
     #   starlette

diff --git a/emmet-api/requirements/ubuntu-latest_py3.9_extras.txt b/emmet-api/requirements/ubuntu-latest_py3.9_extras.txt
@@ -224,7 +224,6 @@ monty==2023.9.25
     #   emmet-core
     #   maggma
     #   matminer
-    #   mp-api
     #   pymatgen
     #   robocrys
 mp-api==0.36.1
@@ -333,7 +332,6 @@ pymatgen==2023.9.10
     #   emmet-api (setup.py)
     #   emmet-core
     #   matminer
-    #   mp-api
     #   pymatgen-analysis-alloys
     #   pymatgen-analysis-diffusion
     #   robocrys
@@ -389,7 +387,6 @@ requests==2.31.0
     # via
     #   matminer
     #   mongogrant
-    #   mp-api
     #   pymatgen
 robocrys==0.2.8
     # via emmet-core
@@ -483,7 +480,6 @@ typing-extensions==4.8.0
     #   fastapi
     #   inflect
     #   mkdocstrings
-    #   mp-api
     #   mypy
     #   pydantic
     #   pydash

diff --git a/emmet-builders/emmet/builders/materials/corrected_entries.py b/emmet-builders/emmet/builders/materials/corrected_entries.py
@@ -36,7 +36,7 @@ def __init__(
             corrected_entries (Store): Store to output corrected entry data
             oxidation_states (Store): Store of oxidation state data to use in correction scheme application
             query (dict): dictionary to limit materials to be analyzed
-            compatibility ([Compatability]): Compatability module
+            compatibility ([Compatibility]): Compatibility module
                 to ensure energies are compatible
             chunk_size (int): Size of chemsys chunks to process at any one time.
         """
@@ -145,12 +145,12 @@ def process_item(self, item):
 
         corrected_entries = {}
 
-        for compatability in self.compatibility:
-            if compatability is not None:
+        for compatibility in self.compatibility:
+            if compatibility is not None:
                 with warnings.catch_warnings():
                     warnings.simplefilter("ignore")
                     with HiddenPrints():
-                        if compatability.name == "MP DFT mixing scheme":
+                        if compatibility.name == "MP DFT mixing scheme":
                             thermo_type = ThermoType.GGA_GGA_U_R2SCAN
 
                             if "R2SCAN" in all_entry_types:
@@ -161,22 +161,22 @@ def process_item(self, item):
                                 ]
                                 corrected_entries["R2SCAN"] = only_scan_pd_entries
 
-                                pd_entries = compatability.process_entries(
+                                pd_entries = compatibility.process_entries(
                                     copy.deepcopy(entries)
                                 )
 
                             else:
                                 corrected_entries["R2SCAN"] = None
                                 pd_entries = None
 
-                        elif compatability.name == "MP2020":
+                        elif compatibility.name == "MP2020":
                             thermo_type = ThermoType.GGA_GGA_U
-                            pd_entries = compatability.process_entries(
+                            pd_entries = compatibility.process_entries(
                                 copy.deepcopy(entries)
                             )
                         else:
                             thermo_type = ThermoType.UNKNOWN
-                            pd_entries = compatability.process_entries(
+                            pd_entries = compatibility.process_entries(
                                 copy.deepcopy(entries)
                             )