diff --git a/examples/ml-multi-cloud/ml_multicloud_sample_store.yaml b/examples/ml-multi-cloud/ml_multicloud_sample_store.yaml index 70eeb2632..f8cf97c10 100644 --- a/examples/ml-multi-cloud/ml_multicloud_sample_store.yaml +++ b/examples/ml-multi-cloud/ml_multicloud_sample_store.yaml @@ -1,28 +1,29 @@ # Copyright IBM Corporation 2025, 2026 # SPDX-License-Identifier: MIT -metadata: - name: "ml_multi_cloud" - description: "samplestore initialised with ml_multi_cloud data" -specification: - module: - moduleName: orchestrator.core.samplestore.sql - moduleClass: SQLSampleStore copyFrom: - module: moduleClass: CSVSampleStore moduleName: orchestrator.core.samplestore.csv - storageLocation: - path: 'ml_export.csv' parameters: - generatorIdentifier: 'multi-cloud-ml' - identifierColumn: 'config' - constitutivePropertyColumns: - - cpu_family - - vcpu_size - - nodes - - provider experiments: - - experimentIdentifier: 'benchmark_performance' - propertyMap: - wallClockRuntime: 'wallClockRuntime' - status: 'status' + - actuatorIdentifier: replay + constitutivePropertyMap: + - cpu_family + - vcpu_size + - nodes + - provider + experimentIdentifier: benchmark_performance + observedPropertyMap: + - wallClockRuntime + - status + generatorIdentifier: multi-cloud-ml + identifierColumn: config + storageLocation: + path: ml_export.csv +metadata: + description: samplestore initialised with ml_multi_cloud data + name: ml_multi_cloud +specification: + module: + moduleClass: SQLSampleStore + moduleName: orchestrator.core.samplestore.sql diff --git a/examples/pfas-generative-models/gen_models_molgx_test_sample_store.yaml b/examples/pfas-generative-models/gen_models_molgx_test_sample_store.yaml index e9cd2837e..99cc44e4f 100644 --- a/examples/pfas-generative-models/gen_models_molgx_test_sample_store.yaml +++ b/examples/pfas-generative-models/gen_models_molgx_test_sample_store.yaml @@ -1,22 +1,25 @@ # Copyright IBM Corporation 2025, 2026 # SPDX-License-Identifier: MIT -specification: - module: - moduleClass: SQLSampleStore - moduleName: orchestrator.model.sqlstore copyFrom: - module: moduleClass: CSVSampleStore - storageLocation: - path: 'data/GM_Comparison/MolGX/Sample_0/PFAS_MolGX_test_SHORT_v0.csv' + moduleName: orchestrator.core.samplestore.csv parameters: - generatorIdentifier: 'gt4sd-pfas-molgx-model-one' - identifierColumn: 'smiles' - constitutivePropertyColumns: ['smiles'] experiments: - - experimentIdentifier: 'molgx-toxicity-inference-experiment' - propertyMap: - pka: "Real_pKa (-0.83, 10.58)" - logws: "Real_LogWS (-6.19, 1.13)" - "biodegradation halflife": "Real_BioDeg (0.47, 2.66)" - ld50: "Real_LD50 (3.9, 7543.0)" + - actuatorIdentifier: replay + constitutivePropertyMap: + - smiles + experimentIdentifier: molgx-toxicity-inference-experiment + observedPropertyMap: + biodegradation halflife: Real_BioDeg (0.47, 2.66) + ld50: Real_LD50 (3.9, 7543.0) + logws: Real_LogWS (-6.19, 1.13) + pka: Real_pKa (-0.83, 10.58) + generatorIdentifier: gt4sd-pfas-molgx-model-one + identifierColumn: smiles + storageLocation: + path: data/GM_Comparison/MolGX/Sample_0/PFAS_MolGX_test_SHORT_v0.csv +specification: + module: + moduleClass: SQLSampleStore + moduleName: orchestrator.core.samplestore.sql diff --git a/tests/resources/samplestore/sample_store_resource.json b/tests/resources/samplestore/sample_store_resource.json index 63545a149..739e9c07a 100644 --- a/tests/resources/samplestore/sample_store_resource.json +++ b/tests/resources/samplestore/sample_store_resource.json @@ -1,45 +1,60 @@ { - "kind": "samplestore", + "created": "2026-02-25T06:07:13.737897Z", "config": { + "specification": { + "module": { + "moduleName": "orchestrator.core.samplestore.sql", + "moduleClass": "SQLSampleStore" + }, + "parameters": { + "identifier": "18ced1" + } + }, "copyFrom": [ { "module": { "moduleName": "orchestrator.core.samplestore.csv", - "modulePath": ".", - "moduleType": "sample_store", "moduleClass": "CSVSampleStore" }, "parameters": { "experiments": [ { - "propertyMap": { "wallClockRuntime": "wallClockRuntime" }, - "experimentIdentifier": "benchmark_performance" + "experimentIdentifier": "benchmark_performance", + "actuatorIdentifier": "replay", + "observedPropertyMap": [ + "wallClockRuntime", + "status" + ], + "constitutivePropertyMap": [ + "cpu_family", + "vcpu_size", + "nodes", + "provider" + ] } ], - "constitutivePropertyColumns": ["cpu_family", "vcpu_size", "nodes", "provider"], - "identifierColumn": "config", - "generatorIdentifier": "multi-cloud-ml" + "generatorIdentifier": "multi-cloud-ml", + "identifierColumn": "config" }, "storageLocation": { - "path": "examples/ml-multi-cloud/ml_export.csv", - "scheme": "file" + "path": "ml_export.csv" } } ], - "specification": { - "module": { - "moduleName": "orchestrator.core.samplestore.sql", - "modulePath": ".", - "moduleType": "sample_store", - "moduleClass": "SQLSampleStore" - }, - "parameters": { "identifier": "4847c1" }, - "storageLocation": {} + "metadata": { + "name": "ml_multi_cloud", + "description": "samplestore initialised with ml_multi_cloud data" } }, - "status": [], - "created": "2024-11-13T10:26:37.090387Z", - "version": "v2", - "metadata": {}, - "identifier": "4847c1" + "identifier": "18ced1", + "status": [ + { + "recorded_at": "2026-02-25T06:07:13.737910Z", + "event": "created" + }, + { + "recorded_at": "2026-02-25T06:07:13.751199Z", + "event": "added" + } + ] } diff --git a/website/docs/actuators/replay.md b/website/docs/actuators/replay.md index 53248cb38..2eb16415d 100644 --- a/website/docs/actuators/replay.md +++ b/website/docs/actuators/replay.md @@ -39,27 +39,27 @@ The relevant fields are: - `storageLocation`: This is the path the CSV file - `parameters.identifierColumn`: This is the column in the CSV, if any, to use as the identifier of the created entities. -- `parameters.constitutivePropertyColumns`: This is a list of the columns in the - CSV file that define the constitutive properties of the entities +- `parameters.constitutivePropertyMap`: This is a list of the columns in the CSV + file that define the constitutive properties of the entities - `experiments`: This section defines the experiments that were used to generate the data in the CSV file - `experiments.experimentIdentifier`: This is the name for the experiment in ado - - `experiments.propertyMap`: This is a dictionary mapping the names of the - properties experiment as they will appear in `ado` to column names in the - CSV + - `experiments.observedPropertyMap`: This is a dictionary mapping the names of + the properties experiment as they will appear in `ado` to column names in + the CSV The above YAML says to associate the data in the columns `wallClockRuntime` and `status` with an experiment 'benchmark_performance' that measures properties with the same name. -The `propertyMap` field allows you to handle column headers had names that are -not suitable for names of properties. For example if there was a column with -measurements on a molecule called `Real_pKa (-0.83, 10.58)`, you might want to -associate this with a property called `pka` instead: +The `observedPropertyMap` field allows you to handle column headers had names +that are not suitable for names of properties. For example if there was a column +with measurements on a molecule called `Real_pKa (-0.83, 10.58)`, you might want +to associate this with a property called `pka` instead: ```yaml -propertyMap: +observedPropertyMap: pka: "Real_pKa (-0.83, 10.58)" ```