Breakthrough Model
Who built a Breakthrough model session.
Attributes:
| Name | Type | Description |
|---|---|---|
USER_MODEL |
str
|
A session built by a user. |
ALBERT_MODEL |
str
|
A session built automatically by Albert. |
Bases: BaseAlbertModel
Build logs and metrics recorded for a model session.
Show JSON schema:
{
"description": "Build logs and metrics recorded for a model session.",
"properties": {
"BuildLogs": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Free-form logs captured while the session's models were built.",
"title": "Buildlogs"
},
"Metrics": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Free-form performance metrics recorded for the session's models.",
"title": "Metrics"
}
},
"title": "BTModelRegistry",
"type": "object"
}
Fields:
Bases: BaseResource
A parent session grouping a related set of Breakthrough models.
Albert Breakthrough is Albert's inverse-design / ML optimization capability. A model session ties
together the models produced from a single dataset
(BTDataset) in one modeling run. The
individual models are represented by BTModel and managed through
BTModelSessionCollection and
BTModelCollection.
Example
Show JSON schema:
{
"$defs": {
"AuditFields": {
"description": "The audit fields for a resource",
"properties": {
"by": {
"default": null,
"title": "By",
"type": "string"
},
"byName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Byname"
},
"at": {
"anyOf": [
{
"format": "date-time",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "At"
}
},
"title": "AuditFields",
"type": "object"
},
"BTModelRegistry": {
"description": "Build logs and metrics recorded for a model session.",
"properties": {
"BuildLogs": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Free-form logs captured while the session's models were built.",
"title": "Buildlogs"
},
"Metrics": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Free-form performance metrics recorded for the session's models.",
"title": "Metrics"
}
},
"title": "BTModelRegistry",
"type": "object"
},
"BTModelSessionCategory": {
"description": "Who built a Breakthrough model session.\n\nAttributes\n----------\nUSER_MODEL : str\n A session built by a user.\nALBERT_MODEL : str\n A session built automatically by Albert.",
"enum": [
"userModel",
"albertModel"
],
"title": "BTModelSessionCategory",
"type": "string"
},
"Status": {
"description": "The status of a resource.\n\nAttributes\n----------\nACTIVE : str\n The resource is fully operational and visible in normal operations.\nINACTIVE : str\n The resource is hidden from normal operations and disabled from use.",
"enum": [
"active",
"inactive"
],
"title": "Status",
"type": "string"
}
},
"description": "A parent session grouping a related set of Breakthrough models.\n\nAlbert Breakthrough is Albert's inverse-design / ML optimization capability. A model session ties\ntogether the models produced from a single dataset\n([`BTDataset`][albert.resources.btdataset.BTDataset]) in one modeling run. The\nindividual models are represented by [`BTModel`][albert.resources.btmodel.BTModel] and managed through\n[`BTModelSessionCollection`][albert.collections.btmodel.BTModelSessionCollection] and\n[`BTModelCollection`][albert.collections.btmodel.BTModelCollection].\n\n!!! example\n ```python\n from albert.resources.btmodel import BTModelSession, BTModelSessionCategory\n\n session = BTModelSession(\n name=\"Tensile strength study\",\n category=BTModelSessionCategory.USER_MODEL,\n dataset_id=\"DST1\",\n )\n ```",
"properties": {
"status": {
"anyOf": [
{
"$ref": "#/$defs/Status"
},
{
"type": "null"
}
],
"default": null,
"description": "The status of the resource, optional."
},
"Created": {
"anyOf": [
{
"$ref": "#/$defs/AuditFields"
},
{
"type": "null"
}
],
"default": null,
"description": "Audit fields for the creation of the resource, optional."
},
"Updated": {
"anyOf": [
{
"$ref": "#/$defs/AuditFields"
},
{
"type": "null"
}
],
"default": null,
"description": "Audit fields for the update of the resource, optional."
},
"name": {
"description": "Human-readable name of the session.",
"title": "Name",
"type": "string"
},
"category": {
"$ref": "#/$defs/BTModelSessionCategory",
"description": "Whether the session was built by a user or by Albert."
},
"id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Unique identifier of the session (format ``MDS...``). Assigned by Albert on creation.",
"title": "Id"
},
"datasetId": {
"description": "Identifier of the dataset the session's models are built from (format ``DST...``).",
"title": "Datasetid",
"type": "string"
},
"defaultModel": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Name of the session's default model, if one is designated.",
"title": "Defaultmodel"
},
"totalTime": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Total time taken to build the session, if recorded.",
"title": "Totaltime"
},
"modelCount": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "Number of models contained in the session, if reported.",
"title": "Modelcount"
},
"target": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "The target variable(s) the session's models predict.",
"title": "Target"
},
"Registry": {
"anyOf": [
{
"$ref": "#/$defs/BTModelRegistry"
},
{
"type": "null"
}
],
"default": null,
"description": "Build logs and metrics recorded for the session."
},
"albertModelDetails": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Details specific to an Albert-built session, when applicable.",
"title": "Albertmodeldetails"
},
"flag": {
"default": false,
"description": "Boolean marker on the session. Defaults to False.",
"title": "Flag",
"type": "boolean"
}
},
"required": [
"name",
"category",
"datasetId"
],
"title": "BTModelSession",
"type": "object"
}
Fields:
-
status(Status | None) -
created(AuditFields | None) -
updated(AuditFields | None) -
name(str) -
category(BTModelSessionCategory) -
id(BTModelSessionId | None) -
dataset_id(BTDatasetId) -
default_model(str | None) -
total_time(str | None) -
model_count(int | None) -
target(list[str] | None) -
registry(BTModelRegistry | None) -
albert_model_details(dict[str, Any] | None) -
flag(bool)
id: BTModelSessionId | None = None
Unique identifier of the session (format MDS...). Assigned by Albert on creation.
dataset_id: BTDatasetId
Identifier of the dataset the session's models are built from (format DST...).
default_model: str | None = None
Name of the session's default model, if one is designated.
Details specific to an Albert-built session, when applicable.
Progress state of a Breakthrough model build.
Attributes:
| Name | Type | Description |
|---|---|---|
QUEUED |
str
|
The build has been queued but has not started. |
BUILDING_MODELS |
str
|
Models are being trained. |
GENERATING_CANDIDATES |
str
|
Candidate solutions are being generated. |
COMPLETE |
str
|
The build has finished successfully. |
ERROR |
str
|
The build failed. |
Bases: BaseResource
A single trained Breakthrough model.
Albert Breakthrough is Albert's inverse-design / ML optimization capability. A model can belong to a
parent session (BTModelSession), in which case parent_id is set to
the session ID, or be a detached, standalone model. Models are managed through
BTModelCollection.
Show JSON schema:
{
"$defs": {
"AuditFields": {
"description": "The audit fields for a resource",
"properties": {
"by": {
"default": null,
"title": "By",
"type": "string"
},
"byName": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Byname"
},
"at": {
"anyOf": [
{
"format": "date-time",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "At"
}
},
"title": "AuditFields",
"type": "object"
},
"BTModelState": {
"description": "Progress state of a Breakthrough model build.\n\nAttributes\n----------\nQUEUED : str\n The build has been queued but has not started.\nBUILDING_MODELS : str\n Models are being trained.\nGENERATING_CANDIDATES : str\n Candidate solutions are being generated.\nCOMPLETE : str\n The build has finished successfully.\nERROR : str\n The build failed.",
"enum": [
"Queued",
"Building Models",
"Generating Candidates",
"Complete",
"Error"
],
"title": "BTModelState",
"type": "string"
},
"BTModelType": {
"description": "Whether a model belongs to a session or stands alone.\n\nAttributes\n----------\nSESSION : str\n A model that belongs to a parent model session.\nDETACHED : str\n A standalone model with no parent session.",
"enum": [
"Session",
"Detached"
],
"title": "BTModelType",
"type": "string"
},
"Status": {
"description": "The status of a resource.\n\nAttributes\n----------\nACTIVE : str\n The resource is fully operational and visible in normal operations.\nINACTIVE : str\n The resource is hidden from normal operations and disabled from use.",
"enum": [
"active",
"inactive"
],
"title": "Status",
"type": "string"
}
},
"description": "A single trained Breakthrough model.\n\nAlbert Breakthrough is Albert's inverse-design / ML optimization capability. A model can belong to a\nparent session ([`BTModelSession`][albert.resources.btmodel.BTModelSession]), in which case ``parent_id`` is set to\nthe session ID, or be a detached, standalone model. Models are managed through\n[`BTModelCollection`][albert.collections.btmodel.BTModelCollection].\n\n!!! example\n ```python\n from albert.resources.btmodel import BTModel\n\n model = BTModel(name=\"Random forest v1\")\n ```",
"properties": {
"status": {
"anyOf": [
{
"$ref": "#/$defs/Status"
},
{
"type": "null"
}
],
"default": null,
"description": "The status of the resource, optional."
},
"Created": {
"anyOf": [
{
"$ref": "#/$defs/AuditFields"
},
{
"type": "null"
}
],
"default": null,
"description": "Audit fields for the creation of the resource, optional."
},
"Updated": {
"anyOf": [
{
"$ref": "#/$defs/AuditFields"
},
{
"type": "null"
}
],
"default": null,
"description": "Audit fields for the update of the resource, optional."
},
"name": {
"description": "Human-readable name of the model.",
"title": "Name",
"type": "string"
},
"id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Unique identifier of the model (format ``MDL...``). Assigned by Albert on creation.",
"title": "Id"
},
"datasetId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Identifier of the dataset the model is built from (format ``DST...``).",
"title": "Datasetid"
},
"parentId": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Identifier of the parent session (format ``MDS...``), or None if the model is detached.",
"title": "Parentid"
},
"Metadata": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Free-form metadata associated with the model.",
"title": "Metadata"
},
"type": {
"anyOf": [
{
"$ref": "#/$defs/BTModelType"
},
{
"type": "null"
}
],
"default": null,
"description": "Whether the model belongs to a session or is detached."
},
"state": {
"anyOf": [
{
"$ref": "#/$defs/BTModelState"
},
{
"type": "null"
}
],
"default": null,
"description": "Current progress state of the model build."
},
"target": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "The target variable(s) the model predicts.",
"title": "Target"
},
"startTime": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "When the model build started, if recorded.",
"title": "Starttime"
},
"endTime": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "When the model build finished, if recorded.",
"title": "Endtime"
},
"totalTime": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Total time taken to build the model, if recorded.",
"title": "Totaltime"
},
"modelBinaryKey": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Storage key for the trained model artifact, if applicable.",
"title": "Modelbinarykey"
},
"flag": {
"default": false,
"description": "Boolean marker on the model. Defaults to False.",
"title": "Flag",
"type": "boolean"
}
},
"required": [
"name"
],
"title": "BTModel",
"type": "object"
}
Fields:
-
status(Status | None) -
created(AuditFields | None) -
updated(AuditFields | None) -
name(str) -
id(BTModelId | None) -
dataset_id(BTDatasetId | None) -
parent_id(BTModelSessionId | None) -
metadata(dict[str, Any] | None) -
type(BTModelType | None) -
state(BTModelState | None) -
target(list[str] | None) -
start_time(str | None) -
end_time(str | None) -
total_time(str | None) -
model_binary_key(str | None) -
flag(bool)
id: BTModelId | None = None
Unique identifier of the model (format MDL...). Assigned by Albert on creation.
dataset_id: BTDatasetId | None = None
Identifier of the dataset the model is built from (format DST...).
parent_id: BTModelSessionId | None = None
Identifier of the parent session (format MDS...), or None if the model is detached.
model_binary_key: str | None = None
Storage key for the trained model artifact, if applicable.