AgentSelectorWorker

from AID.selector.interface import AgentSelectorWorker

Step 17: Champion Promotion (The Executive Decision). The final gate of the pipeline. This method aggregates evidence from the Prediction, Comparison, and Transition steps to officially promote one agent as the ‘Champion.’ It locks the winning model’s state and generates a SHAP-based explainability report for audit purposes.

Parameters

inputs : AgentSelectorInput

Custom selection configuration. If None, resolves from ‘test.ml’ state.

**kwargs : dict

Additional parameters passed to the Selector worker.

Inputs full schema can be obtained by ctx.workers.agent_selector.spec with main params:

`inputs == None`	→	pipeline data context
`data != None`	→	custom data for agent_selector overview and choice

Returns

AgentSelectorWorker

The populated instance of AgentSelectorWorker.

Populates attributes into the worker context:

`model`	→	ctx.workers.agent_selector
`inputs`	→	ctx.workers.agent_selector.spec
`result`	→	ctx.workers.agent_selector.result
`state`	→	ctx.workers.agent_selector.state
`report`	→	ctx.workers.agent_selector.report
`stats`	→	ctx.workers.agent_selector.stats
`fitter`	→	ctx.workers.agent_selector.fitter

Registers data into the datasets context:

`predictions`	→	predictions.train.champion_agent
`predictions`	→	predictions.test.champion_agent
`features`	→	features.champion_agent.predicted
`features`	→	features.champion_agent.selected
`dropped`	→	features.champion_agent.dropped
`stats`	→	stats.agents.champion_agent
`stats`	→	stats.agents.selection

Examples

Defining the Project Context (Control Plane) & Project Scope:

import aidflow as aid

ctx = aid.ProjectContext()

ctx.genesis(
    project      = 'test',
    input_data   = 'test.csv',
    target       = 'target',
    yy_mm        = 'decision_date',
    yy_mm_format = '%Y-%m-%d'
)
ctx.params()

Worker → Model → Fitter

Accessing worker’s inputs schema → parameters & types (shown in the display output):

ctx.workers.agent_selector.spec

Accessing model’s fitter options and schema → parameters & types (shown in the display output):

ctx.workers.agent_selector.fitters

Executing workers with defaults → auto provided by the context:

ctx.flow.process('data')        # 1. process workers 0-3 → data load - data stability
ctx.flow.process('encoding')    # 2. process workers 4-9 → train and apply encoding to train and test samples
ctx.flow.process('training')    # 3. process workers 10-13 → agents trainining on encoded train sample
ctx.workers.agents_comparator() # 4. process agents comparator on test sample to obtain assessment for selection
ctx.workers.agent_selector()    # 5. champion agent selection

Once worker has been executed, thus its main model has been built, we have access to all populated attributes.

worker   = ctx.workers.agent_selector
inputs   = worker.spec.inputs
result   = worker.result
state    = worker.state
features = worker.features
params   = worker.params
stats    = worker.stats
fitter   = worker.fitter  # jump to chosen internal fitter
...

View to model report of executed worker:

ctx.workers.agent_selector.report.show()

Model → Fitter

Once worker has been executed, we can obtain internal fitter state and its parametrization (shown in the display output):

ctx.workers.agent_selector.fitter

The fitted fitter provides all populated attributes.

fitter    = ctx.workers.agent_selector.fitter
params_   = fitter.params
stats_    = fitter.stats

Direct choice and parametrization of internal fitter:

fx  = ctx.workers.agent_selector.fitters[0]
prm = dict(
    alpha = 0.05,
    proba_bins = 15,
    agent_choice = 1
)
agent_selector = ctx.workers.agent_selector(fx_choice = fx, fx_params = prm)

In the experimenting phase, when various parametrization settings might be under testing (note that internal fitter API (fx_config) can vary with respect to chosen fitter):

cfg = dict(
    target = 'target2',
    preprocess = True
)
agent_selector = ctx.workers.agent_selector(fx_config = cfg)

Attributes

All worker attributes return None prior its execution.

Attribute	Type	Description
`inputs`	`ModelInput`	Registered populated inputs containing execution timestamps and feature definitions.
`result`	`ModelResult`	Execution output payload containing model predictions and fit results.
`fitter`	`Fitter`	Underlying fitted estimator instance.
`state`	`ModelState`	Consolidated model state (fitter, choice, params, features, report, stats).
`report`	`DashboardInterface`	Interactive report interface. Call `report.show()` to render the visualization dashboard.
`stats`	`FitStats`	Performance metrics and training metadata gathered during fitting.
`features`	`TransResCols`	Feature schema dataclass required for downstream inference.
`params`	`tuple[FitParams, Parameters, ...]`	Tuple of fit settings, execution parameters, optionally transformer parameters.
`choice`	`RegGet.Choice`	Active configuration parameters including internal fitter choice (`fx_choice`).
`model_signature`	`str`	Unique hash identifier for the fitted model instance.

Execution Interface

Data Interface

Encoding Interface

Training Interface

Selection Interface

Inference Interface

Parameters

Returns

Examples

Worker → Model → Fitter

Model → Fitter

Attributes

​Parameters

​Returns

​Examples

​Worker → Model → Fitter

​Model → Fitter

​Attributes

Parameters

Returns

Examples

Worker → Model → Fitter

Model → Fitter

Attributes