Static Accuracy
Score a static model on new labeled rows for selected target columns and metrics.
Scores a static twin's predictions against the truth already in the rows.
The static counterpart of ScoreForecast: no time axis and no lead times, so the cuts are by column rather than by horizon. Unconnected, it scores the twin's own holdout rather than rows from the flow.
At a glance
Module type
StaticAccuracy
Category
Intelligence
Default tier
reactive
Runs on
reactive, durable
Starts a flow
no
Holds a body
no
Keeps state between runs
no
Available in
every application type
Parameters
digitalTwinId
string · required · defaults to ""
The static twin to score.
digitalTwinName
string · optional
Its name when it was chosen, for the node's label.
digitalTwinVersionIds
string[] · required · defaults to []
Pin the scoring to specific twin versions; empty means the latest.
targetColumns
string[] · required · defaults to []
The columns whose predictions are scored.
metrics
string[] · required · defaults to []
Which accuracy metrics to compute.
primaryMetric
string · optional · defaults to ""
The one a KPI tile reads; must be in metrics.
primaryTarget
string · optional · defaults to ""
The target column a KPI tile reads; must be in targetColumns.
Inputs
on
event
no
Implicit on every module that does not itself start a flow: wire an event here to make this module the start of what that event runs.
features
dataframe
no
Rows to score; unconnected, the twin's holdout is used.
Outputs
comparison
dataframe
dataframe, signal
One row per case: predicted beside actual.
byVariable
dataframe
dataframe, signal
Accuracy per target column.
metrics
dataframe
dataframe, signal
Every scoring this module has run, newest last.
summary
dataframe
dataframe, signal
The latest scoring alone, for a KPI tile.
Last updated