abacusai.model_metrics
Module Contents
Classes
Metrics of the trained model. |
- class abacusai.model_metrics.ModelMetrics(client, algoMetrics=None, selectedAlgorithm=None, modelId=None, modelVersion=None, metricNames=None, targetColumn=None, trainValTestSplit=None, trainingCompletedAt=None, baselineMetrics=None)
Bases:
abacusai.return_class.AbstractApiClass
Metrics of the trained model.
- Parameters:
client (ApiClient) – An authenticated API Client instance
algoMetrics (dict) – Dictionary mapping algorithm ID to algorithm name and algorithm metrics dictionary
selectedAlgorithm (str) – The algorithm ID of the selected (default) algorithm that will be used in deployments of this Model Version
modelId (str) – The Model ID
modelVersion (str) – The Model Version
metricNames (dict) – Maps shorthand names of the metrics to their verbose names
targetColumn (str) – The target feature that the model was trained to predict
trainValTestSplit (dict) – Info on train, val and test split
trainingCompletedAt (datetime) – Timestamp when training was completed
baselineMetrics (dict) – Key/value pairs of the baseline model metrics and their values
- __repr__()
Return repr(self).