UnsupervisedAutoMLBase<T>
Base Classes ยท AiDotNet.AutoML
Base class for unsupervised AutoML search strategies (e.g., clustering AutoML, grid search).
Known derived types: ClusteringAutoML<T>, ClusteringGridSearch<T>
For Beginners
This is the foundation for tools that automatically find the best clustering algorithm and parameters for your data โ without needing labeled examples.
How It Works
Unlike supervised AutoML (which extends AutoMLModelBase),
unsupervised AutoML operates on unlabeled data. This base class provides common infrastructure
for unsupervised search strategies: trial tracking, metric optimization, search space management,
and early stopping.
Properties
| Property | Summary |
|---|---|
ClusteringMetricType PrimaryMetricType { get; set; } |
Gets or sets the primary evaluation metric type. |
TimeSpan TimeLimit { get; set; } |
Gets or sets the time limit for the search. |
bool HigherIsBetter { get; } |
Gets whether higher metric values are better (derived from the metric type). |
double BestScore { get; set; } |
Gets the best score achieved during the search. |
int MaxTrials { get; set; } |
Gets or sets the maximum number of trials to run. |
int TrialsEvaluated { get; set; } |
Gets the total number of trials evaluated. |
string PrimaryMetric { get; } |
Gets the primary metric name for evaluation dictionary lookups. |