ModelStats<T, TInput, TOutput>

Models & Types · AiDotNet.Statistics

Represents a collection of statistical metrics for evaluating and analyzing machine learning models.

For Beginners

Think of ModelStats as a report card for your AI model.

Just like a school report card shows how well a student is doing in different subjects, ModelStats shows how well your AI model is performing in different areas. It helps you:

  • Understand how accurate your model’s predictions are
  • See which features (inputs) are most important
  • Check if your model is too simple or too complex
  • Compare your model’s performance to simpler alternatives

This information helps you improve your model and decide if it’s ready to use in real-world situations.

How It Works

This class calculates and stores various statistical measures that help assess the performance, fit, and characteristics of a machine learning model. It includes metrics for model accuracy, feature importance, model complexity, and various distance and similarity measures.

Properties

Property Summary
Dictionary<string, TOutput> FeatureValues { get; set; } Gets a dictionary mapping feature names to their values.
IFullModel<T, TInput, TOutput> Model { get; } Gets the full model being evaluated.
List<T> LeaveOneOutPredictiveDensities { get; set; }
List<T> PosteriorPredictiveSamples { get; set; }
List<T> VIFList { get; set; }
List<string> FeatureNames { get; set; } Gets the names of the features used in the model.
Matrix<T> CorrelationMatrix { get; set; }
Matrix<T> CovarianceMatrix { get; set; }
T CalinskiHarabaszIndex { get; set; }
T ConditionNumber { get; set; }
T CosineSimilarity { get; set; }
T DaviesBouldinIndex { get; set; }
T EffectiveNumberOfParameters { get; set; }
T EuclideanDistance { get; set; }
T HammingDistance { get; set; }
T JaccardSimilarity { get; set; }
T LogLikelihood { get; set; }
T LogPointwisePredictiveDensity { get; set; }
T MahalanobisDistance { get; set; }
T ManhattanDistance { get; set; }
T MarginalLikelihood { get; set; }
T MeanAveragePrecision { get; set; }
T MeanReciprocalRank { get; set; }
T MutualInformation { get; set; }
T NormalizedDiscountedCumulativeGain { get; set; }
T NormalizedMutualInformation { get; set; }
T ObservedTestStatistic { get; set; }
T ReferenceModelMarginalLikelihood { get; set; }
T SilhouetteScore { get; set; }
T VariationOfInformation { get; set; }
TInput Features { get; } Gets the feature values used in the model.
TOutput Actual { get; } Gets the actual (observed) values from the dataset.
TOutput Predicted { get; } Gets the predicted values from the model.
Vector<T> AutoCorrelationFunction { get; set; } Gets the Auto-Correlation Function, which measures the correlation between a time series and a lagged version of itself.
Vector<T> PartialAutoCorrelationFunction { get; set; } Gets the Partial Auto-Correlation Function, which measures the direct relationship between an observation and its lag.
int FeatureCount { get; set; } Gets the number of features (input variables) used in the model.

Methods

Method Summary
ModelStats<T, TInput, TOutput> Empty() Creates an empty instance of the ModelStats<T> class.
T GetMetric(MetricType metricType) Retrieves the value of a specific metric.
bool HasMetric(MetricType metricType) Checks if a specific metric is available in this ModelStats instance.