DataSetStats<T, TInput, TOutput>

Models & Types · AiDotNet.Models

Represents a comprehensive collection of statistical measures and data for evaluating model performance on a dataset.

For Beginners

This class stores all the statistics and data needed to evaluate how well a model performs.

When evaluating a model’s performance:

  • You need to measure different aspects of accuracy and error
  • You want to compare actual values with predicted values
  • You need to keep track of the input data that produced the predictions

This class stores all that information, including:

  • Various error measurements (how far predictions are from actual values)
  • Basic statistics about both actual values and predictions
  • Statistics about prediction quality (how well the model captures patterns)
  • The actual input features, target values, and model predictions

Having all this information in one place makes it easier to analyze model performance, create visualizations, and compare different models.

How It Works

This class encapsulates various statistical measures and the actual data used to evaluate a model’s performance on a specific dataset. It includes error statistics that quantify prediction errors, basic statistics for both actual and predicted values, prediction quality statistics, and the raw data including features, actual values, and predicted values. This comprehensive collection of information allows for thorough analysis of model performance on the dataset.

Constructors

Constructor Summary
DataSetStats() Initializes a new instance of the DataSetStats class with default empty model data.

Properties

Property Summary
BasicStats<T> ActualBasicStats { get; set; } Gets or sets the basic descriptive statistics for the actual target values.
BasicStats<T> PredictedBasicStats { get; set; } Gets or sets the basic descriptive statistics for the predicted values.
ErrorStats<T> ErrorStats { get; set; } Gets or sets the error statistics for the model’s predictions.
PredictionStats<T> PredictionStats { get; set; } Gets or sets the prediction quality statistics for the model.
RobustnessStats<T> RobustnessStats { get; set; } Gets or sets adversarial robustness diagnostics for the dataset.
TInput Features { get; set; } Gets or sets the input features.
TOutput Actual { get; set; } Gets or sets the actual target values.
TOutput Predicted { get; set; } Gets or sets the predicted values.
UncertaintyStats<T> UncertaintyStats { get; set; } Gets or sets uncertainty quantification diagnostics for the dataset.
bool IsDataProvided { get; set; } Gets or sets a value indicating whether data was actually provided for this dataset.