Class TextClassificationModelMetrics
Model level text classification metrics
Inherited Members
Namespace: Oci.AilanguageService.Models
Assembly: OCI.DotNetSDK.Ailanguage.dll
Syntax
public class TextClassificationModelMetrics
Properties
Accuracy
Declaration
[Required(ErrorMessage = "Accuracy is required.")]
[JsonProperty(PropertyName = "accuracy")]
public float? Accuracy { get; set; }
Property Value
Type | Description |
---|---|
float? | The fraction of the labels that were correctly recognised . |
Remarks
Required
MacroF1
Declaration
[Required(ErrorMessage = "MacroF1 is required.")]
[JsonProperty(PropertyName = "macroF1")]
public float? MacroF1 { get; set; }
Property Value
Type | Description |
---|---|
float? | F1-score, is a measure of a model\u2019s accuracy on a dataset |
Remarks
Required
MacroPrecision
Declaration
[Required(ErrorMessage = "MacroPrecision is required.")]
[JsonProperty(PropertyName = "macroPrecision")]
public float? MacroPrecision { get; set; }
Property Value
Type | Description |
---|---|
float? | Precision refers to the number of true positives divided by the total number of positive predictions (i.e., the number of true positives plus the number of false positives) |
Remarks
Required
MacroRecall
Declaration
[Required(ErrorMessage = "MacroRecall is required.")]
[JsonProperty(PropertyName = "macroRecall")]
public float? MacroRecall { get; set; }
Property Value
Type | Description |
---|---|
float? | Measures the model's ability to predict actual positive classes. It is the ratio between the predicted true positives and what was actually tagged. The recall metric reveals how many of the predicted classes are correct. |
Remarks
Required
MicroF1
Declaration
[Required(ErrorMessage = "MicroF1 is required.")]
[JsonProperty(PropertyName = "microF1")]
public float? MicroF1 { get; set; }
Property Value
Type | Description |
---|---|
float? | F1-score, is a measure of a model\u2019s accuracy on a dataset |
Remarks
Required
MicroPrecision
Declaration
[Required(ErrorMessage = "MicroPrecision is required.")]
[JsonProperty(PropertyName = "microPrecision")]
public float? MicroPrecision { get; set; }
Property Value
Type | Description |
---|---|
float? | Precision refers to the number of true positives divided by the total number of positive predictions (i.e., the number of true positives plus the number of false positives) |
Remarks
Required
MicroRecall
Declaration
[Required(ErrorMessage = "MicroRecall is required.")]
[JsonProperty(PropertyName = "microRecall")]
public float? MicroRecall { get; set; }
Property Value
Type | Description |
---|---|
float? | Measures the model's ability to predict actual positive classes. It is the ratio between the predicted true positives and what was actually tagged. The recall metric reveals how many of the predicted classes are correct. |
Remarks
Required
WeightedF1
Declaration
[JsonProperty(PropertyName = "weightedF1")]
public float? WeightedF1 { get; set; }
Property Value
Type | Description |
---|---|
float? | F1-score, is a measure of a model\u2019s accuracy on a dataset |
WeightedPrecision
Declaration
[JsonProperty(PropertyName = "weightedPrecision")]
public float? WeightedPrecision { get; set; }
Property Value
Type | Description |
---|---|
float? | Precision refers to the number of true positives divided by the total number of positive predictions (i.e., the number of true positives plus the number of false positives) |
WeightedRecall
Declaration
[JsonProperty(PropertyName = "weightedRecall")]
public float? WeightedRecall { get; set; }
Property Value
Type | Description |
---|---|
float? | Measures the model's ability to predict actual positive classes. It is the ratio between the predicted true positives and what was actually tagged. The recall metric reveals how many of the predicted classes are correct. |