---
title: MLClassifierMetrics
framework: createml
role: symbol
role_heading: Structure
path: createml/mlclassifiermetrics
---

# MLClassifierMetrics

Metrics you use to evaluate a classifier’s performance.

## Declaration

```swift
struct MLClassifierMetrics
```

## Mentioned in

Creating a text classifier model Creating an Image Classifier Model Improving Your Model’s Accuracy

## Overview

Overview Use MLClassifierMetrics to evaluate your model’s ability to distinguish between different categories when it’s classifying data. You can determine the model’s accuracy using the classificationError metric. For information about how your model is mislabeling or missing a certain category, use the precisionRecall metric. To determine specific cases where your model is mistaking one label for another, use the confusion property. Accuracy can be a misleading metric if you use unbalanced data, which means the number of examples for some categories are much larger than others. Instead, use precisionRecall or confusion. note: Each trained model contains different metrics for its various data sets (training, validation, and testing). Improving Your Model’s Accuracy compares these metrics between different data sets.

## Topics

### Understanding the model

- [classificationError](createml/mlclassifiermetrics/classificationerror.md)
- [precisionRecall](createml/mlclassifiermetrics/precisionrecall.md)
- [confusion](createml/mlclassifiermetrics/confusion.md)
- [confusionDataFrame](createml/mlclassifiermetrics/confusiondataframe.md)
- [precisionRecallDataFrame](createml/mlclassifiermetrics/precisionrecalldataframe.md)

### Handling errors

- [isValid](createml/mlclassifiermetrics/isvalid.md)
- [error](createml/mlclassifiermetrics/error.md)

### Creating metrics

- [init(classificationError:confusion:precisionRecall:)](createml/mlclassifiermetrics/init(classificationerror:confusion:precisionrecall:).md)

### Describing metrics

- [description](createml/mlclassifiermetrics/description.md)
- [debugDescription](createml/mlclassifiermetrics/debugdescription.md)
- [playgroundDescription](createml/mlclassifiermetrics/playgrounddescription.md)

### Default Implementations

- [CustomDebugStringConvertible Implementations](createml/mlclassifiermetrics/customdebugstringconvertible-implementations.md)
- [CustomPlaygroundDisplayConvertible Implementations](createml/mlclassifiermetrics/customplaygrounddisplayconvertible-implementations.md)
- [CustomStringConvertible Implementations](createml/mlclassifiermetrics/customstringconvertible-implementations.md)

## Relationships

### Conforms To

- [Copyable](swift/copyable.md)
- [CustomDebugStringConvertible](swift/customdebugstringconvertible.md)
- [CustomPlaygroundDisplayConvertible](swift/customplaygrounddisplayconvertible.md)
- [CustomStringConvertible](swift/customstringconvertible.md)
- [Escapable](swift/escapable.md)

## See Also

### Model accuracy

- [Improving Your Model’s Accuracy](createml/improving-your-model-s-accuracy.md)
- [MLRegressorMetrics](createml/mlregressormetrics.md)
- [MLWordTaggerMetrics](createml/mlwordtaggermetrics.md)
- [MLRecommenderMetrics](createml/mlrecommendermetrics.md)
- [MLObjectDetectorMetrics](createml/mlobjectdetectormetrics.md)