---
title: "evaluation(on:featureColumns:labelColumn:recordingFileColumn:)"
framework: Create ML
role: symbol
role_heading: Instance Method
platforms: [macOS 10.15+]
path: "createml/mlactivityclassifier/evaluation(on:featurecolumns:labelcolumn:recordingfilecolumn:)"
---

# evaluation(on:featureColumns:labelColumn:recordingFileColumn:)

Generates metrics describing the activity classifier’s performance on labeled activities in a data source.

## Declaration

```swift
func evaluation(on testingData: MLActivityClassifier.DataSource, featureColumns: [String], labelColumn: String? = nil, recordingFileColumn: String? = nil) -> MLClassifierMetrics
```

## Parameters

- `testingData`: The activity data that you provide to test this model, contained in an doc://com.apple.createml/documentation/CreateML/MLActivityClassifier/DataSource.
- `featureColumns`: The names of the columns that contain sensor data.
- `labelColumn`: The name of the column that contain the activity labels. The method ignores this parameter if the data source uses a labeled directory.
- `recordingFileColumn`: The name of the column that contain the recording file names. The method ignores this parameter if the data source uses a labeled directory.

## Return Value

Return Value An MLClassifierMetrics instance.

## See Also

### Evaluating an activity classifier

- [trainingMetrics](createml/mlactivityclassifier/trainingmetrics.md)
- [validationMetrics](createml/mlactivityclassifier/validationmetrics.md)