<!--
{
  "availability" : [
    "iOS: 15.0.0 -",
    "iPadOS: 15.0.0 -",
    "macCatalyst: 15.0.0 -",
    "macOS: 12.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateML",
  "identifier" : "/documentation/CreateML/MLHandActionClassifier/DataSource/labeledFiles(at:)",
  "metadataVersion" : "0.1.0",
  "role" : "Case",
  "symbol" : {
    "kind" : "Case",
    "modules" : [
      "Create ML"
    ],
    "preciseIdentifier" : "s:8CreateML22MLHandActionClassifierV10DataSourceO12labeledFilesyAE10Foundation3URLV_tcAEmF"
  },
  "title" : "MLHandActionClassifier.DataSource.labeledFiles(at:)"
}
-->

# MLHandActionClassifier.DataSource.labeledFiles(at:)

Creates a data source from a folder that contains videos, each named after the hand action they represent.

```
case labeledFiles(at: URL)
```

## Parameters

`at`

The URL to a folder in the file system that contains folders of hand action videos. The data source
uses each file’s name before the first period as its classification label.

## Discussion

Create a hand action data source from a directory of videos with the `labeledFiles` case. You must name
each video file with a hand action label, followed by a period and an arbitrary string, ending with the
video file’s extension. For example, you can name a hand action classifier’s training files `Wave.3.mov`,
`MoveCloser.1.mov`, `MoveCloser.2.mov`, and so on.

In this example, a hand action classifier would have at least two class labels:

- `Wave`
- `MoveCloser`

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)