Repository files navigation

An example of how to use CreateML and Xcode 10to train a CoreML model that is used by the Natural Language frameworkto classify the programming language of source code.

letcode="""struct Plane: Codable {    var manufacturer: String    var model: String    var seats: Int}"""leturl=Bundle.main.url(forResource:"Classifier",                          withExtension:"mlmodelc")!letmodel=try!NLModel(contentsOf: url)model.predictedLabel(for: code) // Swift

• macOS Mojave Beta
• Xcode 10 Beta

These are available for Apple Developer account members to downloadathttps://developer.apple.com/download/

This project includes a pre-trained programming language classifier model.To see it in action, openClassifier Demo.playground,run the playground with the Assistant editor showing the Live View,and then drag and drop a source code file.The model will predict the language of the file based on its contents.

• Clone and setup the repository by running the following commands:

$ git clone https://github.com/flight-school/Programming-Language-Classifier.git`$ cd Programming-Language-Classifier$ git submodule update --init

• OpenTrainer.swift in an editor and fill in the placeholder valuesfordestinationPath andcorpusPath:

$ open ./Trainer.swift

• RunTrainer.swift and wait for the model to be trained(on a 2017 MacBook Pro, this took a few minutes):

$ swift ./Trainer.swift

• Compile the generated.mlmodel bundle using the following command:

$ xcrun coremlc compile path/to/ProgrammingLanguageClassifier.mlmodel .

• Move the compiled.mlmodelc bundle into the Resources directoryofClassifier Demo.playground, replacing any existing resource.

MIT

Seecode-corporafor licensing information of the included projects.

Flight School is a new book series for Swift developers.Each month, we'll explore an essential part ofiOS, macOS, and Swift development through concise, focused books.

If you'd like to get in touch,feel free to message us on Twitter(@flightdotschool)or email us atmailto:info@flight.school.