创建一个学习模型并使用

参考自苹果官方文档
新建一个data.json 其内容如下

[
    {
        "tokens": ["AirPods", "are", "a", "fantastic", "Apple", "product", "."],
        "labels": ["PROD", "NONE", "NONE", "NONE", "ORG", "NONE", "NONE"]
    },
    {
        "tokens": ["The", "iPhone", "takes", "stunning", "photos", "."],
        "labels": ["NONE", "PROD", "NONE", "NONE", "NONE", "NONE"]
    },
    {
        "tokens": ["Start", "building", "a", "native", "Mac", "app", "from", "your", "current", "iPad", "app", "using", "Mac", "Catalyst", "."],
        "labels": ["NONE", "NONE", "NONE", "NONE", "PROD", "NONE", "NONE", "NONE", "NONE", "PROD", "NONE", "NONE", "PROD", "PROD", "NONE"]
    }
]

创建学习模型

    import NaturalLanguage
    import CreateML
    import CoreML

    // 这个路径是上边创建的json文件的路径
    let url =  URL(fileURLWithPath:"/Users/a111/Desktop/NLP/NLP/data.json")
    let data = try! MLDataTable(contentsOf: url)
    let (trainingData, testingData) = data.randomSplit(by: 0.8, seed: 5)
    let wordTagger = try! MLWordTagger(trainingData: trainingData,
                                 tokenColumn: "tokens",
                                 labelColumn: "labels")
    // Training accuracy as a percentage
    let trainingAccuracy = (1.0 - wordTagger.trainingMetrics.taggingError) * 100
    // Validation accuracy as a percentage
    let validationAccuracy = (1.0 - wordTagger.validationMetrics.taggingError) * 100
    let evaluationMetrics = wordTagger.evaluation(on: testingData,
                                                  tokenColumn: "tokens",
                                                  labelColumn: "labels")
    let evaluationAccuracy = (1.0 - evaluationMetrics.taggingError) * 100
    let metadata = MLModelMetadata(author: "Jane Appleseed",
                                   shortDescription: "A model trained to tag Apple products.",
                                   version: "1.0")
    // 这个路径是模型文件的导出路径
    try! wordTagger.write(to: URL(fileURLWithPath: "/Users/a111/Desktop/AppleTagger.mlmodel"),
                                  metadata: metadata)

将上面导出的模型文件拖入到项目中

使用学习模型

     let text = "The iPad is my favorite Apple product."

    do {
        let mlModel = try AppleTagger(configuration: MLModelConfiguration()).model

        let customModel = try NLModel(mlModel: mlModel)
        let customTagScheme = NLTagScheme("Apple")

        let tagger = NLTagger(tagSchemes: [.nameType, customTagScheme])
        tagger.string = text
        tagger.setModels([customModel], forTagScheme: customTagScheme)

        tagger.enumerateTags(in: text.startIndex..<text.endIndex, unit: .word,
                             scheme: customTagScheme, options: .omitWhitespace) { tag, tokenRange  in
            if let tag = tag {
                print("\(text[tokenRange]): \(tag.rawValue)")
            }
            return true
        }
    } catch {
        print(error)
    }

控制台输出

The: NONE
iPad: PROD
is: NONE
my: NONE
favorite: NONE
Apple: NONE
product: NONE
.: NONE
Program ended with exit code: 0