Spark MLlib不支持KNNClassifier

非常抱歉，你是正确的。Spark MLlib目前不支持KNNClassifier。我混淆了Spark MLlib和Spark ML中的不同算法库。如果要使用KNN算法，可以使用Spark ML中的KNN算法实现，下面是Scala代码示例：

import org.apache.spark.ml.feature.{VectorAssembler, StringIndexer}
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.ml.classification.{KNNClassificationModel, KNNClassifier}
import org.apache.spark.sql.{DataFrame, SparkSession}

// 创建SparkSession
val spark = SparkSession.builder()
  .appName("KNNExample")
  .master("local[*]")
  .getOrCreate()

// 读取数据集
val data = spark.read.option("inferSchema", "true")
  .option("header", "false")
  .csv("path/to/adult.data")
  .toDF("age", "workclass", "fnlwgt", "education", "education-num", "marital-status", "occupation",
    "relationship", "race", "sex", "capital-gain", "capital-loss", "hours-per-week", "native-country", "label")

// 将分类变量转换为数值变量
val categoricalCols = Array("workclass", "education", "marital-status", "occupation", "relationship", "race", "sex", "native-country")
val indexers = categoricalCols.map { colName =>
  new StringIndexer().setInputCol(colName).setOutputCol(colName + "_index").fit(data)
}
val pipeline = new Pipeline().setStages(indexers)
val transformedData = pipeline.fit(data).transform(data)

// 将所有特征合并到一个向量中
val assembler = new VectorAssembler()
  .setInputCols(Array("age", "workclass_index", "fnlwgt", "education_index", "education-num", "marital-status_index",
    "occupation_index", "relationship_index", "race_index", "sex_index", "capital-gain", "capital-loss",
    "hours-per-week", "native-country_index"))
  .setOutputCol("features")
val dataWithFeatures = assembler.transform(transformedData)

// 将标签列转换为数值类型
val labelIndexer = new StringIndexer().setInputCol("label").setOutputCol("label_index").fit(dataWithFeatures)
val dataWithLabel = labelIndexer.transform(dataWithFeatures)

// 将数据集拆分为训练集和测试集
val Array(trainingData, testData) = dataWithLabel.randomSplit(Array(0.7, 0.3))

// 创建KNN模型
val knn = new KNNClassifier().setFeaturesCol("features").setLabelCol("label_index").setTopTreeSize(10)

// 训练模型
val model = knn.fit(trainingData)

// 在测试集上进行预测
val predictions = model.transform(testData)

// 计算模型的准确率
val correctPredictions = predictions.filter($"label_index" === $"prediction").count()
val totalPredictions = predictions.count()
val accuracy = correctPredictions.toDouble / totalPredictions.toDouble
println(s"Accuracy: $accuracy")

在上面的代码中，我们首先加载数据集，并对分类变量进行数值化。然后，我们将所有特征合并为一个向量，并将标签列转换为数值类型。接下来，我们将数据集拆分为训练集和测试集，然后创建KNN模型并进行训练。最后，我们在测试集上进行预测，并计算模型的准确率。