我正在尝试使用Spark ML中的KMeans来分析和聚类芝加哥犯罪数据集。以下是代码片段
case class ChicCase(ID: Long, Case_Number: String, Date: String, Block: String, IUCR: String, Primary_Type: String, Description: String, Location_description: String, Arrest: Boolean, Domestic: Boolean, Beat: Int, District: Int, Ward: Int, Community_Area: Int, FBI_Code: String, X_Coordinate: Int, Y_Coordinate: Int, Year: Int, Updated_On: String, Latitude: Double, Longitude: Double, Location: String)val city = spark.read.option("header", true).option("inferSchema", true).csv("/chicago_city/Crimes_2001_to_present_2").as[ChicCase]val data = city.drop("ID", "Case_Number", "Date", "Block", "IUCR", "Primary_Type", "Description", "Location_description", "Arrest", "Domestic", "FBI_Code", "Year", "Location", "Updated_On")val kmeans = new KMeanskmeans.setK(10).setSeed(1L)val model = kmeans.fit(data)但这会抛出以下异常
org.apache.spark.sql.AnalysisException: cannot resolve '`features`' given input columns: [Ward, Longitude, X_Coordinate, Beat, Latitude, District, Y_Coordinate, Community_Area]; at org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:77) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:74) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:301) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:301) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69) at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:300) at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionUp$1(QueryPlan.scala:190) at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:200) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2$1.apply(QueryPlan.scala:204) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at scala.collection.TraversableLike$class.map(TraversableLike.scala:234) at scala.collection.AbstractTraversable.map(Traversable.scala:104) at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:204) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$5.apply(QueryPlan.scala:209) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179) at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:209) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:74) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:67) at org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:126) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:67) at org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:58) at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:49) at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$withPlan(Dataset.scala:2589) at org.apache.spark.sql.Dataset.select(Dataset.scala:969) at org.apache.spark.ml.clustering.KMeans.fit(KMeans.scala:307) ... 90 elided数据类型要么是Int要么是Double。问题可能出在哪里？
回答：
在Spark ML的数据框API中，所有特征列都应使用VectorAssembler收集到一个名为features的单一列中。当你拟合模型时，它会尝试查找features列，在你的例子中，没有这样的列，这就是为什么会抛出异常：无法解析’`features`’给定的输入列：
import org.apache.spark.ml.feature.VectorAssemblerimport org.apache.spark.ml.clustering.KMeans// assembler用于将所有感兴趣的列收集到一个features列中val assembler = (new VectorAssembler(). setInputCols(Array("Ward", "Longitude", "X_Coordinate", "Beat", "Latitude", "District", "Y_Coordinate", "Community_Area")). setOutputCol("features")) val data = assembler.transform(city) val kmeans = new KMeans()val model = kmeans.fit(data)model.getK// res28: Int = 2 示例在这里