update XGBoost prediction

Author: delphi-xk

pom.xml

@@ -224,7 +224,6 @@
  <target>1.8</target>
  </configuration>
  </plugin>
-
  <plugin>
  <groupId>org.apache.maven.plugins</groupId>
  <artifactId>maven-surefire-plugin</artifactId>
@@ -233,6 +232,30 @@
  <skipTests>true</skipTests>
  </configuration>
  </plugin>
+<!-- <plugin>
+ <artifactId>maven-assembly-plugin</artifactId>
+ <configuration>
+ <appendAssemblyId>false</appendAssemblyId>
+ <descriptorRefs>
+ <descriptorRef>jar-with-dependencies</descriptorRef>
+ </descriptorRefs>
+ <archive>
+ <manifest>
+ &lt;!&ndash; 此处指定main方法入口的class &ndash;&gt;
+ <mainClass>com.hyzs.spark.ml.ModelEvaluation</mainClass>
+ </manifest>
+ </archive>
+ </configuration>
+ <executions>
+ <execution>
+ <id>make-assembly</id>
+ <phase>package</phase>
+ <goals>
+ <goal>assembly</goal>
+ </goals>
+ </execution>
+ </executions>
+ </plugin>-->
  </plugins>
  <resources>
  <resource>

src/main/scala/com/hyzs/spark/ml/ModelPrediction.scala

@@ -141,15 +141,42 @@ object ModelPrediction {
  }
 
 
+ def xgboost_ml(): Unit = {
+ val data = spark.read.format("libsvm").load(libsvmPath)
+ val Array(trainingData, testData) = data.randomSplit(Array(0.6, 0.4))
+ val xgbParam = Map("eta" -> 0.1f,
+ "max_depth" -> 6,
+ "objective" -> "binary:logistic",
+ "num_round" -> 10)
 
+ val xgbClassifier = new XGBoostClassifier(xgbParam).
+ setFeaturesCol("features").
+ setLabelCol("label")
 
- def main(args: Array[String]): Unit = {
- val (trainingData, validData, testData) = prepareData()
- println("random forest =======")
- val randomForestModel = randomForest(trainingData, validData, testData)
- println("gbt =======")
- val gbt = GBT(trainingData, validData, testData)
+ val xgbClassificationModel = xgbClassifier.fit(trainingData)
+ val predictions = xgbClassificationModel.transform(testData)
+
+ val predAndLabels = predictions.select("prediction", "label")
+ .map(row => (row.getDouble(0), row.getDouble(1)))
+ .rdd
+ .collect()
+ val confusion = new ConfusionMatrix(predAndLabels)
+ println("model precision: " + confusion.precision)
+ println("model recall: " + confusion.recall)
+ println("model accuracy: " + confusion.accuracy)
+ println("model f1: " + confusion.f1_score)
 
+ }
+
+
+ def main(args: Array[String]): Unit = {
+ /* val (trainingData, validData, testData) = prepareData()
+ println("random forest =======")
+ val randomForestModel = randomForest(trainingData, validData, testData)
+ println("gbt =======")
+ val gbt = GBT(trainingData, validData, testData)*/
+ println("xgboost =======")
+ xgboost_ml()
 
  }
 }