Github user yinxusen commented on a diff in the pull request:
https://github.com/apache/spark/pull/9689#discussion_r44795900
--- Diff:
examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassificationMetrics.scala
---
@@ -0,0 +1,111 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+// scalastyle:off println
+package org.apache.spark.examples.mllib
+
+
+// $example on$
+import org.apache.spark.mllib.classification.LogisticRegressionWithLBFGS
+import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
+import org.apache.spark.mllib.regression.LabeledPoint
+import org.apache.spark.mllib.util.MLUtils
+// $example off$
+
+import org.apache.spark.{SparkContext, SparkConf}
+import org.apache.spark.sql.SQLContext
+
+object BinaryClassificationMetrics {
+
+ def main(args: Array[String]) {
+
+ val conf = new SparkConf().setAppName("BinaryClassificationMetrics")
+ val sc = new SparkContext(conf)
+ val sqlContext = new SQLContext(sc)
+ import sqlContext.implicits._
+ // $example on$
+ // Load training data in LIBSVM format
+ val data = MLUtils.loadLibSVMFile(sc,
"data/mllib/sample_binary_classification_data.txt")
+
+ // Split data into training (60%) and test (40%)
+ val Array(training, test) = data.randomSplit(Array(0.6, 0.4), seed =
11L)
+ training.cache()
+
+ // Run training algorithm to build the model
+ val model = new LogisticRegressionWithLBFGS()
+ .setNumClasses(2)
+ .run(training)
+
+ // Clear the prediction threshold so the model will return
probabilities
+ model.clearThreshold
+
+ // Compute raw scores on the test set
+ val predictionAndLabels = test.map { case LabeledPoint(label,
features) =>
+ val prediction = model.predict(features)
+ (prediction, label)
+ }
+
+ // Instantiate metrics object
+ val metrics = new BinaryClassificationMetrics(predictionAndLabels)
+
+ // Precision by threshold
+ val precision = metrics.precisionByThreshold
+ precision.foreach { case (t, p) =>
+ println(s"Threshold: $t, Precision: $p")
+ }
+
+ // Recall by threshold
+ val recall = metrics.recallByThreshold
+ recall.foreach { case (t, r) =>
+ println(s"Threshold: $t, Recall: $r")
+ }
+
+ // Precision-Recall Curve
+ val PRC = metrics.pr
+
+ // F-measure
+ val f1Score = metrics.fMeasureByThreshold
+ f1Score.foreach { case (t, f) =>
+ println(s"Threshold: $t, F-score: $f, Beta = 1")
+ }
+
+ val beta = 0.5
+ val fScore = metrics.fMeasureByThreshold(beta)
+ f1Score.foreach { case (t, f) =>
+ println(s"Threshold: $t, F-score: $f, Beta = 0.5")
+ }
+
+ // AUPRC
+ val auPRC = metrics.areaUnderPR
+ println("Area under precision-recall curve = " + auPRC)
+
+ // Compute thresholds used in ROC and PR curves
+ val thresholds = precision.map(_._1)
+
+ // ROC Curve
+ val roc = metrics.roc
+
+ // AUROC
+ val auROC = metrics.areaUnderROC
+ println("Area under ROC = " + auROC)
+
+ // $example off$
+
--- End diff --
remove the line
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
