From a95252823e09939b654dd425db38dadc4100bc87 Mon Sep 17 00:00:00 2001
From: Yanbo Liang <ybliang8@gmail.com>
Date: Mon, 6 Jun 2016 09:36:34 +0100
Subject: [SPARK-15771][ML][EXAMPLES] Use 'accuracy' rather than 'precision' in
 many ML examples

## What changes were proposed in this pull request?
Since [SPARK-15617](https://issues.apache.org/jira/browse/SPARK-15617) deprecated ```precision``` in ```MulticlassClassificationEvaluator```, many ML examples broken.
```python
pyspark.sql.utils.IllegalArgumentException: u'MulticlassClassificationEvaluator_4c3bb1d73d8cc0cedae6 parameter metricName given invalid value precision.'
```
We should use ```accuracy``` to replace ```precision``` in these examples.

## How was this patch tested?
Offline tests.

Author: Yanbo Liang <ybliang8@gmail.com>

Closes #13519 from yanboliang/spark-15771.
---
 .../spark/examples/ml/JavaDecisionTreeClassificationExample.java    | 2 +-
 .../spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java | 2 +-
 .../examples/ml/JavaMultilayerPerceptronClassifierExample.java      | 6 +++---
 .../java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java    | 6 +++---
 .../java/org/apache/spark/examples/ml/JavaOneVsRestExample.java     | 6 +++---
 .../apache/spark/examples/ml/JavaRandomForestClassifierExample.java | 2 +-
 examples/src/main/python/ml/decision_tree_classification_example.py | 2 +-
 .../src/main/python/ml/gradient_boosted_tree_classifier_example.py  | 2 +-
 examples/src/main/python/ml/multilayer_perceptron_classification.py | 6 +++---
 examples/src/main/python/ml/naive_bayes_example.py                  | 6 +++---
 examples/src/main/python/ml/one_vs_rest_example.py                  | 6 +++---
 examples/src/main/python/ml/random_forest_classifier_example.py     | 2 +-
 .../spark/examples/ml/DecisionTreeClassificationExample.scala       | 2 +-
 .../spark/examples/ml/GradientBoostedTreeClassifierExample.scala    | 2 +-
 .../spark/examples/ml/MultilayerPerceptronClassifierExample.scala   | 6 +++---
 .../main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala | 6 +++---
 .../main/scala/org/apache/spark/examples/ml/OneVsRestExample.scala  | 6 +++---
 .../apache/spark/examples/ml/RandomForestClassifierExample.scala    | 2 +-
 18 files changed, 36 insertions(+), 36 deletions(-)

(limited to 'examples/src')

diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java
index bdb76f004f..a9c6e7f0bf 100644
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaDecisionTreeClassificationExample.java
@@ -90,7 +90,7 @@ public class JavaDecisionTreeClassificationExample {
     MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
       .setLabelCol("indexedLabel")
       .setPredictionCol("prediction")
-      .setMetricName("precision");
+      .setMetricName("accuracy");
     double accuracy = evaluator.evaluate(predictions);
     System.out.println("Test Error = " + (1.0 - accuracy));
 
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java
index 5c2e03eda9..3e9eb998c8 100644
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java
@@ -92,7 +92,7 @@ public class JavaGradientBoostedTreeClassifierExample {
     MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
       .setLabelCol("indexedLabel")
       .setPredictionCol("prediction")
-      .setMetricName("precision");
+      .setMetricName("accuracy");
     double accuracy = evaluator.evaluate(predictions);
     System.out.println("Test Error = " + (1.0 - accuracy));
 
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaMultilayerPerceptronClassifierExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaMultilayerPerceptronClassifierExample.java
index c7d03d8593..0f1d9c2634 100644
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaMultilayerPerceptronClassifierExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaMultilayerPerceptronClassifierExample.java
@@ -57,12 +57,12 @@ public class JavaMultilayerPerceptronClassifierExample {
       .setMaxIter(100);
     // train the model
     MultilayerPerceptronClassificationModel model = trainer.fit(train);
-    // compute precision on the test set
+    // compute accuracy on the test set
     Dataset<Row> result = model.transform(test);
     Dataset<Row> predictionAndLabels = result.select("prediction", "label");
     MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
-      .setMetricName("precision");
-    System.out.println("Precision = " + evaluator.evaluate(predictionAndLabels));
+      .setMetricName("accuracy");
+    System.out.println("Accuracy = " + evaluator.evaluate(predictionAndLabels));
     // $example off$
 
     spark.stop();
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java
index 50a46a5774..3226d5d2fa 100644
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java
@@ -50,12 +50,12 @@ public class JavaNaiveBayesExample {
     NaiveBayes nb = new NaiveBayes();
     // train the model
     NaiveBayesModel model = nb.fit(train);
-    // compute precision on the test set
+    // compute accuracy on the test set
     Dataset<Row> result = model.transform(test);
     Dataset<Row> predictionAndLabels = result.select("prediction", "label");
     MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
-      .setMetricName("precision");
-    System.out.println("Precision = " + evaluator.evaluate(predictionAndLabels));
+      .setMetricName("accuracy");
+    System.out.println("Accuracy = " + evaluator.evaluate(predictionAndLabels));
     // $example off$
 
     spark.stop();
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java
index 5bf455ebfe..c6a083ddc9 100644
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java
@@ -71,11 +71,11 @@ public class JavaOneVsRestExample {
 
     // obtain evaluator.
     MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
-            .setMetricName("precision");
+            .setMetricName("accuracy");
 
     // compute the classification error on test data.
-    double precision = evaluator.evaluate(predictions);
-    System.out.println("Test Error : " + (1 - precision));
+    double accuracy = evaluator.evaluate(predictions);
+    System.out.println("Test Error : " + (1 - accuracy));
     // $example off$
 
     spark.stop();
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java
index 14af2fbbbb..da2633e886 100644
--- a/examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaRandomForestClassifierExample.java
@@ -88,7 +88,7 @@ public class JavaRandomForestClassifierExample {
     MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
       .setLabelCol("indexedLabel")
       .setPredictionCol("prediction")
-      .setMetricName("precision");
+      .setMetricName("accuracy");
     double accuracy = evaluator.evaluate(predictions);
     System.out.println("Test Error = " + (1.0 - accuracy));
 
diff --git a/examples/src/main/python/ml/decision_tree_classification_example.py b/examples/src/main/python/ml/decision_tree_classification_example.py
index 9b40b701ec..708f1af6cc 100644
--- a/examples/src/main/python/ml/decision_tree_classification_example.py
+++ b/examples/src/main/python/ml/decision_tree_classification_example.py
@@ -66,7 +66,7 @@ if __name__ == "__main__":
 
     # Select (prediction, true label) and compute test error
     evaluator = MulticlassClassificationEvaluator(
-        labelCol="indexedLabel", predictionCol="prediction", metricName="precision")
+        labelCol="indexedLabel", predictionCol="prediction", metricName="accuracy")
     accuracy = evaluator.evaluate(predictions)
     print("Test Error = %g " % (1.0 - accuracy))
 
diff --git a/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py b/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py
index 50026d7b7e..6c2d7e7b81 100644
--- a/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py
+++ b/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py
@@ -66,7 +66,7 @@ if __name__ == "__main__":
 
     # Select (prediction, true label) and compute test error
     evaluator = MulticlassClassificationEvaluator(
-        labelCol="indexedLabel", predictionCol="prediction", metricName="precision")
+        labelCol="indexedLabel", predictionCol="prediction", metricName="accuracy")
     accuracy = evaluator.evaluate(predictions)
     print("Test Error = %g" % (1.0 - accuracy))
 
diff --git a/examples/src/main/python/ml/multilayer_perceptron_classification.py b/examples/src/main/python/ml/multilayer_perceptron_classification.py
index 8bededc14d..aa33bef5a3 100644
--- a/examples/src/main/python/ml/multilayer_perceptron_classification.py
+++ b/examples/src/main/python/ml/multilayer_perceptron_classification.py
@@ -43,11 +43,11 @@ if __name__ == "__main__":
     trainer = MultilayerPerceptronClassifier(maxIter=100, layers=layers, blockSize=128, seed=1234)
     # train the model
     model = trainer.fit(train)
-    # compute precision on the test set
+    # compute accuracy on the test set
     result = model.transform(test)
     predictionAndLabels = result.select("prediction", "label")
-    evaluator = MulticlassClassificationEvaluator(metricName="precision")
-    print("Precision:" + str(evaluator.evaluate(predictionAndLabels)))
+    evaluator = MulticlassClassificationEvaluator(metricName="accuracy")
+    print("Accuracy: " + str(evaluator.evaluate(predictionAndLabels)))
     # $example off$
 
     spark.stop()
diff --git a/examples/src/main/python/ml/naive_bayes_example.py b/examples/src/main/python/ml/naive_bayes_example.py
index 89255a2bae..8bc32222fe 100644
--- a/examples/src/main/python/ml/naive_bayes_example.py
+++ b/examples/src/main/python/ml/naive_bayes_example.py
@@ -43,11 +43,11 @@ if __name__ == "__main__":
 
     # train the model
     model = nb.fit(train)
-    # compute precision on the test set
+    # compute accuracy on the test set
     result = model.transform(test)
     predictionAndLabels = result.select("prediction", "label")
-    evaluator = MulticlassClassificationEvaluator(metricName="precision")
-    print("Precision:" + str(evaluator.evaluate(predictionAndLabels)))
+    evaluator = MulticlassClassificationEvaluator(metricName="accuracy")
+    print("Accuracy: " + str(evaluator.evaluate(predictionAndLabels)))
     # $example off$
 
     spark.stop()
diff --git a/examples/src/main/python/ml/one_vs_rest_example.py b/examples/src/main/python/ml/one_vs_rest_example.py
index 971156d0dd..b82087beba 100644
--- a/examples/src/main/python/ml/one_vs_rest_example.py
+++ b/examples/src/main/python/ml/one_vs_rest_example.py
@@ -58,11 +58,11 @@ if __name__ == "__main__":
     predictions = ovrModel.transform(test)
 
     # obtain evaluator.
-    evaluator = MulticlassClassificationEvaluator(metricName="precision")
+    evaluator = MulticlassClassificationEvaluator(metricName="accuracy")
 
     # compute the classification error on test data.
-    precision = evaluator.evaluate(predictions)
-    print("Test Error : " + str(1 - precision))
+    accuracy = evaluator.evaluate(predictions)
+    print("Test Error : " + str(1 - accuracy))
     # $example off$
 
     spark.stop()
diff --git a/examples/src/main/python/ml/random_forest_classifier_example.py b/examples/src/main/python/ml/random_forest_classifier_example.py
index c618eaf60c..a7fc765318 100644
--- a/examples/src/main/python/ml/random_forest_classifier_example.py
+++ b/examples/src/main/python/ml/random_forest_classifier_example.py
@@ -66,7 +66,7 @@ if __name__ == "__main__":
 
     # Select (prediction, true label) and compute test error
     evaluator = MulticlassClassificationEvaluator(
-        labelCol="indexedLabel", predictionCol="prediction", metricName="precision")
+        labelCol="indexedLabel", predictionCol="prediction", metricName="accuracy")
     accuracy = evaluator.evaluate(predictions)
     print("Test Error = %g" % (1.0 - accuracy))
 
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala
index b3103ced91..bc6d327593 100644
--- a/examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/DecisionTreeClassificationExample.scala
@@ -81,7 +81,7 @@ object DecisionTreeClassificationExample {
     val evaluator = new MulticlassClassificationEvaluator()
       .setLabelCol("indexedLabel")
       .setPredictionCol("prediction")
-      .setMetricName("precision")
+      .setMetricName("accuracy")
     val accuracy = evaluator.evaluate(predictions)
     println("Test Error = " + (1.0 - accuracy))
 
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala
index 0d1ffbe225..9a39acfbf3 100644
--- a/examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeClassifierExample.scala
@@ -83,7 +83,7 @@ object GradientBoostedTreeClassifierExample {
     val evaluator = new MulticlassClassificationEvaluator()
       .setLabelCol("indexedLabel")
       .setPredictionCol("prediction")
-      .setMetricName("precision")
+      .setMetricName("accuracy")
     val accuracy = evaluator.evaluate(predictions)
     println("Test Error = " + (1.0 - accuracy))
 
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/MultilayerPerceptronClassifierExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/MultilayerPerceptronClassifierExample.scala
index 0e780fb7d3..e8a9b32da9 100644
--- a/examples/src/main/scala/org/apache/spark/examples/ml/MultilayerPerceptronClassifierExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/MultilayerPerceptronClassifierExample.scala
@@ -55,12 +55,12 @@ object MultilayerPerceptronClassifierExample {
       .setMaxIter(100)
     // train the model
     val model = trainer.fit(train)
-    // compute precision on the test set
+    // compute accuracy on the test set
     val result = model.transform(test)
     val predictionAndLabels = result.select("prediction", "label")
     val evaluator = new MulticlassClassificationEvaluator()
-      .setMetricName("precision")
-    println("Precision:" + evaluator.evaluate(predictionAndLabels))
+      .setMetricName("accuracy")
+    println("Accuracy: " + evaluator.evaluate(predictionAndLabels))
     // $example off$
 
     spark.stop()
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala
index 90cdebfcb0..a59ba182fc 100644
--- a/examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala
@@ -49,9 +49,9 @@ object NaiveBayesExample {
     val evaluator = new MulticlassClassificationEvaluator()
       .setLabelCol("label")
       .setPredictionCol("prediction")
-      .setMetricName("precision")
-    val precision = evaluator.evaluate(predictions)
-    println("Precision:" + precision)
+      .setMetricName("accuracy")
+    val accuracy = evaluator.evaluate(predictions)
+    println("Accuracy: " + accuracy)
     // $example off$
 
     spark.stop()
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/OneVsRestExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/OneVsRestExample.scala
index 0da8e3137a..acde110683 100644
--- a/examples/src/main/scala/org/apache/spark/examples/ml/OneVsRestExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/OneVsRestExample.scala
@@ -65,11 +65,11 @@ object OneVsRestExample {
 
     // obtain evaluator.
     val evaluator = new MulticlassClassificationEvaluator()
-      .setMetricName("precision")
+      .setMetricName("accuracy")
 
     // compute the classification error on test data.
-    val precision = evaluator.evaluate(predictions)
-    println(s"Test Error : ${1 - precision}")
+    val accuracy = evaluator.evaluate(predictions)
+    println(s"Test Error : ${1 - accuracy}")
     // $example off$
 
     spark.stop()
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala
index cccc4a6ea2..5eafda8ce4 100644
--- a/examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala
@@ -83,7 +83,7 @@ object RandomForestClassifierExample {
     val evaluator = new MulticlassClassificationEvaluator()
       .setLabelCol("indexedLabel")
       .setPredictionCol("prediction")
-      .setMetricName("precision")
+      .setMetricName("accuracy")
     val accuracy = evaluator.evaluate(predictions)
     println("Test Error = " + (1.0 - accuracy))
 
-- 
cgit v1.2.3