From e451f7f0c3857cdbbca98e66928a97f797f2fc6b Mon Sep 17 00:00:00 2001
From: "wm624@hotmail.com" <wm624@hotmail.com>
Date: Thu, 26 May 2016 12:36:36 +0200
Subject: [PATCH] [SPARK-15492][ML][DOC] Binarization scala example copy &
paste to spark-shell error
## What changes were proposed in this pull request?
(Please fill in changes proposed in this fix)
The Binarization scala example val dataFrame : Dataframe = spark.createDataFrame(data).toDF("label", "feature"), which can't be pasted in the spark-shell as Dataframe is not imported. Compared with other examples, this explicit type is not required.
So I removed Dataframe in the code.
## How was this patch tested?
(Please explain how this patch was tested. E.g. unit tests, integration tests, manual tests)
Manually tested
Author: wm624@hotmail.com <wm624@hotmail.com>
Closes #13266 from wangmiao1981/unit.
---
.../scala/org/apache/spark/examples/ml/BinarizerExample.scala | 4 ++--
.../scala/org/apache/spark/examples/ml/OneVsRestExample.scala | 3 +--
2 files changed, 3 insertions(+), 4 deletions(-)
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/BinarizerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/BinarizerExample.scala
index 82bc14789b..5cd13ad64c 100644
--- a/examples/src/main/scala/org/apache/spark/examples/ml/BinarizerExample.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/BinarizerExample.scala
@@ -21,7 +21,7 @@ package org.apache.spark.examples.ml
// $example on$
import org.apache.spark.ml.feature.Binarizer
// $example off$
-import org.apache.spark.sql.{DataFrame, SparkSession}
+import org.apache.spark.sql.{SparkSession}
object BinarizerExample {
def main(args: Array[String]): Unit = {
@@ -31,7 +31,7 @@ object BinarizerExample {
.getOrCreate()
// $example on$
val data = Array((0, 0.1), (1, 0.8), (2, 0.2))
- val dataFrame: DataFrame = spark.createDataFrame(data).toDF("label", "feature")
+ val dataFrame = spark.createDataFrame(data).toDF("label", "feature")
val binarizer: Binarizer = new Binarizer()
.setInputCol("feature")
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 0b333cf629..0da8e3137a 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
@@ -21,7 +21,6 @@ package org.apache.spark.examples.ml
// $example on$
import org.apache.spark.ml.classification.{LogisticRegression, OneVsRest}
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
-import org.apache.spark.sql.DataFrame
// $example off$
import org.apache.spark.sql.SparkSession
@@ -43,7 +42,7 @@ object OneVsRestExample {
// $example on$
// load data file.
- val inputData: DataFrame = spark.read.format("libsvm")
+ val inputData = spark.read.format("libsvm")
.load("data/mllib/sample_multiclass_classification_data.txt")
// generate the train/test split.
--
GitLab