Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/5699#discussion_r29373356
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/feature/BinarizerSuite.scala ---
@@ -0,0 +1,76 @@
+/*
+ * 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.
+ */
+
+package org.apache.spark.ml.feature
+
+import org.scalatest.FunSuite
+
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.mllib.util.TestingUtils._
+import org.apache.spark.sql.{DataFrame, Row, SQLContext}
+
+
+class BinarizerSuite extends FunSuite with MLlibTestSparkContext {
+
+ @transient var data: Array[Double] = _
+ @transient var dataFrame: DataFrame = _
+ @transient var binarizer: Binarizer = _
+ @transient val threshold = 0.2
+ @transient var defaultBinarized: Array[Double] = _
+ @transient var thresholdBinarized: Array[Double] = _
+
+ override def beforeAll(): Unit = {
+ super.beforeAll()
+
+ data = Array(0.1, -0.5, 0.2, -0.3, 0.8, 0.7, -0.1, -0.4)
+ defaultBinarized = data.map(x => if (x > 0.0) 1.0 else 0.0)
+ thresholdBinarized = data.map(x => if (x > threshold) 1.0 else 0.0)
+
+ val sqlContext = new SQLContext(sc)
+ dataFrame = sqlContext.createDataFrame(sc.parallelize(data,
2).map(BinarizerSuite.FeatureData))
+ binarizer = new Binarizer()
+ .setInputCol("feature")
+ .setOutputCol("binarized_feature")
+ }
+
+ def collectResult(result: DataFrame): Array[Double] = {
--- End diff --
The risk is that if the DataFrame has multiple partitions, `collect()`
doesn't guarantee the ordering. We can create the input and expected output
pairs on local and then create the DataFrame to ensure that they are paired
correctly. See:
https://github.com/apache/spark/blob/master/mllib/src/test/scala/org/apache/spark/ml/feature/IDFSuite.scala#L88
---
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]
