Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/5779#discussion_r30535328
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
---
@@ -0,0 +1,58 @@
+/*
+ * 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 scala.util.Random
+
+import org.scalatest.FunSuite
+
+import org.apache.spark.ml.attribute.{Attribute, NominalAttribute}
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{Row, SQLContext}
+
+class QuantileDiscretizerSuite extends FunSuite with MLlibTestSparkContext
{
+
+ test("Test quantile discretizer") {
+ val sqlContext = new SQLContext(sc)
+ import sqlContext.implicits._
+
+ val random = new Random(47)
+ val data = Array.fill[Double](10)(random.nextDouble())
+ val result = Array[Double](2, 2, 0, 1, 1, 1, 1, 0, 2, 2)
+
+ val df = sc.parallelize(data.zip(result)).toDF("data", "expected")
+
+ val discretizer = new QuantileDiscretizer()
+ .setInputCol("data")
+ .setOutputCol("result")
+ .setNumBuckets(3)
+
+ val bucketizer = discretizer.fit(df)
+ val res = bucketizer.transform(df)
+
+ res.select("expected", "result").collect().foreach {
+ case Row(expected: Double, result: Double) => assert(expected ==
result)
+ }
+
+ val attr =
Attribute.fromStructField(res.schema("result")).asInstanceOf[NominalAttribute]
+ assert(attr.values.get === Array(
--- End diff --
Even though you are using a fixed random seed, I don't think we should use
random data in this test. I would recommend creating a helper method which
tests a given dataset, and then call it with a variety of hand-constructed data.
---
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]
