Github user yinxusen commented on a diff in the pull request:
https://github.com/apache/spark/pull/11053#discussion_r53218506
--- Diff:
examples/src/main/scala/org/apache/spark/examples/ml/ModelSelectionViaCrossValidationExample.scala
---
@@ -0,0 +1,109 @@
+/*
+ * 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.ml
+
+import org.apache.spark.{SparkConf, SparkContext}
+import org.apache.spark.ml.Pipeline
+import org.apache.spark.ml.classification.LogisticRegression
+import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator
+import org.apache.spark.ml.feature.{HashingTF, Tokenizer}
+import org.apache.spark.ml.tuning.{CrossValidator, ParamGridBuilder}
+import org.apache.spark.mllib.linalg.Vector
+import org.apache.spark.sql.Row
+import org.apache.spark.sql.SQLContext
+
+object ModelSelectionViaCrossValidationExample {
+
+ def main(args: Array[String]): Unit = {
+ val conf = new
SparkConf().setAppName("ModelSelectionViaCrossValidationExample")
+ val sc = new SparkContext(conf)
+ val sqlContext = new SQLContext(sc)
+
+ // $example on$
+ // Prepare training data from a list of (id, text, label) tuples.
+ val training = sqlContext.createDataFrame(Seq(
+ (0L, "a b c d e spark", 1.0),
+ (1L, "b d", 0.0),
+ (2L, "spark f g h", 1.0),
+ (3L, "hadoop mapreduce", 0.0),
+ (4L, "b spark who", 1.0),
+ (5L, "g d a y", 0.0),
+ (6L, "spark fly", 1.0),
+ (7L, "was mapreduce", 0.0),
+ (8L, "e spark program", 1.0),
+ (9L, "a e c l", 0.0),
+ (10L, "spark compile", 1.0),
+ (11L, "hadoop software", 0.0)
+ )).toDF("id", "text", "label")
+
+ // Configure an ML pipeline, which consists of three stages:
tokenizer, hashingTF, and lr.
+ val tokenizer = new Tokenizer()
+ .setInputCol("text")
+ .setOutputCol("words")
+ val hashingTF = new HashingTF()
+ .setInputCol(tokenizer.getOutputCol)
+ .setOutputCol("features")
+ val lr = new LogisticRegression()
+ .setMaxIter(10)
+ val pipeline = new Pipeline()
+ .setStages(Array(tokenizer, hashingTF, lr))
+
+ // We use a ParamGridBuilder to construct a grid of parameters to
search over.
+ // With 3 values for hashingTF.numFeatures and 2 values for
lr.regParam,
+ // this grid will have 3 x 2 = 6 parameter settings for CrossValidator
to choose from.
+ val paramGrid = new ParamGridBuilder()
+ .addGrid(hashingTF.numFeatures, Array(10, 100, 1000))
+ .addGrid(lr.regParam, Array(0.1, 0.01))
+ .build()
+
+ // We now treat the Pipeline as an Estimator, wrapping it in a
CrossValidator instance.
+ // This will allow us to jointly choose parameters for all Pipeline
stages.
+ // A CrossValidator requires an Estimator, a set of Estimator
ParamMaps, and an Evaluator.
+ // Note that the evaluator here is a BinaryClassificationEvaluator and
its default metric
+ // is areaUnderROC.
+ val cv = new CrossValidator()
+ .setEstimator(pipeline)
+ .setEvaluator(new BinaryClassificationEvaluator)
+ .setEstimatorParamMaps(paramGrid)
+ .setNumFolds(2) // Use 3+ in practice
--- End diff --
2-indent spaces for inline comments
---
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]
