spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jkbradley <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-13089][ML] [Doc] spark.ml Naive Bayes u...
Date Fri, 08 Apr 2016 20:39:42 GMT
Github user jkbradley commented on a diff in the pull request:

    https://github.com/apache/spark/pull/11015#discussion_r59086028
  
    --- Diff: examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.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.
    + */
    +
    +// scalastyle:off println
    +package org.apache.spark.examples.ml
    +
    +import org.apache.spark.{SparkConf, SparkContext}
    +// $example on$
    +import org.apache.spark.ml.classification.{NaiveBayes}
    +import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
    +// $example off$
    +import org.apache.spark.sql.SQLContext
    +
    +object NaiveBayesExample {
    +  def main(args: Array[String]): Unit = {
    +    val conf = new SparkConf().setAppName("NaiveBayesExample")
    +    val sc = new SparkContext(conf)
    +    val sqlContext = new SQLContext(sc)
    +    // $example on$
    +    // Load the data stored in LIBSVM format as a DataFrame.
    +    val data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
    +
    +    // Split the data into training and test sets (30% held out for testing)
    +    val Array(trainingData, testData) = data.randomSplit(Array(0.7, 0.3))
    +
    +    // Train a DecisionTree model.
    +    val model = new NaiveBayes()
    +      .fit(trainingData)
    +
    +    // Select example rows to display.
    +    val predictions = model.transform(testData)
    +    predictions.show()
    +
    +    // Select (prediction, true label) and compute test error
    +    val evaluator = new MulticlassClassificationEvaluator()
    +      .setLabelCol("label")
    +      .setPredictionCol("prediction")
    +      .setMetricName("precision")
    +    val accuracy = evaluator.evaluate(predictions)
    +    println("Test Error = " + (1.0 - accuracy))
    --- End diff --
    
    Output precision like other examples?


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message