[Case Study]Multilayer Perceptron Classification using Java

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

1. package org.apache.spark.examples.ml;
   
2. 
   
3. // $example on$
   
4. import org.apache.spark.SparkConf;
   
5. import org.apache.spark.api.java.JavaSparkContext;
   
6. import org.apache.spark.sql.SQLContext;
   
7. import org.apache.spark.ml.classification.MultilayerPerceptronClassificationModel;
   
8. import org.apache.spark.ml.classification.MultilayerPerceptronClassifier;
   
9. import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator;
   
10. import org.apache.spark.sql.DataFrame;
    
11. // $example off$
    
12. 
    
13. /**
    
14. * An example for Multilayer Perceptron Classification.
    
15. */
    
16. public class JavaMultilayerPerceptronClassifierExample {
    
17. 
    
18.   public static void main(String[] args) {
    
19.     SparkConf conf = new SparkConf().setAppName("JavaMultilayerPerceptronClassifierExample");
    
20.     JavaSparkContext jsc = new JavaSparkContext(conf);
    
21.     SQLContext jsql = new SQLContext(jsc);
    
22. 
    
23.     // $example on$
    
24.     // Load training data
    
25.     String path = "data/mllib/sample_multiclass_classification_data.txt";
    
26.     DataFrame dataFrame = jsql.read().format("libsvm").load(path);
    
27.     // Split the data into train and test
    
28.     DataFrame[] splits = dataFrame.randomSplit(new double[]{0.6, 0.4}, 1234L);
    
29.     DataFrame train = splits[0];
    
30.     DataFrame test = splits[1];
    
31.     // specify layers for the neural network:
    
32.     // input layer of size 4 (features), two intermediate of size 5 and 4
    
33.     // and output of size 3 (classes)
    
34.     int[] layers = new int[] {4, 5, 4, 3};
    
35.     // create the trainer and set its parameters
    
36.     MultilayerPerceptronClassifier trainer = new MultilayerPerceptronClassifier()
    
37.       .setLayers(layers)
    
38.       .setBlockSize(128)
    
39.       .setSeed(1234L)
    
40.       .setMaxIter(100);
    
41.     // train the model
    
42.     MultilayerPerceptronClassificationModel model = trainer.fit(train);
    
43.     // compute precision on the test set
    
44.     DataFrame result = model.transform(test);
    
45.     DataFrame predictionAndLabels = result.select("prediction", "label");
    
46.     MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
    
47.       .setMetricName("precision");
    
48.     System.out.println("Precision = " + evaluator.evaluate(predictionAndLabels));
    
49.     // $example off$
    
50. 
    
51.     jsc.stop();
    
52.   }
    
53. }

复制代码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Case study multilayer cation Using multi example package import Java