examples/src/main/java/org/apache/ignite/examples/ml/preprocessing/ImputingExample.java

   1 /*
   2  * Licensed to the Apache Software Foundation (ASF) under one or more
   3  * contributor license agreements.  See the NOTICE file distributed with
   4  * this work for additional information regarding copyright ownership.
   5  * The ASF licenses this file to You under the Apache License, Version 2.0
   6  * (the "License"); you may not use this file except in compliance with
   7  * the License.  You may obtain a copy of the License at
   8  *
   9  *      http://www.apache.org/licenses/LICENSE-2.0
  10  *
  11  * Unless required by applicable law or agreed to in writing, software
  12  * distributed under the License is distributed on an "AS IS" BASIS,
  13  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  14  * See the License for the specific language governing permissions and
  15  * limitations under the License.
  16  */
  17
  18 package org.apache.ignite.examples.ml.preprocessing;
  19
  20 import java.util.Arrays;
  21 import org.apache.ignite.Ignite;
  22 import org.apache.ignite.IgniteCache;
  23 import org.apache.ignite.Ignition;
  24 import org.apache.ignite.cache.affinity.rendezvous.RendezvousAffinityFunction;
  25 import org.apache.ignite.configuration.CacheConfiguration;
  26 import org.apache.ignite.examples.ml.dataset.model.Person;
  27 import org.apache.ignite.ml.dataset.DatasetFactory;
  28 import org.apache.ignite.ml.dataset.primitive.SimpleDataset;
  29 import org.apache.ignite.ml.math.Vector;
  30 import org.apache.ignite.ml.math.VectorUtils;
  31 import org.apache.ignite.ml.math.functions.IgniteBiFunction;
  32 import org.apache.ignite.ml.preprocessing.imputing.ImputerTrainer;
  33
  34 /**
  35  * Example that shows how to use Imputing preprocessor to impute the missing value in the given data.
  36  */
  37 public class ImputingExample {
  38     /** Run example. */
  39     public static void main(String[] args) throws Exception {
  40         try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
  41             System.out.println(">>> Imputing example started.");
  42
  43             IgniteCache<Integer, Person> persons = createCache(ignite);
  44
  45             // Defines first preprocessor that extracts features from an upstream data.
  46             IgniteBiFunction<Integer, Person, Vector> featureExtractor = (k, v) -> VectorUtils.of(
  47                 v.getAge(),
  48                 v.getSalary()
  49             );
  50
  51             // Defines second preprocessor that imputing features.
  52             IgniteBiFunction<Integer, Person, Vector> preprocessor = new ImputerTrainer<Integer, Person>()
  53                 .fit(ignite, persons, featureExtractor);
  54
  55             // Creates a cache based simple dataset containing features and providing standard dataset API.
  56             try (SimpleDataset<?> dataset = DatasetFactory.createSimpleDataset(ignite, persons, preprocessor)) {
  57                 // Calculation of the mean value. This calculation will be performed in map-reduce manner.
  58                 double[] mean = dataset.mean();
  59                 System.out.println("Mean \n\t" + Arrays.toString(mean));
  60
  61                 // Calculation of the standard deviation. This calculation will be performed in map-reduce manner.
  62                 double[] std = dataset.std();
  63                 System.out.println("Standard deviation \n\t" + Arrays.toString(std));
  64
  65                 // Calculation of the covariance matrix.  This calculation will be performed in map-reduce manner.
  66                 double[][] cov = dataset.cov();
  67                 System.out.println("Covariance matrix ");
  68                 for (double[] row : cov)
  69                     System.out.println("\t" + Arrays.toString(row));
  70
  71                 // Calculation of the correlation matrix.  This calculation will be performed in map-reduce manner.
  72                 double[][] corr = dataset.corr();
  73                 System.out.println("Correlation matrix ");
  74                 for (double[] row : corr)
  75                     System.out.println("\t" + Arrays.toString(row));
  76             }
  77
  78             System.out.println(">>> Imputing example completed.");
  79         }
  80     }
  81
  82     /** */
  83     private static IgniteCache<Integer, Person> createCache(Ignite ignite) {
  84         CacheConfiguration<Integer, Person> cacheConfiguration = new CacheConfiguration<>();
  85
  86         cacheConfiguration.setName("PERSONS");
  87         cacheConfiguration.setAffinity(new RendezvousAffinityFunction(false, 2));
  88
  89         IgniteCache<Integer, Person> persons = ignite.createCache(cacheConfiguration);
  90
  91         persons.put(1, new Person("Mike", 10, 1));
  92         persons.put(2, new Person("John", 20, 2));
  93         persons.put(3, new Person("George", 15, 1));
  94         persons.put(4, new Person("Piter", 25, Double.NaN));
  95         persons.put(5, new Person("Karl", Double.NaN, 1));
  96         persons.put(6, new Person("Gustaw", 20, 2));
  97         persons.put(7, new Person("Alex", 20, 2));
  98         return persons;
  99     }
 100 }