diff options
Diffstat (limited to 'mllib')
-rw-r--r-- | mllib/src/test/java/org/apache/spark/ml/feature/JavaHashingTFSuite.java | 81 |
1 files changed, 81 insertions, 0 deletions
diff --git a/mllib/src/test/java/org/apache/spark/ml/feature/JavaHashingTFSuite.java b/mllib/src/test/java/org/apache/spark/ml/feature/JavaHashingTFSuite.java new file mode 100644 index 0000000000..23463ab5fe --- /dev/null +++ b/mllib/src/test/java/org/apache/spark/ml/feature/JavaHashingTFSuite.java @@ -0,0 +1,81 @@ +/* + * 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 com.google.common.collect.Lists; +import org.junit.After; +import org.junit.Assert; +import org.junit.Before; +import org.junit.Test; + +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.mllib.linalg.Vector; +import org.apache.spark.sql.DataFrame; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.RowFactory; +import org.apache.spark.sql.SQLContext; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; + + +public class JavaHashingTFSuite { + private transient JavaSparkContext jsc; + private transient SQLContext jsql; + + @Before + public void setUp() { + jsc = new JavaSparkContext("local", "JavaHashingTFSuite"); + jsql = new SQLContext(jsc); + } + + @After + public void tearDown() { + jsc.stop(); + jsc = null; + } + + @Test + public void hashingTF() { + JavaRDD<Row> jrdd = jsc.parallelize(Lists.newArrayList( + RowFactory.create(0, "Hi I heard about Spark"), + RowFactory.create(0, "I wish Java could use case classes"), + RowFactory.create(1, "Logistic regression models are neat") + )); + StructType schema = new StructType(new StructField[]{ + new StructField("label", DataTypes.DoubleType, false, Metadata.empty()), + new StructField("sentence", DataTypes.StringType, false, Metadata.empty()) + }); + DataFrame sentenceDataFrame = jsql.createDataFrame(jrdd, schema); + + Tokenizer tokenizer = new Tokenizer().setInputCol("sentence").setOutputCol("words"); + DataFrame wordsDataFrame = tokenizer.transform(sentenceDataFrame); + int numFeatures = 20; + HashingTF hashingTF = new HashingTF() + .setInputCol("words") + .setOutputCol("features") + .setNumFeatures(numFeatures); + DataFrame featurized = hashingTF.transform(wordsDataFrame); + for (Row r : featurized.select("features", "words", "label").take(3)) { + Vector features = r.getAs(0); + Assert.assertEquals(features.size(), numFeatures); + } + } +} |