diff options
Diffstat (limited to 'mllib/src/test/scala/org/apache/spark/ml/feature/CountVectorizerSuite.scala')
| -rw-r--r-- | mllib/src/test/scala/org/apache/spark/ml/feature/CountVectorizerSuite.scala | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/CountVectorizerSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/CountVectorizerSuite.scala index a59203c33d..863b66bf49 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/feature/CountVectorizerSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/feature/CountVectorizerSuite.scala @@ -77,10 +77,10 @@ class CountVectorizerSuite extends SparkFunSuite with MLlibTestSparkContext test("CountVectorizer vocabSize and minDF") { val df = spark.createDataFrame(Seq( - (0, split("a b c d"), Vectors.sparse(3, Seq((0, 1.0), (1, 1.0)))), - (1, split("a b c"), Vectors.sparse(3, Seq((0, 1.0), (1, 1.0)))), - (2, split("a b"), Vectors.sparse(3, Seq((0, 1.0), (1, 1.0)))), - (3, split("a"), Vectors.sparse(3, Seq((0, 1.0))))) + (0, split("a b c d"), Vectors.sparse(2, Seq((0, 1.0), (1, 1.0)))), + (1, split("a b c"), Vectors.sparse(2, Seq((0, 1.0), (1, 1.0)))), + (2, split("a b"), Vectors.sparse(2, Seq((0, 1.0), (1, 1.0)))), + (3, split("a"), Vectors.sparse(2, Seq((0, 1.0))))) ).toDF("id", "words", "expected") val cvModel = new CountVectorizer() .setInputCol("words") |