diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala index 731f7576c2335f3cfd3dc286b200a0ecfc0f12e4..f65f78299d1827ba5b9f8c8d974e8b7054beb474 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala @@ -158,6 +158,9 @@ class Word2Vec extends Serializable with Logging { .sortWith((a, b) => a.cn > b.cn) vocabSize = vocab.length + require(vocabSize > 0, "The vocabulary size should be > 0. You may need to check " + + "the setting of minCount, which could be large enough to remove all your words in sentences.") + var a = 0 while (a < vocabSize) { vocabHash += vocab(a).word -> a