Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/7263#discussion_r36046871
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
---
@@ -146,6 +148,40 @@ class Word2VecModel private[ml] (
wordVectors: feature.Word2VecModel)
extends Model[Word2VecModel] with Word2VecBase {
+
+ /**
+ * Returns a dataframe with two fields, "word" and "vector", with "word"
being a String and
+ * and the vector the DenseVector that it is mapped to.
+ */
+ val getVectors: DataFrame = {
+ val sc = SparkContext.getOrCreate()
+ val sqlContext = SQLContext.getOrCreate(sc)
+ import sqlContext.implicits._
+ val wordVec = wordVectors.getVectors.mapValues(vec =>
Vectors.dense(vec.map(_.toDouble)))
+ sc.parallelize(wordVec.toSeq).toDF("word", "vector")
+ }
+
+ /**
+ * Find "num" no. words closest in similarity to the given word.
+ * Returns a dataframe with the words and the cosine similarities
between the
+ * synonyms and the given word.
+ */
+ def findSynonyms(word: String, num: Int): DataFrame = {
+ findSynonyms(wordVectors.transform(word), num)
+ }
+
+ /**
+ * Find "num" no. words closest to similarity to the vector
representation of the word.
--- End diff --
"Find "num" number of words closest in similarity to the given vector
representation of a word."
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
