Github user Krimit commented on a diff in the pull request:

    https://github.com/apache/spark/pull/16811#discussion_r99612768
  
    --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala 
---
    @@ -232,19 +232,40 @@ class Word2VecModel private[ml] (
       @Since("1.5.0")
       def findSynonyms(word: String, num: Int): DataFrame = {
         val spark = SparkSession.builder().getOrCreate()
    -    spark.createDataFrame(wordVectors.findSynonyms(word, 
num)).toDF("word", "similarity")
    +    spark.createDataFrame(findSynonymsLocal(word, num)).toDF("word", 
"similarity")
       }
     
       /**
    -   * Find "num" number of words whose vector representation most similar 
to the supplied vector.
    +   * Find "num" number of words whose vector representation is most 
similar to the supplied vector.
        * If the supplied vector is the vector representation of a word in the 
model's vocabulary,
        * that word will be in the results.  Returns a dataframe with the words 
and the cosine
        * similarities between the synonyms and the given word vector.
        */
       @Since("2.0.0")
       def findSynonyms(vec: Vector, num: Int): DataFrame = {
         val spark = SparkSession.builder().getOrCreate()
    -    spark.createDataFrame(wordVectors.findSynonyms(vec, num)).toDF("word", 
"similarity")
    +    spark.createDataFrame(findSynonymsLocal(vec, num)).toDF("word", 
"similarity")
    +  }
    +
    +  /**
    +   * Find "num" number of words whose vector representation is most 
similar to the supplied vector.
    +   * If the supplied vector is the vector representation of a word in the 
model's vocabulary,
    +   * that word will be in the results. Returns an array of the words and 
the cosine
    +   * similarities between the synonyms and the given word vector.
    +   */
    +  @Since("2.2.0")
    +  def findSynonymsLocal(vec: Vector, num: Int): Array[(String, Double)] = {
    +    wordVectors.findSynonyms(vec, num)
    +  }
    +
    +  /**
    +   * Find "num" number of words closest in similarity to the given word, 
not
    +   * including the word itself. Returns a dataframe with the words and the
    --- End diff --
    
    🔍 


---
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]

Reply via email to