1 files changed, 17 insertions, 0 deletions
diff --git a/docs/mllib-feature-extraction.md b/docs/mllib-feature-extraction.md
index 886d71df47..197bc77d50 100644
--- a/docs/mllib-feature-extraction.md
+++ b/docs/mllib-feature-extraction.md
@@ -203,6 +203,23 @@ for((synonym, cosineSimilarity) <- synonyms) {
 }
 {% endhighlight %}
 </div>
+<div data-lang="python">
+{% highlight python %}
+from pyspark import SparkContext
+from pyspark.mllib.feature import Word2Vec
+
+sc = SparkContext(appName='Word2Vec')
+inp = sc.textFile("text8_lines").map(lambda row: row.split(" "))
+
+word2vec = Word2Vec()
+model = word2vec.fit(inp)
+
+synonyms = model.findSynonyms('china', 40)
+
+for word, cosine_distance in synonyms:
+    print "{}: {}".format(word, cosine_distance)
+{% endhighlight %}
+</div>
 </div>
 
 ## StandardScaler