diff options
Diffstat (limited to 'docs/ml-features.md')
-rw-r--r-- | docs/ml-features.md | 23 |
1 files changed, 19 insertions, 4 deletions
diff --git a/docs/ml-features.md b/docs/ml-features.md index cec2cbe673..6b2e36b353 100644 --- a/docs/ml-features.md +++ b/docs/ml-features.md @@ -1212,7 +1212,7 @@ v_N This example below demonstrates how to transform vectors using a transforming vector value. <div class="codetabs"> -<div data-lang="scala"> +<div data-lang="scala" markdown="1"> {% highlight scala %} import org.apache.spark.ml.feature.ElementwiseProduct import org.apache.spark.mllib.linalg.Vectors @@ -1229,12 +1229,12 @@ val transformer = new ElementwiseProduct() .setOutputCol("transformedVector") // Batch transform the vectors to create new column: -val transformedData = transformer.transform(dataFrame) +transformer.transform(dataFrame).show() {% endhighlight %} </div> -<div data-lang="java"> +<div data-lang="java" markdown="1"> {% highlight java %} import com.google.common.collect.Lists; @@ -1267,10 +1267,25 @@ ElementwiseProduct transformer = new ElementwiseProduct() .setInputCol("vector") .setOutputCol("transformedVector"); // Batch transform the vectors to create new column: -DataFrame transformedData = transformer.transform(dataFrame); +transformer.transform(dataFrame).show(); {% endhighlight %} </div> + +<div data-lang="python" markdown="1"> +{% highlight python %} +from pyspark.ml.feature import ElementwiseProduct +from pyspark.mllib.linalg import Vectors + +data = [(Vectors.dense([1.0, 2.0, 3.0]),), (Vectors.dense([4.0, 5.0, 6.0]),)] +df = sqlContext.createDataFrame(data, ["vector"]) +transformer = ElementwiseProduct(scalingVec=Vectors.dense([0.0, 1.0, 2.0]), + inputCol="vector", outputCol="transformedVector") +transformer.transform(df).show() + +{% endhighlight %} +</div> + </div> ## VectorAssembler |