Github user yinxusen commented on a diff in the pull request:
https://github.com/apache/spark/pull/10002#discussion_r46079541
--- Diff: docs/ml-features.md ---
@@ -408,37 +278,7 @@
ngramDataFrame.take(3).map(_.getAs[Stream[String]]("ngrams").toList).foreach(pri
Refer to the [NGram Java
docs](api/java/org/apache/spark/ml/feature/NGram.html)
for more details on the API.
-{% highlight java %}
-import java.util.Arrays;
-
-import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.ml.feature.NGram;
-import org.apache.spark.mllib.linalg.Vector;
-import org.apache.spark.sql.DataFrame;
-import org.apache.spark.sql.Row;
-import org.apache.spark.sql.RowFactory;
-import org.apache.spark.sql.types.DataTypes;
-import org.apache.spark.sql.types.Metadata;
-import org.apache.spark.sql.types.StructField;
-import org.apache.spark.sql.types.StructType;
-
-JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
- RowFactory.create(0.0, Arrays.asList("Hi", "I", "heard", "about",
"Spark")),
- RowFactory.create(1.0, Arrays.asList("I", "wish", "Java", "could",
"use", "case", "classes")),
- RowFactory.create(2.0, Arrays.asList("Logistic", "regression", "models",
"are", "neat"))
-));
-StructType schema = new StructType(new StructField[]{
- new StructField("label", DataTypes.DoubleType, false, Metadata.empty()),
- new StructField("words",
DataTypes.createArrayType(DataTypes.StringType), false, Metadata.empty())
-});
-DataFrame wordDataFrame = sqlContext.createDataFrame(jrdd, schema);
-NGram ngramTransformer = new
NGram().setInputCol("words").setOutputCol("ngrams");
-DataFrame ngramDataFrame = ngramTransformer.transform(wordDataFrame);
-for (Row r : ngramDataFrame.select("ngrams", "label").take(3)) {
- java.util.List<String> ngrams = r.getList(0);
- for (String ngram : ngrams) System.out.print(ngram + " --- ");
- System.out.println();
-}
+{% include_example java/org/apache/spark/examples/ml/JavaNGramExample.java
%}
{% endhighlight %}
--- End diff --
Pls remove this line
---
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]
