From 91a577d2778ab5946f0c40cb80c89de24e3d10e8 Mon Sep 17 00:00:00 2001
From: Yuhao Yang <hhbyyh@gmail.com>
Date: Tue, 8 Sep 2015 22:33:23 -0700
Subject: [PATCH] [SPARK-10249] [ML] [DOC] Add Python Code Example to
StopWordsRemover User Guide
jira: https://issues.apache.org/jira/browse/SPARK-10249
update user guide since python support added.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes #8620 from hhbyyh/swPyDocExample.
---
docs/ml-features.md | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/docs/ml-features.md b/docs/ml-features.md
index 90654d1e5a..58b31a5a5c 100644
--- a/docs/ml-features.md
+++ b/docs/ml-features.md
@@ -512,6 +512,25 @@ DataFrame dataset = jsql.createDataFrame(rdd, schema);
remover.transform(dataset).show();
{% endhighlight %}
</div>
+
+<div data-lang="python" markdown="1">
+[`StopWordsRemover`](api/python/pyspark.ml.html#pyspark.ml.feature.StopWordsRemover)
+takes an input column name, an output column name, a list of stop words,
+and a boolean indicating if the matches should be case sensitive (false
+by default).
+
+{% highlight python %}
+from pyspark.ml.feature import StopWordsRemover
+
+sentenceData = sqlContext.createDataFrame([
+ (0, ["I", "saw", "the", "red", "baloon"]),
+ (1, ["Mary", "had", "a", "little", "lamb"])
+], ["label", "raw"])
+
+remover = StopWordsRemover(inputCol="raw", outputCol="filtered")
+remover.transform(sentenceData).show(truncate=False)
+{% endhighlight %}
+</div>
</div>
## $n$-gram
--
GitLab