From bf0bb39b79e9075b10f2764ba5a3e9ff691725a3 Mon Sep 17 00:00:00 2001
From: Nicolas R <nicapps23@gmail.com>
Date: Tue, 4 Oct 2016 17:26:49 +0200
Subject: [PATCH 1/2] Added the PrefixSpan MLlib example based on the current
 documentation

---
 .../main/python/mllib/prefix_span_example.py  | 38 +++++++++++++++++++
 1 file changed, 38 insertions(+)
 create mode 100644 examples/src/main/python/mllib/prefix_span_example.py

diff --git a/examples/src/main/python/mllib/prefix_span_example.py b/examples/src/main/python/mllib/prefix_span_example.py
new file mode 100644
index 000000000000..3ecad105488a
--- /dev/null
+++ b/examples/src/main/python/mllib/prefix_span_example.py
@@ -0,0 +1,38 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# $example on$
+from pyspark.mllib.fpm import PrefixSpan
+# $example off$
+from pyspark import SparkContext
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="PythonPrefixSpanExample")
+
+    # $example on$
+    sequences = sc.parallelize([
+        [[1,2],[3]],
+        [[1],[3,2],[1,2]],
+        [[1,2],[5]],
+        [[6]],
+    ])
+
+    model = PrefixSpan.train(sequences, minSupport=0.5, maxPatternLength=5)
+    result = model.freqSequences().collect()
+    for fs in result:
+        print('{}, {}'.format(fs.sequence,fs.freq))
+    # $example off$

From bead90c9d1033877f112716d2f67ed1809f8ca23 Mon Sep 17 00:00:00 2001
From: Nicolas R <nicapps23@gmail.com>
Date: Fri, 4 Nov 2016 10:20:38 +0100
Subject: [PATCH 2/2] updated the doc for the Python version of PrefixSpan

---
 docs/mllib-frequent-pattern-mining.md | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/docs/mllib-frequent-pattern-mining.md b/docs/mllib-frequent-pattern-mining.md
index 93e3f0b2d226..16d03c9d3059 100644
--- a/docs/mllib-frequent-pattern-mining.md
+++ b/docs/mllib-frequent-pattern-mining.md
@@ -177,6 +177,20 @@ Refer to the [`PrefixSpan` Java docs](api/java/org/apache/spark/mllib/fpm/Prefix
 
 {% include_example java/org/apache/spark/examples/mllib/JavaPrefixSpanExample.java %}
 
+</div>
+
+<div data-lang="python" markdown="1">
+
+[`PrefixSpan`](api/python/pyspark.mllib.html#pyspark.mllib.fpm.PrefixSpan) implements the
+PrefixSpan algorithm.
+Calling `PrefixSpan.run` returns a
+[`PrefixSpanModel`](api/python/pyspark.mllib.html#pyspark.mllib.fpm.PrefixSpanModel)
+that stores the frequent sequences with their frequencies.
+
+Refer to the [`PrefixSpan` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.fpm.PrefixSpan) and [`PrefixSpanModel` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.fpm.PrefixSpanModel) for details on the API.
+
+{% include_example python/mllib/prefix_span_example.py %}
+
 </div>
 </div>