Skip to content
Snippets Groups Projects
Commit d18276cb authored by Zheng RuiFeng's avatar Zheng RuiFeng Committed by Nick Pentreath
Browse files

[SPARK-13672][ML] Add python examples of BisectingKMeans in ML and MLLIB

JIRA: https://issues.apache.org/jira/browse/SPARK-13672

## What changes were proposed in this pull request?

add two python examples of BisectingKMeans for ml and mllib

## How was this patch tested?

manual tests

Author: Zheng RuiFeng <ruifengz@foxmail.com>

Closes #11515 from zhengruifeng/mllib_bkm_pe.
parent e33bc67c
No related branches found
No related tags found
No related merge requests found
......@@ -399,6 +399,12 @@ Refer to the [`BisectingKMeans` Java docs](api/java/org/apache/spark/mllib/clust
{% include_example java/org/apache/spark/examples/mllib/JavaBisectingKMeansExample.java %}
</div>
<div data-lang="python" markdown="1">
Refer to the [`BisectingKMeans` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.clustering.BisectingKMeans) and [`BisectingKMeansModel` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.clustering.BisectingKMeansModel) for more details on the API.
{% include_example python/mllib/bisecting_k_means_example.py %}
</div>
</div>
## Streaming k-means
......
#
# 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.
#
from __future__ import print_function
from pyspark import SparkContext
# $example on$
from pyspark.ml.clustering import BisectingKMeans, BisectingKMeansModel
from pyspark.mllib.linalg import VectorUDT, _convert_to_vector, Vectors
from pyspark.mllib.linalg import Vectors
from pyspark.sql.types import Row
# $example off$
from pyspark.sql import SQLContext
"""
A simple example demonstrating a bisecting k-means clustering.
"""
if __name__ == "__main__":
sc = SparkContext(appName="PythonBisectingKMeansExample")
sqlContext = SQLContext(sc)
# $example on$
data = sc.textFile("data/mllib/kmeans_data.txt")
parsed = data.map(lambda l: Row(features=Vectors.dense([float(x) for x in l.split(' ')])))
training = sqlContext.createDataFrame(parsed)
kmeans = BisectingKMeans().setK(2).setSeed(1).setFeaturesCol("features")
model = kmeans.fit(training)
# Evaluate clustering
cost = model.computeCost(training)
print("Bisecting K-means Cost = " + str(cost))
centers = model.clusterCenters()
print("Cluster Centers: ")
for center in centers:
print(center)
# $example off$
sc.stop()
#
# 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.
#
from __future__ import print_function
# $example on$
from numpy import array
# $example off$
from pyspark import SparkContext
# $example on$
from pyspark.mllib.clustering import BisectingKMeans, BisectingKMeansModel
# $example off$
if __name__ == "__main__":
sc = SparkContext(appName="PythonBisectingKMeansExample") # SparkContext
# $example on$
# Load and parse the data
data = sc.textFile("data/mllib/kmeans_data.txt")
parsedData = data.map(lambda line: array([float(x) for x in line.split(' ')]))
# Build the model (cluster the data)
model = BisectingKMeans.train(parsedData, 2, maxIterations=5)
# Evaluate clustering
cost = model.computeCost(parsedData)
print("Bisecting K-means Cost = " + str(cost))
# Save and load model
path = "target/org/apache/spark/PythonBisectingKMeansExample/BisectingKMeansModel"
model.save(sc, path)
sameModel = BisectingKMeansModel.load(sc, path)
# $example off$
sc.stop()
......@@ -142,6 +142,7 @@ class BisectingKMeans(object):
.. versionadded:: 2.0.0
"""
@classmethod
@since('2.0.0')
def train(self, rdd, k=4, maxIterations=20, minDivisibleClusterSize=1.0, seed=-1888008604):
"""
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment