blob: 540a4bc3e4bf98641823fe4a44b22f6cd317872a (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
|
#
# 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 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 SparkSession
"""
A simple example demonstrating a bisecting k-means clustering.
"""
if __name__ == "__main__":
spark = SparkSession\
.builder\
.appName("PythonBisectingKMeansExample")\
.getOrCreate()
# $example on$
data = spark.read.text("data/mllib/kmeans_data.txt").rdd
parsed = data\
.map(lambda row: Row(features=Vectors.dense([float(x) for x in row.value.split(' ')])))
training = spark.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)
# $example off$
spark.stop()
|