kmeans_example.py
1.94 KB
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
59
60
61
62
#
# 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.
#
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import print_function
# $example on$
from pyspark.ml.clustering import KMeans
# $example off$
from pyspark.sql import SparkSession
"""
An example demonstrating k-means clustering.
Run with:
bin/spark-submit examples/src/main/python/ml/kmeans_example.py
This example requires NumPy (http://www.numpy.org/).
"""
if __name__ == "__main__":
spark = SparkSession\
.builder\
.appName("PythonKMeansExample")\
.getOrCreate()
# 例子
# 加载数据
dataset = spark.read.format("libsvm").load("sample_kmeans_data.txt")#加载数据
# Trains a k-means model.
kmeans = KMeans().setK(2).setSeed(1) #k-means 模型
model = kmeans.fit(dataset) #建立模型
# Evaluate clustering by computing Within Set Sum of Squared Errors.通过计算误差项平方和内的聚类分析
wssse = model.computeCost(dataset)
print("Within Set Sum of Squared Errors = " + str(wssse))
# 显示结果 clusterCenters 聚类中心
centers = model.clusterCenters()
print("Cluster Centers: ")
for center in centers:
print(center)
# $example off$
spark.stop()