blob: 7d9d80e6452bd014e7cabd2c02a49331269cbebc (
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
59
60
61
62
63
64
65
66
67
68
|
#
# 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
import sys
import numpy as np
from pyspark.ml.clustering import KMeans, KMeansModel
from pyspark.mllib.linalg import VectorUDT, _convert_to_vector
from pyspark.sql import SparkSession
from pyspark.sql.types import Row, StructField, StructType
"""
A simple example demonstrating a k-means clustering.
Run with:
bin/spark-submit examples/src/main/python/ml/kmeans_example.py <input> <k>
This example requires NumPy (http://www.numpy.org/).
"""
def parseVector(row):
array = np.array([float(x) for x in row.value.split(' ')])
return _convert_to_vector(array)
if __name__ == "__main__":
FEATURES_COL = "features"
if len(sys.argv) != 3:
print("Usage: kmeans_example.py <file> <k>", file=sys.stderr)
exit(-1)
path = sys.argv[1]
k = sys.argv[2]
spark = SparkSession.builder.appName("PythonKMeansExample").getOrCreate()
lines = spark.read.text(path).rdd
data = lines.map(parseVector)
row_rdd = data.map(lambda x: Row(x))
schema = StructType([StructField(FEATURES_COL, VectorUDT(), False)])
df = spark.createDataFrame(row_rdd, schema)
kmeans = KMeans().setK(2).setSeed(1).setFeaturesCol(FEATURES_COL)
model = kmeans.fit(df)
centers = model.clusterCenters()
print("Cluster Centers: ")
for center in centers:
print(center)
spark.stop()
|