blob: 146f41c1dd90309b6fd9a93646ab94c00eac10ef (
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
|
#
# 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
from pyspark.sql import SQLContext
# $example on$
from pyspark.ml.feature import VectorIndexer
# $example off$
if __name__ == "__main__":
sc = SparkContext(appName="VectorIndexerExample")
sqlContext = SQLContext(sc)
# $example on$
data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
indexer = VectorIndexer(inputCol="features", outputCol="indexed", maxCategories=10)
indexerModel = indexer.fit(data)
# Create new column "indexed" with categorical values transformed to indices
indexedData = indexerModel.transform(data)
indexedData.show()
# $example off$
sc.stop()
|
