aboutsummaryrefslogtreecommitdiff
path: root/examples/src/main/python/ml/onehot_encoder_example.py
blob: e1996c7f0a55b34537a27fd403fcca8e06e70441 (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
#
# 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.feature import OneHotEncoder, StringIndexer
# $example off$
from pyspark.sql import SparkSession

if __name__ == "__main__":
    spark = SparkSession\
        .builder\
        .appName("OneHotEncoderExample")\
        .getOrCreate()

    # $example on$
    df = spark.createDataFrame([
        (0, "a"),
        (1, "b"),
        (2, "c"),
        (3, "a"),
        (4, "a"),
        (5, "c")
    ], ["id", "category"])

    stringIndexer = StringIndexer(inputCol="category", outputCol="categoryIndex")
    model = stringIndexer.fit(df)
    indexed = model.transform(df)

    encoder = OneHotEncoder(inputCol="categoryIndex", outputCol="categoryVec")
    encoded = encoder.transform(indexed)
    encoded.show()
    # $example off$

    spark.stop()