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
|
#
# 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.
#
"""
Pipeline Example.
"""
# $example on$
from pyspark.ml import Pipeline
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.feature import HashingTF, Tokenizer
# $example off$
from pyspark.sql import SparkSession
if __name__ == "__main__":
spark = SparkSession\
.builder\
.appName("PipelineExample")\
.getOrCreate()
# $example on$
# Prepare training documents from a list of (id, text, label) tuples.
training = spark.createDataFrame([
(0L, "a b c d e spark", 1.0),
(1L, "b d", 0.0),
(2L, "spark f g h", 1.0),
(3L, "hadoop mapreduce", 0.0)], ["id", "text", "label"])
# Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr.
tokenizer = Tokenizer(inputCol="text", outputCol="words")
hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(), outputCol="features")
lr = LogisticRegression(maxIter=10, regParam=0.01)
pipeline = Pipeline(stages=[tokenizer, hashingTF, lr])
# Fit the pipeline to training documents.
model = pipeline.fit(training)
# Prepare test documents, which are unlabeled (id, text) tuples.
test = spark.createDataFrame([
(4L, "spark i j k"),
(5L, "l m n"),
(6L, "mapreduce spark"),
(7L, "apache hadoop")], ["id", "text"])
# Make predictions on test documents and print columns of interest.
prediction = model.transform(test)
selected = prediction.select("id", "text", "prediction")
for row in selected.collect():
print(row)
# $example off$
spark.stop()
|
