blob: e37035542c7e8adb9b5a082fb8f4109ba3f66ba5 (
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.classification import NaiveBayes
from pyspark.ml.evaluation import MulticlassClassificationEvaluator
# $example off$
from pyspark.sql import SparkSession
if __name__ == "__main__":
spark = SparkSession.builder.appName("naive_bayes_example").getOrCreate()
# $example on$
# Load training data
data = spark.read.format("libsvm") \
.load("data/mllib/sample_libsvm_data.txt")
# Split the data into train and test
splits = data.randomSplit([0.6, 0.4], 1234)
train = splits[0]
test = splits[1]
# create the trainer and set its parameters
nb = NaiveBayes(smoothing=1.0, modelType="multinomial")
# train the model
model = nb.fit(train)
# compute precision on the test set
result = model.transform(test)
predictionAndLabels = result.select("prediction", "label")
evaluator = MulticlassClassificationEvaluator(metricName="precision")
print("Precision:" + str(evaluator.evaluate(predictionAndLabels)))
# $example off$
spark.stop()
|