1 from __future__ import print_function
2 from pyspark.ml.classification import MultilayerPerceptronClassifier
3 from pyspark.ml.evaluation import MulticlassClassificationEvaluator
4 from pyspark.sql import SparkSession
5
6 spark = SparkSession\
7 .builder.appName("multilayer_perceptron_classification_example").getOrCreate()
8
9 # 加载数据
10 data = spark.read.format("libsvm")\
11 .load("data/mllib/sample_multiclass_classification_data.txt")
12
13 # 切分训练集和测试集
14 splits = data.randomSplit([0.6, 0.4], 1234)
15 train = splits[0]
16 test = splits[1]
17
18 # 输入、隐层、隐层、输出个数
19 layers = [4, 5, 4, 3]
20
21 # 创建多层感知器
22 trainer = MultilayerPerceptronClassifier(maxIter=100, layers=layers, blockSize=128, seed=1234)
23
24 # 训练模型
25 model = trainer.fit(train)
26
27 # 预测和计算准确度
28 result = model.transform(test)
29 result.show()
30 predictionAndLabels = result.select("prediction", "label")
31 evaluator = MulticlassClassificationEvaluator(metricName="accuracy")
32 print("Test set accuracy = " + str(evaluator.evaluate(predictionAndLabels)))
33
34 spark.stop()
+-----+--------------------+----------+
|label| features|prediction|
+-----+--------------------+----------+
| 0.0|(4,[0,1,2,3],[-0....| 2.0|
| 0.0|(4,[0,1,2,3],[-0....| 0.0|
| 0.0|(4,[0,1,2,3],[-0....| 0.0|
| 0.0|(4,[0,1,2,3],[-0....| 2.0|
| 0.0|(4,[0,1,2,3],[-0....| 2.0|
| 0.0|(4,[0,1,2,3],[-1....| 2.0|
| 0.0|(4,[0,1,2,3],[0.1...| 0.0|
| 0.0|(4,[0,1,2,3],[0.2...| 0.0|
| 0.0|(4,[0,1,2,3],[0.3...| 0.0|
| 0.0|(4,[0,1,2,3],[0.3...| 0.0|
| 0.0|(4,[0,1,2,3],[0.3...| 0.0|
| 0.0|(4,[0,1,2,3],[0.4...| 0.0|
| 0.0|(4,[0,1,2,3],[0.5...| 0.0|
| 0.0|(4,[0,1,2,3],[0.7...| 0.0|
| 0.0|(4,[0,1,2,3],[0.8...| 0.0|
| 0.0|(4,[0,1,2,3],[1.0...| 0.0|
| 0.0|(4,[0,2,3],[0.166...| 0.0|
| 0.0|(4,[0,2,3],[0.388...| 0.0|
| 1.0|(4,[0,1,2,3],[-0....| 1.0|
| 1.0|(4,[0,1,2,3],[-0....| 1.0|
+-----+--------------------+----------+
only showing top 20 rows
Test set accuracy = 0.901960784314
