Python pyspark MultilayerPerceptronClassifier用法及代码示例

>>> from pyspark.ml.linalg import Vectors
>>> df = spark.createDataFrame([
...     (0.0, Vectors.dense([0.0, 0.0])),
...     (1.0, Vectors.dense([0.0, 1.0])),
...     (1.0, Vectors.dense([1.0, 0.0])),
...     (0.0, Vectors.dense([1.0, 1.0]))], ["label", "features"])
>>> mlp = MultilayerPerceptronClassifier(layers=[2, 2, 2], seed=123)
>>> mlp.setMaxIter(100)
MultilayerPerceptronClassifier...
>>> mlp.getMaxIter()
100
>>> mlp.getBlockSize()
128
>>> mlp.setBlockSize(1)
MultilayerPerceptronClassifier...
>>> mlp.getBlockSize()
1
>>> model = mlp.fit(df)
>>> model.setFeaturesCol("features")
MultilayerPerceptronClassificationModel...
>>> model.getMaxIter()
100
>>> model.getLayers()
[2, 2, 2]
>>> model.weights.size
12
>>> testDF = spark.createDataFrame([
...     (Vectors.dense([1.0, 0.0]),),
...     (Vectors.dense([0.0, 0.0]),)], ["features"])
>>> model.predict(testDF.head().features)
1.0
>>> model.predictRaw(testDF.head().features)
DenseVector([-16.208, 16.344])
>>> model.predictProbability(testDF.head().features)
DenseVector([0.0, 1.0])
>>> model.transform(testDF).select("features", "prediction").show()
+---------+----------+
| features|prediction|
+---------+----------+
|[1.0,0.0]|       1.0|
|[0.0,0.0]|       0.0|
+---------+----------+
...
>>> mlp_path = temp_path + "/mlp"
>>> mlp.save(mlp_path)
>>> mlp2 = MultilayerPerceptronClassifier.load(mlp_path)
>>> mlp2.getBlockSize()
1
>>> model_path = temp_path + "/mlp_model"
>>> model.save(model_path)
>>> model2 = MultilayerPerceptronClassificationModel.load(model_path)
>>> model.getLayers() == model2.getLayers()
True
>>> model.weights == model2.weights
True
>>> model.transform(testDF).take(1) == model2.transform(testDF).take(1)
True
>>> mlp2 = mlp2.setInitialWeights(list(range(0, 12)))
>>> model3 = mlp2.fit(df)
>>> model3.weights != model2.weights
True
>>> model3.getLayers() == model.getLayers()
True