Python pyspark IsotonicRegression用法及代码示例

>>> from pyspark.ml.linalg import Vectors
>>> df = spark.createDataFrame([
...     (1.0, Vectors.dense(1.0)),
...     (0.0, Vectors.sparse(1, [], []))], ["label", "features"])
>>> ir = IsotonicRegression()
>>> model = ir.fit(df)
>>> model.setFeaturesCol("features")
IsotonicRegressionModel...
>>> model.numFeatures
1
>>> test0 = spark.createDataFrame([(Vectors.dense(-1.0),)], ["features"])
>>> model.transform(test0).head().prediction
0.0
>>> model.predict(test0.head().features[model.getFeatureIndex()])
0.0
>>> model.boundaries
DenseVector([0.0, 1.0])
>>> ir_path = temp_path + "/ir"
>>> ir.save(ir_path)
>>> ir2 = IsotonicRegression.load(ir_path)
>>> ir2.getIsotonic()
True
>>> model_path = temp_path + "/ir_model"
>>> model.save(model_path)
>>> model2 = IsotonicRegressionModel.load(model_path)
>>> model.boundaries == model2.boundaries
True
>>> model.predictions == model2.predictions
True
>>> model.transform(test0).take(1) == model2.transform(test0).take(1)
True