Python pyspark GBTRegressor用法及代码示例

>>> from numpy import allclose
>>> from pyspark.ml.linalg import Vectors
>>> df = spark.createDataFrame([
...     (1.0, Vectors.dense(1.0)),
...     (0.0, Vectors.sparse(1, [], []))], ["label", "features"])
>>> gbt = GBTRegressor(maxDepth=2, seed=42, leafCol="leafId")
>>> gbt.setMaxIter(5)
GBTRegressor...
>>> gbt.setMinWeightFractionPerNode(0.049)
GBTRegressor...
>>> gbt.getMaxIter()
5
>>> print(gbt.getImpurity())
variance
>>> print(gbt.getFeatureSubsetStrategy())
all
>>> model = gbt.fit(df)
>>> model.featureImportances
SparseVector(1, {0: 1.0})
>>> model.numFeatures
1
>>> allclose(model.treeWeights, [1.0, 0.1, 0.1, 0.1, 0.1])
True
>>> test0 = spark.createDataFrame([(Vectors.dense(-1.0),)], ["features"])
>>> model.predict(test0.head().features)
0.0
>>> model.predictLeaf(test0.head().features)
DenseVector([0.0, 0.0, 0.0, 0.0, 0.0])
>>> result = model.transform(test0).head()
>>> result.prediction
0.0
>>> result.leafId
DenseVector([0.0, 0.0, 0.0, 0.0, 0.0])
>>> test1 = spark.createDataFrame([(Vectors.sparse(1, [0], [1.0]),)], ["features"])
>>> model.transform(test1).head().prediction
1.0
>>> gbtr_path = temp_path + "gbtr"
>>> gbt.save(gbtr_path)
>>> gbt2 = GBTRegressor.load(gbtr_path)
>>> gbt2.getMaxDepth()
2
>>> model_path = temp_path + "gbtr_model"
>>> model.save(model_path)
>>> model2 = GBTRegressionModel.load(model_path)
>>> model.featureImportances == model2.featureImportances
True
>>> model.treeWeights == model2.treeWeights
True
>>> model.transform(test0).take(1) == model2.transform(test0).take(1)
True
>>> model.trees
[DecisionTreeRegressionModel...depth=..., DecisionTreeRegressionModel...]
>>> validation = spark.createDataFrame([(0.0, Vectors.dense(-1.0))],
...              ["label", "features"])
>>> model.evaluateEachIteration(validation, "squared")
[0.0, 0.0, 0.0, 0.0, 0.0]
>>> gbt = gbt.setValidationIndicatorCol("validationIndicator")
>>> gbt.getValidationIndicatorCol()
'validationIndicator'
>>> gbt.getValidationTol()
0.01