Github user BryanCutler commented on a diff in the pull request:
https://github.com/apache/spark/pull/21465#discussion_r238809338
--- Diff: python/pyspark/ml/classification.py ---
@@ -1242,40 +1255,36 @@ class GBTClassifier(JavaEstimator, HasFeaturesCol,
HasLabelCol, HasPredictionCol
[0.25..., 0.23..., 0.21..., 0.19..., 0.18...]
>>> model.numClasses
2
+ >>> gbt = gbt.setValidationIndicatorCol("validationIndicator")
+ >>> gbt.getValidationIndicatorCol()
+ 'validationIndicator'
+ >>> gbt.getValidationTol()
+ 0.01
.. versionadded:: 1.4.0
"""
- lossType = Param(Params._dummy(), "lossType",
- "Loss function which GBT tries to minimize
(case-insensitive). " +
- "Supported options: " + ",
".join(GBTParams.supportedLossTypes),
- typeConverter=TypeConverters.toString)
-
- stepSize = Param(Params._dummy(), "stepSize",
- "Step size (a.k.a. learning rate) in interval (0, 1]
for shrinking " +
- "the contribution of each estimator.",
- typeConverter=TypeConverters.toFloat)
-
@keyword_only
def __init__(self, featuresCol="features", labelCol="label",
predictionCol="prediction",
maxDepth=5, maxBins=32, minInstancesPerNode=1,
minInfoGain=0.0,
maxMemoryInMB=256, cacheNodeIds=False,
checkpointInterval=10, lossType="logistic",
- maxIter=20, stepSize=0.1, seed=None, subsamplingRate=1.0,
- featureSubsetStrategy="all"):
+ maxIter=20, stepSize=0.1, seed=None, subsamplingRate=1.0,
impurity="variance",
--- End diff --
this is not the correct default impurity
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
