[SPARK-14931][ML][PYTHON] Mismatched default values between pipelines in Spark and PySpark - update

## What changes were proposed in this pull request?

This PR is an update for [https://github.com/apache/spark/pull/12738] which:
* Adds a generic unit test for JavaParams wrappers in pyspark.ml for checking default Param values vs. the defaults in the Scala side
* Various fixes for bugs found
  * This includes changing classes taking weightCol to treat unset and empty String Param values the same way.

Defaults changed:
* Scala
 * LogisticRegression: weightCol defaults to not set (instead of empty string)
 * StringIndexer: labels default to not set (instead of empty array)
 * GeneralizedLinearRegression:
   * maxIter always defaults to 25 (simpler than defaulting to 25 for a particular solver)
   * weightCol defaults to not set (instead of empty string)
 * LinearRegression: weightCol defaults to not set (instead of empty string)
* Python
 * MultilayerPerceptron: layers default to not set (instead of [1,1])
 * ChiSqSelector: numTopFeatures defaults to 50 (instead of not set)

## How was this patch tested?

Generic unit test.  Manually tested that unit test by changing defaults and verifying that broke the test.

Author: Joseph K. Bradley <joseph@databricks.com>
Author: yinxusen <yinxusen@gmail.com>

Closes #12816 from jkbradley/yinxusen-SPARK-14931.

5 files changed, 62 insertions, 12 deletions

diff --git a/python/pyspark/ml/classification.py b/python/pyspark/ml/classification.py
index f616c7fbec..4331f73b73 100644
--- a/python/pyspark/ml/classification.py
+++ b/python/pyspark/ml/classification.py
@@ -1056,7 +1056,7 @@ class MultilayerPerceptronClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol,
 
     layers = Param(Params._dummy(), "layers", "Sizes of layers from input layer to output layer " +
                    "E.g., Array(780, 100, 10) means 780 inputs, one hidden layer with 100 " +
-                   "neurons and output layer of 10 neurons, default is [1, 1].",
+                   "neurons and output layer of 10 neurons.",
                    typeConverter=TypeConverters.toListInt)
     blockSize = Param(Params._dummy(), "blockSize", "Block size for stacking input data in " +
                       "matrices. Data is stacked within partitions. If block size is more than " +
@@ -1069,12 +1069,12 @@ class MultilayerPerceptronClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol,
                  maxIter=100, tol=1e-4, seed=None, layers=None, blockSize=128):
         """
         __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
-                 maxIter=100, tol=1e-4, seed=None, layers=[1, 1], blockSize=128)
+                 maxIter=100, tol=1e-4, seed=None, layers=None, blockSize=128)
         """
         super(MultilayerPerceptronClassifier, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.classification.MultilayerPerceptronClassifier", self.uid)
-        self._setDefault(maxIter=100, tol=1E-4, layers=[1, 1], blockSize=128)
+        self._setDefault(maxIter=100, tol=1E-4, blockSize=128)
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)
 
@@ -1084,14 +1084,11 @@ class MultilayerPerceptronClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol,
                   maxIter=100, tol=1e-4, seed=None, layers=None, blockSize=128):
         """
         setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
-                  maxIter=100, tol=1e-4, seed=None, layers=[1, 1], blockSize=128)
+                  maxIter=100, tol=1e-4, seed=None, layers=None, blockSize=128)
         Sets params for MultilayerPerceptronClassifier.
         """
         kwargs = self.setParams._input_kwargs
-        if layers is None:
-            return self._set(**kwargs).setLayers([1, 1])
-        else:
-            return self._set(**kwargs)
+        return self._set(**kwargs)
 
     def _create_model(self, java_model):
         return MultilayerPerceptronClassificationModel(java_model)
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index 1b059a7199..b95d288198 100644
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -2617,6 +2617,7 @@ class ChiSqSelector(JavaEstimator, HasFeaturesCol, HasOutputCol, HasLabelCol, Ja
         """
         super(ChiSqSelector, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.ChiSqSelector", self.uid)
+        self._setDefault(numTopFeatures=50)
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)
 
diff --git a/python/pyspark/ml/regression.py b/python/pyspark/ml/regression.py
index d490953f79..0f08f9b973 100644
--- a/python/pyspark/ml/regression.py
+++ b/python/pyspark/ml/regression.py
@@ -1080,7 +1080,8 @@ class AFTSurvivalRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
     @keyword_only
     def __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction",
                  fitIntercept=True, maxIter=100, tol=1E-6, censorCol="censor",
-                 quantileProbabilities=None, quantilesCol=None):
+                 quantileProbabilities=list([0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99]),
+                 quantilesCol=None):
         """
         __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
                  fitIntercept=True, maxIter=100, tol=1E-6, censorCol="censor", \
@@ -1091,7 +1092,8 @@ class AFTSurvivalRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.regression.AFTSurvivalRegression", self.uid)
         self._setDefault(censorCol="censor",
-                         quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99])
+                         quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99],
+                         maxIter=100, tol=1E-6)
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)
 
@@ -1099,7 +1101,8 @@ class AFTSurvivalRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
     @since("1.6.0")
     def setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction",
                   fitIntercept=True, maxIter=100, tol=1E-6, censorCol="censor",
-                  quantileProbabilities=None, quantilesCol=None):
+                  quantileProbabilities=list([0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99]),
+                  quantilesCol=None):
         """
         setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
                   fitIntercept=True, maxIter=100, tol=1E-6, censorCol="censor", \
diff --git a/python/pyspark/ml/tests.py b/python/pyspark/ml/tests.py
index d5dd6d43c2..78ec96af8a 100644
--- a/python/pyspark/ml/tests.py
+++ b/python/pyspark/ml/tests.py
@@ -41,6 +41,7 @@ else:
 from shutil import rmtree
 import tempfile
 import numpy as np
+import inspect
 
 from pyspark import keyword_only
 from pyspark.ml import Estimator, Model, Pipeline, PipelineModel, Transformer
@@ -54,6 +55,7 @@ from pyspark.ml.recommendation import ALS
 from pyspark.ml.regression import LinearRegression, DecisionTreeRegressor
 from pyspark.ml.tuning import *
 from pyspark.ml.wrapper import JavaParams
+from pyspark.mllib.common import _java2py
 from pyspark.mllib.linalg import Vectors, DenseVector, SparseVector
 from pyspark.sql import DataFrame, SQLContext, Row
 from pyspark.sql.functions import rand
@@ -1026,6 +1028,52 @@ class ALSTest(PySparkTestCase):
         self.assertEqual(als._java_obj.getFinalStorageLevel(), "DISK_ONLY")
 
 
+class DefaultValuesTests(PySparkTestCase):
+    """
+    Test :py:class:`JavaParams` classes to see if their default Param values match
+    those in their Scala counterparts.
+    """
+
+    def check_params(self, py_stage):
+        if not hasattr(py_stage, "_to_java"):
+            return
+        java_stage = py_stage._to_java()
+        if java_stage is None:
+            return
+        for p in py_stage.params:
+            java_param = java_stage.getParam(p.name)
+            py_has_default = py_stage.hasDefault(p)
+            java_has_default = java_stage.hasDefault(java_param)
+            self.assertEqual(py_has_default, java_has_default,
+                             "Default value mismatch of param %s for Params %s"
+                             % (p.name, str(py_stage)))
+            if py_has_default:
+                if p.name == "seed":
+                    return  # Random seeds between Spark and PySpark are different
+                java_default =\
+                    _java2py(self.sc, java_stage.clear(java_param).getOrDefault(java_param))
+                py_stage._clear(p)
+                py_default = py_stage.getOrDefault(p)
+                self.assertEqual(java_default, py_default,
+                                 "Java default %s != python default %s of param %s for Params %s"
+                                 % (str(java_default), str(py_default), p.name, str(py_stage)))
+
+    def test_java_params(self):
+        import pyspark.ml.feature
+        import pyspark.ml.classification
+        import pyspark.ml.clustering
+        import pyspark.ml.pipeline
+        import pyspark.ml.recommendation
+        import pyspark.ml.regression
+        modules = [pyspark.ml.feature, pyspark.ml.classification, pyspark.ml.clustering,
+                   pyspark.ml.pipeline, pyspark.ml.recommendation, pyspark.ml.regression]
+        for module in modules:
+            for name, cls in inspect.getmembers(module, inspect.isclass):
+                if not name.endswith('Model') and issubclass(cls, JavaParams)\
+                        and not inspect.isabstract(cls):
+                    self.check_params(cls())
+
+
 if __name__ == "__main__":
     from pyspark.ml.tests import *
     if xmlrunner:
diff --git a/python/pyspark/ml/wrapper.py b/python/pyspark/ml/wrapper.py
index fef626c7fa..fef0040faf 100644
--- a/python/pyspark/ml/wrapper.py
+++ b/python/pyspark/ml/wrapper.py
@@ -110,7 +110,8 @@ class JavaParams(JavaWrapper, Params):
         for param in self.params:
             if self._java_obj.hasParam(param.name):
                 java_param = self._java_obj.getParam(param.name)
-                if self._java_obj.isDefined(java_param):
+                # SPARK-14931: Only check set params back to avoid default params mismatch.
+                if self._java_obj.isSet(java_param):
                     value = _java2py(sc, self._java_obj.getOrDefault(java_param))
                     self._set(**{param.name: value})