本文整理匯總了Python中pyspark.ml.tuning.CrossValidator.getEstimator方法的典型用法代碼示例。如果您正苦於以下問題：Python CrossValidator.getEstimator方法的具體用法？Python CrossValidator.getEstimator怎麽用？Python CrossValidator.getEstimator使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類pyspark.ml.tuning.CrossValidator的用法示例。
在下文中一共展示了CrossValidator.getEstimator方法的3個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: test_save_load_simple_estimator
# 需要導入模塊: from pyspark.ml.tuning import CrossValidator [as 別名]
# 或者: from pyspark.ml.tuning.CrossValidator import getEstimator [as 別名]
def test_save_load_simple_estimator(self):
temp_path = tempfile.mkdtemp()
dataset = self.spark.createDataFrame(
[(Vectors.dense([0.0]), 0.0),
(Vectors.dense([0.4]), 1.0),
(Vectors.dense([0.5]), 0.0),
(Vectors.dense([0.6]), 1.0),
(Vectors.dense([1.0]), 1.0)] * 10,
["features", "label"])
lr = LogisticRegression()
grid = ParamGridBuilder().addGrid(lr.maxIter, [0, 1]).build()
evaluator = BinaryClassificationEvaluator()
# test save/load of CrossValidator
cv = CrossValidator(estimator=lr, estimatorParamMaps=grid, evaluator=evaluator)
cvModel = cv.fit(dataset)
cvPath = temp_path + "/cv"
cv.save(cvPath)
loadedCV = CrossValidator.load(cvPath)
self.assertEqual(loadedCV.getEstimator().uid, cv.getEstimator().uid)
self.assertEqual(loadedCV.getEvaluator().uid, cv.getEvaluator().uid)
self.assertEqual(loadedCV.getEstimatorParamMaps(), cv.getEstimatorParamMaps())
# test save/load of CrossValidatorModel
cvModelPath = temp_path + "/cvModel"
cvModel.save(cvModelPath)
loadedModel = CrossValidatorModel.load(cvModelPath)
self.assertEqual(loadedModel.bestModel.uid, cvModel.bestModel.uid)示例2: test_save_load_nested_estimator
# 需要導入模塊: from pyspark.ml.tuning import CrossValidator [as 別名]
# 或者: from pyspark.ml.tuning.CrossValidator import getEstimator [as 別名]
def test_save_load_nested_estimator(self):
temp_path = tempfile.mkdtemp()
dataset = self.spark.createDataFrame(
[(Vectors.dense([0.0]), 0.0),
(Vectors.dense([0.4]), 1.0),
(Vectors.dense([0.5]), 0.0),
(Vectors.dense([0.6]), 1.0),
(Vectors.dense([1.0]), 1.0)] * 10,
["features", "label"])
ova = OneVsRest(classifier=LogisticRegression())
lr1 = LogisticRegression().setMaxIter(100)
lr2 = LogisticRegression().setMaxIter(150)
grid = ParamGridBuilder().addGrid(ova.classifier, [lr1, lr2]).build()
evaluator = MulticlassClassificationEvaluator()
# test save/load of CrossValidator
cv = CrossValidator(estimator=ova, estimatorParamMaps=grid, evaluator=evaluator)
cvModel = cv.fit(dataset)
cvPath = temp_path + "/cv"
cv.save(cvPath)
loadedCV = CrossValidator.load(cvPath)
self.assertEqual(loadedCV.getEstimator().uid, cv.getEstimator().uid)
self.assertEqual(loadedCV.getEvaluator().uid, cv.getEvaluator().uid)
originalParamMap = cv.getEstimatorParamMaps()
loadedParamMap = loadedCV.getEstimatorParamMaps()
for i, param in enumerate(loadedParamMap):
for p in param:
if p.name == "classifier":
self.assertEqual(param[p].uid, originalParamMap[i][p].uid)
else:
self.assertEqual(param[p], originalParamMap[i][p])
# test save/load of CrossValidatorModel
cvModelPath = temp_path + "/cvModel"
cvModel.save(cvModelPath)
loadedModel = CrossValidatorModel.load(cvModelPath)
self.assertEqual(loadedModel.bestModel.uid, cvModel.bestModel.uid)示例3: test_copy
# 需要導入模塊: from pyspark.ml.tuning import CrossValidator [as 別名]
# 或者: from pyspark.ml.tuning.CrossValidator import getEstimator [as 別名]
def test_copy(self):
dataset = self.spark.createDataFrame([
(10, 10.0),
(50, 50.0),
(100, 100.0),
(500, 500.0)] * 10,
["feature", "label"])
iee = InducedErrorEstimator()
evaluator = RegressionEvaluator(metricName="rmse")
grid = (ParamGridBuilder()
.addGrid(iee.inducedError, [100.0, 0.0, 10000.0])
.build())
cv = CrossValidator(estimator=iee, estimatorParamMaps=grid, evaluator=evaluator)
cvCopied = cv.copy()
self.assertEqual(cv.getEstimator().uid, cvCopied.getEstimator().uid)
cvModel = cv.fit(dataset)
cvModelCopied = cvModel.copy()
for index in range(len(cvModel.avgMetrics)):
self.assertTrue(abs(cvModel.avgMetrics[index] - cvModelCopied.avgMetrics[index])
< 0.0001)