Python 在Spark中运行交叉验证估计器
所以我正在Spark中建立一个推荐系统。虽然我已经能够在具有初始手动输入超参数值的数据集上评估和运行算法。我想让交叉验证估计器从超参数值网格中进行选择,从而实现自动化。因此,我为同样的问题编写了以下函数Python 在Spark中运行交叉验证估计器,python,apache-spark,pyspark,apache-spark-mllib,Python,Apache Spark,Pyspark,Apache Spark Mllib,所以我正在Spark中建立一个推荐系统。虽然我已经能够在具有初始手动输入超参数值的数据集上评估和运行算法。我想让交叉验证估计器从超参数值网格中进行选择,从而实现自动化。因此,我为同样的问题编写了以下函数 def recommendation(train): """ This function trains a collaborative filtering algorithm on a ratings training data We use a Cross Vali
def recommendation(train):
""" This function trains a collaborative filtering
algorithm on a ratings training data
We use a Cross Validator and Grid Search to find the right hyper-parameter values
Param:
train----> training data
TUNING PARAMETERS:
alpha----> Alpha value to calculate the confidence matrix (only for implicit datasets)
rank-----> no. of latent factors of the resulting X, Y matrix
reg------> regularization parameter for penalising the X, Y factors
Returns:
model-> ALS model object
"""
from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
from pyspark.ml.evaluation import BinaryClassificationEvaluator
from pyspark.ml.recommendation import ALS
alsImplicit = ALS(implicitPrefs=True)
#model=als.fit(train)
paramMapImplicit = ParamGridBuilder() \
.addGrid(alsImplicit.rank, [20, 120]) \
.addGrid(alsImplicit.maxIter, [10, 15]) \
.addGrid(alsImplicit.regParam, [0.01, 1.0]) \
.addGrid(alsImplicit.alpha, [10.0, 40.0]) \
.build()
evaluator=BinaryClassificationEvaluator(rawPredictionCol="prediction", labelCol="rating",metricName="areaUnderROC")
# Build the recommendation model using ALS on the training data
#als = ALS(rank=120, maxIter=15, regParam=0.01, implicitPrefs=True)
#model = als.fit(train)
cvEstimator= CrossValidator(estimator=alsImplicit, estimatorParamMaps=paramMapImplicit, evaluator=evaluator)
cvModel=cvEstimator.fit(train)
return cvModel,evaluator
问题是,当我调用此函数时,会出现以下错误:
运行ALS功能以训练数据
但是,由于算法通过在主交叉验证程序类中的交叉验证数据集上测试来选择正确的超参数,因此在使用交叉验证程序估计器时,我不确定在交叉验证程序估计器运行时如何更改预测概率的数据类型
有人能在这里指导吗?可能是@LostInOverflow的副本,谢谢。但我不确定我是否完全理解了答案。它没有使用Spark的交叉验证方法。我想使用交叉验证程序来获得最佳模型。只需使用交叉验证程序进行尝试。我确实尝试了交叉验证程序。我想说的是,Cross_validator需要一个evaluator参数,并对其进行评估。由于模型变换方法的预测不是以数据类型作为向量,因此会产生误差
model,evaluator=recommendation(train)
---------------------------------------------------------------------------
IllegalArgumentException Traceback (most recent call last)
<ipython-input-21-ea5de889f984> in <module>()
1 # Running the ALS function to train the data
2
----> 3 model,evaluator=recommendation(train)
<ipython-input-15-0fb855b138b1> in recommendation(train)
138 cvEstimator= CrossValidator(estimator=alsImplicit, estimatorParamMaps=paramMapImplicit, evaluator=evaluator)
139
--> 140 cvModel=cvEstimator.fit(train)
141
142 return cvModel,evaluator
/Users/i854319/spark/python/pyspark/ml/pipeline.pyc in fit(self, dataset, params)
67 return self.copy(params)._fit(dataset)
68 else:
---> 69 return self._fit(dataset)
70 else:
71 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
/Users/i854319/spark/python/pyspark/ml/tuning.pyc in _fit(self, dataset)
239 model = est.fit(train, epm[j])
240 # TODO: duplicate evaluator to take extra params from input
--> 241 metric = eva.evaluate(model.transform(validation, epm[j]))
242 metrics[j] += metric
243
/Users/i854319/spark/python/pyspark/ml/evaluation.pyc in evaluate(self, dataset, params)
67 return self.copy(params)._evaluate(dataset)
68 else:
---> 69 return self._evaluate(dataset)
70 else:
71 raise ValueError("Params must be a param map but got %s." % type(params))
/Users/i854319/spark/python/pyspark/ml/evaluation.pyc in _evaluate(self, dataset)
97 """
98 self._transfer_params_to_java()
---> 99 return self._java_obj.evaluate(dataset._jdf)
100
101 def isLargerBetter(self):
/Users/i854319/spark/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py in __call__(self, *args)
811 answer = self.gateway_client.send_command(command)
812 return_value = get_return_value(
--> 813 answer, self.gateway_client, self.target_id, self.name)
814
815 for temp_arg in temp_args:
/Users/i854319/spark/python/pyspark/sql/utils.pyc in deco(*a, **kw)
51 raise AnalysisException(s.split(': ', 1)[1], stackTrace)
52 if s.startswith('java.lang.IllegalArgumentException: '):
---> 53 raise IllegalArgumentException(s.split(': ', 1)[1], stackTrace)
54 raise
55 return deco
IllegalArgumentException: u'requirement failed: Column prediction must be of type org.apache.spark.mllib.linalg.VectorUDT@f71b0bce but was actually FloatType.'
def calcEval(testDF,predictions,evaluator):
""" This function checks the evaluation metric for the recommendation algorithm
testDF-> Validation or Test data to check the evalutation metric on
"""
from pyspark.sql.functions import udf
from pyspark.mllib.linalg import VectorUDT, DenseVector
from pyspark.sql.types import DoubleType
from pyspark.ml.evaluation import BinaryClassificationEvaluator
#predictions=model.transform(testDF)
#print "Total Count of the predictions data is {}".format(predictions.count())
## Converting the Data Type of the Rating and Prediction column
as_prob = udf(lambda x: DenseVector([1-x,x]), VectorUDT())
predictions=predictions.withColumn("prediction", as_prob(predictions["prediction"]))
# Converting the Rating column to DoubleType()
#predictions=predictions.withColumn("rating", predictions["rating"].cast(DoubleType()))
predictions.show(5)
# Calculating the AUC
print evaluator.getMetricName(), "The AUC of the Model is {}".format(evaluator.evaluate(predictions))
print "The AUC under PR curve is {}".format(evaluator.evaluate(predictions, {evaluator.metricName: "areaUnderPR"}))