# Copyright (C) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See LICENSE in project root for information.
import sys
if sys.version >= '3':
basestring = str
from pyspark import SparkContext, SQLContext
from pyspark.sql import DataFrame
from pyspark.ml.param.shared import *
from pyspark import keyword_only
from pyspark.ml.util import JavaMLReadable, JavaMLWritable
from mmlspark.core.serialize.java_params_patch import *
from pyspark.ml.evaluation import JavaEvaluator
from pyspark.ml.common import inherit_doc
from mmlspark.core.schema.Utils import *
[docs]@inherit_doc
class RankingEvaluator(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaEvaluator):
"""
Args:
itemCol (str): Column of items
k (int): number of items (default: 10)
labelCol (str): label column name (default: label)
metricName (str): metric name in evaluation (ndcgAt|map|precisionAtk|recallAtK|diversityAtK|maxDiversity|mrr|fcp) (default: ndcgAt)
nItems (long): number of items (default: -1)
predictionCol (str): prediction column name (default: prediction)
ratingCol (str): Column of ratings
userCol (str): Column of users
"""
@keyword_only
def __init__(self, itemCol=None, k=10, labelCol="label", metricName="ndcgAt", nItems=-1, predictionCol="prediction", ratingCol=None, userCol=None):
super(RankingEvaluator, self).__init__()
self._java_obj = self._new_java_obj("com.microsoft.ml.spark.recommendation.RankingEvaluator")
self.itemCol = Param(self, "itemCol", "itemCol: Column of items")
self.k = Param(self, "k", "k: number of items (default: 10)")
self._setDefault(k=10)
self.labelCol = Param(self, "labelCol", "labelCol: label column name (default: label)")
self._setDefault(labelCol="label")
self.metricName = Param(self, "metricName", "metricName: metric name in evaluation (ndcgAt|map|precisionAtk|recallAtK|diversityAtK|maxDiversity|mrr|fcp) (default: ndcgAt)")
self._setDefault(metricName="ndcgAt")
self.nItems = Param(self, "nItems", "nItems: number of items (default: -1)")
self._setDefault(nItems=-1)
self.predictionCol = Param(self, "predictionCol", "predictionCol: prediction column name (default: prediction)")
self._setDefault(predictionCol="prediction")
self.ratingCol = Param(self, "ratingCol", "ratingCol: Column of ratings")
self.userCol = Param(self, "userCol", "userCol: Column of users")
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
self.setParams(**kwargs)
[docs] @keyword_only
def setParams(self, itemCol=None, k=10, labelCol="label", metricName="ndcgAt", nItems=-1, predictionCol="prediction", ratingCol=None, userCol=None):
"""
Set the (keyword only) parameters
Args:
itemCol (str): Column of items
k (int): number of items (default: 10)
labelCol (str): label column name (default: label)
metricName (str): metric name in evaluation (ndcgAt|map|precisionAtk|recallAtK|diversityAtK|maxDiversity|mrr|fcp) (default: ndcgAt)
nItems (long): number of items (default: -1)
predictionCol (str): prediction column name (default: prediction)
ratingCol (str): Column of ratings
userCol (str): Column of users
"""
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
return self._set(**kwargs)
[docs] def getItemCol(self):
"""
Returns:
str: Column of items
"""
return self.getOrDefault(self.itemCol)
[docs] def getK(self):
"""
Returns:
int: number of items (default: 10)
"""
return self.getOrDefault(self.k)
[docs] def getLabelCol(self):
"""
Returns:
str: label column name (default: label)
"""
return self.getOrDefault(self.labelCol)
[docs] def getMetricName(self):
"""
Returns:
str: metric name in evaluation (ndcgAt|map|precisionAtk|recallAtK|diversityAtK|maxDiversity|mrr|fcp) (default: ndcgAt)
"""
return self.getOrDefault(self.metricName)
[docs] def getNItems(self):
"""
Returns:
long: number of items (default: -1)
"""
return self.getOrDefault(self.nItems)
[docs] def getPredictionCol(self):
"""
Returns:
str: prediction column name (default: prediction)
"""
return self.getOrDefault(self.predictionCol)
[docs] def getRatingCol(self):
"""
Returns:
str: Column of ratings
"""
return self.getOrDefault(self.ratingCol)
[docs] def getUserCol(self):
"""
Returns:
str: Column of users
"""
return self.getOrDefault(self.userCol)
[docs] def setItemCol(self, value):
"""
Args:
itemCol: Column of items
"""
self._set(itemCol=value)
return self
[docs] def setK(self, value):
"""
Args:
k: number of items (default: 10)
"""
self._set(k=value)
return self
[docs] def setLabelCol(self, value):
"""
Args:
labelCol: label column name (default: label)
"""
self._set(labelCol=value)
return self
[docs] def setMetricName(self, value):
"""
Args:
metricName: metric name in evaluation (ndcgAt|map|precisionAtk|recallAtK|diversityAtK|maxDiversity|mrr|fcp) (default: ndcgAt)
"""
self._set(metricName=value)
return self
[docs] def setNItems(self, value):
"""
Args:
nItems: number of items (default: -1)
"""
self._set(nItems=value)
return self
[docs] def setPredictionCol(self, value):
"""
Args:
predictionCol: prediction column name (default: prediction)
"""
self._set(predictionCol=value)
return self
[docs] def setRatingCol(self, value):
"""
Args:
ratingCol: Column of ratings
"""
self._set(ratingCol=value)
return self
[docs] def setUserCol(self, value):
"""
Args:
userCol: Column of users
"""
self._set(userCol=value)
return self
[docs] @classmethod
def read(cls):
""" Returns an MLReader instance for this class. """
return JavaMMLReader(cls)
[docs] @staticmethod
def getJavaPackage():
""" Returns package name String. """
return "com.microsoft.ml.spark.recommendation.RankingEvaluator"
@staticmethod
def _from_java(java_stage):
module_name=RankingEvaluator.__module__
module_name=module_name.rsplit(".", 1)[0] + ".RankingEvaluator"
return from_java(java_stage, module_name)