# 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 synapse.ml.core.serialize.java_params_patch import *
from pyspark.ml.wrapper import JavaTransformer, JavaEstimator, JavaModel
from pyspark.ml.evaluation import JavaEvaluator
from pyspark.ml.common import inherit_doc
from synapse.ml.core.schema.Utils import *
from pyspark.ml.param import TypeConverters
from synapse.ml.core.schema.TypeConversionUtils import generateTypeConverter, complexTypeConverter
from synapse.ml.recommendation.SARModel import SARModel
[docs]@inherit_doc
class SAR(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaEstimator):
"""
Args:
activityTimeFormat (object): Time format for events, default: yyyy/MM/dd'T'h:mm:ss
alpha (float): alpha for implicit preference
blockSize (int): block size for stacking input data in matrices. Data is stacked within partitions. If block size is more than remaining data in a partition then it is adjusted to the size of this data.
checkpointInterval (int): set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext
coldStartStrategy (object): strategy for dealing with unknown or new users/items at prediction time. This may be useful in cross-validation or production scenarios, for handling user/item ids the model has not seen in the training data. Supported values: nan,drop.
finalStorageLevel (object): StorageLevel for ALS model factors.
implicitPrefs (bool): whether to use implicit preference
intermediateStorageLevel (object): StorageLevel for intermediate datasets. Cannot be 'NONE'.
itemCol (object): column name for item ids. Ids must be within the integer value range.
maxIter (int): maximum number of iterations (>= 0)
nonnegative (bool): whether to use nonnegative constraint for least squares
numItemBlocks (int): number of item blocks
numUserBlocks (int): number of user blocks
predictionCol (object): prediction column name
rank (int): rank of the factorization
ratingCol (object): column name for ratings
regParam (float): regularization parameter (>= 0)
seed (long): random seed
similarityFunction (object): Defines the similarity function to be used by the model. Lift favors serendipity, Co-occurrence favors predictability, and Jaccard is a nice compromise between the two.
startTime (object): Set time custom now time if using historical data
startTimeFormat (object): Format for start time
supportThreshold (int): Minimum number of ratings per item
timeCol (object): Time of activity
timeDecayCoeff (int): Use to scale time decay coeff to different half life dur
userCol (object): column name for user ids. Ids must be within the integer value range.
"""
activityTimeFormat = Param(Params._dummy(), "activityTimeFormat", "Time format for events, default: yyyy/MM/dd'T'h:mm:ss")
alpha = Param(Params._dummy(), "alpha", "alpha for implicit preference", typeConverter=TypeConverters.toFloat)
blockSize = Param(Params._dummy(), "blockSize", "block size for stacking input data in matrices. Data is stacked within partitions. If block size is more than remaining data in a partition then it is adjusted to the size of this data.", typeConverter=TypeConverters.toInt)
checkpointInterval = Param(Params._dummy(), "checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext", typeConverter=TypeConverters.toInt)
coldStartStrategy = Param(Params._dummy(), "coldStartStrategy", "strategy for dealing with unknown or new users/items at prediction time. This may be useful in cross-validation or production scenarios, for handling user/item ids the model has not seen in the training data. Supported values: nan,drop.")
finalStorageLevel = Param(Params._dummy(), "finalStorageLevel", "StorageLevel for ALS model factors.")
implicitPrefs = Param(Params._dummy(), "implicitPrefs", "whether to use implicit preference", typeConverter=TypeConverters.toBoolean)
intermediateStorageLevel = Param(Params._dummy(), "intermediateStorageLevel", "StorageLevel for intermediate datasets. Cannot be 'NONE'.")
itemCol = Param(Params._dummy(), "itemCol", "column name for item ids. Ids must be within the integer value range.")
maxIter = Param(Params._dummy(), "maxIter", "maximum number of iterations (>= 0)", typeConverter=TypeConverters.toInt)
nonnegative = Param(Params._dummy(), "nonnegative", "whether to use nonnegative constraint for least squares", typeConverter=TypeConverters.toBoolean)
numItemBlocks = Param(Params._dummy(), "numItemBlocks", "number of item blocks", typeConverter=TypeConverters.toInt)
numUserBlocks = Param(Params._dummy(), "numUserBlocks", "number of user blocks", typeConverter=TypeConverters.toInt)
predictionCol = Param(Params._dummy(), "predictionCol", "prediction column name")
rank = Param(Params._dummy(), "rank", "rank of the factorization", typeConverter=TypeConverters.toInt)
ratingCol = Param(Params._dummy(), "ratingCol", "column name for ratings")
regParam = Param(Params._dummy(), "regParam", "regularization parameter (>= 0)", typeConverter=TypeConverters.toFloat)
seed = Param(Params._dummy(), "seed", "random seed")
similarityFunction = Param(Params._dummy(), "similarityFunction", "Defines the similarity function to be used by the model. Lift favors serendipity, Co-occurrence favors predictability, and Jaccard is a nice compromise between the two.")
startTime = Param(Params._dummy(), "startTime", "Set time custom now time if using historical data")
startTimeFormat = Param(Params._dummy(), "startTimeFormat", "Format for start time")
supportThreshold = Param(Params._dummy(), "supportThreshold", "Minimum number of ratings per item", typeConverter=TypeConverters.toInt)
timeCol = Param(Params._dummy(), "timeCol", "Time of activity")
timeDecayCoeff = Param(Params._dummy(), "timeDecayCoeff", "Use to scale time decay coeff to different half life dur", typeConverter=TypeConverters.toInt)
userCol = Param(Params._dummy(), "userCol", "column name for user ids. Ids must be within the integer value range.")
@keyword_only
def __init__(
self,
java_obj=None,
activityTimeFormat="yyyy/MM/dd'T'h:mm:ss",
alpha=1.0,
blockSize=4096,
checkpointInterval=10,
coldStartStrategy="nan",
finalStorageLevel="MEMORY_AND_DISK",
implicitPrefs=False,
intermediateStorageLevel="MEMORY_AND_DISK",
itemCol="item",
maxIter=10,
nonnegative=False,
numItemBlocks=10,
numUserBlocks=10,
predictionCol="prediction",
rank=10,
ratingCol="rating",
regParam=0.1,
seed=356704333,
similarityFunction="jaccard",
startTime=None,
startTimeFormat="EEE MMM dd HH:mm:ss Z yyyy",
supportThreshold=4,
timeCol="time",
timeDecayCoeff=30,
userCol="user"
):
super(SAR, self).__init__()
if java_obj is None:
self._java_obj = self._new_java_obj("com.microsoft.azure.synapse.ml.recommendation.SAR", self.uid)
else:
self._java_obj = java_obj
self._setDefault(activityTimeFormat="yyyy/MM/dd'T'h:mm:ss")
self._setDefault(alpha=1.0)
self._setDefault(blockSize=4096)
self._setDefault(checkpointInterval=10)
self._setDefault(coldStartStrategy="nan")
self._setDefault(finalStorageLevel="MEMORY_AND_DISK")
self._setDefault(implicitPrefs=False)
self._setDefault(intermediateStorageLevel="MEMORY_AND_DISK")
self._setDefault(itemCol="item")
self._setDefault(maxIter=10)
self._setDefault(nonnegative=False)
self._setDefault(numItemBlocks=10)
self._setDefault(numUserBlocks=10)
self._setDefault(predictionCol="prediction")
self._setDefault(rank=10)
self._setDefault(ratingCol="rating")
self._setDefault(regParam=0.1)
self._setDefault(seed=356704333)
self._setDefault(similarityFunction="jaccard")
self._setDefault(startTimeFormat="EEE MMM dd HH:mm:ss Z yyyy")
self._setDefault(supportThreshold=4)
self._setDefault(timeCol="time")
self._setDefault(timeDecayCoeff=30)
self._setDefault(userCol="user")
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
if java_obj is None:
for k,v in kwargs.items():
if v is not None:
getattr(self, "set" + k[0].upper() + k[1:])(v)
[docs] @keyword_only
def setParams(
self,
activityTimeFormat="yyyy/MM/dd'T'h:mm:ss",
alpha=1.0,
blockSize=4096,
checkpointInterval=10,
coldStartStrategy="nan",
finalStorageLevel="MEMORY_AND_DISK",
implicitPrefs=False,
intermediateStorageLevel="MEMORY_AND_DISK",
itemCol="item",
maxIter=10,
nonnegative=False,
numItemBlocks=10,
numUserBlocks=10,
predictionCol="prediction",
rank=10,
ratingCol="rating",
regParam=0.1,
seed=356704333,
similarityFunction="jaccard",
startTime=None,
startTimeFormat="EEE MMM dd HH:mm:ss Z yyyy",
supportThreshold=4,
timeCol="time",
timeDecayCoeff=30,
userCol="user"
):
"""
Set the (keyword only) parameters
"""
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
return self._set(**kwargs)
[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.azure.synapse.ml.recommendation.SAR"
@staticmethod
def _from_java(java_stage):
module_name=SAR.__module__
module_name=module_name.rsplit(".", 1)[0] + ".SAR"
return from_java(java_stage, module_name)
[docs] def setAlpha(self, value):
"""
Args:
alpha: alpha for implicit preference
"""
self._set(alpha=value)
return self
[docs] def setBlockSize(self, value):
"""
Args:
blockSize: block size for stacking input data in matrices. Data is stacked within partitions. If block size is more than remaining data in a partition then it is adjusted to the size of this data.
"""
self._set(blockSize=value)
return self
[docs] def setCheckpointInterval(self, value):
"""
Args:
checkpointInterval: set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext
"""
self._set(checkpointInterval=value)
return self
[docs] def setColdStartStrategy(self, value):
"""
Args:
coldStartStrategy: strategy for dealing with unknown or new users/items at prediction time. This may be useful in cross-validation or production scenarios, for handling user/item ids the model has not seen in the training data. Supported values: nan,drop.
"""
self._set(coldStartStrategy=value)
return self
[docs] def setFinalStorageLevel(self, value):
"""
Args:
finalStorageLevel: StorageLevel for ALS model factors.
"""
self._set(finalStorageLevel=value)
return self
[docs] def setImplicitPrefs(self, value):
"""
Args:
implicitPrefs: whether to use implicit preference
"""
self._set(implicitPrefs=value)
return self
[docs] def setItemCol(self, value):
"""
Args:
itemCol: column name for item ids. Ids must be within the integer value range.
"""
self._set(itemCol=value)
return self
[docs] def setMaxIter(self, value):
"""
Args:
maxIter: maximum number of iterations (>= 0)
"""
self._set(maxIter=value)
return self
[docs] def setNonnegative(self, value):
"""
Args:
nonnegative: whether to use nonnegative constraint for least squares
"""
self._set(nonnegative=value)
return self
[docs] def setNumItemBlocks(self, value):
"""
Args:
numItemBlocks: number of item blocks
"""
self._set(numItemBlocks=value)
return self
[docs] def setNumUserBlocks(self, value):
"""
Args:
numUserBlocks: number of user blocks
"""
self._set(numUserBlocks=value)
return self
[docs] def setPredictionCol(self, value):
"""
Args:
predictionCol: prediction column name
"""
self._set(predictionCol=value)
return self
[docs] def setRank(self, value):
"""
Args:
rank: rank of the factorization
"""
self._set(rank=value)
return self
[docs] def setRatingCol(self, value):
"""
Args:
ratingCol: column name for ratings
"""
self._set(ratingCol=value)
return self
[docs] def setRegParam(self, value):
"""
Args:
regParam: regularization parameter (>= 0)
"""
self._set(regParam=value)
return self
[docs] def setSeed(self, value):
"""
Args:
seed: random seed
"""
self._set(seed=value)
return self
[docs] def setSimilarityFunction(self, value):
"""
Args:
similarityFunction: Defines the similarity function to be used by the model. Lift favors serendipity, Co-occurrence favors predictability, and Jaccard is a nice compromise between the two.
"""
self._set(similarityFunction=value)
return self
[docs] def setStartTime(self, value):
"""
Args:
startTime: Set time custom now time if using historical data
"""
self._set(startTime=value)
return self
[docs] def setSupportThreshold(self, value):
"""
Args:
supportThreshold: Minimum number of ratings per item
"""
self._set(supportThreshold=value)
return self
[docs] def setTimeCol(self, value):
"""
Args:
timeCol: Time of activity
"""
self._set(timeCol=value)
return self
[docs] def setTimeDecayCoeff(self, value):
"""
Args:
timeDecayCoeff: Use to scale time decay coeff to different half life dur
"""
self._set(timeDecayCoeff=value)
return self
[docs] def setUserCol(self, value):
"""
Args:
userCol: column name for user ids. Ids must be within the integer value range.
"""
self._set(userCol=value)
return self
[docs] def getAlpha(self):
"""
Returns:
alpha: alpha for implicit preference
"""
return self.getOrDefault(self.alpha)
[docs] def getBlockSize(self):
"""
Returns:
blockSize: block size for stacking input data in matrices. Data is stacked within partitions. If block size is more than remaining data in a partition then it is adjusted to the size of this data.
"""
return self.getOrDefault(self.blockSize)
[docs] def getCheckpointInterval(self):
"""
Returns:
checkpointInterval: set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext
"""
return self.getOrDefault(self.checkpointInterval)
[docs] def getColdStartStrategy(self):
"""
Returns:
coldStartStrategy: strategy for dealing with unknown or new users/items at prediction time. This may be useful in cross-validation or production scenarios, for handling user/item ids the model has not seen in the training data. Supported values: nan,drop.
"""
return self.getOrDefault(self.coldStartStrategy)
[docs] def getFinalStorageLevel(self):
"""
Returns:
finalStorageLevel: StorageLevel for ALS model factors.
"""
return self.getOrDefault(self.finalStorageLevel)
[docs] def getImplicitPrefs(self):
"""
Returns:
implicitPrefs: whether to use implicit preference
"""
return self.getOrDefault(self.implicitPrefs)
[docs] def getItemCol(self):
"""
Returns:
itemCol: column name for item ids. Ids must be within the integer value range.
"""
return self.getOrDefault(self.itemCol)
[docs] def getMaxIter(self):
"""
Returns:
maxIter: maximum number of iterations (>= 0)
"""
return self.getOrDefault(self.maxIter)
[docs] def getNonnegative(self):
"""
Returns:
nonnegative: whether to use nonnegative constraint for least squares
"""
return self.getOrDefault(self.nonnegative)
[docs] def getNumItemBlocks(self):
"""
Returns:
numItemBlocks: number of item blocks
"""
return self.getOrDefault(self.numItemBlocks)
[docs] def getNumUserBlocks(self):
"""
Returns:
numUserBlocks: number of user blocks
"""
return self.getOrDefault(self.numUserBlocks)
[docs] def getPredictionCol(self):
"""
Returns:
predictionCol: prediction column name
"""
return self.getOrDefault(self.predictionCol)
[docs] def getRank(self):
"""
Returns:
rank: rank of the factorization
"""
return self.getOrDefault(self.rank)
[docs] def getRatingCol(self):
"""
Returns:
ratingCol: column name for ratings
"""
return self.getOrDefault(self.ratingCol)
[docs] def getRegParam(self):
"""
Returns:
regParam: regularization parameter (>= 0)
"""
return self.getOrDefault(self.regParam)
[docs] def getSeed(self):
"""
Returns:
seed: random seed
"""
return self.getOrDefault(self.seed)
[docs] def getSimilarityFunction(self):
"""
Returns:
similarityFunction: Defines the similarity function to be used by the model. Lift favors serendipity, Co-occurrence favors predictability, and Jaccard is a nice compromise between the two.
"""
return self.getOrDefault(self.similarityFunction)
[docs] def getStartTime(self):
"""
Returns:
startTime: Set time custom now time if using historical data
"""
return self.getOrDefault(self.startTime)
[docs] def getSupportThreshold(self):
"""
Returns:
supportThreshold: Minimum number of ratings per item
"""
return self.getOrDefault(self.supportThreshold)
[docs] def getTimeCol(self):
"""
Returns:
timeCol: Time of activity
"""
return self.getOrDefault(self.timeCol)
[docs] def getTimeDecayCoeff(self):
"""
Returns:
timeDecayCoeff: Use to scale time decay coeff to different half life dur
"""
return self.getOrDefault(self.timeDecayCoeff)
[docs] def getUserCol(self):
"""
Returns:
userCol: column name for user ids. Ids must be within the integer value range.
"""
return self.getOrDefault(self.userCol)
def _create_model(self, java_model):
try:
model = SARModel(java_obj=java_model)
model._transfer_params_from_java()
except TypeError:
model = SARModel._from_java(java_model)
return model
def _fit(self, dataset):
java_model = self._fit_java(dataset)
return self._create_model(java_model)