def getBanditData(dataset, logger, frac, count):
alterDataset = DatasetReader.DatasetReader(copy_dataset=dataset,
verbose=False)
alterDataset.trainFeatures = dataset.testFeatures
alterDataset.trainLabels = dataset.testLabels
streamer = Logger.DataStream(dataset=alterDataset, verbose=False)
replayed_dataset = DatasetReader.DatasetReader(copy_dataset=alterDataset,
verbose=False)
features, labels = streamer.generateStream(subsampleFrac=frac,
replayCount=count)
replayed_dataset.trainFeatures = features
replayed_dataset.trainLabels = labels
sampledLabels, sampledLogPropensity, sampledLoss = logger.generateLog(
replayed_dataset)
bandit_dataset = DatasetReader.BanditDataset(dataset=replayed_dataset,
verbose=False)
replayed_dataset.freeAuxiliaryMatrices()
del replayed_dataset
alterDataset.freeAuxiliaryMatrices()
del alterDataset
bandit_dataset.registerSampledData(sampledLabels, sampledLogPropensity,
sampledLoss)
return bandit_dataset
def getLogger(dataset, frac):
streamer = Logger.DataStream(dataset=dataset, verbose=False)
features, labels = streamer.generateStream(subsampleFrac=frac,
replayCount=1)
subsampled_dataset = DatasetReader.DatasetReader(copy_dataset=dataset,
verbose=False)
subsampled_dataset.trainFeatures = features
subsampled_dataset.trainLabels = labels
logger = Logger.Logger(subsampled_dataset,
loggerC=-1,
stochasticMultiplier=1,
verbose=False)
subsampled_dataset.freeAuxiliaryMatrices()
del subsampled_dataset
return logger
svm_scores.append(svm.test())
crf = Skylines.CRF(dataset=supervised_dataset,
tol=1e-6,
minC=-2,
maxC=2,
verbose=True,
parallel=pool)
crf_time.append(crf.validate())
crf_scores.append(crf.test())
crf_expected_scores.append(crf.expectedTestLoss())
supervised_dataset.freeAuxiliaryMatrices()
del supervised_dataset
streamer = Logger.DataStream(dataset=dataset, verbose=True)
features, labels = streamer.generateStream(subsampleFrac=0.05,
replayCount=1)
subsampled_dataset = DatasetReader.DatasetReader(
copy_dataset=dataset, verbose=True)
subsampled_dataset.trainFeatures = features
subsampled_dataset.trainLabels = labels
logger = Logger.Logger(subsampled_dataset,
loggerC=-1,
stochasticMultiplier=1,
verbose=True)
logger_map_scores.append(logger.crf.test())
logger_scores.append(logger.crf.expectedTestLoss())
replayed_dataset = DatasetReader.DatasetReader(
