import constants
import realdata
import sklearn.metrics
# dataName = "breastcancer_5foldCV"
# dataName = "pima_5foldCV"
# dataName = "pyhsioNetWithMissing_5foldCV"
dataName = "heartDiseaseWithMissing_5foldCV"
resultsRecorder = experimentHelper.ResultsRecorder(len(constants.allFalsePositiveCosts))
readyForSaving = False
definedFeatureCosts = realdata.getFeaturesCosts(dataName)
for falsePositiveCost in constants.allFalsePositiveCosts:
falseNegativeCost = falsePositiveCost * constants.FN_TO_FP_RATIO
allBestSettings = numpy.zeros((constants.NUMBER_OF_FOLDS, 2), dtype = numpy.int)
for testFoldId in range(constants.NUMBER_OF_FOLDS):
print("*************************** GREEDY MISER *******************************************")
bestLambdaId, bestTreeId = evaluation.getBestParametersForGreedyMiser_asymmetric(dataName, definedFeatureCosts, testFoldId, falsePositiveCost, falseNegativeCost)
if variationName == DYNAMIC:
infoStr += "_" + densityRegressionModelName
if USE_UNLABELED_DATA:
infoStr += "_withUnlabeledData"
else:
infoStr += "_noUnlabeledData"
if variationName == FULL_MODEL:
infoStr = FULL_MODEL
else:
infoStr += "_" + FEATURE_SELECTION_METHOD
infoStr += "_" + classificationModelName
resultsRecorder = experimentHelper.ResultsRecorder(
len(ALL_FALSE_POSITIVE_COSTS))
for costId in range(len(ALL_FALSE_POSITIVE_COSTS)):
falsePositiveCost = ALL_FALSE_POSITIVE_COSTS[costId]
if COST_TYPE == "symmetricCost":
falseNegativeCost = falsePositiveCost
assert (dataName == "pima_5foldCV")
correctClassificationCost = -50.0 # in order to align to the setting in (Ji and Carin, 2007; Dulac-Arnold et al., 2012) for Diabetes.
misclassificationCosts = numpy.zeros((2, 2))
misclassificationCosts[0, 1] = falsePositiveCost
misclassificationCosts[1, 0] = falseNegativeCost
misclassificationCosts[0, 0] = correctClassificationCost
misclassificationCosts[1, 1] = correctClassificationCost
dataName = "breastcancer_5foldCV"
if dataName == "pima_5foldCV":
sameClassCost = -50.0 # set to -50.0 in order to compare to Li and Carin work
# assert(misclassificationCostsSymmetric == 400 or misclassificationCostsSymmetric == 800)
else:
sameClassCost = 0.0
NUMBER_OF_FOLDS = 5
allMisclassificationCostsSymmetric = [100.0, 200.0, 300.0, 400.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0]
resultsRecorder = experimentHelper.ResultsRecorder(len(allMisclassificationCostsSymmetric))
readyForSaving = False
for misclassificationCostsSymmetric in allMisclassificationCostsSymmetric:
validTotalCostsAllFolds = numpy.zeros(NUMBER_OF_FOLDS)
validFeatureCostsAllFolds = numpy.zeros(NUMBER_OF_FOLDS)
validMisClassificationCostsAllFolds = numpy.zeros(NUMBER_OF_FOLDS)
validAccuracyAllFolds = numpy.zeros(NUMBER_OF_FOLDS)
allTestFoldAvgBestTotalCostsValidResult = numpy.zeros(NUMBER_OF_FOLDS) # for analysis only
allBestSettings = numpy.zeros((NUMBER_OF_FOLDS, 2), dtype = numpy.int)
for testFoldId in range(NUMBER_OF_FOLDS):