def setUp(self):
NS_telephone = ps.EqualitySelector("own_telephone", b"yes")
NS_foreign_worker = ps.EqualitySelector("foreign_worker", b"yes")
NS_other_parties = ps.EqualitySelector("other_parties", b"none")
NS_personal = ps.EqualitySelector("personal_status", b'male single')
NS_job = ps.EqualitySelector("job", b'high qualif/self emp/mgmt')
NS_class = ps.EqualitySelector("class", b"bad")
o = [[NS_telephone], [NS_foreign_worker, NS_telephone],
[NS_other_parties, NS_telephone],
[NS_foreign_worker, NS_telephone, NS_personal],
[NS_telephone, NS_personal],
[NS_foreign_worker, NS_other_parties, NS_telephone], [NS_job],
[NS_class, NS_telephone], [NS_foreign_worker, NS_job],
[NS_foreign_worker, NS_other_parties, NS_telephone, NS_personal]]
self.result = list(map(ps.Conjunction, o))
self.qualities = [
383476.7679999999, 361710.05800000014, 345352.9920000001,
338205.08, 336857.8220000001, 323586.28200000006,
320306.81600000005, 300963.84599999996, 299447.332,
297422.98200000013
]
data = get_credit_data()
target = ps.NumericTarget('credit_amount')
searchSpace_Nominal = ps.create_nominal_selectors(
data, ignore=['credit_amount'])
searchSpace_Numeric = [
] #ps.create_numeric_selectors(data, ignore=['credit_amount'], nbins=10)
searchSpace = searchSpace_Nominal + searchSpace_Numeric
self.task = ps.SubgroupDiscoveryTask(
data,
target,
searchSpace,
result_set_size=10,
depth=5,
qf=ps.CountCallsInterestingMeasure(
ps.StandardQFNumeric(1, False, 'sum')))
############################################################ from pysubgroup.tests.DataSets import get_credit_data data = get_credit_data() np.random.seed(1111) target_variables = np.random.randint(low=0, high=2, size=1000) target_estimates = np.random.uniform(size=1000) target = ps.PredictionTarget(target_variables, target_estimates, roc_auc_score) searchSpace_Nominal = ps.create_nominal_selectors(data, ignore=['credit_amount']) searchSpace_Numeric = [] #ps.create_numeric_selectors(data, ignore=['credit_amount'], nbins=10) searchSpace = searchSpace_Nominal + searchSpace_Numeric task = ps.SubgroupDiscoveryTask(data, target, searchSpace, result_set_size=10, depth=5, qf=ps.CountCallsInterestingMeasure(ps.PredictionQFNumeric(1, False))) resultBS = ps.BeamSearch().execute(task) resultA = ps.Apriori(use_numba=False).execute(task) resultA_numba = ps.Apriori(use_numba=True).execute(task) resultSimpleDFS = ps.SimpleDFS().execute(task) resultDFS = ps.DFS(ps.BitSetRepresentation).execute(task) resultDFS.to_dataframe() ############################################################ ## Toy example using the default eval to generate answers ## ############################################################ np.random.seed(1111)
def test_BeamSearch_sum(self):
self.task.qf = ps.CountCallsInterestingMeasure(
ps.StandardQFNumeric(self.task.qf.a, False, 'sum'))
self.runAlgorithm(ps.BeamSearch(), "BeamSearch sum", self.result,
self.qualities, self.task)
def test_DFS_sum(self):
self.task.qf = ps.CountCallsInterestingMeasure(
ps.StandardQFNumeric(self.task.qf.a, False, 'sum'))
self.runAlgorithm(ps.DFS(ps.BitSetRepresentation), "DFS sum",
self.result, self.qualities, self.task)
def test_BeamSearch(self):
self.task.qf = ps.CountCallsInterestingMeasure(ps.PredictionQFNumeric(self.task.qf.a, False))
self.runAlgorithm(ps.BeamSearch(), "BeamSearch sum", self.result, self.qualities, self.task)
def test_DFS(self):
self.task.qf = ps.CountCallsInterestingMeasure(ps.PredictionQFNumeric(self.task.qf.a, False))
self.runAlgorithm(ps.DFS(ps.BitSetRepresentation), "DFS", self.DFSresult, self.DFSqualities, self.task)
def setUp(self):
#NS_all = ps.EqualitySelector(True)
NS_payment = ps.EqualitySelector("other_payment_plans",b"none")
NS_foreign_worker = ps.EqualitySelector("foreign_worker", b"yes")
NS_other_parties = ps.EqualitySelector("other_parties", b"none")
NS_housing = ps.EqualitySelector("housing", b'own')
NS_class = ps.EqualitySelector("class", b"good")
DFSo = [[NS_foreign_worker],
[NS_other_parties],
[NS_foreign_worker, NS_other_parties],
[NS_payment],
[NS_foreign_worker, NS_payment],
[NS_other_parties, NS_payment],
[NS_housing],
[NS_class],
[NS_foreign_worker, NS_other_parties, NS_payment]]
self.DFSresult = list(map(ps.Conjunction, DFSo))
self.DFSresult.insert(0,True)
self.DFSqualities = [500.4980179286455,
483.3153195123844,
459.2862838915471,
444.60343785358896,
398.25539855072464,
384.0460358056267,
362.090608537693,
355.0749649843413,
355.010575658835,
349.8188702669149]
o = [[NS_foreign_worker],
[NS_other_parties],
[NS_foreign_worker, NS_other_parties],
[NS_payment],
[NS_foreign_worker, NS_payment],
[NS_other_parties, NS_payment],
[NS_housing],
[NS_class],
[NS_foreign_worker, NS_other_parties, NS_payment],
[NS_foreign_worker, NS_housing]]
self.result = list(map(ps.Conjunction, o))
self.qualities = [483.3153195123844,
459.2862838915471,
444.60343785358896,
398.25539855072464,
384.0460358056267,
362.090608537693,
355.0749649843413,
355.010575658835,
349.8188702669149,
342.20780439530444]
np.random.seed(1111)
self.target_variables = np.random.randint(low=0, high=2, size=1000)
self.target_estimates = np.random.uniform(size=1000)
data = get_credit_data()
target = ps.PredictionTarget(self.target_variables, self.target_estimates, roc_auc_score)
searchSpace_Nominal = ps.create_nominal_selectors(data, ignore=['credit_amount'])
searchSpace_Numeric = [] #ps.create_numeric_selectors(data, ignore=['credit_amount'], nbins=10)
searchSpace = searchSpace_Nominal + searchSpace_Numeric
self.task = ps.SubgroupDiscoveryTask(data, target, searchSpace, result_set_size=10, depth=5, qf=ps.CountCallsInterestingMeasure(ps.PredictionQFNumeric(1, False)))