def setUp(self):
NS_checking = ps.EqualitySelector("checking_status", b"<0")
NS_foreign_worker = ps.EqualitySelector("foreign_worker", b"yes")
NS_other_parties = ps.EqualitySelector("other_parties", b"none")
NS_savings_status = ps.EqualitySelector("savings_status", b"<100")
NS_job = ps.EqualitySelector("job", b"skilled")
NS_dependents = ps.EqualitySelector("num_dependents", 1.0)
self.result = [
ps.Conjunction([NS_checking, NS_foreign_worker]),
ps.Conjunction([NS_checking]),
ps.Conjunction([NS_checking, NS_other_parties, NS_foreign_worker]),
ps.Conjunction([NS_checking, NS_other_parties]),
ps.Conjunction([NS_checking, NS_savings_status,
NS_foreign_worker]),
ps.Conjunction([NS_checking, NS_foreign_worker, NS_dependents]),
ps.Conjunction([NS_checking, NS_savings_status]),
ps.Conjunction([NS_checking, NS_dependents]),
ps.Conjunction([
NS_checking, NS_savings_status, NS_other_parties,
NS_foreign_worker
]),
ps.Conjunction([NS_checking, NS_job, NS_foreign_worker]),
ps.Conjunction([NS_checking, NS_savings_status, NS_other_parties]),
ps.Conjunction([NS_checking, NS_job]),
]
self.qualities = [
0.055299999999999995, 0.05280000000000001, 0.052300000000000006,
0.05059999999999999, 0.04959999999999999, 0.04870000000000001,
0.048299999999999996, 0.0474, 0.04660000000000001,
0.04550000000000001, 0.0452, 0.044399999999999995
]
data = get_credit_data()
target = ps.BinaryTarget('class', b'bad')
searchSpace_Nominal = ps.create_nominal_selectors(data,
ignore=['class'])
searchSpace_Numeric = ps.create_numeric_selectors(data,
ignore=['class'])
searchSpace = searchSpace_Nominal + searchSpace_Numeric
self.task = ps.SubgroupDiscoveryTask(data,
target,
searchSpace,
result_set_size=12,
depth=5,
qf=ps.StandardQF(1.0))
def setUp(self):
NS_checking = ps.EqualitySelector("checking_status", b"<0")
NS_foreign_worker = ps.EqualitySelector("foreign_worker", b"yes")
NS_other_parties = ps.EqualitySelector("other_parties", b"none")
NS_savings_status = ps.EqualitySelector("savings_status", b"<100")
NS_job = ps.EqualitySelector("job", b"skilled")
NS_dependents = ps.EqualitySelector("num_dependents", 1.0)
self.result = [ps.Conjunction([NS_checking, NS_foreign_worker, NS_job, NS_other_parties, NS_savings_status]), # AND job=='b'skilled'' AND other_parties=='b'none'' AND savings_status=='b'<100'
# 0.113713540226172: checking_status=='b'<0'' AND foreign_worker=='b'yes'' AND job=='b'skilled'' AND savings_status=='b'<100''
ps.Conjunction([NS_checking, NS_foreign_worker, NS_job, NS_savings_status]),
ps.Conjunction([NS_checking, NS_foreign_worker, NS_job]), # checking_status=='b'<0'' AND foreign_worker=='b'yes'' AND job=='b'skilled''
# checking_status=='b'<0'' AND job=='b'skilled'' AND other_parties=='b'none'' AND savings_status=='b'<100''
ps.Conjunction([NS_checking, NS_job, NS_other_parties, NS_savings_status]),
ps.Conjunction([NS_checking, NS_foreign_worker, NS_job, NS_other_parties]),
ps.Conjunction([NS_checking, NS_job, NS_savings_status]),
ps.Conjunction([NS_checking, NS_foreign_worker, NS_other_parties, NS_savings_status]),
ps.Conjunction([NS_checking, NS_foreign_worker, NS_other_parties]),
ps.Conjunction([NS_checking, NS_foreign_worker, NS_savings_status]),
ps.Conjunction([NS_checking, NS_foreign_worker]),
ps.Conjunction([NS_checking, NS_foreign_worker, NS_job, NS_dependents, NS_savings_status]),
ps.Conjunction([NS_checking, NS_job, NS_other_parties])]
self.qualities = [0.11457431093955019,
0.113713540226172,
0.11201325679119281,
0.1117538749727658,
0.11161046793076415,
0.11145710640046322,
0.11045259291161472,
0.10929088624672183,
0.10875519439407161,
0.10866138825404954,
0.10832735026213287,
0.10813405094128754]
data = get_credit_data()
target = ps.BinaryTarget('class', b'bad')
searchSpace_Nominal = ps.create_nominal_selectors(data, ignore=['class'])
searchSpace_Numeric = ps.create_numeric_selectors(data, ignore=['class'])
searchSpace = searchSpace_Nominal + searchSpace_Numeric
self.task = ps.SubgroupDiscoveryTask(data, target, searchSpace, result_set_size=12, depth=5, qf=ps.StandardQF(0.5))
#print(np.nonzero(row)[0])
f.write(" ".join(map(str,
np.nonzero(row)[0])) + " " +
task.qf.gp_to_str(self.get_stats(row_index)) + "\r\n")
if __name__ == '__main__':
from pysubgroup.tests.DataSets import get_credit_data
from pysubgroup import model_target
data = get_credit_data()
#warnings.filterwarnings("error")
print(data.columns)
searchSpace_Nominal = ps.create_nominal_selectors(
data, ignore=['duration', 'credit_amount'])
searchSpace_Numeric = ps.create_numeric_selectors(
data, ignore=['duration', 'credit_amount'])
searchSpace = searchSpace_Nominal + searchSpace_Numeric
target = ps.FITarget()
#QF=model_target.EMM_Likelihood(model_target.PolyRegression_ModelClass(x_name='duration', y_name='credit_amount'))
QF = ps.CountQF()
task = ps.SubgroupDiscoveryTask(data,
target,
searchSpace,
result_set_size=200,
depth=4,
qf=QF)
GpGrowth(mode='b_u').to_file(task, 'E:/tmp/gp_credit.txt')
import time
start_time = time.time()
gp = GpGrowth(mode='b_u').execute(task)