def setUpClass(cls):
data = get_credit_data()
target = ps.NumericTarget('credit_amount')
searchSpace = ps.create_nominal_selectors(data,
ignore=['credit_amount'])
cls.task = ps.SubgroupDiscoveryTask(data,
target,
searchSpace,
result_set_size=10,
depth=3,
qf=ps.StandardQFNumeric(1.0))
cls.result = ps.SimpleDFS().execute(cls.task)
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')))
import pprint
import numpy as np
import pandas as pd
import pysubgroup as ps
pp = pprint.PrettyPrinter(indent=4)
data = np.array([[1, 2, 3, 4, 5], ["F", "F", "F", "Tr", "Tr"]]).T
data = pd.DataFrame(data, columns=["Target", "A"])
data["Target"] = pd.to_numeric(data["Target"])
target = ps.NumericTarget('Target')
print(data[target.target_variable])
sgd = ps.EqualitySelector("A", "Tr")
target.calculate_statistics(sgd, data)
qf = ps.StandardQFNumeric(1.0)
print(qf.evaluate(sgd, target, data))
print(qf.optimistic_estimate(sgd, target, data))
from scipy.io import arff
import pysubgroup as ps
import pandas as pd
import pprint
pp = pprint.PrettyPrinter(indent=4)
data = pd.DataFrame(arff.loadarff("../data/credit-g.arff")[0])
target = ps.NumericTarget('credit_amount')
sg = ps.Subgroup(target, ps.NominalSelector("purpose", b"other"))
print(target.get_base_statistics(data, sg))
sg.calculateStatistics(data)
# pp.pprint (sg.statistics)
qf = ps.StandardQF_numeric(1.0)
print(qf.evaluateFromDataset(data, sg))