def test_CountQf(self):
task = ps.SubgroupDiscoveryTask(self.data, ps.FITarget, None, None)
qf = ps.CountQF()
qf.calculate_constant_statistics(task)
sel = ps.EqualitySelector('checking_status', b'no checking')
print(self.data.columns)
print(self.data.checking_status.value_counts())
size = qf.evaluate(sel, self.data)
self.assertEqual(size, 394)
size = qf.evaluate(slice(None))
self.assertEqual(size, len(self.data))
size = qf.evaluate(slice(0, 10))
self.assertEqual(size, 10)
size = qf.evaluate(np.array([1, 3, 5, 7, 11], dtype=int))
self.assertEqual(size, 5)
def setUp(self):
NS_cabin = ps.EqualitySelector("Cabin", np.nan)
NS_embarked = ps.EqualitySelector("Embarked", 'S')
NS_male = ps.EqualitySelector("Sex", 'male')
NS_female = ps.EqualitySelector("Sex", 'female')
#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")
self.result = [
ps.Conjunction([]),
ps.Conjunction([NS_cabin]),
ps.Conjunction([NS_embarked]),
ps.Conjunction([NS_male]),
ps.Conjunction([NS_cabin, NS_embarked]),
ps.Conjunction([NS_cabin, NS_male]),
ps.Conjunction([NS_embarked, NS_male]),
ps.Conjunction([NS_cabin, NS_embarked, NS_male]),
ps.Conjunction([NS_female]),
ps.Conjunction([NS_cabin, NS_female]),
ps.Conjunction([NS_embarked, NS_female]),
# ps.Conjunction([NS_checking, NS_job]),
]
self.qualities = [156, 125, 110, 100, 89, 82, 73, 60, 56, 43, 37]
data = get_titanic_data()
self.qualities2 = [
np.count_nonzero(conj.covers(data)) for conj in self.result
]
self.assertEqual(self.qualities, self.qualities2)
searchSpace = ps.create_nominal_selectors(data)
self.task = ps.SubgroupDiscoveryTask(data,
ps.FITarget,
searchSpace,
result_set_size=10,
depth=5,
qf=ps.CountQF())
def setUp(self):
self.qf = ps.CountQF()
self.ga_qf = ps.GeneralizationAwareQF(self.qf)
self.prepare_df()
import pandas as pd
import pprint
pp = pprint.PrettyPrinter(indent=4)
data = pd.read_csv("~/datasets/titanic.csv")
searchSpace = ps.createSelectors(data, ignore="survived")
dt = data.dtypes
task = ps.SubgroupDiscoveryTask(data,
ps.FITarget,
searchSpace,
resultSetSize=10,
depth=5,
qf=ps.CountQF())
result = ps.SimpleDFS().execute(task)
for (q, sg) in result:
print(str(q) + ":\t" + str(sg.subgroupDescription))
task = ps.SubgroupDiscoveryTask(data,
ps.FITarget,
searchSpace,
resultSetSize=10,
depth=3,
qf=ps.AreaQF())
result = ps.SimpleDFS().execute(task)
for (q, sg) in result:
print(f"{q}\t{sg.subgroupDescription}\t{sg.count(data)}")
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)
print("--- %s seconds ---" % (time.time() - start_time))
#gp = [(qual, sg) for qual, sg in gp if sg.depth <= task.depth]
gp = sorted(gp)
quit()