def test_Apriori(self):
self.runAlgorithm(ps.Apriori(), "Apriori", self.result, self.qualities,
self.task)
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)
eval_dict = {"AUPRC(ish)":average_precision_score}
target_variables = np.random.randint(low=0, high=2, size=1000)
def test_Apriori_with_numba(self):
self.runAlgorithm(ps.Apriori(use_numba=True), "Apriori use_numba=True",
self.result, self.qualities, self.task)
def test_Apriori_no_numba(self):
self.runAlgorithm(ps.Apriori(use_numba=False),
"Apriori use_numba=False", self.result,
self.qualities, self.task)
def test_GeneralisingApriori(self):
algorithm = ps.Apriori(combination_name='Disjunction')
algorithm.optimistic_estimate_name = 'optimistic_generalisation'
self.runAlgorithm(algorithm, "GeneralisingApriori", self.result,
self.qualities, self.task)
import cProfile
from timeit import default_timer as timer
data = pd.DataFrame(arff.loadarff("../data/credit-g.arff")[0])
target = ps.NominalTarget('class', b'bad')
searchSpace = ps.createNominalSelectors(data, ignore=['class'])
task = ps.SubgroupDiscoveryTask(data,
target,
searchSpace,
resultSetSize=10,
depth=5,
qf=ps.StandardQF(1.0))
start = timer()
result = ps.Apriori().execute(task)
end = timer()
print("Time elapsed: ", (end - start))
for (q, sg) in result:
print(str(q) + ":\t" + str(sg.subgroupDescription))
print("******")
start = timer()
result = ps.SimpleDFS().execute(task)
end = timer()
print("Time elapsed: ", (end - start))
for (q, sg) in result:
print(str(q) + ":\t" + str(sg.subgroupDescription))