import pysubgroup as ps
import pandas as pd
data = pd.read_table("../data/titanic.csv")
target = ps.NominalTarget('Survived', True)
searchspace = ps.create_selectors(data, ignore=['Survived'])
task = ps.SubgroupDiscoveryTask(data,
target,
searchspace,
result_set_size=5,
depth=2,
qf=ps.ChiSquaredQF())
result = ps.BeamSearch().execute(task)
for (q, sg) in result:
print(str(q) + ":\t" + str(sg.subgroup_description))
from scipy.io import arff
import pysubgroup as ps
import pandas as pd
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=3,
qf=ps.StandardQF(1.0))
result = ps.BeamSearch(beamWidth=10).execute(task)
for (q, sg) in result:
print(str(q) + ":\t" + str(sg.subgroupDescription))
print("******")
result = ps.SimpleDFS().execute(task)
for (q, sg) in result:
print(str(q) + ":\t" + str(sg.subgroupDescription))
# print WRAccQF().evaluateFromDataset(data, Subgroup(target, []))
import pysubgroup as ps
import pandas as pd
import matplotlib.pyplot as plt
plt.interactive(False)
data = pd.read_csv("~/datasets/titanic.csv")
target = ps.NominalTarget ('survived', 0)
searchSpace = ps.createSelectors(data, ignore=['survived'])
task = ps.SubgroupDiscoveryTask (data, target, searchSpace,
resultSetSize=5, depth=2,
qf=ps.ChiSquaredQF())
result = ps.SimpleDFS().execute(task)
dfs = ps.utils.resultsAsDataFrame (data, result)
plt = ps.plot_roc (data, dfs, ps.ChiSquaredQF())
plt.show()
