def test_LeavePSubGroupOut(self):
cv = cross_validation.LeavePSubGroupOut(verbose=2)
for tr, vl in cv.split(X, y, g):
assert (not np.unique(np.in1d([1, 2], [3, 4]))[0])
self.assertRaises(ValueError,
cross_validation.LeavePSubGroupOut,
valid_size='ko')
self.assertRaises(ValueError,
cross_validation.LeavePSubGroupOut,
valid_size=5.1)
field = 'Class'
group = 'uniquefid'
X, y, g = extract_ROI(raster, vector, field, group)
##############################################################################
# Initialize Random-Forest
# ---------------------------
classifier = RandomForestClassifier(random_state=12, n_jobs=1)
##############################################################################
# Create list of different CV
# ---------------------------
CVs = [
cross_validation.RandomStratifiedKFold(n_splits=2),
cross_validation.LeavePSubGroupOut(valid_size=0.5),
cross_validation.LeaveOneSubGroupOut(),
StratifiedKFold(n_splits=2, shuffle=True) #from sklearn
]
kappas = []
for cv in CVs:
SL = SuperLearner(classifier=classifier,
param_grid=dict(n_estimators=[50, 100]),
n_jobs=1)
SL.fit(X, y, group=g, cv=cv)
print('Kappa for ' + str(type(cv).__name__))
cvKappa = []
for stats in SL.get_stats_from_cv(confusion_matrix=False, kappa=True):