def test_ola_proba(knn_methods):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
ola = OLA(pool_classifiers, knn_classifier=knn_methods)
ola.fit(X_dsel, y_dsel)
probas = ola.predict_proba(X_test)
expected = np.load(
'deslib/tests/expected_values/ola_proba_integration.npy')
assert np.allclose(probas, expected)
def test_ola_subspaces():
rng = np.random.RandomState(123456)
X_dsel, X_test, X_train, y_dsel, y_test, y_train = load_dataset(None, rng)
pool = BaggingClassifier(LogisticRegression(),
bootstrap_features=True,
max_features=0.5,
random_state=rng).fit(X_train, y_train)
ola = OLA(pool)
ola.fit(X_dsel, y_dsel)
assert np.isclose(ola.score(X_test, y_test), 0.9680851063829787)
def _create_hard_estimator(self, k):
clf = None
if self.selection_method == 'ola':
clf = OLA(self.pool_classifiers, DFP=self.dfp, k=k)
elif self.selection_method == 'lca':
clf = LCA(self.pool_classifiers, DFP=self.dfp, k=k)
else:
raise ValueError("The chosen selection method is not available")
return clf
def initialize_ds(pool_classifiers, X, y, k=5):
knorau = KNORAU(pool_classifiers, k=k)
kne = KNORAE(pool_classifiers, k=k)
desknn = DESKNN(pool_classifiers, k=k)
ola = OLA(pool_classifiers, k=k)
lca = LCA(pool_classifiers, k=k)
mla = MLA(pool_classifiers, k=k)
mcb = MCB(pool_classifiers, k=k)
rank = Rank(pool_classifiers, k=k)
knop = KNOP(pool_classifiers, k=k)
meta = METADES(pool_classifiers, k=k)
list_ds = [knorau, kne, ola, lca, mla, desknn, mcb, rank, knop, meta]
names = [
'KNORA-U', 'KNORA-E', 'OLA', 'LCA', 'MLA', 'DESKNN', 'MCB', 'RANK',
'KNOP', 'META-DES'
]
# fit the ds techniques
for ds in list_ds:
ds.fit(X, y)
return list_ds, names
def test_ola(knn_methods):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
ola = OLA(pool_classifiers, knn_classifier=knn_methods)
ola.fit(X_dsel, y_dsel)
assert np.isclose(ola.score(X_test, y_test), 0.9787234042553191)
]
voting_classifiers = [("perceptron", model_perceptron), ("svc", model_svc),
("bayes", model_bayes), ("tree", model_tree),
("knn", model_knn)]
model_voting = VotingClassifier(estimators=voting_classifiers).fit(
X_train, y_train)
# Initializing the techniques
knorau = KNORAU(pool_classifiers)
kne = KNORAE(pool_classifiers)
desp = DESP(pool_classifiers)
metades = METADES(pool_classifiers, mode='hybrid')
# DCS techniques
ola = OLA(pool_classifiers)
mcb = MCB(pool_classifiers)
##############################################################################
# Adding stacked classifier as baseline comparison. Stacked classifier can
# be found in the static module. In this experiment we consider two types
# of stacking: one using logistic regression as meta-classifier
# (default configuration) and the other using a Decision Tree.
stacked_lr = StackedClassifier(pool_classifiers, random_state=rng)
stacked_dt = StackedClassifier(pool_classifiers,
random_state=rng,
meta_classifier=DecisionTreeClassifier())
# Fitting the DS techniques
knorau.fit(X_dsel, y_dsel)
kne.fit(X_dsel, y_dsel)
desp.fit(X_dsel, y_dsel)
X_test = scaler.transform(X_test)
# Training a pool of classifiers using the bagging technique.
pool_classifiers = BaggingClassifier(DecisionTreeClassifier(random_state=rng),
random_state=rng)
pool_classifiers.fit(X_train, y_train)
###############################################################################
# Setting DS method to use the switch mechanism
# ----------------------------------------------
# In order to activate the functionality to switch between DS and KNN according
# to the instance hardness level we need to set the DS techniques to use this
# information. This is done by setting the hyperparameter `with_IH` to True.
# In this example we consider four different values for te threshold
mcb = MCB(pool_classifiers, with_IH=True, random_state=rng)
ola = OLA(pool_classifiers, with_IH=True, random_state=rng)
rank = Rank(pool_classifiers, with_IH=True, random_state=rng)
des_p = DESP(pool_classifiers, with_IH=True, random_state=rng)
kne = KNORAE(pool_classifiers, with_IH=True, random_state=rng)
knu = KNORAU(pool_classifiers, with_IH=True, random_state=rng)
list_ih_values = [0.0, 1. / 7., 2. / 7., 3. / 7.]
list_ds_methods = [
method.fit(X_train, y_train)
for method in [mcb, ola, rank, des_p, kne, knu]
]
names = ['MCB', 'OLA', 'Mod. Rank', 'DES-P', 'KNORA-E', 'KNORA-U']
# Plot accuracy x IH
fig, ax = plt.subplots()
for ds_method, name in zip(list_ds_methods, names):
pool_classifiers = BaggingClassifier(base_estimator=DecisionTreeClassifier(),
n_estimators=100,
random_state=rng)
pool_classifiers.fit(X_train, y_train)
# Setting up static methods.
stacked = StackedClassifier(pool_classifiers)
static_selection = StaticSelection(pool_classifiers)
single_best = SingleBest(pool_classifiers)
# Initialize a DS technique. Here we specify the size of
# the region of competence (5 neighbors)
knorau = KNORAU(pool_classifiers, random_state=rng)
kne = KNORAE(pool_classifiers, random_state=rng)
desp = DESP(pool_classifiers, random_state=rng)
ola = OLA(pool_classifiers, random_state=rng)
mcb = MCB(pool_classifiers, random_state=rng)
knop = KNOP(pool_classifiers, random_state=rng)
meta = METADES(pool_classifiers, random_state=rng)
names = [
'Single Best', 'Static Selection', 'Stacked', 'KNORA-U', 'KNORA-E',
'DES-P', 'OLA', 'MCB', 'KNOP', 'META-DES'
]
methods = [
single_best, static_selection, stacked, knorau, kne, desp, ola, mcb, knop,
meta
]
# Fit the DS techniques
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=rng)
# Normalizing the dataset to have 0 mean and unit variance.
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
pool_classifiers = BaggingClassifier(Perceptron(max_iter=100),
random_state=rng)
pool_classifiers.fit(X_train, y_train)
# Setting with_IH
mcb = MCB(pool_classifiers)
ola = OLA(pool_classifiers)
des_p = DESP(pool_classifiers)
knu = KNORAU(pool_classifiers)
lca = LCA(pool_classifiers)
kne = KNORAE(pool_classifiers)
rank = Rank(pool_classifiers)
list_ds_methods = [mcb, ola, des_p, knu, lca, kne, rank]
names = ['MCB', 'OLA', 'DES-P', 'KNORA-U', 'LCA', 'KNORA-E', 'Rank']
k_value_list = range(3, 16)
###############################################################################
# Plot accuracy x region of competence size.
# -------------------------------------------
# We can see the this parameter can have a huge influence in the performance
# of certain DS techniques. The main exception being the KNORA-E and Rank
X_train, X_dsel, y_train, y_dsel = train_test_split(X_train,
y_train,
test_size=0.5,
random_state=rng)
# Considering a pool composed of 10 base classifiers
pool_classifiers = RandomForestClassifier(n_estimators=10,
random_state=rng,
max_depth=10)
pool_classifiers.fit(X_train, y_train)
ds_names = ['A Priori', 'A Posteriori', 'OLA', 'LCA', 'DES-P', 'META-DES']
# DS techniques without DFP
apriori = APriori(pool_classifiers, random_state=rng)
aposteriori = APosteriori(pool_classifiers, random_state=rng)
ola = OLA(pool_classifiers)
lca = LCA(pool_classifiers)
desp = DESP(pool_classifiers)
meta = METADES(pool_classifiers)
# FIRE-DS techniques (with DFP)
fire_apriori = APriori(pool_classifiers, DFP=True, random_state=rng)
fire_aposteriori = APosteriori(pool_classifiers, DFP=True, random_state=rng)
fire_ola = OLA(pool_classifiers, DFP=True)
fire_lca = LCA(pool_classifiers, DFP=True)
fire_desp = DESP(pool_classifiers, DFP=True)
fire_meta = METADES(pool_classifiers, DFP=True)
list_ds = [apriori, aposteriori, ola, lca, desp, meta]
list_fire_ds = [
fire_apriori, fire_aposteriori, fire_ola, fire_lca, fire_desp, fire_meta