def DCS(self, x_train, y_train,X_test, Y_test, dsel):
pool_classifiers = BaggingClassifier(linear_model.Perceptron(max_iter=5), self.pool_size)
pool_classifiers.fit(x_train, y_train)
# Initialize the DES model
lca = LCA(pool_classifiers)
ola = OLA(pool_classifiers)
# Preprocess the Dynamic Selection dataset (DSEL)
score1 = lca.fit(x_train[dsel], y_train[dsel])
score2 = ola.fit(x_train[dsel], y_train[dsel])
# Predict new examples:
# print (lca.score(X_test, Y_test), ola.score(X_test, Y_test))
return (score1, score2, ) + self.calc_metrics(X_test, Y_test) # dependendo da base formato nao suportado
def fit(self, x_sel, y_sel, P, k):
'''
metodo para chamar o tipo de DS
:param: x_sel: dados de treinamento da janela de validacao
:param: y_sel: rotulos da janela de validacao
:param: P: pool de classificadores
:param: k: vizinhanca
'''
# escolhendo a tecnica de selecao de classificadores
if (self.TYPE == 'knorae'):
DS = KNORAE(P, k)
elif (self.TYPE == 'knorau'):
DS = KNORAU(P, k)
elif (self.TYPE == 'ola'):
DS = OLA(P, k)
elif (self.TYPE == 'lca'):
DS = LCA(P, k)
elif (self.TYPE == 'posteriori'):
DS = APosteriori(P, k)
elif (self.TYPE == 'priori'):
DS = APriori(P, k)
# encontrando os classificadores competentes do DS escolhido
self.DS = copy.deepcopy(DS)
self.DS.fit(x_sel, y_sel)
def escolher_modelo(nome, x_sel, y_sel, P, k):
'''
metodo para chamar o tipo de DS
:param: x_sel: dados de treinamento da janela de validacao
:param: y_sel: rotulos da janela de validacao
:param: P: pool de classificadores
:param: k: vizinhanca
'''
# escolhendo a tecnica de selecao de classificadores
if(nome=='OLA'):
DS = OLA(P, k)
number_model = 0
elif(nome=='LCA'):
DS = LCA(P, k)
number_model = 1
elif(nome=='KNORAE'):
DS = KNORAE(P, k)
number_model = 2
elif(nome=='KNORAU'):
DS = KNORAU(P, k)
number_model = 3
# encontrando os classificadores competentes do DS escolhido
DS.fit(x_sel, y_sel)
# retornando a tecnica de DS
return DS, number_model
def __init__(
self,
name: str,
model_params: Dict[str, Any],
classifier_paths: Iterable[Tuple[str, str]],
) -> None:
super().__init__(name, model_params, classifier_paths)
self._selector = LCA(self.classifiers, **model_params)
def test_estimate_competence_woods(index, expected):
lca_test = LCA(create_pool_classifiers())
lca_test.processed_dsel = dsel_processed_ex1
lca_test.neighbors = neighbors_ex1[index, :]
lca_test.distances = distances_ex1[index, :]
lca_test.DFP_mask = [1, 1, 1]
lca_test.DSEL_target = y_dsel_ex1
query = np.array([1, 1])
competences = lca_test.estimate_competence(query.reshape(1, -1))
assert np.isclose(competences, expected).all()
def train(train_index, test_index):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = Y[train_index], Y[test_index]
#train_perc = 0.7
#split_point = int(train_perc*len(train_index))
# valid_index = train_index[split_point:]
# train_index = train_index[:split_point]
# X_train, X_valid, X_test = X[train_index], X[valid_index], X[test_index]
# y_train, y_valid, y_test = Y[train_index], Y[valid_index], Y[test_index]
#print("TRAIN:", train_index, "VALID:", valid_index, "TEST:", test_index)
X_train, X_valid, y_train, y_valid = train_test_split(
X_train, y_train, test_size=0.3, random_state=seed)
pool_classifiers.fit(X_train, y_train)
validation_data, validation_labels = get_validation_data(
X_valid, y_valid, 0.5, hardness=hardness)
dynamic_selection_algorithm = None
try:
if args.dynamic_selection == True and args.dynamic_algorithm is None:
raise ValueError(
'Dynamic selection requires you provide an algorithm.')
elif args.dynamic_selection == True and args.dynamic_algorithm is not None:
if args.dynamic_algorithm == 'ola':
dynamic_selection_algorithm = OLA(pool_classifiers,
random_state=seed)
elif args.dynamic_algorithm == 'lca':
dynamic_selection_algorithm = LCA(pool_classifiers,
random_state=seed)
elif args.dynamic_algorithm == 'mcb':
dynamic_selection_algorithm = MCB(pool_classifiers,
random_state=seed)
elif args.dynamic_algorithm == 'knorau':
dynamic_selection_algorithm = KNORAU(pool_classifiers,
random_state=seed)
elif args.dynamic_algorithm == 'kne':
dynamic_selection_algorithm = KNORAE(pool_classifiers,
random_state=seed)
dynamic_selection_algorithm.fit(validation_data,
validation_labels)
preds = dynamic_selection_algorithm.predict(X_test)
else:
# Static combination by voting
preds = voting(X_test, pool_classifiers)
except Exception as error:
raise error
acc = get_accuracy_score(y_test, preds)
g1 = get_g1_score(y_test, preds, average='macro')
f1 = get_f1_score(y_test, preds)
roc = roc_auc_score(y_test, preds, average='macro')
return dict(f1=f1, g1=g1, acc=acc, roc=roc)
def test_estimate_competence_batch(example_estimate_competence):
_, y, neighbors, distances, dsel_processed, _ = example_estimate_competence
expected = np.array([[0.75000000, 0.66666667, 0.75000000],
[0.80000000, 1.00000000, 0.80000000],
[1.00000000, 0.60000000, 0.50000000]])
lca_test = LCA()
lca_test.DSEL_processed_ = dsel_processed
lca_test.DSEL_target_ = y
query = np.ones((3, 2))
predictions = np.array([[0, 1, 0]])
competences = lca_test.estimate_competence(neighbors,
distances=distances,
predictions=np.array(
predictions))
assert np.isclose(competences, expected).all()
def test_estimate_competence_diff_target(index):
lca_test = LCA(create_pool_classifiers())
lca_test.DSEL_processed_ = dsel_processed_ex1
lca_test.DSEL_target_ = np.ones(15, dtype=int) * 3
neighbors = neighbors_ex1[index, :].reshape(1, -1)
distances = distances_ex1[index, :].reshape(1, -1)
query = np.atleast_2d([1, 1])
expected = [0.0, 0.0, 0.0]
predictions = []
for clf in lca_test.pool_classifiers:
predictions.append(clf.predict(query)[0])
competences = lca_test.estimate_competence(
query,
neighbors,
distances=distances,
predictions=np.array(predictions))
assert np.isclose(competences, expected).all()
def test_estimate_competence_diff_target(index, example_estimate_competence,
create_pool_classifiers):
_, y, neighbors, distances, dsel_processed, _ = example_estimate_competence
lca_test = LCA(create_pool_classifiers)
lca_test.DSEL_processed_ = dsel_processed
lca_test.DSEL_target_ = np.ones(15, dtype=int) * 3
neighbors = neighbors[index, :].reshape(1, -1)
distances = distances[index, :].reshape(1, -1)
query = np.atleast_2d([1, 1])
expected = [0.0, 0.0, 0.0]
predictions = np.array([[0, 1, 0]])
competences = lca_test.estimate_competence(
query,
neighbors,
distances=distances,
predictions=np.array(predictions))
assert np.isclose(competences, expected).all()
def test_estimate_competence_woods(index, expected):
lca_test = LCA(create_pool_classifiers())
lca_test.processed_dsel = dsel_processed_ex1
lca_test.neighbors = neighbors_ex1[index, :]
lca_test.distances = distances_ex1[index, :]
lca_test.DFP_mask = [1, 1, 1]
lca_test.DSEL_target = y_dsel_ex1
query = np.atleast_2d([1, 1])
predictions = []
for clf in lca_test.pool_classifiers:
predictions.append(clf.predict(query)[0])
competences = lca_test.estimate_competence(query, predictions=np.array(predictions))
assert np.allclose(competences, expected)
def test_estimate_competence_diff_target(index):
query = np.array([1, 1])
lca = LCA(create_pool_classifiers())
lca.processed_dsel = dsel_processed_ex1
lca.DSEL_target = np.ones(15, dtype=int) * 3
lca.neighbors = neighbors_ex1[index, :]
lca.distances = distances_ex1[index, :]
lca.DFP_mask = [1, 1, 1]
expected = [0.0, 0.0, 0.0]
competences = lca.estimate_competence(query.reshape(1, -1))
assert np.isclose(competences, expected).all()
def test_estimate_competence_batch():
expected = np.array([[0.75000000, 0.66666667, 0.75000000],
[0.80000000, 1.00000000, 0.80000000],
[1.00000000, 0.60000000, 0.50000000]])
lca_test = LCA(create_pool_classifiers())
lca_test.processed_dsel = dsel_processed_ex1
lca_test.neighbors = neighbors_ex1
lca_test.distances = distances_ex1
lca_test.DFP_mask = np.ones((3, 3))
lca_test.DSEL_target = y_dsel_ex1
query = np.ones((3, 2))
predictions = []
for clf in lca_test.pool_classifiers:
predictions.append(clf.predict(query)[0])
competences = lca_test.estimate_competence(query, predictions=np.array(predictions))
assert np.isclose(competences, expected).all()
def test_predict_proba():
X = X_dsel_ex1
y = y_dsel_ex1
clf1 = Perceptron()
clf1.fit(X, y)
LCA([clf1, clf1])
def test_lca(knn_methods):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
lca = LCA(pool_classifiers, knn_classifier=knn_methods)
lca.fit(X_dsel, y_dsel)
assert np.isclose(lca.score(X_test, y_test), 0.96808510638297873)
X_train, y_train)
model_linear_svm = CalibratedClassifierCV(LinearSVC()).fit(
X_train, y_train)
model_svc = SVC(probability=True).fit(X_train, y_train)
model_bayes = GaussianNB().fit(X_train, y_train)
model_tree = DecisionTreeClassifier().fit(X_train, y_train)
model_knn = KNeighborsClassifier(n_neighbors=5).fit(X_train, y_train)
pool_classifiers = [
model_perceptron, model_linear_svm, model_svc, model_bayes, model_tree,
model_knn
]
# Initializing the DS techniques
knop = KNOP(pool_classifiers)
rrc = RRC(pool_classifiers)
lca = LCA(pool_classifiers)
mcb = MCB(pool_classifiers)
aposteriori = APosteriori(pool_classifiers)
# Fitting the techniques
knop.fit(X_dsel, y_dsel)
rrc.fit(X_dsel, y_dsel)
lca.fit(X_dsel, y_dsel)
mcb.fit(X_dsel, y_dsel)
aposteriori.fit(X_dsel, y_dsel)
# Calculate classification accuracy of each technique
print('Evaluating DS techniques:')
print('Classification accuracy KNOP: ', knop.score(X_test, y_test))
print('Classification accuracy RRC: ', rrc.score(X_test, y_test))
print('Classification accuracy LCA: ', lca.score(X_test, y_test))
def test_check_estimator():
check_estimator(LCA())
def test_lca(knne, expected):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
lca = LCA(pool_classifiers, DFP=True, knne=knne)
lca.fit(X_dsel, y_dsel)
assert np.isclose(lca.score(X_test, y_test), expected)
def test_lca(knn_methods):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
lca = LCA(pool_classifiers, knn_classifier=knn_methods)
lca.fit(X_dsel, y_dsel)
assert np.isclose(lca.score(X_test, y_test), 0.973404255319149)
# Split the data into training and DSEL for DS techniques
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 techniques without DFP
apriori = APriori(pool_classifiers)
aposteriori = APosteriori(pool_classifiers)
ola = OLA(pool_classifiers)
lca = LCA(pool_classifiers)
desp = DESP(pool_classifiers)
meta = METADES(pool_classifiers)
apriori.fit(X_dsel, y_dsel)
aposteriori.fit(X_dsel, y_dsel)
ola.fit(X_dsel, y_dsel)
lca.fit(X_dsel, y_dsel)
desp.fit(X_dsel, y_dsel)
meta.fit(X_dsel, y_dsel)
print('Evaluating DS techniques:')
print('Classification accuracy of OLA: ', ola.score(X_test, y_test))
print('Classification accuracy of LCA: ', lca.score(X_test, y_test))
print('Classification accuracy of A priori: ', apriori.score(X_test, y_test))
print('Classification accuracy of A posteriori: ',
def _generate_local_pool(self, query):
"""
Local pool generation.
This procedure populates the "pool_classifiers" based on the query sample's neighborhood.
Thus, for each query sample, a different pool is created.
In each iteration, the training samples near the query sample are singled out and a
subpool is generated using the Self-Generating Hyperplanes (SGH) method.
Then, the DCS technique selects the best classifier in the generated subpool and it is added to the local pool.
In the following iteration, the neighborhood is increased and another SGH-generated subpool is obtained
over the new neighborhood, and again the DCS technique singles out the best in it, which is then added to the local pool.
This process is repeated until the pool reaches "n_classifiers".
Parameters
----------
query : array of shape = [n_features]
The test sample.
Returns
-------
self
References
----------
M. A. Souza, G. D. Cavalcanti, R. M. Cruz, R. Sabourin, On the characterization of the
oracle for dynamic classi
er selection, in: International Joint Conference on Neural Networks,
IEEE, 2017, pp. 332-339.
"""
n_samples, _ = self.DSEL_data.shape
self.pool_classifiers = []
n_err = 0
max_err = 2 * self.n_classifiers
curr_k = self.k
# Classifier count
n = 0
while n < self.n_classifiers and n_err < max_err:
subpool = SGH()
included_samples = np.zeros((n_samples), int)
if self.knne:
idx_neighb = np.array([], dtype=int)
# Obtain neighbors of each class individually
for j in np.arange(0, self.n_classes):
# Obtain neighbors from the classes in the RoC
if np.any(self.classes[j] == self.DSEL_target[
self.neighbors[0][np.arange(0, curr_k)]]):
nc = np.where(self.classes[j] == self.DSEL_target[
self.neighbors[0]])
idx_nc = self.neighbors[0][nc]
idx_nc = idx_nc[np.arange(
0, np.minimum(curr_k, len(idx_nc)))]
idx_neighb = np.concatenate((idx_neighb, idx_nc),
axis=0)
else:
idx_neighb = np.asarray(self.neighbors)[0][np.arange(
0, curr_k)]
# Indicate participating instances in the training of the subpool
included_samples[idx_neighb] = 1
curr_classes = np.unique(self.DSEL_target[idx_neighb])
# If there are +1 classes in the local region
if len(curr_classes) > 1:
# Obtain SGH pool
subpool.fit(self.DSEL_data, self.DSEL_target, included_samples)
# Adjust chosen DCS technique parameters
if self.ds_tech == 'ola':
ds = OLA(subpool, k=len(idx_neighb)) # change for self.k
elif self.ds_tech == 'lca':
ds = LCA(subpool, k=len(idx_neighb))
elif self.ds_tech == 'mcb':
ds = MCB(subpool, k=len(idx_neighb))
elif self.ds_tech == 'mla':
ds = MLA(subpool, k=len(idx_neighb))
elif self.ds_tech == 'a_priori':
ds = APriori(subpool, k=len(idx_neighb))
elif self.ds_tech == 'a_posteriori':
ds = APosteriori(subpool, k=len(idx_neighb))
# Fit ds technique
ds.fit(self.DSEL_data, self.DSEL_target)
neighb = np.in1d(
self.neighbors,
idx_neighb) # True/False vector of selected neighbors
# Set distances and neighbors of the query sample (already calculated)
ds.distances = np.asarray([self.distances[0][neighb]
]) # Neighborhood
ds.neighbors = np.asarray([self.neighbors[0][neighb]
]) # Neighborhood
ds.DFP_mask = np.ones(ds.n_classifiers)
# Estimate competence
comp = ds.estimate_competence(query, ds._predict_base(query))
# Select best classifier in subpool
sel_c = ds.select(comp)
# Add to local pool
self.pool_classifiers.append(copy.deepcopy(subpool[sel_c[0]]))
n += 1
# else:
# # Exception: fewer than 2 classes in the neighborhood
# print('OPS! Next!')
# Increase neighborhood size
curr_k += 2
n_err += 1
return self
def test_lca():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
lca = LCA(pool_classifiers, DFP=True)
lca.fit(X_dsel, y_dsel)
assert np.isclose(lca.score(X_test, y_test), 0.88787878787878793)
def test_predict_proba(create_X_y):
X, y = create_X_y
clf1 = Perceptron()
clf1.fit(X, y)
LCA([clf1, clf1]).fit(X, y)
