def test_mcb():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rng = np.random.RandomState(123456)
mcb = MCB(pool_classifiers, random_state=rng)
mcb.fit(X_dsel, y_dsel)
assert np.isclose(mcb.score(X_test, y_test), 0.7196969696969697)
def test_mcb():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rng = np.random.RandomState(123456)
mcb = MCB(pool_classifiers, rng=rng, DFP=True)
mcb.fit(X_dsel, y_dsel)
assert np.isclose(mcb.score(X_test, y_test), 0.8606060606060606)
def test_mcb(knn_methods):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rng = np.random.RandomState(123456)
mcb = MCB(pool_classifiers, random_state=rng, knn_classifier=knn_methods)
mcb.fit(X_dsel, y_dsel)
assert np.isclose(mcb.score(X_test, y_test), 0.96276595744680848)
def test_mcb_proba():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rng = np.random.RandomState(123456)
mcb = MCB(pool_classifiers, rng=rng, DFP=True)
mcb.fit(X_dsel, y_dsel)
probas = mcb.predict_proba(X_test)
expected = np.load('deslib/tests/expected_values/mcb_proba_DFP.npy')
assert np.allclose(probas, expected)
def test_mcb_proba(knn_methods):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rng = np.random.RandomState(123456)
mcb = MCB(pool_classifiers, random_state=rng, knn_classifier=knn_methods)
mcb.fit(X_dsel, y_dsel)
probas = mcb.predict_proba(X_test)
expected = np.load(
'deslib/tests/expected_values/mcb_proba_integration.npy')
assert np.allclose(probas, expected)
def test_mcb():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rng = np.random.RandomState(123456)
mcb = MCB(pool_classifiers,
random_state=rng,
DFP=True,
with_IH=True,
IH_rate=0.1)
mcb.fit(X_dsel, y_dsel)
assert np.isclose(mcb.score(X_test, y_test), 0.9)
Feature_train_o, Label_train_o = sm.fit_sample(Feature_train, Label_train.ravel())
bdt = AdaBoostClassifier(DecisionTreeClassifier(max_depth=2, min_samples_split=20, min_samples_leaf=5),
algorithm='SAMME', n_estimators=200, learning_rate=0.8)
bdt.fit(Feature_train_o, Label_train_o)
Label_predict = bdt.predict(Feature_test)
elif m == 'META-DES':
pool_classifiers = RandomForestClassifier(n_estimators=10)
pool_classifiers.fit(Feature_train, Label_train.ravel())
metades = METADES(pool_classifiers)
metades.fit(Feature_train, Label_train.ravel())
Label_predict = metades.predict(Feature_test)
elif m == 'MCB':
pool_classifiers = RandomForestClassifier(n_estimators=10)
pool_classifiers.fit(Feature_train, Label_train.ravel())
mcb = MCB(pool_classifiers)
mcb.fit(Feature_train, Label_train.ravel())
Label_predict = mcb.predict(Feature_test)
elif m == 'DES-MI':
pool_classifiers = RandomForestClassifier(n_estimators=10)
pool_classifiers.fit(Feature_train, Label_train.ravel())
dmi = DESMI(pool_classifiers)
dmi.fit(Feature_train, Label_train.ravel())
Label_predict = dmi.predict(Feature_test)
elif m == 'One_vs_Rest-SMOTE-XGBoost':
sm = SMOTE()
Feature_train_o, Label_train_o = sm.fit_sample(Feature_train, Label_train.ravel())
clf = OneVsRestClassifier(xgboost.XGBClassifier())
clf.fit(Feature_train_o, Label_train_o)
Label_predict = clf.predict(Feature_test)
elif m == 'One_vs_Rest-XGBoost':
clf = OneVsRestClassifier(xgboost.XGBClassifier())
def test_similarity_threshold_type(similarity_threshold):
with pytest.raises(TypeError):
mcb = MCB(create_pool_classifiers(),
similarity_threshold=similarity_threshold)
mcb.fit(X_dsel_ex1, y_dsel_ex1)
# can estimate probabilities
pool_classifiers = RandomForestClassifier(n_estimators=10, max_depth=5)
pool_classifiers.fit(X_train, y_train)
# Initialize a DS technique. Here we specify the size of the region of competence (5 neighbors)
knorau = KNORAU(pool_classifiers)
kne = KNORAE(pool_classifiers, k=5)
desp = DESP(pool_classifiers, k=5)
ola = OLA(pool_classifiers, k=5)
mcb = MCB(pool_classifiers, k=5)
meta = METADES(pool_classifiers, k=5)
# Fit the DS techniques
knorau.fit(X_dsel, y_dsel)
kne.fit(X_dsel, y_dsel)
desp.fit(X_dsel, y_dsel)
meta.fit(X_dsel, y_dsel)
ola.fit(X_dsel, y_dsel)
mcb.fit(X_dsel, y_dsel)
# Calculate classification accuracy of each technique
print('Classification accuracy RF: ', RF.score(X_test, y_test))
print('Evaluating DS techniques:')
print('Classification accuracy KNORAU: ', knorau.score(X_test, y_test))
print('Classification accuracy KNORA-Eliminate: ',
kne.score(X_test, y_test))
print('Classification accuracy DESP: ', desp.score(X_test, y_test))
print('Classification accuracy OLA: ', ola.score(X_test, y_test))
print('Classification accuracy MCB: ', mcb.score(X_test, y_test))
print('Classification accuracy META-DES: ', meta.score(X_test, y_test))
def test_similarity_threshold_type(similarity_threshold, create_X_y):
X, y = create_X_y
with pytest.raises(TypeError):
mcb = MCB(similarity_threshold=similarity_threshold)
mcb.fit(X, y)
def main():
###############################################################################
# Preparing the dataset
# ---------------------
# In this part we load the breast cancer dataset from scikit-learn and
# preprocess it in order to pass to the DS models. An important point here is
# to normalize the data so that it has zero mean and unit variance, which is
# a common requirement for many machine learning algorithms.
# This step can be easily done using the StandardScaler class.
rng = np.random.RandomState(123)
data = load_breast_cancer()
X = data.data
y = data.target
# split the data into training and test data
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
random_state=rng)
# Scale the variables to have 0 mean and unit variance
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
# 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)
# Train a pool of 100 base classifiers
pool_classifiers = BaggingClassifier(Perceptron(max_iter=10),
n_estimators=100,
random_state=rng)
pool_classifiers.fit(X_train, y_train)
# Initialize the DS techniques
knorau = KNORAU(pool_classifiers)
kne = KNORAE(pool_classifiers)
desp = DESP(pool_classifiers)
ola = OLA(pool_classifiers)
mcb = MCB(pool_classifiers)
###############################################################################
# Calibrating base classifiers
# -----------------------------
# Some dynamic selection techniques requires that the base classifiers estimate
# probabilities in order to estimate its competence level. Since the Perceptron
# model is not a probabilistic classifier (does not implements the
# predict_proba method, it needs to be calibrated for
# probability estimation before being used by such DS techniques. This step can
# be conducted using the CalibrateClassifierCV class from scikit-learn. Note
# that in this example we pass a prefited pool of classifiers to the
# calibration method in order to use exactly the same pool used in the other
# DS methods.
calibrated_pool = []
for clf in pool_classifiers:
calibrated = CalibratedClassifierCV(base_estimator=clf, cv='prefit')
calibrated.fit(X_dsel, y_dsel)
calibrated_pool.append(calibrated)
apriori = APriori(calibrated_pool)
meta = METADES(calibrated_pool)
knorau.fit(X_dsel, y_dsel)
kne.fit(X_dsel, y_dsel)
desp.fit(X_dsel, y_dsel)
ola.fit(X_dsel, y_dsel)
mcb.fit(X_dsel, y_dsel)
apriori.fit(X_dsel, y_dsel)
meta.fit(X_dsel, y_dsel)
###############################################################################
# Evaluating the methods
# -----------------------
# Let's now evaluate the methods on the test set. We also use the performance
# of Bagging (pool of classifiers without any selection) as a baseline
# comparison. We can see that the majority of DS methods achieve higher
# classification accuracy.
print('Evaluating DS techniques:')
print('Classification accuracy KNORA-Union: ',
knorau.score(X_test, y_test))
print('Classification accuracy KNORA-Eliminate: ',
kne.score(X_test, y_test))
print('Classification accuracy DESP: ', desp.score(X_test, y_test))
print('Classification accuracy OLA: ', ola.score(X_test, y_test))
print('Classification accuracy A priori: ', apriori.score(X_test, y_test))
print('Classification accuracy MCB: ', mcb.score(X_test, y_test))
print('Classification accuracy META-DES: ', meta.score(X_test, y_test))
print('Classification accuracy Bagging: ',
pool_classifiers.score(X_test, y_test))