def test_apriori():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rng = np.random.RandomState(123456)
apriori = APriori(pool_classifiers, random_state=rng)
apriori.fit(X_dsel, y_dsel)
assert np.isclose(apriori.score(X_test, y_test), 0.6878787878787879)
def test_apriori():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rng = np.random.RandomState(123456)
apriori = APriori(pool_classifiers, rng=rng, DFP=True)
apriori.fit(X_dsel, y_dsel)
assert np.isclose(apriori.score(X_test, y_test), 0.87272727272727268)
def test_apriori(knn_methods):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rng = np.random.RandomState(123456)
apriori = APriori(pool_classifiers, random_state=rng,
knn_classifier=knn_methods)
apriori.fit(X_dsel, y_dsel)
assert np.isclose(apriori.score(X_test, y_test), 0.97872340425531912)
def test_fit(create_pool_classifiers, create_X_y):
X, y = create_X_y
a_priori_test = APriori(create_pool_classifiers)
a_priori_test.fit(X, y)
expected = np.array([[0.5, 0.5], [1.0, 0.0], [0.33, 0.67]])
expected = np.tile(expected, (15, 1, 1))
assert np.array_equal(a_priori_test.dsel_scores_, expected)
knorau = KNORAU(pool_classifiers)
kne = KNORAE(pool_classifiers)
desp = DESP(pool_classifiers)
ola = OLA(pool_classifiers)
mcb = MCB(pool_classifiers)
apriori = APriori(pool_classifiers)
meta = METADES(pool_classifiers)
# Fit the des techniques
knorau.fit(X_dsel, y_dsel)
kne.fit(X_dsel, y_dsel)
desp.fit(X_dsel, y_dsel)
# Fit the dcs techniques
ola.fit(X_dsel, y_dsel)
mcb.fit(X_dsel, y_dsel)
apriori.fit(X_dsel, y_dsel)
meta.fit(X_dsel, y_dsel)
# Calculate classification accuracy of each technique
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))
def test_fit():
a_priori_test = APriori(create_pool_classifiers())
a_priori_test.fit(X_dsel_ex1, y_dsel_ex1)
expected = np.array([[0.5, 0.5], [1.0, 0.0], [0.33, 0.67]])
expected = np.tile(expected, (15, 1, 1))
assert np.array_equal(a_priori_test.dsel_scores, expected)
def test_fit():
a_priori_test = APriori(create_pool_classifiers())
a_priori_test.fit(X_dsel_ex1, y_dsel_ex1)
assert np.isclose(a_priori_test.dsel_scores,
[0.5, 0.5, 1.0, 0.0, 0.33, 0.67]).all()
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: ',
aposteriori.score(X_test, y_test))
print('Classification accuracy of DES-P: ', desp.score(X_test, y_test))
print('Classification accuracy of META-DES: ', meta.score(X_test, y_test))
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))