def test_knorae_subspaces():
rng = np.random.RandomState(123456)
X_dsel, X_test, X_train, y_dsel, y_test, y_train = load_dataset(None, rng)
# split the data into training and test data
pool = BaggingClassifier(LogisticRegression(),
max_features=0.5,
random_state=rng).fit(X_train, y_train)
knorae = KNORAE(pool)
knorae.fit(X_dsel, y_dsel)
assert np.isclose(knorae.score(X_test, y_test), 0.9787234042553191)
# 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)
metades.fit(X_dsel, y_dsel)
ola.fit(X_dsel, y_dsel)
mcb.fit(X_dsel, y_dsel)
# Fitting the tacking models
stacked_lr.fit(X_dsel, y_dsel)
stacked_dt.fit(X_dsel, y_dsel)
# Calculate classification accuracy of each technique
print('Evaluating DS techniques:')
print('Classification accuracy of Majority voting the pool: ',
model_voting.score(X_test, y_test))
print('Classification accuracy of KNORA-U: ', knorau.score(X_test, y_test))
print('Classification accuracy of KNORA-E: ', kne.score(X_test, y_test))
print('Classification accuracy of DESP: ', desp.score(X_test, y_test))
print('Classification accuracy of META-DES: ', metades.score(X_test, y_test))
print('Classification accuracy of OLA: ', ola.score(X_test, y_test))
print('Classification accuracy Stacking LR', stacked_lr.score(X_test, y_test))
print('Classification accuracy Stacking DT', stacked_dt.score(X_test, y_test))
def test_kne(knn_methods, voting):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
kne = KNORAE(pool_classifiers, knn_classifier=knn_methods, voting=voting)
kne.fit(X_dsel, y_dsel)
assert np.isclose(kne.score(X_test, y_test), 0.9787234042553191)
# Setting up the random state to have consistent results
rng = np.random.RandomState(42)
# Generate a classification dataset
X, y = make_classification(n_samples=1000, random_state=rng)
# 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)
# 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)
# Initialize the DS techniques. DS methods can be initialized without
# specifying a single input parameter. In this example, we just pass the random
# state in order to always have the same result.
kne = KNORAE(random_state=rng)
meta = METADES(random_state=rng)
# Fitting the des techniques
kne.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-Eliminate: ',
kne.score(X_test, y_test))
print('Classification accuracy META-DES: ', meta.score(X_test, y_test))