def test_estimate_competence_batch(example_estimate_competence):
_, _, neighbors, distances, dsel_processed, _ = example_estimate_competence
expected = np.array([[1, 5, 0], [1, 1, 2], [0, 0, 1]])
rank_test = Rank()
rank_test.DSEL_processed_ = dsel_processed
competences = rank_test.estimate_competence(neighbors, distances=distances)
assert np.allclose(competences, expected)
def test_estimate_competence(index, expected):
rank_test = Rank(create_pool_classifiers())
rank_test.processed_dsel = dsel_processed_ex1
rank_test.neighbors = neighbors_ex1[index, :]
rank_test.distances = distances_ex1[index, :]
rank_test.DFP_mask = [1, 1, 1]
query = np.array([1, 1])
competences = rank_test.estimate_competence(query.reshape(1, -1))
assert np.isclose(competences, expected).all()
def test_estimate_competence_batch():
expected = np.array([[1, 5, 0], [1, 1, 2], [0, 0, 1]])
rank_test = Rank(create_pool_classifiers())
rank_test.processed_dsel = dsel_processed_ex1
rank_test.neighbors = neighbors_ex1
rank_test.distances = distances_ex1
rank_test.DFP_mask = np.ones((3, 3))
query = np.array([[1, 1], [1, 1], [1, 1]])
competences = rank_test.estimate_competence(query)
assert np.allclose(competences, expected)
def test_estimate_competence_batch():
expected = np.array([[1, 5, 0], [1, 1, 2], [0, 0, 1]])
rank_test = Rank(create_pool_classifiers())
rank_test.DSEL_processed_ = dsel_processed_ex1
neighbors = neighbors_ex1
distances = distances_ex1
query = np.array([[1, 1], [1, 1], [1, 1]])
competences = rank_test.estimate_competence(query,
neighbors,
distances=distances)
assert np.allclose(competences, expected)
def test_rank():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rank = Rank(pool_classifiers, DFP=True)
rank.fit(X_dsel, y_dsel)
assert np.isclose(rank.score(X_test, y_test), 0.8787878787878788)
def test_rank(knn_methods):
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rank = Rank(pool_classifiers, knn_classifier=knn_methods)
rank.fit(X_dsel, y_dsel)
assert np.isclose(rank.score(X_test, y_test), 0.973404255319149)
def test_predict_proba():
X = X_dsel_ex1
y = y_dsel_ex1
clf1 = Perceptron()
clf1.fit(X, y)
Rank([clf1, clf1]).fit(X, y)
plt.show()
plt.tight_layout()
###############################################################################
# Comparison with Dynamic Selection techniques
# --------------------------------------------
#
# We will now consider four DS methods: k-Nearest Oracle-Eliminate (KNORA-E),
# Dynamic Ensemble Selection performance (DES-P), Overall Local Accuracy (OLA)
# and Rank. Let's train the classifiers and plot their decision boundaries:
knora_e = KNORAE(pool_classifiers).fit(X_train, y_train)
desp = DESP(pool_classifiers).fit(X_train, y_train)
ola = OLA(pool_classifiers).fit(X_train, y_train)
rank = Rank(pool_classifiers).fit(X_train, y_train)
# Plotting the Decision Border of the DS methods.
fig2, sub = plt.subplots(2, 2, figsize=(15, 10))
plt.subplots_adjust(wspace=0.4, hspace=0.4)
titles = [
'KNORA-Eliminate', 'DES-P', 'Overall Local Accuracy (OLA)', 'Modified Rank'
]
classifiers = [knora_e, desp, ola, rank]
for clf, ax, title in zip(classifiers, sub.flatten(), titles):
plot_classifier_decision(ax, clf, X_train, mode='filled', alpha=0.4)
plot_dataset(X_test, y_test, ax=ax)
ax.set_xlim(np.min(X[:, 0]), np.max(X[:, 0]))
ax.set_ylim(np.min(X[:, 1]), np.max(X[:, 1]))
ax.set_title(title, fontsize=15)
def test_check_estimator():
check_estimator(Rank())
def test_predict_proba(create_X_y):
X, y = create_X_y
clf1 = Perceptron()
clf1.fit(X, y)
Rank([clf1, clf1]).fit(X, y)
def test_rank():
pool_classifiers, X_dsel, y_dsel, X_test, y_test = setup_classifiers()
rank = Rank(pool_classifiers)
rank.fit(X_dsel, y_dsel)
assert np.isclose(rank.score(X_test, y_test), 0.96276595744680848)