def test_classification_toy():
# Check classification on a toy dataset, including sparse versions.
clf = NearestCentroid()
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
# Same test, but with a sparse matrix to fit and test.
clf = NearestCentroid()
clf.fit(X_csr, y)
assert_array_equal(clf.predict(T_csr), true_result)
# Fit with sparse, test with non-sparse
clf = NearestCentroid()
clf.fit(X_csr, y)
assert_array_equal(clf.predict(T), true_result)
# Fit with non-sparse, test with sparse
clf = NearestCentroid()
clf.fit(X, y)
assert_array_equal(clf.predict(T_csr), true_result)
# Fit and predict with non-CSR sparse matrices
clf = NearestCentroid()
clf.fit(X_csr.tocoo(), y)
assert_array_equal(clf.predict(T_csr.tolil()), true_result)
def test_predict_translated_data():
# Test that NearestCentroid gives same results on translated data
rng = np.random.RandomState(0)
X = rng.rand(50, 50)
y = rng.randint(0, 3, 50)
noise = rng.rand(50)
clf = NearestCentroid(shrink_threshold=0.1)
clf.fit(X, y)
y_init = clf.predict(X)
clf = NearestCentroid(shrink_threshold=0.1)
X_noise = X + noise
clf.fit(X_noise, y)
y_translate = clf.predict(X_noise)
assert_array_equal(y_init, y_translate)
def test_iris_shrinkage():
# Check consistency on dataset iris, when using shrinkage.
for metric in ('euclidean', 'cosine'):
for shrink_threshold in [None, 0.1, 0.5]:
clf = NearestCentroid(metric=metric,
shrink_threshold=shrink_threshold)
clf = clf.fit(iris.data, iris.target)
score = np.mean(clf.predict(iris.data) == iris.target)
assert score > 0.8, "Failed with score = " + str(score)
# we only take the first two features. We could avoid this ugly
# slicing by using a two-dim dataset
X = iris.data[:, :2]
y = iris.target
h = .02 # step size in the mesh
# Create color maps
cmap_light = ListedColormap(['orange', 'cyan', 'cornflowerblue'])
cmap_bold = ListedColormap(['darkorange', 'c', 'darkblue'])
for shrinkage in [None, .2]:
# we create an instance of Neighbours Classifier and fit the data.
clf = NearestCentroid(shrink_threshold=shrinkage)
clf.fit(X, y)
y_pred = clf.predict(X)
print(shrinkage, np.mean(y == y_pred))
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_max]x[y_min, y_max].
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure()
plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
# Plot also the training points
def test_iris():
# Check consistency on dataset iris.
for metric in ('euclidean', 'cosine'):
clf = NearestCentroid(metric=metric).fit(iris.data, iris.target)
score = np.mean(clf.predict(iris.data) == iris.target)
assert score > 0.9, "Failed with score = " + str(score)