def test_make_moons():
X, y = make_moons(3, shuffle=False)
for x, label in zip(X, y):
center = [0.0, 0.0] if label == 0 else [1.0, 0.5]
dist_sqr = ((x - center)**2).sum()
assert_almost_equal(dist_sqr,
1.0,
err_msg="Point is not on expected unit circle")
def test_single_linkage_clustering():
# Check that we get the correct result in two emblematic cases
moons, moon_labels = make_moons(noise=0.05, random_state=42)
clustering = AgglomerativeClustering(n_clusters=2, linkage='single')
clustering.fit(moons)
assert_almost_equal(
normalized_mutual_info_score(clustering.labels_, moon_labels), 1)
circles, circle_labels = make_circles(factor=0.5,
noise=0.025,
random_state=42)
clustering = AgglomerativeClustering(n_clusters=2, linkage='single')
clustering.fit(circles)
assert_almost_equal(
normalized_mutual_info_score(clustering.labels_, circle_labels), 1)
from mrex import cluster, datasets, mixture
from mrex.neighbors import kneighbors_graph
from mrex.preprocessing import StandardScaler
from itertools import cycle, islice
np.random.seed(0)
# ============
# Generate datasets. We choose the size big enough to see the scalability
# of the algorithms, but not too big to avoid too long running times
# ============
n_samples = 1500
noisy_circles = datasets.make_circles(n_samples=n_samples, factor=.5,
noise=.05)
noisy_moons = datasets.make_moons(n_samples=n_samples, noise=.05)
blobs = datasets.make_blobs(n_samples=n_samples, random_state=8)
no_structure = np.random.rand(n_samples, 2), None
# Anisotropicly distributed data
random_state = 170
X, y = datasets.make_blobs(n_samples=n_samples, random_state=random_state)
transformation = [[0.6, -0.6], [-0.4, 0.8]]
X_aniso = np.dot(X, transformation)
aniso = (X_aniso, y)
# blobs with varied variances
varied = datasets.make_blobs(n_samples=n_samples,
cluster_std=[1.0, 2.5, 0.5],
random_state=random_state)
# some parameter combinations will not converge as can be seen on the
# plots so they are ignored here
with warnings.catch_warnings():
warnings.filterwarnings("ignore",
category=ConvergenceWarning,
module="mrex")
mlp.fit(X, y)
mlps.append(mlp)
print("Training set score: %f" % mlp.score(X, y))
print("Training set loss: %f" % mlp.loss_)
for mlp, label, args in zip(mlps, labels, plot_args):
ax.plot(mlp.loss_curve_, label=label, **args)
fig, axes = plt.subplots(2, 2, figsize=(15, 10))
# load / generate some toy datasets
iris = datasets.load_iris()
X_digits, y_digits = datasets.load_digits(return_X_y=True)
data_sets = [(iris.data, iris.target), (X_digits, y_digits),
datasets.make_circles(noise=0.2, factor=0.5, random_state=1),
datasets.make_moons(noise=0.3, random_state=0)]
for ax, data, name in zip(axes.ravel(), data_sets,
['iris', 'digits', 'circles', 'moons']):
plot_on_dataset(*data, ax=ax, name=name)
fig.legend(ax.get_lines(), labels, ncol=3, loc="upper center")
plt.show()
'kbinsdiscretizer__n_bins': np.arange(2, 10),
'linearsvc__C': np.logspace(-2, 7, 10),
}),
(GradientBoostingClassifier(n_estimators=50, random_state=0), {
'learning_rate': np.logspace(-4, 0, 10)
}),
(SVC(random_state=0), {
'C': np.logspace(-2, 7, 10)
}),
]
names = [get_name(e) for e, g in classifiers]
n_samples = 100
datasets = [
make_moons(n_samples=n_samples, noise=0.2, random_state=0),
make_circles(n_samples=n_samples, noise=0.2, factor=0.5, random_state=1),
make_classification(n_samples=n_samples, n_features=2, n_redundant=0,
n_informative=2, random_state=2,
n_clusters_per_class=1)
]
fig, axes = plt.subplots(nrows=len(datasets), ncols=len(classifiers) + 1,
figsize=(21, 9))
cm = plt.cm.PiYG
cm_bright = ListedColormap(['#b30065', '#178000'])
# iterate over datasets
for ds_cnt, (X, y) in enumerate(datasets):
print('\ndataset %d\n---------' % ds_cnt)
AdaBoostClassifier(),
GaussianNB(),
QuadraticDiscriminantAnalysis()
]
X, y = make_classification(n_features=2,
n_redundant=0,
n_informative=2,
random_state=1,
n_clusters_per_class=1)
rng = np.random.RandomState(2)
X += 2 * rng.uniform(size=X.shape)
linearly_separable = (X, y)
datasets = [
make_moons(noise=0.3, random_state=0),
make_circles(noise=0.2, factor=0.5, random_state=1), linearly_separable
]
figure = plt.figure(figsize=(27, 9))
i = 1
# iterate over datasets
for ds_cnt, ds in enumerate(datasets):
# preprocess dataset, split into training and test part
X, y = ds
X = StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=.4, random_state=42)
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
random_state=42)),
("Local Outlier Factor",
LocalOutlierFactor(n_neighbors=35,
contamination=outliers_fraction))]
# Define datasets
blobs_params = dict(random_state=0, n_samples=n_inliers, n_features=2)
datasets = [
make_blobs(centers=[[0, 0], [0, 0]], cluster_std=0.5, **blobs_params)[0],
make_blobs(centers=[[2, 2], [-2, -2]],
cluster_std=[0.5, 0.5],
**blobs_params)[0],
make_blobs(centers=[[2, 2], [-2, -2]],
cluster_std=[1.5, .3],
**blobs_params)[0],
4. * (make_moons(n_samples=n_samples, noise=.05, random_state=0)[0] -
np.array([0.5, 0.25])),
14. * (np.random.RandomState(42).rand(n_samples, 2) - 0.5)
]
# Compare given classifiers under given settings
xx, yy = np.meshgrid(np.linspace(-7, 7, 150), np.linspace(-7, 7, 150))
plt.figure(figsize=(len(anomaly_algorithms) * 2 + 3, 12.5))
plt.subplots_adjust(left=.02,
right=.98,
bottom=.001,
top=.96,
wspace=.05,
hspace=.01)