wianstipp / size_constrained_clustering Goto Github PK

# setup
from size_constrained_clustering import fcm, equal, minmax, shrinkage
# by default it is euclidean distance, but can select others
from sklearn.metrics.pairwise import haversine_distances
import numpy as np

n_samples = 2000
n_clusters = 4
centers = [(-5, -5), (0, 0), (5, 5), (7, 10)]
X, _ = make_blobs(n_samples=n_samples, n_features=2, cluster_std=1.0,
                    centers=centers, shuffle=False, random_state=42)
model = fcm.FCM(n_clusters)
# use other distance function: e.g. haversine distance
# model = fcm.FCM(n_clusters, distance_func=haversine_distances)
model.fit(X)
centers = model.cluster_centers_
labels = model.labels_

n_samples = 2000
n_clusters = 3
X = np.random.rand(n_samples, 2)
# use minimum cost flow framework to solve
model = equal.SameSizeKMeansMinCostFlow(n_clusters)
# use heuristics method to solve
model = equal.SameSizeKMeansHeuristics(n_clusters)
model.fit(X)
centers = model.cluster_centers_
labels = model.labels_

n_samples = 2000
n_clusters = 3
X = np.random.rand(n_samples, 2)
model = minmax.MinMaxKMeansMinCostFlow(n_clusters, size_min=400,   size_max=800)
model.fit(X)
centers = model.cluster_centers_
labels = model.labels_

n_samples = 2000
n_clusters = 3
X = np.random.rand(n_samples, 2)
# distribution is the distribution of cluster sizes
model = da.DeterministicAnnealing(n_clusters, distribution=[0.1, 0.6, 0.3])
model.fit(X)
centers = model.cluster_centers_
labels = model.labels_

n_samples = 1000
n_clusters = 4
centers = [(-5, -5), (0, 0), (5, 5), (7, 10)]
X, _ = make_blobs(n_samples=n_samples, n_features=2, cluster_std=1.0, centers=centers, shuffle=False, random_state=42)

model = shrinkage.Shrinkage(n_clusters, size_min=100)
model.fit(X)
centers = model.cluster_centers_
labels = model.labels_