def main():
X, y = load_dataset.load_dataset("stream1")
# Experiment parameters
nclusters = 4
nsamples = 2000 * nclusters
train_size = 800 * nclusters
window_size = 100
evol_model = EvolvingClustering.EvolvingClustering(macro_cluster_update=1,
variance_limit=0.001,
debug=True)
Benchmarks.prequential_evaluation(evol_model, X, y, adjusted_rand_score,
train_size, window_size)
def main():
X, y = load_dataset.load_dataset("gaussian")
# X, y = load_dataset.load_dataset("s2")
X = X[:1000, :8]
y = y[:1000]
standardized_X = preprocessing.scale(X)
minmaxscaler = preprocessing.MinMaxScaler()
minmaxscaler.fit(standardized_X)
X = minmaxscaler.transform(standardized_X)
evol_model = EvolvingClustering.EvolvingClustering(variance_limit=0.01,
debug=True)
# evol_model = EvolvingClustering2.EvolvingClustering2(rad=0.04, debug=True)
evol_model.fit(X[:100])
evol_model.fit(X[100:200])
y_pred = evol_model.predict(X[:3000])
cmap = plt.cm.get_cmap('rainbow')
nsamples = 1000
from sklearn import datasets
from sklearn import preprocessing
X,y = datasets.fetch_covtype(return_X_y=True)
X = X[:nsamples]
y = y[:nsamples]
X = preprocessing.scale(X)
minmaxscaler = preprocessing.MinMaxScaler()
minmaxscaler.fit(X)
X = minmaxscaler.transform(X)
## Running training and prediction..
evol_model = EvolvingClustering.EvolvingClustering(variance_limit=0.00001, debug=True)
tic = time()
evol_model.fit(X)
tac = time()
print('Operation took {} ms'.format((tac - tic) * 1e3))
y_pred = evol_model.predict(X)
#pickle.dump(evol_model, open("evol_model.pkl", "wb"))
## END Running training and prediction..
## Load pickle
# evol_model = pickle.load(open("evol_model.pkl", "rb"))
# y_pred = evol_model.labels_
## END Load pickle
n_clusters=params['n_clusters'], linkage='ward',
connectivity=connectivity)
spectral = cluster.SpectralClustering(
n_clusters=params['n_clusters'], eigen_solver='arpack',
affinity="nearest_neighbors")
dbscan = cluster.DBSCAN(eps=params['eps'])
affinity_propagation = cluster.AffinityPropagation(
damping=params['damping'], preference=params['preference'])
average_linkage = cluster.AgglomerativeClustering(
linkage="average", affinity="cityblock",
n_clusters=params['n_clusters'], connectivity=connectivity)
birch = cluster.Birch(n_clusters=params['n_clusters'])
# gmm = mixture.GaussianMixture(
# n_components=params['n_clusters'], covariance_type='full')
evol = EvolvingClustering.EvolvingClustering(macro_cluster_update=1, variance_limit=0.01, debug=False)
# clustering_algorithms = (
# ('MiniBatchKMeans', two_means),
# ('AffinityPropagation', affinity_propagation),
# ('MeanShift', ms),
# ('SpectralClustering', spectral),
# ('Ward', ward),
# ('AgglomerativeClustering', average_linkage),
# ('DBSCAN', dbscan),
# ('Birch', birch),
# ('GaussianMixture', gmm)
# )
clustering_algorithms = (
('MiniBatchKMeans', two_means),