def main_kmeans(X, U_init):
"""
Will perform the k means algorithm on X with U_init as initialization
:param X: The input data in which to find the clusters.
:param U_init: The initialization of the the clusters.
:return: The final centroids, the indicator vector
"""
start_kmeans = time.process_time()
if paraman["--minibatch"]:
objective_values_k, final_centroids, indicator_vector_final = kmeans_minibatch(X_data=X,
K_nb_cluster=paraman["--nb-cluster"],
nb_iter=paraman["--nb-iteration"],
initialization=U_init,
batch_size=paraman["--minibatch"]
)
else:
objective_values_k, final_centroids, indicator_vector_final = kmeans(X_data=X,
K_nb_cluster=paraman["--nb-cluster"],
nb_iter=paraman["--nb-iteration"],
initialization=U_init)
stop_kmeans = time.process_time()
kmeans_traintime = stop_kmeans - start_kmeans
kmeans_results = {
"traintime": kmeans_traintime
}
objprinter.add("kmeans_objective", ("after t", ), objective_values_k)
resprinter.add(kmeans_results)
return final_centroids, indicator_vector_final
def main_kmeans(X, U_init):
"""
Will perform the k means algorithm on X with U_init as initialization
:param X: The input data in which to find the clusters.
:param U_init: The initialization of the the clusters.
:return: The final centroids, the indicator vector
"""
if paraman["--minibatch"]:
objective_values_k, final_centroids, indicator_vector_final = kmeans_minibatch(X_data=X,
K_nb_cluster=U_init.shape[0],
nb_iter=paraman["--nb-iteration"],
initialization=U_init,
batch_size=paraman["--minibatch"]
)
else:
objective_values_k, final_centroids, indicator_vector_final = kmeans(X_data=X,
K_nb_cluster=U_init.shape[0],
nb_iter=paraman["--nb-iteration"],
initialization=U_init)
return final_centroids, indicator_vector_final
def main_kmeans(X, U_init):
"""
Will perform the k means algorithm on X with U_init as initialization
:param X: The input data in which to find the clusters.
:param U_init: The initialization of the the clusters.
:return: The final centroids, the indicator vector
"""
if paraman["--l1-proj"] is not None and paraman["--lambda-l1-proj"] is None:
if paraman["--blobs"] is not None:
param_lambda = None
elif paraman["--caltech256"] is not None:
param_lambda = 868
elif paraman["--census"]:
param_lambda = None
elif paraman["--kddcup04"]:
param_lambda = None
elif paraman["--kddcup99"]:
param_lambda = 4.9
elif paraman["--plants"]:
param_lambda = None
elif paraman["--breast-cancer"]:
param_lambda = 600
elif paraman["--covtype"]:
param_lambda = 964
elif paraman["--mnist"]:
param_lambda = 2550
elif paraman["--fashion-mnist"]:
param_lambda = 1485
elif paraman["--light-blobs"]:
param_lambda = None
elif paraman["--lfw"]:
param_lambda = None
elif paraman["--million-blobs"] is not None:
param_lambda = None
elif paraman["--coil20"] is not None:
param_lambda = 5.6
else:
raise NotImplementedError("Unknown dataset.")
else:
param_lambda = paraman["--lambda-l1-proj"]
start_kmeans = time.process_time()
if paraman["--minibatch"]:
objective_values_k, final_centroids, indicator_vector_final = kmeans_minibatch(
X_data=X,
K_nb_cluster=paraman["--nb-cluster"],
nb_iter=paraman["--nb-iteration"],
initialization=U_init,
batch_size=paraman["--minibatch"],
proj_l1=paraman["--l1-proj"],
_lambda=param_lambda,
epsilon=paraman["--epsilon-tol-proj"])
else:
objective_values_k, final_centroids, indicator_vector_final = kmeans(
X_data=X,
K_nb_cluster=paraman["--nb-cluster"],
nb_iter=paraman["--nb-iteration"],
initialization=U_init,
proj_l1=paraman["--l1-proj"],
_lambda=param_lambda,
epsilon=paraman["--epsilon-tol-proj"])
stop_kmeans = time.process_time()
kmeans_traintime = stop_kmeans - start_kmeans
print(objective_values_k[-1])
kmeans_results = {
"traintime": kmeans_traintime,
"actual_param_lambda": param_lambda
}
objprinter.add("kmeans_objective", ("after t", ), objective_values_k)
resprinter.add(kmeans_results)
return final_centroids, indicator_vector_final
