def __init__(self,
n_cluster: int,
data: np.ndarray,
use_kmeans: bool = False,
w: float = 0.9,
c1: float = 0.5,
c2: float = 0.3,
flag: int = 1,
weights: list = None):
index = np.random.choice(list(range(len(data))), n_cluster)
self.centroids = data[index].copy()
if use_kmeans:
kmeans = KMeans(n_cluster=n_cluster, init_pp=False)
kmeans.fit(data)
self.centroids = kmeans.centroid.copy()
self.best_position = self.centroids.copy()
self.best_score = quantization_error(self.centroids, self._predict(data), data)
self.flag=flag
if self.flag%2==1:
self.best_sse = calc_sse(self.centroids, self._predict(data), data)
else:
self.best_sse = calc_sse2(self.centroids, self._predict(data), data, weights)
self.velocity = np.zeros_like(self.centroids)
self._w = w
self._c1 = c1
self._c2 = c2
def _update_centroids(self, data: np.ndarray):
self.centroids = self.centroids + self.velocity
new_score = quantization_error(self.centroids, self._predict(data),
data)
sse = calc_sse(self.centroids, self._predict(data), data)
self.best_sse = min(sse, self.best_sse)
if new_score < self.best_score:
self.best_score = new_score
self.best_position = self.centroids.copy()
def __init__(self,
n_cluster: int,
data: np.ndarray,
use_kmeans: bool = False,
w: int = 9,
c1: int = 5,
c2: int = 3):
index = np.random.choice(list(range(len(data))), n_cluster)
self.centroids = data[index].copy()
if use_kmeans:
kmeans = KMeans(n_cluster=n_cluster, init_pp=False)
kmeans.fit(data)
self.centroids = kmeans.centroid.copy()
self.best_position = self.centroids.copy()
self.best_score = quantization_error(self.centroids,
self._predict(data), data)
self.best_sse = calc_sse(self.centroids, self._predict(data), data)
self.velocity = np.zeros_like(self.centroids)
self._w = w
self._c1 = c1
self._c2 = c2
def kmeans_custom(k, data, stdev_mean):
num_examples = len(data)
num_features = len(data[0]['point'])
min_sse = float("inf")
min_sse_clusters = []
sse_list = []
clusters = init_clusters_custom(k, data)
# do 50 iterations
for i in range (0, 49):
kmeans.calc_cluster_centroids(clusters)
if kmeans.reassign_clusters(clusters) == False:
# print "break at " + str(i)
break
sse = kmeans.calc_sse(clusters)
if sse < min_sse:
min_sse_clusters = copy.deepcopy(clusters)
min_sse = sse
print "k = " + str(k)
kmeans.print_cluster_centroids(min_sse_clusters, stdev_mean)
print ""
