You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
64 lines
1.9 KiB
64 lines
1.9 KiB
from sklearn.cluster import DBSCAN, KMeans
|
|
import numpy as np
|
|
|
|
class DBSCAN_cluster():
|
|
def __init__(self, eps, min_samples,data):
|
|
self.eps = eps
|
|
self.min_samples = min_samples
|
|
self.data = data
|
|
self.labels = np.array([])
|
|
|
|
def run(self):
|
|
dbscan = DBSCAN(eps=self.eps, min_samples=self.min_samples)
|
|
self.labels = dbscan.fit_predict(self.data)
|
|
return self.labels
|
|
|
|
def get_stats(self):
|
|
unique_labels = np.unique(self.labels)
|
|
stats = []
|
|
for label in unique_labels:
|
|
if label == -1:
|
|
continue
|
|
cluster_points = self.data[self.labels == label]
|
|
num_points = len(cluster_points)
|
|
density = num_points / (np.max(cluster_points, axis=0) - np.min(cluster_points, axis=0)).prod()
|
|
stats.append({
|
|
"cluster": label,
|
|
"num_points": num_points,
|
|
"density": density
|
|
})
|
|
|
|
return stats
|
|
|
|
|
|
class KMeans_cluster():
|
|
def __init__(self, n_clusters, n_init, max_iter, data):
|
|
self.n_clusters = n_clusters
|
|
self.n_init = n_init
|
|
self.max_iter = max_iter
|
|
self.data = data
|
|
self.labels = np.array([])
|
|
self.centers = []
|
|
|
|
def run(self):
|
|
kmeans = KMeans(n_clusters=self.n_clusters, init="random", n_init=self.n_init, max_iter=self.max_iter, random_state=111)
|
|
self.labels = kmeans.fit_predict(self.data)
|
|
self.centers = kmeans.cluster_centers_
|
|
return self.labels
|
|
|
|
|
|
def get_stats(self):
|
|
unique_labels = np.unique(self.labels)
|
|
stats = []
|
|
|
|
for label in unique_labels:
|
|
cluster_points = self.data[self.labels == label]
|
|
num_points = len(cluster_points)
|
|
center = self.centers[label]
|
|
stats.append({
|
|
'cluster': label,
|
|
'num_points': num_points,
|
|
'center': center
|
|
})
|
|
return stats
|