def fast_dbscan(X,
eps=0.5,
min_samples=5,
n_clusters=None,
metric='euclidean',
algorithm='brute',
random_state: int = 1,
framework: Literal['auto', 'cuml', 'sklearn'] = 'auto'):
r""" DBSCAN - Density-Based Spatial Clustering of Applications with Noise.
Finds core samples of high density and expands clusters from them.
Good for data which contains clusters of similar density.
DBSCAN is a very powerful if the datapoints tend to congregate in
larger groups.
Arguments:
eps : float, default=0.5
The maximum distance between two samples for one to be considered
as in the neighborhood of the other. This is not a maximum bound
on the distances of points within a cluster. This is the most
important DBSCAN parameter to choose appropriately for your data set
and distance function.
min_samples : int, default=5
The number of samples (or total weight) in a neighborhood for a point
to be considered as a core point. This includes the point itself.
algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='brute'
The algorithm to be used by the NearestNeighbors module
to compute pointwise distances and find nearest neighbors.
See NearestNeighbors module documentation for details.
"""
kwargs = dict(locals())
X = kwargs.pop('X')
framework = kwargs.pop('framework')
n_cluster = kwargs.pop('n_clusters')
random_state = kwargs.pop('random_state')
## fine-tuning the kwargs
if _check_cuml(framework):
from cuml.cluster import DBSCAN
kwargs.pop('algorithm')
kwargs.pop('metric')
else:
from sklearn.cluster import DBSCAN
## fitting
dbscan = DBSCAN(**kwargs)
dbscan.fit(X)
dbscan._fitid = id(X)
dbscan.predict = types.MethodType(dbscan_predict, dbscan)
return dbscan
