scikit-learn（工程中用的相对较多的模型介绍）：2.3. Clustering（可用于特征的无监督降维）

参考：http://scikit-learn.org/stable/modules/clustering.html

在实际项目中，我们真的很少用到那些简单的模型，比如LR、kNN、NB等，虽然经典，但在工程中确实不实用。

今天我们不关注具体的模型，而关注无监督的聚类方法。

之所以关注无监督聚类方法，是因为，在实际项目中，我们除了使用PCA等方法降维外，有时候我们也会考虑使用聚类的方法降维特征。

Overview of clustering methods：



A comparison of the clustering algorithms in scikit-learn

[thead]
[/thead]

Method name	Parameters	Scalability	Usecase	Geometry (metric used)
K-Means	number of clusters	Very large n_samples, medium n_clusterswith MiniBatch code	General-purpose, even cluster size, flat geometry, not too many clusters	Distances between points
Affinity propagation	damping, sample preference	Not scalable with n_samples	Many clusters, uneven cluster size, non-flat geometry	Graph distance (e.g. nearest-neighbor graph)
Mean-shift	bandwidth	Not scalable withn_samples	Many clusters, uneven cluster size, non-flat geometry	Distances between points
Spectral clustering	number of clusters	Medium n_samples, small n_clusters	Few clusters, even cluster size, non-flat geometry	Graph distance (e.g. nearest-neighbor graph)
Ward hierarchical clustering	number of clusters	Large n_samples andn_clusters	Many clusters, possibly connectivity constraints	Distances between points
Agglomerative clustering	number of clusters, linkage type, distance	Large n_samples andn_clusters	Many clusters, possibly connectivity constraints, non Euclidean distances	Any pairwise distance
DBSCAN	neighborhood size	Very large n_samples, medium n_clusters	Non-flat geometry, uneven cluster sizes	Distances between nearest points
Gaussian mixtures	many	Not scalable	Flat geometry, good for density estimation	Mahalanobis distances to centers
Birch	branching factor, threshold, optional global clusterer.	Large n_clusters andn_samples	Large dataset, outlier removal, data reduction.	Euclidean distance between points