fuzzy

fuzzyCmeans(X, max_cluster=10, m=2, error=1e-06, maxiter=1000, init=None, metric=‘euclidean’, output=’./’, processes=1, verbose=False)

Fuzzy C-Means clustering function. Iteratively test and report statistics on multiple number of clusters. Based on documentation found here : https://pythonhosted.org/scikit-fuzzy/auto_examples/plot_cmeans.html

Parameters

X : Numpy array with data to cluster (Subject x Features).

max_cluster : Maximum number of clusters to fit a model for. Defaults to 10.

m : Exponentiation value to apply on the membership function. Defaults to 2.

error : Stopping criterion. Defaults to 1E-6.

maxiter : Maximum iteration value. Defaults to 1000.

init : Initial fuzzy c-partitioned matrix. Defaults to None.

metric : Distance metric to use to compute intra/inter subjects/clusters distance. Defaults to euclidean.

output : Output folder to save the visualization. Defaults to “./”.

processes : Number of processes to use. Defaults to 1.

verbose : If true, produce verbose output. Defaults to False.

Returns

cntr : Cluster centroids array.

u : Membership array.

wss : Within-cluster Sum of Square Error.

fpc : Fuzzy partition coefficient.

ss : Silhouette Coefficient Score.

chi : Calinski-Harabasz Index.

dbi : Davies-Bouldin Index.

gap : GAP statistic.

sk : GAP standard error.