fuzzy clustering

#1
I am very new R and statistics..

I have dataset that contain 4 columns of data

incident | Lat | Long | ClosedDate >
Construction Noise | 1.324 | 1.44 | 29/03/2011>
Smell | 1.324 | 1.525 | 29/02/2009>
Accident | 1.323 | 1.424 | 29/01/2012>
A correlation matrix is generated by combining spatial and temporal correlation. Incident clustering was done using Hierarchical Agglomerative Clustering (HAC). Sample code shown below

hc_issues <- hclust(as.dist(inverse_cc_combined), "complete")
plot(hc_issues, cex=0.8, hang=-1)

###Automatically cut the dendrogram
require(dynamicTreeCut)
ct_issues <- cutreeHybrid(hc_issues, inverse_cc_combined, minClusterSize=5)
Now that i need to find to probabilities of data elements acrross multiple clusters and i want to use fuzzy clustering.

below is the desire output

Incident Cluster_1_Prob Cluster_2_Prob Cluster_3_Prob
Noise 0.52 0.5 0.4
Smell 0 .32 0.5 0.9
How can acheive this in R (using Fanny or any other method)

i have attached the dataset sample and current H clustering code...
 
Last edited: