install.packages(vegan)
library(vegan)

getwd()
setwd("c:/DANKA HLAVNY ADRESAR/Vyuka/Bi5980 Biodiverzita/Biodiverzita vyuka 2015")

pilatkoviti <- read.csv("05_2015_Data Pilatkoviti.csv",sep = ";" ,dec = ",", header = T, row.names = 1)
pilatkoviti

# nazvy riadkov su povodny prvy stlpec 

pilatkoviti.bray <- vegdist(pilatkoviti, "bray", diag = T, upper = T) 
pilatkoviti.bray

?hclust
hclust(pilatkoviti.bray, method = "complete")

pilatkoviti.bray.complete <- hclust(pilatkoviti.bray, method = "complete") 

plot(pilatkoviti.bray.complete)
plot(pilatkoviti.bray.complete, main = "Bray-Curtis, Complete linkage")
plot(pilatkoviti.bray.complete, labels = rownames(pilatkoviti.bray), hang = -1, main = "Bray-Curtis, Complete linkage")
plot(pilatkoviti.bray.complete, labels = rownames(pilatkoviti.bray), hang = -1, axes = FALSE, main = "Bray-Curtis, Complete linkage")
plot(pilatkoviti.bray.complete, labels = rownames(pilatkoviti.bray), hang = -1, axes = FALSE, ann = FALSE)

pilatkoviti.bray.ward <- hclust(pilatkoviti.bray, method = "ward.D2")  # ... ale tu pozor, lebo Ward sa nemá používať s Bray-Curtis
# Ward method should not be combined with distance measures, which are not strictly metric, which is e.g. popular Bray-Curtis distance

plot(pilatkoviti.bray.ward, labels = rownames(pilatkoviti.bray), hang = -1, main = "Bray-Curtis, Ward")
plot(pilatkoviti.bray.ward, labels = rownames(pilatkoviti.bray), hang = -1, axes = FALSE, ann = FALSE)


--------------------------------------------------------------------------------------------------------------

# oznaceni shluku v dendrogramu, budem tam chciet oznacit 2 shkuky, alebo 3 shluky

plot (pilatkoviti.bray.complete, labels = rownames(pilatkoviti.bray), hang = -1, axes = FALSE, main = 'Complete linkage')

rect.hclust (pilatkoviti.bray.complete, k = 2)
rect.hclust (pilatkoviti.bray.complete, k = 3, border = "blue")


prislusnost.3shluky <- cutree (pilatkoviti.bray.complete, k = 3)   # vrati prislusnost objektu ke shlukum 
prislusnost.3shluky

--------------------------------------------------------------------------------------------------------------

# nakreslime 3 dendrogramy na jeden obrazok - single linkage, average linkage, complete linkage

pilatkoviti.bray.single <- hclust(pilatkoviti.bray, method = "single") 
pilatkoviti.bray.average <- hclust(pilatkoviti.bray, method = "average") 
pilatkoviti.bray.complete <- hclust(pilatkoviti.bray, method = "complete") 

par (mfrow = c (1,3))   # nakresli vsetky dendrogramy do jedneho obrazku

plot (pilatkoviti.bray.single, main = 'Single linkage')
plot (pilatkoviti.bray.average, main = 'Average linkage')
plot (pilatkoviti.bray.complete, main = 'Complete linkage')

# alebo ak chceme mat "nozicky" od zaciatku, tak takto:

par (mfrow = c (1,3))
plot (pilatkoviti.bray.single, labels = rownames(pilatkoviti.bray), hang = -1, axes = FALSE, main = 'Single linkage')
plot (pilatkoviti.bray.average, labels = rownames(pilatkoviti.bray), hang = -1, axes = FALSE, main = 'Average linkage')
plot (pilatkoviti.bray.complete, labels = rownames(pilatkoviti.bray), hang = -1, axes = FALSE, main = 'Complete linkage')


# aby nechcelo kreslit vsetky dalsie obrazky po troch, tak ... par(mfrow = c(1,1))

--------------------------------------------------------------------------------------------------------------
POZNAMKA:

agnes (library cluster) ... obsahuje 6 shlukovacich algoritmu, nektere z nich nejsou obsazeny ve funkci 'hclust'.
pak pri kresleni dendrogramu je vhodne nejdrive transformovat objekt z agnes jako objekt z hclust (pouzit as.hclust)

--------------------------------------------------------------------------------------------------------------
POZNAMKA:
nehierarchicke shlukovani - metoda k-means

cluster.kmeans <- kmeans (dis, centers = 5)
cluster.kmeans$cluster