MODULO 5 - Estatística Multivariada - Cluster
Leonardo Reffatti
1 de maio de 2019
Aulas 5.3 à 5.6
Cluster
Este material está disponível em: http://rpubs.com/leonardoreffatti.
Leitura de dados, resumo dos dados e plot de um Cluster simples.
Passo 1- Lendo os dados, resumo dos dados e carregando pacotes
setwd("C:/R/Curso do R/MODULO_5.1")
dados<-read.table("insetos.txt", h=T)
head(dados)## UA Ambiente Gado Temperatura Cobertura Luz Flores sp.1 sp.2
## 1 área1 Mata_Primária Presente 21.8 73 53.5 14 4 0
## 2 área2 Mata_Primária Ausente 21.3 62 61.0 28 5 0
## 3 área3 Mata_Primária Presente 23.8 57 71.5 17 1 0
## 4 área4 Mata_Primária Presente 23.2 49 69.5 29 3 0
## 5 área5 Mata_Primária Presente 21.5 59 61.5 15 5 0
## 6 área6 Mata_Primária Ausente 21.7 78 53.0 24 1 0
## sp.3 sp.4 sp.5 sp.6 sp.7 sp.8 sp.9 sp.10 sp.11 sp.12 sp.13 sp.14 sp.15
## 1 7 2 0 0 3 2 1 1 0 1 3 3 0
## 2 3 7 2 5 2 4 2 3 0 5 6 4 0
## 3 2 0 2 2 3 3 0 5 0 0 0 2 0
## 4 6 4 1 14 2 5 0 2 4 2 3 10 0
## 5 7 2 1 4 1 2 0 1 0 0 3 5 1
## 6 2 4 0 3 4 3 0 1 2 2 2 2 0
## sp.16 sp.17 sp.18 sp.19 sp.20 sp.21 sp.22 sp.23 sp.24 sp.25 sp.26 sp.27
## 1 3 0 0 0 0 0 1 1 1 0 2 0
## 2 3 0 1 0 3 1 2 0 1 1 2 0
## 3 0 0 2 2 0 3 1 1 0 0 1 0
## 4 2 1 3 2 0 4 2 2 2 2 0 0
## 5 0 0 1 3 0 2 2 1 1 0 1 0
## 6 0 0 3 0 4 1 2 1 2 1 1 0
## sp.28 sp.29 sp.30 sp.31 sp.32 sp.33 sp.34
## 1 1 0 0 0 1 0 0
## 2 0 0 0 5 1 0 0
## 3 0 0 0 0 1 0 0
## 4 0 0 0 0 0 0 0
## 5 0 1 0 0 1 1 1
## 6 0 0 0 0 1 0 0attach(dados)
summary(dados)## UA Ambiente Gado Temperatura
## área1 : 1 Mata_Primária :17 Ausente :15 Min. :19.70
## área10 : 1 Mata_Secundária:13 Presente:15 1st Qu.:21.55
## área11 : 1 Median :23.55
## área12 : 1 Mean :24.59
## área13 : 1 3rd Qu.:27.18
## área14 : 1 Max. :31.20
## (Other):24
## Cobertura Luz Flores sp.1
## Min. :27.00 Min. :53.00 Min. : 5.00 Min. :0.000
## 1st Qu.:42.75 1st Qu.:61.12 1st Qu.:20.25 1st Qu.:1.250
## Median :50.50 Median :69.00 Median :26.50 Median :4.000
## Mean :53.37 Mean :67.95 Mean :26.67 Mean :3.433
## 3rd Qu.:64.00 3rd Qu.:74.00 3rd Qu.:35.75 3rd Qu.:5.000
## Max. :78.00 Max. :84.00 Max. :47.00 Max. :6.000
##
## sp.2 sp.3 sp.4 sp.5 sp.6
## Min. :0.00 Min. : 1 Min. :0.00 Min. :0.0 Min. : 0.00
## 1st Qu.:0.00 1st Qu.: 3 1st Qu.:2.00 1st Qu.:0.0 1st Qu.: 3.25
## Median :0.50 Median : 5 Median :4.00 Median :1.5 Median : 7.00
## Mean :1.10 Mean : 5 Mean :3.80 Mean :1.8 Mean : 7.60
## 3rd Qu.:1.75 3rd Qu.: 7 3rd Qu.:5.75 3rd Qu.:3.0 3rd Qu.:11.25
## Max. :5.00 Max. :10 Max. :8.00 Max. :5.0 Max. :20.00
##
## sp.7 sp.8 sp.9 sp.10
## Min. :0.000 Min. :0.0 Min. :0.000 Min. :0.000
## 1st Qu.:1.000 1st Qu.:2.0 1st Qu.:0.000 1st Qu.:0.250
## Median :2.000 Median :3.0 Median :2.000 Median :1.000
## Mean :2.133 Mean :3.3 Mean :1.833 Mean :1.667
## 3rd Qu.:3.000 3rd Qu.:5.0 3rd Qu.:2.750 3rd Qu.:2.750
## Max. :6.000 Max. :7.0 Max. :6.000 Max. :6.000
##
## sp.11 sp.12 sp.13 sp.14
## Min. : 0.000 Min. :0.000 Min. :0.000 Min. : 0.00
## 1st Qu.: 0.000 1st Qu.:0.250 1st Qu.:2.000 1st Qu.: 4.00
## Median : 2.000 Median :2.000 Median :3.000 Median : 6.00
## Mean : 2.967 Mean :2.367 Mean :3.167 Mean : 6.10
## 3rd Qu.: 5.750 3rd Qu.:3.750 3rd Qu.:4.750 3rd Qu.: 8.75
## Max. :11.000 Max. :9.000 Max. :7.000 Max. :13.00
##
## sp.15 sp.16 sp.17 sp.18
## Min. :0.0 Min. :0.0000 Min. :0.0000 Min. :0.0
## 1st Qu.:0.0 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0
## Median :0.0 Median :0.0000 Median :0.0000 Median :0.0
## Mean :1.2 Mean :0.8667 Mean :0.9667 Mean :0.9
## 3rd Qu.:2.0 3rd Qu.:1.7500 3rd Qu.:1.0000 3rd Qu.:2.0
## Max. :5.0 Max. :4.0000 Max. :7.0000 Max. :3.0
##
## sp.19 sp.20 sp.21 sp.22
## Min. :0.0000 Min. :0.0 Min. :0.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:0.0 1st Qu.:2.000 1st Qu.:1.000
## Median :0.0000 Median :0.0 Median :3.000 Median :2.000
## Mean :0.6667 Mean :0.6 Mean :2.467 Mean :1.833
## 3rd Qu.:1.0000 3rd Qu.:0.0 3rd Qu.:3.000 3rd Qu.:2.000
## Max. :4.0000 Max. :4.0 Max. :4.000 Max. :3.000
##
## sp.23 sp.24 sp.25 sp.26
## Min. :0.0000 Min. :0.0000 Min. :0 Min. :0.0000
## 1st Qu.:1.0000 1st Qu.:0.0000 1st Qu.:1 1st Qu.:0.0000
## Median :1.0000 Median :0.0000 Median :1 Median :0.5000
## Mean :0.9667 Mean :0.5333 Mean :1 Mean :0.6333
## 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1 3rd Qu.:1.0000
## Max. :2.0000 Max. :2.0000 Max. :2 Max. :2.0000
##
## sp.27 sp.28 sp.29 sp.30
## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0
## 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0
## Median :0.0000 Median :0.0000 Median :0.0000 Median :0.0
## Mean :0.1667 Mean :0.2667 Mean :0.2333 Mean :0.1
## 3rd Qu.:0.0000 3rd Qu.:0.0000 3rd Qu.:0.0000 3rd Qu.:0.0
## Max. :3.0000 Max. :4.0000 Max. :3.0000 Max. :2.0
##
## sp.31 sp.32 sp.33 sp.34
## Min. :0.0000 Min. :0.0000 Min. :0.0 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0 1st Qu.:0.0000
## Median :0.0000 Median :1.0000 Median :0.0 Median :0.0000
## Mean :0.2667 Mean :0.6667 Mean :0.2 Mean :0.1333
## 3rd Qu.:0.0000 3rd Qu.:1.0000 3rd Qu.:0.0 3rd Qu.:0.0000
## Max. :5.0000 Max. :1.0000 Max. :1.0 Max. :1.0000
## str(dados)## 'data.frame': 30 obs. of 41 variables:
## $ UA : Factor w/ 30 levels "área1","área10",..: 1 12 23 25 26 27 28 29 30 2 ...
## $ Ambiente : Factor w/ 2 levels "Mata_Primária",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ Gado : Factor w/ 2 levels "Ausente","Presente": 2 1 2 2 2 1 1 1 2 2 ...
## $ Temperatura: num 21.8 21.3 23.8 23.2 21.5 21.7 20.3 19.7 24.7 20.2 ...
## $ Cobertura : int 73 62 57 49 59 78 64 74 48 75 ...
## $ Luz : num 53.5 61 71.5 69.5 61.5 53 58 56 71 60.5 ...
## $ Flores : int 14 28 17 29 15 24 21 29 20 5 ...
## $ sp.1 : int 4 5 1 3 5 1 1 0 6 3 ...
## $ sp.2 : int 0 0 0 0 0 0 3 1 4 0 ...
## $ sp.3 : int 7 3 2 6 7 2 2 1 8 3 ...
## $ sp.4 : int 2 7 0 4 2 4 5 3 3 1 ...
## $ sp.5 : int 0 2 2 1 1 0 3 4 0 0 ...
## $ sp.6 : int 0 5 2 14 4 3 3 9 8 0 ...
## $ sp.7 : int 3 2 3 2 1 4 3 2 1 3 ...
## $ sp.8 : int 2 4 3 5 2 3 0 0 1 0 ...
## $ sp.9 : int 1 2 0 0 0 0 2 0 1 0 ...
## $ sp.10 : int 1 3 5 2 1 1 0 0 1 1 ...
## $ sp.11 : int 0 0 0 4 0 2 0 2 0 0 ...
## $ sp.12 : int 1 5 0 2 0 2 4 5 0 0 ...
## $ sp.13 : int 3 6 0 3 3 2 3 1 4 2 ...
## $ sp.14 : int 3 4 2 10 5 2 2 5 8 0 ...
## $ sp.15 : int 0 0 0 0 1 0 0 0 1 0 ...
## $ sp.16 : int 3 3 0 2 0 0 3 0 1 0 ...
## $ sp.17 : int 0 0 0 1 0 0 0 0 0 0 ...
## $ sp.18 : int 0 1 2 3 1 3 0 0 2 0 ...
## $ sp.19 : int 0 0 2 2 3 0 0 2 0 1 ...
## $ sp.20 : int 0 3 0 0 0 4 0 2 0 0 ...
## $ sp.21 : int 0 1 3 4 2 1 3 3 3 2 ...
## $ sp.22 : int 1 2 1 2 2 2 1 2 2 2 ...
## $ sp.23 : int 1 0 1 2 1 1 2 1 2 1 ...
## $ sp.24 : int 1 1 0 2 1 2 0 1 1 1 ...
## $ sp.25 : int 0 1 0 2 0 1 1 0 0 1 ...
## $ sp.26 : int 2 2 1 0 1 1 2 1 1 1 ...
## $ sp.27 : int 0 0 0 0 0 0 3 0 0 0 ...
## $ sp.28 : int 1 0 0 0 0 0 0 0 0 2 ...
## $ sp.29 : int 0 0 0 0 1 0 0 0 0 0 ...
## $ sp.30 : int 0 0 0 0 0 0 0 0 0 0 ...
## $ sp.31 : int 0 5 0 0 0 0 1 0 0 0 ...
## $ sp.32 : int 1 1 1 0 1 1 1 0 1 1 ...
## $ sp.33 : int 0 0 0 0 1 0 0 0 1 0 ...
## $ sp.34 : int 0 0 0 0 1 0 0 0 0 0 ...library(permute)
library(lattice)
library(vegan)## This is vegan 2.5-2Passo 2: Padronizar os valores das variáveis ambientais quando as escalas das unidades das variáveis são diferentes.
#padronização = (cada valor - média) / desvio padrão
#todas as variáveis variam na mesma magnitude, média = 0 e sd = 1
#as diferenças serão mantidas após a padronização
var.amb <- dados[ ,4:7]
var.amb.pad <- decostand(var.amb, method = "standardize")
plot(var.amb[,1:2])
plot(var.amb.pad[,1:2])
Passo 3: Criando a Matriz de distâncias pelo método euclidiano
dist.amb <- dist(var.amb.pad, method = "euclid")Passo 4: Criando o Cluster
cluster.amb <- hclust(dist.amb, method = "average")
#method = "average" = UPGMA
plot(cluster.amb)
Passo 5: Customizando o Cluster - Definindo altura de corte de grupos
cluster.amb <- hclust(dist.amb, method = "average")
#method = "average" = UPGMA
plot(cluster.amb, hang = -1)
#para fazer um corte "agrupamentos" em uma determinada distância
rect.hclust(cluster.amb, h=2)
Passo 6: Customizando o Cluster - Definindo número de grupos e listando os agrupamentos formados
cluster.amb <- hclust(dist.amb, method = "average")
#method = "average" = UPGMA
plot(cluster.amb, hang = -1)
#para fazer"agrupamentos" definindo um número de grupos
rect.hclust(cluster.amb, k=3)
grupos <- cutree(cluster.amb, k=3)
grupos## [1] 1 1 2 3 1 1 1 1 2 1 1 2 2 1 1 2 1 3 3 3 3 3 3 3 3 3 3 3 3 3Passo 7: Customizando o Cluster - Colocando o Cluster na Horizontal
cluster.amb <- hclust(dist.amb, method = "average")
#method = "average" = UPGMA
plot(as.dendrogram(cluster.amb), horiz = TRUE)
Passo 8: Customizando o Cluster - Identificando as Unidades Amostrais no Cluster
#inserindo os nomes das UAs no Cluster
setwd("C:/R/Curso do R/MODULO_5.1")
dados<-read.table("insetos.txt", h=T, row.names = 1)
attach(dados)## The following objects are masked from dados (pos = 6):
##
## Ambiente, Cobertura, Flores, Gado, Luz, sp.1, sp.10, sp.11,
## sp.12, sp.13, sp.14, sp.15, sp.16, sp.17, sp.18, sp.19, sp.2,
## sp.20, sp.21, sp.22, sp.23, sp.24, sp.25, sp.26, sp.27, sp.28,
## sp.29, sp.3, sp.30, sp.31, sp.32, sp.33, sp.34, sp.4, sp.5,
## sp.6, sp.7, sp.8, sp.9, Temperaturavar.amb <- dados[ ,3:6]
var.amb.pad <- decostand(var.amb, method = "standardize")
dist.amb <- dist(var.amb.pad, method = "euclid")
cluster.amb <- hclust(dist.amb, method = "average")
plot(as.dendrogram(cluster.amb), horiz = TRUE)