n <- 50
ii <- sample(1:nrow(iris), n)
d <- iris[ii, ]
group <- d[, 5]
rownames(d) <- paste(d$Species, 1:nrow(d))

library(DT)
datatable(d, options = list(pageLength = 5))

# カラーパレット
COL <- c(rgb(255,   0,   0,  105, max = 255), # 赤
         rgb(  0,   0, 255,  105, max = 255), # 青
         rgb(  0, 155,   0,  105, max = 255), # 緑
         rgb(100, 100, 100,   55, max = 255)) # 灰

pairs(d[, -5], pch = 15 + as.numeric(d$Species), col = COL[group], 
      lower.panel = NULL, oma = c(3, 3, 5, 3), main = 'Iris Data')

par(xpd = T)
legend('bottomleft', col = COL[1:3], pch = 16:18, legend = unique(d$Species))

library(cluster)
library(factoextra)

##  要求されたパッケージ ggplot2 をロード中です

## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa

# AGNES
hc.a <- agnes(d)
fviz_dend(as.hclust(hc.a), k = 3, horiz = T, rect = T, rect_fill = T,
 color_labels_by_k = F, rect_border = 'jco', k_colors = 'jco', cex = 0.4)

## Warning: The `<scale>` argument of `guides()` cannot be `FALSE`. Use "none" instead as
## of ggplot2 3.3.4.
## ℹ The deprecated feature was likely used in the factoextra package.
##   Please report the issue at <https://github.com/kassambara/factoextra/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

gr <- cutree(hc.a, k = 3) # クラスター数kのときのグループ番号
head(gr)

## [1] 1 2 1 1 1 2

# DIANA
hc.d <- diana(d)
fviz_dend(as.hclust(hc.d), k = 3, horiz = T, rect = T, rect_fill = T,
 color_labels_by_k = F, rect_border = 'jco', k_colors = 'jco', cex = 0.4)

library(plotly)

## 
##  次のパッケージを付け加えます: 'plotly'

##  以下のオブジェクトは 'package:ggplot2' からマスクされています:
## 
##     last_plot

##  以下のオブジェクトは 'package:stats' からマスクされています:
## 
##     filter

##  以下のオブジェクトは 'package:graphics' からマスクされています:
## 
##     layout

library(ggplot2)
library(cluster)
library(ggdendro)
hc.a |> as.dendrogram() |> ggdendrogram(rotate = T) |> ggplotly() # AGNES

hc.d |> as.dendrogram() |> ggdendrogram(rotate = T) |> ggplotly() # DIANA

METHOD <- c('single', 'complete', 'average',
            'weighted', 'ward', 'gaverage', 'flexible')

ac <- rep(NA, 7)
for (i in 1:6) ac[i] <- agnes(d, method = METHOD[i])$ac
ac[7] <- agnes(d, method = METHOD[7], par.method = 0.5)$ac
names(ac) <- METHOD

barplot(ac, ylim = c(0.8, 1.0), xpd = F)
abline(h = seq(0, 1, 0.05), lty = 3)

fviz_nbclust(d[, -5], FUNcluster = hcut, method = 'wss')

fviz_nbclust(d[, -5], FUNcluster = hcut, method = 'gap_stat')

fviz_nbclust(d[, -5], FUNcluster = hcut, method = 'silhouette')

#kadai
d <- read.csv('https://stats.dip.jp/01_ds/data/Mall_Customers.csv')

colnames(d) <- c('id', 'gender', 'age', 'income', 'score')

datatable(d, options = list(pageLength = 5))

NGROUPS <- 2


COL <- rainbow(NGROUPS)

matplot(x = d$income, y = d$score, pch = 16, type = 'p', col = COL[1])
grid()

library(cluster)

d_clust <- d[, c('income', 'score')]
hc.a <- agnes(d_clust)
gr <- cutree(as.hclust(hc.a), k = 5)  

COL <- c("red", "green", "blue", "yellow", "purple")

a <- vector("list", length(unique(gr))) 
for (i in 1:length(unique(gr))) {
  a[[i]] <- d[gr == i, ]  
}

matplot(x = d$income, y = d$score, pch = 16, type = 'n', col = COL[1])

for (i in 1:length(unique(gr))) {
  matpoints(x = a[[i]]$income, y = a[[i]]$score, pch = 16, type = 'p', col = COL[i])
}

grid()