install.packages("factoextra")
install.packages("cluster")
install.packages("magrittr")
library("cluster")
library("factoextra")
library("magrittr")
install.packages("pacman")
pacman::p_load(pacman, party,rio, tidyverse)
install.packages('dplyr', dependencies = TRUE)
df<-read_csv("datadc.csv") 
df2<-scale(df)
h.means<-hclust(df2,method="ward.D2")

dist_mat <- dist(df2, method = 'euclidean')
hclust_avg <- hclust(dist_mat, method = 'ward.D2')
plot(hclust_avg)

cut_avg <- cutree(hclust_avg, k =6)
suppressPackageStartupMessages(library(dplyr))
df_cl <- mutate(df, cluster = cut_avg)
count(df_cl,cluster)
df_cl
write.csv(df_cl,"output207.csv")

rect.hclust(hclust_avg , k = 6, border = 2:6) 
abline(h =1 , col = 'red')


suppressPackage]StartupMessages(library(dendextend))
avg_dend_obj <- as.dendrogram(hclust_avg)
avg_col_dend <- color_branches(avg_dend_obj, h = 1)
plot(avg_col_dend)

suppressPackageStartupMessages(library(ggplot2))
ggplot(df, aes(x=220, y = 1220, color = factor(rect.hclust))) + geom_point()