packageVersion("rlang")
## [1] '1.3.0'
library(factoextra)
## Warning: package 'factoextra' was built under R version 4.5.3
## Loading required package: ggplot2
## Welcome to factoextra!
## Want to learn more? See two factoextra-related books at https://www.datanovia.com/library/principal-component-methods
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.5.2
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(tidyr)
## Warning: package 'tidyr' was built under R version 4.5.3
library(ggplot2)
library(corrplot)
## Warning: package 'corrplot' was built under R version 4.5.3
## corrplot 0.95 loaded
library(cluster)
## Warning: package 'cluster' was built under R version 4.5.3
library(factoextra)
library(knitr)
## Warning: package 'knitr' was built under R version 4.5.3
data_whr <- read.csv(
"world-happiness-report-2021.csv",
fileEncoding = "UTF-8-BOM",
stringsAsFactors = FALSE
)
# Menampilkan dimensi data
cat("Jumlah baris (negara):", nrow(data_whr), "\n")
## Jumlah baris (negara): 149
cat("Jumlah kolom (variabel):", ncol(data_whr), "\n")
## Jumlah kolom (variabel): 20
# Struktur dataset
str(data_whr)
## 'data.frame': 149 obs. of 20 variables:
## $ Country.name : chr "Finland" "Denmark" "Switzerland" "Iceland" ...
## $ Regional.indicator : chr "Western Europe" "Western Europe" "Western Europe" "Western Europe" ...
## $ Ladder.score : num 7.84 7.62 7.57 7.55 7.46 ...
## $ Standard.error.of.ladder.score : num 0.032 0.035 0.036 0.059 0.027 0.035 0.036 0.037 0.04 0.036 ...
## $ upperwhisker : num 7.9 7.69 7.64 7.67 7.52 ...
## $ lowerwhisker : num 7.78 7.55 7.5 7.44 7.41 ...
## $ Logged.GDP.per.capita : num 10.8 10.9 11.1 10.9 10.9 ...
## $ Social.support : num 0.954 0.954 0.942 0.983 0.942 0.954 0.934 0.908 0.948 0.934 ...
## $ Healthy.life.expectancy : num 72 72.7 74.4 73 72.4 73.3 72.7 72.6 73.4 73.3 ...
## $ Freedom.to.make.life.choices : num 0.949 0.946 0.919 0.955 0.913 0.96 0.945 0.907 0.929 0.908 ...
## $ Generosity : num -0.098 0.03 0.025 0.16 0.175 0.093 0.086 -0.034 0.134 0.042 ...
## $ Perceptions.of.corruption : num 0.186 0.179 0.292 0.673 0.338 0.27 0.237 0.386 0.242 0.481 ...
## $ Ladder.score.in.Dystopia : num 2.43 2.43 2.43 2.43 2.43 2.43 2.43 2.43 2.43 2.43 ...
## $ Explained.by..Log.GDP.per.capita : num 1.45 1.5 1.57 1.48 1.5 ...
## $ Explained.by..Social.support : num 1.11 1.11 1.08 1.17 1.08 ...
## $ Explained.by..Healthy.life.expectancy : num 0.741 0.763 0.816 0.772 0.753 0.782 0.763 0.76 0.785 0.782 ...
## $ Explained.by..Freedom.to.make.life.choices: num 0.691 0.686 0.653 0.698 0.647 0.703 0.685 0.639 0.665 0.64 ...
## $ Explained.by..Generosity : num 0.124 0.208 0.204 0.293 0.302 0.249 0.244 0.166 0.276 0.215 ...
## $ Explained.by..Perceptions.of.corruption : num 0.481 0.485 0.413 0.17 0.384 0.427 0.448 0.353 0.445 0.292 ...
## $ Dystopia...residual : num 3.25 2.87 2.84 2.97 2.8 ...
# Cek missing values per kolom
missing_count <- colSums(is.na(data_whr))
kable(
data.frame(Variabel = names(missing_count), Missing_Values = as.numeric(missing_count)),
caption = "Pemeriksaan Nilai Hilang (Missing Values)"
)
| Variabel | Missing_Values |
|---|---|
| Country.name | 0 |
| Regional.indicator | 0 |
| Ladder.score | 0 |
| Standard.error.of.ladder.score | 0 |
| upperwhisker | 0 |
| lowerwhisker | 0 |
| Logged.GDP.per.capita | 0 |
| Social.support | 0 |
| Healthy.life.expectancy | 0 |
| Freedom.to.make.life.choices | 0 |
| Generosity | 0 |
| Perceptions.of.corruption | 0 |
| Ladder.score.in.Dystopia | 0 |
| Explained.by..Log.GDP.per.capita | 0 |
| Explained.by..Social.support | 0 |
| Explained.by..Healthy.life.expectancy | 0 |
| Explained.by..Freedom.to.make.life.choices | 0 |
| Explained.by..Generosity | 0 |
| Explained.by..Perceptions.of.corruption | 0 |
| Dystopia…residual | 0 |
# Cek jumlah baris duplikat
cat("Jumlah data duplikat:", sum(duplicated(data_whr)), "\n")
## Jumlah data duplikat: 0
cat("Jumlah negara unik:", n_distinct(data_whr$Country.name), "\n")
## Jumlah negara unik: 149
#Pemilihan Variabel untuk Clustering
fitur_klaster <- c(
"Logged.GDP.per.capita",
"Social.support",
"Healthy.life.expectancy",
"Freedom.to.make.life.choices",
"Generosity",
"Perceptions.of.corruption"
)
data_fitur <- data_whr %>%
select(all_of(fitur_klaster))
rownames(data_fitur) <- data_whr$Country.name
#EDA ## Statistik Deskriptif
ringkasan_stat <- data_whr %>%
select(Ladder.score, all_of(fitur_klaster)) %>%
pivot_longer(everything(), names_to = "Variabel", values_to = "Nilai") %>%
group_by(Variabel) %>%
summarise(
Min = round(min(Nilai), 3),
Q1 = round(quantile(Nilai, 0.25), 3),
Median = round(median(Nilai), 3),
Mean = round(mean(Nilai), 3),
Q3 = round(quantile(Nilai, 0.75), 3),
Max = round(max(Nilai), 3),
SD = round(sd(Nilai), 3),
.groups = "drop"
)
kable(ringkasan_stat, caption = "Statistik Deskriptif Variabel Utama Kebahagiaan Global 2021")
| Variabel | Min | Q1 | Median | Mean | Q3 | Max | SD |
|---|---|---|---|---|---|---|---|
| Freedom.to.make.life.choices | 0.382 | 0.718 | 0.804 | 0.792 | 0.877 | 0.970 | 0.113 |
| Generosity | -0.288 | -0.126 | -0.036 | -0.015 | 0.079 | 0.542 | 0.151 |
| Healthy.life.expectancy | 48.478 | 59.802 | 66.603 | 64.993 | 69.600 | 76.953 | 6.762 |
| Ladder.score | 2.523 | 4.852 | 5.534 | 5.533 | 6.255 | 7.842 | 1.074 |
| Logged.GDP.per.capita | 6.635 | 8.541 | 9.569 | 9.432 | 10.421 | 11.647 | 1.159 |
| Perceptions.of.corruption | 0.082 | 0.667 | 0.781 | 0.727 | 0.845 | 0.939 | 0.179 |
| Social.support | 0.463 | 0.750 | 0.832 | 0.815 | 0.905 | 0.983 | 0.115 |
data_whr %>%
select(
`Ladder Score` = Ladder.score,
`Logged GDP per Capita` = Logged.GDP.per.capita,
`Social Support` = Social.support,
`Healthy Life Expectancy` = Healthy.life.expectancy,
`Freedom of Choice` = Freedom.to.make.life.choices,
`Generosity` = Generosity,
`Perceptions of Corruption` = Perceptions.of.corruption
) %>%
pivot_longer(everything(), names_to = "Variabel", values_to = "Nilai") %>%
ggplot(aes(x = Nilai)) +
geom_histogram(bins = 20, fill = "coral3", color = "white", alpha = 0.85) +
facet_wrap(~ Variabel, scales = "free", ncol = 3) +
theme_minimal(base_size = 9) +
theme(
plot.title = element_text(size = 11, face = "bold", hjust = 0.5),
strip.text = element_text(size = 8.5, face = "bold")
) +
labs(
title = "Distribusi Histogram Skor Kebahagiaan\ndan Faktor Penjelasnya",
x = "Nilai",
y = "Frekuensi (Jumlah Negara)"
)
data_korelasi <- data_whr %>%
select(
Ladder.score,
all_of(fitur_klaster)
)
mat_kor <- cor(data_korelasi)
df_kor <- as.data.frame(as.table(mat_kor))
colnames(df_kor) <- c("Var1", "Var2", "Korelasi")
ggplot(df_kor, aes(x = Var1, y = Var2, fill = Korelasi)) +
geom_tile(color = "white") +
geom_text(aes(label = sprintf("%.2f", Korelasi)), size = 3.2) +
scale_fill_gradient2(
low = "aquamarine3", mid = "white", high = "pink",
midpoint = 0, limit = c(-1, 1)
) +
theme_minimal(base_size = 10) +
theme(
axis.text.x = element_text(angle = 35, hjust = 1),
axis.title = element_blank()
) +
labs(title = "Matriks Korelasi Variabel Kebahagiaan Global 2021")
data_scaled <- scale(data_fitur)
set.seed(42)
wss <- sapply(1:10, function(k) {
kmeans(data_scaled, centers = k, nstart = 25)$tot.withinss
})
df_elbow <- data.frame(k = 1:10, WCSS = wss)
ggplot(df_elbow, aes(x = k, y = WCSS)) +
geom_line(color = "pink", linewidth = 1) +
geom_point(color = "pink", size = 3) +
geom_vline(xintercept = 3, linetype = 2, color = "red") +
scale_x_continuous(breaks = 1:10) +
theme_minimal() +
labs(
title = "Metode Elbow untuk Menentukan Jumlah Klaster Optimal",
subtitle = "Garis putus-putus menunjukkan titik siku pada k = 3",
x = "Jumlah Klaster (k)",
y = "Total Within-Cluster Sum of Squares (WCSS)"
)
### Metode Silhouette
set.seed(42)
dist_mat <- dist(data_scaled)
sil_avg <- sapply(2:10, function(k) {
km <- kmeans(data_scaled, centers = k, nstart = 25)
ss <- silhouette(km$cluster, dist_mat)
mean(ss[, 3])
})
df_sil <- data.frame(k = 2:10, Silhouette = sil_avg)
ggplot(df_sil, aes(x = k, y = Silhouette)) +
geom_line(color = "coral", linewidth = 1) +
geom_point(color = "coral", size = 3) +
scale_x_continuous(breaks = 2:10) +
theme_minimal() +
labs(
title = "Evaluasi Average Silhouette Width untuk Berbagai Nilai k",
x = "Jumlah Klaster (k)",
y = "Average Silhouette Width"
)
#Pemodelan K-Means Clustering (k=3)
set.seed(42)
kmeans_model <- kmeans(data_scaled, centers = 3, nstart = 25)
# Menambahkan label klaster ke dataset asli
data_clustered <- data_whr %>%
mutate(Cluster = factor(kmeans_model$cluster))
# Menampilkan jumlah negara pada setiap klaster
kable(
as.data.frame(table(Cluster = data_clustered$Cluster)),
col.names = c("Klaster", "Jumlah Negara"),
caption = "Distribusi Jumlah Anggota per Klaster"
)
| Klaster | Jumlah Negara |
|---|---|
| 1 | 83 |
| 2 | 44 |
| 3 | 22 |
pca_res <- prcomp(data_scaled)
var_exp <- round(100 * summary(pca_res)$importance[2, 1:2], 1)
df_pca <- data.frame(
PC1 = pca_res$x[, 1],
PC2 = pca_res$x[, 2],
Cluster = data_clustered$Cluster
)
ggplot(df_pca, aes(x = PC1, y = PC2, color = Cluster, fill = Cluster)) +
geom_point(size = 2.8, alpha = 0.85) +
stat_ellipse(geom = "polygon", alpha = 0.15, level = 0.90) +
scale_color_brewer(palette = "Dark2") +
scale_fill_brewer(palette = "Dark2") +
theme_minimal() +
labs(
title = "Visualisasi Klaster K-Means (k = 3) Menggunakan Reduksi Dimensi PCA",
subtitle = "Pengelompokan 149 Negara Berdasarkan 6 Faktor Kebahagiaan",
x = paste0("PC1 (", var_exp[1], "%)"),
y = paste0("PC2 (", var_exp[2], "%)")
)
ggplot(data_clustered, aes(x = Logged.GDP.per.capita, y = Social.support, color = Cluster)) +
geom_point(size = 3, alpha = 0.85) +
scale_color_brewer(palette = "Dark2") +
theme_minimal() +
labs(
title = "Sebaran Klaster Negara: Logged GDP per Capita vs Social Support",
x = "Logged GDP per capita",
y = "Social support",
color = "Klaster"
)
## Evaluasi Kualitas Klaster dengan Silhouette Plot (k=3)
sil <- silhouette(kmeans_model$cluster, dist(data_scaled))
df_sil_k3 <- data.frame(
cluster = factor(sil[, 1]),
sil_width = sil[, 3]
) %>%
arrange(cluster, sil_width) %>%
mutate(order = row_number())
ggplot(df_sil_k3, aes(x = order, y = sil_width, fill = cluster)) +
geom_col(width = 1) +
geom_hline(yintercept = mean(df_sil_k3$sil_width), linetype = "dashed", color = "red") +
scale_fill_brewer(palette = "Dark2") +
theme_minimal() +
theme(axis.text.x = element_blank(), axis.ticks.x = element_blank()) +
labs(
title = paste0("Silhouette Plot K-Means (k = 3), Rata-rata Silhouette = ", round(mean(df_sil_k3$sil_width), 3)),
x = "Observasi (Negara)",
y = "Silhouette Width",
fill = "Klaster"
)
# Profil dan Interpretasi Tiap Klaster ## Ringkasan Karakteristik Tiap
Klaster
profil_klaster <- data_clustered %>%
group_by(Cluster) %>%
summarise(
N = n(),
Ladder_Score = round(mean(Ladder.score), 3),
GDP = round(mean(Logged.GDP.per.capita), 3),
Social_Support = round(mean(Social.support), 3),
Life_Exp = round(mean(Healthy.life.expectancy), 3),
Freedom = round(mean(Freedom.to.make.life.choices), 3),
Generosity = round(mean(Generosity), 3),
Corruption = round(mean(Perceptions.of.corruption), 3),
.groups = "drop"
) %>%
arrange(desc(Ladder_Score))
kable(profil_klaster, caption = "Profil Rata-Rata Karakteristik Setiap Klaster (Diurutkan dari Skor Kebahagiaan Tertinggi)")
| Cluster | N | Ladder_Score | GDP | Social_Support | Life_Exp | Freedom | Generosity | Corruption |
|---|---|---|---|---|---|---|---|---|
| 3 | 22 | 7.015 | 10.842 | 0.929 | 72.557 | 0.908 | 0.068 | 0.398 |
| 1 | 83 | 5.711 | 9.795 | 0.857 | 67.327 | 0.799 | -0.079 | 0.798 |
| 2 | 44 | 4.455 | 8.042 | 0.678 | 56.808 | 0.720 | 0.063 | 0.760 |
profil_z <- as.data.frame(data_scaled) %>%
mutate(Cluster = data_clustered$Cluster) %>%
group_by(Cluster) %>%
summarise(across(everything(), mean), .groups = "drop") %>%
pivot_longer(-Cluster, names_to = "Faktor", values_to = "Rata2_Z_Score")
ggplot(profil_z, aes(x = Faktor, y = Rata2_Z_Score, group = Cluster, color = Cluster)) +
geom_line(size = 1.1) +
geom_point(size = 3) +
geom_hline(yintercept = 0, linetype = "dashed", color = "skyblue") +
scale_color_brewer(palette = "Dark2") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 25, hjust = 1)) +
labs(
title = "Perbandingan Profil Faktor Antar Klaster (Nilai Terstandardisasi / Z-Score)",
x = "Faktor Penentu Kebahagiaan",
y = "Rata-rata Z-Score",
color = "Klaster"
)
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## Daftar Contoh Negara dan Komposisi Wilayah per Klaster
# Contoh 5 negara dengan Ladder Score tertinggi di masing-masing klaster
contoh_negara <- data_clustered %>%
group_by(Cluster) %>%
arrange(desc(Ladder.score)) %>%
slice_head(n = 5) %>%
summarise(
Contoh_5_Negara = paste(Country.name, collapse = ", "),
.groups = "drop"
)
kable(contoh_negara, caption = "Contoh 5 Negara dengan Skor Kebahagiaan Tertinggi pada Tiap Klaster")
| Cluster | Contoh_5_Negara |
|---|---|
| 1 | Israel, Costa Rica, Czech Republic, United States, Belgium |
| 2 | Indonesia, Congo (Brazzaville), Ivory Coast, Nepal, Cameroon |
| 3 | Finland, Denmark, Switzerland, Iceland, Netherlands |
# Distribusi wilayah (Regional indicator) per klaster
tabel_wilayah <- as.data.frame.matrix(table(data_clustered$Regional.indicator, data_clustered$Cluster))
kable(tabel_wilayah, caption = "Distribusi Jumlah Negara Berdasarkan Wilayah dan Klaster")
| 1 | 2 | 3 | |
|---|---|---|---|
| Central and Eastern Europe | 16 | 0 | 1 |
| Commonwealth of Independent States | 11 | 0 | 1 |
| East Asia | 5 | 0 | 1 |
| Latin America and Caribbean | 19 | 1 | 0 |
| Middle East and North Africa | 12 | 4 | 1 |
| North America and ANZ | 1 | 0 | 3 |
| South Asia | 2 | 5 | 0 |
| Southeast Asia | 5 | 3 | 1 |
| Sub-Saharan Africa | 5 | 31 | 0 |
| Western Europe | 7 | 0 | 14 |