Pengaturan global laporan & ukuran grafik

knitr::opts_chunk$set(
  echo = TRUE,
  warning = FALSE,
  message = FALSE,
  fig.align = "center",
  fig.width = 7,
  fig.height = 4.5
)

Load Library

library(tidyverse)   
library(cluster)     
library(corrplot)    
library(knitr) 

Import Dataset

data_whr <- read.csv("world-happiness-report-2021.csv", fileEncoding = "UTF-8-BOM")

dim(data_whr)
## [1] 149  20
kable(head(data_whr[, 1:8]), digits = 3)
Country.name Regional.indicator Ladder.score Standard.error.of.ladder.score upperwhisker lowerwhisker Logged.GDP.per.capita Social.support
Finland Western Europe 7.842 0.032 7.904 7.780 10.775 0.954
Denmark Western Europe 7.620 0.035 7.687 7.552 10.933 0.954
Switzerland Western Europe 7.571 0.036 7.643 7.500 11.117 0.942
Iceland Western Europe 7.554 0.059 7.670 7.438 10.878 0.983
Netherlands Western Europe 7.464 0.027 7.518 7.410 10.932 0.942
Norway Western Europe 7.392 0.035 7.462 7.323 11.053 0.954

Tahap 3: Preprocessing Data

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 ...
colSums(is.na(data_whr))
##                               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
sum(duplicated(data_whr))
## [1] 0
fitur_cluster <- c(
  "Logged.GDP.per.capita",
  "Social.support",
  "Healthy.life.expectancy",
  "Freedom.to.make.life.choices",
  "Generosity",
  "Perceptions.of.corruption"
)

data_cluster <- data_whr %>%
  select(all_of(fitur_cluster))

rownames(data_cluster) <- data_whr$Country.name

Tahap 4: Exploratory Data Analysis (EDA)

Statistik Deskriptif

ringkasan <- data_whr %>%
  select(Ladder.score, all_of(fitur_cluster)) %>%
  summarise(across(everything(), list(
    Mean = mean,
    SD = sd,
    Min = min,
    Median = median,
    Max = max
  ))) %>%
  pivot_longer(everything(), names_to = c("Variabel", ".value"), names_sep = "_")

kable(ringkasan, digits = 3, caption = "Statistik Deskriptif Variabel Utama")
Statistik Deskriptif Variabel Utama
Variabel Mean SD Min Median Max
Ladder.score 5.533 1.074 2.523 5.534 7.842
Logged.GDP.per.capita 9.432 1.159 6.635 9.569 11.647
Social.support 0.815 0.115 0.463 0.832 0.983
Healthy.life.expectancy 64.993 6.762 48.478 66.603 76.953
Freedom.to.make.life.choices 0.792 0.113 0.382 0.804 0.970
Generosity -0.015 0.151 -0.288 -0.036 0.542
Perceptions.of.corruption 0.727 0.179 0.082 0.781 0.939

Distribusi Data (Histogram)

Ladder Score

ggplot(data_whr, aes(x = Ladder.score)) +
  geom_histogram(bins = 20, fill = "steelblue", color = "white") +
  theme_minimal() +
  labs(title = "Histogram Ladder Score", x = "Ladder Score", y = "Frekuensi")

### Logged GDP per Capita

ggplot(data_whr, aes(x = Logged.GDP.per.capita)) +
  geom_histogram(bins = 20, fill = "steelblue", color = "white") +
  theme_minimal() +
  labs(title = "Histogram Logged GDP per Capita", x = "Logged GDP per Capita", y = "Frekuensi")

### Social Support

ggplot(data_whr, aes(x = Social.support)) +
  geom_histogram(bins = 20, fill = "steelblue", color = "white") +
  theme_minimal() +
  labs(title = "Histogram Social Support", x = "Social Support", y = "Frekuensi")

### Healthy Life Expectancy

ggplot(data_whr, aes(x = Healthy.life.expectancy)) +
  geom_histogram(bins = 20, fill = "steelblue", color = "white") +
  theme_minimal() +
  labs(title = "Histogram Healthy Life Expectancy", x = "Healthy Life Expectancy", y = "Frekuensi")

Freedom to Make Life Choices

ggplot(data_whr, aes(x = Freedom.to.make.life.choices)) +
  geom_histogram(bins = 20, fill = "steelblue", color = "white") +
  theme_minimal() +
  labs(title = "Histogram Freedom to Make Life Choices", x = "Freedom to Make Life Choices", y = "Frekuensi")

Generosity

ggplot(data_whr, aes(x = Generosity)) +
  geom_histogram(bins = 20, fill = "steelblue", color = "white") +
  theme_minimal() +
  labs(title = "Histogram Generosity", x = "Generosity", y = "Frekuensi")

Perceptions of Corruption

ggplot(data_whr, aes(x = Perceptions.of.corruption)) +
  geom_histogram(bins = 20, fill = "steelblue", color = "white") +
  theme_minimal() +
  labs(title = "Histogram Perceptions of Corruption", x = "Perceptions of Corruption", y = "Frekuensi")

Matriks Korelasi

data_corr <- data_whr %>%
  select(Ladder.score, all_of(fitur_cluster))

matriks_korelasi <- cor(data_corr)

corrplot(
  matriks_korelasi,
  method = "color",
  type = "upper",
  addCoef.col = "black",
  tl.col = "black",
  tl.srt = 45,
  number.cex = 0.75,
  title = "Matriks Korelasi Antar Variabel",
  mar = c(0, 0, 2, 0)
)

# Tahap 5: Standardisasi Data

data_scaled <- scale(data_cluster)

kable(head(round(data_scaled, 3)), caption = "Cuplikan Data Setelah Standardisasi")
Cuplikan Data Setelah Standardisasi
Logged.GDP.per.capita Social.support Healthy.life.expectancy Freedom.to.make.life.choices Generosity Perceptions.of.corruption
Finland 1.159 1.212 1.036 1.389 -0.550 -3.021
Denmark 1.295 1.212 1.140 1.362 0.300 -3.060
Switzerland 1.454 1.108 1.391 1.124 0.266 -2.430
Iceland 1.248 1.465 1.184 1.442 1.162 -0.304
Netherlands 1.294 1.108 1.095 1.071 1.262 -2.173
Norway 1.399 1.212 1.229 1.486 0.718 -2.552

Tahap 6: Penentuan Jumlah Klaster Optimal

Metode Elbow

set.seed(123)
wss <- sapply(1:10, function(k) {
  kmeans(data_scaled, centers = k, nstart = 25)$tot.withinss
})

df_elbow <- data.frame(k = 1:10, wss = wss)

ggplot(df_elbow, aes(x = k, y = wss)) +
  geom_line(color = "steelblue") +
  geom_point(color = "steelblue", size = 3) +
  geom_vline(xintercept = 3, linetype = "dashed", color = "red") +
  scale_x_continuous(breaks = 1:10) +
  theme_minimal() +
  labs(
    title = "Penentuan Jumlah Klaster Optimal dengan Metode Elbow",
    x = "Jumlah Klaster (k)",
    y = "Total Within Sum of Squares (Inertia)"
  )

## Metode Silhouette

set.seed(123)
dist_matrix <- dist(data_scaled)
sil_avg <- sapply(2:10, function(k) {
  km <- kmeans(data_scaled, centers = k, nstart = 25)
  ss <- silhouette(km$cluster, dist_matrix)
  mean(ss[, 3])
})

df_sil <- data.frame(k = 2:10, silhouette = sil_avg)

ggplot(df_sil, aes(x = k, y = silhouette)) +
  geom_line(color = "steelblue") +
  geom_point(color = "steelblue", size = 3) +
  scale_x_continuous(breaks = 2:10) +
  theme_minimal() +
  labs(
    title = "Penentuan Jumlah Klaster Optimal dengan Metode Silhouette",
    x = "Jumlah Klaster (k)",
    y = "Rata-rata Lebar Silhouette"
  )

Tahap 7: Pemodelan K-Means Clustering

set.seed(123)
kmeans_model <- kmeans(data_scaled, centers = 3, nstart = 25)

kmeans_model$size
## [1] 22 83 44
data_hasil <- data_whr %>%
  mutate(Cluster = as.factor(kmeans_model$cluster))

Tahap 8: Evaluasi & Profiling Karakteristik Klaster

Evaluasi Silhouette

sil <- silhouette(kmeans_model$cluster, dist(data_scaled))
rata_sil <- round(mean(sil[, 3]), 3)

df_sil_plot <- data.frame(
  cluster = factor(sil[, 1]),
  sil_width = sil[, 3]
) %>%
  arrange(cluster, desc(sil_width)) %>%
  mutate(order = row_number())

ggplot(df_sil_plot, aes(x = order, y = sil_width, fill = cluster)) +
  geom_col(width = 1) +
  geom_hline(yintercept = rata_sil, linetype = "dashed", color = "red") +
  theme_minimal() +
  labs(
    title = paste("Plot Silhouette K-Means (Rata-rata =", rata_sil, ")"),
    x = "Observasi (Negara)",
    y = "Lebar Silhouette",
    fill = "Klaster"
  )

Profil Rata-rata Tiap Klaster

profil_klaster <- data_hasil %>%
  group_by(Cluster) %>%
  summarise(
    Jumlah_Negara = n(),
    Mean_Ladder_Score = mean(Ladder.score),
    Mean_GDP = mean(Logged.GDP.per.capita),
    Mean_Social_Support = mean(Social.support),
    Mean_Life_Expectancy = mean(Healthy.life.expectancy),
    Mean_Freedom = mean(Freedom.to.make.life.choices),
    Mean_Generosity = mean(Generosity),
    Mean_Corruption = mean(Perceptions.of.corruption)
  ) %>%
  arrange(desc(Mean_Ladder_Score))

kable(t(profil_klaster), digits = 3, caption = "Profil Rata-rata Karakteristik Tiap Klaster")
Profil Rata-rata Karakteristik Tiap Klaster
Cluster 1 2 3
Jumlah_Negara 22 83 44
Mean_Ladder_Score 7.015455 5.711000 4.455455
Mean_GDP 10.841500 9.795410 8.042432
Mean_Social_Support 0.9286364 0.8570723 0.6779545
Mean_Life_Expectancy 72.55732 67.32652 56.80830
Mean_Freedom 0.9080455 0.7987952 0.7197955
Mean_Generosity 0.06800000 -0.07861446 0.06304545
Mean_Corruption 0.3983182 0.7975904 0.7597045

Contoh Negara per Klaster & Posisi Indonesia

contoh_negara <- data_hasil %>%
  group_by(Cluster) %>%
  slice_max(order_by = Ladder.score, n = 5) %>%
  summarise(Contoh_Negara = paste(Country.name, collapse = ", "))

kable(contoh_negara, caption = "5 Negara Teratas di Masing-masing Klaster")
5 Negara Teratas di Masing-masing Klaster
Cluster Contoh_Negara
1 Finland, Denmark, Switzerland, Iceland, Netherlands
2 Israel, Costa Rica, Czech Republic, United States, Belgium
3 Indonesia, Congo (Brazzaville), Ivory Coast, Nepal, Cameroon
indonesia <- data_hasil %>%
  filter(Country.name == "Indonesia") %>%
  select(Country.name, Regional.indicator, Ladder.score, Cluster)

kable(indonesia, digits = 3, caption = "Posisi Klaster Indonesia")
Posisi Klaster Indonesia
Country.name Regional.indicator Ladder.score Cluster
Indonesia Southeast Asia 5.345 3

Tahap 9: Visualisasi Hasil Clustering

Visualisasi Klaster Berbasis PCA

pca_res <- prcomp(data_scaled, scale. = FALSE)
var_exp <- round(100 * (pca_res$sdev^2 / sum(pca_res$sdev^2)), 1)

df_pca <- data.frame(
  PC1 = pca_res$x[, 1],
  PC2 = pca_res$x[, 2],
  Cluster = data_hasil$Cluster
)

hulls <- df_pca %>%
  group_by(Cluster) %>%
  slice(chull(PC1, PC2))

ggplot(df_pca, aes(x = PC1, y = PC2, color = Cluster, fill = Cluster)) +
  geom_polygon(data = hulls, alpha = 0.15) +
  geom_point(size = 2.8, alpha = 0.85) +
  theme_minimal() +
  labs(
    title = "Visualisasi Klaster Negara (PCA Projection)",
    x = paste0("PC1 (", var_exp[1], "%)"),
    y = paste0("PC2 (", var_exp[2], "%)"),
    color = "Klaster",
    fill = "Klaster"
  )

Scatter Plot GDP vs Social Support

ggplot(data_hasil, aes(x = Logged.GDP.per.capita, y = Social.support, color = Cluster)) +
  geom_point(size = 2.8, alpha = 0.85) +
  theme_minimal() +
  labs(
    title = "Hasil K-Means Clustering: Logged GDP per Capita vs Social Support",
    x = "Logged GDP per Capita",
    y = "Social Support",
    color = "Klaster"
  )