Import Library

library(rworldmap)
library(RColorBrewer)
library(tidyverse)
library(factoextra)
library(ggradar)
library(scales)
library(kableExtra)

Dataset

dataset <- read.csv("Country-data.csv")
rmarkdown::paged_table(dataset)

Dataset ini berisi data mengenai indikator indikator yang menggambarkan kesejahteraan dari suatu negara, seperti inflasi, kesehatan angka harapan hidup dan lain lain.
Tujuan dari RmD kali ini adalah menclusterkan data data tersebut kedalam beberapa kategori dan membuat visualisasi dari persebaran dari tiap kategori tersebut.
Child mort adalah kematian anak dibawah 5 tahun per 1000 kelahiran
Export adalah total ekspor barang dan jasa ke luar negeri selama setahun dalam dollar
Health adalah nilai kesehatan dari tiap negara
Export adalah total impor barang dan jasa dari luar negeri selama setahun dalam dollar
Income adalah pendapatan dari tiap negara selama setahun
Inflation adalah tingkat inflasi tahunan dari tiap negara
Life Expectancy adalah angka harapan hidup atau rata rata umur orang orang di suatu negara ketika dia meninggal
Total Fertility adalah angka kelahiran per 1000 wanita
GDPP adalah pendapatan per kapita, yaitu total pendapatan selama setahun, dibagi dengan jumlah penduduk di negara tersebut

Data Wrangling

rownames(dataset) <- dataset$country
dataset <- dataset %>% 
  select(-country)

data_scale <- scale(dataset)

Clustering

fviz_nbclust(x = data_scale,FUNcluster = kmeans, method = "wss")

RNGkind(sample.kind = "Rounding")

## Warning in RNGkind(sample.kind = "Rounding"): non-uniform 'Rounding' sampler
## used

set.seed(123)

country_scale <- kmeans(data_scale, centers = 3)

fviz_cluster(object = country_scale,data = data_scale)

dataset$group <- country_scale$cluster
dataset$group <- str_replace(dataset$group, "1", "Developing")
dataset$group <- str_replace(dataset$group, "2", "Middle")
dataset$group <- str_replace(dataset$group, "3", "Rich")

Data Analysis

Karakteristik tiap Cluster

dat_radar <- dataset %>% 
             group_by(group) %>% 
             summarise_all("mean") %>% 
             mutate(group = as.character(group)) %>%
             mutate_at(vars(-group),
             funs(rescale))

## Warning: `funs()` was deprecated in dplyr 0.8.0.
## Please use a list of either functions or lambdas: 
## 
##   # Simple named list: 
##   list(mean = mean, median = median)
## 
##   # Auto named with `tibble::lst()`: 
##   tibble::lst(mean, median)
## 
##   # Using lambdas
##   list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))

ggradar(dat_radar, 
        grid.label.size = 3,
        axis.label.size = 3, 
        group.point.size = 4,
        group.line.width = 1,
        legend.text.size= 10)

Create Score

ranking <- dataset
ranking$child_mort <- ranking$child_mort*-1
ranking$inflation <- ranking$inflation*-1
ranking$total_fer <- ranking$total_fer*-1
ranking$netexport <- ranking$exports - ranking$imports
ranking <- ranking %>%
  mutate(score = child_mort + health + income + inflation + life_expec + total_fer + gdpp + netexport)

Ranking

ranking %>% 
  select(score) %>% 
  arrange(desc(score)) %>% 
  head() %>% 
  kbl() %>% 
  kable_paper("hover", full_width = F)

	score
Luxembourg	196814.0
Qatar	195401.8
Norway	150190.6
Switzerland	130198.1
Singapore	118808.8
Brunei	115990.3

ranking %>% 
  select(score) %>% 
  arrange(score) %>% 
  head() %>% 
  kbl() %>% 
  kable_paper("hover", full_width = F)

	score
Congo, Dem. Rep.	856.57
Burundi	921.86
Liberia	926.31
Niger	1066.02
Central African Republic	1214.56
Mozambique	1267.81

Grouping

Developing Country

Developing_Country <- dataset %>% 
  filter(group == "Developing") %>% 
  select(group)
Developing_Country %>% 
  kbl() %>%
  kable_material_dark()

	group
Afghanistan	Developing
Angola	Developing
Benin	Developing
Botswana	Developing
Burkina Faso	Developing
Burundi	Developing
Cameroon	Developing
Central African Republic	Developing
Chad	Developing
Comoros	Developing
Congo, Dem. Rep.	Developing
Congo, Rep.	Developing
Cote d’Ivoire	Developing
Equatorial Guinea	Developing
Eritrea	Developing
Gabon	Developing
Gambia	Developing
Ghana	Developing
Guinea	Developing
Guinea-Bissau	Developing
Haiti	Developing
Iraq	Developing
Kenya	Developing
Kiribati	Developing
Lao	Developing
Lesotho	Developing
Liberia	Developing
Madagascar	Developing
Malawi	Developing
Mali	Developing
Mauritania	Developing
Mozambique	Developing
Namibia	Developing
Niger	Developing
Nigeria	Developing
Pakistan	Developing
Rwanda	Developing
Senegal	Developing
Sierra Leone	Developing
South Africa	Developing
Sudan	Developing
Tanzania	Developing
Timor-Leste	Developing
Togo	Developing
Uganda	Developing
Yemen	Developing
Zambia	Developing

Middle Country

Middle_Country <- dataset %>% 
  filter(group == "Middle") %>% 
  select(group)
Middle_Country %>% 
  kbl() %>%
  kable_material_dark()

	group
Albania	Middle
Algeria	Middle
Antigua and Barbuda	Middle
Argentina	Middle
Armenia	Middle
Azerbaijan	Middle
Bahamas	Middle
Bangladesh	Middle
Barbados	Middle
Belarus	Middle
Belize	Middle
Bhutan	Middle
Bolivia	Middle
Bosnia and Herzegovina	Middle
Brazil	Middle
Bulgaria	Middle
Cambodia	Middle
Cape Verde	Middle
Chile	Middle
China	Middle
Colombia	Middle
Costa Rica	Middle
Croatia	Middle
Dominican Republic	Middle
Ecuador	Middle
Egypt	Middle
El Salvador	Middle
Estonia	Middle
Fiji	Middle
Georgia	Middle
Grenada	Middle
Guatemala	Middle
Guyana	Middle
Hungary	Middle
India	Middle
Indonesia	Middle
Iran	Middle
Jamaica	Middle
Jordan	Middle
Kazakhstan	Middle
Kyrgyz Republic	Middle
Latvia	Middle
Lebanon	Middle
Libya	Middle
Lithuania	Middle
Macedonia, FYR	Middle
Malaysia	Middle
Maldives	Middle
Mauritius	Middle
Micronesia, Fed. Sts.	Middle
Moldova	Middle
Mongolia	Middle
Montenegro	Middle
Morocco	Middle
Myanmar	Middle
Nepal	Middle
Oman	Middle
Panama	Middle
Paraguay	Middle
Peru	Middle
Philippines	Middle
Poland	Middle
Romania	Middle
Russia	Middle
Samoa	Middle
Saudi Arabia	Middle
Serbia	Middle
Seychelles	Middle
Solomon Islands	Middle
Sri Lanka	Middle
St. Vincent and the Grenadines	Middle
Suriname	Middle
Tajikistan	Middle
Thailand	Middle
Tonga	Middle
Tunisia	Middle
Turkey	Middle
Turkmenistan	Middle
Ukraine	Middle
Uruguay	Middle
Uzbekistan	Middle
Vanuatu	Middle
Venezuela	Middle
Vietnam	Middle

Rich Country

Rich_Country <- dataset %>% 
  filter(group == "Rich") %>% 
  select(group)
Rich_Country %>% 
  kbl() %>%
  kable_material_dark()

	group
Australia	Rich
Austria	Rich
Bahrain	Rich
Belgium	Rich
Brunei	Rich
Canada	Rich
Cyprus	Rich
Czech Republic	Rich
Denmark	Rich
Finland	Rich
France	Rich
Germany	Rich
Greece	Rich
Iceland	Rich
Ireland	Rich
Israel	Rich
Italy	Rich
Japan	Rich
Kuwait	Rich
Luxembourg	Rich
Malta	Rich
Netherlands	Rich
New Zealand	Rich
Norway	Rich
Portugal	Rich
Qatar	Rich
Singapore	Rich
Slovak Republic	Rich
Slovenia	Rich
South Korea	Rich
Spain	Rich
Sweden	Rich
Switzerland	Rich
United Arab Emirates	Rich
United Kingdom	Rich
United States	Rich

Map Data

data_final <- cbind(country = rownames(dataset), status = dataset$group)
data_final <- as.data.frame(data_final)
data_final$status <- as.factor(data_final$status)

worldmap <- joinCountryData2Map(data_final, joinCode = "ADMIN", nameJoinColumn = "country")

## 166 codes from your data successfully matched countries in the map
## 1 codes from your data failed to match with a country code in the map
## 77 codes from the map weren't represented in your data

colourPalette <- brewer.pal(8,'PiYG')
mapCountryData(worldmap, nameColumnToPlot="status", colourPalette = colourPalette)

## using catMethod='categorical' for non numeric data in mapCountryData

## Warning in rwmGetColours(colourPalette, numColours): 8 colours specified and 3
## required, using interpolation to calculate colours

Conclusion

Negara Negara Maju masih didominasi oleh negara negara di eropa dan amerika bagian utara, serta negara Australia dan selandia baru. Negara Negara di Kawasan asia masih belum terlalu banyak yang berpredikat negara maju, namun sudah sedikit juga negara di asia yang masih berpredikat negara berkembang (negara miskin). dan yang perlu menjadi concern disini adalah masih sangat banyak (lebih dari 60%) negara di kawasan afrika yang berpredikat negara berkembang, sehingga saya rasa perlu adanya big program untuk meningkatkan kesejahteraan di afrika agar misi SDG 30 dari PBB bisa tercapai.

Clustering Country Based On Social and Economy Indicator