Tugas Kelompok
2025-03-02
Install dan Load Library
Berikut ini adalah library yang digunakan untuk mengolah data :
library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.4.3library(readxl)
library(ggthemes)
library(gridExtra)
library(scales)
library(dplyr)## Warning: package 'dplyr' was built under R version 4.4.3##
## Attaching package: 'dplyr'## The following object is masked from 'package:gridExtra':
##
## combine## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(tidyr)## Warning: package 'tidyr' was built under R version 4.4.3library(readr)## Warning: package 'readr' was built under R version 4.4.3##
## Attaching package: 'readr'## The following object is masked from 'package:scales':
##
## col_factoroptions(scipen = 999)
custom_theme <- theme(
plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
axis.title.x = element_text(size = 14, face = "bold"),
axis.title.y = element_text(size = 14, face = "bold"),
axis.text.x = element_text(size = 12, angle = 45, hjust = 1),
axis.text.y = element_text(size = 12),
panel.background = element_rect(fill = "white"),
panel.grid.major = element_line(color = "gray80"),
panel.grid.minor = element_blank(),
legend.position = "bottom",
legend.title = element_text(size = 12, face = "bold"),
legend.text = element_text(size = 10)
)
theme_void() +
theme(legend.title = element_blank())## List of 136
## $ line : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ rect : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ text :List of 11
## ..$ family : chr ""
## ..$ face : chr "plain"
## ..$ colour : chr "black"
## ..$ size : num 11
## ..$ hjust : num 0.5
## ..$ vjust : num 0.5
## ..$ angle : num 0
## ..$ lineheight : num 0.9
## ..$ margin : 'margin' num [1:4] 0points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ title : NULL
## $ aspect.ratio : NULL
## $ axis.title : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ axis.title.x : NULL
## $ axis.title.x.top : NULL
## $ axis.title.x.bottom : NULL
## $ axis.title.y : NULL
## $ axis.title.y.left : NULL
## $ axis.title.y.right : NULL
## $ axis.text : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ axis.text.x : NULL
## $ axis.text.x.top : NULL
## $ axis.text.x.bottom : NULL
## $ axis.text.y : NULL
## $ axis.text.y.left : NULL
## $ axis.text.y.right : NULL
## $ axis.text.theta : NULL
## $ axis.text.r : NULL
## $ axis.ticks : NULL
## $ axis.ticks.x : NULL
## $ axis.ticks.x.top : NULL
## $ axis.ticks.x.bottom : NULL
## $ axis.ticks.y : NULL
## $ axis.ticks.y.left : NULL
## $ axis.ticks.y.right : NULL
## $ axis.ticks.theta : NULL
## $ axis.ticks.r : NULL
## $ axis.minor.ticks.x.top : NULL
## $ axis.minor.ticks.x.bottom : NULL
## $ axis.minor.ticks.y.left : NULL
## $ axis.minor.ticks.y.right : NULL
## $ axis.minor.ticks.theta : NULL
## $ axis.minor.ticks.r : NULL
## $ axis.ticks.length : 'simpleUnit' num 0points
## ..- attr(*, "unit")= int 8
## $ axis.ticks.length.x : NULL
## $ axis.ticks.length.x.top : NULL
## $ axis.ticks.length.x.bottom : NULL
## $ axis.ticks.length.y : NULL
## $ axis.ticks.length.y.left : NULL
## $ axis.ticks.length.y.right : NULL
## $ axis.ticks.length.theta : NULL
## $ axis.ticks.length.r : NULL
## $ axis.minor.ticks.length : 'simpleUnit' num 0points
## ..- attr(*, "unit")= int 8
## $ axis.minor.ticks.length.x : NULL
## $ axis.minor.ticks.length.x.top : NULL
## $ axis.minor.ticks.length.x.bottom: NULL
## $ axis.minor.ticks.length.y : NULL
## $ axis.minor.ticks.length.y.left : NULL
## $ axis.minor.ticks.length.y.right : NULL
## $ axis.minor.ticks.length.theta : NULL
## $ axis.minor.ticks.length.r : NULL
## $ axis.line : NULL
## $ axis.line.x : NULL
## $ axis.line.x.top : NULL
## $ axis.line.x.bottom : NULL
## $ axis.line.y : NULL
## $ axis.line.y.left : NULL
## $ axis.line.y.right : NULL
## $ axis.line.theta : NULL
## $ axis.line.r : NULL
## $ legend.background : NULL
## $ legend.margin : NULL
## $ legend.spacing : NULL
## $ legend.spacing.x : NULL
## $ legend.spacing.y : NULL
## $ legend.key : NULL
## $ legend.key.size : 'simpleUnit' num 1.2lines
## ..- attr(*, "unit")= int 3
## $ legend.key.height : NULL
## $ legend.key.width : NULL
## $ legend.key.spacing : 'simpleUnit' num 5.5points
## ..- attr(*, "unit")= int 8
## $ legend.key.spacing.x : NULL
## $ legend.key.spacing.y : NULL
## $ legend.frame : NULL
## $ legend.ticks : NULL
## $ legend.ticks.length : 'rel' num 0.2
## $ legend.axis.line : NULL
## $ legend.text :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 0.8
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ legend.text.position : NULL
## $ legend.title : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ legend.title.position : NULL
## $ legend.position : chr "right"
## $ legend.position.inside : NULL
## $ legend.direction : NULL
## $ legend.byrow : NULL
## $ legend.justification : NULL
## $ legend.justification.top : NULL
## $ legend.justification.bottom : NULL
## $ legend.justification.left : NULL
## $ legend.justification.right : NULL
## $ legend.justification.inside : NULL
## $ legend.location : NULL
## $ legend.box : NULL
## $ legend.box.just : NULL
## $ legend.box.margin : NULL
## $ legend.box.background : NULL
## $ legend.box.spacing : NULL
## [list output truncated]
## - attr(*, "class")= chr [1:2] "theme" "gg"
## - attr(*, "complete")= logi TRUE
## - attr(*, "validate")= logi TRUEImport Data
Data berikut diinput dari file :
setwd("C:/Users/Acer/Pictures/Probstat/Pertemuan Ketiga (2-3-2025)")data <- read_excel("data_tugas.xlsx")
head(data)## # A tibble: 6 × 4
## Negara Hari Total_Kasus Total_Kematian
## <chr> <dttm> <dbl> <dbl>
## 1 Brunei 2025-02-23 00:00:00 350550 182
## 2 Cambodia 2025-02-23 00:00:00 139326 3056
## 3 Indonesia 2025-02-23 00:00:00 6830212 162059
## 4 Laos 2025-02-23 00:00:00 219060 671
## 5 Malaysia 2025-02-23 00:00:00 5329836 37351
## 6 Myanmar 2025-02-23 00:00:00 643241 19494df <- read.csv("Total Kasus & Kematian/vaccinations.csv")
head(df)## country date total_vaccinations people_vaccinated
## 1 Afghanistan 2021-02-22 0 0
## 2 Afghanistan 2021-02-23 NA NA
## 3 Afghanistan 2021-02-24 NA NA
## 4 Afghanistan 2021-02-25 NA NA
## 5 Afghanistan 2021-02-26 NA NA
## 6 Afghanistan 2021-02-27 NA NA
## people_fully_vaccinated total_boosters daily_vaccinations
## 1 NA NA NA
## 2 NA NA NA
## 3 NA NA NA
## 4 NA NA NA
## 5 NA NA NA
## 6 NA NA NA
## daily_vaccinations_smoothed daily_people_vaccinated_smoothed
## 1 NA NA
## 2 1366.667 1366.667
## 3 1366.667 1366.667
## 4 1366.667 1366.667
## 5 1366.667 1366.667
## 6 1366.667 1366.667
## total_vaccinations_per_hundred people_vaccinated_per_hundred
## 1 0 0
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA
## people_fully_vaccinated_per_hundred total_boosters_per_hundred
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA
## daily_people_vaccinated_smoothed_per_hundred
## 1 NA
## 2 0.003367929
## 3 0.003367929
## 4 0.003367929
## 5 0.003367929
## 6 0.003367929
## daily_vaccinations_smoothed_per_million people_unvaccinated share_of_boosters
## 1 NA 39671220 NA
## 2 33.67929 NA NA
## 3 33.67929 NA NA
## 4 33.67929 NA NA
## 5 33.67929 NA NA
## 6 33.67929 NA NA
## total_vaccinations_interpolated people_vaccinated_interpolated
## 1 0.000 0.000
## 2 1366.667 1366.667
## 3 2733.333 2733.333
## 4 4100.000 4100.000
## 5 5466.667 5466.667
## 6 6833.333 6833.333
## people_fully_vaccinated_interpolated total_boosters_interpolated
## 1 55624 0
## 2 55624 0
## 3 55624 0
## 4 55624 0
## 5 55624 0
## 6 55624 0
## total_vaccinations_no_boosters_interpolated
## 1 0.000
## 2 1366.667
## 3 2733.333
## 4 4100.000
## 5 5466.667
## 6 6833.333
## total_vaccinations_no_boosters_per_hundred_interpolated
## 1 NA
## 2 NA
## 3 NA
## 4 NA
## 5 NA
## 6 NA
## rolling_vaccinations_6m rolling_vaccinations_6m_per_hundred
## 1 NA NA
## 2 1366.667 0.003367929
## 3 2733.333 0.006735858
## 4 4100.000 0.010103787
## 5 5466.667 0.013471715
## 6 6833.333 0.016839644
## rolling_vaccinations_9m rolling_vaccinations_9m_per_hundred
## 1 NA NA
## 2 1366.667 0.003367929
## 3 2733.333 0.006735858
## 4 4100.000 0.010103787
## 5 5466.667 0.013471715
## 6 6833.333 0.016839644
## rolling_vaccinations_12m rolling_vaccinations_12m_per_hundred
## 1 NA NA
## 2 1366.667 0.003367929
## 3 2733.333 0.006735858
## 4 4100.000 0.010103787
## 5 5466.667 0.013471715
## 6 6833.333 0.016839644df <- read.csv("Total Kasus & Kematian/varian.csv")
head(df)## Entity Code Day
## 1 Argentina ARG 2020-12-04
## 2 Argentina ARG 2020-12-05
## 3 Argentina ARG 2020-12-06
## 4 Argentina ARG 2020-12-07
## 5 Argentina ARG 2020-12-08
## 6 Argentina ARG 2020-12-09
## COVID.19.doses..cumulative....Manufacturer.Pfizer.BioNTech
## 1 1
## 2 1
## 3 1
## 4 1
## 5 1
## 6 1
## COVID.19.doses..cumulative....Manufacturer.Moderna
## 1 1
## 2 1
## 3 1
## 4 1
## 5 1
## 6 1
## COVID.19.doses..cumulative....Manufacturer.Oxford.AstraZeneca
## 1 1
## 2 1
## 3 1
## 4 1
## 5 1
## 6 1
## COVID.19.doses..cumulative....Manufacturer.Johnson.Johnson
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## COVID.19.doses..cumulative....Manufacturer.Sputnik.V
## 1 20493
## 2 20493
## 3 20493
## 4 20493
## 5 20493
## 6 20493
## COVID.19.doses..cumulative....Manufacturer.Sinovac
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## COVID.19.doses..cumulative....Manufacturer.Sinopharm.Beijing
## 1 1
## 2 1
## 3 1
## 4 1
## 5 1
## 6 1
## COVID.19.doses..cumulative....Manufacturer.CanSino
## 1 1
## 2 1
## 3 1
## 4 1
## 5 1
## 6 1
## COVID.19.doses..cumulative....Manufacturer.Novavax
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## COVID.19.doses..cumulative....Manufacturer.Covaxin
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## COVID.19.doses..cumulative....Manufacturer.Medicago
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## COVID.19.doses..cumulative....Manufacturer.Sanofi.GSK
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## COVID.19.doses..cumulative....Manufacturer.SKYCovione
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## COVID.19.doses..cumulative....Manufacturer.Valneva
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0Datasets diambil dari situs Our World in Data “COVID-19 Pandemic” dengan link berikut : https://ourworldindata.org/coronavirus#all-charts
Visualisasi Data Total Kasus dan Total Kematian COVID-19
1. Bar Chart
Berdasarkan data COVID-19 dengan tujuan untuk menunjukkan Total Kasus dan Total Kematian per Negara. Dilampirkan visualisasi data dalam bentuk Bar Chart:
bar_chart <- ggplot(data, aes(x = reorder(Negara, Total_Kasus), y = Total_Kasus)) +
geom_bar(stat = "identity", fill = "blue") +
labs(title = "Total Kasus per Negara", x = "Negara", y = "Total Kasus") +
custom_theme
print(bar_chart)
bar_chart <- ggplot(data, aes(x = reorder(Negara, Total_Kematian), y = Total_Kematian)) +
geom_bar(stat = "identity", fill = "red") +
labs(title = "Total Kematian per Negara", x = "Negara", y = "Total Kematian") +
custom_theme
print(bar_chart)
Interpretasi : Berdasarkan kedua Bar Chart diatas Negara Vietnam
memiliki Total Kasus tertinggi diikuti oleh Indonesia lalu Malaysia,
sedangkan Total Kematian tertinggi ditempati oleh Indonesia dengan
selisih yang sangat jauh dengan negara Asean lainnya.
2. Histogram
Berdasarkan data COVID-19 dengan tujuan menunjukkan Total Kasus per Negara. Dilampirkan visualisasi data dalam bentuk Histogram :
histogram <- ggplot(data, aes(x = Total_Kasus)) +
geom_histogram(binwidth = 1000000, fill = "blue", color = "black") +
labs(title = "Distribusi Total Kasus", x = "Total Kasus", y = "Frekuensi") +
custom_theme
print(histogram)
Interpretasi : Berdasarkan Histogram diatas mayoritas negara Asean
memiliki distribusi Total Kasus antara 0 hingga 5 juta, dengan beberapa
outlier seperti Vietnam yang memiliki total kasus yang sangat
tinggi.
3. Density Plot
Berdasarkan data COVID-19 dengan tujuan menunjukkan Total Kasus dan Total Kematian per Negara. Dilampirkan visualisasi data dalam bentuk Density Plot :
density_plot <- ggplot(data, aes(x = Total_Kasus)) +
geom_density(fill = "blue", alpha = 0.5) +
labs(title = "Density Plot Total Kasus", x = "Total Kasus", y = "Density") +
custom_theme
print(density_plot)
density_plot <- ggplot(data, aes(x = Total_Kematian)) +
geom_density(fill = "blue", alpha = 0.5) +
labs(title = "Density Plot Total Kematian", x = "Total Kematian", y = "Density") +
custom_theme
print(density_plot)
Interpretasi : Berdasarkan Density Plot dapat disimpulkan dari kurva
yang cenderung miring ke kiri bahwa mayoritas Negara Asean memiliki
nilai Kasus dan Kematian akibat Covid - 19 yang relatif rendah, dengan
beberapa negara memiliki nilai yang sangat tinggi.
4. Box Plot
Berdasarkan data COVID-19 dengan tujuan menunjukkan Total Kasus dan Total Kematian per Negara. Dilampirkan visualisasi data dalam bentuk Box Plot :
boxplot <- ggplot(data, aes(x = "", y = Total_Kasus)) +
geom_boxplot(fill = "blue", alpha = 0.5) +
labs(title = "Boxplot Total Kasus", x = "", y = "Total Kasus") +
custom_theme
print(boxplot)
boxplot <- ggplot(data, aes(x = "", y = Total_Kematian)) +
geom_boxplot(fill = "blue", alpha = 0.5) +
labs(title = "Boxplot Total Kematian", x = "", y = "Total Kematian") +
custom_theme
print(boxplot)
Interpretasi : Berdasarkan Box Plot dapat dikatakan mayoritas negara
Asean memiliki nilai Kasus dan Kematian yang rendah. Terdapat beberapa
outlier, terutama Vietnam dan Indonesia, yang memiliki total nilai jauh
lebih tinggi dari yang lainnya.
Mean (Rata-Rata)
Mean untuk Total Kasus :
mean(data$Total_Kasus)## [1] 3709310Rata-rata total kasus terkena COVID-19 pada negara Asean sekitar 3.5 juta.
Mean untuk Total Kematian :
mean(data$Total_Kematian)## [1] 36965Rata-rata total kematian akibat COVID-19 pada negara Asean sekitar 36 ribu.
Median (Nilai Tengah)
Median atau nilai tengah digunakan untuk menentukan nilai yang terletak di tengah jika data diurutkan. Median untuk Total Kasus :
median(data$Total_Kasus)## [1] 3573269Distribusi total kasus di Asean hampir simetris.
Median untuk Total Kematian :
median(data$Total_Kematian)## [1] 27118.5Distribusi total kematian di Asean condong ke nilai yang rendah.
Modus (Nilai yang sering muncul)
Modus untuk Total Kasus :
modus <- function(x) {
uniqx <- unique(x)
uniqx[which.max(tabulate(match(x, uniqx)))]
}
modus(data$Total_Kasus)## [1] 350550Modus untuk Total Kematian :
modus(data$Total_Kematian)## [1] 182Ukuran Letak Data
(Q0/Min, Q1, Q2/Median, Q3, Q4/Max) Digunakan untuk memberikan gambaran atau rangkuman dari data. Letak Data untuk Total Kasus :
quantile(data$Total_Kasus)## 0% 25% 50% 75% 100%
## 139326.0 423722.8 3573269.0 5199961.5 11624000.0Letak Data untuk Total Kematian :
quantile(data$Total_Kematian)## 0% 25% 50% 75% 100%
## 182.00 2282.00 27118.50 41742.25 162059.00Ukuran Penyebaran Data
- Jangkauan Jangkauan atau range digunakan untuk menentukan selisih nilai terkecil dan nilai terbesar dari data. Range untuk Total Kasus :
diff(range(data$Total_Kasus))## [1] 11484674Range untuk Total Kematian :
diff(range(data$Total_Kematian))## [1] 161877- Ragam Ragam atau variance digunakan untuk menentukan nilai sebaran kuadrat dari data. Ragam untuk Total Kasus :
var(data$Total_Kasus)## [1] 13612182646848Ragam untuk Total Kematian :
var(data$Total_Kematian)## [1] 2436963170- Standar Deviasi Deviasi standar atau standard deviation digunakan untuk menentukan nilai sebaran sesuai satuan data awalnya. Standar Deviasi untuk Total Kasus :
sd(data$Total_Kasus)## [1] 3689469Standar Deviasi untuk Total Kematian :
sd(data$Total_Kematian)## [1] 49365.61Visualisasi Data Status Vaksinasi dan Varian Vaksin
df <- read.csv("Total Kasus & Kematian/vaccinations.csv")# Cek apakah kolom 'people_unvaccinated' ada dalam dataset
if ("people_unvaccinated" %in% colnames(df)) {
# Gantilah NA dengan 0 pada kolom people_unvaccinated
df <- df %>%
mutate(people_unvaccinated = ifelse(is.na(people_unvaccinated), 0, people_unvaccinated))
print("Kolom 'people_unvaccinated' berhasil diproses.")
} else {
print("Kolom 'people_unvaccinated' tidak ditemukan dalam dataset.")
}## [1] "Kolom 'people_unvaccinated' berhasil diproses."# Cek struktur dataset setelah perubahan
str(df)## 'data.frame': 203057 obs. of 29 variables:
## $ country : chr "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
## $ date : chr "2021-02-22" "2021-02-23" "2021-02-24" "2021-02-25" ...
## $ total_vaccinations : num 0 NA NA NA NA NA 8200 NA NA NA ...
## $ people_vaccinated : num 0 NA NA NA NA NA 8200 NA NA NA ...
## $ people_fully_vaccinated : num NA NA NA NA NA NA NA NA NA NA ...
## $ total_boosters : num NA NA NA NA NA NA NA NA NA NA ...
## $ daily_vaccinations : num NA NA NA NA NA NA NA NA NA NA ...
## $ daily_vaccinations_smoothed : num NA 1367 1367 1367 1367 ...
## $ daily_people_vaccinated_smoothed : num NA 1367 1367 1367 1367 ...
## $ total_vaccinations_per_hundred : num 0 NA NA NA NA ...
## $ people_vaccinated_per_hundred : num 0 NA NA NA NA ...
## $ people_fully_vaccinated_per_hundred : num NA NA NA NA NA NA NA NA NA NA ...
## $ total_boosters_per_hundred : num NA NA NA NA NA NA NA NA NA NA ...
## $ daily_people_vaccinated_smoothed_per_hundred : num NA 0.00337 0.00337 0.00337 0.00337 ...
## $ daily_vaccinations_smoothed_per_million : num NA 33.7 33.7 33.7 33.7 ...
## $ people_unvaccinated : num 39671220 0 0 0 0 ...
## $ share_of_boosters : num NA NA NA NA NA NA NA NA NA NA ...
## $ total_vaccinations_interpolated : num 0 1367 2733 4100 5467 ...
## $ people_vaccinated_interpolated : num 0 1367 2733 4100 5467 ...
## $ people_fully_vaccinated_interpolated : num 55624 55624 55624 55624 55624 ...
## $ total_boosters_interpolated : num 0 0 0 0 0 0 0 0 0 0 ...
## $ total_vaccinations_no_boosters_interpolated : num 0 1367 2733 4100 5467 ...
## $ total_vaccinations_no_boosters_per_hundred_interpolated: num NA NA NA NA NA NA NA NA NA NA ...
## $ rolling_vaccinations_6m : num NA 1367 2733 4100 5467 ...
## $ rolling_vaccinations_6m_per_hundred : num NA 0.00337 0.00674 0.0101 0.01347 ...
## $ rolling_vaccinations_9m : num NA 1367 2733 4100 5467 ...
## $ rolling_vaccinations_9m_per_hundred : num NA 0.00337 0.00674 0.0101 0.01347 ...
## $ rolling_vaccinations_12m : num NA 1367 2733 4100 5467 ...
## $ rolling_vaccinations_12m_per_hundred : num NA 0.00337 0.00674 0.0101 0.01347 ...# Mengganti semua nilai NA dalam dataset dengan 0
df[is.na(df)] <- 0
# Cek hasil setelah perubahan
str(df)## 'data.frame': 203057 obs. of 29 variables:
## $ country : chr "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
## $ date : chr "2021-02-22" "2021-02-23" "2021-02-24" "2021-02-25" ...
## $ total_vaccinations : num 0 0 0 0 0 0 8200 0 0 0 ...
## $ people_vaccinated : num 0 0 0 0 0 0 8200 0 0 0 ...
## $ people_fully_vaccinated : num 0 0 0 0 0 0 0 0 0 0 ...
## $ total_boosters : num 0 0 0 0 0 0 0 0 0 0 ...
## $ daily_vaccinations : num 0 0 0 0 0 0 0 0 0 0 ...
## $ daily_vaccinations_smoothed : num 0 1367 1367 1367 1367 ...
## $ daily_people_vaccinated_smoothed : num 0 1367 1367 1367 1367 ...
## $ total_vaccinations_per_hundred : num 0 0 0 0 0 ...
## $ people_vaccinated_per_hundred : num 0 0 0 0 0 ...
## $ people_fully_vaccinated_per_hundred : num 0 0 0 0 0 0 0 0 0 0 ...
## $ total_boosters_per_hundred : num 0 0 0 0 0 0 0 0 0 0 ...
## $ daily_people_vaccinated_smoothed_per_hundred : num 0 0.00337 0.00337 0.00337 0.00337 ...
## $ daily_vaccinations_smoothed_per_million : num 0 33.7 33.7 33.7 33.7 ...
## $ people_unvaccinated : num 39671220 0 0 0 0 ...
## $ share_of_boosters : num 0 0 0 0 0 0 0 0 0 0 ...
## $ total_vaccinations_interpolated : num 0 1367 2733 4100 5467 ...
## $ people_vaccinated_interpolated : num 0 1367 2733 4100 5467 ...
## $ people_fully_vaccinated_interpolated : num 55624 55624 55624 55624 55624 ...
## $ total_boosters_interpolated : num 0 0 0 0 0 0 0 0 0 0 ...
## $ total_vaccinations_no_boosters_interpolated : num 0 1367 2733 4100 5467 ...
## $ total_vaccinations_no_boosters_per_hundred_interpolated: num 0 0 0 0 0 0 0 0 0 0 ...
## $ rolling_vaccinations_6m : num 0 1367 2733 4100 5467 ...
## $ rolling_vaccinations_6m_per_hundred : num 0 0.00337 0.00674 0.0101 0.01347 ...
## $ rolling_vaccinations_9m : num 0 1367 2733 4100 5467 ...
## $ rolling_vaccinations_9m_per_hundred : num 0 0.00337 0.00674 0.0101 0.01347 ...
## $ rolling_vaccinations_12m : num 0 1367 2733 4100 5467 ...
## $ rolling_vaccinations_12m_per_hundred : num 0 0.00337 0.00674 0.0101 0.01347 ...# Filter data terbaru untuk seluruh dunia
df_global <- df %>%
group_by(country) %>%
filter(date == max(date)) %>%
ungroup()
# Hitung rata-rata persentase vaksinasi global
global_vaccinated <- mean(df_global$people_vaccinated_per_hundred, na.rm = TRUE)
global_unvaccinated <- 100 - global_vaccinated
# Buat dataframe untuk visualisasi
df_status_global <- data.frame(
status = c("Vaccinated", "Unvaccinated"),
percentage = c(global_vaccinated, global_unvaccinated)
)
# Plot bar chart status vaksinasi global
ggplot(df_status_global, aes(x = "", y = percentage, fill = status)) +
geom_bar(stat = "identity", width = 0.5) +
coord_polar("y", start = 0) + # Pie chart
labs(
title = "Status Vaksinasi Global",
fill = "Status"
) +
scale_fill_manual(values = c("Vaccinated" = "blue", "Unvaccinated" = "red")) +
theme_minimal()
ggplot(df_status_global, aes(x = status, y = percentage, fill = status)) +
geom_bar(stat = "identity", width = 0.5) +
labs(
title = "Status Vaksinasi Global",
x = "Status",
y = "Persentase (%)",
fill = "Status"
) +
scale_fill_manual(values = c("Vaccinated" = "blue", "Unvaccinated" = "red")) +
theme_minimal()
negara_asean <- c("Indonesia", "Malaysia", "Singapore", "Thailand", "Vietnam",
"Philippines ETC")
# Filter data untuk negara ASEAN dan lakukan pivot
df_asean <- df %>%
filter(country %in% negara_asean) %>%
summarise(
total_vaccinated = sum(people_vaccinated, na.rm = TRUE),
total_unvaccinated = sum(people_unvaccinated, na.rm = TRUE)
) %>%
pivot_longer(cols = everything(), names_to = "status", values_to = "jumlah")
# Ubah label status
df_asean$status <- recode(df_asean$status,
"total_vaccinated" = "Vaccinated",
"total_unvaccinated" = "Unvaccinated")
# Buat pie chart dengan daftar negara di judul
ggplot(df_asean, aes(x = "", y = jumlah, fill = status)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0) +
labs(
title = paste0("Distribusi Status Vaksinasi di ASEAN\n(",
paste(negara_asean, collapse = ", "), ")"),
fill = "Status"
) +
scale_fill_manual(values = c("Vaccinated" = "blue", "Unvaccinated" = "red")) +
theme_void()
df <- read.csv("Total Kasus & Kematian/varian.csv")# Menghilangkan kolom yang tidak perlu (Entity, Code, Day)
vaksin_data <- df %>% select(-c(Entity, Code, Day))
# Menjumlahkan total dosis per jenis vaksin
total_dosis <- colSums(vaksin_data, na.rm = TRUE)
# Membuat data frame baru untuk visualisasi
df_vaksin <- data.frame(Vaksin = names(total_dosis), Jumlah = total_dosis)
# Mengambil 10 vaksin dengan dosis terbanyak
df_vaksin_top10 <- df_vaksin %>% top_n(10, Jumlah)ggplot(df_vaksin_top10, aes(x = "", y = Jumlah, fill = Vaksin)) +
geom_bar(stat = "identity", width = 1) +
coord_polar(theta = "y") +
labs(title = "Distribusi 10 Vaksin COVID-19 Terbanyak") +
theme_void()
# Filter hanya untuk negara ASEAN
asean_countries <- c("Indonesia", "Malaysia", "Thailand", "Singapore", "Vietnam", "Philippines", "Myanmar", "Cambodia", "Laos", "Brunei")
varian_asean <- df %>% filter(Entity %in% asean_countries)
# Pilih hanya kolom vaksin berdasarkan dataset yang ada
vaksin_cols <- c(
"COVID.19.doses..cumulative....Manufacturer.Pfizer.BioNTech",
"COVID.19.doses..cumulative....Manufacturer.Moderna",
"COVID.19.doses..cumulative....Manufacturer.Oxford.AstraZeneca",
"COVID.19.doses..cumulative....Manufacturer.Johnson.Johnson",
"COVID.19.doses..cumulative....Manufacturer.Sputnik.V",
"COVID.19.doses..cumulative....Manufacturer.Sinovac",
"COVID.19.doses..cumulative....Manufacturer.Sinopharm.Beijing" ,
"COVID.19.doses..cumulative....Manufacturer.CanSino",
"COVID.19.doses..cumulative....Manufacturer.Novavax",
"COVID.19.doses..cumulative....Manufacturer.Covaxin",
"COVID.19.doses..cumulative....Manufacturer.Medicago",
"COVID.19.doses..cumulative....Manufacturer.Sanofi.GSK" ,
"COVID.19.doses..cumulative....Manufacturer.SKYCovione",
"COVID.19.doses..cumulative....Manufacturer.Valneva"
)
# Hanya ambil kolom yang ada di dataset
vaksin_cols <- intersect(vaksin_cols, colnames(varian_asean))
# Jika tidak ada kolom vaksin, hentikan eksekusi
if (length(vaksin_cols) == 0) {
stop("Tidak ada data vaksin yang sesuai.")
}
# Hitung total dosis setiap jenis vaksin
total_vaksin <- colSums(varian_asean[, vaksin_cols], na.rm = TRUE)
# Konversi ke data frame untuk pie chart
varian_vaksin <- data.frame(
Vaksin = names(total_vaksin),
Dosis = as.numeric(total_vaksin)
)
# Buat pie chart
ggplot(varian_vaksin, aes(x = "", y = Dosis, fill = Vaksin)) +
geom_bar(stat = "identity", width = 1) +
coord_polar(theta = "y") +
labs(title = "Distribusi Jenis Vaksin di ASEAN") +
theme_void() +
theme(legend.position = "right")