data <- read.csv("C:\\Users\\ade\\Downloads\\ds_salaries.csv", sep= ",")
str (data)
## 'data.frame': 607 obs. of 12 variables:
## $ id : int 0 1 2 3 4 5 6 7 8 9 ...
## $ work_year : int 2020 2020 2020 2020 2020 2020 2020 2020 2020 2020 ...
## $ experience_level : chr "MI" "SE" "SE" "MI" ...
## $ employment_type : chr "FT" "FT" "FT" "FT" ...
## $ job_title : chr "Data Scientist" "Machine Learning Scientist" "Big Data Engineer" "Product Data Analyst" ...
## $ salary : int 70000 260000 85000 20000 150000 72000 190000 11000000 135000 125000 ...
## $ salary_currency : chr "EUR" "USD" "GBP" "USD" ...
## $ salary_in_usd : int 79833 260000 109024 20000 150000 72000 190000 35735 135000 125000 ...
## $ employee_residence: chr "DE" "JP" "GB" "HN" ...
## $ remote_ratio : int 0 0 50 0 50 100 100 50 100 50 ...
## $ company_location : chr "DE" "JP" "GB" "HN" ...
## $ company_size : chr "L" "S" "M" "S" ...
rataan_gaji <- aggregate(salary_in_usd ~ job_title, data=data, FUN=mean)
rataan_gaji <- rataan_gaji %>%
arrange(desc(salary_in_usd))
View(rataan_gaji)
top_10_gaji <- rataan_gaji %>%
slice_head(n = 10)
ggplot(data= top_10_gaji,
aes(x= salary_in_usd, y= reorder(job_title, salary_in_usd), fill= salary_in_usd)) +
geom_bar(stat= "identity") +
geom_text(aes(label= salary_in_usd), hjust= 1.1, color= "white", size= 3) +
labs(title= "Top 10 Job Title dengan Gaji Tertinggi",
caption= "Sumber: Badan Pusat Statistik", y= "Job title", x= "Gaji (US Dollar)") +
scale_fill_gradient(low= "orange", high= "red") +
theme(plot.title = element_text(hjust = 0.5))
data_remote <- table(data$remote_ratio)
data_remote <- data.frame(value= names(data_remote), frequency= as.numeric(data_remote))
ggplot(data_remote, aes(x = value, y = frequency, label = frequency)) +
geom_bar(stat = "identity", fill = "skyblue", color = "black") +
geom_text(size = 3, position = position_stack(vjust = 0.5)) +
labs(x = "Remote Ratio", y = "Frequency", title = "Bar Chart of Remote Ratio") +
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5))
# Membuat data hanya job dan merubah dalam tipe numeric
top10_job <- table(data$job_title)
top10_job <- data.frame(value= names(top10_job), frequency= as.numeric(top10_job))
# Mengurutkan job dari yang terbesar ke yang terkecil
top10_job <- top10_job %>%
arrange(desc(frequency))
# Menyusun data frame untuk top 10 job
top10_job <- data %>%
group_by(job_title) %>%
summarise(frequency = n()) %>%
arrange(desc(frequency)) %>%
slice(1:10)
# Membuat plot
ggplot(data= top10_job,
aes(x= frequency, y= reorder(job_title, frequency), fill= frequency)) +
geom_bar(stat= "identity") +
geom_text(aes(label= frequency), hjust= 1.5, color= "white", size= 3) +
labs(title= "Top 10 Job Terbanyak",
caption= "Sumber: Badan Pusat Statistik", y= "Job title", x= "frequency") +
scale_fill_gradient(low= "lightblue", high= "blue") +
theme(plot.title = element_text(hjust = 0.5))
2. Visualisasi Sebaran
ggplot(data = data) +
geom_density(aes(x = salary_in_usd, fill = as.factor(work_year), color = as.factor(work_year)), alpha = 0.5) +
labs(title = "Density Plot Sebaran Data Gaji Tiap Tahun",
x = "Gaji (US Dollar)",
y = "Jumlah") +
theme(plot.title = element_text(hjust = 0.5))
data$experience_level <- factor(data$experience_level, levels = c("EN", "MI", "SE", "EX"))
ggplot(data, aes(experience_level, salary_in_usd)) +
geom_violin(aes(col = experience_level), fill = NA, draw_quantiles = c(0.25,0.5,0.75)) +
labs(title = "Violin Plot Sebaran Data Gaji Berdasarkan Pengalaman Kerja",
caption = "Sumber: Badan Pusat Statistik")
# Mengubah variabel Bulan menjadi faktor dengan urutan yang diinginkan
data$experience_level <- factor(data$experience_level, levels = c("EN", "MI", "SE", "EX"))
ggplot(data = data, aes(x = experience_level, y = salary_in_usd, fill = experience_level , color=experience_level)) +
geom_boxplot(color="black") +
theme()+
scale_fill_manual(values = c("#711DB0", "#C21292", "#EF4040", "#FFA732")) +
labs(x = NULL, y = "Besar Gaji (US Dollar")
#Membuat data baru job title berdasarkan frekuensi job title
ds_job <- table(data$job_title)
ds_job <- data.frame(value = (names(ds_job)), frequency = as.numeric(ds_job))
treemap(ds_job,
index = "value", # Kolom untuk kategori
vSize = "frequency", # Kolom untuk ukuran
title = "Proporsi Job title") # Judul treemap
#Subset data
exp.S <- subset(data[,c("company_size","experience_level")], company_size == "S")
exp.S <- exp.S[,"experience_level"]
exp.M <- subset(data[,c("company_size","experience_level")], company_size == "M")
exp.M <- exp.M[,"experience_level"]
exp.L <- subset(data[,c("company_size","experience_level")], company_size == "L")
exp.L <- exp.L[,"experience_level"]
category.exp.S <- table(exp.S)
category.exp.M <- table(exp.M)
category.exp.L <- table(exp.L)
dat.exp.S <- data.frame(value = (names(category.exp.S)), frequency = as.numeric(category.exp.S))
dat.exp.M <- data.frame(value = (names(category.exp.M)), frequency = as.numeric(category.exp.M))
dat.exp.L <- data.frame(value = (names(category.exp.L)), frequency = as.numeric(category.exp.L))
data.exp <- data.frame(dat.exp.S, dat.exp.M[,"frequency"], dat.exp.L[,"frequency"])
colnames(data.exp) <- c("experience_level", "S", "M", "L")
# Melt the data
data.exp.melt <- melt(data.exp, id.vars = "experience_level")
# Calculate proportions
data.exp.melt <- ddply(data.exp.melt, "experience_level", transform, prop = value / sum(value))
# Plot
ggplot(data.exp.melt, aes(x = experience_level, y = prop, fill = variable)) +
geom_bar(stat = "identity") +
geom_text(aes(label = scales::percent(prop), group = variable),
position = position_stack(vjust = 0.5),
color = "white", size = 3) + # Menambahkan label proporsi
scale_y_continuous(labels = scales::percent_format()) +
labs(x = "experience_level", y = "Proportion", fill = "Group") +
ggtitle("Stacked Bar Chart of Proportions") +
theme_minimal()+
theme(plot.margin = margin(0, -5, 0, 0, "pt"))+
coord_flip()