Demografi
Fathir
30/11/2021
ANALISIS DEMOGRAFI_TUGAS 2
- Anda dipekerjakan sebagai Data Scientist oleh Bank Dunia dan Anda sedang mengerjakan sebuah proyek untuk menganalisis tren demografis Dunia.
- Anda diminta untuk membuat scatterplot yang menggambarkan Angka Kelahiran dan Stattistik Penggunaan Internet menurut Negara.
- Scatterplot juga perlu dikategorikan berdasarkan Kelompok Pendapatan Negara.
- Anda mendapat pekerjaan pembaruan mendesak dan secepatnya dilaksanakan dari manajer Anda.
- Anda diminta untuk membuat scatterplot kedua yang juga menggambarkan Angka Kelahiran dan Statistik Penggunaan Internet menurut Negara.
- Namun, kali ini scatterplot perlu dikategorikan berdasarkan Wilayah Negara.
- Data tambahan telah disediakan dalam bentuk vektor R.
#baca data
demografi <- read.csv("D:/KULIAH UIN/SMT 2/MACHINE LEARNING/tugas 2/P2-Demographic-Data.csv")
head(demografi)## Country.Name Country.Code Birth.rate Internet.users
## 1 Aruba ABW 10.244 78.9
## 2 Afghanistan AFG 35.253 5.9
## 3 Angola AGO 45.985 19.1
## 4 Albania ALB 12.877 57.2
## 5 United Arab Emirates ARE 11.044 88.0
## 6 Argentina ARG 17.716 59.9
## Income.Group
## 1 High income
## 2 Low income
## 3 Upper middle income
## 4 Upper middle income
## 5 High income
## 6 High incomesummary(demografi)## Country.Name Country.Code Birth.rate Internet.users
## Length:195 Length:195 Min. : 7.90 Min. : 0.90
## Class :character Class :character 1st Qu.:12.12 1st Qu.:14.52
## Mode :character Mode :character Median :19.68 Median :41.00
## Mean :21.47 Mean :42.08
## 3rd Qu.:29.76 3rd Qu.:66.22
## Max. :49.66 Max. :96.55
## Income.Group
## Length:195
## Class :character
## Mode :character
##
##
## #Data dengan Angka Kelahiran di atas 2
filter_br <- demografi$Birth.rate > 2
head(demografi[filter_br,])## Country.Name Country.Code Birth.rate Internet.users
## 1 Aruba ABW 10.244 78.9
## 2 Afghanistan AFG 35.253 5.9
## 3 Angola AGO 45.985 19.1
## 4 Albania ALB 12.877 57.2
## 5 United Arab Emirates ARE 11.044 88.0
## 6 Argentina ARG 17.716 59.9
## Income.Group
## 1 High income
## 2 Low income
## 3 Upper middle income
## 4 Upper middle income
## 5 High income
## 6 High incomehead(demografi[demografi$Birth.rate > 40,]) ## Country.Name Country.Code Birth.rate Internet.users Income.Group
## 3 Angola AGO 45.985 19.1 Upper middle income
## 12 Burundi BDI 44.151 1.3 Low income
## 15 Burkina Faso BFA 40.551 9.1 Low income
## 66 Gambia, The GMB 42.525 14.0 Low income
## 116 Mali MLI 44.138 3.5 Low income
## 128 Niger NER 49.661 1.7 Low incomehead(demografi[demografi$Income.Group == "High income",])## Country.Name Country.Code Birth.rate Internet.users Income.Group
## 1 Aruba ABW 10.244 78.9000 High income
## 5 United Arab Emirates ARE 11.044 88.0000 High income
## 6 Argentina ARG 17.716 59.9000 High income
## 8 Antigua and Barbuda ATG 16.447 63.4000 High income
## 9 Australia AUS 13.200 83.0000 High income
## 10 Austria AUT 9.400 80.6188 High incomeMENCARI BERDASARKAN NEGARA
head(demografi[demografi$Country.Code == "AFG ",])## [1] Country.Name Country.Code Birth.rate Internet.users Income.Group
## <0 rows> (or 0-length row.names)library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.0.5qplot(data = demografi, x=Internet.users, y = Birth.rate, size=I(4), colour=I("blue"))
#
qplot(data = demografi, x=Internet.users, y = Birth.rate, size=I(3), colour=Income.Group)
Berdasarkan Negara
#Scatter Plot antara Pengguna.Internet & Angka.Kelahiran dan dikategorikan berdasarkan Wilayah Negara
qplot(data = demografi, x= Internet.users, y= Birth.rate, size=I(3), colour=Country.Name)
A. Membuat Scatter Plot dengan Kategori Berdasarkan Wilayah Negara
Country.Code <- c("ABW","AFG","AGO","ALB","ARE","ARG","ARM","ATG","AUS","AUT","AZE","BDI","BEL","BEN","BFA","BGD","BGR","BHR","BHS","BIH","BLR","BLZ","BMU","BOL","BRA","BRB","BRN","BTN","BWA","CAF","CAN","CHE","CHL","CHN","CIV","CMR","COG","COL","COM","CPV","CRI","CUB","CYM","CYP","CZE","DEU","DJI","DNK","DOM","DZA","ECU","EGY","ERI","ESP","EST","ETH","FIN","FJI","FRA","FSM","GAB","GBR","GEO","GHA","GIN","GMB","GNB","GNQ","GRC","GRD","GRL","GTM","GUM","GUY","HKG","HND","HRV","HTI","HUN","IDN","IND","IRL","IRN","IRQ","ISL","ISR","ITA","JAM","JOR","JPN","KAZ","KEN","KGZ","KHM","KIR","KOR","KWT","LAO","LBN","LBR","LBY","LCA","LIE","LKA","LSO","LTU","LUX","LVA","MAC","MAR","MDA","MDG","MDV","MEX","MKD","MLI","MLT","MMR","MNE","MNG","MOZ","MRT","MUS","MWI","MYS","NAM","NCL","NER","NGA","NIC","NLD","NOR","NPL","NZL","OMN","PAK","PAN","PER","PHL","PNG","POL","PRI","PRT","PRY","PYF","QAT","ROU","RUS","RWA","SAU","SDN","SEN","SGP","SLB","SLE","SLV","SOM","SRB","SSD","STP","SUR","SVK","SVN","SWE","SWZ","SYC","SYR","TCD","TGO","THA","TJK","TKM","TLS","TON","TTO","TUN","TUR","TZA","UGA","UKR","URY","USA","UZB","VCT","VEN","VIR","VNM","VUT","PSE","WSM","YEM","ZAF","COD","ZMB","ZWE")
Country.Name <- c("Amerika","Asia","Afrika","Eropa","Middle East","Amerika","Asia","Amerika","Oceania","Eropa","Asia","Afrika","Eropa","Afrika","Afrika","Asia","Eropa","Middle East","Amerika","Eropa","Eropa","Amerika","Amerika","Amerika","Amerika","Amerika","Asia","Asia","Afrika","Afrika","Amerika","Eropa","Amerika","Asia","Afrika","Afrika","Afrika","Amerika","Afrika","Afrika","Amerika","Amerika","Amerika","Eropa","Eropa","Eropa","Afrika","Eropa","Amerika","Afrika","Amerika","Afrika","Afrika","Eropa","Eropa","Afrika","Eropa","Oceania","Eropa","Oceania","Afrika","Eropa","Asia","Afrika","Afrika","Afrika","Afrika","Afrika","Eropa","Amerika","Amerika","Amerika","Oceania","Amerika","Asia","Amerika","Eropa","Amerika","Eropa","Asia","Asia","Eropa","Middle East","Middle East","Eropa","Middle East","Eropa","Amerika","Middle East","Asia","Asia","Afrika","Asia","Asia","Oceania","Asia","Middle East","Asia","Middle East","Afrika","Afrika","Amerika","Eropa","Asia","Afrika","Eropa","Eropa","Eropa","Asia","Afrika","Eropa","Afrika","Asia","Amerika","Eropa","Afrika","Eropa","Asia","Eropa","Asia","Afrika","Afrika","Afrika","Afrika","Asia","Afrika","Oceania","Afrika","Afrika","Amerika","Eropa","Eropa","Asia","Oceania","Middle East","Asia","Amerika","Amerika","Asia","Oceania","Eropa","Amerika","Eropa","Amerika","Oceania","Middle East","Eropa","Eropa","Afrika","Middle East","Afrika","Afrika","Asia","Oceania","Afrika","Amerika","Afrika","Eropa","Afrika","Afrika","Amerika","Eropa","Eropa","Eropa","Afrika","Afrika","Middle East","Afrika","Afrika","Asia","Asia","Asia","Asia","Oceania","Amerika","Afrika","Eropa","Afrika","Afrika","Eropa","Amerika","Amerika","Asia","Amerika","Amerika","Amerika","Asia","Oceania","Middle East","Oceania","Middle East","Afrika","Afrika","Afrika","Afrika")
# Membuat Data Frame
dataset_demographic <- data.frame(Country.Code, Country.Name)
head(dataset_demographic)## Country.Code Country.Name
## 1 ABW Amerika
## 2 AFG Asia
## 3 AGO Afrika
## 4 ALB Eropa
## 5 ARE Middle East
## 6 ARG AmerikaMENYATUKAN 2 DATA : DI ATAS
merge_dataset <- merge(demografi, dataset_demographic, by.x="Country.Code", by.y ="Country.Code")head(merge_dataset)## Country.Code Country.Name.x Birth.rate Internet.users
## 1 ABW Aruba 10.244 78.9
## 2 AFG Afghanistan 35.253 5.9
## 3 AGO Angola 45.985 19.1
## 4 ALB Albania 12.877 57.2
## 5 ARE United Arab Emirates 11.044 88.0
## 6 ARG Argentina 17.716 59.9
## Income.Group Country.Name.y
## 1 High income Amerika
## 2 Low income Asia
## 3 Upper middle income Afrika
## 4 Upper middle income Eropa
## 5 High income Middle East
## 6 High income AmerikaB. Scatter Plot Angka Kelahiran dan Pengguna Internet Berdasarkan Wilayah Negara.
scatterplot2 <- ggplot(merge_dataset, aes(x = Birth.rate, y = Internet.users, shape = Country.Name, color=Country.Name))+
geom_point()
scatterplot2