# Displaying an introduction to the dataset:
library(readr)
## Warning: package 'readr' was built under R version 4.3.3
wpdata<-read.csv("wpdata.csv")
str(wpdata)
## 'data.frame': 234 obs. of 17 variables:
## $ Rank : int 36 138 34 213 203 42 224 201 33 140 ...
## $ CCA3 : chr "AFG" "ALB" "DZA" "ASM" ...
## $ Country.Territory : chr "Afghanistan" "Albania" "Algeria" "American Samoa" ...
## $ Capital : chr "Kabul" "Tirana" "Algiers" "Pago Pago" ...
## $ Continent : chr "Asia" "Europe" "Africa" "Oceania" ...
## $ X2022.Population : int 41128771 2842321 44903225 44273 79824 35588987 15857 93763 45510318 2780469 ...
## $ X2020.Population : int 38972230 2866849 43451666 46189 77700 33428485 15585 92664 45036032 2805608 ...
## $ X2015.Population : int 33753499 2882481 39543154 51368 71746 28127721 14525 89941 43257065 2878595 ...
## $ X2010.Population : int 28189672 2913399 35856344 54849 71519 23364185 13172 85695 41100123 2946293 ...
## $ X2000.Population : int 19542982 3182021 30774621 58230 66097 16394062 11047 75055 37070774 3168523 ...
## $ X1990.Population : int 10694796 3295066 25518074 47818 53569 11828638 8316 63328 32637657 3556539 ...
## $ X1980.Population : int 12486631 2941651 18739378 32886 35611 8330047 6560 64888 28024803 3135123 ...
## $ X1970.Population : int 10752971 2324731 13795915 27075 19860 6029700 6283 64516 23842803 2534377 ...
## $ Area..kmÂ.. : int 652230 28748 2381741 199 468 1246700 91 442 2780400 29743 ...
## $ Density..per.kmÂ.. : num 63.1 98.9 18.9 222.5 170.6 ...
## $ Growth.Rate : num 1.026 0.996 1.016 0.983 1.01 ...
## $ World.Population.Percentage: num 0.52 0.04 0.56 0 0 0.45 0 0 0.57 0.03 ...
#1).What is the total population of the world according to the dataset?
#In 1970:
wp_1970<-sum(wpdata$X1970.Population)
#In 2000:
wp_2000<-sum(wpdata$X2000.Population)
#In 2022:
wp_2022<-sum(wpdata$X2022.Population)
cat("World Population in 1970: ",wp_1970, " ")
## World Population in 1970: 3694136661
cat("\nWorld Population in 2000: ",wp_2000, " ", "Change(1970-2000):",wp_2000-wp_1970)
##
## World Population in 2000: 6147055703 Change(1970-2000): 2452919042
cat("\nWorld Population in 2022: ",wp_2022, " ", "Change(2000-2022):",wp_2022-wp_2000)
##
## World Population in 2022: 7973413042 Change(2000-2022): 1826357339
barplot(c(wp_1970, wp_2000, wp_2022), xlab = "Year", ylab = "Population", main = "Population over year", names.arg = c("1970", "2000", "2022"), col = c("red", "green", "blue"))
#2).How much Population increased between 1970 and 2022?
#Making a new column in of difference in world population bewtween 1970-2022 of each country:
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.3.3
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
wpdata<-mutate(wpdata, DifferenceX2022_X1970=X2022.Population-X1970.Population)
#Percentage increased in World Population Country wise:
wpdata<-mutate(wpdata, PerecIncreased=(DifferenceX2022_X1970/X1970.Population)*100)
pop_diff<-wpdata%>%select(Country.Territory, X2022.Population, X1970.Population, PerecIncreased)%>%slice_head(n=10)
pop_diff
## Country.Territory X2022.Population X1970.Population PerecIncreased
## 1 Afghanistan 41128771 10752971 282.487510
## 2 Albania 2842321 2324731 22.264511
## 3 Algeria 44903225 13795915 225.482036
## 4 American Samoa 44273 27075 63.519852
## 5 Andorra 79824 19860 301.933535
## 6 Angola 35588987 6029700 490.228154
## 7 Anguilla 15857 6283 152.379437
## 8 Antigua and Barbuda 93763 64516 45.332941
## 9 Argentina 45510318 23842803 90.876542
## 10 Armenia 2780469 2534377 9.710158
#Barplotting:
barplot(pop_diff$PerecIncreased, col = c("red", "green", "blue", "black","orange","maroon","grey","pink","navy","skyblue","brown"), names.arg = pop_diff$Country.Territor, las=2, xlab = "Countries", ylab = "% increase in Population", main = "Percentage increased in World Population in Terms of Countries")
#3).Identifying countries with declining populations?
library(dplyr)
dec_pop<-wpdata%>%select(Country.Territory,PerecIncreased)%>%filter(PerecIncreased<0)
dec_pop
## Country.Territory PerecIncreased
## 1 Bosnia and Herzegovina -15.254244
## 2 Bulgaria -20.983426
## 3 Cook Islands -16.897899
## 4 Croatia -10.289723
## 5 Estonia -2.638548
## 6 Georgia -21.998902
## 7 Hungary -3.374170
## 8 Latvia -22.806366
## 9 Lithuania -14.332428
## 10 Moldova -11.806184
## 11 Montserrat -61.497983
## 12 Niue -62.700096
## 13 Romania -1.321869
## 14 Ukraine -16.026847
## 15 Vatican City -32.180851
#Most decrease in Population:
most_dec<-min(dec_pop$PerecIncreased)
cat("Most decrease in Population: ",most_dec)
## Most decrease in Population: -62.7001
#Pie Chart:
pie(abs(dec_pop$PerecIncreased), labels = dec_pop$Country.Territory, main = "Decrease in Population", col = rainbow(length(dec_pop$Country.Territory)))
#4).The total population for each continent in year 2022:
library(dplyr)
total_population_by_continent<-wpdata%>%group_by(Continent)%>%summarize(Total_Population=sum(X2022.Population))
total_population_by_continent
## # A tibble: 6 × 2
## Continent Total_Population
## <chr> <dbl>
## 1 Africa 1426730932
## 2 Asia 4721383274
## 3 Europe 743147538
## 4 North America 600296136
## 5 Oceania 45038554
## 6 South America 436816608
#Barplotting:
barplot(total_population_by_continent$Total_Population, names.arg = total_population_by_continent$Continent, las = 2, xlab = "Continent", ylab = "Population", main = "Total Population in Each Continent", col = c("yellow","maroon","orange","brown","red","blue"))
#5).Top 10 populated countries in 2022:
library(dplyr)
wpdata1<-wpdata%>%select(Country.Territory, Rank,X2022.Population)%>%arrange(desc(X2022.Population))
wpdata1<-wpdata1%>%slice_head(n=10)
wpdata1
## Country.Territory Rank X2022.Population
## 1 China 1 1425887337
## 2 India 2 1417173173
## 3 United States 3 338289857
## 4 Indonesia 4 275501339
## 5 Pakistan 5 235824862
## 6 Nigeria 6 218541212
## 7 Brazil 7 215313498
## 8 Bangladesh 8 171186372
## 9 Russia 9 144713314
## 10 Mexico 10 127504125
#Barplotting:
barplot(wpdata1$X2022.Population, names.arg = wpdata1$Country.Territory, xlab = "Countries", ylab = "Population", main = "Top 10 populated Countries", col = c("red", "green", "blue", "black","orange","maroon","grey","pink","navy","skyblue","brown"))
#6).Average Density of Population in World?
avg_density<-mean(wpdata$Density..per.kmÂ..)
cat("Average density of Poulation: ",avg_density)
## Average density of Poulation: 452.127
#7).What is the growth rate of population of \n top 10 populated countries:
library(dplyr)
wpdata2<-wpdata%>%select(Country.Territory, Growth.Rate,X2022.Population)%>%arrange(desc(X2022.Population))%>%slice_head(n=10)
wpdata2
## Country.Territory Growth.Rate X2022.Population
## 1 China 1.0000 1425887337
## 2 India 1.0068 1417173173
## 3 United States 1.0038 338289857
## 4 Indonesia 1.0064 275501339
## 5 Pakistan 1.0191 235824862
## 6 Nigeria 1.0241 218541212
## 7 Brazil 1.0046 215313498
## 8 Bangladesh 1.0108 171186372
## 9 Russia 0.9973 144713314
## 10 Mexico 1.0063 127504125
#Country with highest Growth Rate:
max(wpdata2$Growth.Rate)
## [1] 1.0241
#Barplotting:
barplot(wpdata2$Growth.Rate, names.arg = wpdata2$Country.Territory, xlab = "Countries", ylab = "Growth Rate", col = c("red", "green", "blue", "black","orange","maroon","grey","pink","navy","skyblue","brown"), main = "Growth Rate of Population.", las = 2)
#8).Which country has most population but Area of that country is small in top 10 populated country:
wpdata3<-wpdata%>%select(Country.Territory, Density..per.kmÂ..,Area..kmÂ..,X2022.Population)%>%arrange(desc(X2022.Population))%>%slice_head(n=10)
wpdata3
## Country.Territory Density..per.kmÂ.. Area..kmÂ.. X2022.Population
## 1 China 146.8933 9706961 1425887337
## 2 India 431.0675 3287590 1417173173
## 3 United States 36.0935 9372610 338289857
## 4 Indonesia 144.6529 1904569 275501339
## 5 Pakistan 267.4018 881912 235824862
## 6 Nigeria 236.5759 923768 218541212
## 7 Brazil 25.2841 8515767 215313498
## 8 Bangladesh 1160.0350 147570 171186372
## 9 Russia 8.4636 17098242 144713314
## 10 Mexico 64.9082 1964375 127504125
min(wpdata3$Area..kmÂ..)
## [1] 147570
#Barplotting:
barplot(wpdata3$X2022.Population, main = "Population in 2022", xlab = "Countries", ylab = "Population", names.arg = wpdata3$Country.Territory, las = 2,col = "orange")
barplot(wpdata3$Area..kmÂ.., main = "Area of The Country", xlab = "Country", ylab = "Area", las = 2, names.arg = wpdata3$Country.Territory, col = "red", density = 60)
#9).Change in Rank of the countries in top 10 populated countries in 1970 and 2022:
library(dplyr)
wpdata4<-wpdata%>%select(Country.Territory, X1970.Population)%>%arrange(desc(X1970.Population))%>%slice_head(n=10)
wpdata4
## Country.Territory X1970.Population
## 1 China 822534450
## 2 India 557501301
## 3 United States 200328340
## 4 Russia 130093010
## 5 Indonesia 115228394
## 6 Japan 105416839
## 7 Brazil 96369875
## 8 Germany 78294583
## 9 Bangladesh 67541860
## 10 Pakistan 59290872
wpdata1
## Country.Territory Rank X2022.Population
## 1 China 1 1425887337
## 2 India 2 1417173173
## 3 United States 3 338289857
## 4 Indonesia 4 275501339
## 5 Pakistan 5 235824862
## 6 Nigeria 6 218541212
## 7 Brazil 7 215313498
## 8 Bangladesh 8 171186372
## 9 Russia 9 144713314
## 10 Mexico 10 127504125
#10).Which countries are recorded highest increase in population:
max_perc<-wpdata%>%select(Country.Territory, PerecIncreased)%>%arrange(desc(PerecIncreased))%>%slice_head(n=10)
max_perc
## Country.Territory PerecIncreased
## 1 United Arab Emirates 3067.2713
## 2 Qatar 2183.8662
## 3 Mayotte 821.6319
## 4 Turks and Caicos Islands 706.7608
## 5 Djibouti 676.3241
## 6 Western Sahara 654.1947
## 7 Jordan 624.6730
## 8 Sint Maarten 605.6709
## 9 Oman 582.3238
## 10 Bahrain 561.5142
#Barplotting:
barplot(max_perc$PerecIncreased, names.arg = max_perc$Country.Territory, xlab = "Country", ylab = "% Increased", main = "Recorded highest increase in population \n Between 1970-2022", col = c("red", "green", "blue", "black","orange","maroon","grey","pink","navy","skyblue","brown"), las = 2)
#11).How much percentage of world population held by top 10 populated countries:
library(dplyr)
most_wpperc<-wpdata%>%select(Country.Territory, World.Population.Percentage, Area..kmÂ..)%>%arrange(desc(World.Population.Percentage))%>%slice_head(n=10)
most_wpperc
## Country.Territory World.Population.Percentage Area..kmÂ..
## 1 China 17.88 9706961
## 2 India 17.77 3287590
## 3 United States 4.24 9372610
## 4 Indonesia 3.45 1904569
## 5 Pakistan 2.96 881912
## 6 Nigeria 2.74 923768
## 7 Brazil 2.70 8515767
## 8 Bangladesh 2.15 147570
## 9 Russia 1.81 17098242
## 10 Mexico 1.60 1964375
#Pie Chart:
pie(most_wpperc$World.Population.Percentage, labels = abs(most_wpperc$World.Population.Percentage), main = "Percentage of world population held by \n top 10 populated countries.")
