Importing the libraries
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.4.2 ✔ purrr 1.0.1
## ✔ tibble 3.2.1 ✔ dplyr 1.1.2
## ✔ tidyr 1.3.0 ✔ stringr 1.5.0
## ✔ readr 2.1.3 ✔ forcats 0.5.2
## Warning: package 'ggplot2' was built under R version 4.2.3
## Warning: package 'tibble' was built under R version 4.2.3
## Warning: package 'tidyr' was built under R version 4.2.3
## Warning: package 'purrr' was built under R version 4.2.3
## Warning: package 'dplyr' was built under R version 4.2.3
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
library(leaflet)
## Warning: package 'leaflet' was built under R version 4.2.3
library(treemap)
## Warning: package 'treemap' was built under R version 4.2.3
library(rmarkdown)
library(highcharter)
## Warning: package 'highcharter' was built under R version 4.2.3
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
## Highcharts (www.highcharts.com) is a Highsoft software product which is
## not free for commercial and Governmental use
library(viridis)
## Loading required package: viridisLite
library(ggplot2)
library(tidyr)
library(dplyr)
library(viridisLite)
library(RColorBrewer)
library(countrycode)
## Warning: package 'countrycode' was built under R version 4.2.3
library(wordcloud)
## Warning: package 'wordcloud' was built under R version 4.2.3
library(tidytext)
## Warning: package 'tidytext' was built under R version 4.2.3
library(tm)
## Warning: package 'tm' was built under R version 4.2.3
## Loading required package: NLP
##
## Attaching package: 'NLP'
##
## The following object is masked from 'package:ggplot2':
##
## annotate
library(plotly)
## Warning: package 'plotly' was built under R version 4.2.3
##
## Attaching package: 'plotly'
##
## The following object is masked from 'package:ggplot2':
##
## last_plot
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following object is masked from 'package:graphics':
##
## layout
Importing the Dataset
data = read.csv("D:/SOBAT KARIER/PORTOFOLIO/Terrorist/globalterrorismdb.csv")
str(data)
## 'data.frame': 181691 obs. of 135 variables:
## $ eventid : num 1.97e+11 1.97e+11 1.97e+11 1.97e+11 1.97e+11 ...
## $ iyear : int 1970 1970 1970 1970 1970 1970 1970 1970 1970 1970 ...
## $ imonth : int 7 0 1 1 1 1 1 1 1 1 ...
## $ iday : int 2 0 0 0 0 1 2 2 2 3 ...
## $ approxdate : chr "" "" "" "" ...
## $ extended : int 0 0 0 0 0 0 0 0 0 0 ...
## $ resolution : chr "" "" "" "" ...
## $ country : int 58 130 160 78 101 217 218 217 217 217 ...
## $ country_txt : chr "Dominican Republic" "Mexico" "Philippines" "Greece" ...
## $ region : int 2 1 5 8 4 1 3 1 1 1 ...
## $ region_txt : chr "Central America & Caribbean" "North America" "Southeast Asia" "Western Europe" ...
## $ provstate : chr "" "Federal" "Tarlac" "Attica" ...
## $ city : chr "Santo Domingo" "Mexico city" "Unknown" "Athens" ...
## $ latitude : num 18.5 19.4 15.5 38 33.6 ...
## $ longitude : num -70 -99.1 120.6 23.8 130.4 ...
## $ specificity : int 1 1 4 1 1 1 1 1 1 1 ...
## $ vicinity : int 0 0 0 0 0 0 0 0 0 0 ...
## $ location : chr "" "" "" "" ...
## $ summary : chr "" "" "" "" ...
## $ crit1 : int 1 1 1 1 1 1 1 1 1 1 ...
## $ crit2 : int 1 1 1 1 1 1 1 1 1 1 ...
## $ crit3 : int 1 1 1 1 1 1 1 1 1 1 ...
## $ doubtterr : int 0 0 0 0 -9 0 0 1 0 0 ...
## $ alternative : int NA NA NA NA NA NA NA 2 NA NA ...
## $ alternative_txt : chr "" "" "" "" ...
## $ multiple : int 0 0 0 0 0 0 0 0 0 0 ...
## $ success : int 1 1 1 1 1 1 0 1 1 1 ...
## $ suicide : int 0 0 0 0 0 0 0 0 0 0 ...
## $ attacktype1 : int 1 6 1 3 7 2 1 3 7 7 ...
## $ attacktype1_txt : chr "Assassination" "Hostage Taking (Kidnapping)" "Assassination" "Bombing/Explosion" ...
## $ attacktype2 : int NA NA NA NA NA NA NA NA NA NA ...
## $ attacktype2_txt : chr "" "" "" "" ...
## $ attacktype3 : int NA NA NA NA NA NA NA NA NA NA ...
## $ attacktype3_txt : chr "" "" "" "" ...
## $ targtype1 : int 14 7 10 7 7 3 3 21 4 2 ...
## $ targtype1_txt : chr "Private Citizens & Property" "Government (Diplomatic)" "Journalists & Media" "Government (Diplomatic)" ...
## $ targsubtype1 : int 68 45 54 46 46 22 25 107 28 21 ...
## $ targsubtype1_txt : chr "Named Civilian" "Diplomatic Personnel (outside of embassy, consulate)" "Radio Journalist/Staff/Facility" "Embassy/Consulate" ...
## $ corp1 : chr "" "Belgian Ambassador Daughter" "Voice of America" "" ...
## $ target1 : chr "Julio Guzman" "Nadine Chaval, daughter" "Employee" "U.S. Embassy" ...
## $ natlty1 : int 58 21 217 217 217 217 218 217 217 217 ...
## $ natlty1_txt : chr "Dominican Republic" "Belgium" "United States" "United States" ...
## $ targtype2 : int NA NA NA NA NA NA NA NA NA NA ...
## $ targtype2_txt : chr "" "" "" "" ...
## $ targsubtype2 : int NA NA NA NA NA NA NA NA NA NA ...
## $ targsubtype2_txt : chr "" "" "" "" ...
## $ corp2 : chr "" "" "" "" ...
## $ target2 : chr "" "" "" "" ...
## $ natlty2 : int NA NA NA NA NA NA NA NA NA NA ...
## $ natlty2_txt : chr "" "" "" "" ...
## $ targtype3 : int NA NA NA NA NA NA NA NA NA NA ...
## $ targtype3_txt : chr "" "" "" "" ...
## $ targsubtype3 : int NA NA NA NA NA NA NA NA NA NA ...
## $ targsubtype3_txt : chr "" "" "" "" ...
## $ corp3 : chr "" "" "" "" ...
## $ target3 : chr "" "" "" "" ...
## $ natlty3 : int NA NA NA NA NA NA NA NA NA NA ...
## $ natlty3_txt : chr "" "" "" "" ...
## $ gname : chr "MANO-D" "23rd of September Communist League" "Unknown" "Unknown" ...
## $ gsubname : chr "" "" "" "" ...
## $ gname2 : chr "" "" "" "" ...
## $ gsubname2 : chr "" "" "" "" ...
## $ gname3 : chr "" "" "" "" ...
## $ gsubname3 : chr "" "" "" "" ...
## $ motive : chr "" "" "" "" ...
## $ guncertain1 : int 0 0 0 0 0 0 0 0 0 0 ...
## $ guncertain2 : int NA NA NA NA NA NA NA NA NA NA ...
## $ guncertain3 : int NA NA NA NA NA NA NA NA NA NA ...
## $ individual : int 0 0 0 0 0 0 0 0 0 0 ...
## $ nperps : int NA 7 NA NA NA -99 3 -99 1 1 ...
## $ nperpcap : num NA NA NA NA NA -99 NA -99 1 1 ...
## $ claimed : int NA NA NA NA NA 0 NA 0 1 0 ...
## $ claimmode : int NA NA NA NA NA NA NA NA 1 NA ...
## $ claimmode_txt : chr "" "" "" "" ...
## $ claim2 : int NA NA NA NA NA NA NA NA NA NA ...
## $ claimmode2 : int NA NA NA NA NA NA NA NA NA NA ...
## $ claimmode2_txt : chr "" "" "" "" ...
## $ claim3 : int NA NA NA NA NA NA NA NA NA NA ...
## $ claimmode3 : int NA NA NA NA NA NA NA NA NA NA ...
## $ claimmode3_txt : chr "" "" "" "" ...
## $ compclaim : int NA NA NA NA NA NA NA NA NA NA ...
## $ weaptype1 : int 13 13 13 6 8 5 5 6 8 8 ...
## $ weaptype1_txt : chr "Unknown" "Unknown" "Unknown" "Explosives" ...
## $ weapsubtype1 : int NA NA NA 16 NA 5 2 16 19 20 ...
## $ weapsubtype1_txt : chr "" "" "" "Unknown Explosive Type" ...
## $ weaptype2 : int NA NA NA NA NA NA NA NA NA NA ...
## $ weaptype2_txt : chr "" "" "" "" ...
## $ weapsubtype2 : int NA NA NA NA NA NA NA NA NA NA ...
## $ weapsubtype2_txt : chr "" "" "" "" ...
## $ weaptype3 : int NA NA NA NA NA NA NA NA NA NA ...
## $ weaptype3_txt : chr "" "" "" "" ...
## $ weapsubtype3 : int NA NA NA NA NA NA NA NA NA NA ...
## $ weapsubtype3_txt : chr "" "" "" "" ...
## $ weaptype4 : int NA NA NA NA NA NA NA NA NA NA ...
## $ weaptype4_txt : chr "" "" "" "" ...
## $ weapsubtype4 : int NA NA NA NA NA NA NA NA NA NA ...
## $ weapsubtype4_txt : chr "" "" "" "" ...
## $ weapdetail : chr "" "" "" "Explosive" ...
## $ nkill : int 1 0 1 NA NA 0 0 0 0 0 ...
## [list output truncated]
Terrorism
countries <- data %>%
group_by(country_txt) %>%
summarise(Total = n())
names(countries) <- c("country.name", "total")
countries$iso3 = countrycode(countries$country.name, origin = "country.name", destination = "iso3c")
## Warning: Some values were not matched unambiguously: Czechoslovakia, East Germany (GDR), International, Kosovo, North Yemen, Serbia-Montenegro, South Vietnam, South Yemen, Yugoslavia
stops <- data.frame(q = c(0, exp(1:10)/exp(10)),
c = substring(viridis(10 + 1, option = "D"), 0, 7)) %>%
list_parse2()
data(worldgeojson, package = "highcharter")
hc_plot = highchart() %>%
hc_add_series_map(worldgeojson, countries, value = "total", joinBy = "iso3") %>%
hc_colorAxis(stops = stops) %>%
hc_legend(enabled = TRUE) %>%
hc_add_theme(hc_theme_db()) %>%
hc_mapNavigation(enabled = TRUE) %>%
hc_title(text = "Total Number of Attacks From 1970 to 2017") %>%
hc_add_theme(hc_theme_google())
hc_plot
Terrosism over the years
year_killing <- data %>%
group_by(Year = iyear) %>%
filter(nkill > 0) %>%
summarise(total_killing = sum(nkill)) %>%
ungroup()
hc_plot <- highchart() %>%
hc_add_series(year_killing, hcaes(x = Year, y = total_killing), type = "line") %>%
hc_tooltip(crosshairs = TRUE, borderWidth = 1.5, headerFormat = "", pointFormat = paste("Year: <b>{point.Year}</b> <br>","Killing: <b>{point.total_killing}</b><br>")) %>%
hc_title(text = "Terrorism over the years") %>%
hc_subtitle(text = "1970-2017") %>%
hc_xAxis(title = list(text = "Year")) %>%
hc_yAxis(title = list(text = "Number of people killed"),
allowDecimals = FALSE,
plotLines = list(list(
color = "black", width = 1, dashStyle = "Dash",
value = mean(year_killing$total_killing),
label = list(text = "Average people killed = 8763",
style = list(color = 'red', fontSize = 20))))) %>%
hc_add_theme(hc_theme_ffx())
hc_plot
Countries effected by the terrorism
country1 <- data %>%
group_by(country_txt) %>%
summarise(incidents = n()) %>%
arrange(desc(incidents))
treemap(country1,
index=c("country_txt"),
vSize = "incidents",
palette = "RdYlBu",
title="Number of events - Terrorism",
fontsize.title = 16
)
Citites Effected by the terrorism
killings_city <- data %>%
drop_na(nkill) %>%
filter(nkill > 1) %>%
group_by(city)%>%
summarise(total_killing = sum(nkill)) %>%
arrange(desc(total_killing)) %>%
head(n=15)
ggplot(killings_city, aes(x=reorder(city, total_killing), y= total_killing)) +
geom_bar(stat = "identity", fill = "red", col = "black") +
coord_flip() +
labs(x="City", y="Killings", title = "Number of people killed - CITY")
Number Of terrorists killed from 1970 to 2016
killter <- data %>%
filter(nkillter > 0) %>%
group_by(region = region_txt, year = iyear) %>%
summarise(terrorist_killed = sum(nkillter))
## `summarise()` has grouped output by 'region'. You can override using the
## `.groups` argument.
ggplot(killter, aes(x=reorder(year, terrorist_killed), y=terrorist_killed)) +
geom_bar(stat = "identity", fill = "red") +
coord_flip() +
labs(x="Year", y="Terrorist killed", title = "Number of terrorist killed from 1970 - 2016")
Number of Killings - Regionwise
region <- data %>%
group_by(region = region_txt) %>%
filter(nkill > 0) %>%
summarise(killings = sum(nkill)) %>%
arrange(desc(killings))
hc_plot = hctreemap2(region,
group_vars = "region",
size_var = "killings",
color_var = "killings",
layoutAlgorithm = "squarified",
levelIsConstant = FALSE,
levels = list(
list(level = 1, dataLabels = list(enabled = TRUE)),
list(level = 2, dataLabels = list(enabled = FALSE)),
list(level = 3, dataLabels = list(enabled = FALSE))
)
) %>%
hc_colorAxis(minColor = brewer.pal(7, "Reds")[1],
maxColor = brewer.pal(7, "Reds")[7]) %>%
hc_tooltip(pointFormat = "<b>{point.region}</b>:<br>
killings: {point.colorValue:,.0f}")
## Warning: 'hctreemap2' is deprecated.
## Use 'data_to_hierarchical' instead.
## See help("Deprecated")
hc_plot
Terrorist group Involved
gang_killing <- data %>%
group_by(gang = gname) %>%
summarise(killing = sum(nkill)) %>%
arrange(desc(killing)) %>%
head(n=20)
ggplot(gang_killing, aes(x=reorder(gang, killing), y = killing)) +
geom_bar(fill = 'red', col = "black", stat = "identity") +
theme_classic() +
labs(x="Gangs", y="Number of people killed") +
coord_flip()
Terrorist nationality
terrorist <- data %>%
filter(nkill > 0) %>%
group_by(natlty1_txt) %>%
summarise(killing = sum(nkill)) %>%
arrange(desc(killing)) %>%
head(n = 10)
ggplot(terrorist, aes(x=reorder(natlty1_txt, killing), y = killing)) +
geom_bar(fill = 'red', col = "black", stat = "identity") +
theme_classic() +
labs(x="Nationality of Terrorists", y="Number of people killed") +
coord_flip()
Crime Types
crime <- data %>%
filter(nkill > 0) %>%
group_by(alternative_txt) %>%
summarise(killing = sum(nkill)) %>%
arrange(desc(killing))
ggplot(crime, aes(x=reorder(alternative_txt, killing), y = killing)) +
geom_bar(fill = 'red', col = "black", stat = "identity") +
theme_classic() +
labs(x="Crime Type", y="Number of people killed") +
coord_flip()
Crime Types
weapon <- data %>%
filter(weaptype1_txt != "Unknown") %>%
group_by(weaptype1_txt) %>%
summarise(Events = n())
plot1 <- ggplot(weapon, aes(x = reorder(weaptype1_txt, Events), y = Events)) +
geom_bar(stat = "identity", fill = "Red", col = "black") +
labs(x = "Weapon Used", y = "Number of times", title = "Weapon Type") +
coord_flip() +
theme_classic()
plot1
Target Terrorists
target <- data %>%
group_by(targtype1_txt) %>%
summarise(Events = n())
plot4 <- ggplot(target, aes(x = reorder(targtype1_txt, Events), y = Events)) +
geom_bar(stat = "identity",col = "black", fill = "darkblue") +
coord_flip() +
labs(x = "Target", y = "Events", title = "Target")
plot4
