# Loading required packages
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.9
## ✔ tidyr 1.2.0 ✔ stringr 1.4.1
## ✔ readr 2.1.2 ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
# Loading the dataset
crimes<-read_csv("crimes_uk.csv")
## Rows: 1267826 Columns: 15
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (14): cja, type, sex, ageband, agegroup, courttype, offencetype, offence...
## dbl (1): year
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
EDA
Top 10 administrative units with highest number of crimes
crimes %>%
count(cja) %>%
mutate(cja = fct_reorder(cja, n)) %>%
slice_max(cja, n = 10) %>%
ggplot(aes(cja, n, fill = cja)) +
geom_col() +
scale_fill_brewer(palette = "Paired") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 5) +
theme(text = element_text(size = 18), legend.position = "none") +
labs(y = "Number of crimes", x = NULL) +
coord_flip()
Crime number by year and administrative unit (top 10 only)
crimes %>%
count(year, cja) %>%
mutate(cja = fct_reorder(cja, n)) %>%
slice_max(cja, n = 50) %>%
ggplot(aes(cja, n, fill = cja)) +
geom_col() +
scale_fill_brewer(palette = "Paired") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of crimes", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Crime number by year and type of perpetrator
crimes %>%
count(year, type) %>%
mutate(type = fct_reorder(type, n)) %>%
ggplot(aes(type, log(n), fill = type)) +
geom_col() +
scale_fill_brewer(palette = "Dark2") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of crimes (log scale)", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Crime number by year and sex of perpetrator
crimes %>%
mutate(sex = fct_recode(sex, "Other" = "Other (companies, public bodies, etc)")) %>%
count(year, sex) %>%
mutate(sex = fct_reorder(sex, n)) %>%
ggplot(aes(sex, log(n), fill = sex)) +
geom_col() +
scale_fill_brewer(palette = "Dark2") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of crimes (log scale)", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Crime number by year and age band
crimes %>%
drop_na(ageband) %>%
count(year, ageband) %>%
mutate(ageband = fct_reorder(ageband, n)) %>%
ggplot(aes(ageband, log(n), fill = ageband)) +
geom_col() +
scale_fill_brewer(palette = "Dark2") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of crimes (log scale)", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Crime number by year and age group
crimes %>%
drop_na(agegroup) %>%
count(year, agegroup) %>%
mutate(agegroup = fct_relevel(agegroup, "10-11", "12-14", "15-17", "18-20", "21-24", "25-29", "30-39",
"40-49", "50-59", "60+")) %>%
ggplot(aes(agegroup, n, fill = agegroup)) +
geom_col() +
scale_fill_brewer(palette = "Paired") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of crimes", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Case number by year and court type
crimes %>%
drop_na(courttype) %>%
count(year, courttype) %>%
mutate(courttype = fct_reorder(courttype, n)) %>%
ggplot(aes(courttype, n, fill = courttype)) +
geom_col() +
scale_fill_brewer(palette = "Dark2") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of cases", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Crime number by year and offence type
crimes %>%
drop_na(offencetype) %>%
count(year, offencetype) %>%
mutate(offencetype = fct_reorder(offencetype, n)) %>%
ggplot(aes(offencetype, n, fill = offencetype)) +
geom_col() +
scale_fill_brewer(palette = "Dark2") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of crimes", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Crime number by year and offence group
crimes %>%
drop_na(offencegroup) %>%
count(year, offencegroup) %>%
mutate(offencegroup = fct_reorder(offencegroup, n)) %>%
ggplot(aes(offencegroup, n, fill = offencegroup)) +
geom_col() +
scale_fill_brewer(palette = "Paired") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of crimes", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Crime number by year and offence (top 10 only)
crimes %>%
drop_na(offence) %>%
count(year, offence) %>%
mutate(offence = fct_reorder(offence, n)) %>%
slice_max(offence, n = 50) %>%
ggplot(aes(offence, n, fill = offence)) +
geom_col() +
scale_fill_brewer(palette = "Paired") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none",
axis.text.x = element_blank(),
axis.ticks.x = element_blank()) +
labs(y = NULL, x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Number of cases by year and verdict
crimes %>%
drop_na(found_guilty) %>%
count(year, found_guilty) %>%
mutate(found_guilty = fct_reorder(found_guilty, n)) %>%
ggplot(aes(found_guilty, n, fill = found_guilty)) +
geom_col() +
scale_fill_brewer(palette = "Dark2") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of cases", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Number of cases by year and sentence
crimes %>%
drop_na(sentenced) %>%
count(year, sentenced) %>%
mutate(sentenced = fct_reorder(sentenced, n)) %>%
ggplot(aes(sentenced, n, fill = sentenced)) +
geom_col() +
scale_fill_brewer(palette = "Dark2") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of cases", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Number of cases by year and detailed sentence (top 10 only)
crimes %>%
drop_na(detailed_sentence) %>%
filter(!detailed_sentence == "Other") %>%
count(year, detailed_sentence) %>%
mutate(detailed_sentence = fct_reorder(detailed_sentence, n)) %>%
slice_max(detailed_sentence, n = 50) %>%
ggplot(aes(detailed_sentence, log(n), fill = detailed_sentence)) +
geom_col() +
scale_fill_brewer(palette = "Paired") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of cases (log scale)", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
Number of cases by year and sentence length (top 10 only)
crimes %>%
drop_na(sentencelength) %>%
count(year, sentencelength) %>%
mutate(sentencelength = fct_reorder(sentencelength, n)) %>%
slice_max(sentencelength, n = 50) %>%
ggplot(aes(sentencelength, n, fill = sentencelength)) +
geom_col() +
scale_fill_brewer(palette = "Paired") +
geom_text(aes(label = n), position = position_stack(vjust = 0.5), size = 3.5) +
theme(text = element_text(size = 14), legend.position = "none") +
labs(y = "Number of cases", x = NULL) +
facet_wrap(~year, ncol = 3) +
coord_flip()
