shootings.R

library(tidyverse)
library(ggbeeswarm)
library(gglabeller)
library(scales)

data <- read_csv("schoolshootingsdata FINAL - data.csv", 
  col_types = cols(date = col_date(format = "%m/%d/%Y")))

tidy.shooter.age <- gather(data, "shooter_i", "shooter.age", c("age_shooter", "shooter 2 age")) %>%
  filter(is.numeric(shooter.age))

p <- ggplot(tidy.shooter.age, aes(shooter.age)) + 
  geom_dotplot(binwidth=1) + 
  theme_minimal() + 
  ggtitle('Distribution of shooter age')
ggsave('shooter_age_histogram.pdf', plot=p, useDingbats=FALSE)

theeeeme <- theme_minimal() + theme(
  axis.text.y=element_blank(), 
  axis.ticks=element_blank(), 
  axis.line.y=element_blank(),
  panel.grid=element_blank())

ggplot(data, aes(date, 0, size=adjust)) +
  geom_beeswarm(method = "frowney", groupOnX=FALSE, dodge.width=0.5) +
  scale_size_area(max_size = 20) +
  scale_x_date(date_breaks="1 year", labels=date_format("%Y")) +
  theeeeme
ggsave('shooting_dots_timeline.pdf', width=50, height=5, limitsize=FALSE)


ggplot(data, aes(date, 0, size=adjust)) +
  geom_beeswarm(method = "frowney", groupOnX=FALSE, dodge.width=0.5, alpha=0.5) +
  scale_size_area(max_size = 20) +
  scale_x_date(date_breaks="1 year", labels=date_format("%Y"), limits=as.Date(c('1998-04-01', '2023-04-01'))) +
  scale_y_continuous(limits=c(-20, 10)) +
  coord_polar(direction = -1) +
  theeeeme
ggsave('shooting_timeline.pdf', width=40, height=40)

years <- c("1999", "2000", "2001", "2002", "2003", "2004", "2005", "2006", "2007", "2008", "2009", "2010", "2011", "2012", "2013", "2014", "2015", "2016", "2017", "2018")
startvalues <- c(0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0)
start.frame <- data.frame(year=years, sum=startvalues, dayofyear=startvalues, school_name=rep(list(""), 19), stringsAsFactors=FALSE)
cumulative <- data %>% 
  mutate(year = format(date, '%Y'), dayofyear=as.numeric(format(date, '%j'))) %>% 
  group_by(year) %>% 
  arrange(date) %>% 
  mutate(sum=cumsum(adjust)) %>%
  ungroup() %>%
  select(sum, dayofyear, year, school_name) %>%
  rbind(start.frame)

endofyear <- cumulative %>%
  group_by(year) %>%
  summarise(sum=max(sum)) %>%
  filter(year!=2018) %>%
  mutate(dayofyear=365, school_name="end of year")

cumulative %>% rbind(endofyear) %>% rbind(start.frame) %>% arrange(year) %>%
  ggplot(aes(dayofyear, sum, group=year)) + 
  geom_step(alpha=0.4) + 
  geom_text(data=endofyear, aes(dayofyear, sum, label=year), hjust = 0, vjust = 0.5) +
  geom_text()
  theme_minimal() +
  ggtitle("Cumulative number of students in school")

ggsave('cumulative_adjust.pdf')


cumulative.casualties <- data %>% 
  mutate(year = format(date, '%Y'), dayofyear=as.numeric(format(date, '%j'))) %>% 
  group_by(year) %>% 
  arrange(date) %>% 
  mutate(sum=cumsum(ifelse(is.na(casualties), 0, casualties))) %>%
  ungroup() %>%
  select(sum, dayofyear, year) %>%
  rbind(start.frame)

endofyear.casualties <- cumulative.casualties %>%
  group_by(year) %>%
  summarise(sum=max(sum)) %>%
  filter(year!=2018) %>%
  mutate(dayofyear=365)

cumulative.casualties %>% rbind(endofyear.casualties) %>% rbind(start.frame) %>% arrange(year) %>%
  ggplot(aes(dayofyear, sum, group=year)) + 
  geom_step(alpha=0.4) + 
  geom_text(data=endofyear.casualties, aes(dayofyear, sum, label=year), hjust = 0, vjust = 0.5) +
  theme_minimal() +
  ggtitle("Cumulative causualties")

ggsave('cumulative_causalties.pdf')

cumulative.count <- data %>% 
  mutate(year = format(date, '%Y'), dayofyear=as.numeric(format(date, '%j')), one=1) %>% 
  group_by(year) %>% 
  arrange(date) %>% 
  mutate(sum=cumsum(one)) %>%
  ungroup() %>%
  select(sum, dayofyear, year) %>%
  rbind(start.frame)

endofyear.count <- cumulative.count %>%
  group_by(year) %>%
  summarise(sum=max(sum)) %>%
  filter(year!=2018) %>%
  mutate(dayofyear=365)

cumulative.count %>% rbind(endofyear.count) %>% rbind(start.frame) %>% arrange(year) %>%
  ggplot(aes(dayofyear, sum, group=year)) + 
  geom_step(alpha=0.4) + 
  geom_text(data=endofyear.count, aes(dayofyear, sum, label=year), hjust = 0, vjust = 0.5) +
  theme_minimal() +
  ggtitle("Cumulative count")

ggsave('cumulative_count.pdf')

data %>%
  mutate(year = format(date, '%Y')) %>%
  ggplot(aes(year)) + geom_bar()
ggsave('years.pdf')