R Notebook

library(leaflet)
library(tidyverse)
library(lubridate)
library(htmltools)
library(rtweet)
library(readxl)
library(broom)
library(plotly)
library(DT)
library(dplyr)

shootings %>%
  leaflet() %>%
  addTiles() %>%
  setView(lng = -98.5795, lat = 39.8283, zoom = 4) %>%
  addCircleMarkers(radius = ~log(total_victims))

Assuming "longitude" and "latitude" are longitude and latitude, respectively

This is a general overview map of shootings in the U.S.

shootings %>% 
  summarize(median_total_victims = median(total_victims))

This is the mean of total victims.

shootings %>% 
  summarize(median_fatalities = median(fatalities))

This is the mean of fatalaties.

shootings %>% 
  mutate(case = as_factor(case)) %>% 
  mutate(case = fct_collapse(case)) %>% 
  count(case)

This collapses variables and shows a table of how many shootings each place had.

shootings %>% 
  plot_ly(x = ~year) %>% 
  add_histogram(nbinsx = 40)

This histogram shows the number of shootings over the years.

shootings %>% 
  mutate(race = as_factor(race)) %>% 
  mutate(race = fct_collapse(race,
             Unknown = c("-", "Other", "unclear"))) %>%
  count(race)

Another collapse of variables and table showing shootings per race.

shootings %>%
  mutate(gender = as_factor(gender)) %>% 
  mutate(gender = fct_collapse(gender,
             Unknown = c("-", "Male & Female"))) %>%
  count(gender)

Another collapse of variables and table showing shooters as per thier gender.

shootings %>%
  plot_ly(x = ~gender, y = ~race) %>%
  add_histogram2dcontour()

This is a heat map showing the race and gender of the shooters.

shootings %>% 
  mutate(gender = as_factor(gender)) %>% 
  mutate(gender = fct_collapse(gender)) %>%
  count(gender)

shootings %>%
  mutate(age_of_shooter = as_factor(age_of_shooter)) %>% 
  mutate(age_of_shooter = fct_collapse(age_of_shooter)) %>%
  count(age_of_shooter)

shootings %>%
  plot_ly(x = ~gender, y = ~age_of_shooter) %>%
  add_histogram2dcontour()

This is a heat map that shows the gender and age.

shootings %>% 
  plot_ly(x = ~injured, 
          y = ~fatalities,
           hoverinfo = "text",
          text = ~paste("Fatalities per shooting:")) %>%
  add_markers(showlegend = F) %>%
layout(title = "Number of fatalities per shooting by year",
   xaxis = list(title = "Number injured"),
   yaxis = list(title = "Number of fatalities per shooting"))

This scatterplot shows the number of fatalities by number injured.

num_per_year <- shootings %>% 
  filter(fatalities > 3) %>% 
  count(year) %>% 
  filter(year < 2019)

num_per_year

This is setting up a regression.

fatalities_per_incident_model2 <- lm(fatalities ~ year, data = shootings)

fatalities_per_incident_model2

Call:
lm(formula = fatalities ~ year, data = shootings)

Coefficients:
(Intercept)         year  
 10.0315821   -0.0009737  

This is a print out of the model.

tidy(fatalities_per_incident_model2)

glance(fatalities_per_incident_model2)

These are the stats for the regression.

shootings %>% 
  plot_ly(x = ~year, 
          y = ~fatalities) %>% 
  add_markers() %>%
  add_lines(y = ~fitted(fatalities_per_incident_model2))

This scatterplot shows the fatalities over the years due to the shootings.