R Notebook

Kaitlin Kavlie PSYC-541

Lab #10: Dot Maps

library(leaflet)
library(tidyverse)
library(lubridate)
library(broom)
library(plotly)
library(DT)

1. I created a map of the shootings with dots on the map marking the location of each shooting.

shootings %>% 
  leaflet() %>% 
  addTiles() %>%
  addCircleMarkers(stroke = F, fillOpacity = .6, radius = 5, label = ~fatalities)

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

1A. I centered the map on the continental US by searching for the latitude and longitude of the center of the continental US, which are latitude 39° 57’ 52.00” N and longitude:-82° 59’ 49.69. So I calculated the decimal for the minutes of the latitude and the longitude. This calculated and rounded up into latitude 40.1 and longitude -83.1.

57/60

[1] 0.95

59/60

[1] 0.9833333

Then I used the code below to create a new map centered on the basis of the specific latitude and longitude coordinates calculated above.

shootings %>% 
  leaflet() %>% 
  addTiles() %>%
  addCircleMarkers(stroke = F, fillOpacity = .6, radius = 5, label = ~fatalities) %>%
  setView(lng = -83.1, lat = 40.1, zoom = 4) %>%
  addMarkers(lng = -83.1, lat = 40.1)

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

1B. Then I changed the size of the dots so that the more victims of a shooting, the larger the dot on the map. I did so by using the code chunk below.

shootings %>% 
  leaflet() %>% 
  addTiles() %>%
  addCircleMarkers(radius = ~log(total_victims))

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

2A. I found the median number of total victims and median number of fatalities by using the two code chunks below.

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

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

2B. Then I created a histogram of the number of shootings per year using the code chunk below.

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

NA

2C. Then I used the code below to create a heatmaps with add_histogram2dcontour() of the gender and race of the shooter.

shootings %>%
  drop_na(race) %>% 
  mutate(race = as_factor(race)) %>% 
  mutate(race = fct_collapse(race, White = c("white", "White"), Black = c("black", "Black"), Other = c("unclear", "other"))) %>%
  mutate(gender = fct_collapse(gender, Male = c("Male", "M"), Female = c("Female", "F"))) %>%
  plot_ly(x = ~race, y = ~gender) %>%
  add_histogram2dcontour()

Warning: Problem while computing `race = fct_collapse(...)`.
i Unknown levels in `f`: other

2D. I used the code below to create a scatterplot with plotly of the number of people injured by the number of fatalities in the shooting.

shootings %>% 
  plot_ly(x = ~fatalities, 
          y = ~injured) %>% 
  add_markers() 

NA

3. Lastly, I conducted a regression analysis testing the hypothesis that the number of shootings has increased over the years.

First, I set the data up by creating the data set num_per_year which focuses only on the number of shootings per year.

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

num_per_year

Then I ran analyses on the data using the code below and found that the p-value is less than .05, leading me to reject the null hypothesis. This means that there has been a statistically significant increase in the number of shootings each year.

shootings_per_year_model <- lm(n ~ year, data = num_per_year)
tidy(shootings_per_year_model)

glance(shootings_per_year_model)

NA

Lastly, I created a regression analysis scatter plot displaying the number of shootings that have occurred each year.

num_per_year %>% 
  plot_ly(x = ~year, 
          y = ~n, hoverinfo = "text", text = ~paste("Number of shootings per year: ", round(num_per_year, 1), "<br>", "Year: ", year)) %>% 
  add_markers(showlegend = F) %>%
add_lines(y = ~fitted(shootings_per_year_model)) %>%
  layout(title = "Number of shootings per year",
   xaxis = list(title = "Year"),
   yaxis = list(title = "Number of shootings"))