R Notebook

library(tidyverse)

── Attaching packages ──────────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.3.0 ──
✓ ggplot2 3.3.1     ✓ purrr   0.3.4
✓ tibble  3.0.1     ✓ dplyr   1.0.0
✓ tidyr   1.1.0     ✓ stringr 1.4.0
✓ readr   1.3.1     ✓ forcats 0.5.0
── Conflicts ─────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(leaflet)
library(sf)

Linking to GEOS 3.5.1, GDAL 2.2.2, PROJ 4.9.2

library(readxl)
library(DT)
library(plotly)

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

library(broom)
library(tidycensus)

senate_counties <- read_xlsx("Statewide Results.xlsx", sheet = 1)

New names:
* `` -> ...2
* `` -> ...3
* `` -> ...4
* `` -> ...5

This loads the data.

senate_counties <- read_xlsx("Statewide Results.xlsx", sheet = 1, range = "B7:E63")

This loads the data.

glimpse(senate_counties)

Rows: 56
Columns: 4
$ County                             <chr> "Beaverhead", "Big Horn", "Blaine", "Broadwater", "Carbon", "Carter", "Cascade", "Chout…
$ `JON TESTER\r\nDemocrat`           <dbl> 1876, 3027, 1961, 1071, 2680, 128, 17435, 1275, 1942, 281, 1233, 2892, 281, 1964, 19652…
$ `MATT ROSENDALE\r\nRepublican`     <dbl> 2866, 1558, 982, 2086, 3209, 602, 15566, 1312, 2762, 631, 2700, 1208, 951, 3640, 26759,…
$ `RICK BRECKENRIDGE\r\nLibertarian` <dbl> 155, 91, 76, 104, 178, 22, 1008, 70, 179, 29, 140, 136, 57, 189, 1349, 1434, 30, 89, 21…

This shows a preview of data.

senate_counties <- senate_counties %>% 
  rename(Republican = "MATT ROSENDALE\r\nRepublican") %>% 
  rename(Democrat = "JON TESTER\r\nDemocrat") %>% 
  rename(Libertarian = "RICK BRECKENRIDGE\r\nLibertarian")

senate_counties <- senate_counties %>% 
  mutate(total_votes = Republican + Democrat + Libertarian) %>% 
  mutate(Repub_advantage = Republican/total_votes - Democrat/total_votes) %>% 
  mutate(Repub_advantage = round(Repub_advantage*100, 1))
  senate_counties %>% 
  arrange(-Repub_advantage)

This is a table showing the the votes for the candidates by county a long with the republican advantage of each county.

mt_counties <- get_acs(geography = "county",
                       variables = "B01003_001",
                       state = "MT",
                       geometry = TRUE) 

Getting data from the 2014-2018 5-year ACS
Downloading feature geometry from the Census website.  To cache shapefiles for use in future sessions, set `options(tigris_use_cache = TRUE)`.
Using FIPS code '30' for state 'MT'

This gets data for state.

senate_counties[25, "County"] <- "Lewis and Clark"              # Changes  "&" "and"

mt_counties <- mt_counties %>% 
  mutate(County = gsub(" County, Montana", "", NAME)) %>%      # Removes unnecessary words
  rename(Population = estimate)                                # Renames the 'estimate' to 'Population'

This is just replacing and with & from two mismatched titles.

senate_election <- mt_counties %>% 
  full_join(senate_counties)

Joining, by = "County"

This joins the data from mt counties with the senate race data.

senate_election %>%
  as_tibble() %>% 
  select(County, Population, Democrat, Republican, Libertarian, total_votes, Repub_advantage) %>% 
  datatable()

This is a table showing the counties with thier population and the votes per candidate with the republican advantage.

vote_colors <- colorNumeric(palette = "viridis", domain = senate_election$Repub_advantage)

senate_election %>%
  leaflet() %>% 
  addTiles() %>%
  addPolygons(weight = 1,
              fillColor = ~vote_colors(Repub_advantage), 
              label = ~paste0(County, ", Republican advantage = ", Repub_advantage),
              highlight = highlightOptions(weight = 2)) %>% 
  setView(-110, 47, zoom = 6) %>% 
  addLegend(pal = vote_colors, values = ~Repub_advantage)

sf layer has inconsistent datum (+proj=longlat +datum=NAD83 +no_defs ).
Need '+proj=longlat +datum=WGS84'

This shows the republican advantage by county. The lighter or more toward yellow indicates a stronger advantage.

senate_election %>%
  plot_ly(x = ~Population, 
          y = ~Repub_advantage,
          hoverinfo = "text", 
          text = ~paste("County:", 
                        County, "<br>", 
                        "Population: ", Population, "<br>", 
                        "Republican advantage: ", Repub_advantage)) %>% 
  add_markers(marker = list(opacity = 0.7)) %>%
  layout(title = "Predicting Republican Vote Advantage from Population, by County",
         xaxis = list(title = "County population"),
         yaxis = list(title = "Republican vote advantage"))

`arrange_()` is deprecated as of dplyr 0.7.0.
Please use `arrange()` instead.
See vignette('programming') for more help
This warning is displayed once every 8 hours.
Call `lifecycle::last_warnings()` to see where this warning was generated.

This is a plotly graph idicating a negative correllation.

pop_model <- lm(Repub_advantage ~ Population, data = senate_election)

This is a linear regression.

summary(pop_model)

Call:
lm(formula = Repub_advantage ~ Population, data = senate_election)

Residuals:
    Min      1Q  Median      3Q     Max 
-71.228 -12.013   3.247  15.782  47.948 

Coefficients:
              Estimate Std. Error t value Pr(>|t|)    
(Intercept) 24.2809050  4.0835813   5.946 2.08e-07 ***
Population  -0.0003761  0.0001100  -3.418  0.00121 ** 
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 26.44 on 54 degrees of freedom
Multiple R-squared:  0.1779,    Adjusted R-squared:  0.1626 
F-statistic: 11.68 on 1 and 54 DF,  p-value: 0.001207

This is a summary of the regression results.

tidy(pop_model)

glance(pop_model)

This shows the information in a cleaner way.

senate_election %>%
  plot_ly(x = ~Population, 
          y = ~Repub_advantage,
          hoverinfo = "text", 
          text = ~paste("County:", 
                        County, "<br>", 
                        "Population: ", Population, "<br>", 
                        "Republican advantage: ", Repub_advantage)) %>% 
  add_markers(showlegend = F, marker = list(opacity = 0.7)) %>%
  layout(title = "Predicting Republican Vote Advantage from Population, by County",
         xaxis = list(title = "County population"),
         yaxis = list(title = "Republican vote advantage")) %>%
  add_lines(y = ~fitted(pop_model))

This predicts the republican vote advantage from population and by county.

senate_election <- senate_election %>% 
  mutate(Longitude = as_tibble(st_coordinates(st_centroid(senate_election$geometry)))$X) %>% 
  mutate(Latitude = as_tibble(st_coordinates(st_centroid(senate_election$geometry)))$Y)

st_centroid does not give correct centroids for longitude/latitude datast_centroid does not give correct centroids for longitude/latitude data

senate_election %>%
  leaflet() %>% 
  addTiles() %>%
  addPolygons(weight = 1) %>% 
  setView(-110, 47, zoom = 6) %>% 
addCircleMarkers(~Longitude, ~Latitude)

sf layer has inconsistent datum (+proj=longlat +datum=NAD83 +no_defs ).
Need '+proj=longlat +datum=WGS84'

This is just another graph showing the center of counties.

senate_election %>%
  plot_ly(x = ~Longitude, y = ~Repub_advantage) %>% 
  add_markers()

This is a plotly graph of the longitute and republican vote indicating a positive correlation that the further east the more votes for republican.

longitude_lm <- lm(Repub_advantage ~ Longitude, data = senate_election)
tidy(longitude_lm)

glance(longitude_lm)

This is a regression predicting republican vote from longitude.

senate_election %>% 
  plot_ly(x = ~Longitude, 
          y = ~Repub_advantage,
          hoverinfo = "text", 
          text = ~paste("County:", County, "<br>", "Longitude: ", Longitude, "<br>", "Republican advantage: ", Repub_advantage)) %>% 
  add_markers(marker = list(opacity = 0.7), showlegend = F) %>%
  layout(title = "Predicting Republican Vote Advantage from Longitude, by County",
         xaxis = list(title = "County longitude"),
         yaxis = list(title = "Republican vote advantage")) %>% 
  add_lines(y = ~fitted(longitude_lm))

This is a plotly graph predicting the republican vote advantage from longitude, by county.

multiple_lm <- lm(Repub_advantage ~ Population + Longitude, data = senate_election)
tidy(multiple_lm)

glance(multiple_lm)

This is a multiple regression, predicting the Republican advantage from both Population and Longitude at the same time.

senate_election %>% 
  plot_ly(x = ~Longitude, y = ~Population, z = ~Repub_advantage, 
          text = ~County, hoverinfo = "text") %>% 
  add_markers(opacity = .7, showlegend = F)

This is a 3D scatterplot showing the republican advantage, population, and votes per longitudinal data.