if (!require("tidyverse"))
  install.packages("tidyverse")

## Loading required package: tidyverse

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

if (!require("foreign"))
  install.packages("foreign")

## Loading required package: foreign

if (!require("sf"))
  install.packages("sf")

## Loading required package: sf
## Linking to GEOS 3.12.1, GDAL 3.8.4, PROJ 9.3.1; sf_use_s2() is TRUE

if (!require("scales"))
  install.packages("scales")

## Loading required package: scales
## 
## Attaching package: 'scales'
## 
## The following object is masked from 'package:purrr':
## 
##     discard
## 
## The following object is masked from 'package:readr':
## 
##     col_factor

if (!require("mapview"))
  install.packages("mapview")

## Loading required package: mapview

if (!require("leaflet"))
  install.packages("leaflet")

## Loading required package: leaflet

if (!require("leaflet.extras2"))
  install.packages("leaflet.extras2")

## Loading required package: leaflet.extras2

library(tidyverse)
library(foreign)
library(sf)
library(scales)
library(mapview)
library(leaflet)
library(leafpop)

# Read the first data file and use it to create
# an "AllData" dataframe.

AddData <- read.dbf("10162024.dbf")
AllData <- AddData

# Add each subsequent day's file name to this list,
# then run

datafiles <- c("10172024.dbf",
               "10182024.dbf",
               "10192024.dbf",
               "10212024.dbf",
               "10222024.dbf",
               "10232024.dbf")

# This "for loop" adds each listed datafile
# to the AllData dataframe

for (x in datafiles) {
  AddData <- read.dbf(x, as.is = FALSE)
  AllData <- rbind(AllData, AddData)
}

# Save AllData file as .csv
write_csv(AllData,"EarlyVoterData2024.csv")

# Get total votes so far

TotalVotes <- nrow(AllData)
PctVotes <- round((TotalVotes / 224746)*100, digits = 0)

### Make a chart showing vote totals by day ###

# Aggregate data by day
# and do some formatting

VotesByDay <- AllData %>% 
  group_by(VOTEDDATE) %>% 
  summarize(Votes = n()) %>% 
  rename(Date = VOTEDDATE) %>% 
  mutate(Date = (str_remove(Date,"2024-")))

# Make the chart

chart = ggplot(data = VotesByDay,
               aes(x = Date,
                   y = Votes))+
  geom_bar(stat="identity", fill = "#41B3A2") +
  geom_text(aes(label=comma(Votes)),
            vjust=1.6,
            color="black",
            size=3.5)+
  theme(
    axis.title.x = element_blank(),
    axis.ticks.y = element_blank(),
    axis.title.y = element_blank(),
    axis.text.y = element_blank(),
    panel.background = element_blank())

# Show the chart

chart

### Make a precinct-level map of early voting turnout ***

# Aggregate early voting data by precinct

PrecinctData <- AllData %>% 
  group_by(PCT_NBR) %>% 
  summarize(Votes = n()) %>% 
  rename(Precinct = PCT_NBR)

# Download and unzip a precinct map to pair with the vote data

download.file("https://github.com/drkblake/Data/raw/main/Voting_Precincts_5_31_24.zip","TNVotingPrecincts.zip")

unzip("TNVotingPrecincts.zip")

# Read the unzipped data into an All_Precincts dataframe

All_Precincts <- read_sf("Voting_Precincts_5_31_24.shp")

# Filter for RuCo precincts, 
# strip dash from precinct numbers,
# and do some renaming

County_Precincts <- All_Precincts %>%
  filter(COUNTY == 149) %>%
  rename(Precinct = NEWVOTINGP) %>% 
  mutate(Precinct = (str_remove(Precinct,"-")))

# Use left_join() function to join the data and map file
# using the "Precinct" variable as the joining key

MapData <-  left_join(PrecinctData, County_Precincts, by = "Precinct")

# Use left_join() again, this time to add
# voter registration totals per precinct
# This file was in the .zip file along with
# the daily .dbf files

RegData <- read_csv("RegVotersRuCo.csv") %>% 
  mutate(Precinct = as.character(Precinct))

## Rows: 33 Columns: 2
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (2): Precinct, RegVoters
## 
## 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.

MapData <- left_join(MapData, RegData, by = "Precinct")

# Calculate and add Percent column
# Then select columns to keep
# and put them in a MapData dataframe

MapData <- MapData %>% 
  mutate(Percent = round((Votes/RegVoters)*100), digits = 0) %>%
  rename(Voters = RegVoters) %>% 
  select(Precinct, Votes, Voters, Percent, geometry)

# Make a mappable MapData_sf file out of MapData

MapData_sf <- st_as_sf(MapData)

# Make the map

Map <- mapview(
  MapData_sf,
  zcol = "Percent",
  layer.name = "Pct. early voted",
  popup = popupTable(
    MapData_sf,
    feature.id = FALSE,
    row.numbers = FALSE,
    zcol = c(
      "Precinct",
      "Votes",
      "Voters",
      "Percent"
    )
  )
)

# Show the map

Map

# Calculate some additional voting stats

MinTurnout <- min(MapData$Percent)
MaxTurnout <- max(MapData$Percent)
MedianTurnout <- median(MapData$Percent)
MeanTurnout <- mean(MapData$Percent)