DATA101Final

# 1. **First, read the 1976-2020 Senate election results data into a dataframe in R. 
# You can either download the file through Canvas, or use 
# [this link](https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/PEJ5QU) 
# (1976-2020-senate).**

setwd(dir = "/Users/ade/Documents/Education/Dropbox/DATA101//DATA/RAW")
library(readr)
senate_election_results <- read_csv("Documents/Education/Dropbox/DATA101/DATA/RAW/1976-2020-senate.csv")
View(X1976_2020_senate)

# 2. **Out first step to clean this data is to keep only the 
# columns with information we care about. Keep only the variables 
#`year`, `state`, `state_po`, `stage`, `candidate`, `party_simplified`, 
# `candidatevotes`, `totalvotes`.**

senate_data_cleaned <- senate_election_results%>%
  select("year", "state", "state_po", "stage", "candidate", "party_simplified",
         "candidatevotes", "totalvotes")

# 3. **Next, we're going to remove rows with some incomplete data. 
# Remove any rows that have missing data in the "candidate"
# or "party_simplified" columns.**

senate_data_cleaned <- senate_data_cleaned%>%
na.omit(candidate, party_simplified)

# 4. **Next, create a new variable, "party3" which recodes the "party_simplified" 
# column into "D" for Democrats, "R" for Republicans, and "I" for all other parties. 
# (Hint: you may want to first create this column so that all rows equal "I". 
# Then use the ifelse() function to recode to "R" if the row represents a Republican
# and otherwise stays equal to its current value.)**

senate_data_cleaned <- senate_data_cleaned%>%
  mutate(party3 = recode(party_simplified, "DEMOCRAT" = "D", "REPUBLICAN" = "R", "LIBERTARIAN" = "I", "OTHER" = "I"))
  

# 5. **How many Democrats are in this dataset? How many Republicans? 
# How many Independents?**

senate_data_cleaned%>%
  count(party3, "R", "D", "I")

# 810 Democrats, 802 Republicans, 1594 Independents

# 6. **Now let's look at the 2-party vote in these data. 
# First, remove the independent candidates from the data. 
# Next, remove all the rows where "stage" is not equal to "gen". 
# This ensures that we only get results from the general election.**

independent_data <- senate_data_cleaned%>%
  filter(party3 == "I")

twoparty_data <- senate_data_cleaned%>%
  filter(party3!= "I", stage == "gen")

# 7. **How many races were contested between more than two candidates?
# Which state had the most of these races?**
  
contested_races <- senate_data_cleaned%>%
  group_by(year, state)%>%
  count(year)
  
morethantwo_candidates <- contested_races%>%
  filter(n > 2)

# 580 races were contested by more than two candidates. 
# Louisiana had the most of these races.

# 8. **For Democratic and Republican candidates create a figure that displays 
# the year on the x-axis and each candidate's percent of the vote on the y-axis. 
# Be sure to color code each candidate by their respective party. 
# Add two lines--one for each party--that represents the trend in that 
# parties' support over time.**

candidate_perc_vote <- twoparty_data%>%
  mutate(candidate_perc = candidatevotes/totalvotes)

ggplot(candidate_perc_vote, aes(year, candidate_perc, color = party3))+
  geom_point(alpha = .65)+
  geom_smooth(method=lm)+
  theme_light()+
  ggtitle("2012 Senate Election Results")+
  xlab("Year")+
  ylab("Percent of Vote")

# 9. **Let's take a look at the races from 2012. Filter your dataset so that it 
# only contains the results for 2012, and only the columns `year`, `state`, 
# `party3`, and the candidate percent you calculated in the previous question. 
# Reshape this data so that there is only one row per state, and two columns 
# that represent the percent of the vote won by the Republican candidate and the 
# percent of the vote won by the Democratic candidate. 
# Note that you will not have 50 rows because not all states have a Senate 
# election in an election year.**

candidates_2012 <- candidate_perc_vote%>%
  filter(year == 2012)%>%
  select(year, state, party3, candidate_perc)

perc_2012 <- candidates_2012%>%
  pivot_wider(names_from = party3, values_from = candidate_perc)


# 10. **Create a variable "demwin" that records if the Democrat received a 
# higher vote share than the Republican in each race in 2012.**

perc_2012 <- perc_2012%>%
  mutate(demwin = D > R)

# 11. **Create a variable "demdiff" that records the difference between the 
# Democratic percent and Republican percent of the vote in each race in 2012.**

perc_2012 <- perc_2012%>%
  mutate(demdiff = D - R)

# 12. **Next, we're going to do some analysis to map this data. Load in the 
# state-level mapping data that we've worked with from the package `mapdata`**


install.packages("maps")
install.packages("mapdata")
library(mapdata)
library(maps)

states <- map_data("state")%>%
  select(-subregion)
  

# 13. **Join the 2012 Senate election data to this mapping data. 
# Be cautious about the format of the state names!**

perc_2012 <- perc_2012%>%
  mutate(state = tolower(state))

state_voter_data <- perc_2012%>%
  full_join(states, by = c("state" = "region"))

# 14. **Create a map that shows the winner of each Senate contest in 2012, with 
# Democrats in blue and Republicans in red. If there was no Senate contest in a 
# state ([or if a party other than Democrats or Republicans won the seat]
# (https://i.guim.co.uk/img/media/58adf5bbdd8ad0ba8a6c70ab7908178cbb5b1a0e/48_557_3862_2318/master/3862.jpg?width=445&quality=45&auto=format&fit=max&dpr=2&s=d0576b59344d8961e72dd679e52b4172)), leave the state blank. **

ggplot(state_voter_data)+
  geom_polygon(aes(x = long, y = lat, group = group, fill = demwin), col = "black", lwd = 0.25)+
  coord_quickmap()+
  theme_void()+
  ggtitle("2012 Senate Election Results")+
  labs(fill = "Dem Won?")


# 15. **Create a map that shades each state by the Democratic vote difference you 
# created above. Again, If there was no Senate contest in a state 
# (or if a party other than Democrats or Republicans won the seat), leave the state blank.**

ggplot(state_voter_data)+
  geom_polygon(aes(x = long, y = lat, group = group, fill = demdiff), col = "black", lwd = 0.25)+
  scale_fill_gradient(low = "red", high = "blue")+
  coord_quickmap()+
  theme_void()+
  ggtitle("2012 Senate Election Results")+
  labs(fill = "Dem Win Diff")