reuning

library(tidyverse)
library(ggpubr)
library(ggrepel)
data <- read_csv("nyt_pundits.csv")

sum_data <- data |> group_by(Pundit) |>
  summarize(Avg_Elect=mean(Electable), 
         Avg_Excit=mean(Exciting))

ggplot(data, aes(x=Electable, y=Exciting, color=Candidate)) + 

reuning

library(tidyverse)

## Data from: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi%3A10.7910%2FDVN%2F42MVDX
df <- read_csv("1976-2020-president.csv")

cook_pvi <- df |> filter(party_simplified%in% c("DEMOCRAT", "REPUBLICAN")) |> 
  select(year, state, party_simplified, candidatevotes) |> 
  pivot_wider(id_cols=c(year,state), 
              names_from = party_simplified, 
              values_from=candidatevotes, values_fn=sum) |> 

reuning

setwd("~/Downloads/")
library(ggplot)
library(ggrepel)
library(data.table)
df <- fread("https://data.cdc.gov/resource/8xkx-amqh.csv")
df_election <- fread("countypres_2000-2020.csv") # https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/42MVDX
df_election <- df_election[year==2020 & party == "DEMOCRAT" & mode=="TOTAL"]
df_election[,prop:=100*candidatevotes/totalvotes]
df[,fips:=as.numeric(fips)]
all <- merge(df, df_election, by.x="fips",by.y="county_fips")

reuning

library(rvest)
library(data.table)
library(ggplot2)
library(ggrepel)

page <- read_html("https://www.nytimes.com/interactive/2020/11/03/us/elections/results-president.html")
links <- page %>% html_node(".e-state-list") %>% html_nodes("a") %>% html_attr("href")

get_data <- function(link){
  

reuning

N_all <- 1000
out <- numeric(N_all)
N <- 50

for(ii in 1:N_all){
  set.seed(ii)
  tmp <- round(rnorm(N, 50, 1.9), 0)
  tmp <- ((tmp[-1] - tmp[-N]))
  

reuning

library(rvest)
library(magrittr)

tmp <- read_html("https://results.thecaucuses.org/")
full <- tmp %>% html_nodes("ul.thead") %>% html_nodes("li") %>% html_text()
sub <- tmp %>% html_nodes("ul.sub-head") %>% html_nodes("li") %>% html_text()
full <- full[-1:-2]
sub <- sub[-1:-2]

counties <- tmp %>%  html_nodes('div.precinct-rows') 

reuning

library(rtweet)
library(data.table)
library(ggplot2)
library(stringr)
tweets <- as.data.table(get_timeline("PpollingNumbers", n=3200))

tweets <- tweets[is_retweet!=TRUE,]
tweets[,nat:=grepl("National", text, ignore.case = T) &
         grepl("Biden", text, ignore.case = T) & 
         !grepl("students", text, ignore.case=T) &

reuning

library(twitteR)
library(tm)
library(SentimentAnalysis)


setup_twitter_oauth(consumer_key = ,
                    consumer_secret =,
                    access_token = ,
                    access_secret = )

reuning

poll.conf <- function(url, inc.und=T){
  library(rvest)
  library(magrittr)
  library(stringr)
  
  poll.page <- html(url)
  
  poll.r <- poll.page %>% html_node("table[class='poll-results-table']") %>% html_table()
  poll.n <- poll.page %>% html_node("div[class='subpop-description']") %>% html_text()
  tmp <- gregexpr("\\d", poll.n)[[1]]