# Load packages
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 3.4.4 ✔ 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("tidytext")) install.packages("tidytext")
## Loading required package: tidytext
library(tidyverse)
library(tidytext)
mydata <- read.csv("https://raw.githubusercontent.com/drkblake/Data/main/TNBills22_23.csv")
# Extract individual words to a "tidytext" data frame
tidy_text <- mydata %>%
unnest_tokens(word,description) %>%
count(word, sort = TRUE)
# Delete standard stop words
data("stop_words")
tidy_text <- tidy_text %>%
anti_join(stop_words)
## Joining with `by = join_by(word)`
# Delete custom stop words
my_stopwords <- tibble(word = c("https",
"t.co",
"rt"))
tidy_text <- tidy_text %>%
anti_join(my_stopwords)
## Joining with `by = join_by(word)`
searchterms <- "assemble|right|sentence|charges"
mydata$title <- ifelse(grepl(searchterms,
mydata$description,
ignore.case = TRUE),1,0)
sum(mydata$title)
## [1] 71
From this data it seems that the most common topic brought up is school related. Another topic that also seems to be brought up a lot of children.