week 14

The most topics dealt with the bills being passed so far are the terms: program, school, department, and education. These terms were used 354 times throughout the bills and help give a summary of each bill.

mydata <- read.csv("https://raw.githubusercontent.com/drkblake/Data/main/TNBills22_23.csv")

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

## Loading required package: tidyverse

## Warning: package 'tidyverse' was built under R version 4.3.3

## ── 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

## Warning: package 'tidytext' was built under R version 4.3.3

library(tidyverse)
library(tidytext)

tidy_text <- mydata %>% 
  unnest_tokens(word,description) %>% 
  count(word, sort = TRUE)

data("stop_words")
tidy_text <- tidy_text %>%
  anti_join(stop_words)

## Joining with `by = join_by(word)`

my_stopwords <- tibble(word = c("https",
                                "t.co",
                                "rt"))
tidy_text <- tidy_text %>% 
  anti_join(my_stopwords)

## Joining with `by = join_by(word)`

searchterms <- "program|school|department|education"
mydata$school <- ifelse(grepl(searchterms,
                             mydata$description,
                             ignore.case = TRUE),1,0)
sum(mydata$school)

## [1] 354