Created
February 5, 2019 15:37
-
-
Save slarge/3326deedfd3147726082881e8d59d984 to your computer and use it in GitHub Desktop.
Quick demo of fedregs package to explore northeastern US fisheries regulatoins
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
install.packages("fedregs") | |
library(fedregs) | |
library(dplyr) | |
library(ggplot2) | |
library(quanteda) | |
library(magick) | |
## For more info, check out the fedregs github repository: | |
## https://github.com/slarge/fedregs | |
## What does the text look like for northeastern US Fisheries regulations? | |
regs <- cfr_text(year = 2017, | |
title_number = 50, | |
chapter = 6, | |
part = 648, | |
#token = "ngrams", # uncomment for ngrams of length 2 | |
#n = 2, # uncomment for ngrams of length 2 | |
return_tidytext = TRUE, | |
verbose = FALSE) | |
## "stop words" are common that don't hold a lot of significance | |
stop_words <- data_frame(word = quanteda::stopwords("english")) | |
## Clean up words to try and find most meaningful words | |
clean_words <- regs %>% | |
tidyr::unnest() %>% | |
mutate(word = gsub("[[:punct:]]", "", word), # remove any remaining punctuation | |
word = gsub("^[[:digit:]]*", "", word)) %>% # remove digits (e.g., 1st, 1881a, 15th, etc) | |
anti_join(stop_words, by = "word") %>% # remove "stop words" | |
filter(is.na(as.numeric(word)), | |
!grepl("^m{0,4}(cm|cd|d?c{0,3})(xc|xl|l?x{0,3})(ix|iv|v?i{0,3})$", | |
word), # adios Roman Numerals | |
!grepl("\\b[a-z]{1}\\b", word), # get rid of one letter words | |
!grepl("\\bwww*.", word)) %>% # get rid of web addresses | |
mutate(word = quanteda::tokens(word), | |
word = as.character(quanteda::tokens_wordstem(word))) | |
## Count the 50 most frequent words | |
count_words <- clean_words %>% | |
group_by(word) %>% | |
summarise(n = n()) %>% | |
ungroup() %>% | |
arrange(-n) %>% | |
top_n(n = 50, wt = n) %>% | |
mutate(word = reorder(word, n)) | |
## Plot | |
gg <- ggplot(count_words, aes(n, word)) + | |
geom_segment(aes(xend=0, yend=word), size=3.5) + | |
labs(y = NULL, | |
x = "count", | |
title = "Code of Federal Regulations", | |
subtitle = "Title 50, Chapter VI, Part 648", | |
caption = sprintf("Data accessed on %s from:\n https://www.govinfo.gov/bulkdata/CFR/", | |
format(Sys.Date(), "%d %B %Y"))) + | |
theme(axis.text.x = element_text(angle = 45, hjust = 1), | |
legend.direction = "horizontal", | |
legend.position = "bottom", | |
text = element_text(size = 6)) + | |
theme_minimal() | |
## Save | |
fig <- image_graph(width=1016, height=573, res=72) | |
print(gg) | |
dev.off() | |
image_write(fig, "final.png") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment