fedreg-eo-r

library(rvest)
library(stringi)
library(pluralize) # devtools::install_github("hrbrmstr/pluralize")
library(hrbrthemes)
library(tidyverse)

#' Retrieve the Federal Register main EO page so we can get the links for each POTUS
pg <- read_html("https://www.federalregister.gov/executive-orders") 

#' Find the POTUS EO data nodes, excluding the one for "All"
html_nodes(pg, "ul.bulk-files") %>% 
  html_nodes(xpath = ".//li[span[a[contains(@href, 'json')]] and 
                            not(span[contains(., 'All')])]") -> potus_nodes

#' Turn the POTUS info into a data frame with the POTUS name and EO JSON link,
#' then retrieve the JSON file and make a data frame of individual data elements
data_frame(
  potus = html_nodes(potus_nodes, "span:nth-of-type(1)") %>% html_text(),
  eo_link = html_nodes(potus_nodes, "a[href *= 'json']") %>% 
    html_attr("href") %>% 
    sprintf("https://www.federalregister.gov%s", .)
) %>% 
  mutate(eo = map(eo_link, jsonlite::fromJSON)) %>% 
  mutate(eo = map(eo, "results")) %>% 
  unnest() -> eo_df

glimpse(eo_df)
## Observations: 887
## Variables: 16
## $ potus                  <chr> "Donald Trump", "Donald Trump", "Donald Trump", "Donald Trump", "Donald Trump", "D...
## $ eo_link                <chr> "https://www.federalregister.gov/documents/search.json?conditions%5Bcorrection%5D=...
## $ citation               <chr> "82 FR 8351", "82 FR 8657", "82 FR 8793", "82 FR 8799", "82 FR 8977", "82 FR 9333"...
## $ document_number        <chr> "2017-01799", "2017-02029", "2017-02095", "2017-02102", "2017-02281", "2017-02450"...
## $ end_page               <int> 8352, 8658, 8797, 8803, 8982, 9338, 9341, 9966, 10693, 10696, 10698, 10700, 12287,...
## $ executive_order_notes  <chr> NA, "See: EO 13807, August 15, 2017", NA, NA, "See: EO 13780, March 6, 2017", "Sup...
## $ executive_order_number <int> 13765, 13766, 13767, 13768, 13769, 13770, 13771, 13772, 13773, 13774, 13775, 13776...
## $ html_url               <chr> "https://www.federalregister.gov/documents/2017/01/24/2017-01799/minimizing-the-ec...
## $ pdf_url                <chr> "https://www.gpo.gov/fdsys/pkg/FR-2017-01-24/pdf/2017-01799.pdf", "https://www.gpo...
## $ publication_date       <chr> "2017-01-24", "2017-01-30", "2017-01-30", "2017-01-30", "2017-02-01", "2017-02-03"...
## $ signing_date           <chr> "2017-01-20", "2017-01-24", "2017-01-25", "2017-01-25", "2017-01-27", "2017-01-28"...
## $ start_page             <int> 8351, 8657, 8793, 8799, 8977, 9333, 9339, 9965, 10691, 10695, 10697, 10699, 12285,...
## $ title                  <chr> "Minimizing the Economic Burden of the Patient Protection and Affordable Care Act ...
## $ full_text_xml_url      <chr> "https://www.federalregister.gov/documents/full_text/xml/2017/01/24/2017-01799.xml...
## $ body_html_url          <chr> "https://www.federalregister.gov/documents/full_text/html/2017/01/24/2017-01799.ht...
## $ json_url               <chr> "https://www.federalregister.gov/api/v1/documents/2017-01799.json", "https://www.f...

#' Now, count by year and POTUS and see how many EOs were signed
mutate(eo_df, year = lubridate::year(signing_date)) %>% 
  mutate(year = as.Date(sprintf("%s-01-01", year))) %>% 
  count(year, potus) %>%
  mutate(
    potus = factor(
      potus, 
      levels = c("Donald Trump", "Barack Obama", "George W. Bush", "William J. Clinton")
    )
  ) %>%
  ggplot(aes(year, n, group=potus)) +
  geom_col(position = "stack", aes(fill = potus)) +
  scale_x_date(
    name = NULL,
    expand = c(0,0),
    breaks = as.Date(c("1993-01-01", "2001-01-01", "2009-01-01", "2017-01-01")),
    date_labels = "%Y",
    limits = as.Date(c("1992-01-01", "2020-12-31"))
  ) +
  scale_y_comma(name = "# EOs") +
  scale_fill_ipsum(name = NULL) +
  labs(
    title = "Number of Executive Orders Signed Per-Year, Per-POTUS",
    subtitle = "1993-Present",
    caption = "Source: Federal Register <https://www.federalregister.gov/executive-orders>"
  ) +
  theme_ipsum_rc(grid = "Y") +
  theme(legend.position = "bottom")

#' Famous first words?

mutate(eo_df, year = lubridate::year(signing_date)) %>% 
  mutate(year = as.Date(sprintf("%s-01-01", year))) %>%
  mutate(first_word = stri_replace_first_regex(title, "^[[:digit:]]+\ *", "") %>% 
           stri_replace_first_regex("^(To|The|A|White House) ", "") %>% 
           stri_replace_first_fixed("Half-Day", "HalfDay") %>% 
           stri_extract_first_words()) -> titles_df

mutate(titles_df, first_word = singularize(first_word)) %>% 
  count(first_word, sort=TRUE) %>% 
  mutate(pct = n/sum(n)) %>% 
  filter(!stri_detect_regex(first_word, "President|Federal|National"))

#' Top 5 first words per POTUS
mutate(titles_df, first_word = singularize(first_word)) %>% 
  count(potus, first_word, sort=TRUE) %>% 
  filter(!stri_detect_regex(first_word, "President|Federal|National")) %>%
  mutate(first_word = stri_replace_all_fixed(first_word, "Establishment", "Establishing")) %>% 
  mutate(first_word = stri_replace_all_fixed(first_word, "Amendment", "Amending")) -> first_words

group_by(first_words, potus) %>% 
    top_n(5) %>%  
    ungroup() %>% 
    distinct(first_word) %>% 
    pull(first_word) -> all_first_words

filter(first_words, first_word %in% all_first_words) %>% 
  mutate(
    potus = factor(
      potus, 
      levels = c("Donald Trump", "Barack Obama", "George W. Bush", "William J. Clinton")
    )
  ) %>% 
  mutate(
    first_word = factor(
      first_word, 
      levels = rev(sort(unique(first_word)))
    )
  ) -> first_df

ggplot(first_df, aes(n, first_word)) +
  geom_segment(aes(xend=0, yend=first_word, color=potus), size=4) +
  scale_x_comma(limits=c(0,40)) +
  scale_y_discrete(limits = sort(unique(first_df$first_word))) +
  facet_wrap(~potus, scales = "free", ncol = 2) +
  labs(
    x = "# EOs",
    y = NULL,
    title = "Top 5 Executive Order 'First Words' by POTUS",
    subtitle = "1993-Present",
    caption = "Source: Federal Register <https://www.federalregister.gov/executive-orders>"
  ) +
  theme_ipsum_rc(grid="X", strip_text_face = "bold") +
  theme(panel.spacing.x = unit(5, "lines")) +
  theme(legend.position="none")