R-Ladies Events Stats

text-analysis
Published

March 12, 2024

Overview

Let’s scrap the R-Ladies chapters events from Meetup.com We can use the {meetupr} package.

urlname <- c("rladies-paris","rladies-rome")
events <- purrr::map(urlname,get_events)
dat <- dplyr::bind_rows(events)

Load necessary libraries

R-Ladies Rome Events

urlname <- "rladies-rome"
events <- get_events(urlname)
dplyr::arrange(events, desc(time))%>%
  head()
urlname <- c("rladies-paris","rladies-rome")
events <- purrr::map(urlname,get_events)
dat <- dplyr::bind_rows(events)
dat%>%
  mutate(link=gsub("https://www.meetup.com/","",link),
         chapter=stringr::str_extract(link, "^rladies(.+?)/"),
         chapter=gsub("/","",chapter))%>%
  count(chapter)

All Chapters Events

To do it for all chapters on meetup, we need the list of the chapters from the rladies github archive.

data <- jsonlite::fromJSON('https://raw.githubusercontent.com/rladies/meetup_archive/main/data/events.json')
chapter <- data %>%
  count(group_urlname)%>%
  filter(!str_detect(group_urlname,"@"))
chapters <- chapter$group_urlname

events <- purrr::map(chapters,get_events)
# saveRDS(events,"events.rds")
# another way
# x <- lapply(paths, func)
# res <- dplyr::bind_rows(x)
bind_rows(events[1])%>%head()
dat <- dplyr::bind_rows(events)
# saveRDS(dat,"dat.rds")
dat1 <- dat%>% 
  mutate(link=gsub("https://www.meetup.com/","",link),
         chapter=stringr::str_extract(link, "^rladies(.+?)/"),
         chapter=gsub("/","",chapter))%>%
  relocate(chapter)

# saveRDS(dat1,"dat1.rds")
dat2 <- dat1%>%
  select(time,chapter,title,going,venue_city,
         venue_lon,venue_lat,venue_state,venue_country)%>%
  mutate(time=as.Date(time))%>%
  arrange(desc(going))
dat2%>%
  mutate(year=year(time),.after = time)%>%
  pull(year)%>%
  summary(year)
dat3 <- dat2%>%
  tidytext::unnest_tokens(word, title,drop = F)%>%
  select(chapter,title,going,word)%>% 
  anti_join(get_stopwords())%>%
  filter(!str_length(word)<=3)
dat3%>%
  count(word, sort = TRUE) %>%
  with(wordcloud::wordcloud(word, n, max.words = 100))

Latent Dirichlet Allocation with the topicmodels package

chapters_dtm <- dat3 %>%
  count(title, word, sort = TRUE)%>%
  cast_dtm(title, word, n)

chapters_dtm
chapters_lda <- topicmodels::LDA(chapters_dtm, 
                    k = 4, 
                    control = list(seed = 1234))
chapters_lda_td <- tidy(chapters_lda)
chapters_lda_td
top_terms <- chapters_lda_td %>%
  group_by(topic) %>%
  slice_max(beta, n = 5) %>%
  ungroup() %>%
  arrange(topic, -beta)

top_terms
top_terms %>%
  mutate(term = reorder_within(term, beta, topic)) %>%
  ggplot(aes(term, beta)) +
  geom_col() +
  scale_x_reordered() +
  facet_wrap(vars(topic), scales = "free_x")


assignments <- augment(chapters_lda, data = chapters_dtm)

assignments%>%
  filter(!term=="ladies")

# how words in titles changed overtime
inaug_freq <- dat3 %>%
  inner_join(dat2,by=c("chapter","title","going"))%>%#View
  count(time, word) %>%
  complete(time, word, fill = list(n = 0)) %>%
  group_by(time) %>%
  mutate(time_total = sum(n), 
         percent = n / time_total) %>%
  ungroup()

inaug_freq
# library(broom)
models <- inaug_freq %>%
  group_by(word) %>%
  filter(sum(n) > 50) %>%
  group_modify(
    ~ tidy(glm(cbind(n, time_total - n) ~ time, ., 
               family = "binomial"))
  ) %>%
  ungroup() %>%
  filter(term == "time")

models
models %>%
  filter(term == "time") %>%
  arrange(desc(abs(estimate)))
models %>%
  mutate(adjusted.p.value = p.adjust(p.value)) %>%
  ggplot(aes(estimate, adjusted.p.value)) +
  geom_point(shape=".") +
  #scale_y_log10() +
  geom_text(aes(label = word), 
            #vjust = 1, hjust = 1, 
            check_overlap = TRUE) +
  labs(x = "Estimated change over time", y = "Adjusted p-value")
models %>%
  slice_max(abs(estimate), n = 6) %>%
  inner_join(inaug_freq) %>%
  ggplot(aes(time, percent)) +
  geom_point() +
  geom_smooth() +
  facet_wrap(vars(word)) +
  scale_y_continuous(labels = scales::percent_format()) +
  labs(y = "Frequency of word in speech")
Back to top