In farach/huggingfaceR: Hugging Face State-of-the-Art Models in R

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

library(huggingfaceR)
library(scales)
library(ggplot2)

Just storing some ggplot boiler plate for model data EDA

library(scales)
library(ggplot2)

models <- huggingfaceR::models_with_downloads
models%>%
  ggplot(aes(x= downloads))+
  geom_histogram(alpha = 0.8, color = "black")+
  scale_x_continuous(trans = "log10", labels = comma)+
  theme_bw(base_family = "sans")+
  labs(title = "Log-transformed Histogram of Downloads per Model",
       subtitle = "The vast majority of models have received < 1k downloads",
       y = "Number of Models",
       x = "Number of Downloads",
       caption = paste0("Up to date as of: ", Sys.Date()))

models%>%
  count(task, sort = TRUE)%>%
  mutate(task = stringr::str_to_title(task),
         task = stringr::str_replace_all(task, "-", " "))%>%
  na.omit()%>%
  ggplot(aes(y= reorder(task,n), x = n))+
  geom_col(fill = "#0f50d2")+
  theme_bw(base_family = "sans")+
  labs(title = "Models Saved on Hugging Face Hub by Task",
       subtitle = "Models without download information & NA's for task omitted",
       caption = paste0("Up to date as of: ", Sys.Date()),
       y = "Model task",
       x = "Number of models per task")

models %>%
  mutate(task = forcats::fct_lump_n(task, n = 16))%>%
  na.omit()%>%
  group_by(task)%>%
  summarise(av_dl = mean(downloads), med_dl = median(downloads), n = n())%>%
  arrange(desc(av_dl))%>%
  ggplot(aes(y= av_dl, x = n))+
  geom_point()+
  geom_text(aes(label = stringr::str_to_title(stringr::str_replace_all(task, "-", " "))),
            check_overlap = TRUE, size =3, nudge_y = 350)+
  theme_bw()+
  labs(title = "Average Downloads per Task vs Number of Models")+
  labs(y = "Average Downloads", x = "Number of Models",
       caption = paste0("Up to date as of: ", Sys.Date()))+
  expand_limits(x = c(-10, 8500))

models %>%
  mutate(task = forcats::fct_lump_n(task, n = 16))%>%
  na.omit()%>%
  group_by(task)%>%
  summarise(av_dl = mean(downloads), med_dl = median(downloads), n = n())%>%
  arrange(desc(av_dl))%>%
  ggplot(aes(y= med_dl, x = n))+
  geom_point()+
  geom_text(aes(label = stringr::str_to_title(stringr::str_replace_all(task, "-", " "))),
            check_overlap = FALSE, size =3)+
  theme_bw()+
  labs(title = "Median Downloads per Task vs Number of Models")+
  labs(y = "Median Downloads", x = "Number of Models",
       caption = paste0("Up to date as of: ", Sys.Date()),
       subtitle = "Median is far below mean - models are a winner-takes-most game")+
  expand_limits(x = c(-100, 8500))