prod_comp.R

library(tidyverse)
library(wordbankr)

eng_wg_inst <- wordbankr::get_instrument_data(form = "WG", language = "English (American)", 
                                              item_info = TRUE, administration_info = TRUE)

by_cat <- eng_wg_inst |>
  filter(item_kind == "word") |>
  group_by(data_id, lexical_category, age) |>
  summarise(prod = sum(produces), 
         comp = sum(understands), 
         prod_comp_ratio = prod / (prod + comp))

ggplot(filter(by_cat, !(lexical_category == "function_words")),
       aes(x = age, y = prod_comp_ratio, col = lexical_category)) + 
   geom_jitter(alpha = .2, size = 0.7) +
  geom_smooth() +
  scale_x_continuous(breaks = seq(8, 18, 1)) +
  xlab("Age (months)") +
  ylab("Productivity ratio")

by_sem <- eng_wg_inst |>
  filter(item_kind == "word") |>
  group_by(data_id, category, age) |>
  summarise(prod = sum(produces), 
         comp = sum(understands), 
         prod_comp_ratio = prod / (prod + comp))

ggplot(filter(by_sem, !(category %in% c("question_words","quantifiers","pronouns"))),
       aes(x = age, y = prod_comp_ratio, col = category)) + 
   geom_jitter(alpha = .2, size = 0.7) +
  geom_smooth() +
  scale_x_continuous(breaks = seq(8, 18, 1)) +
  xlab("Age (months)") +
  ylab("Productivity ratio")