Example Data Exploration with ravelRy
In ravelRy: An Interface to the 'Ravelry' API

knitr::opts_chunk$set(echo = TRUE, fig.width = 6, fig.height = 4)
library(ravelRy)
library(tidyverse)
source('../../../kp_themes/theme_kp.R')
theme_set(theme_classic() + theme_kp())

Patterns

Start by retrieving a sample of patterns for babies and their details.

patterns <- search_patterns(page_size = 100, fit = 'baby')
pattern_details <- get_patterns(ids = patterns$id)

Top 10 designers by pattern count in sample:

patterns %>%
  group_by(designer.name) %>%
  count() %>%
  ungroup() %>%
  arrange(desc(n)) %>%
  slice(1:10)

Look at the density of comments based on the cost of the pattern:

pattern_details %>%
  ggplot(aes(x = comments_count, fill = free)) +
  geom_density(alpha = 0.7) +
  labs(title = 'Comment count by free/paid in sample') +
  scale_fill_kp()

Unnest two columns and take a count:

pattern_details %>%
  unnest(craft, names_sep = '_') %>% 
  unnest(pattern_type, names_sep = '_') %>% 
  group_by(craft_name, pattern_type_name) %>%
  count() %>%
  ggplot(aes(x = reorder(pattern_type_name, n, sum), y = n, fill = craft_name)) +
  geom_col() +
  labs(title = 'Pattern type by craft in sample',
       x = 'pattern_type_name') +
  scale_fill_kp()

Yarn

Start by retrieving a sample of yarns and their details.

yarns <- search_yarn(page_size = 100, sort = 'projects', fiberc = '2')
yarn_details <- get_yarns(ids = yarns$id)

Get the top rated yarns in the sample:

yarns %>%
  arrange(desc(rating_average)) %>%
  select(id, name, rating_average) %>%
  slice(1:5)

How do fiber types appear together in yarn?

# get the top 10 fiber types 
top_fiber_types <- yarn_details %>%
  unnest(yarn_fibers, names_sep = '_') %>%
  count(yarn_fibers_fiber_type.name) %>%
  filter(n > 5) %>%
  arrange(desc(n)) %>%
  slice(1:10)

# unnest the yarn_fibers column, bucket fiber names, and spread wide
yarn_fibers_wide <- yarn_details %>% 
  unnest(yarn_fibers, names_sep = '_') %>%
  mutate(yarn_fiber_name = ifelse(yarn_fibers_fiber_type.name %in% top_fiber_types$yarn_fibers_fiber_type.name,
                                  yarn_fibers_fiber_type.name,
                                  'Other')) %>%
  pivot_wider(id_cols = 'id', 
              names_from = 'yarn_fiber_name', 
              values_from = 'yarn_fibers_percentage', 
              values_fn = list(yarn_fibers_percentage = sum)) 

# compute correlation and plot
yarn_fibers_wide %>%
  select(-id) %>%
  mutate_if(is.numeric, function(x) ifelse(is.na(x), 0, 1)) %>%
  cor() %>%
  corrplot::corrplot(type = 'upper', 
                     method = 'color', 
                     order = 'hclust', 
                     tl.col = 'black', 
                     addCoef.col = 'black',
                     number.cex = 0.6,
                     col = colorRampPalette(colors = c(
                       kp_cols('red'), 
                       'white', 
                       kp_cols('dark_blue')))(200),
                     mar = c(2,2,2,2),
                     main = 'Yarn Fiber Correlation',
                     family = 'Avenir')