From 3f1adff5520828ad876161a6ca14bac1f10a13a1 Mon Sep 17 00:00:00 2001
From: Jeremy <jeremy.stanley@instacart.com>
Date: Thu, 25 Aug 2016 09:19:49 -0700
Subject: [PATCH] first version of new vignette #4

---
 vignettes/making-tidyjson-purrr.Rmd | 120 +++++++++++++++++++++++++++-
 1 file changed, 119 insertions(+), 1 deletion(-)

diff --git a/vignettes/making-tidyjson-purrr.Rmd b/vignettes/making-tidyjson-purrr.Rmd
index 94bc56a..1b9252f 100644
--- a/vignettes/making-tidyjson-purrr.Rmd
+++ b/vignettes/making-tidyjson-purrr.Rmd
@@ -10,13 +10,15 @@ vignette: >
 ---
 
 ```{r, echo = FALSE}
-knitr::opts_chunk$set(collapse = TRUE, comment = "#>")
+knitr::opts_chunk$set(collapse = TRUE, comment = "#>", fig.width = 7, fig.height = 5)
 options(dplyr.print_min = 4L, dplyr.print_max = 4L)
 ```
 
 ## Load required libraries
 
 ```{r, message = FALSE}
+library(igraph)
+library(RColorBrewer)
 library(tidyjson)   # this library
 library(dplyr)      # for %>% and other dplyr functions
 library(purrr)      # to compare against purrr
@@ -26,6 +28,7 @@ library(tibble)     # for tibble creation
 library(magrittr)   # for `%$%`
 library(ggplot2)    # for plotting
 library(forcats)    # easier factor manipulation
+library(stringr)    # for truncating values
 ```
 
 ## Companies Data
@@ -43,6 +46,121 @@ We can see the structure of a sample record with `str`
 str(fromJSON(samp_co[[1]]))
 ```
 
+Alternatively, we can compute the structure using `tidyjson::json_structure`
+
+```{r}
+structure <- samp_co[[1]] %>% json_structure
+
+max_length <- 20
+structure %>%
+  mutate(json = structure %@% "JSON") %>%
+  transmute(child.id, key, type, length, 
+    json = ifelse(!(type %in% c("object", "array")), as.character(json), NA_character_))%>%
+  mutate(json = paste0(json %>% str_sub(end = max_length - 3),
+                       ifelse(str_length(json) > max_length - 3, "...", "")))
+```
+
+Hard to understand this using ggplot
+
+```{r}
+structure %>%
+  replace_na(list(key = "NA")) %>%
+  mutate(level = factor(level)) %>%
+  ggplot(aes(type, key)) +
+    geom_tile() +
+    facet_grid(level ~ ., scale = "free", space = "free")
+```
+
+Plot as a network graph
+
+```{r}
+plot_structure_graph <- function(json, legend = TRUE) {
+  
+  structure <- json %>% json_structure
+  
+  type_colors <- brewer.pal(6, "Accent")
+
+  g <- graph_from_data_frame(
+    structure %>%
+      filter(!is.na(parent.id)) %>%
+      select(parent.id, child.id),
+    directed = TRUE,
+    vertices = structure %>% 
+      transmute(child.id, 
+                vertex.color = type_colors[as.integer(type)],
+                vertex.label = ifelse(type %in% c("object", "array") & length > 0,
+                                      key, NA_character_)))
+  
+  op <- par(mar = c(0, 0, 0, 0))
+  plot(g, edge.arrow.size = .1, vertex.color = V(g)$vertex.color, vertex.size = 4,
+       vertex.label = V(g)$vertex.label, layout = layout_with_kk, 
+       edge.color = 'grey70', edge.width = 2)
+  
+  if (legend)
+    legend(x = -1.3, y = -.6, levels(structure$type), pch = 21,
+           col="#777777", pt.bg = type_colors, 
+           pt.cex = 2, cex = .8, bty = "n", ncol = 1)
+  
+  par(op)
+  
+  NULL
+  
+}
+```
+
+Plot a single company
+
+```{r}
+samp_co[[1]] %>% plot_structure_graph
+```
+
+A lot of variety
+
+```{r}
+nrow <- 3
+ncol <- 4
+op <- par(mfrow = c(nrow, ncol))
+walk(samp_co[1:(nrow*ncol)], plot_structure_graph, legend = FALSE)
+par(op)
+```
+
+The most complex
+
+```{r}
+lengths <- companies %>% 
+  map(fromJSON, simplifyVector = FALSE) %>%
+  map(unlist, recursive = TRUE) %>%
+  map_int(length)
+most_complex <- companies[which(lengths == max(lengths))]
+
+most_complex %>% spread_values(name = jstring("name")) %>% extract2("name")
+``` 
+
+Let's try to plot it!
+
+```{r}
+plot_structure_graph(most_complex)
+```
+
+That is just too big, let's simplify things
+
+```{r, fig.height = 8}
+sub_objects <- most_complex %>%
+  gather_keys %>%
+  json_types %>%
+  json_lengths %>%
+  filter(length > 1)
+
+nrow <- 5
+ncol <- 3
+op <- par(mfrow = c(nrow, ncol))
+for(i in 1:nrow(sub_objects)) {
+  plot_structure_graph(sub_objects[i, ], legend = FALSE)
+  title(sub_objects$key[i], col.main = 'red')
+}
+par(op)
+```
+
 ## `tbl_json`
 
 We are working with a character array of JSON, which tidyjson coerces directly