提交: 70a74d019c9a1c88ed1473e2f0fd6c473d05dedd - myprojects-hg-reborn (hg)

Commit MetaInfo

• 修订版: 70a74d019c9a1c88ed1473e2f0fd6c473d05dedd (tree)
• 时间: 2020-08-28 00:44:23
• 作者: Lorenzo Isella <lorenzo.isella@gmai...>
• Commiter: Lorenzo Isella

Log Message

A code which illustrates how to rectangle a json file.

更改概述

• add: R-codes/json_test.R

差异

diff -r abc3ff5205e5 -r 70a74d019c9a R-codes/json_test.R
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/R-codes/json_test.R	Thu Aug 27 17:44:23 2020 +0200
@@ -0,0 +1,84 @@
+rm(list=ls())
+
+
+library(tidyjson)   # this library
+library(tidyverse)      # for %>% and other dplyr functions
+
+
+## see https://mran.microsoft.com/snapshot/2016-08-05/web/packages/tidyjson/vignettes/introduction-to-tidyjson.html
+
+
+
+
+purch_json <- '
+[
+  {
+    "name": "bob", 
+    "purchases": [
+      {
+        "date": "2014/09/13",
+        "items": [
+          {"name": "shoes", "price": 187},
+          {"name": "belt", "price": 35}
+        ]
+      }
+    ]
+  },
+  {
+    "name": "susan", 
+    "purchases": [
+      {
+        "date": "2014/10/01",
+        "items": [
+          {"name": "dress", "price": 58},
+          {"name": "bag", "price": 118}
+        ]
+      },
+      {
+        "date": "2015/01/03",
+        "items": [
+          {"name": "shoes", "price": 115}
+        ]
+      }
+    ]
+  }
+]'
+
+
+
+library(jsonlite)
+# Parse the JSON into a data.frame
+purch_df <- jsonlite::fromJSON(purch_json, simplifyDataFrame = TRUE)
+
+
+
+
+
+purch_items <- purch_json %>%
+  gather_array %>%                                     # stack the users 
+  spread_values(person = jstring("name")) %>%          # extract the user name
+  enter_object("purchases") %>% gather_array %>%       # stack the purchases
+  spread_values(purchase.date = jstring("date")) %>%   # extract the purchase date
+  enter_object("items") %>% gather_array %>%           # stack the items
+  spread_values(                                       # extract item name and price
+    item.name = jstring("name"),
+    item.price = jnumber("price")
+  ) %>%
+  select(person, purchase.date, item.name, item.price) # select only what is needed
+
+
+
+### I comment what I did before. The object where "name" is the key is simple.
+## As a consequence, I just have to gather the array and spread its value.
+
+## A "gather" operation is always in front of a "spread" operation .
+
+## The "purchases" object is way more complicated and first I need to enter it.
+## It has also another complex object inside (the "items" object), but at least the "date" object is simple. As a consequence, I gather the array and spread the "date".
+
+## Then the "items" object is left. It is complex and I enter it before the usual gather and spread procedure.
+
+
+
+
+print("So far so good")