การจัดการโครงสร้าง JSON แบบซ้อนกัน

เหตุใด JSON ที่ซ้อนกันจึงจัดการได้ยาก

# Example nested JSON from a REST API:
json_str <- '{
  "user": {
    "id": 1,
    "name": "Alice",
    "orders": [
      {"order_id": 101, "total": 59.99, "status": "shipped"},
      {"order_id": 102, "total": 24.50, "status": "pending"}
    ]
  }
}'

# The challenge: 'orders' is an array of objects inside 'user'
cat('Nested JSON loaded as string, length:', nchar(json_str))

fromJSON() — การแยกวิเคราะห์พื้นฐาน

library(jsonlite)

# Parse flat JSON
flat_json <- '{"name": "Alice", "age": 30, "score": 95.5}'
result <- fromJSON(flat_json)
cat('Name:', result$name, '\n')
cat('Age: ', result$age,  '\n')

# Parse an array of objects — becomes a data frame
array_json <- '[{"id":1,"val":10},{"id":2,"val":20},{"id":3,"val":30}]'
df <- fromJSON(array_json)
cat('Class:', class(df), '\n')
print(df)

fromJSON() พร้อม flatten = TRUE

library(jsonlite)

json_str <- '[{
  "id": 1,
  "name": "Alice",
  "address": {"city": "Berlin", "country": "Germany"}
},{
  "id": 2,
  "name": "Bob",
  "address": {"city": "Paris", "country": "France"}
}]'

# Without flatten:
nested_df <- fromJSON(json_str, flatten = FALSE)
cat('address class:', class(nested_df$address), '\n')

# With flatten = TRUE:
flat_df <- fromJSON(json_str, flatten = TRUE)
cat('Columns:', names(flat_df), '\n')
print(flat_df)

อาร์เรย์ที่ซ้อนกันจะกลายเป็นคอลัมน์ลิสต์

library(jsonlite)

json_str <- '[{
  "user_id": 1,
  "tags": ["R", "Python", "SQL"]
},{
  "user_id": 2,
  "tags": ["Java", "Kotlin"]
}]'

df <- fromJSON(json_str)
cat('tags column class:', class(df$tags), '\n')

# Access tags for user 1:
cat('User 1 tags:', df$tags[[1]], '\n')
cat('User 2 tags:', df$tags[[2]])

purrr::map() — ดึงฟิลด์ที่ซ้อนกัน

library(jsonlite)
library(purrr)

json_str <- '[{
  "id": 1,
  "meta": {"score": 88, "grade": "B"}
},{
  "id": 2,
  "meta": {"score": 95, "grade": "A"}
},{
  "id": 3,
  "meta": {"score": 72, "grade": "C"}
}]'

records <- fromJSON(json_str, simplifyDataFrame = FALSE)

# Extract 'score' from each record's 'meta' object
scores <- map_dbl(records, function(r) r$meta$score)
grades <- map_chr(records, function(r) r$meta$grade)

cat('Scores:', scores, '\n')
cat('Grades:', grades)

purrr::map() พร้อมทางลัดแบบสตริง

library(jsonlite)
library(purrr)

json_str <- '[{"name":"Alice","score":90},{"name":"Bob","score":78},{"name":"Carol","score":85}]'

# Parse as list of lists
records <- fromJSON(json_str, simplifyDataFrame = FALSE)

# String shortcut to extract field
names_vec  <- map_chr(records, 'name')
scores_vec <- map_dbl(records, 'score')

cat('Names: ', names_vec, '\n')
cat('Scores:', scores_vec, '\n')

# Build a clean data frame
clean_df <- data.frame(name = names_vec, score = scores_vec)
print(clean_df)

การซ้อนหลายชั้นด้วยสายโซ่ map()

library(jsonlite)
library(purrr)

json_str <- '[{
  "id": 1,
  "company": {"hq": {"city": "Berlin", "country": "Germany"}}
},{
  "id": 2,
  "company": {"hq": {"city": "Tokyo",  "country": "Japan"}}
}]'

records <- fromJSON(json_str, simplifyDataFrame = FALSE)

# Navigate: records -> company -> hq -> city
cities <- map_chr(records, function(r) r$company$hq$city)
cat('Cities:', cities, '\n')

# Or using nested map shortcut:
ids <- map_int(records, 'id')
cat('IDs:', ids)

tidyr::unnest() — คลี่คอลัมน์ลิสต์

library(jsonlite)
library(tidyr)
library(dplyr)

json_str <- '[{
  "user_id": 1,
  "orders": [{"oid":101,"total":50},{"oid":102,"total":30}]
},{
  "user_id": 2,
  "orders": [{"oid":103,"total":80}]
}]'

df <- fromJSON(json_str)
cat('Before unnest, rows:', nrow(df), '\n')
cat('orders class:', class(df$orders), '\n')

# Unnest expands one row per order
expanded <- unnest(df, cols = orders)
cat('After unnest, rows:', nrow(expanded), '\n')
print(expanded)

jsonlite::flatten() กับกรอบข้อมูล

library(jsonlite)

json_str <- '[{
  "id": 1,
  "profile": {"age": 25, "city": "Rome"}
},{
  "id": 2,
  "profile": {"age": 31, "city": "Oslo"}
}]'

# Parse without auto-flatten
nested <- fromJSON(json_str, flatten = FALSE)
cat('Columns before flatten:', names(nested), '\n')
cat('profile class:', class(nested$profile), '\n')

# Apply flatten() post-hoc
flat <- flatten(nested)
cat('Columns after flatten:', names(flat), '\n')
print(flat)

จัดการค่า Null ใน JSON ที่ซ้อนกัน

library(jsonlite)
library(purrr)

json_str <- '[{"id":1,"email":"alice@example.com"},{"id":2,"email":null},{"id":3,"email":"carol@example.com"}]'

records <- fromJSON(json_str, simplifyDataFrame = FALSE)

# Unsafe: NULL drops the element
# emails <- map_chr(records, 'email')  # ERROR on null

# Safe: provide a default for missing values
emails <- map_chr(records, function(r) {
  if (is.null(r$email)) NA_character_ else r$email
})

cat('Emails:', emails)
cat('NAs:', sum(is.na(emails)))

กระบวนการสมบูรณ์: จาก API JSON สู่กรอบข้อมูลที่เป็นระเบียบ

library(jsonlite)
library(purrr)
library(dplyr)

# Simulated API response
api_json <- '[{
  "id": 1, "name": "Alice",
  "stats": {"score": 92, "rank": 1}
},{
  "id": 2, "name": "Bob",
  "stats": null
},{
  "id": 3, "name": "Carol",
  "stats": {"score": 85, "rank": 3}
}]'

records <- fromJSON(api_json, simplifyDataFrame = FALSE)

result <- tibble(
  id    = map_int(records,  'id'),
  name  = map_chr(records,  'name'),
  score = map_dbl(records,  function(r) if (is.null(r$stats)) NA_real_ else r$stats$score),
  rank  = map_int(records,  function(r) if (is.null(r$stats)) NA_integer_ else r$stats$rank)
)

print(result)

ตรวจสอบความเข้าใจอย่างรวดเร็ว

ประเด็นสำคัญของ JSON แบบซ้อนกัน

library(jsonlite)
library(purrr)

# Quick reference:
json <- '[{"id":1,"info":{"val":10}},{"id":2,"info":null}]'
recs <- fromJSON(json, simplifyDataFrame = FALSE)

# Safe extraction with null guard
vals <- map_dbl(recs, function(r) {
  if (is.null(r$info)) NA_real_ else r$info$val
})

result <- data.frame(id = map_int(recs, 'id'), val = vals)
print(result)