تضمين إطارات البيانات وفك تضمينها

أعمدة القوائم والبيانات المتداخلة

library(tidyr)
library(dplyr)

# A simple data frame with a list-column
df <- data.frame(
  group = c('A','B','C'),
  n = c(3, 2, 4)
)
df$values <- list(c(1,2,3), c(4,5), c(6,7,8,9))

print(df)
print(df$values[[1]])  # Access the first list element

nest() — إنشاء إطارات بيانات متداخلة

library(tidyr)
library(dplyr)

df <- data.frame(
  region = c('East','East','East','West','West'),
  month = c(1,2,3,1,2),
  sales = c(100,120,110,200,190)
)

nested <- df %>%
  nest(data = c(month, sales))

print(nested)
print(nested$data[[1]])  # East region's data

nest() مع group_by()

library(tidyr)
library(dplyr)

df <- data.frame(
  category = c('A','A','A','B','B','C','C','C','C'),
  x = c(1,2,3,4,5,6,7,8,9),
  y = c(2,4,3,8,7,5,6,9,8)
)

nested <- df %>%
  group_by(category) %>%
  nest()

print(nested)
cat('Rows per category B:', nrow(nested$data[[2]]))

map() مع إطارات البيانات المتداخلة

library(tidyr)
library(dplyr)
library(purrr)

df <- data.frame(
  group = c('A','A','A','B','B','B'),
  x = c(1,2,3,1,2,3),
  y = c(2.1,4.0,5.9,3.2,5.8,9.1)
)

models <- df %>%
  group_by(group) %>%
  nest() %>%
  mutate(model = map(data, ~lm(y ~ x, data = .x)))

print(models)

استخراج نتائج النماذج باستخدام map()

library(tidyr)
library(dplyr)
library(purrr)

df <- data.frame(
  group = c('A','A','A','B','B','B'),
  x = c(1,2,3,1,2,3),
  y = c(2.1,4.0,5.9,3.2,5.8,9.1)
)

df %>%
  group_by(group) %>%
  nest() %>%
  mutate(
    model = map(data, ~lm(y ~ x, data = .x)),
    r_squared = map_dbl(model, ~summary(.x)$r.squared),
    intercept = map_dbl(model, ~coef(.x)[1]),
    slope = map_dbl(model, ~coef(.x)[2])
  ) %>%
  select(group, r_squared, intercept, slope)

unnest() — توسيع أعمدة القوائم

library(tidyr)
library(dplyr)

nested <- data.frame(
  region = c('East','West')
)
nested$data <- list(
  data.frame(month=1:3, sales=c(100,120,110)),
  data.frame(month=1:2, sales=c(200,190))
)

unnested <- unnest(nested, cols = data)
print(unnested)

unnest_longer() — توسيع القائمة إلى صفوف

library(tidyr)

df <- data.frame(
  person = c('Alice','Bob','Carol')
)
df$skills <- list(
  c('R','Python','SQL'),
  c('Excel','Tableau'),
  c('R','Julia','Stan','BUGS')
)

unnest_longer(df, skills)

unnest_wider() — توسيع القائمة إلى أعمدة

library(tidyr)

df <- data.frame(id = 1:3)
df$info <- list(
  list(name='Alice', age=30, city='NYC'),
  list(name='Bob', age=25, city='LA'),
  list(name='Carol', age=35, city='Chicago')
)

unnest_wider(df, info)

النمط الكامل لسير عمل البيانات المتداخلة

library(tidyr)
library(dplyr)
library(purrr)

df <- data.frame(
  region = c('East','East','East','West','West','West'),
  month = c(1,2,3,1,2,3),
  revenue = c(100,120,115,200,195,210)
)

df %>%
  group_by(region) %>%
  nest() %>%
  mutate(
    mean_rev = map_dbl(data, ~mean(.x$revenue)),
    trend = map_dbl(data, ~coef(lm(revenue~month, data=.x))[2])
  ) %>%
  select(region, mean_rev, trend)

تداخل عدة أعمدة

library(tidyr)
library(dplyr)

df <- data.frame(
  region = c('East','East','West','West'),
  year = c(2023,2024,2023,2024),
  q1 = c(100,110,200,210),
  q2 = c(105,115,195,215),
  target = c(105,112,198,212)
)

# Only nest quarterly data, keep target as outer column
nested <- df %>%
  group_by(region, year) %>%
  nest(quarters = c(q1, q2))

print(nested)

متى تستخدم إطارات البيانات المتداخلة

library(tidyr)
library(dplyr)
library(purrr)

# Bootstrap confidence interval per group
df <- data.frame(
  group = c('A','A','A','A','B','B','B','B'),
  value = c(10,12,11,13,20,22,19,21)
)

set.seed(42)
df %>%
  group_by(group) %>%
  nest() %>%
  mutate(
    boot_means = map(data, function(d) {
      replicate(100, mean(sample(d$value, replace=TRUE)))
    }),
    ci_low = map_dbl(boot_means, ~quantile(.x, 0.025)),
    ci_high = map_dbl(boot_means, ~quantile(.x, 0.975))
  ) %>%
  select(group, ci_low, ci_high)

تحقق سريع

مراجعة: التداخل وفك التداخل

library(tidyr)
library(dplyr)
library(purrr)

data.frame(
  team = c('A','A','B','B'),
  x = c(1,2,1,2),
  y = c(2,4,3,6)
) %>%
  group_by(team) %>%
  nest() %>%
  mutate(
    model = map(data, ~lm(y ~ x, data = .x)),
    slope = map_dbl(model, ~coef(.x)['x'])
  ) %>%
  select(team, slope)