من العريض إلى الطولي باستخدام pivot_longer()

تنسيقا البيانات العريض والطويل

library(tidyr)
library(dplyr)

# Wide format: each quarter is a column
wide_df <- data.frame(
  student = c('Alice','Bob','Carol'),
  q1 = c(85, 90, 78),
  q2 = c(88, 85, 80),
  q3 = c(92, 88, 84)
)

print(wide_df)
cat('\nShape:', nrow(wide_df), 'rows x', ncol(wide_df), 'cols')

أساسيات pivot_longer()

library(tidyr)

wide_df <- data.frame(
  student = c('Alice','Bob','Carol'),
  q1 = c(85, 90, 78),
  q2 = c(88, 85, 80),
  q3 = c(92, 88, 84)
)

long_df <- pivot_longer(
  wide_df,
  cols = c(q1, q2, q3),
  names_to = 'quarter',
  values_to = 'score'
)

print(long_df)

تحديد الأعمدة باستخدام starts_with()

library(tidyr)

df <- data.frame(
  id = 1:3,
  sales_jan = c(100, 200, 150),
  sales_feb = c(120, 180, 160),
  sales_mar = c(130, 190, 170)
)

# Select all sales_ columns automatically
pivot_longer(
  df,
  cols = starts_with('sales_'),
  names_to = 'month',
  values_to = 'sales'
)

استبعاد الأعمدة باستخدام -col

library(tidyr)

df <- data.frame(
  region = c('East','West'),
  jan = c(100, 200),
  feb = c(110, 210),
  mar = c(120, 220),
  apr = c(130, 230)
)

# Pivot everything except 'region'
pivot_longer(df, cols = -region, names_to = 'month', values_to = 'revenue')

names_prefix — إزالة البادئات

library(tidyr)

df <- data.frame(
  id = 1:3,
  score_q1 = c(85, 90, 78),
  score_q2 = c(88, 85, 80),
  score_q3 = c(92, 88, 84)
)

pivot_longer(
  df,
  cols = starts_with('score_'),
  names_to = 'quarter',
  names_prefix = 'score_',
  values_to = 'score'
)

تحويل مجموعات متعددة من الأعمدة

library(tidyr)

df <- data.frame(
  id = 1:2,
  sales_q1 = c(100, 200),
  sales_q2 = c(110, 210),
  cost_q1 = c(60, 110),
  cost_q2 = c(65, 115)
)

pivot_longer(
  df,
  cols = -id,
  names_to = c('.value', 'quarter'),
  names_pattern = '(.+)_(q[0-9]+)'
)

names_transform — تحويل الأنواع

library(tidyr)

df <- data.frame(
  product = c('A','B'),
  y2021 = c(100, 200),
  y2022 = c(110, 210),
  y2023 = c(120, 220)
)

result <- pivot_longer(
  df,
  cols = -product,
  names_to = 'year',
  names_prefix = 'y',
  names_transform = list(year = as.integer),
  values_to = 'sales'
)

print(result)
cat('year column type:', class(result$year))

values_drop_na — إزالة القيم المفقودة

library(tidyr)

df <- data.frame(
  student = c('Alice','Bob','Carol'),
  q1 = c(85, NA, 78),
  q2 = c(88, 85, NA),
  q3 = c(NA, 88, 84)
)

# Without drop: 9 rows including NAs
pivot_longer(df, -student, names_to='quarter', values_to='score',
             values_drop_na = TRUE)

التنسيق الطويل يتيح استخدام ggplot2

library(tidyr)
# (ggplot2 not run here, but showing the data preparation)

df <- data.frame(
  month = c('Jan','Feb','Mar'),
  product_A = c(100, 120, 110),
  product_B = c(200, 190, 210)
)

# After pivoting, ready for ggplot2:
long_df <- pivot_longer(df, -month, names_to='product', values_to='sales')
print(long_df)
# ggplot(long_df, aes(x=month, y=sales, color=product)) + geom_line()

التحويل مع أسماء الأعمدة الرقمية

library(tidyr)

# Year columns as numbers (common in census-style data)
df <- data.frame(
  country = c('US','UK'),
  '2021' = c(100, 80),
  '2022' = c(110, 85),
  '2023' = c(120, 90),
  check.names = FALSE
)

pivot_longer(
  df,
  cols = c('2021','2022','2023'),
  names_to = 'year',
  values_to = 'gdp_index'
)

مقارنة نتائج التحويل

library(tidyr)

wide <- data.frame(
  id = 1:4,
  jan = c(10,20,30,40),
  feb = c(11,21,31,41),
  mar = c(12,22,32,42)
)

long <- pivot_longer(wide, -id, names_to='month', values_to='value')

cat('Wide rows:', nrow(wide), '\n')
cat('Long rows:', nrow(long), '(expected', nrow(wide)*3, ')\n')
cat('Months:', paste(unique(long$month), collapse=', '), '\n')

تحقق سريع

مراجعة: pivot_longer()

library(tidyr)

df <- data.frame(
  team = c('Alpha','Beta'),
  sales_2022 = c(100, 200),
  sales_2023 = c(120, 220),
  sales_2024 = c(140, 240)
)

pivot_longer(
  df,
  cols = starts_with('sales_'),
  names_to = 'year',
  names_prefix = 'sales_',
  names_transform = list(year = as.integer),
  values_to = 'revenue'
)