التقييم المنظّم: {{ }} و.data

المشكلة: البرمجة باستخدام dplyr

library(dplyr)

df <- data.frame(x=1:5, y=c(2,4,6,8,10))

# Works fine interactively:
df %>% summarize(mean_x = mean(x))

# But what if 'x' is a variable?
col_name <- 'x'
# df %>% summarize(result = mean(col_name))  # WRONG! treats 'col_name' as column
cat('Need tidy evaluation to solve this!')

عامل الاحتواء {{ }}

library(dplyr)

df <- data.frame(
  group = c('A','A','B','B'),
  sales = c(100, 120, 200, 180),
  costs = c(60, 70, 110, 90)
)

# Function using {{ }}
group_mean <- function(data, group_col, value_col) {
  data %>%
    group_by({{ group_col }}) %>%
    summarize(mean_val = mean({{ value_col }}), .groups = 'drop')
}

group_mean(df, group, sales)
group_mean(df, group, costs)

استخدام {{ }} لأسماء الأعمدة في الناتج

library(dplyr)

df <- data.frame(a=1:4, b=c(2,4,6,8))

# Dynamic output column name
compute_mean <- function(data, col) {
  col_name <- paste0('mean_', deparse(substitute(col)))
  data %>% summarize('{col_name}' := mean({{ col }}))
}

compute_mean(df, a)
compute_mean(df, b)

ضمير .data

library(dplyr)

df <- data.frame(
  name = c('Alice','Bob','Carol'),
  score = c(85, 92, 78),
  grade = c('B','A','C')
)

# Using .data with a string variable
get_summary <- function(data, col_name) {
  data %>%
    summarize(
      n = n(),
      mean_val = mean(.data[[col_name]])
    )
}

get_summary(df, 'score')

across() — التطبيق على أعمدة متعددة

library(dplyr)

df <- data.frame(
  id = 1:3,
  sales_q1 = c(100, 200, 150),
  sales_q2 = c(120, 180, 160),
  cost_q1 = c(60, 110, 80),
  cost_q2 = c(70, 100, 85)
)

# Summarize all numeric columns except 'id'
df %>%
  summarize(across(where(is.numeric) & !id, mean))

استخدام across() مع دوال مسماة

library(dplyr)

df <- data.frame(
  x = c(10, 20, 30, 40),
  y = c(5, 15, 25, 35)
)

# Compute mean and sd for both columns
df %>%
  summarize(across(
    c(x, y),
    list(mean = mean, sd = sd),
    .names = '{.col}_{.fn}'
  ))

استخدام across() في mutate()

library(dplyr)

df <- data.frame(
  id = 1:3,
  revenue = c(1000, 2000, 1500),
  cost = c(600, 1100, 800),
  tax = c(100, 200, 150)
)

# Round all numeric columns except id to nearest 10
df %>%
  mutate(across(where(is.numeric) & !id,
                ~round(., -2)))

pick() — تحديد أعمدة للعمليات

library(dplyr)

df <- data.frame(
  id = 1:3,
  a = c(1, 2, 3),
  b = c(4, 5, 6),
  c_val = c(7, 8, 9)
)

# Use pick() to compute row-wise mean across selected columns
df %>%
  mutate(
    row_mean = rowMeans(pick(a, b, c_val)),
    row_max = do.call(pmax, pick(a, b, c_val))
  )

كتابة دوال dplyr قابلة لإعادة الاستخدام

library(dplyr)

df <- data.frame(
  region = c('East','East','West','West'),
  product = c('A','B','A','B'),
  revenue = c(100, 200, 150, 250),
  units = c(10, 15, 12, 20)
)

# Flexible grouped summary function
group_stats <- function(data, ..., metric) {
  data %>%
    group_by(...) %>%
    summarize(
      total = sum({{ metric }}),
      average = mean({{ metric }}),
      .groups = 'drop'
    )
}

group_stats(df, region, metric = revenue)
group_stats(df, region, product, metric = units)

أدوات التحديد المنظم

library(dplyr)

df <- data.frame(
  id = 1:3,
  score_2022 = c(80,85,90),
  score_2023 = c(82,88,91),
  score_2024 = c(85,90,93),
  category = c('A','B','A')
)

# Select all score columns and compute their means
df %>%
  summarize(
    across(starts_with('score'), mean),
    n = n()
  )

دمج أنماط التقييم المنظم

library(dplyr)

df <- data.frame(
  dept = c('HR','HR','Eng','Eng'),
  salary = c(60000, 65000, 100000, 110000),
  bonus = c(5000, 6000, 15000, 18000)
)

# String-based column selection with .data
summarize_column <- function(data, group_col, value_col_name) {
  data %>%
    group_by(.data[[group_col]]) %>%
    summarize(
      mean = mean(.data[[value_col_name]]),
      total = sum(.data[[value_col_name]]),
      .groups = 'drop'
    )
}

summarize_column(df, 'dept', 'salary')
summarize_column(df, 'dept', 'bonus')

تحقق سريع

مراجعة: التقييم المنظم

library(dplyr)

df <- data.frame(
  group = c('A','A','B','B'),
  v1 = c(10, 20, 30, 40),
  v2 = c(5, 15, 25, 35)
)

# Reusable function using {{ }} + across
group_summary <- function(data, grp) {
  data %>%
    group_by({{ grp }}) %>%
    summarize(across(where(is.numeric), list(mean=mean, sum=sum)), .groups='drop')
}

group_summary(df, group)