NA في الحسابات والتجميعات

المعامل na.rm

scores <- c(88, NA, 72, 95, NA, 81, 67)
cat('With na.rm=FALSE (default):
')
cat('  mean:', mean(scores), '
')           # NA
cat('  sum: ', sum(scores), '
')            # NA
cat('With na.rm=TRUE:
')
cat('  mean:', mean(scores, na.rm = TRUE), '
')  # 80.6
cat('  sum: ', sum(scores, na.rm = TRUE), '
')   # 403

mean() مع na.rm

temperatures <- c(22.1, NA, 19.8, 25.1, NA, 17.3, 20.0)

cat('Total elements:', length(temperatures), '
')
cat('Present elements:', sum(!is.na(temperatures)), '
')
cat('Mean (na.rm=TRUE):', mean(temperatures, na.rm = TRUE), '
')

# Manual verification
cat('Manual mean:', sum(temperatures, na.rm=TRUE) / sum(!is.na(temperatures)), '
')

sum() مع na.rm

sales_daily <- c(1200, NA, 980, 1450, NA, 1100, 890)
cat('Sum (default):', sum(sales_daily), '
')            # NA
cat('Sum (na.rm):  ', sum(sales_daily, na.rm = TRUE), '
')  # 5620

# Count observations meeting a condition (NA-safe)
cat('Days over 1000:', sum(sales_daily > 1000, na.rm = TRUE), '
')

min() وmax() مع na.rm

blood_pressure <- c(120, NA, 135, 118, NA, 142, 125, NA, 130)
cat('Max BP (default):', max(blood_pressure), '
')              # NA
cat('Max BP (na.rm):  ', max(blood_pressure, na.rm = TRUE), '
')  # 142
cat('Min BP (na.rm):  ', min(blood_pressure, na.rm = TRUE), '
')  # 118
cat('Range (na.rm):   ', range(blood_pressure, na.rm = TRUE), '
')

var() وsd() مع na.rm

exam_scores <- c(78, 85, NA, 92, 68, 75, NA, 88, 91, NA)
n_valid <- sum(!is.na(exam_scores))
cat('Valid observations:', n_valid, '
')
cat('Mean:   ', round(mean(exam_scores, na.rm = TRUE), 2), '
')
cat('SD:     ', round(sd(exam_scores, na.rm = TRUE), 2), '
')
cat('Var:    ', round(var(exam_scores, na.rm = TRUE), 2), '
')

median() وquantile() مع na.rm

incomes <- c(45000, NA, 52000, 48000, NA, 210000, 51000, NA, 49000)
cat('Observations:', sum(!is.na(incomes)), '
')
cat('Median income:', median(incomes, na.rm = TRUE), '
')
cat('Mean income:  ', mean(incomes, na.rm = TRUE), '
')  # pulled up by 210000
cat('25th pctile:  ', quantile(incomes, 0.25, na.rm = TRUE), '
')
cat('75th pctile:  ', quantile(incomes, 0.75, na.rm = TRUE), '
')

prod() وcumsum() مع na.rm

growth_rates <- c(1.05, NA, 1.03, 1.08, NA, 1.02)
cat('Product of rates:', prod(growth_rates, na.rm = TRUE), '
')

# cumsum propagates NAs
values <- c(10, 20, NA, 40, 50)
cat('cumsum (with NA):', cumsum(values), '
')

# Workaround: replace NA first
filled <- replace(values, is.na(values), 0)
cat('cumsum (NA=0):   ', cumsum(filled), '
')

na.rm في دوال Apply

m <- matrix(c(88,NA,72, 95,81,NA, 67,75,90), nrow = 3)
cat('Matrix:
'); print(m)

# Row means ignoring NAs
cat('Row means (na.rm=TRUE):', apply(m, 1, mean, na.rm = TRUE), '
')

# Col means ignoring NAs
cat('Col means (na.rm=TRUE):', apply(m, 2, mean, na.rm = TRUE), '
')

rowSums() / colSums() مع na.rm

sales <- matrix(c(100,NA,80, NA,90,70, 110,85,NA), nrow = 3)
cat('Sales matrix:
'); print(sales)

cat('Row sums (na.rm=F):', rowSums(sales), '
')             # NAs propagate
cat('Row sums (na.rm=T):', rowSums(sales, na.rm = TRUE), '
')
cat('Col means (na.rm=T):', colMeans(sales, na.rm = TRUE), '
')

مقارنة: na.rm=FALSE مقابل TRUE

# Always check: how much data is missing BEFORE using na.rm=TRUE
collected <- c(78, NA, 85, NA, 91, 74, NA, 88, 82, NA)
pct_missing <- mean(is.na(collected)) * 100
cat('Missing:', round(pct_missing, 1), '% of data
')

if (pct_missing < 20) {
  cat('Acceptable: computing mean with na.rm=TRUE
')
  cat('Mean:', round(mean(collected, na.rm = TRUE), 2), '
')
} else {
  cat('Too much missing data — investigate before computing
')
}

na.rm في الدوال التي ينشئها المستخدم

# Custom function with na.rm support
cv <- function(x, na.rm = FALSE) {
  # Coefficient of Variation = SD / mean
  s <- sd(x, na.rm = na.rm)
  m <- mean(x, na.rm = na.rm)
  return(s / m)
}

readings <- c(22.1, NA, 19.8, 25.1, NA, 17.3, 20.0)
cat('CV (na.rm=FALSE):', cv(readings), '
')          # NA
cat('CV (na.rm=TRUE): ', round(cv(readings, na.rm = TRUE), 4), '
')

تحقق سريع

مراجعة: NA في العمليات الحسابية

# Complete summary with na.rm
data_vec <- c(55, NA, 72, 88, NA, 61, 79, NA, 93, 68)
cat('N valid:', sum(!is.na(data_vec)), '
')
cat('Mean:  ', round(mean(data_vec, na.rm=TRUE), 2), '
')
cat('Median:', median(data_vec, na.rm=TRUE), '
')
cat('SD:    ', round(sd(data_vec, na.rm=TRUE), 2), '
')
cat('Min:   ', min(data_vec, na.rm=TRUE), '
')
cat('Max:   ', max(data_vec, na.rm=TRUE), '
')