NA-Werte entfernen und ersetzen

data_vals <- c(88, NA, 72, NA, 91, 65, NA, 78)
cat('Original data:', data_vals, '
')
cat('NA count:', sum(is.na(data_vals)), '
')

# Strategy 1: remove
cat('After removal:', data_vals[!is.na(data_vals)], '
')
# Strategy 2: replace with 0
replaced <- data_vals; replaced[is.na(replaced)] <- 0
cat('Replaced with 0:', replaced, '
')

response_times <- c(1.2, NA, 0.9, 1.5, NA, 1.1, 0.8, NA, 1.3)
cat('With NAs:    ', response_times, '
')
cat('Length:', length(response_times), '
')

clean_times <- response_times[!is.na(response_times)]
cat('Without NAs: ', clean_times, '
')
cat('Length:', length(clean_times), '
')
cat('Mean after removal:', round(mean(clean_times), 3), '
')

scores <- c(88, NA, 72, NA, 91, 65, NA, 78)
clean_scores <- na.omit(scores)
cat('Original:', scores, '
')
cat('Cleaned: ', as.numeric(clean_scores), '
')

# na.omit records which positions were removed
removed_at <- attr(clean_scores, 'na.action')
cat('NAs were at positions:', removed_at, '
')

df <- data.frame(
  name   = c('Alice', 'Bob', 'Carol', 'Dave', 'Eve'),
  age    = c(28, NA, 32, 45, 29),
  salary = c(55000, 72000, NA, 90000, 61000)
)
cat('Original rows:', nrow(df), '
')
df_clean <- na.omit(df)
cat('After na.omit rows:', nrow(df_clean), '
')
print(df_clean)

df <- data.frame(
  id  = 1:5,
  x   = c(1, NA, 3, 4, NA),
  y   = c(NA, 2, 3, NA, 5)
)
cc <- complete.cases(df)
cat('Complete cases (T/F):', cc, '
')
cat('Complete rows:
')
print(df[cc, ])
cat('Number complete:', sum(cc), '
')

# Replace with 0
counts <- c(5, NA, 3, NA, 8, 1, NA, 4)
counts_filled <- counts
counts_filled[is.na(counts_filled)] <- 0
cat('Original:', counts, '
')
cat('Filled:  ', counts_filled, '
')

# Replace with mean of present values
mean_val <- mean(counts, na.rm = TRUE)
counts_mean <- counts
counts_mean[is.na(counts_mean)] <- mean_val
cat('Mean-filled:', round(counts_mean, 1), '
')

temps <- c(22.1, NA, 19.8, NA, 25.1)
cat('Original:', temps, '
')

# Replace NAs with the median
median_temp <- median(temps, na.rm = TRUE)
filled_temps <- replace(temps, is.na(temps), median_temp)
cat('Filled:  ', filled_temps, '
')
cat('Original unchanged:', temps, '
')  # original not modified

# Manual forward-fill
readings <- c(10, NA, NA, 13, NA, 15, NA, NA, 18)
filled <- readings
for (i in seq_along(filled)) {
  if (is.na(filled[i]) && i > 1) {
    filled[i] <- filled[i - 1]
  }
}
cat('Original:     ', readings, '
')
cat('Forward-filled:', filled, '
')

categories <- c('A', NA, 'B', 'A', NA, 'C', NA, 'B')
cat('Original:', categories, '
')

# Replace with 'Unknown'
filled_cat <- replace(categories, is.na(categories), 'Unknown')
cat('Filled:  ', filled_cat, '
')

# Count each category
cat('Table:
')
print(table(filled_cat))

# Scores: replace NA with group mean
group   <- c('A', 'A', 'B', 'B', 'A', 'B')
scores  <- c(85, NA, 72, NA, 90, 78)

mean_a <- mean(scores[group == 'A'], na.rm = TRUE)
mean_b <- mean(scores[group == 'B'], na.rm = TRUE)

imputed <- scores
imputed[is.na(imputed) & group == 'A'] <- mean_a
imputed[is.na(imputed) & group == 'B'] <- mean_b

cat('Original:', scores, '
')
cat('Imputed: ', imputed, '
')

v <- c(5, NA, 8, NA, 3, 7)
cat('Remove:          ', v[!is.na(v)], '
')
cat('Replace with 0:  ', replace(v, is.na(v), 0), '
')
cat('Replace with mean:', replace(v, is.na(v), mean(v, na.rm=TRUE)), '
')

# Complete workflow: audit, then handle
data_raw <- c(82, NA, 75, NA, 91, 68, NA, 79)
cat('Missing:', sum(is.na(data_raw)), '/', length(data_raw), '
')

# Replace with median (robust to outliers)
imputed <- replace(data_raw, is.na(data_raw), median(data_raw, na.rm=TRUE))
cat('Before imputation mean:', round(mean(data_raw, na.rm=TRUE), 2), '
')
cat('After imputation mean: ', round(mean(imputed), 2), '
')