在R语言中按分类分组计算数值变量的均值、中位数、众数

Hey there! Let's tackle this problem step by step. You want to calculate descriptive stats (mean, median, mode) for Mass_kg grouped by Order_or_higher in R—here's how you can do it easily:

First, handle the mode (since R doesn't have a built-in mode function) #

Unlike mean and median, R doesn’t come with a default function to calculate mode. Let’s make a simple one that works for your numeric Mass_kg values:

get_mode <- function(x) {
  # Get unique values and find which occurs most frequently
  unique_vals <- unique(x)
  unique_vals[which.max(tabulate(match(x, unique_vals)))]
}

Note: This returns the first mode if there are multiple values with the same highest frequency. If you need to return all modes, use this modified version instead:

get_mode_multi <- function(x) {
  freq_table <- table(x)
  max_frequency <- max(freq_table)
  # Return all values that match the highest frequency
  names(freq_table[freq_table == max_frequency])
}

Option 1: Use dplyr (clean, readable approach) #

dplyr is perfect for grouped operations. First install it if you haven’t, then load the package and compute your stats:

# Install dplyr if needed (run once)
install.packages("dplyr")

# Load the package
library(dplyr)

# Replace `your_data` with the name of your actual dataset
grouped_stats <- your_data %>%
  group_by(Order_or_higher) %>%
  summarise(
    average_mass = mean(Mass_kg, na.rm = TRUE),  # na.rm handles missing values
    median_mass = median(Mass_kg, na.rm = TRUE),
    mode_mass = get_mode(Mass_kg)  # Use get_mode_multi if you need all modes
  )

# View the result
print(grouped_stats)

Option 2: Base R (no extra packages needed) #

If you prefer not to use external packages, you can use aggregate() and merge the results:

# Calculate each stat separately
mean_data <- aggregate(Mass_kg ~ Order_or_higher, data = your_data, FUN = mean, na.rm = TRUE)
median_data <- aggregate(Mass_kg ~ Order_or_higher, data = your_data, FUN = median, na.rm = TRUE)
mode_data <- aggregate(Mass_kg ~ Order_or_higher, data = your_data, FUN = get_mode)

# Merge into one dataframe
grouped_stats_base <- merge(merge(mean_data, median_data, by = "Order_or_higher"),
                            mode_data, by = "Order_or_higher")

# Rename columns for clarity
colnames(grouped_stats_base) <- c("Order_or_higher", "average_mass", "median_mass", "mode_mass")

# View the result
print(grouped_stats_base)

Just remember to replace your_data with the actual name of your dataset. The na.rm = TRUE argument is important—it ensures missing values in Mass_kg don’t break your calculations!

内容的提问来源于stack exchange，提问作者SomebodyNeedingHelp