Welcome back! In the previous lessons, we explored various techniques to reshape and tidy data using the tidyr package in R. These skills are essential for transforming data into a format suitable for analysis. Now, we will focus on handling missing values — an inevitable part of any real-world dataset. Get ready to learn how to clean data by using drop_na and replace_na functions.

In this lesson, you will learn how to:

1. Drop Rows with Missing Values: Remove rows that contain NA (missing) values using the drop_na function. This is useful when missing data cannot be filled or when it represents a negligible portion of your dataset.
2. Replace Missing Values: Impute missing values with meaningful substitutes, such as averages or specific constants, using the replace_na function. This helps in retaining all data points while mitigating the impact of missing information.

Let's look at an example to illustrate these functions:

R
Copy to clipboard
1# Suppress package startup messages for a cleaner output
2suppressPackageStartupMessages(library(tidyr))
3suppressPackageStartupMessages(library(dplyr))
4
5# Sample Data
6data <- tibble(
7  Person = c("John", "Jane", "Emily", "Alex"),
8  Age = c(28, NA, 35, 29),
9  Weight = c(NA, 60, 70, 80)
10)
11
12# Drop rows with NA values
13dropped_data <- drop_na(data)
14
15# Replace NA values with averages
16filled_data <- data %>%
17  mutate(
18    Age = replace_na(Age, mean(Age, na.rm = TRUE)),
19    Weight = replace_na(Weight, mean(Weight, na.rm = TRUE))
20  )

NA in R represents missing values. In the above data data frame:

• For "Jane," the Age is missing (NA).
• For "John," the Weight is missing (NA).

Handling missing data is crucial for maintaining the integrity of your dataset. Missing values can lead to misleading analyses and incorrect conclusions. By effectively managing these gaps, you ensure that your data is more reliable and your analyses are more accurate.

Dropping rows with missing values might be necessary when the missingness is critical to the analysis or the proportion of missing values is small. On the other hand, replacing missing values allows you to use all available data and can be especially useful when the missing values are widespread but not necessarily fatal to the analysis.

Ready to enhance your data cleaning skills? Let’s dive into the practice section and apply these techniques to handle missing values efficiently.