Handling missing values (drop_na, fill) in R Programming - Step-by-Step Execution

Concept Flow - Handling missing values (drop_na, fill)

Start with data frame

↓

Check for missing values

↓

drop_na()

↓

Remove rows

↓

Cleaned data frame

Start with a data frame, check for missing values, then either remove rows with missing data using drop_na() or fill missing values using fill(), resulting in a cleaned data frame.

Execution Sample

R Programming

library(tidyr)
data <- data.frame(x = c(1, NA, 3), y = c(NA, 2, 3))
data_clean <- drop_na(data)
data_filled <- fill(data, x, .direction = "down")

This code creates a data frame with missing values, then removes rows with any NA using drop_na(), and fills missing x values downward using fill().

Execution Table

Step	Data Frame State	Action	Resulting Data Frame
1	x: 1, NA, 3; y: NA, 2, 3	Initial data frame with missing values	x: 1, NA, 3; y: NA, 2, 3
2	x: 1, NA, 3; y: NA, 2, 3	Apply drop_na() to remove rows with any NA	x: 3; y: 3 (only row 3 remains)
3	x: 1, NA, 3; y: NA, 2, 3	Apply fill(x, .direction = "down") to fill NA in x	x: 1, 1, 3; y: NA, 2, 3
4	x: 1, 1, 3; y: NA, 2, 3	No further action	Final cleaned data frames ready

💡 All missing values handled either by removal or filling; process complete.

Variable Tracker

Variable	Start	After drop_na	After fill	Final
data	x: 1, NA, 3; y: NA, 2, 3	Unchanged	Unchanged	Unchanged
data_clean	NA	x: 3; y: 3	NA	x: 3; y: 3
data_filled	NA	NA	x: 1, 1, 3; y: NA, 2, 3	x: 1, 1, 3; y: NA, 2, 3

Key Moments - 2 Insights

Why does drop_na() remove the second row but keep the third row even though the third row has no missing x value?

drop_na() removes rows with any NA in any column. The second row has NA in x, so it is removed. The third row has no NA in any column, so it stays (see execution_table step 2).

How does fill() decide what value to use to replace NA in the x column?

fill() replaces NA with the last non-NA value above it in the column (downward direction). So the NA in row 2 is replaced by 1 from row 1 (see execution_table step 3).

Visual Quiz - 3 Questions

Look at the execution_table at step 2. What rows remain after drop_na() is applied?

A First and third rows

B Only the third row

C Only the first row

D All rows

💡 Hint

Check the 'Resulting Data Frame' column at step 2 in execution_table.

According to variable_tracker, what is the value of x in the second row after fill() is applied?

A NA

B 3

C 1

D 2

💡 Hint

Look at 'data_filled' column in variable_tracker for the x variable.

If we changed fill() direction to 'up', what would happen to the NA in x at row 2?

A It would be replaced by 3 from row 3

B It would remain NA

C It would be replaced by 1 from row 1

D All rows would be removed

💡 Hint

fill() with direction 'up' fills NA with next non-NA value below (see fill() behavior).

Concept Snapshot

Handling missing values in R with tidyr:
- drop_na(data): removes rows with any NA
- fill(data, column, .direction): fills NA with nearby values
- drop_na removes rows; fill replaces NA
- Use fill direction 'down' or 'up' to control filling
- Clean data frames ready for analysis

Full Transcript

We start with a data frame containing missing values (NA). We use drop_na() to remove any rows that have missing values in any column, leaving only complete rows. Alternatively, we use fill() to replace missing values in a specific column by carrying forward or backward the last known value. In the example, drop_na() removes the second row because it has NA, and fill() replaces the NA in the second row's x column with the value from the first row. This way, we clean the data by either removing or filling missing values, preparing it for further use.