Exploring Built-in Datasets in R: Learn mtcars, iris & airquality with Summary, Structure & Manipulation

🌤️ airquality Dataset

The airquality dataset contains daily air quality measurements in New York from May to September 1973. It includes variables such as:

• Ozone – Mean ozone in parts per billion (ppb)
• Solar.R – Solar radiation in Langleys
• Wind – Average wind speed (mph)
• Temp – Maximum daily temperature (°F)
• Month – Month of observation (5 = May, ..., 9 = September)
• Day – Day of the month

This dataset is useful for learning data cleaning, transformation, and basic statistical analysis in R.

🔹 Step 1: Load and Inspect the Dataset

# Load the dataset
data(airquality)

# Display first few rows
head(airquality)

# View structure and summary
str(airquality)
summary(airquality)

Explanation:

• data(airquality) loads the dataset from R's built-in datasets package.
• head() shows the first few rows, helping you see variable names and formats.
• str() reveals data types (numeric, integer, etc.) and number of observations.
• summary() provides minimum, mean, median, and maximum values for each column.

🔹 Step 2: Handling Missing Values

Some columns (like Ozone and Solar.R) contain missing values (NAs). We can detect and handle them using:

# Count missing values in Ozone
sum(is.na(airquality$Ozone))

# Replace missing Ozone values with mean
airquality$Ozone[is.na(airquality$Ozone)] <- mean(airquality$Ozone, na.rm = TRUE)

# View updated dataset
summary(airquality)

Explanation:

• is.na() identifies missing values (returns TRUE/FALSE).
• sum() counts total missing entries in the Ozone column.
• mean(..., na.rm = TRUE) calculates the average while ignoring NAs.
• We then replace all missing values with the calculated mean to make the dataset complete for analysis.

🔹 Step 3: Create New Derived Columns

We can add new columns to make data analysis more meaningful — for example, converting temperature to Celsius and categorizing air quality levels.

# Convert temperature from Fahrenheit to Celsius
airquality$Temp_C <- round((airquality$Temp - 32) * 5/9, 1)

# Create air quality categories based on Ozone levels
airquality$Ozone_Level <- ifelse(airquality$Ozone > 100, "High",
                           ifelse(airquality$Ozone > 50, "Moderate", "Low"))

# View a few rows
head(airquality)

Explanation:

• (Temp - 32) * 5/9 converts Fahrenheit to Celsius.
• round(..., 1) rounds the result to one decimal place for readability.
• ifelse() creates a new categorical column — "Low," "Moderate," or "High" ozone levels.
• New derived columns help students connect data cleaning with real-world interpretation.

🔹 Step 4: Monthly Air Quality Averages

We can group data by Month to find how air quality changes over time using aggregate():

# Compute monthly average Ozone and Temperature
monthly_avg <- aggregate(cbind(Ozone, Temp_C) ~ Month, data = airquality, FUN = mean)

# View result
monthly_avg

Explanation:

• aggregate() groups data by a variable — here Month.
• cbind(Ozone, Temp_C) combines multiple numeric columns for group averaging.
• FUN = mean applies the mean function to each group.
• The output helps identify which months had higher ozone and temperature levels.

🔹 Step 5: Filtering Specific Conditions

We can filter records where temperature is high and wind speed is low — conditions that may indicate poor air quality:

# Filter for hot days with low wind
poor_air_days <- subset(airquality, Temp_C > 30 & Wind < 8)

# View filtered records
head(poor_air_days)

Explanation:

• subset() extracts rows meeting specific logical conditions.
• Temp_C > 30 filters hot days.
• Wind < 8 filters calm wind conditions (less air movement).
• This subset helps analyze when ozone concentrations might be unusually high.

Overall, the airquality dataset helps students practice data cleaning, transformation, group analysis, and conditional filtering — all crucial skills for data analytics in R.