Data visualization

Data visualization in R is primarily done using base R functions or popular libraries like ggplot2, which is part of the tidyverse package. Data visualization transforms raw data into meaningful insights through charts, graphs, and plots. R offers two main methods for visualization:

Base R functions is helpful for Quick and simple visualizations. ggplot2 is a powerful library for creating complex and customizable plots.

Using ggplot2 for Advanced Visualizations

Make sure you have the necessary R packages installed: install.packages(“ggplot2”) # For data visualization install.packages(“dplyr”) # For data manipulation

Load the ggplot2 and dplyr libraries

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.4.2

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.4.2

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

Bar Plot

A bar plot (or bar chart) is a graphical representation of categorical data using rectangular bars where the length or height of each bar corresponds to the data’s value or frequency.

Types of Bar Plots:

Vertical Bar Plot: Bars are drawn vertically; height represents the value.
Horizontal Bar Plot: Bars are drawn horizontally; length represents the value.
Stacked Bar Plot: Multiple data series stacked on top of each other in a single bar.
Grouped Bar Plot: Bars representing different groups placed side by side for comparison.

Key Components:

X-axis (or Y-axis for horizontal bars): Represents the categories.
Y-axis (or X-axis for horizontal bars): Represents the values or frequency.
Bars: Show the magnitude of the data for each category.
Labels & Title: Improve clarity and interpretation.

Uses:

Comparing values across categories.
Showing trends over time (if categories are time-based).
Visualizing frequencies or counts in survey or research data.

Advantages:

Simple and easy to interpret.
Effective for comparing data across categories.

Disadvantages:

Not ideal for displaying continuous data.
Can become cluttered with too many categories.

1. Let us take a quick example.

Using Base R for Quick Plots

Sample data

data <- data.frame(
  Category = c("A", "B", "C", "D"),
  Value = c(10, 23, 17, 35)
)

Bar Plot

barplot(data$Value, names.arg = data$Category, 
        col = "skyblue", main = "Base R Bar Plot", ylab = "Value")

2. Another example of a bar plot

ggplot(data, aes(x = Category, y = Value, fill = Category)) +
  geom_bar(stat = "identity") +
  theme_minimal() +
  labs(title = "ggplot2 Bar Plot", y = "Value")

3. Basic Bar Plot – Base R

Plotting the count of cars by the number of cylinders (cyl). Displays how many cars have 4, 6, or 8 cylinders.

Load mtcars dataset

data(mtcars)

Convert ‘cyl’ to a factor

mtcars$cyl <- as.factor(mtcars$cyl)

Create a frequency table for cylinders

cyl_counts <- table(mtcars$cyl)

Base R Bar Plot

barplot(cyl_counts,
        main = "Number of Cars by Cylinders",
        xlab = "Number of Cylinders",
        ylab = "Count of Cars",
        col = c("skyblue", "salmon", "lightgreen"),
        border = "black")

4. Bar Plot Using ggplot2

Bar plot showing counts with ggplot2.

ggplot(mtcars, aes(x = cyl, fill = cyl)) +
  geom_bar() +
  labs(title = "Count of Cars by Number of Cylinders",
       x = "Number of Cylinders", y = "Count of Cars") +
  scale_fill_manual(values = c("skyblue", "salmon", "lightgreen")) +
  theme_minimal()

5. Stacked Bar Plot

See how automatic and manual cars are distributed within each cylinder category.

Visualizing the number of cylinders stacked by the type of transmission (am).

Convert ‘am’ to a factor (0 = Automatic, 1 = Manual)

mtcars$am <- factor(mtcars$am, labels = c("Automatic", "Manual"))

Stacked Bar Plot

ggplot(mtcars, aes(x = cyl, fill = am)) +
  geom_bar(position = "stack") +
  labs(title = "Cylinders by Transmission Type",
       x = "Number of Cylinders", y = "Count of Cars") +
  scale_fill_manual(values = c("lightblue", "orange")) +
  theme_light()

6. Grouped (Dodged) Bar Plot

Separate bars for each transmission type.

Easy to compare the number of manual vs. automatic cars within each cylinder group.

ggplot(mtcars, aes(x = cyl, fill = am)) +
  geom_bar(position = "dodge") +
  labs(title = "Cylinders by Transmission Type (Grouped)",
       x = "Number of Cylinders", y = "Count of Cars") +
  scale_fill_manual(values = c("lightblue", "orange")) +
  theme_classic()

7. Horizontal Bar Plot

ggplot(mtcars, aes(x = cyl, fill = cyl)) +
  geom_bar() +
  coord_flip() +  # Flips the axes
  labs(title = "Horizontal Bar Plot: Cars by Cylinders",
       x = "Count of Cars", y = "Number of Cylinders") +
  theme_minimal()

Box Plot

A box plot (or box-and-whisker plot) is a standardized way of displaying the distribution of data based on a five-number summary: Minimum, First Quartile (Q1), Median (Q2), Third Quartile (Q3), and Maximum. It is especially useful for identifying outliers, spread, and central tendency in a dataset.

Key Components of a Box Plot:

Box (Interquartile Range - IQR):

Represents the middle 50% of the data.
Lower Bound (Q1 - 25th percentile): The median of the lower half.
Upper Bound (Q3 - 75th percentile): The median of the upper half.
IQR = Q3 - Q1 → Measures data spread.

Median (Q2 - 50th percentile):

Shown as a horizontal line inside the box.
Indicates the central tendency of the data.

Whiskers:

Extend from the box to the smallest and largest data points within 1.5 × IQR from Q1 and Q3.
They help to visualize the overall range of the dataset.

Outliers:

Data points lying outside the whiskers (beyond 1.5 × IQR).
Displayed as dots or asterisks.

Minimum & Maximum:

The lowest and highest data points within the whiskers.

How to Interpret a Box Plot:

Median Position:

If the median is centered, the data is symmetric.
If the median is closer to Q1 or Q3, it indicates skewness.

Spread of Data (IQR):

A wider box suggests more variability.
A narrow box indicates less spread.

Skewness:

Right-skewed (positive skew) → longer upper whisker.
Left-skewed (negative skew) → longer lower whisker.

Outliers:

Indicates unusual data points that may need further investigation.

Advantages of Box Plots:

Easy to compare distributions between groups. Summarizes data spread, central tendency, and outliers. Useful for large datasets.

Limitations:

Does not show the distribution’s exact shape (e.g., bimodality).
Less informative for small datasets.

1. Using Base R (boxplot())

Sample data

radd <- data.frame(
  Group = rep(c("A", "B", "C"), each = 20),
  Value = c(rnorm(20, mean = 5), rnorm(20, mean = 7), rnorm(20, mean = 6))
)

Create boxplot

boxplot(Value ~ Group, data = radd,
        main = "Boxplot Example (Base R)",
        xlab = "Group",
        ylab = "Value",
        col = c("skyblue", "salmon", "lightgreen"),
        border = "black")

2. Using ggplot2 for Enhanced Visualization

Sample data

datas <- data.frame(
  Group = rep(c("A", "B", "C"), each = 20),
  Value = c(rnorm(20, mean = 5), rnorm(20, mean = 7), rnorm(20, mean = 6))
)

Create boxplot

ggplot(datas, aes(x = Group, y = Value, fill = Group)) +
  geom_boxplot() +
  labs(title = "Boxplot Example (ggplot2)",
       x = "Group", y = "Value") +
  theme_minimal()

3. Boxplot of Miles per Gallon (mpg) by Number of Cylinders (cyl) – Base R

Compare fuel efficiency across cars with 4, 6, and 8 cylinders. Cars with 4 cylinders generally have higher MPG.

Load mtcars dataset

data(mtcars)

Convert ‘cyl’ to a factor for categorical plotting

mtcars$cyl <- as.factor(mtcars$cyl)

Base R Boxplot

boxplot(mpg ~ cyl, data = mtcars,
        main = "MPG by Number of Cylinders",
        xlab = "Number of Cylinders",
        ylab = "Miles Per Gallon (MPG)",
        col = c("lightblue", "salmon", "lightgreen"),
        border = "black")

4. Enhanced Boxplot Using ggplot2

Load ggplot2 library

ggplot2 Boxplot

ggplot(mtcars, aes(x = cyl, y = mpg, fill = cyl)) +
  geom_boxplot() +
  labs(title = "MPG by Number of Cylinders (ggplot2)",
       x = "Number of Cylinders",
       y = "Miles Per Gallon (MPG)") +
  scale_fill_manual(values = c("skyblue", "salmon", "lightgreen")) +
  theme_minimal()

5. Adding Outliers & Jitter for Better Data Spread

Outliers are in red. Jittered points show the exact data distribution.

ggplot(mtcars, aes(x = cyl, y = mpg, fill = cyl)) +
  geom_boxplot(outlier.color = "red", outlier.shape = 16, outlier.size = 2) +
  geom_jitter(width = 0.2, alpha = 0.6) +  # Adds data points
  labs(title = "MPG by Number of Cylinders with Outliers Highlighted",
       x = "Number of Cylinders", y = "MPG") +
  scale_fill_manual(values = c("skyblue", "salmon", "lightgreen")) +
  theme_light()

6. Horizontal Boxplot Example

ggplot(mtcars, aes(y = mpg, x = cyl, fill = cyl)) +
  geom_boxplot() +
  coord_flip() +  # Flips axes
  labs(title = "Horizontal Boxplot: MPG by Cylinders",
       x = "Number of Cylinders", y = "MPG") +
  theme_classic()

Line Plot

A line plot (or line graph) is a type of chart used to display data points connected by straight lines. It is commonly used to show trends over time, continuous data, or relationships between variables.

Key Features of a Line Plot:

Axes:

X-axis usually represents time or independent variables.
Y-axis shows the dependent variable or the data being measured.

Data Points:

Individual data values plotted as points on the graph.

Connecting Lines:

Straight lines connect data points to highlight trends and changes.

When to Use a Line Plot:

To show trends over time (e.g., sales over months).
To compare multiple data series.
To analyze patterns, fluctuations, or seasonality.

dvantages:

Simple and easy to interpret.
Effective for showing continuous data.
Useful for identifying trends, spikes, and declines.

Limitations:

Not ideal for large datasets with many fluctuations.
Can be misleading if scales are inconsistent.

1. Example of Line plot

df <- data.frame(Time = 1:10, Measurement = cumsum(rnorm(10)))
ggplot(df, aes(x = Time, y = Measurement)) +
  geom_line(color = "blue", size = 1.2) +
  labs(title = "Line Plot", x = "Time", y = "Measurement") +
  theme_light()

## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

2. Basic Line Graph – Base R

Plotting mpg (miles per gallon) as a function of car index (just the row number) in mtcars.

Load mtcars dataset

data(mtcars)

Basic Line Graph in Base R This graph shows MPG against the car index (row number), connecting the data points to show the trend.

plot(mtcars$mpg, type = "o", col = "blue", 
     main = "Miles per Gallon (MPG) by Car Index",
     xlab = "Car Index (Row Number)", ylab = "Miles per Gallon (MPG)",
     pch = 16, lwd = 2)

3. Line Graph Using ggplot2

Plotting mpg versus hp (horsepower) as a line graph.

ggplot(mtcars, aes(x = hp, y = mpg)) +
  geom_line(color = "blue", size = 1) +
  labs(title = "MPG vs Horsepower", x = "Horsepower", y = "Miles per Gallon (MPG)") +
  theme_minimal()

4. Line Graph with Multiple Series Using ggplot2

Plotting mpg versus hp with different lines for number of cylinders (cyl). Each cylinder group (4, 6, or 8 cylinders) is represented by a different line with a distinct color.

ggplot(mtcars, aes(x = hp, y = mpg, color = factor(cyl))) +
  geom_line(size = 1) +
  labs(title = "MPG vs Horsepower by Number of Cylinders",
       x = "Horsepower", y = "Miles per Gallon (MPG)") +
  scale_color_manual(values = c("red", "green", "blue")) +
  theme_minimal()

5. Adding Points to the Line Graph Using ggplot2

Plotting mpg as a function of hp and adding data points.

ggplot(mtcars, aes(x = hp, y = mpg)) +
  geom_line(color = "blue", size = 1) +
  geom_point(color = "red", size = 3) +
  labs(title = "MPG vs Horsepower with Data Points",
       x = "Horsepower", y = "Miles per Gallon (MPG)") +
  theme_light()

6. Smooth Line (Trend Line)

Adding a smoothed line to visualize trends more clearly.

ggplot(mtcars, aes(x = hp, y = mpg)) +
  geom_point(color = "red", size = 3) +
  geom_smooth(method = "loess", color = "blue", size = 1) +
  labs(title = "MPG vs Horsepower with Trend Line",
       x = "Horsepower", y = "Miles per Gallon (MPG)") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Scatter Plot

A scatter plot (or scatter chart) is a type of graph used to represent the relationship between two continuous variables. Each point on the graph represents an observation in the dataset, with the position on the X-axis and Y-axis corresponding to the values of the variables.

Key Features of a Scatter Plot:

Axes:

X-axis represents one variable (independent variable).
Y-axis represents the second variable (dependent variable).

Data Points:

Each point on the graph represents a single data point, plotted according to its x and y values.

Trend/Relationship:

Scatter plots help identify patterns, relationships, and correlations between the two variables (e.g., linear, non-linear, or no relationship).

When to Use a Scatter Plot:

To explore the relationship between two continuous variables (e.g., height and weight, age and income).
To visually check for correlation (positive, negative, or none).
To identify outliers and clusters in the data.

dvantages:

Simple and effective for displaying the relationship between two variables.
Helps to easily spot correlation patterns, outliers, and trends.
Great for visualizing large datasets.

Limitations:

May become cluttered with large datasets.
Cannot be used for categorical data directly.
Doesn’t provide information on causality—just correlation.

Types of Patterns in a Scatter Plot:

Positive Correlation: Points tend to rise as you move right (e.g., height and weight).
Negative Correlation: Points tend to fall as you move right (e.g., income vs. unemployment rate).
No Correlation: No discernible pattern or trend (e.g., shoe size vs. IQ).
Curvilinear Relationship: A curved or U-shape pattern.

Outliers:

Data points that are distant from others, indicating unusual values.

Tips for Effective Scatter Plots:

Use color or size to represent additional variables.
Add a trend line or regression line to summarize relationships.
Ensure axis scales are appropriate to avoid misleading interpretations.

1. Scatter Plot with Trend Line

ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point(color = "darkgreen") +
  geom_smooth(method = "lm", col = "red") +
  labs(title = "MPG vs Weight", x = "Weight", y = "Miles Per Gallon")

## `geom_smooth()` using formula = 'y ~ x'

2. Basic Scatter Plot – Base R

Plotting mpg (miles per gallon) against hp (horsepower) in mtcars.

Load mtcars dataset

data(mtcars)

Basic Scatter Plot in Base R The scatter plot shows the relationship between horsepower and miles per gallon.

plot(mtcars$hp, mtcars$mpg, 
     main = "Scatter Plot of MPG vs Horsepower",
     xlab = "Horsepower", ylab = "Miles per Gallon (MPG)",
     pch = 19, col = "blue")

3. Scatter Plot Using ggplot2

Plotting mpg versus hp with custom styling using ggplot2.

ggplot2 Scatter Plot

ggplot(mtcars, aes(x = hp, y = mpg)) +
  geom_point(color = "blue", size = 3) +
  labs(title = "Scatter Plot of MPG vs Horsepower", x = "Horsepower", y = "Miles per Gallon (MPG)") +
  theme_minimal()

4. Scatter Plot with Color Grouping by Cylinders

Points are colored based on the number of cylinders (4, 6, 8 cylinders). Each group (cylinder type) has a different color for better distinction.

Scatter plot of mpg vs hp, where points are colored by the number of cylinders (cyl).

ggplot(mtcars, aes(x = hp, y = mpg, color = factor(cyl))) +
  geom_point(size = 3) +
  labs(title = "MPG vs Horsepower by Number of Cylinders", x = "Horsepower", y = "Miles per Gallon (MPG)") +
  scale_color_manual(values = c("red", "green", "blue")) +
  theme_light()

5. Scatter Plot with Smooth Trend Line

Adding a smooth trend line to the scatter plot to visualize the relationship. The red trend line (linear regression) helps show the overall relationship between horsepower and MPG.

ggplot(mtcars, aes(x = hp, y = mpg)) +
  geom_point(color = "blue", size = 3) +
  geom_smooth(method = "lm", color = "red", size = 1) +
  labs(title = "MPG vs Horsepower with Linear Trend Line", x = "Horsepower", y = "Miles per Gallon (MPG)") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

6. Scatter Plot with Jitter for Overlapping Points

Using jitter to add noise to overlapping points for better visibility. Jittering helps separate points that are clustered in the same spot, especially when multiple cars have the same mpg or hp values.

ggplot(mtcars, aes(x = hp, y = mpg)) +
  geom_jitter(color = "blue", size = 3, width = 0.2, height = 0.2) +
  labs(title = "MPG vs Horsepower with Jitter", x = "Horsepower", y = "Miles per Gallon (MPG)") +
  theme_minimal()

7. Adding a Regression Line with Confidence Interval

Adding a regression line with the confidence interval to the scatter plot. Confidence interval (shaded area around the red line) shows the range within which the true regression line is expected to fall.

ggplot(mtcars, aes(x = hp, y = mpg)) +
  geom_point(color = "blue", size = 3) +
  geom_smooth(method = "lm", se = TRUE, color = "red", size = 1) +
  labs(title = "MPG vs Horsepower with Regression Line and Confidence Interval",
       x = "Horsepower", y = "Miles per Gallon (MPG)") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Conclusion

In this tutorial, we explored different methods for visualizing data in R. We started with basic plotting techniques in Base R and then moved to more advanced visualizations using ggplot2.

Base R plots like bar plots, scatter plots, histograms, and boxplots provide a quick way to visualize data and can be useful for exploratory data analysis.

ggplot2 allows for more refined and customizable visualizations. It provides a wide range of functionalities such as regression lines, faceting, and aesthetics, which help present data in a more clear and insightful manner.

DATA VISUALIZATION

Oumo David

2025-02-21

Data visualization

Using ggplot2 for Advanced Visualizations

Bar Plot

Types of Bar Plots:

Key Components:

Uses:

Advantages:

Disadvantages:

1. Let us take a quick example.

2. Another example of a bar plot

3. Basic Bar Plot – Base R

4. Bar Plot Using ggplot2

5. Stacked Bar Plot

6. Grouped (Dodged) Bar Plot

7. Horizontal Bar Plot

Box Plot

Key Components of a Box Plot:

How to Interpret a Box Plot:

Advantages of Box Plots:

Limitations:

1. Using Base R (boxplot())

2. Using ggplot2 for Enhanced Visualization

3. Boxplot of Miles per Gallon (mpg) by Number of Cylinders (cyl) – Base R

4. Enhanced Boxplot Using ggplot2

5. Adding Outliers & Jitter for Better Data Spread

6. Horizontal Boxplot Example

Line Plot

Key Features of a Line Plot:

1. Example of Line plot

2. Basic Line Graph – Base R

3. Line Graph Using ggplot2

4. Line Graph with Multiple Series Using ggplot2

5. Adding Points to the Line Graph Using ggplot2

6. Smooth Line (Trend Line)

Scatter Plot

Key Features of a Scatter Plot:

1. Scatter Plot with Trend Line

2. Basic Scatter Plot – Base R

3. Scatter Plot Using ggplot2

4. Scatter Plot with Color Grouping by Cylinders

5. Scatter Plot with Smooth Trend Line

6. Scatter Plot with Jitter for Overlapping Points

7. Adding a Regression Line with Confidence Interval

Conclusion