Chapter 2:

Data Visualization
Objective
● Understand the concept and importance of data visualization in the context of
data mining.
● Explore the goals and benefits of using data visualization techniques.
● Learn various techniques for numerical data, including line charts, bar charts,
scatter plots, etc.
● Understand the techniques specific to non-numerical data, such as pie charts,
word clouds, network graphs, etc.
● Gain insights into the visualization of dashboards, including the components,
design principles, and interactive features.

2
Visualization of Numerical Data
Numerical Data
● Numerical data consists of quantitative values that can be measured and
represented using numerical scales. Visualizing numerical data helps us
understand the distribution, trends, and relationships between numerical
variables.
Numerical Data Visualization
● Numerical data visualization refers to the graphical representation of
quantitative data using charts, graphs, and plots to communicate insights
effectively.
● Human brains process visual information more efficiently than raw data.
● Visualizations help in identifying patterns, trends, and outliers in numerical data,
leading to better decision-making. 3
Visualization of Numerical Data
Different Kinds of Visualizations and Their Applications
● Line Graphs: Depicting Trends over Time or Ordered Data
○ Line graphs connect data points with lines to show trends over time or an
ordered variable.
○ Representing stock market trends, tracking temperature changes, showing
population growth.

4
Visualization of Numerical Data
Different Kinds of Visualizations and Their Applications
● Bar Charts: Displaying Categorical Data with Rectangles
○ Bar charts use rectangular bars to compare categorical data.
○ Visualizing survey results, comparing sales of different products,
displaying frequency distributions.

5
Visualization of Numerical Data
Different Kinds of Visualizations and Their Applications
● Scatter Plots: Visualizing the Relationship between Two Variables
○ Scatter plots use data points to display the relationship between two
numerical variables.
○ Assessing correlation between variables, identifying clusters or trends,
detecting outliers.

6
Visualization of Numerical Data
Choosing the Right Visualization for Your Data
● Factors Influencing Visualization Selection:
○ Nature of data (categorical, ordinal, numerical): Different data types
require specific visualizations.
○ Data distribution and granularity: Data distribution impacts the choice of
visualization.
● Guidelines for Matching Data Types with Visualizations:
○ Decision tree for choosing appropriate visualizations: A step-by-step guide
for selecting the right chart type.
○ Examples of correct and incorrect visualization choices: Illustrations to
reinforce the concept.
7
Visualization of Numerical Data
Line Charts and Area Charts
● Line charts display data points connected by lines, representing the trend or
change in a variable over time or another continuous dimension.
● Area charts are similar to line charts but filled with colors or patterns below the
line, representing the cumulative values of the variable.

[Credit: https://www.fusioncharts.com/ ] 8
Visualization of Numerical Data
Bar Charts and Histograms
● Bar charts use rectangular bars of varying lengths or heights to represent the
values of different categories or groups. They are useful for comparing discrete
or categorical data.
● Histograms display the distribution of continuous data by dividing it into bins or
intervals and representing the frequency or count of data points within each bin
as vertical bars.

[Credit: https://www.fusioncharts.com/ ] 9
Visualization of Numerical Data
Scatter Plots and Bubble Charts
● Scatter plots show the relationship
between two numerical variables.
Each data point is plotted as a point
on the graph, with one variable on
the x-axis and the other on the y-axis.
● Bubble charts are an extension of
scatter plots where an additional
numerical variable is represented by
the size or color of the data points,
adding another dimension to the
visualization.
[Credit: https://www.fusioncharts.com/ ] 10
Visualization of Numerical Data
Box Plots and Violin Plots
● Box plots (also known as box-and-whisker
plots) display the summary statistics of a
numerical variable, including the minimum,
maximum, median, quartiles, and outliers.
They provide insights into the distribution
and skewness of the data.
● Violin plots combine a box plot with a
kernel density plot, providing a more
detailed view of the distribution and density
of the data.

[Credit: https://www.fusioncharts.com/ ] 11
Visualization of Numerical Data
Heatmaps and Treemaps
● Heatmaps use color-coded cells in a grid to
represent the values of a numerical variable
across two dimensions. They are effective
for visualizing large datasets and
identifying patterns or correlations.
● Treemaps represent hierarchical data as
nested rectangles, with the size of each
rectangle proportional to a numerical value.
They are useful for displaying hierarchical
relationships and comparing proportions.

[Credit: https://www.fusioncharts.com/ ] 12
Visualization of Numerical Data
Elements of Design and Color Usage
● Importance of Design Principles in Data Visualization:
○ Emphasizing clarity, simplicity, and consistency: Addressing the
significance of design in data visualization.
○ Well-designed vs. poorly designed visualizations

[Credit: https://www.fusioncharts.com/ ] 13
Visualization of Numerical Data
Elements of Design and Color Usage
● Choosing the Right Color Palettes for Numerical Data:
○ Addressing potential color blindness issues: Ensuring accessibility and
inclusivity.
○ Examples of color palettes suitable for numerical data

[Credit: https://www.fusioncharts.com/ ] 14
Visualization of Numerical Data
Elements of Design and Color Usage
● Color Blindness Considerations and Accessibility:
○ Designing visualizations accessible to color-blind users: Applying best
practices for inclusive design.
○ Visual examples of visualizations with and without color blindness
considerations

[Credit: https://www.fusioncharts.com/ ] 15
Visualization of Numerical Data
Best Practices for Visualizing Numerical Data
● Choose the appropriate visualization technique based on the nature of the data
and the insights you want to convey.
● Ensure clear labeling of axes, titles, and legends to provide context and aid
interpretation.
● Use appropriate scales and axes ranges to avoid distorting the data or misleading
the viewer.
● Apply color and visual cues thoughtfully to highlight patterns, trends, or specific
data points.
● Consider adding interactivity, such as zooming or filtering, to allow users to
explore the data in more detail.
16
Summary
Visualization of Numerical Data
● Techniques for Numerical Data:
- Learn diverse visualization techniques.
- Examples include line charts, bar charts, scatter plots, etc.

17