Multivariate Data
Visualization
Rahmatin Nur Amalia
Program Studi Sains Data, FSAD, Institut Teknologi Sepuluh Nopember
Today’s Topics
Data Visualization:
▪ What? Why?
▪ Type of Graphs
▪ Technique
Team Teaching:
• Novri Suhermi (M1-M5)
• Rahmatin Nur A (M6-M10)
• Muhammad Ahsan (M10-M14)
What is Data Visualization?
Data Visualization is the act of taking information (data) and placing it into a visual
context, such as a map or graph. Data visualization make big and small data easier for the
human brain understand, and visualization also makes it easier to detect pattern trends,
and outliers in groups of data.
In the world of Big Data, data visualization tools and technologies are essential to
analyze massive amounts of information and make data-driven decisions.
Why it is Important?
Anscombe’s Quartet,
Completely different pattern
Anscombe’s Quartet,
The same mean, variance, and correlation score
Data Visualization Roles
❖ Showing change over time
❖ Showing a part-to-whole
composition
❖ Depicting flows and processes
❖ Looking at how data is distributed
❖ Comparing values between groups
❖ Observing relationships between
variables
❖ Looking at geographical data
Some Basic Principles
• Graphics should be clear on their own
• The depictions should enable meaningful
1 The chart should tell a story comparison
• The chart should yield insight beyond the text
The chart should have
2 graphical integrity
• Basically, it shouldn’t “lie” (mislead the reader)
The chart should minimize • The simple, the better…
3 graphical complexity
The “lie factor”
• The visual overstates the actual improvement in fuel economy.
• The heights and volumes of the barrels increase dramatically
The simple, the better…
For a few data points, a table can do just as well…
The table carries more information in less space and is more precise.
Data Visualization Catalogue
What do you want to show?
More details visit [Link]
Data Visualization Catalogue
Scatterplot → A Scatterplot places points on a
Cartesian Coordinates system to display all the
values between two variables
Identify the relationship between two variables
Data Visualization Catalogue
Heatmaps → Heatmaps visualise data through variations in colouring. Heatmaps are good for
showing variance across multiple variables, revealing any patterns, displaying whether any variables
are similar to each other, and for detecting if any correlations exist. Anatomy
Number of visitors in each Town every month
Data Visualization Catalogue
• This type of visualization is used for plotting multivariate,
numerical data
• Parallel Coordinates Plots are ideal for comparing many
variables together and seeing the relationships between
them
Data Visualization Tools
Visualization Tools Programming
❑Tableau ❑Python ([Link] )
❑Looker Studio – matplotlib
– seaborn
❑Power BI – plotly
❑SAS Visual Anaytics – pylab
❑R ([Link]
– graphics
– ggplot2
Scatterplot in python
Several tools allow to build scatterplots in python. Seaborn is
probably the most straightforward library for the job,
but matplotlib allows a greater level of customization. If you are
looking for an interactive chart, plotly is definitely the way to go.
Scatterplot in R
*the plot() function of R also allows to build a scatterplot.
Both numeric variables of the input dataframe must be
specified in the x and y argument.
Heatmap in Python
Seaborn is a python library allowing to make better
charts easily thanks to its heatmap() function
Heatmap in R
Parallel Coordinates in Python
Parallel Coordinates in R
Exercise
Open : [Link]
THANK
YOU
[Link]/instrumentasi Teknik Instrumentasi ITS
@instrumentasi_its @instrumentasiits
@instrumentasits Rahmatin Nur Amalia
[Link]@[Link]
Program Studi Sains Data, FSAD, Institut Teknologi Sepuluh Nopember