0% found this document useful (0 votes)
3 views9 pages

Data Visualization

The document provides an overview of various data visualization techniques, including Bar Charts, Box and Whisker Plots, Bubble Charts, Histograms, Line Charts, Stacked Bar Graphs, Density Plots, Error Bars, Violin Plots, and Pie Charts. Each visualization method is described in terms of its purpose, advantages, and limitations, helping users choose the appropriate chart for their data. The document emphasizes the importance of selecting the right visualization to effectively communicate data insights.

Uploaded by

vhansraj01
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
3 views9 pages

Data Visualization

The document provides an overview of various data visualization techniques, including Bar Charts, Box and Whisker Plots, Bubble Charts, Histograms, Line Charts, Stacked Bar Graphs, Density Plots, Error Bars, Violin Plots, and Pie Charts. Each visualization method is described in terms of its purpose, advantages, and limitations, helping users choose the appropriate chart for their data. The document emphasizes the importance of selecting the right visualization to effectively communicate data insights.

Uploaded by

vhansraj01
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Data Visualization

1. Bar Charts1
Also known as Bar Graph or Column
Graph. The classic Bar Chart uses either
horizontal or vertical bars (column chart)

om
to show discrete, numerical compari-

.c
sons across categories. One axis of the

ail
m
chart shows the specific categories be-

@g
ing compared and the other axis repre-

00
sents a discrete value scale.

20
01
Bars Charts are distinguished from His-

24
tograms, as they do not display continu-
ur
ous developments over an interval. Bar Chart's discrete data is categorical
dh
data and therefore answers the question of "how many?" in each category.
ma
g)
.or

2. Box and Whisker Plot


ion
at

A Box and Whisker Plot (or Box Plot) is a


d
un

convenient way of visually displaying the


ifo

data distribution through their quartiles.


.yb

The lines extending parallel from the


w
ww

boxes are known as the “whiskers”,


n(

which are used to indicate variability out-


io

side the upper and lower quartiles. Outli-


at
nd

ers are sometimes plotted as individual


ou

dots that are in-line with whiskers. Box


IF

Plots can be drawn either vertically or horizontally.


YB

Although Box Plots may seem primitive in comparison to a Histogram


or Density Plot, they have the advantage of taking up less space, which

1
[Link]

[Link] (+91) 966 798 7711 support@[Link]


is useful when comparing distributions between many groups or da-
tasets.
Here are the types of observations one can make from viewing a Box
Plot: (a) What the key values are, such as: the average, median 25th
percentile etc. (b) If there are any outliers and what their values are. (c)
Is the data symmetrical. (d) How tightly is the data grouped. (e) If the

om
data is skewed and if so, in what direction.

.c
ail
m
@g
3. Bubble Chart

00
A Bubble Chart is a multi-variable graph

20
that is a cross between a Scatterplot and

01
a Proportional Area Chart.

24
ur
Like a Scatterplot, Bubble Charts use a
dh
ma

Cartesian coordinate system to plot


points along a grid where the X and Y
g)
.or

axis are separate variables. However.


ion

unlike a Scatterplot, each point is as-


at

signed a label or category (either dis-


d
un

played alongside or on a legend). Each


ifo

plotted point then represents a third var-


.yb

iable by the area of its circle.


w
ww

Colors can also be used to distinguish


n(

between categories or used to represent an additional data variable.


io
at

Time can be shown either by having it as a variable on one of the


nd

axis or by animating the data variables changing over time. Bubble


ou
IF

Charts are typically used to compare and show the relationships be-
YB

tween categorized circles, by the use of positioning and proportions.


The overall picture of Bubble Charts can be used to analyze for pat-
terns/correlations. Too many bubbles can make the chart hard to
read, so Bubble Charts have a limited data size capacity. Like with
Proportional Area Charts, the sizes of the circles need to be drawn
based on the circle’s area, not its radius or diameter. Not only will

[Link] (+91) 966 798 7711 support@[Link]


the size of the circles change exponentially, but this will lead to mis-
interpretations by the human visual system.

4. Histogram
Histogram visualizes the distri-
bution of data over a continuous
interval or certain time period.

om
Each bar in a histogram repre-

.c
ail
sents the tabulated frequency at

m
each interval/bin. Histograms

@g
help give an estimate as to

00
20
where values are concentrated, what the extremes are and whether

01
there are any gaps or unusual values. They are also useful for giving

24
a rough view of the probability distribution.
ur
dh
ma

5. Line Chart
g)
.or

Line Graphs are used to dis-


ion

play quantitative values over


at

a continuous interval or time


d
un

period. A Line Graph is most


ifo

frequently used to show


.yb

trends and analyses how the


w
ww

data has changed over time.


n(

Line Graphs are drawn by


io

first plotting data points on a


at
nd

Cartesian coordinate grid,


ou

then connecting a line be-


IF

tween all of these points.


YB

Typically, the y-axis has a


quantitative value, while the x-axis is a timescale or a sequence of inter-
vals. Negative values can be displayed below the x-axis.

[Link] (+91) 966 798 7711 support@[Link]


The direction of the lines on the graph works as a nice metaphor for the
data: an upward slope indicates where values have increased and a down-
ward slope indicates where values have decreased. The line's journey
across the graph can create patterns that reveal trends in a dataset.

When grouped with other lines (other data series), individual lines can be

om
compared to one another. However, avoid using more than 3-4 lines per

.c
ail
graph, as this makes the chart more cluttered and harder to read. A solu-

m
tion to this is to divide the chart into smaller multiples (have a small Line

@g
Graph for each data series).

00
20
01
6. Stacked Bar Graph

24
ur
Stacked Bar Graphs segment
dh
their bars. Stacked Bar
ma

Graphs are used to show


g)
.or

how a larger category is di-


ion

vided into smaller categories


at

and what the relationship of


d
un

each part has on the total


ifo

amount. There are two types


.yb

of Stacked Bar Graphs:


w
ww
n(

Simple Stacked Bar Graphs


io
at

place each value for the seg-


nd

ment after the previous one.


ou

The total value of the bar is


IF

all the segment values added


YB

together. Ideal for comparing the total amounts across each group/seg-
mented bar.
100% Stack Bar Graphs show the percentage-of-the-whole of each group
and are plotted by the percentage of each value to the total amount in

[Link] (+91) 966 798 7711 support@[Link]


each group. This makes it easier to see the relative differences between
quantities in each group.
One major flaw of Stacked Bar Graphs is that they become harder to read
the more segments each bar has. Also comparing each segment to each
other is difficult, as they're not aligned on a common baseline.

.com
7. Density Plot

ail
m
@g
As known as Kernel Density

00
20
Plots, Density Trace Graph.

01
A Density Plot visualises the

24
distribution of data over a
ur
dh
continuous interval or time
ma

period. This chart is a varia-


g)

tion of a Histogram that uses


.or

kernel smoothing to plot val-


ion

ues, allowing for smoother


at

distributions by smoothing
d
un

out the noise. The peaks of a


ifo

Density Plot help display


.yb

where values are concen-


w
ww

trated over the interval.


n(
io
at

An advantage Density Plots have over Histograms is that they're better at


nd

determining the distribution shape because they're not affected by the


ou
IF

number of bins used (each bar used in a typical histogram). A Histogram


YB

comprising of only 4 bins wouldn't produce a distinguishable enough


shape of distribution as a 20-bin Histogram would. However, with Density
Plots, this isn't an issue.

[Link] (+91) 966 798 7711 support@[Link]


8. Error Bar

Although not a chart outright,


Error Bars function as a
graphical enhancement that
visualises the variability of

om
the plotted data on a Carte-

.c
ail
sian graph. Error Bars can be

m
applied to graphs such as

@g
Scatterplots, Dot Plots, Bar

00
Charts or Line Graphs, to pro-

20
vide an additional layer of de-

01
24
tail on the presented data.
ur
dh
ma

Error Bars help to indicate es-


g)

timated error or uncertainty


.or

to give a general sense of


ion

how precise a measurement


dat

is. This is done through the


un

use of markers drawn over


ifo

the original graph and its


.yb

data points. Typically, Error


w
ww

bars are used to display ei-


n(

ther the standard deviation,


io

standard error, confidence intervals or the minimum and maximum values


at
nd

in a ranged dataset.
ou
IF
YB

To visualise this information, Error Bars work by drawing cap-tipped lines


that extend from the centre of the plotted data point (or edge with Bar
Charts). The length of an Error Bar helps reveal the uncertainty of a data
point: a short Error Bar shows that values are concentrated, signalling that
the plotted average value is more likely, while a long Error Bar would indi-
cate that the values are more spread out and less reliable. Also depending

[Link] (+91) 966 798 7711 support@[Link]


on the type of data, the length of each pair of Error Bars tend to be of equal
length on both sides. However, if the data is skewed, then the lengths on
each side would be unbalanced.

Error Bars always run parallel to a quantitative scale axis, so they can be
displayed either vertically or horizontally, depending on whether the quan-

om
titative scale is on the Y or X axis. If there are two quantitative scales, then

.c
ail
two pairs of Error Bars can be used for both axes.

m
@g
00
9. Violin Plot

20
01
A Violin Plot is used to visualise the

24
distribution of the data and its proba-
ur
bility density.
dh
ma
g)

This chart is a combination of a Box


.or
ion

Plot and a Density Plot that is rotated


and placed on each side, to show the
dat

distribution shape of the data. The


un
ifo

white dot in the middle is the median


.yb

value and the thick black bar in the


w

centre represents the interquartile range. The thin black line extended
ww

from it represents the upper (max) and lower (min) adjacent values in the
n(

data. Sometimes the graph marker is clipped from the end of this line.
io
at

Box Plots are limited in their display of the data, as their visual simplicity
nd

tends to hide significant details about how values in the data are distrib-
ou
IF

uted. For example, with Box Plots, you can't see if the distribution is bi-
YB

modal or multimodal. While Violin Plots display more information, they


can be noisier than a Box Plot.

[Link] (+91) 966 798 7711 support@[Link]


10. Pie chart

Extensively used in presentations


and offices, Pie Charts help show

om
proportions and percentages be-

.c
tween categories, by dividing a cir-

ail
cle into proportional segments.

m
@g
Each arc length represents a propor-

00
tion of each category, while the full

20
circle represents the total sum of all

01
the data, equal to 100%.

24
ur
dh
Pie Charts are ideal for giving the
ma

reader a quick idea of the propor-


g)
.or

tional distribution of the data. How-


ion

ever the major downsides to pie


at

charts are:
d
un
ifo
.yb

They cannot show more than a few values, because as the number of val-
w

ues shown increases, the size of each segment/slice becomes smaller.


ww

This makes them unsuitable for large amounts of data.


n(
io

They take up more space than their alternatives, like a 100% Stacked Bar
at

Chart for example. Mainly due to their size and for the usual need for a
nd

legend.
ou
IF

They are not great for making accurate comparisons between groups of
YB

Pie Charts. This being that it is harder to distinguish the size of items via
area when it is for length.
In spite of that, comparing a given category (one slice) within the total of
a single Pie Chart, then it can often be more effective.

[Link] (+91) 966 798 7711 support@[Link]


.com
ail
m
@g
00
20
01
24
ur
dh
ma
g)
.or
ion
dat
un
ifo
[Link]
ww
n(
io
at
nd
ou
IF
YB

[Link] (+91) 966 798 7711 support@[Link]

You might also like