Network Graph
Network Graph : Motivation
Given a table showing the friendships between people in a group, you are
assigned to split that group into groups of two.
However, it is difficult to do so by looking at the table.
Network Graph: Motivation
Wouldn’t it be nice if you could visualize their connections using an
interactive network graph like below?
Network Graph: Pyvis
What is Pyvis?
Pyvis is a Python library that allows you to create interactive network graphs
in a few lines of code.
To install pyvis, type:
pip install pyvis
What is a Tree map?
What is a Tree map?
A tree map is a special type of chart for visualization using a set of nested
rectangles of categorical data that is preferably hierarchical.
In Hierarchical data, the categories or items share parent-child type
relationships in an overall tree structure.
The simplest example of this type of data structure can be seen in a
company where all individuals and their designations within teams could be
grouped under one entity i.e., the company itself
What is a Tree map?
When to use a Tree map?
These are some key points to consider before using tree maps for
visualization.
Tree maps work well when there is a clear ‘Part-to-whole’ relationship
amongst multiple categories present in the data.
Hierarchical Data is needed. This indicates that the data could be arranged
in branches and sub-branches.
The focus is not on precise comparisons between categories but rather on
spotting the key factors/trends or patterns.
Benefits of using a Tree map?
Benefits of using a Tree map:
Space constraint: There is a large amount of hierarchical data that needs to
be visualized in a smaller space.
Easier to read: When compared to a circular multi-level pie chart, the tree
map is easier to read due to its linear visual appearance.
Quickly spot patterns: Since each group is represented by a rectangle and
the area of this rectangle is always proportional to its value, trends and
patterns (similarities and anomalies) are quickly visible in tree maps.
Real-world use cases for Tree map Charts?
1. Displaying region-wise customer complaints about a product
Suppose there are 10 different types of complaints (assume these are
denoted as C1 to C10) about a product and the company wants to visualize
which complaints are relevant to a region then in such a case a tree map
could be used. Here, it can be clearly seen how different regions have
specific types of user complaints.
Real-world use cases for Tree map Charts?
2. Showcasing category-wise product availability like mobile phones
Let us assume that there are four categories of mobile phones with their
market share percentages i.e., Low-end (up to 10,000 INR – 15%), Mid-Range
(10,000-25000 INR- 55%), Premium (above 25,000 to 50,000 INR-25%), and
Top-end (above 50,000 INR-10%).
From this tree map, we can gauge that there is a bigger demand and market
for Mid-Range phones while there are limited phones available in the Top-End
category.
Real-world use cases for Tree map Charts?
3. Explore customer segmentation for a product
Usually, companies for apparel or personal products divide their customers
based on their age. This way they can categorize their products and the
product variants separately for each age group.
In the case of this tree map, the company could decide whether to launch
more products for particular customer segments based on the distribution.
Challenges associated with a Tree map
Tree maps also come with a set of limitations as outlined below-
– Tree maps built with large data points on a single level could be hard to read
as well as print for reporting purposes.
– Sometimes, additional sorting might be required to understand the data
better. However, all the rectangles are automatically ordered within the parent
node by area.
– With too many categories and colors to represent these, the tree map
becomes overwhelming for the reader.
– Tree maps become ineffective for datasets with balanced trees i.e., when
items are of a similar value. In these cases, the main purpose of a tree map of
highlighting the largest item in a given category becomes impossible.
Dendrograms in Python
A dendrogram is a diagram that depicts a tree.
The create_dendrogram figure factory conducts hierarchical clustering on data
and depicts the resultant tree.
Distances between clusters are represented by the values on the tree depth axis.
Dendrogram plots are often used in computational biology to depict gene or
sample grouping, occasionally in the margins of heatmaps.
Hierarchical clustering produces dendrograms as an output. Many people claim
that dendrograms of this type may be used to determine the number of clusters.
Dendrograms in Python
Wholesale Customer Segmentation Problem using Hierarchical Clustering
We will be working on a wholesale customer segmentation problem. You
can download the dataset using this link.
The data is hosted on the UCI Machine Learning repository. The aim of this
problem is to segment the clients of a wholesale distributor based on their
annual spending on diverse product categories, like milk, grocery, region, etc.
Scree Plot in Python
How to Create a Scree Plot in Python
Principal components analysis (PCA) is an unsupervised machine learning
technique that finds principal components (linear combinations of the
predictor variables) that explain a large portion of the variation in a dataset.
When we perform PCA, we’re interested in understanding what percentage
of the total variation in the dataset can be explained by each principal
component.
One of the easiest ways to visualize the percentage of variation explained
by each principal component is to create a scree plot.
