Author: Aaron Jones
Pub Date: 2020
Size: 426 Mb
With the help of interesting examples and activities, learn how to apply unsupervised algorithms on unlabelled datasets
Do you find it difficult to learn how big companies like WhatsApp and Amazon find valuable insight from volumes of unorganised data? Don’t worry, this workshop will give you enough confidence to deal with cluttered and unlabelled datasets using unsupervised algorithms.
The workshop starts by introducing one of the most popular algorithms of unsupervised learning, Clustering. You’ll learn about different techniques of clustering algorithms and study the key differences between them. Next, you’ll find out how Autoencoders comes handy in data decoding. Moving ahead, you’ll use t-SNE models to extract high-dimensional information into a lower dimension for better visualization and work with topic modeling for implementing natural language processing. In the final chapters, you’ll find key relationships between customers and the business using Market Basket Analysis and use Hotspot Analysis for estimating the population density of an area.
By the end of this workshop, you’ll be able to apply unsupervised algorithms on cluttered datasets to find useful patterns and insights.
What you will learn
- Distinguish between hierarchical clustering and k-means algorithm
- Find out the process of finding clusters in the data
- Grasp interesting techniques to reduce the size of the data
- Use Autoencoders to decode the data
- Extract text from a large collection of documents using Topic Modeling
- Apply Market Based Analysis to extract insights from transactional data