Exploratory Data Analysis with AWS Machine Learning
Understanding how to deal with data is becoming a required skill in the information age. This course will teach you how to do exploratory data analysis and leverage relevant AWS services.
What you'll learn
Understanding underlying trends and outliers in data is a necessary step to do proper data preparation and feature engineering for subsequent machine learning tasks.
In this course, Exploratory Data Analysis with AWS Machine Learning, you’ll learn how to analyze, visualize, preprocess and feature engineer datasets to make them ready for subsequent machine learning steps.
What you will learn in this beginner level AWS machine learning tutorial:
- First, you’ll explore how to understand data trends and distribution using basic statistics.
- Next, you’ll discover how to visualize your dataset to understand the overall patterns.
- Finally, you’ll learn how to prepare your data for the machine learning pipeline by doing preprocessing and feature engineering.
When you’re finished with this course, you’ll have the skills and knowledge of exploratory data analysis needed to achieve AWS Machine Learning specialty certification.
Table of contents
- Overview 1m
- Why Data Preparation? 4m
- Imbalanced Data Challenge 3m
- Scale of Features Challenge 3m
- Inconsistent Formats Challenge 3m
- Difficult Presentation of Data Challenge 2m
- Missing Data Challenge 2m
- Outliers Challenge 3m
- High Dimensionality Challenge 4m
- Highly Correlated Features Challenge 4m
- Malformed Distribution Challenge 3m
- Demo: Fixing Missing Values 9m
- Demo: Removing Highly Correlated Features 2m
- Demo: Removing Outliers 1m
- Demo: Fixing Difficult Presentation of Data 1m
- Demo: Fixing Scale of Data 1m
- Demo: Fixing Malformed Distribution 1m
- Summary 3m