Exploratory Data Analysis Feature Engineering
About
Explain what feature engineering is, why it is important, and how to do it.
Learning Objectives
You will be able to:
- Explain the reasons for applying feature engineering to the data when modeling.
- Identify the relevant methods to apply to categorical data.
- Understand how and when to group continuous data into bins.
- Explain the reasons to transform your continuous data when modeling.
- Create transformers with
scikit-learnto develop a pipeline of transformations for your data.
Content
| Topic | About |
|---|---|
| Full Lesson Deck | A walkthrough of feature engineering in 5 parts: Why Feature Engineering Matters; Working with Categorical Data; Binning Continuous Variables; Transforming Continuous Variables; and Pipelines |
| 02 feature engineering notebook | A demonstration of how to do feature engineering |
Prerequisites
- Interpret and use Python dictionaries
- Build
pandasDataFramesfrom dictionaries - Perform simple data manipulation on
pandasobjects - Build
forandwhileloops in Python - Use
pip installfor package management - For the Pipelines section: know how to build a Linear Regression model and how to evaluate it with RMSE
References
📖 Reference Materials
Important note
Please ignore the _layouts folder and the config.yml file in the root of this repo. They are needed to make sure the repo renders well; please don’t change them or delete them and your repo will work fine :)