Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

CodeSignal

Shaping and Transforming Features

via CodeSignal

Go to class Write review

Overview

Transform raw data into meaningful features using encoding, binning, and interaction terms. Enhance dataset representation by uncovering relationships within the data, paving the way for more insightful analysis and model building.

Syllabus

  • Unit 1: Categorical Data Encoding Techniques
    • Identify Categorical Columns in Data
    • One-hot Encoding with Pandas
    • Refining One-Hot Encoding Parameters
    • One-hot Encode with Scikit-Learn
    • Label Encode the Titanic Data
    • Efficient Label Encoding with Loops
  • Unit 2: Categorizing Continuous Data with Binning
    • Fill in the Missing Bins
    • Binning Age Groups in Titanic Dataset
    • Fix Feature Binning Bug
    • Age Binning Challenge in Titanic Dataset
  • Unit 3: Applying Mathematical Transformations to Data
    • Insert Function Names for Transformations
    • Log Transformation in Titanic Dataset
    • Square Root Transformation in Action
    • From Square to Cube Roots
  • Unit 4: Creating New Features from Existing Data
    • Creating a New Feature
    • Calculate Fare Per Person Feature
    • Identify Potential Couples
    • Creating a Family Size Category

Reviews

Start your review of Shaping and Transforming Features

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.