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

CodeSignal

Hypertuning Classical Models

via CodeSignal

Go to class Write review

Overview

This course teaches learners how to systematically improve classical ML models using hyperparameter search and evaluation strategies, continuing from a weak baseline.

Syllabus

  • Unit 1: Grid Search for Hyperparameter Tuning in scikit-learn
    • Your First Grid Search Parameter Grid
    • Creating and Fitting GridSearchCV
    • Debugging Parameter Names in Grid Search
    • Building Models with Optimal Hyperparameters
  • Unit 2: Random Search for Hyperparameter Tuning in scikit-learn
    • Increasing Random Iterations for Better Results
    • Defining Parameter Distributions for Random Search
    • Debugging RandomizedSearchCV Configuration Parameters
    • Expanding Random Search with Continuous Parameters
  • Unit 3: Cross-Validation with StratifiedKFold in scikit-learn
    • Implementing StratifiedKFold for Better Validation
    • Making Cross Validation Results Reproducible
    • Comparing Models with Stratified Cross Validation
    • Comparing KFold vs StratifiedKFold on Imbalanced Data
  • Unit 4: Tuning Pipelines with GridSearchCV in scikit-learn
    • Adding the Missing Pipeline Step
    • Fixing Parameter References in Pipeline Grids
    • Creating Tunable Preprocessing Pipelines
    • Fixing Cross Validation in Pipeline Tuning

Reviews

Start your review of Hypertuning Classical Models

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.