Supervised Machine Learning: Classification

Description

In this course, you will learn :

• How to train predictive models to classify categorical outcomes and how to compare different models using error metrics.
• This course's hands-on section focuses on using best practises for classification, such as train and test splits and handling data sets with unbalanced classes.
• Differentiate between classification and classification ensembles' uses and applications.
• Explain and apply logistic regression models.
• Explain and apply decision tree and tree-ensemble models.
• Describe and apply other ensemble classification methods.
• Compare and select the classification model that best fits your data using a variety of error metrics.
• To handle unbalanced classes in a data set, use oversampling and undersampling techniques.

Syllabus :

1. Logistic Regression

• Introduction: What is Classification?
• Introduction to Logistic Regression
• Classification with Logistic Regression
• Logistic Regression with Multi-Classes
• Implementing Logistic Regression Models
• Confusion Matrix, Accuracy, Specificity, Precision, and Recall
• Classification Error Metrics: ROC and Precision-Recall Curves
• Implementing the Calculation of ROC and Precision-Recall Curves

 

2. K Nearest Neighbors

• K Nearest Neighbors for Classification
• K Nearest Neighbors Decision Boundary
• K Nearest Neighbors Distance Measurement
• K Nearest Neighbors Pros and Cons
• K Nearest Neighbors with Feature Scaling

 

3. Support Vector Machines

• Introduction to Support Vector Machines
• Classification with Support Vector Machines
• The Support Vector Machines Cost Function
• Regularization in Support Vector Machines
• Introduction to Support Vector Machines Gaussian Kernels
• Support Vector Machines Gaussian Kernels
• Support Vector Machines Workflow
• Implementing Support Vector Machines Kernal Models
• Support Vector Machines Notebook

 

4. Decision Trees

• Introduction to Decision Trees
• Building a Decision Tree
• Entropy-based Splitting
• Other Decision Tree Splitting Criteria
• Pros and Cons of Decision Trees

 

5. Ensemble Models

• Ensemble Based Methods and Bagging
• Random Forest
• Review of Bagging
• Overview of Boosting
• Adaboost and Gradient Boosting Overview
• Adaboost and Gradient Boosting Syntax
• Stacking

 

6. Modeling Unbalanced Classes

• Model Interpretability
• Examples of Self-Interpretable and Non-Self-Interpretable Models
• Model-Agnostic Explanations
• Surrogate Models
• Introduction to Unbalanced Classes
• Upsampling and Downsampling
• Modeling Approaches: Weighting and Stratified Sampling
• Modeling Approaches: Random and Synthetic Oversampling
• Modeling Approaches: Nearing Neighbor Methods
• Modeling Approaches: Blagging

Show more