Skip to content

Latest commit

 

History

History
27 lines (19 loc) · 1.64 KB

README.md

File metadata and controls

27 lines (19 loc) · 1.64 KB
Raw

Implementation of LDA and QDA Classifiers for the Iris Dataset

This project involves implementing Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA) classifiers in Google Colab, using the Iris dataset as the basis for evaluation. The implementation includes data normalization, training, testing, and accuracy measurement.

Implementation Steps

Data Preparation

The Iris dataset was divided into training and testing sets to evaluate the performance of the classifiers. Data normalization was applied before training and classification to ensure that all features contribute equally.

Classifier Implementation

LDA Classifier

  • Implemented the Linear Discriminant Analysis (LDA) classifier.
  • Trained the LDA classifier on the training set.
  • Tested the LDA classifier on the testing set.

QDA Classifier

  • Implemented the Quadratic Discriminant Analysis (QDA) classifier.
  • Trained the QDA classifier on the training set.
  • Tested the QDA classifier on the testing set.

Performance Measurement

  • Measured the accuracy of both classifiers on the training and testing sets.
  • Compared the results to evaluate the effectiveness and generalization capability of each classifier.

Conclusion

The project demonstrates the implementation of LDA and QDA classifiers from scratch. The performance of both classifiers was evaluated on both training and testing sets, providing insights into their accuracy and generalization capabilities. This project showcases the effectiveness of discriminant analysis techniques in classification tasks, emphasizing the importance of data normalization and accurate performance measurement.