Principal Component Analysis in Python and MATLAB

Name: Principal Component Analysis in Python and MATLAB
Rating: 4.5 (168 reviews)

From Theory to Implementation

Created byYarpiz Team, Mostapha Kalami Heris

Last updated 12/2019

English

English [Auto],

What you'll learn

Theory of Principal Component Analysis (PCA)
Concept of Dimensionality Reduction
Step-by-step Implementation of PCA
PCA using Scikit-Learn (Python Library for Machine Learning)
PCA using MATLAB (Using Statistics and Machine Learning Toolbox)

Course content

3 sections • 9 lectures • 1h 21m total length

Introduction5:14
Learn principal component analysis (PCA) as an unsupervised, linear method for dimensionality reduction and feature extraction, producing uncorrelated, orthogonal components by maximizing variance through optimized coefficients.
Mathematics Behind PCA – Part 111:00
Form PCA as an optimization: maximize z = u^T x by a unit vector u, yielding variance z = u^T C u with C the covariance matrix.
Mathematics Behind PCA – Part 29:45
Apply eigenvalues and eigenvectors of the covariance matrix to maximize variance along principal components. Choose top eigenvectors to form the transformation and map X to Z for dimensionality reduction.

Basic PCA Implementation in Python14:05
Learn to implement principal component analysis from scratch in Python using matrix operations, compute the covariance matrix, extract eigenvectors, and project data onto the first principal component for dimensionality reduction.
Applying PCA to Iris Dataset Using Sciket-Learn and Python5:42
Apply principal component analysis on iris dataset using scikit-learn in Python to reduce four features to two components, transforming data and visualizing class separation in a two-dimensional scatter plot.
Applying PCA to Handwritten Digits Dataset in Python7:28
Apply principal component analysis to the handwritten digits dataset in Python, reducing 64 features to 2 and visualizing the two components colored by digit labels to assess separability.

Basic PCA Implementation in MATLAB12:53
Perform basic principal component analysis in MATLAB by generating random two‑D data, computing covariance and eigenvectors, projecting onto the first principal component, and visualizing the data and its projection.
Applying PCA to Iris Dataset Using Statistics Toolbox of MATLAB7:14
Apply principal component analysis to the iris dataset in MATLAB using the statistics toolbox, transform data to two components, and visualize with a color-coded scatter plot by class.
Applying PCA to Handwritten Digits Dataset in MATLAB7:51
Apply principal component analysis in MATLAB to a handwritten digits dataset, reducing 64-input images to two principal components, visualize separations with a scatter plot, and assess data preservation via eigenvalues.

Requirements

Python Programming
MATLAB Programming
Basics of Data Analysis

Description

Principal Component Analysis (PCA) is an unsupervised learning algorithms and it is mainly used for dimensionality reduction, lossy data compression and feature extraction. It is the mostly used unsupervised learning algorithm in the field of Machine Learning.

In this video tutorial, after reviewing the theoretical foundations of Principal Component Analysis (PCA), this method is implemented step-by-step in Python and MATLAB. Also, PCA is performed on Iris Dataset and images of hand-written numerical digits, using Scikit-Learn (Python library for Machine Learning) and Statistics Toolbox of MATLAB. Also the projects files are available to download at the end of this post.

Who this course is for:

Data Scientists and Analysts
Computer Science and Engineering Students
Anyone interested in Data Science

Principal Component Analysis in Python and MATLAB

What you'll learn

Explore related topics

Course content

Theory of Principal Component Analysis (PCA)3 lectures • 26min

Principal Component Analysis in Python3 lectures • 27min

Principal Component Analysis in MATLAB3 lectures • 28min

Requirements

Description

Who this course is for: