Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Generate and visualize data in Python and MATLAB

Name: Generate and visualize data in Python and MATLAB
Rating: 4.6 (377 reviews)

Learn how to simulate and visualize data for data science, statistics, and machine learning in MATLAB and Python

Created byMike X Cohen

Last updated 6/2026

English

English [Auto],

What you'll learn

Understand different categories of data
Generate various datasets and modify them with parameters
Visualize data using a multitude of techniques
Generate data from distributions, trigonometric functions, and images
Understand forward models and how to use them to generate data
Improve MATLAB and Python programming skills

Course content

10 sections • 46 lectures • 6h 25m total length

Following along in Python, MATLAB, or Octave6:44
Explore how each video blends theory with hands-on coding in Python and MATLAB, switching between languages, and guiding you through slides, graphs, and code with concluding remarks.
Overall goals of this course4:55
Develop proficiency in generating and visualizing diverse data with Python and MATLAB, covering distributions, time series, images, and spatial clusters, while mastering data analysis and model fitting.
Why and how to simulate data5:42
Explore why and how to simulate data to validate analysis methods against ground truth and understand noise, parameters, features, using Python and MATLAB.
What is "signal" and what is "noise"?3:45
Define signal by relevance to the current application and treat noise as context-dependent, illustrated by neuroscience, radio, and the cosmic microwave background from the Big Bang.
The importance of visualization7:13
Explore why data visualization matters for understanding data and avoiding misinterpretation of descriptive statistics in practice. Show how visualizations reveal distribution and patterns unseen in descriptive statistics.

Course materials for this section (reader, MATLAB code, Python code)0:02
Mean, median, standard deviation, variance16:31
Learn descriptive statistics of mean, median, standard deviation, and variance, including interpretation and computation in Python and MATLAB.
Histogram7:15
Interquartile range8:27
Violin plot8:29
Learn to create and interpret violin plots to visualize data distributions, highlighting descriptive statistics like the median, inner quartile range, mean, and outliers, with Python matplotlib and MATLAB demonstrations.

Course materials for this section (reader, MATLAB code, Python code)0:02
Normal and uniform distributions15:35
Learn about the two most important distributions used in data science. Then see it in action in Python and MATLAB!
QQ plot9:22
QQ sounds funny, right? But it is a powerful data visualization and inspection method.
Poisson distribution11:40
Many physical and biological data distributions are characterized by Poisson. Learn how to simulate them in Python and MATLAB.
Log-normal distribution8:14
Log-normal data distributions come from combining other distributions. Hint: They're never negative!
Measures of distribution quality (SNR and Fano factor)8:55
Data quality is super-important in data science. Here you will learn the math, Python, and MATLAB methods for measuring data distribution quality.
Cohen's d for separating distributions10:01
You're probably thinking that I'm promoting my own method. But it's a different Cohen's D. Still a good metric, though!

Course materials for this section (reader, MATLAB code, Python code)0:02
Sharp transients12:29
Smooth transients19:55
Explore smooth transients in time series using Gaussian, Hun, and Planck windowing functions to shape edges and spectra. Demonstrate wave light concepts, including Gabor wave light, in Python and MATLAB.
Repeating: sine, square, and triangle waves10:28
Explore continuous time series features by analyzing repeated sine, square, and triangle waves in time and frequency domains, using Python and Matlab to see amplitude, frequency, and harmonics.
Multicomponent oscillators6:03
Dipolar and multipolar chirps17:41
Explore time-varying sine waves using dipolar and multipolar chirps, including frequency sliding, and analyze instantaneous frequency via the Hilbert transform to reveal time-domain dynamics.

Course materials for this section (reader, MATLAB code, Python code)0:02
Seeded reproducible normal and uniform noise9:20
Pink noise (aka 1/f aka fractal)14:58
Explore pink noise, a one over f fractal spectrum where power decreases with frequency, using two methods in Python and MATLAB to generate and visualize time series.
Brownian noise (aka random walk)10:27
Explore Brownian noise, a drunken-walk, arising from the cumulative sum of random numbers. See how integration yields a one over f spectrum in Python and MATLAB.
Multivariable correlated noise11:58

Course materials for this section (reader, MATLAB code, Python code)0:04
Forward model: 2D sheet12:40
Explore forward models that map low-dimensional inputs to high-dimensional measurements. See real-world examples like atmospheric temperature and hurricane simulations, plus a simple Gabor patch visualization in Python and MATLAB.
Mixed overlapping forward models10:20
Explore mixed overlapping forward models by combining a Gabor patch and a rectangle with independent amplitude modulators, and examine how singular value decomposition attempts to separate their spatial patterns.
Example: Simulate human brain (EEG) data16:47
Simulate eeg data with forward models by projecting dipole activity to the scalp. Explore two-dipole scenarios and source separation using generalised i candy composition.

Requirements

Interest in data
High-school math
Basic programming familiarity (MATLAB or Python)
Familiarity with power spectra from the Fourier transform

Description

Data science is quickly becoming one of the most important skills in industry, academia, marketing, and science. Most data-science courses teach analysis methods, but there are many methods; which method do you use for which data? The answer to that question comes from understanding data. That is the focus of this course.

What you will learn in this course:

You will learn how to generate data from the most commonly used data categories for statistics, machine learning, classification, and clustering, using models, equations, and parameters. This includes distributions, time series, images, clusters, and more. You will also learn how to visualize data in 1D, 2D, and 3D.

All videos come with MATLAB and Python code for you to learn from and adapt!

This course is for you if you are an aspiring or established:

Data scientist
Statistician
Computer scientist (MATLAB and/or Python)
Signal processor or image processor
Biologist
Engineer
Student
Curious independent learner!

What you get in this course:

>6 hours of video lectures that include explanations, pictures, and diagrams
pdf readers with important notes and explanations
Exercises and their solutions
MATLAB code and Python code

With >4000 lines of MATLAB and Python code, this course is also a great way to improve your programming skills, particularly in the context of data analysis, statistics, and machine learning.

What do you need to know before taking this course?

You need some experience with either Python or MATLAB programming. You don't need to be an expert coder, but if you are comfortable working with variables, for-loops, and basic plotting, then you already know enough to take this course!

Who this course is for:

Data scientists who want to learn how to generate data
Statisticians who want to evaluate and validate methods
Someone who wants to improve their MATLAB skills
Someone who wants to improve their Python skills
Scientists who want a better understanding of data characteristics
Someone looking for tools to better understand data
Anyone who wants to learn how to visualize data

Generate and visualize data in Python and MATLAB

What you'll learn

Explore related topics

Course content

Introductions5 lectures • 28min

Descriptive statistics and basic visualizations5 lectures • 41min

Data distributions7 lectures • 1hr 4min

Time series signals6 lectures • 1hr 7min

Time series noise5 lectures • 47min

Image signals5 lectures • 45min

Image noise5 lectures • 35min

Data clustering in space3 lectures • 18min

Spatiotemporal structure using forward models4 lectures • 40min

Bonus section1 lecture • 1min

Requirements

Description

Who this course is for: