In this chapter, you will be introduced to fundamental concepts in model-based clustering and how this approach differs from other clustering techniques. You will learn the generating process of Gaussian Mixture Models as well as how to visualize the clusters.

Introduction to model-based clustering

Clustering approaches

Explore gender data

Gaussian distribution

Sampling a Gaussian distribution

(not so good) Estimations of the mean and sd

Gaussian mixture models (GMM)

Simulate a mixture of two Gaussian distributions

Plot histogram of Gaussian Mixture

Mixture of three Gaussian distributions

Introduction to Mixture Models

In this chapter, you will be introduced to the main structure of Mixture Models, how to address different data with this approach and how to estimate the parameters involved. To accomplish the estimation, you will learn an iterative method called Expectation-Maximization algorithm.

Structure of mixture models

Which probability distribution?

Handwritten digits dataset

Parameters estimation

Estimation given the probabilities

Calculating the probabilities

EM algorithm

Expectation function

Maximization function

Apply the two steps

Plot the estimated clusters

Structure of Mixture Models and Parameters Estimation

This chapter shows how to fit Gaussian Mixture Models in 1 and 2 dimensions with `flexmix` package. The data used is formed by 10.000 observations of people with their weight, height, body mass index and informed gender.

Univariate Gaussian Mixture Models

Number of clusters

Number of parameters

Univariate Gaussian Mixture Models with flexmix

Univariate case with flexmix

Extracting Parameters for Univariate Case

Visualizing Univariate Gaussian Mixture Model

Compare the results

Bivariate Gaussian Mixture Models

Cross-term from covariance matrix

Parameters in the bivariate case

Bivariate Gaussian Mixture Models with flexmix

Fit the model with cross-terms

Get the components

Create the ellipses

Visualize the clusters

Mixture of Gaussians with `flexmix`

In this module, you will learn how Mixture Models extends to consider probability distributions different from the Gaussian and how these models are fitted with `flexmix`. The datasets used are handwritten digits images and the number of crimes in Chicago city. For the first dataset you will find clusters that summarize the handwritten digits and for the second dataset, you will find clusters of communities where is more or less dangerous to live in.

Bernoulli Mixture Models

Binary images

How many values?

Bernoulli Mixture Models with flexmix

Handwritten digits with `flexmix`

Poisson Mixture Models

Discover the lambda

Sample from Poisson distribution

Poisson Mixture Models with flexmix

Crimes data with `flexmix`

Mixture Models Beyond Gaussians

Chicago Crimes dataset

Digits dataset

Gender dataset

Mixture modeling is a way of representing populations when we are interested in their heterogeneity. Mixture models use familiar probability distributions (e.g. Gaussian, Poisson, Binomial) to provide a convenient yet formal statistical framework for clustering and classification. Unlike standard clustering approaches, we can estimate the probability of belonging to a cluster and make inference about the sub-populations. For example, in the context of marketing, you may want to cluster different customer groups and find their respective probabilities of purchasing specific products to better target them with custom promotions. When applying natural language processing to a large set of documents, you may want to cluster documents into different topics and understand how important each topic is across each document. In this course, you will learn what Mixture Models are, how they are estimated, and when it is appropriate to apply them!

Intermediate R

Introduction to the Tidyverse

Foundations of Probability in R

Learn mixture models: a convenient and formal statistical framework for probabilistic clustering and classification.

Mixture Models in R

Discover the lambda

Mixture Models in R

Interaktive Übung