Associate Professor
Applied Unsupervised Learning in Python
What You'll Learn
- Apply basic unsupervised learning methods for transforming and visualizing data: dimensionality reduction, manifold learning, and density estimation.
- Understand, evaluate, optimize, and correctly apply clustering algorithms using hierarchical, partitioning, and density-based methods.
- Use topic modeling to find important themes in text data and use word embeddings to analyze patterns in text data.
- Manage missing data using supervised and unsupervised imputation methods, and use semi-supervised learning to work with partially-labeled datasets.
4 Modules
32 Hours
8 hrs per module (approx.)
Rating
About Applied Unsupervised Learning in Python
In “Applied Unsupervised Learning in Python,” you will learn how to use algorithms to find interesting structure in datasets. You will practice applying, interpreting, and refining unsupervised machine learning models to solve a diverse set of problems on real-world datasets.
This course will show you how to explore unlabelled data using several techniques: dimensionality reduction and manifold learning for condensing and visualizing high-dimensional data, clustering to reveal interesting groups and outliers, topic modeling for summarizing important themes in text, methods for dealing with missing data, and more. This course also covers best practices associated with different techniques, as well as demonstrating how unsupervised learning can be used to improve supervised prediction.
This is the second course in “More Applied Data Science with Python,” a four-course series focused on helping you apply advanced data science techniques using Python. It is recommended that all learners complete the Applied Data Science with Python specialization prior to beginning this course.
Skills You'll Gain
- Machine Learning
- Python For Data Analysis
- Unsupervised Learning
What You'll Earn
- Certificate of Completion:
- Certificates of completion acknowledge knowledge acquired upon completion of a non-credit course or program.
Welcome Message
Applied Unsupervised Learning in Python focuses on discovering structure in unlabeled data using practical, real-world applications. You will learn how to apply, evaluate, and refine unsupervised learning techniques such as dimensionality reduction, clustering, and topic modeling. The course emphasizes interpretation and iterative improvement of models rather than theoretical derivations.
This abbreviated syllabus description was created with the help of AI tools and reviewed by staff. The full syllabus is available to those who enroll in the course.
Course Schedule
Module 1: Basic Unsupervised Learning Methods
- Video: Welcome to Applied Unsupervised Learning in Python
- Reading: MADSwPy Certificate Roadmap
- Reading: Course Syllabus
- Reading: Additional Resources
- Discussion Prompt: Meet Your Fellow Learners
- Reading: Help Us Learn About You
- Video: Dimensionality Reduction: A Brief Introduction
- Video: Dimensionality Reduction with Feature Selection: Information Gain
- Video: Dimensionality Reduction with Feature Selection: Principal Component Analysis (PCA) Explained
- Video: Visualizing PCA Results: Foundations
- Video: Visualizing PCA Results: Biplots and Variance Plots
- Reading: Ten Quick Tips for Effective Dimensionality Reduction
- Video: Singular Value Decomposition (SVD)
- Video: Applications of SVD in Data Science
- Video: Manifold Learning: Multidimensional Scaling (Part 1)
- Video: Manifold Learning: Multidimensional Scaling (Part 2)
- Video: Manifold Learning: t-Distributed Stochastic Neighbor Embedding (t-SNE)
- Video: Manifold Learning: Uniform Manifold Approximation and Projection (UMAP)
- Video: Density Estimation Part 1: Probability Density Functions
- Video: Density Estimation Part 1: Parametric vs. Non-Parametric Density Estimator
- Video: Density Estimation Part 2: Local Density Estimators
- Video: Density Estimation Part 2: Kernel Density Estimators
- Video: Density Estimation Part 2: Evaluating Density Estimators
- Video: Density Estimation Part 3: Local Density Estimators and Gaussian Mixture Models (GMMs)
- Reading: Introduction to Module 1 Programming Assignment: An Introduction to Unsupervised Learning
- Role Play: Assignment 1 Follow-Up
- Reading: Module 1 Optional Readings & Resources
- Graded: Time to Practice: Dimensionality Reduction
- Graded: Time to Practice: Principal Component Analysis (PCA)
- Graded: Time to Practice: Singular Value Decomposition (SVD)
- Graded: Time to Practice: Manifold Learning (Multidimensional scaling: Parts 1 & 2)
- Graded: Time to Practice: Manifold Learning (t-SNE, and UMAP)
- Graded: Time to Practice: Density Estimation Methods (Part 1)
- Graded: Time to Practice: Density Estimation Methods (Parts 2 & 3)
- Graded: Create & Submit Module 1 Assignment
Module 2: Clustering
- Video: A Brief Introduction to Clustering (Part 1)
- Video: A Brief Introduction to Clustering (Part 2)
- Video: Hierarchical Clustering Part 1: Introduction
- Video: Hierarchical Clustering Part 2: Ward's Method
- Video: Hierarchical Clustering Part 2: Dendograms
- Video: Introduction to K-means
- Video: Applying K-means in Practice
- Video: DBSCAN Clustering
- Video: Evaluating Cluster Quality (Part 1)
- Video: Evaluating Cluster Quality (Part 2)
- Reading: Cluster Labeling
- Reading: Introduction to Module 2 Assignment: Clustering
- Role Play: Assignment 2 Followup
- Reading: Module 2 Optional Readings & Resources
- Graded: Time to Practice: Clustering Overview
- Graded: Time to Practice: Hierarchical Clustering
- Graded: Time to Practice: K-means Clustering
- Graded: Time to Practice: DBSCAN Clustering
- Graded: Time to Practice: Cluster Quality
- Graded: Create & Submit Module 2 Assignment
Module 3: Unsupervised Methods for Text Analysis
- Video: How to Represent Text as a Vector: A Typical Workflow
- Video: Text Processing in SciKit-Learn
- Video: Introduction to Topic Modeling
- Video: Latent Dirichlet Allocation (LDA)
- Video: Using LDA with Scikit-Learn
- Video: Non-Negative Matrix Factorization (NMF)
- Video: Word Embeddings Technique #1: Word2vec
- Video: Word Embeddings Technique #2: Glove
- Reading: Introduction to Module 3 Assignment: Text Representations, Topic Modeling, and Word Embeddings
- Role Play: Assignment 3 Followup
- Reading: Module 3 Optional Readings & Resources
- Graded: Time to Practice: Representing Text as a Vector
- Graded: Time to Practice: Text Processing in SciKit-Learn
- Graded: Time to Practice: Latent Dirichlet Allocation (LDA)
- Graded: Time to Practice: Non-Negative Matrix Factorization (NMF)
- Graded: Time to Practice: Word2vec & Glove
- Graded: Create & Submit Module 3 Assignment
Module 4: Applications and Variants of Unsupervised Learning
- Video: Applying Unsupervised Learning to Supervised Learning Tasks
- Video: Imputation of Missing Data
- Video: Imputation with Scikit-Learn
- Video: A Brief Introduction to Semi-Supervised Learning
- Video: Label propagation with scikit-learn
- Video: A Brief Introduction to Self-Supervised Learning
- Reading: Introduction to Module 4 Assignment: Applying Methods and Techniques for Data Imputation and Semi-Supervised Learning
- Role Play: Assignment 4 Followup
- Reading: Module 4 Optional Readings & Resources
- Graded: Time to Practice: Applying Unsupervised Learning to Supervised Learning Tasks
- Graded: Time to Practice: Imputation of Missing Data
- Graded: Time to Practice: Semi-Supervised Learning
- Graded: Time to Practice: Self-Supervised Learning
- Graded: Create & Submit Module 4 Assignment
Grading Policy
There are a series of module quizzes and programming assignments in this course. The quizzes for each module account for between 5-7% of your final grade. The programming assignments are worth between 18-20% of your final grade.
Course content developed by U-M faculty and managed by the university. Faculty titles and affiliations are updated periodically.
Advanced Level
A basic understanding of statistics and linear algebra, and completing the “Applied Data Science with Python” series, is recommended.
