Online Courses Reviews
Online courses have been a great supplementary part to my offline study and work. Whenever I am interested in exploring some new fields, or find myself lacking some key skills, I would turn to them. This blog keeps a list of online courses I have taken. I also include some notes on those courses for your reference. Most of the courses are on computer science, statistics, data analytics, or machine learning.
Coursera
Coursera is the very first MOOC platform I have ever tried. It is a platform led by Stanford University and many other top universities around the world, and it offers online courses from these universities. When I was an accounting-major Junior, I was thinking about transitting into the world of computer science and data science, but I was not sure whether that was the right thing for me to pursue. Therefore, I took a number of courses in these fields on Coursera. I enjoyed these courses a lot (I mean, much more than the accounting courses), and they strengthened my confidence in pursuing a MS Business Analytics degree in the US and entering the data science world.
| Courses | Topics | Time | Notes |
|---|---|---|---|
| Data Visualization | Data Visualization | Aug 2015 | Introduce some general data viz principles and fancy tools. |
| An Introduction to Interactive Programming in Python (Part 1) | Computer Science | Aug 2015 | Excellent course!!! It’s the first course of the Fundamentals of Computing Specialization by Rice University. It teaches basic Python by building small games. And the faculty is very accessible and friendly. Strongly recommend it to anyone wants to learn Python. |
| An Introduction to Interactive Programming in Python (Part 2) | Computer Science | Oct 2015 | Second part of the above specialization. The final project is to build an Asteroid game. Super fun and helpful. |
| Data Processing Using Python | Computer Science | Nov 2015 | Great to see a Coursera course by a university in China. This course covers the basics of the common data manipulation packages in Python (Numpy, pandas, etc.). |
| Using Python to Access Web Data | Computer Science | Nov 2015 | This is the third course of the Python for Everybody Specialization from UMich. The Professor is excellent. The content covers basics of web, Regex, and web scraping with beatifulsoup. |
| Using Databases with Python | Computer Science | Dec 2015 | This is the fourth course of the Python for Everybody Specialization from UMich. It covers basics of databases, SQL, and how to connect Python to SQL server. |
| R Programming | Computer Science | Jan 2016 | Basic R programming. The assignments are not very much related to the lectures (maybe a good motivation to self-learning). |
| Machine Learning Foundations: A Case Study Approach | Machine Learning | Jan 2016 | The first course of the Machine Learning Specialization by UW. It gives a lot of real-world machine learning applications to inspire the interests on machine learning. The professor is good at conveying those complex ideas very clearly. |
| Principles of Computing (Part 1) | Computer Science | Feb 2016 | The third course of the Fundamentals of Computing Specialization. The assignments are still small games, but involve more mathematical concepts and algorithms. |
| Managing Big Data with MySQL | Data Analytics | Feb 2016 | Very good course to learn database principles and SQL. It provides some real datasets on the Teradata server for exercises and quizzes. |
| Principles of Computing (Part 2) | Computer Science | Mar 2016 | The fourth course of the specialization. It begins to explore some more advanced CS topics such as stack and queue, graph and trees, and recursion. |
| Machine Learning: Regression | Machine Learning | Mar 2016 | The second course of the Machine Learning Specialization by UW. Great course with a lot of real-world examples and coding exercies. |
| Algorithmatic Thinking (Part 1) | Computer Science | Apr 2016 | The fifth course of the Fundamentals of Computing Specialization. It starts to focus on Big O, and covers algorithms such as BFS, DFS. Much more challenging than the previous four, yet very much enjoyable. |
| Machine Learning: Classification | Machine Learning | May 2016 | The third course of the Machine Learning Specialization by UW. It coveres practical cases and algorithms details of classification algorithms including logistic regression, decision tree, AdaBoost tree, etc. |
| Algorithmatic Thinking (Part 2) | Computer Science | May 2016 | The last course of the Fundamentals of Computing Specialization! (I did it!!!) This incldes three big projects, one on clustering algorithm, one on DP algorithm, and another on genomics text analytics. The best specialization ever!!! |
| Introduction to Probability and Data | Statistics | May 2016 | The first course of the Statistics with R Specialization by Duke University. Introduces some basic R (mainly dplyr package and ggplot2) and basic probability and statistics. |
| Inferential Statistics | Statistics | June 2016 | The second course of the Statistics with R Specialization by Duke University. This course focuses more on hypothesis testing. Very good professor and clear lectures. |
| Linear Regression and Modeling | Statistics | June 2016 | The third course of the Statistics with R Specialization by Duke University. This course focuses on linear regression. Very good professor, clear lectures, and practical final project. |
| Bayesian Statistics | Statistics | Aug 2016 | The last course of the Statistics with R Specialization by Duke University. Different from the previous courses, this one is from the Beyasian perspective. Overall, this is a great specialization to review statistics while learning some R. |
| Machine Learning: Clustering & Retrieval | Machine Learning | Aug 2016 | The last course of the Machine Learning Specialization by UW. It covers similarity calculation, TF-IDF, LDA, etc. Again, this is a great specialization with a lot of real-world examples and coding exercies (althrough it did not use a very popular machine learning package in Python like sklearn). |
| Machine Learning | Machine Learning | Jan 2017 | The very famous machine learning course by Andrew Ng. Definitely great course and great professor. This course covers common machine learning algorithms in details, though it uses Matlab or Octave. |
| A Crash Course in Causality: Inferring Causal Effects from Observational Data | Statistics | Nov 2019 | This course focus on most frequently used causal inference analysis methodologies, including the concept and application of DAG in causal inference, matching, propensity scores, Inverse Probability of Treatment Weighting (IPTW), and Instrumental variables methods. I took this course because of some recent project needs at work, though this course ended up being a little bit too academic. |
edX
edX is another awesome MOOC platform led by MIT and some other top universities and institutions.
| Courses | Topics | Time | Notes |
|---|---|---|---|
| Introduction to Computer Science and Programming Using Python | Computer Science | July 2016 | A comprehensive and intensive introduction course to Python by MIT. It covers topics including basic grammar, functions, recursion, debugging tools, algorithm efficiency & search algorithms, classes & oop, and trees. |
| Programming with Python for Data Science | Machine Learning | Aug 2016 | This course starts from basic data manipulation and visualization with Numpy, Pandas and matplotlib, then introduced some basic machine learning models including regression, KNN, decision tree, random forest, and techniques such as PCA and Cross Validation, and how to implement them with scikit-learn. Great course to help students to build a whole picture of machine learning. |
| Introduction to R for Data Science | Data Analytics | Nov 2016 | A comprehensive tutorial on doing basic data manipulation and visualization in R. |
| Programming in R for Data Science | Data Analytics | Nov 2016 | This one is the subsequent course of the above one, and it includes some more advanced topics in R programming, such as loop, flow control, simulation, reading data from SQL database,and simple modeling. |
Udacity Courses
I personally believe that the best thing about Udacity is that many of the lecturers actually come from those tech giants in the Silicon Vally. Therefore, the courses on Udacity is much closer to the real business world practices. Besides, the course format of Udacity is quite different from Coursera and edX - it includes very short and interactive videos with bunch of small quizzes poping up between the videos.
| Courses | Topics | Time | Notes |
|---|---|---|---|
| Intro to Machine Learning | Machine Learning | Feb 2017 | This course also uses scikit-learn in Python to explore common machine learning algorithms and includes practical exercises on a real dataset (the famous Enron dataset – as an accounting-major undergrad, it is just too much familiar to me). |
| A/B Testing | Data Analytics | Jan 2018 | A/B testing course by Google. This is a great course to bridge the gap between what we learned in stats class and what is actually doing in real business world. |
Lynda
Lynda offeres very short (typically 2-4 hours) and introductionary level courses in all fields. Therefore, it is always the place I go to, to find some quick tutorials to get started with something, or to review some staff learned before. For example, before I started my summer internship, I took three courses on Tableau to refresh my knowledge and learn more practical skills; To prepare myself for a course with Data Mining projects in Scala, I took the Scala Essential Training course.
| Courses | Topics | Time | Notes |
|---|---|---|---|
| Python: Data Analysis | Data Analytics | Jan 2017 | Basic NumPy and pandas. |
| NumPy Data Science Essential Training | Data Analytics | Jan 2017 | Basic NumPy and pandas. |
| Data Science Fundations Data Mining | Machine Learning | Jan 2017 | Compare the implementation of common machine learning algorithms using different tools including Python, R, Orange, RapidMiner, BigML and KNIME. |
| Tableau 10: Mastering Calculation | Data Visualization | May 2017 | Focus on how to build those calculated fields in Tableau. |
| Tableau 10 for Data Science | Data Visualization | May 2017 | A comprehensive introduction to data visualization in Tableau 10. |
| Integrating Tableau and R for Data Science | Data Visualization | May 2017 | This course talks about how to run R scripts in Tableau. |
| HTML Essential Training | Web Development | Aug 2017 | Very basic training to HTML. |
| Scala Essential Training | Computer Science | Sept 2017 | Basic grammar of Scala. Very helpful to get started with Scala for someone already has some programming experience in other languages. |
DataCamp
DataCamp is an emegering MOOC platform, specialized in data science courses with R, Python and SQL. It offers courses on all kinds of specific data science topics (but mostly introductionary level). And as it is subscription-based, i.e., users pay monthly (or annually), it could be a good choice for someone who wants to learn R or Python from the beginning, and who has much spare time to focus on learning in one or two months.
A sweet tip from @Nikhil Bhatewara on LinkedIn: you can get 2 months of DataCamp premium subscription with your microsoft live id!