Category: English
This semester, I have completed my first Massive Open Online Course: The Analytics Edge course on edX platform. I loved this course. Although it was one of the most time consuming courses I've taken, it was very enjoyable. The course teaches Data Science concepts using R language. It covers commonly used and essential Machine Learning methods together with Visualization, Optimization and Text Processing. The syllabus is as following:
- Introduction to R
- Linear Regression
- Logistic Regression
- Trees
- Text Analytics
- Clustering
- Kaggle Competition
- Visualization
- Linear Optimization
- Integer Optimization
Before the course, I didn't know anything about R language but I learned enough to fulfill my needs. It teaches R throughout the course, step by step, as needed. Each week, lectures require 1-2 hours to watch and answer the quick questions, assignments (3 required for each week) take at least 5-6 hours per week.
I recommend you to take notes while you're watching the lectures and doing the assignments on Rmd files. RStudio app allows you write R notebooks in markdown format where you can use it as a reference document later on. Since assignments require knowledge from the previous weeks, reference documents are very handy. When you take notes, the course will require almost 10 hours per week. You can do the extra assignments if you wish, that would take 1 extra hours each.
Assignments let us apply the methods we learned on real life datasets, that's the best part of this lecture. We analyze car crime dataset to infer when and where the police should patrol in order to prevent new crimes. We analyze flight delays in order to guess which flights will have delay. We predict election results based on previous ones, we predict stock prices, we find suspicious documents among thousands, we segment (cluster) customers based on their behaviors, we find factors affecting heart attacks, we try to predict popularity of music records and loan payments (who will pay or not pay), we detect sentiment on tweets, we analyze MR image to detect tumors, form the best baseball team to be champion, etc. We also join a competition on Kaggle to test our skills as well. This is where you will find a chance to assess what you've learned.
I wasn't bored at any part of the course but got excited. I recommend you to take this course if you are interested in Data Science and R but beware you'll have to invest a lot of time for it. A new batch is starting on June 2nd. It is free to join and you will get a certificate upon successful completion, but if you want a verified certificate, you will have to pay for it.