A few days ago I have completed the "Data Scientist's Toolbox" course from Coursera offered by Johns Hopkins University - Bloomberg School of Public Health
this course collaboratively thought by
Today I am going to share my learning experiences, reflections, and review. hope you enjoy reading and if you're a data science learner or practitioner then I would love to advise you to take this course before moving forward.
This course is 4 weeks long and exactly 4 different parts:
Week-1: Data Science Fundamentals
Week-2: R and RStudio
Week-3: Version Control and GitHub
Week-4: R Markdown, Scientific Thinking, and Big Data
this week you will learn about what is data science is and surprisingly you will find out the hype and reality regarding this topic. The most valuable thing I've learned from this week is the Data Science Process.
- Substantive expertise,
- Hacking skills, and
- Math and statistics.
This week our instructor helps to install the R programming language itself and the most powerful R programming IDE called RStudio. also introduce the R packages and how to build R projects.
this week we learned the importance of using version control and git is the winner of the world of version control and it's has a lot of benefits, and obviously when you are using git then GitHub will come in handy and play a vital role for your project hosting and managing.
We also learn how to connect git, Github, and RStudio to work together smoothly.
this week we learned R Markdown and its benefits. Scientific thinking, Experimental Design, and Big Data, etc.
The most important lesson I've learned here is the questions. You have to ask the right question to get insight from your data. data is everywhere but if you do not ask the right question to your data then you will get the wrong insight for sure.
There are, broadly speaking, six categories in which data analyses fall. In the approximate order of difficulty, they are:
Another important thing is experimental design. it is a very important part of your data science projects or working process. you have to define your working path or formula before starting the actual hands-on work.
An example, we've seen what and how a Bad Experimental design will lead to other research get miss leading results.
that's all for the course.