Відео

The S-philosophy completely changed my mind. There's constant tension between R and Python users, and as part of the university teaching staff, we often debate which to teach, when, and why. Researchers tend to favor Python and often hate R, with a push to abandon R entirely. Yet, students frequently find R easier to learn than Python, which always baffled me. Since they’re introduced so late to concepts like writing functions and classes. Plus that working with lists, strings (filenames) often feel cumbersome. But now I see it - R is designed to introduce packages and plotting first, then you will eventually outgrow it. It might actually align better with the mindset of science and statistics students than Python. Plus, RStudio is a fantastic teaching tool-far superior to Jupyter Notebooks, which often confuse students.

Here in 2025 ❤

just amazing.

How remove the warnings?

His voice is sexy af 😫🤤

Hello fellow Masterschool Students 😄

Thank you, Prof Roger. I would love to have you as my supervisor in a PhD program.

Thank you so much for this lesson.

Thank you very easy to follow.

great video!

Very Useful, Thanks

Brilliant - just what I needed! 2 minutes in I knew what to do! Shame the R documentation didn't give those steps that would have saved me a lot of lost time last night! Thank you!

Thank you this video is amazing, could you do a presentation for us about anything and after, show us when did you answer the question and how did you managed it?

I observe 2024 and want to address the relevance of Rstudio or R compared to Python. Taking into account new specializations emerging in 2023 and 2024, such as COURSER's bootcamps, I wonder if completing my current DATA SCIENCE SPECIALIZATION is worthwhile. In 2018, R peaked, but its demand decreased after 2021. I am curious about its practicality now, especially with the growing demand for Python. I am contemplating restarting the JHU specialization, having skipped six courses to focus on practical machine learning. Is it necessary to update the program, and how would this help professional growth with program theories not being updated with what the market still demands in its existing data science roles in 2024? Additionally, I am interested in knowing if JHU is still making updates, or if it's not as important whether it's about Python or R but rather about taking the course for its practicality." Does this certification and its teaching have weight in the market?

I like to use ctrl+alt+i to quickly create the codeblocks

Concise and helpful!

Thank you for this video. Im currently looking into DA role and as someone with anxiety when it comes to presenting, the process seemed intimidating. This video made it seem much more manageable by breaking it up into steps.

Very good video. Thanks for the comprehensive explanation and intro into the grammar of graphics paradigm 👍

This is GREAT! Thank you!!!

stat 433 gang

Thank you very much

Thank you!!!

In my version R markdown isn't opening

Love these! Really enjoyed the commentary on the academic system.

Hilary is listening to too many political podcasts, many of which are whipping up AI hysteria

The EU's AI regulation is absurd, requiring a license for every commercial LLM

It seems the generator does not generate the sample to have exactly the mean and sd you give it. I wonder how it cannot achieve this?

What happened to this podcast. I miss you guys!

I was trying ChatGPT, you have explained here better. Thanks a lot!!

Wow! I am impressed by how clearly you explained the markdown. I am so excited to try it myself. Thanks for the great video!

Why, between slides 20 and 21, does the (.*) suddenly NOT refer to open or closed parentheses? I.e. the thing being searched for (with anything or nothing in the middle). There are no parentheses in slide 21 but it only means anything between a numeric.

Wow. Never knew the difference between putting color in or outside of the aes. I would always just play with it. You're so profoundly good

this is the best : short, simple, clear, and cover important information!!! thanks a lot!!!

Oh I'm sure Tucker will be just fine Hitlery, you have her cackle too! ;)

Plots show deviation

Where can we find the excercises?

for anyone who wanted to know what the hell the attr(, match.length) thing does, it can be used define the vector that describes the length of the matches. In case you have many matches and you wanna display each of them in a string you can label your gregexpr(blabla) as "matches". And that will give you the first vector (the one that tells you where each of your matches begins). matches <- gregexpr(blabla) Then you can call attr() to use the second vector by putting matches INSIDE of attr(). Like this: attr(matches, "match.length"). (because remember your aim/end-goal is to rip out some specific substring and manipulate it to do what you want.) You can then use a for loop to generate out all of your substrings all at once.

Thank you so much I have a presentation I have to submit for a job, and this really did help especially in giving me confidence in what I’m doing

As a total novice, even something short and simple like this is extremely helpful and has calmed my nerves a lot. Thank you!

So cool! Thanks, Prof. Peng! It's really helpful!

I started my jorney sure I will be professional on R with you.

I'm running RStudio on macos and when I copy data of a column from the dataset to an object then use View(), the source window shows that column as row with titles Name, type, values . Moreover I can't even scroll left or right to see the complete values. please help no solution is available on net

you are great sir ,i appretiate you

Thks

Quick question! How would a team create an effective Data Analysis Prenstation? How should sections of the presentation should be broken in between individuals?

Never bothered learning anything deep about the grDevices package. R is so wide ranging and production requirements so many, it's been hard to learn depth. But this video broke the ice to diving a bit.

What/where is the website you downloaded "chicago" from?

In minute 20, you talk about how you might be able to compare analyst quality by their ability to intuitively evaluate counterfactuals on their models/analyses. Good analysts need to efficiently explore their hypothesis space and a lot of time can be lost when they don't have strong experience doing so. Do you think analysts can be misled by their intuition? What are some good methods to fight against past experience creating false confidence? Do you think that using past experience to drive analysis can be dangerous? I feel that educated "guessing" to drive model development has caused a lot of issues in my own work. As an example, when you build a model, you might spend a lot of time fine tuning parameters, and your past experience might be helpful, but, there's a danger in coming to believe that you know how manipulating those parameters will effect outcomes. That's why hyper parameter searching methods exist. I've personally made the mistake of using intuition to take shortcuts in model development, when a better approach would be to write more code to use evidence to drive that search (like grid search).

Inspiring 😊

Hi, Roger, I appreciated your effort and the work you do. I took few advanced courses of statistics, but not with software analysis side. I had a bit of experience with R, but I really want to focus heavily on it from now on. I bought your book "R Programming for Data Science", and it is consistent with the videos. Thank you very much, and I subscribed to your channel. Thanks again for the good work!