Free Data Science courses starting very soon - Learning Statistics & SAP Hana Text Analysis


Hi All,

There are two courses starting very soon, which could be of interest for Data Scientist, I mean the people of this forum :slight_smile:

1.* Statistical Learning by T. Hastie and R. Tibshirani from Stanford.* I am sure few of us know those names. The course follows the book of same name (you can get electronic copy free). Fantastic chapters and both Professors are very engaging as Andrew NG (for the folk who did Machine Learning on Coursera). The course link. Go quickly the course starts tomorrow.

By the way T Hastie and R Tibshurani put there last book free as well :slight_smile: see here Statistical Learning with Sparsity. Great book but on the mathematical side. Do not take this one as one example of the course :slight_smile:

  1. For people interested in SAP Hana, SAP organises one on line course about Text Analytics on Hana platform, this is the first course of this type. I can not say a lot only that I should follow it. We shall certainly learn about the PAL Library. Usually you have one SAP Hana development instance when you take one SAP open course, so I think it will be the same this time. The course start in one week time. Link to SAP Hana and Text

If any further questions or need support add your questions below.
Best regards


Perhaps we could start an AV study circle? :slightly_smiling:


thanks @Lesaffrea for sharing this.



thanks a lot @Lesaffrea for this. And @anon you are right…A study group of Av can be formed for this course.


Hi @shuvayan, @anon, @kunal

here it is, it starts !!! All the details below. @kunal do you think we need a special page if people are interested by the study group?


Welcome to Statistical Learning!

Your learning adventure with Trevor, Rob and their team begins today.

The course follows closely the sequence of chapters in the course text “An Introduction to Statistical Learning, with Applications in R” (James, Witten, Hastie, Tibshirani - Springer 2013). Remember, this textbook is available for free online at

The first week will be an overview of Statistical Learning, and will cover the first two chapters of the book. On each subsequent Saturday we will release the materials for a new chapter. Here is the schedule in detail:

Week 1: Introduction and Overview of Statistical Learning (Chapters 1-2, starts Jan 12)
Week 2: Linear Regression (Chapter 3, starts Jan 16)
Week 3: Classification (Chapter 4, starts Jan 23)
Week 4: Resampling Methods (Chapter 5, starts Jan 30)
Week 5: Linear Model Selection and Regularization (Chapter 6, starts Feb 6)
Week 6: Moving Beyond Linearity (Chapter 7, starts Feb 13)
Week 7: Tree-based Methods (Chapter 8, starts Feb 20)
Week 8: Support Vector Machines (Chapter 9, starts Feb 27)
Week 9: Unsupervised Learning (Chapter 10, starts Mar 5)

We hope that you will follow along with the class each week and share your comments and questions along the way. However, if you join the class late or are unavailable for a week, access to the material from previous weeks will remain open. Notice that we give you quite a long period from end of week 9 till the course termination. The deadline for completing all the requirements to get your Statement of Accomplishment is April 4.

To pass the course you need to get 50% or more correct answers on the quiz questions. If you score 90% or higher, your statement will be “with distinction”.

To see the course materials, click on the Courseware tab on the upper left of the entry page. You’ll see the sequence of sections in this course listed on the left. Click on a section to see its subsections, and click on a subsection to see its units, which contain videos, questions, etc. Within a given subsection, you can move from one unit to the next by clicking the next icons, which appear at the top and bottom of each page. The sequence of sections, subsections, and units is intended to be experienced in order.

Versions of the class videos are available for download. If you look under any section’s video, you will see a “Download video” button. If you click that, you can download and save the video on your device. These are not as high resolution as the class video, but if you also download the pdf slides for each chapter, you should be fine.

For further details on the course, click on the Courseware tab, open the “Course Logistics” section, and click on both the “Getting started” and “How to access the course textbook” subsections.

It’s a pleasure to have you as part of the course. Enjoy the journey!

If you are a fan of the course, please help us reach more students through social media. Please use Facebook, Twitter, or the social media of your choice to share:

  1. Our Promo Video:

  2. Our Course Site:

  • Trevor Hastie and Rob Tibshirani



Study group is an interesting idea.

Let us float a new thread asking people to leave there name if they want to be part of study circle. We will also put a word on social media channels later today / tomorrow.

If you can start a thread by providing all the necessary details, I’ll also pin it here for a few days so that the regulars notice this initiative.

In order to help addressing people, we will enable a group address for this group (say something like @stats_coursera and also a category, so that people can distinguish it clearly.

I can see this becoming a far bigger and engaging initiative, if it does well in tests.



Hi @Lesaffrea,

Just a small question about the Statistical learning course. Is this course different from Machine learning by Andrew NG? Because I have already done that, would this course be beneficial to me? Please let me know.



Hi @aayushmnit

This course is very different from the one of Andrew NG. Andrew emphasis calculus for example for gradient descent, which he explains very well. T. Hastie and R. Tibshirani gives you one overview of statistics with all the methods, for example when you are at the lm chapter they will introduce GAM (a method I like a lot , my view) of Loess, one of the chapter I like as well is how they explain bias variance they use lm as a support.
I think the best is to go though few chapters of the book as the course follows the book exactly, advantage here if you want the certification you do the lab exercises and you got it !!
In few words this course gives you one overview of statistics and some methods, keep in mind T. haste and R.Tibshirani are the fathers of Lasso and Elastic Net and they are engaging so very high quality and a very good way to refresh your memory on some topics and to learn some new. Something in common with Andrew it is a demanding course as well :slight_smile:
If you want to go further than the course of Andrew I would recommend you take it, it will even clarify some points this I am quite sure.
Hope this help


@Lesaffrea Thanks for the explanation. Let’s do this :slightly_smiling:


good idea let start :slightly_smiling:


Hi @aayushmnit and all.

So during the first week few questions that have appeared in this forum are explained. I try to put the points here.

  1. Supervised unsupervised leanring. Explained in introduction video and slide “introduction Handout” page 22 and 25

  2. Overfitting - First overview in 2.2 Dimensionality and Structure Model = Example split thin plate- P14 of the slides of the second handout.

and more to come … well there is the quiz as well, the one about dimensionality could look quite difficult it is not.

Have a good time



Execellent I will definitely try an follow these stats courses.