You are on page 1of 2

How to learn Data Science [or anything in general]

1. Get a hold over the language to be used for implementation – practice the basics till you are
comfortable.
2. Practice and become comfortable with data cleaning and processing – this is essential.You
need to know about your data well before analyzing it.
3. Understand and implement one algorithm at a time. You may not understand it completely
in the beginning. Give it time. Do not get stuck at one place.
4. Try something else and come back later. Get the intuition of what is going on behind the few
lines of code written to implement it.
5. Dont watch course videos like movies , make your own notes and code along, make changes
in the code , make mistakes and try to resolve them.
6. With practice things will keep getting clearer. Keep reading about it from multiple sources.
7. Go through the course videos before attending the class.
8. Make extensive notes when trying to understand / watching videos or attending the live
online class – it helps with internalising the information as well as with the review.
9. Understand limitations of each algorithm, if any. Understand the usual application areas of
each of the algorithms and why are they used there. Try understanding how these algorithms
differ from each other. Using a single problem statement and solving it using different
applicable algorithms should help here.
10. Remember, the algorithms are just tools to solve problems. Don’t lose sight of the main
problem statement during implementation. Many times, simple implementations are good
enough. Build a simple solution first quickly and then iterate - you may want to try different
features, tuning the parameters and hyperparameters, different algorithms, stacking
different algorithms together and so on.
11. Make sure you try one thing at a time and not everything together since you would want to
know what change made the algorithm(s) better or worse. Explain what you have done to
one person who knows about the algorithms in technical terms and to another who does not
know the algorithms per se but can follow the problem and its solution logically. Gaps in
understanding are best understood when explaining to others.
12. Learning is an iterative process – your first implementation may not be the best; your first
take on understanding an algorithm may not be complete. It can be made better over time.
Please be patient. Journal your progress. This may help you blog later.

How to ask good questions?


Asking questions is the key to learn . Figuring out everything on your own is good, but it takes time
and energy which can be best used in progressing further instead of digging your heals in one
place , struggle and possibly lose motivation . Now to "how to ask good question?"

If you want people to help you, give them a way to do it

1. Complete context is important . Whenever you ask a question, assume that the person who
is going to answer your question , knows nothing about the problem . And proceed from
there
1. A code is giving error. Attach full code , along with error message .
2. Make sure the information that you provide is accessible . For example , a screen shot of
the error msg, pasted into a doc file and uploaded in zip format; can not be readily
copied and used to quickly perform a google search.
2. Make everything relating to your problem available upfront . Many times , your issue remains
pending for response despite having a simple solution, because the way information was
presented; doesnt make it very apparent.

1. A code is giving error . Add the error msg as part of the text you write on your forum .
2. While you are attaching the full code , also paste the part of the code on forum, directly
visible, which according to you gave the error .
3. Do mention the solutions that you tried and did not work. Paste the link to the
resources where you found the solutions that you tried
3. Reduce the effort needed to solve your problem

1. If you are attaching the code , make sure it contains the relevant bits only , instead of
being a 500 lines of mixed code .
2. Make sure that its enough to reproduce your issue
4. Do try to quickly google the issue wherever possible and try to make sense of the solutions
that people suggest online. While resolving the doubt certainly helps you learn and grow.
Learning to find solutions on your own is a key skill set to develop in any area.

5. Instructor that you mail your questions to , is handling tons of other conversations across
multiple threads . Make sure that every mail that you send has complete context of the
conversation and progress made so far . Otherwise it might move down the priority ladder
and might even be forgotten

6. Search in the forum if others have had the same issue, its possible that same issues has
already been discussed an resolved in the forum

7. Acknowledge the help when you are the beneficiary and help others in the community with
your learnings . Be polite and above all, understand that language is a handicapped way of
communication. Trust that everyone had best intention in their heart ; even if, at times your
perception of their language doesn't reflect it.

8. Edvancer platform is there to enable you to learn; not for helping you mug up answers of all
possible ML questions out there. Many at times , instructors might answer your questions
with a question, follow up with your answers , you will eventually reach to the solution of
your original problem and would have learnt valuable lessons along the way .

Some resources which you will helpful in this journey :

https://stackoverflow.com/help/how-to-ask

https://princetonuniversity.github.io/PUbootcamp/sessions/technical-questions/HowToAskQuesti
ons2018Bootcamp.pdf

You might also like