hi friends welcome back to another video in
today's video we're going to talk about how i would learn data science if i could start all
over again this is part two of the first video and if you haven't seen the first video where i
actually shared my path i highly suggest that you go ahead and watch that video because this video
is going to build on top of it one of the piece of feedback that you all gave me in that video is
that i should be highlighting the path with some resources for you to learn from so in this video
we're going to do exactly that i'm going to share how i would learn data science with the resources
that i would use for learning data science and thanks to coursera for sponsoring today's
video and making it possible for me to share these tips with all of you today so since this
video is sponsored by corsair the courses that i will be mentioning today is specifically from
corsair i understand there are many resources out there that are available to you in this video
i'm specifically going to focus on coursera courses because personally i'm a huge fan of the
offering by coursera so let's get into the video so i'm gonna go step by step in terms of how i
would learn data science what is the first thing i would do what is the second thing i would do and
then in each of those steps i will have resources linked again like if you haven't watched the
previous video i would highly recommend that you go watch that um if you haven't watched it
i will cover i will be covering some of those topics that i shared the the steps i shared at
a high level so the first thing is let's say you want to get into data science the first thing
that you should be doing is finding your niche as i mentioned in my previous videos data science
is a huge job family so i highly highly highly recommend you to narrow down your focus and study
all the jaw families that are in data science so you can narrow down your focus and figure out what
is it exactly that you want to do in data science so some of example of data science job families
include data engineering data science data scientist generalists machine learning scientists
applied scientists research scientists and so many more so the field is huge and there are several
roles within it so the first thing you should be doing is narrowing down your focus and figuring
out where do you want to pursue a career because that will make your study plan much easier once
you know what you want to do you'll be able to define your path much more easily create a study
plan around it and follow through so let's say you figured out what you want to do uh let's say
you're picked data scientist generalist as your niche and you want to continue making a steady
plan for that so the first thing i would recommend let's say a data scientist generalist is your
target role one of the piece of advice that a lot of people give is to start learning to code is
the first thing you do i disagree with that advice and here's why so i'm gonna i'm gonna say this
coding languages and programming is a method is a tool to apply data science it's not the data
science in itself and so for that reason what i recommend to start with is learning the basics
which includes the fundamentals of statistics and machine learning so you're getting your foundation
right so think of it like you're building a house you want to set the foundation first and what
is the foundation of data science or a data scientist role the foundation and the core work
and understanding of a data scientist role is application of advanced statistics and machine
learning so when you start with the foundation you learn the fundamentals start with statistics
start with math start with machine learning that way you have your foundation set so whatever
you do next you're building on top of it so now what i promised that i will be sharing
resources so here are some of the resources that i would personally use for learning statistics and
machine learning and getting a fundamentals right one of the course that i'm actually personally
taking right now as a refresher is introduction to statistics by stanford this is an amazing course
and it covers the basics it covers the descriptive statistics probability data sampling distribute
data distribution regression inference and more and as i said i'm personally taking this course
and i'm actually really enjoying it and i really like the simplified explanation in this course
and i truly believe that once you when you start learning these basic statistics knowledge
and then go into advanced statistics you're actually getting a better understanding of
what data science actually is the second is i would focus on machine learning so a lot of the
concepts that you would learn in statistics would also apply to machine learning so once you start
doing machine learning you will actually realize that a large chunk of machine learning is driven
from statistics and for machine learning one of my favorite data science instructor is andrew
angie who actually recently launched a new machine learning specialization course on coursera on june
16th in partnership with deep learning ai and this is actually the upgraded version of the previous
machine learning course that was available it covers various topics in supervision learning as
well as unsupervised learning including multiple linear regression logistic regression neural
networks such as deep learning decision trees unsupervised learning clustering dimensionality
as well as some of the best practices used in the silicon valley and another bonus of this one is
that instead of using the matte matlab which is what the previous course ml course was using this
one is actually has assignments graded assignments and lectures that teach python so these are
a lot of topics and this course is actually 11 weeks and it's pretty rigorous so it's possible
that you'll start taking this course and you're like oh my gosh what did i get myself into it is
pretty intense so i would make sure that when you go into it you go in with your full attention
and you're able to grasp those topics and if you get stuck like there's a community and that's
another thing that i love about cursora because there's like a community of people who have taken
those courses and then there's a discussion forum where you can ask questions you have access to tas
so you can ask those questions you can you have access to other students who are taking the course
so you can do a lot of like peer learning from each other so hands down a great machine learning
course definitely something to look into and let's say if these two are not enough and you're
still trying to build your foundational skills um your basics of data science um and let's
say if you want to get a bigger picture of what data science is and how it's applied in
the industry ibm actually has an awesome course on coursera as well which is actually a certificate
so ibm data science professional certificate that course goes into what is data science what is the
application what are the different data science methodologies so this course actually covers the
whole data science the data science job family and gives you a very nice overview it gives you
an overview of what data science job family is and then you get a very good understanding of
how data science work in the bigger picture and the last part of the course also taps into a bit
of python so the three courses that i mentioned these are not hands-on coding courses these are
courses that are more theoretical and that's the part that i want to emphasize on building your
theoretical knowledge is very very important 90 of these courses are more on theories and the theory
can be dry i i know like coding is a lot of fun and you like you get to do hands-on work so this
can be a little bit dry so make sure that you're prepared to be slightly bored and if you're
not getting bored which is actually perfect so it it might it's possible that it it might be a
little bit too much at once so pace yourself so you're able to grasp the knowledge and retain it
to sign up for any of these courses i mentioned click the link in the bio and i'm going to
list all the courses that i mentioned today in the description box so make sure that you
click there and you sign up for those courses on that note i'm going to tell you a little bit
more about coursera coursera is an educational platform with hundreds of courses and certificate
from top universities and companies designed for individuals as well as organizations you get to
learn from the comfort of your home from top tier faculty which is one of my favorite parts
and in fact my top favorite data analytics course by google is actually available through
corsair corsair offers both free and paid options and one of my favorite parts about coursera is
that it offers financial aid so if somebody cannot afford to take that course a paid course you can
actually apply for financial aid which means that education on coursera is accessible to everybody
and let's say if you're planning to take multiple courses on carcera you can also look into crusader
plus which gives you access to over 7000 courses at a monthly flat fee which is a pretty sweet
deal so talking about retaining the knowledge let's say you build your theories you build
your fundamentals you build your theoretical knowledge you have very good grasp of what machine
learning is what statistics is you understand the basics you have a good foundation of theoretical
knowledge and if given a data science problem you're able to solve it using theory so now the
next part and this is the fun part and i know like a lot of us like i personally love enjoy coding so
this is the next part so let's say once you build your fundamentals the next part that you'll jump
into is learning to code and this is where you actually apply the knowledge that you have learned
and get hands-on experience i have done a detailed video in terms of the languages that you should
be learning as a data scientist i'm gonna link it here and i'm gonna link it somewhere here you can
go ahead and watch it but specifically i want to focus on three languages that any data scientist
generalists should be very very familiar with number one is sql second is python third is r so
you can pick a combination of sql python or sql r i'm going to share courses on all three of
these and it's actually up to you to decide which combination you want to pick do you want
to pick sql and python or do you want to pick sql nr i have my own opinion in terms of what language
i would recommend i personally would go to python and i have very legit reason of why i would choose
that i've done a detailed video on that as well so you can go ahead and watch it um but i'm gonna
mention courses for all those three languages all right so as i said i'm gonna mention courses on
all three languages so let's start with sql which is my favorite i think a lot of people there is a
misconception that data scientists do not need to know sql i actually completely disagree i think
you need to have a very very good understanding of sql because you will very likely be using sql
to access your data do the joins and to make sure like you have your basic data ready before you
actually do any advanced statistics or machine learning on it so sql is a must-have so for
learning sql i really like the course learn sql basics for data science fundamentals by uc
database and what what i love about it again like there are so many courses on sql but what i love
about these courses that i'm specifically going to mention today for sql python r is that these
are designed for data science in mind so these are for people who want to get into data science
these are for people who are learning data science so this course specifically is targeted toward
analyzing data with in mind that this is for your learning sequel for learning data science
it actually has a hands-on project there are four courses in the course and if you finish all those
four courses you can actually earn a certificate in sql so which is great so the next is python so
python again it's a very popular language there are so many courses that are focused on software
engineering as well as data science so you have to be mindful which course you pick one of the
courses that i've recommended to a lot of people for learning python is python for everybody's
specialization by university of michigan this is created for data science in mind and there
are over 1 million people who have actually taken this course so it's a very very popular option and
people keep taking it because it does a wonderful job teaching python um it's again hands-on course
which involves a lot of quizzes and uh projects and a lot of it covers python data structures
how to use python to access web data which is super cool because you can do project on any if
you learn how to access web data you can actually do project on any of your favorite websites how
to use python for when working with databases and then the final course is the capstone project
which combines everything that you've learned in the course again this is just one of the
course in python that i'm mentioning here obviously like one course is not gonna
be enough i would highly recommend that you possibly supplement this with additional
learning material as well as when you learn something make sure that you're doing additional
projects on top of it to retain that information so for our programming again there are so many
options the good thing about our programming is that most of the courses and learning material
that are out there they're targeting toward data science and data analysis which you can go
wrong so there is a specific course on cursera that teaches r in a very short it's a very short
course it's three courses it's the the course is called data analysis with our specialization and
the reason i specifically love that that it's only three courses so it doesn't go too deep so
you can let's say if you're doing sql and python combination but you still want to get a flavor
of r you can still take this course and kind of like get an idea although i do not recommend
that you try to learn too much at once because then you'll just be overwhelmed but let's say if
you're still curious and you want to understand how r works and like how to um how to basically do
the data analysis using r this course specifically does a good job because it covers introduction
to probability and data using r so it basically covers the basics it also talks about inferential
statistics which i think is is amazing because i do a lot of experimentation work and inferential
statistics is very very important so this this is a good way to also see an application using r
the last one is linear regression and modeling again like this is a short course so this is not
going to cover everything so i recommend that first of all you build solid foundation on these
three concepts that i share in these three courses that are in this course and let's say if you
finish all these three courses and you want to get a certificate for it that's also an option
in coursera let's say if you're taking multiple courses on coursera and it starts to get expensive
you can do that you can continue that so it would be an economically better option to sign up for
coursera plus which is like a monthly membership but you get access to over 7000 courses with one
flat fee which is a pretty good deal it includes many of the courses that i mentioned today sign up
for corsair plus visit the link in my description all right so i think we got the meaty stuff out
of the way you know the fundamentals you know your coding you're able to in in step one what you
learned you able to take your theory you're able to take your coding knowledge and you're able to
like do hands-on projects and solve data science problems so that's where the third part comes in
taking these courses is not going to be enough you actually have to do hands-on project to build
your portfolio and retain that knowledge i'm sure like you have heard of that term um tutorial trap
which basically you take course after course after course and you think like you've learned but
you haven't when what you actually go to do your project you're not able to do it that's called
tutorial track because when you take a course it you think that you have you have gotten it down
when it comes time to actually do it you're not able to do it because there's so many nuances that
you can run into when you are actually doing the project so that's why i want to emphasize building
your portfolio because there are two benefits to it one it's gonna help you retain the knowledge
and two it's gonna help you build the portfolio with additional projects that you would do that
you can highlight on your resume and it's gonna help you with your job search and hopefully help
you land a job and let's say if you have done the courses that i mentioned previously there are
capstone projects next to each course so possibly by the end of taking all those courses you already
have a project portfolio but i still recommend that you do more projects on your own and add
to your portfolio beyond the capstone projects and another thing talking about capstone projects
the reason i love courses that have capstone projects because it the capstone project it gives
you an idea how a data science project looks like so you can take inspiration from it and actually
pick one of your own projects and frame it into a problem similar to the capstone project that
you took there are two ways to build your project portfolio one is that you can go to so many
existing websites that are already out there where there they have given you the data set and they
have defined the data science problem and um you can go to those websites pick up one of any of the
data science problems the data set that is related to it and then start working on your own and solve
that problem one of the favorite websites that i like to mention here is kaggle it has thousands of
free data sets that you can use for building your data science portfolio the second option might be
more interesting to you if you're curious and have a creative side so with this one you can actually
pick your own problem and you can choose to solve it for example i love doing content creation
so one of the projects that i would like to do which i don't know if it's possible i
need to think more about it is predicting if a youtube video will go vital what are the
elements of a youtube video going viral and then doing some sort of predictive analytics on
top of it to figure out if a video given elements xxx will go viral and if you if
there is an interest for you let's say cars video games tweeting whatever it is like you can
pick an area that interests you and you can um define you can define your problem and then you
can work on it using the skills that you have learned and solve it and that the bonus with
that is that when you put it on your resume and you go to an interview you'll actually have
something interesting to talk about something that you are actually excited about so something to
think about all right so we have covered so far picking your niche learning the fundamentals with
statistics machine learning and math learning to code building portfolio and then we're at the last
part we're not done yet so for those of you i mean i personally if i'm learning data science my end
goal is that i want to land a job so i'm sure a lot of you are learning data science your end
goal is to find a job right so i don't want you to stop after building the portfolio there is more
that you need to do in order to meet your end goal if finding a job is what it is which i hope it
is um and i understand if you're just learning data science if you're curious that's fine too
you can stop at the previous step all right so the reason i wanted to dedicate a section to
job hunting is because interview prep learning knowing data science being able to do it is
not enough to land a job and that is because interview in itself is a monster it requires
skills for you to be able to answer questions in a timely fashion so most of those interviews
are like 45 minutes or one hour and you're given multiple problems in that time frame and you
need to be able to solve and allah it will be theoretical it will be also hands-on coding so it
requires skills and practice to be able to answer those questions in a timely fashion under a
pressure setting so once you're ready to go into the job market make sure that you're dedicating
enough time to prepare for the interviews because it's an investment similar to the previous
steps i mentioned this is very important because it's going to help you land the job so i've
done a few videos on interview framework that i have i personally use so you're welcome to watch
those videos if you're looking for more detailed guide on interview prep it's not specific to data
science but it's more general you can watch some of my previous videos where i haven't talked
i have talked about interview prep and maybe i'll do more videos on that topic and share some
resources with you all so stay tuned for that so this is the honorary mention of one of the courses
that i was debating if i should mention it or not i'm gonna mention it anyway because i personally
love love love this course yes this is google's data analytics certificate i understand this is
targeted the name suggests it's targeted toward more data analytics career letter but i think
it's super helpful for anybody who is entering into data science as well and the reason for that
is let's say if you don't have any data background if you're just entering new to the data science
domain this course actually does a very good job of connecting the dots of why data is important
and why there are so many jaw families in the data world that exist today it also does a very
good job of providing the business context solving problem and storytelling which i believe
is super important for a data scientist as well so although this course is not targeted toward
data science it does give you a very good understanding of the fundamentals and the whole
data world and why we're doing what we're doing basically so i highly recommend that you check out
this course i love this course so much i actually have done a dedicated video on the course
itself reviewing the course in detail and giving my thoughts so the the course basically
has eight courses starts with building foundation and the course is actually designed in a way
that is how a data project would be designed for a data analyst but it gives you still it like
gives you a very solid idea so it starts with like foundation of data how to ask the right question
which again is very relevant to data scientists as well although the set of questions would be
different how to prepare your data for exploration how to process your data from dirty to clean data
visualization and storytelling so if you're new to the data domain this course is also actually a
good start in addition to the other courses that i mentioned to kind of get a good understanding of
the data domain itself and why it's important to ask good questions and why it's important to have
a have a good storytelling great communication um and the bonus in this course which i
haven't seen in a lot of other courses is that it talks about interview prep they're like
mock interviews at the end of at the end of the course so it basically prepares you for more than
just the core curriculum it gives you like toolkit to be successful in the job search phase as well
so which is another reason i love this course again i wanted to mention this course because this
is like hands-down one of my favorite course if somebody is entering in the data domain regardless
of withdrawal family i think this is a good start to kind of like build your foundation in the
data world well i didn't mean for this video to be this long but i really hope the information that
i shared in this video is helpful to you if you have any questions or suggestions for future
video make sure to give this video a thumbs up and let me know in comments and again like
the courses that i mentioned today they're all linked in the description thank you so much for
watching i hope you're having a great day bye
