Data Science Full Course | Data Science Tutorial | Intellipaat

Hey guys. Welcome to Intellipaat In today’s Video. We’re going to talk about a technology that
is a backbone of Hottest job of 21st century. That is data science. So let’s start this video with a quick fact. According to McKinsey. That is a 50 percent gap between the supply
and demand of data scientists. This clearly indicates that there’s a right
time to seize an opportunity to land yuorselves in the hottest job of 21st century. So in this spirit of helping you guys to become
a data scientist we have come up with the most comprehensive video. On data science. So this video has everything you need right
from the very basic concepts of data science that the most frequently ask technical interview
questions. So before we get started please do subscribe
to Intellipaat’s YouTube channel to get some instant notification about upcoming videos
also guys if you are interested in doing a full fledged course in data science please
do check out Intellipaat’s data science architects masters course that is co-created in association
with IBM. Link for the same is available in the description
box below. please do check out. Now let’s take a look at the agenda of this
video. We’ll start off with a quick introduction
to data science to understand what it is and why do we need it. Later we’ll be working on the complex mathematical
operations using numpy Then we’ll be learning about data manipulation using pandas and data
visualization using matplotlib. Then we’ll be moving ahead with a machine
learning concepts. We will be also learning about machine learning
algorithms such as logistic regression and linear regression and much more. We will also be working on an end to end project
in data science which will help you to polish all the necessary data science skills. Finally you will also be learning about the
most frequently asked technical interview questions. So without any further delays let’s get started. So guys we’ve all heard the term data scientists
some where in our life I presume and to put it all in one simple sentence. This is how I would pretty much go about saying
guys well data scientists are a new breed of analytical data experts who have the technical
skill to solve any complex problems. And then the curiosity to explore what problems
need to be solved as well sound sounds amazingly complex right. Well it actually isn’t. Well let me tell you this very funny thing
that I just read on the Internet data science is an rocket science. And let me prove why. And there’s endless opportunities with data
science and you all can grab Very good opportunities guys so coming the data scientist is a person
who is a combination of a mathematician a computer scientist and he’s a trend spotter
as well. Well mathematician because he is required
to play around with a lot of mathematical concepts a lot of differentiation a lot of
calculus and so much more. And then a computer scientist because he needs
to convert all the mathematics into computer science and then work with it later and then
as a traend spotter he needs to find out some analytics or to hunt for trends in the future
or to make it a part of his forum or her forum for example and then pull all the concepts
together and to work with it guys. So the question you might be asking right
now is so where do data scientists come from. Right. Oh well think about it this way a data scientist
is pretty much a person who can assume multiple roles over the course of a day right. So he can be a software engineer in the morning
or he can be all data analysts at lunchtime can be a troubleshooter. At the time of high tea you can be a data
miner a business communicator a manager and then a key stakeholder in any data driven
enterprise as well So basically at the end of the day. He puts his hand in multiple roles with the
designation of a data scientist and gets the job done. With respect to everything from the lower
levels to the highest levels and all this level of business should making in this level
of skill required to become a data scientist is what people look up to these days and that’s
why they’re very highly paid as well guys. So many data scientist you know again pretty
much began their careers either as data analysts or decisions as I have mentioned right. But then think about think about all the big
data that has pretty much went to grow and evolve or these days right. So I support the data being evolved again. The roles are being evolved as well. Data is no longer just an afterthought for
I.T. to handle. I had to put this in bold for you guys too
pretty much you know look at it and contemplate about it as well so data. Again as we pretty much talk about it as in
the Hexa bites these days and petabytes is pretty much a thing of the history by the
way. So when you have so much data to handle you
are going to need some good manpower behind that right up to coming back again. It’s a key information that requires analysis
create of curiosity and a knack for translating high tech ideas into new ways to turn a profit. Well you pretty much are getting the other
side of a data scientist right from the slide right. So you pretty much might be thinking a data
scientist just sits in you know punches in code to day in day out new pretty much gets
paid and goes on. Well not exactly that. I do have a good number of data scientists
as my close friends and all of them seem to agree about this point as well. A quick and four guys. In case you are looking for a full fledged
course in data science please do check out in Intellipaats data science architect Masters
course that is co-created an association with IBM. This causes all the required skills to master
the concepts of data science and become a data science professional. Link for the same is available in the description
box below. please do check out. Now let’s continue with the session coming
to the next question that you might have in your mind right now. What does a data scientist actually do well
a data scientist job again is to analyze all the data for any insights that can be generated
to find these hidden insights like these tiny amounts of tressure that’s so hidden inside
a business and then to pull it all out guys. So here are the following tasks that I would
like to mention that a data scientist would do right. So the first thing is to pretty much go about
identifying all the data analytics problem that offer the greatest value to the organization. Yes because at the end of the day these data
analytics problems if they’re sold really early than it is it sounds very lucrative
and at the end of the day it brings more money to the organization as well right. And the second point is pretty much to get
to know. You know you’re right. Data sets your right variables your core to
what are you working with. You know to have of hand advantage with your
core is going to pretty much again give you an upper hand compared to your peers as well. So all you’ll be working with will pretty
much you know unstructured data you’ll have a lot of images from data sets you’ll have
a lot of videos you’ll have a lot of music there’s so much more that you know you have
to look into as a data scientist than just looking at it from a far perspective and then
coming to or discovering new solutions and opportunities by analyzing the data. Well I’ve already told you that you know data
is the store well data just is is this raw information which pretty much is is useless
right. Making sense of this data converting that
data into information that at the end of the day and a company can go about making use
that’s that’s again that really takes a lot of skill right. So coming to the next point of collecting
well a large set of structured and unstructured data from disparate sources well structured
data is something which can be handled very easily. So consider an SQL table or something which
is in the form of a structure where you can look at it and make sense out of it. Even your computer can make sense out of it. That’s pretty much what is the simplest form
for a structure data well unstructured data again as you can probably discern it but then
you really need you machine you machine would need a little help to understand what the
actual data is right. So that is unstructured data. And then the next pretty much you know insight
is you’ll have to go about cleaning and validate the data to ensure that your data is extremely
accurate. You do it as complete and thourough your data
is uniform as well. The next pretty much again the point speaks
for itself right. Data has to be clean. We would we wouldn’t want to be working with
data on unless it actually goes into your business model and work with it right. So if it is working on a piece of data at
the end of the day if you know it is useless then you’re just wasting your time you just
wasting your resources on it right. We don’t want that and then you would want
device and apply more tools and machine learning algorithms and used to go about mining and
hunting or you know for it or let’s say it’s a literal treasure to hunt in the world of
big data and then you need to analyze the data to identify patterns and trends. Well to me just looking at what a data scientist
does day in and day out that’s pretty much entertaining at the same fact. And then knowing that this is a very highly
paid job and knowing that the people who are data scientists have a good amount of fun
at their jobs is pretty much an amazing thing. And on that note we need to come check out
what are the prerequisites that we can pretty much have to go about becoming data scientists
on our own guys. The first most important thing which you might
not have thought of was effective verbal and communication skills guys see because at the
end of the day let’s say you’re writing machine learning algorithms or you’re working with
your big data team you’ve pulled out very good insights. If you do not have the communication skills
where you can go on tell this to your superiors let’s say pretty much have to go to a stakeholder
and tell him this you have a meeting where you have to tell a superior or you have to
explain this to your junior you have to explain this to your co-workers peers and if you can
not do that if you cannot explain machine learning or neural network to a person who
doesn’t know machine learning but wants to understand what’s going on. Well that would be really tough if you did
not have communication skills as a data scientist so having skills is a very important thing
guys. And the second thing is if you work for a
moderately sized company your project will be too big to handle single handedly perhaps. Right. So you need to be at the top of your game
when you’re working alone all when you’re working with the team because your pretty
much whatever code you are writing may be split among five people many split among 10
people and then you guys are sitting at different parts of the world just writing the single
piece of code right so knowing that you can pretty much communicate with each other really
well get the work done and have be a very good team player at the end of the day is
a very good prerequisite if it gives you guys a very good team players then guys you can
pretty much become a data scientist. A quick and for guys. In case you’re looking for a full fledged
course in data science please do check out Intellipaat’s data science architect Masters
course that is co created an association with IBM. This causes all the required skills to master
the concepts of data science and become a data science professional. Link for the same is available in the description
box below. please do check out. Now lets continue with a session and the third
important thing is you need to have this interest to dvelve in to data to pretty much hunt for
stuff and data and collect and make sense out of the data and eventually by analyzing
this data you’ll be picking out some very very good insights from this particular data
guys. And number four is very good problem solving
skills. Again you will need to have a certain amount
of skill when it comes to problem solving puzzle solving you know because you’ll be. Because this is this not well some field where
you have a very simple goal and you just go and get it. You will have you’ll have you will know what
you’re going after right. So you will have some goals that you know
are. Let’s say there are hidden goals right now
but then you start hunting in your data you start picking up your insights and you realize
Whoa three months from now my data is going to look like this or let’s say three days
from now or after I run this machine learning algorithm my data is going to look like that. So you need to have that kind of analytical
thinking and problem solving skills. And if you guys have that then trust me you
can become a very good data scientist Well if you’re wondering if you might be a junior
and associate or a student watching this livestream right now and you might be wondering well
is it possible for me well guys sure you do not have to be an absolute professional in
this right now. But and then they stick to the end of the
video we will make sure that you know I will personally make sure that I can get you on
track to get all the prerequisites to become a scientist guys and then the most important
highlight in this particular slide is the educational background right you guys. I wouldn’t stress on this very much because
I know people who do not have a computer science background becoming data scientist but then
many of the companies especially in India and Asia they require a computer science background
for you to become a data scientist or you need an educational background from information
technology you will need mathematics and statistics is extremely important because you’ll be working
with a lot of numbers you’ll be crunching in a lot of graphs and so much more and then
work experience in a related field. Well if you have it good enough. If you don’t then a certification will come
into play in this particular point guys so on that note we need to quickly check out
what the roles and responsibilities of a data scientist are. Again I have pretty much put it into a very
simple terms. I’ve broken it down to four concepts right. So as a data scientist again guys you will
need to know that you are need pretty much need to design your own systems your own algorithms
you need to develop something from data you need to deploy the most relevant solutions
for your business and share your results with all these stakeholders and business leaders
and so much more right. So what does this call for. Well this pretty much has you to know requires
you to pretty much go about preparing goal for all the big data all that have data that
the world has to offer. Implement all the relevant data models create
databases to support a business solution present all of these to stakeholders and so much more
right. So as i told to keep it simple I’ve broken
it down into four terms out here analytics collaboration business understanding and strategy
design guys so coming to the first one it does analytics. Again I have to put it out in simple terms
it’s exploring ways to infer relevancy in your particular data right. We already know that you know the amount of
data that’s being generated every day is 2.5 quintillion bytes 2.5 quintillion bytes I
wanted to put that in bold and probably this let you guys share it quintillion bytes site
and having up and most of it is relevant data at the end of the day right. This is huge. You need to you need to take charge and go
about leveraging your fast growing data sources and you need to capture the market analyze
the market and knowing that data is the biggest business challenge these days and that your
competitors are facing it. Solving that problem right now is really important
as a data scientist guys and then regardless of whether the data is you know from a computer
it’s from other sources it’s from Twitter. We really don’t care. The data comes in from all the different sources
in this world. But then at the end of it you will be doing
some relevant analytics on it and you will be making sure to discover some important
information that which if you would not then the information would just stay hidden in
this data which is useless right. A quick info guys. In case you are looking for a full fledged
course in data science please do check out Intellipaat Data science architect Masters
course that is co created in association with IBM. This course has all the required skills to
master the concepts of data science and become a data science professional. Link for the same is available in the description
box below. please do check out. Now let’s continue with a session. So this brings us to the second important
thing. So does this collaboration collaboration again
as it all collaborating with your teammates collaborating with your peers. But then the highlight of a data scientist
is collaborating mostly with the stakeholders. So you must need to learn. Do you know you have to learn to design develop
and implement the most appropriate solution for your business and then pretty much does
the exact same point that we already discussed. You need to prepare for big data you need
to handle and create databases. Implement a data models guys so as data scientist
you know you will be working closely with your marketing team. You will be working closely with decision
makers stakeholders in the products and your different products to basically you know communicate
all your possible outcomes of what can happen to your product guys and this type of collaboration
as we already know what has been proven to be a huge achievement and is often considered
to be one of the most important data scientist roles and responsibilities well. Think about it. I already told you right. Communication is an extremely vital part of
data scientist life and as you might have thought initially that coding is everything. Well actually it is’nt guys if you’re very
good at communication trust me you can become a very good data scientist in your life as
well. So this brings us to our third important role
and responsibility which is understanding your business. You need to understand what your business
problems are and then you need to find the best possible solution to your business problem
right. So again data scientists combine lot of data. They go on computing and all the technology
they use is at the end of the day helping them to gain very much valuable insights you
know by digging by leveraging all the business levers available to them right they will be
pretty much making use of everything that thrown at you to make sense and then do analytics
on it. This requires a lot of skill and and this
just look at it. So pretty much you have to combine your data
to compute the data you have to go on using the technology right. It sounds so complex. I do not want you guys to be overwhelmed by
this. When you put it down on paper this looks complex
but then at the end of the day it is a very simple concept and stick to the end of the
video and I show you how you can become a data scientist. So coming back you know advising companies
on data potential and gaining new insights and then transforming these insights into
business goals is very important guys. Developing solutions that improve business
performance through advanced statistical analysis global data mining we just saw that person’s
resume. Data mining was a big part of that resumé
right. And then data visualization techniques as
well. last one I promise. So the last roles and responsibility that
I want to discuss with you is strategy and designing that you need to know how you can
interact with your teams and customers right. Ask a lot of questions as a data scientist
build relationships because when you ask a question you will get to know the details
of how you can work faster. And then when you all pretty much build relationships
you can understand the context of the roles in your organizations right. Take a second to give that another read again
and this would make much more sense to you. Now that you have been enforcing this part
of interaction a lot so I hope you guys did that anyway. Up to you know a good way to learn is to interact
with people we already know that. And then even let’s say if you want to know
how you can retrieve data you will be know which table you need to go to which person
you need to talk to in real life. Here the table we’re talking about is a database
table. But then yeah you will actually know which
physical day will you need to go to to get your data from your big data team and so much
more guys so you can answer as many questions as possible just by finding out where you
can look guys coming to the most important part of a data scientist job is a data scientist
salary guys do not be dumb founded by these numbers these numbers are just the average
and the number can be lower or number can be very high from the numbers that I’ve quoted
here in the United States of America. The average salary for a data scientist is
one hundred and twenty American in hundred and twenty thousand American dollars. And in the in the country of India and pretty
much is 16 lac Indian rupees per year. So this is per annum rate. So these numbers I always get an audience
where you people are asking me to give me numbers in Indian rupees and in American dollars
well guys to see your curiosity zero. The average numbers. I personally know people walking in Fortune
500 companies who make a lot more than both. The numbers that you see on the screen. But then I just do not want to give you false
numbers tonight. So this is the average I do like it stands
right now a hundred and twenty thousand dollars and 16 lac indian rupees. And then this is for many of us is a big number
and we can be happy with this. Well we can be happy with this knowing that
day in and day out we are going into office. Are not on the way to become a good data scientist
or we are the scientist already. And then we are loving our job whenever I
need a data scientist or data analyst from very good company. Those guys love their jobs and you know they
do not complain one bit about their job. They like anirudh it has been amazing we love
our job. you know we love coding and we love that we
are being paid handsomely for doing what we love right. Guys again this number again speaks speaks
huge volumes for me and I hope it does for you as well. So this will bring you to a very curious thought
of who might be hiring in this world right. Let me first begin with India guys with Unisys
we have fractal analytics we have IBM we have enstant young they have edgeverveof edgeverve
was an infosis company we neosigma in a very good data analytics company here in Bengaluru
again we have OlA you have Oracle Siemens Truecaller all these guys are on the constant
hunt for data scientists around the world guys that are ready to pay you the amount
you have to show them that you are skilled enough to get the job and they will hire you
irrespective of your location irrespective of your pay and then coming to the rest of
the world or mostly the United States of America. Well Instagram’s hiring LinkedIn’s hiring
Pinterest Viber WhatsApp Evernote Android ah Twitter Tumblr wechat Facebook Vimeo YouTube
Amazon Oh I’m just trying to name all these logos I see on the screen and do not be in
be fedeled by just the logos on your screen each and every one of these companies is paying
over one hundred thousand dollars over 15 lakh Indian rupees to hire the best data scientists
out there guys again I’m pushing on it you just need the right skills and you will land
an amazing job as a data scientist with all these guys Skype is hiring and adobe is hiring
Best Buy is hiring Wal-Mart Apple BBC Google well throughout the world again let me push
this fact again you might be wondering well these guys are hired in a America not in India. Well no if you guys have the right skills
if you are trained first certified and the right thing you can push for all of these
jobs and you will get there guys this is the guy you know this is pretty much it you’re
seeing your screen bombarded with employers around the world who just want to hire are
data scientists right now we had data coming in every second from every corner of the world
but the problem is we did not know what to do with it. So we had a lot of data with us but we were
not trying to find out any insights from the data or in other words we were not making
any decisions based on this data and this need to understand and analyze data to make
better decisions is what gave birth to data science. so now we will go ahead and look at the scenario
where data scientist needed. So this is MAT CEO of a telecom company called
black space in the last six months the company has been losing its customers to its rival
company named white space and the company goes into a loss. Now Matt wants to understand what is the reason
behind this So Matt calls up David who is a data scientist working at this company. He asks David to analyze the entire customer
data which they have and come up with solutions to increase customer retention. So David starts out by understanding the data
first. Then he goes ahead and build some algorithms
on top of this. And finally shows the results in the form
of beautiful visualizations. So guys the need of data science comes in
and we have to understand the data to find interesting insights and make informed decisions
on the basis of this data. So the simplest explanation of data science
would be applying some sort of scientific skills on top of the data so that we can make
this data talk to us. Now what do we exactly mean by applying scientific
skills on the data. Well precisely. Data science is an umbrella term rates and
combines multiple scientific skills and techniques. So some of the techniques which data science
comprises are. Data visualization data manipulation statistical
analysis and machine learning. So when you combine all of the scientific
skills into one what you get is nothing but data science a quick info guys In case you are looking for a full fledged
course in data science please do check out Intellipaat Data science architect Masters
course that is co created in association with IBM. This course has all the required skills to
master the concepts of data science and become a data science professional. Link for the same is available in the description
box below. please do checkout. Now let’s continue with the session. Now let’s go ahead and have a look at these
different scientific techniques in brief. So we’ll start with data visualization so
data visualization is an essential component of the data scientist skill set. So when simple terms data visualization can
be said to be an amalgamation of signs and design in a meaningful way to interpret the
raw data through graphs and plots. The next technique in data science is data
manipulation. So normally the raw data which we get from
different sources is extremely untidy that is drawing inferences from this data is extremely
difficult. So this is where data manipulation comes and
these data manipulation techniques help both to change the data and make it more organized. So that finding insights from the data becomes
easy. Then we have statistical analysis. So simply put statistical analysis helps us
to understand the data through mathematics that as these mathematical equations help
in understanding the nature of the data set. And also to explored the relationship of the
underlying entities. And finally we have machine learning which
makes up the major part of data science fully understand the concept of machine learning
where this example here. So what you see in this light. What is this exactly. It’s a car isn’t it. And how about this. Well this is a car two. And thus again a car. Now how do you know all of these are cars. Well as a kid you would have come across a
picture of a car. And you would have been told by your kindergarten
teacher or your parents that this is a car and your brain learned that anything which
looks like this is a car. And that is how our brain functions. But what about a machine. well like the same way as fed to a machine. How will the machine identify it to be a car. So guys this is where machine learning comes
in. So we keep on feeding images of a car to a
computer where the label car under the machine learns all of the features associated with
the car. And once the machine learns all of the features
associated with the car. We will feed it new data to determine how
much has it learned. In other words raw data or the training data
is given to the machine so that the machine learns all of the features associated with
the training data. And once the learning is done the machine
is given new data or the test data to determine how well it has learned and that is the underlying
concept of machine learning. So guys just to sum it up. Data science is an umbrella term that’s comprised
of different scientific skills such as data visualization data manipulation statistical
analysis and machine learning. So guys these are the stages involved in the
life cycle of our science data acquisition data processing model building pattern evaluation
and knowledge representation. So let us go ahead and understand each of
these individually. Let’s start with the first step which is data
acquisition. So we already know with our data comes from
multiple sources and it is present in multiple formats. So our first step would be to integrate all
of this data and store it in one single location which is a data warehouse. Now from this integrated data we have to select
a particular section to implement a data science tasks. So this would be all about target data. Once the data acquisition is done it’s time
for pre processing. So the raw data which you have acquired cannot
be used directly for the data science tasks. This data needs to be processed by applying
some operation such as normalization and aggregation and after pre processing is done and it’s
time for most important step in this data science lifecycle which is model building. So here we apply different scientific algorithm
such as linear regression K means and random forest to finding interesting insights. So after we build a model on top of a data
and extract some patterns it’s time to check for the viability of these pattern that is
in the step. We check that all the information is correct
useful and new and only if the information satisfies these three conditions we consider
the information to be valid elsewhere discarded once the information is validated. It’s finally time to represent that information
with simple esthetic graphs so you guys are summing up the data lifecycle comprises of
these steps. Data Acquisition data reprocessing model building
pattern evaluation and knowledge representation. So one such application of data science application
is chatbot. So would these chat boards are automated boards
which respond to all our queries. Now I believe all if you must have heard of
Siri and Cortana So these chat bots are perfect applications of data science and these chat
bots are also used across different sectors such as hospitality sector banking retailing
publishing and another very interesting application of data science is the self-driving car. So will the self-driving car is the future
of automotive industry a car that drives by itself without any human intervention is just
mind boggling isn’t it. And all of this is possible with the help
of data science. Next a sentiment analysis for sentiment analysis
is an application of data science which helps in understanding that emotion or sentiment
behind something. So let’s say elections are going on and you’ll
want to know how would a particular party fails the election. So just by analyzing the sentiment of the
people you can understand when the performance of the party in the elections and other application
of data scientists images tagging. So I believe all of you have Facebook accounts
now whenever you have it on a person’s picture Facebook automatically tags a name to the
person. And this again is done with the help of data
science. Let’s get start with NumPy. So I believe you guys already know like what
Python is capable of how powerful it is so we can use python for all sorts of things
right from digital development web development and data science. We can do anything and everything with python
in the programming world. Next thing is Python builds up on its functional
modules. So it has all the all code constructs of programming. There are three types of programming that
we have structural. Object oriented and functional so it can if
it is capable of doing everything. The next is when we work with anything in
Python. We have a fancy thing called package in python. So those packages are available for free in
the market. It has a lot of built in functions and built
in things that will help you guys to write many many codes easily without waiting for
the detailed algorithm and all So in that way these packages are really helpful. So what will be will we do. We will be starting with this Numpy for today. Okay. So after that we will see where we know that
we will go for SyPy so these two are basic packages for data scientists. So numpy. What it does it is used for mathematical and
logical operations on that is and it provides feature for multidimensional. arrays also so again when we tell arrays Python
doesn’t have any array. It is built on a list on it. So basically when we go to numPy when we go
for indexing slicing and all those kind of stuff it will only be the list. Everything will be based on the lists. So that’s how it goes. Okay so that’s what we will start with. So NumPy will have a lot of functions which
will help you to I mean play around with the arrays of it. Okay. So that’s how it works. So now what we will do we will just cover
the basics of numpy and then we will go for the coding examples and All and thats how
we will be planning for the day for that let me open up a new console for you guys So. That it gets easier for typing of the codes. Okay. Okay so go ahead to the ppt now. So first of all we will see how to create
an Numpy Array. Okay Numpy Array once again I will repeat
it is just Python list it is nothing more than that but it has some added features along
with Python lists. It has some added features so that’s why numPy
is used again due to some extra features that we don’t get in a normal lists in Python So numpy can support 1d 2d both of the banch
of array okay. And I think you might be using this Anaconda
version of Python so but that will be coming along with Pandas having NumPy version of
restart. Numpy will be pre installed in the Python
versions. Okay. I mean Anaconda python. Now when you use a package right what we do
we import the package we import the package with something like we with the Syntax. It can be any package okay. Alias can be anything. So what is the syntax Syntax is import then
in that package name then that will ask you what it does to assign an alias. Otherwise you would need to type the entire
thing throughout the program and then we will have alias name of NP okay. So that’s what it was. Okay so now when I say NumpyArray it can convert
anything any any python data structure to arrays. So that so it works. Okay. So if a show you like this. why it is taking time now Yeah so C it has converted both these things. So the first one is Python list. Second one is a python double right. So when we pass that argument that that tuple
or list to apply a numpy array function it converts them all to a numpy array. So that is what this returns and what ever
to be provided as you see the outputs are starting and ending with square brackets. So that means it is already converted to a
list. Now we can perform various functions and we
can perform various functions in numpy. Yes so once we have numpy array created which
can be editable. Because it’s a list now it’s not. Anymore a tuple So that’s the way it is editable. And numpy doesn’t come by default with Python
if we want to use it. We need to install it. So let’s say you are not using Anaconda and
you are using this kind of Python user interface then what you need to do you need to install
it using Command prompt install. Sorry. Yeah. And again and again we’ve been strong number. So it will find it and it will install numpy. I don’t have this preversion set so thats
why it is not working but it should install it. OK. So that’s how it works. That’s all we can use numpy in the end this
kind of functions also. Now we can have 2d arrays in Python also like
2d arrays in numpy also. So how we write it we write it like this. So we just need to pass 2d arrays 2d arrays
means to let’s say we can pass two lists. So it will be. Condemning it to. 2d array. OK so it will be changing ainto 2d array. So that is how we write it in Numpy array
that is how we create arrays in Python. So that’s how we do it. So now next will be how where it is and where
it is advantageous other than using basic python List or python like that. I can list all Python right. So by number you were changing that. Yes so we are changing data type from mutable
to non mutable this is the other one. Right. Next is ND array object. OK. So in numpy as I have shown you to 2d arrays
right it can go up to n and then can have any number. So in the real world if you ask me we don’t
use more than two Max to max 3d arrays but yes it can go up to that. So like that it works. So next is and next is like why why we use
a numPy arrays so and numpy this ND arrays will have all the items of same type. Okay. So it can’t be one of them is int and one
of them is string list. It has to it all all of them has to be entries
like that. So items can be accessed using zero index
as you know Python arrays are Python lists also starts from zero indexing rate. So here also it remains the same property
it has zero index so if we go for a numPy area then if we want to see the first row
it will be like this. So it will give you the first row and this
will give you the second row right. Similarly for columns. If you want to see first. Sorry. If you want to see the first column. You need to do this right Sorry. So you need to do this so you will see the
entire values. If you need to see that only the first column
then you need to do it do it at this. Like that. It works great. So that’s how it will be working now for 2d
arrays. I will be coming. Okay. I am working on 2d arrays. So that’s how it works. OK. So we will be coming to that in a few minutes. So 2d aarrays I will show you. So for others what was the names A and B 2d
arrays it is I will be showing you. No not an issue. So for arrays if you see 1d array it will
give you a zero. That will be 1 a 1 will be 2 like that. And if you do want to go then it will be printing
on every single element because the right hand side index is always left right and that
index it is not up to it goes up to that. It is not including that right right hand
set index so it has has two elements. Now if we do this then it will print all. If we do this that also will mean the same
and it will be in the same way it is pretty basic pretty much like the list that we have
in python. Now numpy arrays are beneficial because it
picks up the same size of blocking the memory for all objects at stores. This part we will see a comparison in the
later little half of the section and then we can understand like whether it is beneficial
rather than storing it in a classical list then numpy array Now next is if you go in to check the individual. Yes right. So it will begin colon n-1 that is how the
right hand side the we will always be excluded like that. OK. Next is NumPy Array initialization right. So how do we initialize NumPy Array as we
have already seen. Right. How do we do that but still. This is how you do it. OK. So initialize means what we want to do is. We don’t want to place any list in List in
there Okay. But what we want to do we want to have some
by default values. OK default arrays we want to pick it up. But let’s see how we do it. First one is we will I mean if you guys are
familiar with the terms like masking and all that is for image processing and for data
processing we will do that a lot of things we will do that. OK. So a lot of time we will be. Lot of time we will be using the zero based
or one based indexes. OK. So for creating a zero based arrays rate what
we need to. Come on what we need to do we need to have
some some sort of like some shape of a zero arrays. OK so that’s how you do it again. That’s how you do it in NumPy So what do you
do. You write. NP.0 Then you specify the when you specify
the dimension of that. Three by four means it will have like three
rows and four columns so first one is off so you can think it like this it will be NP.0
then row comma column. That’s all what you need to pass it that that
this kind of tuple you need to pass it to the python arrays OK. So that’s how it works in Python. I mean NumPy. So that’s how you print 0 arrays in NumPy. OK. Next is if you want something with the interval. Right. So how you do. Right. Like this. NP.array within Bracket we pass. So it will print you thjat another a new arrays
or what we are doing. We are sorry.n here. What we are doing. By. Array. So in this what we are doing we are we are
right. It’s arranged So it’s a range actually. OK. So what we are doing we are passing three
variables. First one is the starting number. Second one is the ending number. And last one is that the line is the interval
that we want to print. So from 10 to 25 we are having five. Are we one one lists to we have five separated. So first one and second differentially five
like that. So that’s all we have. So we have three numbers 10 15 20 and always
remember right and will be excluded. So 25 won’t be taken up till 20 we will go
till 20 we will print it out. OK. So that so this kind of arrays are getting
printed out and in the NumPy Now this is the same thing again. Next thing is this A range is done right now
let’s say we want as we want to spread some points over a straight. OK. So how do we do it. We want to what I mean what I mean is if you
think of it 2d plane right like x and y plane if you think of and we want to spread some
points along that line. So what we will do then like we want some
points between range A and range B. OK so here we are giving intervals right. So we need to calculate the interval we need
to calculate the point difference and all then we need to provide it here. So that’s how it works. But we don’t want it. We want it other ways. We want it to spread along on Nireline like
this. So for between five and 10 we were we want
six numbers. It is almost same as NumPy. It has a big difference. So how it is different I will show you. OK. So one doubt in the arange the last of the
N number. Can we put as 19 instead of 20 to the last
exam. Yeah. Then it will print single number no no no
in the second argument. yeah yeah we can. It will go to like in only. OK thanks. Now you can put anything so the logic is when
it reaches the end number right. With interval if it goes past or if it goes
till the last number then that number will be called. I mean that number would be excluded right. So let’s say 18 plus two will be twenty eight. So 20 will be excluded. Okay. So that’s how it works. OK. So for 19 18 plus two is 20 these when you
is 19 will be excluded right. No no no no. Nothing is there to print it out. So that is why we are not in the loop so I
wouldn’t go in that. Okay. Next is this leanpace. leanspace and at any rate. So arrange what it does it takes in. Two num three numbers for start number and
number. And. So we what we do in arrange we have to use
three numbers as a parameter. We what we take we take n numbers the start
number end number and the interval and we print out the values based on the interval. So from start numbered till the number we
print out the values based on the interval. Okay. But in Lynn space what we take we take three
parameters again and what we have in that we have like we have a start number end number. And then we take in number of points in the
number of points in there. So if we give you a start number end number
then if we split it into 10 points then we will get 10 points between that start number
and end number. That is the difference between lean spaceand
arrange and all these functions. We will be using heavily when we use to go
forthe data science okay because these things we will need and they will see how do we do
that. The things we will be discussing when we discuss
about the data science concept. Okay. Now next is how do we do array with the same
number. Okay. Next is how to create an array with the same
number. So this is same as same for same uses like
that. Like for zeros iight formats for. Carving up some masks like that. Okay. So if you use this keyword. Then if you pass some values. Along. If you pass some values then it will give
you that number of the damage dimention it will take care and it will get and it will
give you that kind of an array so row and then column and then it will be picking up. So NP.pull it will take up. A.first the tuple tuple for row numbers. Column numbers and it will pick up the number
to fill that array with the. Number to fill like that. This thing works this full function works. It can be anything. Okay. It will give you array full of the kind of
numbers of any any dimension any dimension can be given to any real world number that
can be given. I’m sorry any integer number can be provided
to them by dimension so thathow this full function will work. Okay. Next is to randomize an array again for I
mean that masking only. So what we do Let’s say we want that three
by four for Matrix to be randomized. So it will give you some some here and there
numbers of random numbers. So that will be and that those will be structured
in a matrix form. Yeah but I mean you pass and that rate will
be organized. So random as this thing. Okay now we go to how do we access this NumPy
Array. Now let’s say we are creating two arrays. How do we access it. Okay. How do we see what’s wrong with the array
and what not. Let’s say I am creating upthe 2d array. Now If i do. So that’s how they shift function. So again that’s how we can access a shape
of an array. So shift function will return below. row number and column number. So a dot shaPE. it turns tuple.row and coloumn Like that. Okay so it will be returning like this now. The major next thing is what is the use of
this shape function. Okay so this is a tuple but we can change
the values of the tuples. This will change it. We can access the shape function of it. And we can change the values. Even. Now we can access like our come. Come on. We can access this. Yeah so we can access it like this okay. Come on. I have not given print. Okay so we can access individual elements
of the shape tuple that is being returned like this. Okay. Like we use it like we access normal tuples. So we can what we can do with this. A dot shape. We can go. We can get the tuple. I mean tuple for row number and column number
as an output. We can change the axis. Change the shape of the shap of the matrix
with that with the shape function and we can access individual arrays let’s say you want
to see how many rows are there. It as a trade. You can use it. You would want to loop through all the data
sets all the rows of your data sets using a for loop. You don’t want to go for a map and all thats
why when you use a dot shape and for printing a. That’s how you use okay for print a. What you do you. You will just. I’m sorry For shape zero. That means you are accessing individual elements
of Tuple right so zero will be giving you the number of rows and one will be giving
you the number of columns like that. Okay. Okay. One thing you guys are learned with. I mean you guys know about lambda functions
right. It was covered. Yes. Correct. But just to want to go back to the zero index
zero index it to return the number of row correct. Right. If you keep comma on another zero then you
click the number of column. Is it working. It’s not. No one shape is always give the column and
rows yaar that zero will give the rows and one will give the colomns that’s it So that
is tuple basically right. Can you please do that. So tuple how it works. Number of elements in Tuple we will we will
have a one D array right for one D arrays Can’t be having to two indexes. OK so it will be zero to like that. But it one day one d tuple or one day array
what do whatever you it. OK. So that’s how it works. OK. Now we can have several more examples of data. I mean this shape function but I am not going
into the detail but you need to remember one thing you need to max the number of elements
in the Tuple right we have six elements right 1 to split it 2 to 3 it won’t work because
the size of that is that total of six right. So we need to have a multiple of six only
that so we can break that so we can reshape that’s what is about this shape function OK. Next is how to get the total number of columns. OK. So again I am having 10 functions and I want
to see the size of it. So it will give you 24. As you can see there are 24 elements in the
array. OK so that’s how that so this size function
works and this is another syntax of in NP dot arrange. So here is what it takes it takes some number
of. Number of values. Number of points needed. These. Numbers. Between 0. till That numbers. OK. So that’s how the another syntax of arrange
works. OK. So for size function it will give you the
total number of elements in an array. So that is what size function works for. OK. Next is dimension of array it is more or less
same like this it is more or less the same thing like that like shape functions. So I will put it right in there and only difference
it can be modified. So where were we we were with this endim right. So how it will work endim will return you. It is not. I mean it is a bit different from shpe shape
returns you the exact shape of the array like the number of rows and number of columns. Right. But endim will return you the number of dimensions
of the array. Okay. So if you see the endim then what we have
we have two has return right. That means it has total of two dimensions. 3 and 2 2 dimensions right. So that’s what ended returns. And endim will return you. The number of dimensions of array. So that we need to. Remember. OK so that is a word to remember so endim
returns to the number of. Dimensions. Again it is not shape but it is a dimension. OK. Now D type is the array data type that we
have already. OK. Next is D type OK. D Type is to give you the type of each element
and the array. And then NumpyArray will give your type of
all the elements an NumPy Array cannot be heterogeneous. It has to be homogeneous always. So NumPy arrays will return you. I mean the the order the homogeneous arrays
so when you do a D type function on an array it will return you the number of dimensions
of that. I mean sorry the database of each of the elements
in array. So here we have 24 24 int numbers right. So that’s why we have int 32 as a return type. Yes. So that’s how it works. OK. So that is what is about this d type function
next is how do we use it for maths calculations. OK. So any any doubts till this part till this
d type. Now if I show you something more here. OK. Next as I have created. Now aray with like float numbers so you see
that arrays are D types sre printed as to 64. OK. So you have you’ve got an array of I mean
the D-type as float sixty four. So that so this d type function works. OK so. NumPy as the name suggests it used it is used
for linear algebra. So numpy is used for no. mathematics or linear algebra. So you won’t be really having string arrays
in Numpy. OK so you won’t be having it. That is not provision to a Numpy. It’s only useful linear algebraic operations
and for that we need in. Integers and a floats Right. nothing more than that. OK. Next is a numPy maths. We can do summation division multiplication
and all those kind of here and there stuff with this numPy. Again how do we do it. OK. Let’s get started with a single array. So this is how numPy submission function works
and it can add up to different things. Okay then some will return you some of the
elements or it can be you sum up two arrays. OK some can do anything. Anyone. So sorry. So some can detain you either some off all
elements in a Python array or it can return you the some of elements of two mattresses. So matrix multiplication matrix addition all
this logic will be implemented in there. It won’t say why it is not working. Sorry I haven’t put it in a list OK so now
what it will do it will take up to list it will add up all the elements and it will return
you the out. OK so 5 10 2 3 that means 10 15 and 2 3 5
so twenty eight and subtract it will take to arrays and it will subtract the results
and it will throw it up for you. So that’s so this abstract subtract and numPy
dot sum function is used for summing up and the finding difference between two mattresses
and NP.sum has a few flares in it can do a few things so we will discuss that. So let’s say we have seen how it takes in
two lists and eight. It sums you up that result and show it to
you. Now if you specify an excess parameter then
it will do the sum based on the rows or based on the columns. OK. We’ve been told A and B for you. Yeah. So see a and b are 5 10 2 3 8. If we do some of some with exit 0 that means
it will do your column wise some. So that means 5 2 7 10 3 13. Okay. And if you will for row wise sum then it will
be X as equals 1 so it will return you fifteen and five right so that so this will. work this will work row wise some that. That’s how it will work. So that’s what is the. So that so this functions work. that’s how this numPy arrays. Arrays some function well. So that’s how you can get the.


  1. Guys, what else do you want to learn from Intellipaat? Comment down below and let us know so we can create more such tutorials for you.

  2. 👋 Guys everyday we upload in depth tutorial on your requested topic/technology so kindly SUBSCRIBE to our channel👉( ) & also share with your connections on social media to help them grow in their career.🙂

  3. Hi I am a Collage student and I know c++ and little bit about python means I can build small projects on python.
    But I want to learn Data science so please tell me should I start this course or I focus on python first.

  4. 🔥🔥🔥Following topics are covered in this video:
    01:45 – Who is a Data Scientist?

    03:03 – Where do Data Scientists come from?

    05:35 – What does a Data Scientist do?

    08:55 – Prerequisites to become a Data Scientist

    13:12 – Data Scientist Roles and Responsibilities

    19:20 – Data Scientist salary

    21:05 – Who's Hiring Data Scientists?

    22:52 – Need of Data Science

    23:19 – Where is Data Science Needed?

    24:14 – What is Data Science?

    25:15 – Understanding Different Techniques

    28:09 – Life Cycle of Data Science

    31:24 – Numpy

    33:21 – How to create Numpy Array?

    36:50 – Ndarray Object

    40:00 – Numpy Array Initialization

    46:31 – Randomize an Array

    47:00 – Numpy Array Inspection

    53:33 – Numpy Array Mathematics

    01:09:24 – Numpy Breadcasting

    01:09:40 – Indexing and Slicing in Python

    01:15:25 – Array Manipulation in Python

    01:30:15 – Splitting of Arrays

    01:36:31 – Advantages of Numpy over List

    01:45:46 – Python Tutorial for beginners

    01:46:44 – Introduction to Pandas

    01:49:56 – introduction to Pandas

    01:56:20 – Pandas vs Numpy

    01:58:27 – How to Import pandas in Python?

    01:45:46 – Python Tutorial for beginners

    01:46:44 – Introduction to Pandas

    01:49:56 – introduction to Pandas

    01:56:20 – Pandas vs Numpy

    01:58:27 – How to Import pandas in Python?

    02:00:00 – Data Structures in Pandas

    02:00:29 – What is Series object?

    02:03:00 – How to change the index name?

    02:05:16 – What is a Data Frame?

    02:07:28 – How to create a Data Frame?

    02:125:53 – Merge, join and concatenate data frames in Pandas

    02:32:34 – Analysis functions

    02:37:10 – Cleaning function

    02:45:32 – Manipulation

    02:50:10 – Sorting the Data

    02:51:00 – Filtering

    02:51:55 – Data Visualization

    02:56:00 – Quiz

    02:58:35 – What is Data Visualization

    03:04:01 – Anscome's Quartet

    03:13:34 – Data Visualization libraries

    03:15:36 – What is Matplotlib?

    03:19:24 – What are the types of Plots?

    04:39:56 – Introduction to Machine learning

    05:03:40 – Linear Regression

    06:23:43 – Logistic Regression

    06:44:30 – Spam Email Classifier

    07:28:06 – Logistic Regression Example of a person having the heart disease or not

    07:56:00 – What is Classification?

    07:56:47 – Decision tree

    08:34:00 – Understanding Confusion Matrix
    08:45:10 – Naive Bayes classifier
    9:03:17 – What is Clustering?
    09:34:27: Data Science project 1

    10:33:49 – Interview Questions

    11:30:27 – Data science project 2

    12:11:31 – Quiz

    12:11:51 – Data Science Interview Questions

  5. Can you guys make a separate video for numpy stacking as at 1:28:58 the whole concept is getting mixed up. I think the teacher was not very familar with that topic also plz use some other IDE(Which has a black background) or big font as what you guys are typing is also not getting visible clearly at 720p also.

  6. Good teaching
    I have a question about data science how I can contact to you
    I need assurance about job
    I am ready to hard working

  7. I am from commerce background do I would be able to do data science and if yes how much time it would take to learn data science

  8. Respected sir, I am pursuing MBA finance. I want to learn Python for finance and marketing domain. Can you help me out in that?

  9. I don't know phython.. Nd i m manual tester.. Want to switch data science… How to start… Nd how much time it will take….what skill needs for data science

  10. I have 10 years of experience in Testing (Selenium+Python and Java), How difficult will it be to switch career in Data Science (with no experience) and getting the same pay I am getting; presently?

  11. Hi sir can i please know how real time object detection and recognition can be done and how to train the existing pretrained models pls…

  12. can i know the order of becoming of data scientist
    1. data science
    2. machine learning
    3. deep learning
    4. nlp
    5. statistics
    am i correct? if not? correct me..!
    thank u

  13. Sir, I want to learn basic learn of computer. Like DIPLOMA IN COMPUTER APPLICATION, ADVANCE DIPLOMA IN COMPUTER APPLICATION. any course you have on youtube

  14. I am from mechanical background…is it possible for me to go for it?… how much time it will take in general to understand?

  15. Yes I am civil engineering I want to shift career in data science but I was poor in computer programming subject in my academic …will it be good option to shift & how.muvh time will it take to learn data science .

  16. Sir how to get a job as a fresher there is no job for fresher everybody wants 3-4 years of experience even startup also 🙏🙏

  17. Which video is best to learn data science from ur channel ?? Whether this video or another video of 11:14 : 00. Hrs .. Can u suggest ??

  18. In the linear regression topic, we got R**2=0.36, and then you mentioned that we should rotate the line until we get R**2 value close to 1. Is there any calculation to obtain the slope to which we should rotate upto.. or else it's just a trail and error method ?

  19. I am working on MNC as Oracle Database Administrator with more than 2years experience..Is this useful to me in anyways

Leave a Reply

Your email address will not be published. Required fields are marked *