Skip to main content
Loading Explore guides…
Data Visualization with Python · Acedra
Home
Explore
Computer Science
Data Visualization with Python
Sign in to save
Chat
If YouTube asks you to sign in, open the video on YouTube.
Watch on YouTube
Reload player
Transcript
83 segments
Copy
Hide video
0:10
hey guys welcome to the session by intellipaat so just a quick info the session would also be simultaneously broadcasted on YouTube as well so in this session we're going to learn how to do data visualization with Python so let's how quick glance at the agenda we'll start by understanding the importance of data visualization and then we'll see how to do data visualization with the matplotlib package so simply put data visualization
0:38
is the art of representing the raw data in the form of beautiful and ascetic graphs now let's say you're working on a huge dataset which comprise of around thousand columns and 1 million rows now finding insights from this data is extremely hard so this is where we can take the help of data visualization to find interesting patterns from the data so we have this data set over you and this data set is represented in the form of images now we see that these images
1:09
help us to easily identify the features of these animals so we have got mammoths over here and with the help of this image we can see that the size of mammoths is
1:33
right so sorry for that interruption so as I was saying we've got these images over here and these images easily help us to identify the features of these animals so this is mammoth and the citizens of first record and this is saber-tooth cat which represents the second record and with the help of this image we can see that the size of mammoth us
2:15
yeah sorry so there seems to be some technical issue with the screen so now I hope that the screen is visible to everyone all right so let me actually start from the beginning so as I was saying data visualization is basically the art of representing raw data in the form of beautiful and ascetic graphs now let's take this example while you're walking on a huge data set which comprise off around thousand columns and 1 million rows
2:41
now to find insights from this extremely huge data it's very very difficult so this is where we can take the help of data visualization to find extremely meaningful insights from the data so here we've got this data set and we have represented this data set in the form of these images so this is the image of mammoth which represents the first record and this is the image of Sabretooth cat which represents the second record and we can easily find
3:08
insights of these two animals from this image so we see that the size of mammoth is 13,000 lbs and its aggressiveness is very low and the speed of mammoth is around 25 kilometers per hour and then we have got saber-toothed cat so we see that from this image the speed of saber-toothed cat is 75 kilometres per hour its aggressiveness is very high and its size is 400 lbs all right so now again let's take this example so we've got this Anscombe squatted so this data
3:37
set basically comprised of four files in total and these four files have these values of x and y now if you look closely at this data set you'd see that these values are very similar to each other now let's actually go ahead and find the sum average and standard deviation for x and y for all of these four files now again if we look at this result we see that the values of x and y are same throughout all of these four files so if you just have a glance at
4:07
some average and standard deviation then we might think that the X and y values for all of these four files are very similar but let's actually go ahead and plot these four files so when we actually make a pictorial representation of this data set we see that the relationship between x and y is very different fur these four files and we were able to understand this with the help of data visualization so now that we know the importance of data
4:35
visualization let's actually look at the different visualization libraries with Python provides so python has got mad rot lip GG plot plot leads your plot lab and see bond and in this session we want to do a visualization with the my plot lip package so let's go to Jupiter notebook and stary I'll also import the numpy package so I'll type an import numpy ass NP right right so I'll just copy these two values over here and paste them over you let me also copy
5:08
these two lines over here right so now what I'll do is I will actually add some colors to this line plot so I've got the value for X I've got the value for y now what I'll do is I will change the color of this so I will use the attribute Co lor and I'll given the color let's say red do this and after this what I'll do is I'll assign a title to the plot so for that I'd have to use PLT dot title and the title which I will be giving this is line plot and I can also give
5:49
labels to the x-axis as well as the y-axis so to give labels to the x-axis I'd have to type in PLT dot X label and I will give in the x-axis label as x-axis similarly I when you given the label for the y-axis so this would be PLT dot Y label and the label which I am giving to the y-axis is y-axis as simple as that right so we've customized a line plot so we started off by creating a simple line plot where the color of the line was blue after that we made a line
6:25
plot and this time we've customized the line plot so the color of the line is red and we've also assigned the labels for the title for the x-axis and also for the by axis now we'll see how to do a bit of subploting notice we'll see how to add two plots in the same figure right so for this what I'll do is I will actually have two Y values so let me copy this and let me pass it over here so the x-axis values would be the same and I'll
6:53
have y one over here so Y minus two cross X plus five then I'll also have Y 2 so y two would become three cross X plus 10 and with the help of these values I will create two plots so to have two subplots in the same faker I would have to use PLT dot subplot method and this basically takes in three parameters so the first parameter is the number of images in the rows and number of images in the columns so since I want two images this would basically mean one
7:26
comma two so I'll have one row and two columns and I'll put in one over here so this one Basically means that I am activating the for a subplot now let me go ahead and plot the so plt dot plot and the values would be X comma y1 now let me go ahead and also at the second subplot so time will be plt DOT subplot and I'll given those two parameters so 1 comma 2 so one row two columns and this time I'll activate the second subplot so I'll
8:01
add in two over you now let me copy this piece it over here and I will plot the second graph so this time it is X comma y2 and I'll finally show that figure so PLT dot show now let me click on run alright so now we have created two plots or two subplots in the same figure and if you look at these values these values are different right so the x-axis values are same but y1 and y2 are difference over here y 1 ranges from 525 and y2 would range from around seven point five
8:35
to forty right so this was line plot now let's go ahead and see how to create a bar plot so let me just type in bar plot over here now to update this bar plot let us first clear the dataset so I'll go ahead and create a dictionary first and Ill name that dictionary as fruit so to create a dictionary we'd have to given these curly braces so we have a key value pair in a dictionary now let me assign the first key value pair so let's
9:04
see my first fruit is Apple and there are 30 apples the second fruit is mango and there are 45 mangos after that I've got banana and I've got around 10 bananas now I will add so now what I'll do is I'll extract the individual keys and individual values and store them in separate objects so over here I will create a new object and in that object has names and I'll extract only the keys from this dictionary so I'd have to type fruit dot keys and I'll store the keys
9:48
and names similarly I'll extract the values so I'll store the values and quantity so I'll have to type in fruit dot values all right so extracted the keys I've extracted the values now I'd also have to store this in the form of a list so let me just type in list and let me cut this and let me piece this inside a list similarly I'll do the same thing over here I'll type in list let me cut this from over here and let me piece this
10:25
inside the list all right so we have created the dictionary now let me just print out names and quantity over here names quantity right so we've got the individual names of the fruits and the quantity of the fruits over here now we'll go ahead and create this bar plot so to create the bar plot we'll have to type in PLT dot bar and this basically takes in two parameters so the first parameter would be the names of the fruits or the categorical variable which
11:00
contains the names and then we'll have the values so values I in quantity now after this I'll just show the so plt dot show all right so we have successfully created this bar plot where we have the names of the fruits on the x-axis and the quality of the fruits on the by axis so again this plot easily helps us to understand that the major quantity of the fruits belongs to mangoes and the minimal quantity of the fruits it belongs to bananas now let's
11:32
actually go ahead and also customize this bar plot so I'll just type in customizing bar plot I'll copy this same thing over here now let me add a title x-axis label and y-axis label so plt dot title and I'll assign the title to be lets say distribution of fruits and then i'll get the x axis labels so plt dot X label and the x axis label would be fruits of that I'll given the y-axis label so it'll be plt dot y label and this label would be
12:21
quantity right now let me print this out right so we've added the title we've added the x axis labels to added the y axis label and let me use the argument color and I let's say given the or an H bar right so let me actually change this first plt dot bar so we've got this let's start off by creating the word data for the scatterplot so what I'll do is I'll have my first data and I and some values over here so 10 20 30 40 50 60 70 so there is a relationship
13:05
between X and a and they're all that the number of points are same let me at the x-axis label again so it'll be the same plt dot X label and I'll just be X now let me add the Y label so plt dot y label so this would be a and b now let me print this out right so we've got the title they've got the x-axis label and we've got the y-axis label now what we'll do is we'll change the size of these points right so let's see how can we do that so to
13:39
change the size of these points we've got a parameter which is s so this stands for the size now let me set this to be 200 and let's see what happens right so we see that the size of these points where the relationship between X and a has changed right so this has changed to 200 now let's also change the size of these points so I'll set this to be let's say s equals 500 Over here so we've change the size of both of these points over here and it can also
14:12
change the shape of these points right so I'll change the shape of this so over here to change the shape we have this argument called as marker and let me give in the value three so if I given the value 3 I have this over here now instead of three let me put it to be one and let's see what do we get all right so here this is tilted downwards now let me given the value two and let's see what do we get right so this time it is tilted upwards right so we can have
14:44
different markers or different shapes for these points over here right and we can also change the size of this figure over here to change the size of the figure so about the plot method we would have to use in PLT dot figure let me just type in PL d dot figure and the stakes in a parameter whose name is fixed size and I'll give it a tuple so let me assign a value of 10 comma 10 over here all right so over here I've increased the size of this figure all right now after this let me go ahead and
15:23
start with the next geometry so our next geometry would be your histogram so let me give in the common histogram over here now let me again create a list so I'll give n different values for the list over here so the numbers range from 0 to 9 so I'll just given one to my 1 come out 1 and then let me just go ahead and keep on giving some random values between 0 & 9 7 5 4 3 I'll again give a 1 so I'm just making sure that there is a greater frequency of ones over here right so this is all
16:07
of the data which would be going into the histogram and to create a histogram I'd have to use plt dot hist method and I will pass in the data inside this now to show the image I have type in PLD dot show let me run this alright so we have success we created this histogram so this basically gives us the distribution of this data and with the help of this we can easily see that there is a greater frequency of once in this data and after that we've got three we've got
16:39
five right so after one the frequency is high for three and then there is frequency for five right and there is not even a single seven or not even a single sorry there is not even a single eight over here right so that is what this gap tells you right so this is how you can interpret different insights from a histogram now again we'll see how can we create a histogram on top of a data set so what I'll do is I'll go ahead and import the iris dataset first
17:10
so for this I would require the pandas library so I'll type in import pandas as pd now let me go ahead and load the iris dataset so I'll type in PD dot read CSV
17:29
and let me give in the name of the file which would be IRS dot CSV and I'll show this in a new object and I'll name that object to be iris now let me have a glance at the head of the data set I said that is I'll have a glance of the first few records of the data set so iris dot head and this is our dataset over here now I would have a sorry I want to make a histogram for this sepal length column from this iris dataset so all I have to do is I'll type in PLT dot hist
18:02
and I'll given the data so the data would be coming from this iris dataset so I will type in iris I will give in pieces over here and let me select the column for which I'd want to make a histogram so I'd want to make a histogram for the sepal length column so I'll just type in sepal length now let me run this let me also just put in plt dot show right so we have successfully created a histogram for this sepal length column from this iris dataset so
18:34
this basically tells us that when it comes to sepal length of the flower so there is a greater frequency for the sepal length to be around six point five or 5.5 or you can see that the sepal length would vary mostly between five and six point five and there are very very few flowers who sepal length would be greater than six point five right and those flowers who sepal length is eight those are almost non-existent all right now let's actually also go
19:05
ahead and change the color of the histogram so I'll type in color over here and I'll assign the color to be red all right so we have successfully changed the color now we can also change the number of pins over here to you know increase the distribution so I'll set the number of bends to be equal to thirty right so we can also vary the number of pins now let me change the number of pins to be hundred and let's see what we get so I'll type in hundred
19:32
over here right so this gives us a grade distribution in the histogram right now let me actually keep this to be fifty because fifty seems to be the perfect distribution for us right now yep so this is basically how we can create histograms in Python or with matplotlib now going ahead we'll see how can we create a box plot so I'll just type in box plot over you now let's go ahead and create data for this box plot so I'll create three lists so I'll type
20:08
in one two three four five six seven eight and nine so this is our first list after that I'll go ahead and create the second list so when this the values would range between 1 and 5 so 1 2 3 4 5 4 3 2 1 7 let me just count 5 6 7 8 9 right let me create another list over here and this would have values between 6 & 9 so let me type in 6 7 8 9 and there will be 8 7 6 5 so I've got 1 2 3 4 5 6 7 8 9 values over here right so I've got my data ready now I will create
20:55
a list of lists over here so data equals list and I'll just pass in 1 2 & 3 inside us now I'll use PLT dot boxplot I'll use this method and I'll just pass in data inside this again to show the box plot I will put in PLT dot show right so we have successfully created our box lured over here so this basically states that there is a greater distribution for this data 1 right so the values of this data it basically ranges from 1 to 9 and the
21:36
median value is 5 so this line which you see at the center of the box this basically denotes the median value and the median value for this data is fine then we have this box plot and this tells us that the data it ranges from 1 and Costel five and the median value yes three and then we have this so over here though data points it starts at four and it goes to nine and the median value for this is seven correct now similar to box
22:04
plot we also have a violin plot so the only difference between oh a box plot into a violin plot is that the sheep is different so box court looks like a box and the violin plot looks like a violin so that's pretty much the only difference when it comes to the box stored in the violin plot so I'll copy this and I will paste it over here now the only change is I'd have to make over here as instead of PLT dot box plot I'd have to put in PL d dot violin plot
22:34
alright so this is what we have over you alright so this is the same thing it's just that these three figures they are in the form of a violin instead of a box and we can also add a grid to our data so to add a grid I'd have to use PL d dot grid and then set the value to be equal to true so this is how we can add a grade to a plot now again let's also add title to this so I'll just put in PL d dot title and let me put in the title to be distribution of data let me put in
23:16
the X label so PL T dot X label and let me just put in this as x axis and let me also give in the why label over here so PL d dot Y label and this would be y axis alright so we have successfully added the title the x-axis label and the y-axis label now similar to box plot we can also add the median to this while in plot so to do that we have this argument called us show median and I would have to set this to be true over here right so we have added these lines for the
23:56
median values so not just medians we can also show the mean value over here so we'll show the mean you we have this argument show means and again I'll set this to be equal to true all right so we have added the meanwhile line as well as the median line now if you look at this while and plaudits very interesting observation so you see that the value of mean and median is same for this distribution over here right so the
24:25
mean value is Phi as well as the median value is fight for this data right so we are done with while in plot as well now let's go ahead then create a pie chart so let me just type in pie chart over here alright now let me go ahead and create some data for this pie chart so again what I'll do is I'll create a list with the name fruits and I'll add some fruits over here so let's see I'll add Apple after that I'll add mango and then I like oranges a lot so I'll also type
24:59
in orange and well I've not eaten creeps for a long time so I'll also add creeps in my shopping basket right so we've got the first list now we'll also add the quantity for this so I'll type in quantity and let me give in the values for this so let's say I would want 30 apples and since I like mangoes a lot I had want 45 mangoes I don't like oranges so I'll put in at the b12 and well someone told me that grapes would make my health better so I would want
25:36
around 100 grapes right so I assign the values for this now all I have to do is create a pie chart so for this I'll type in PL d dot pie and let me give them the values so this force takes in the values so I'll type in quantity over here and then I'll give in the labels the labels are stored in root right now I'll just type in PL d dot show over here and let me create this pie chart right now isn't this a beautiful pie chart over here right so this pie chart easily tells us
26:11
that the major quantity of the fruits as grapes and the least quantity of the fruits as orange you can also add percentage over here salut add percentage we've got this argument Auto PCD and over here I'll just type in percent zero point one F F F % percent now let me run this so we have successfully added percentage to this pie chart so we see that from the entire basket fifty three point five percent of the fruits are grapes and the
26:44
least is six point four percent right so the least amount of fruits available in this basket are oranges now we can also add a shadow to this pie chart so to add a shadow I have this argument known as shadow and I just have to set it to be equal to true all right and so let's say if I want to highlight one of these slices right we can also do that so to highlight a slice I have this argument called as explode now let's say I want to highlight the slice of creeps because
27:21
this is the largest piece so I'll Luis I will type in zero comma zero comma zero and then I'll give in 0.1 over here and let's see what do we get right so you see that this portion over here is separated from this entire pie now the zero zero zero basically means that all of these three slices would be intact together and when I given 0.1 this means that this explodes from the original pie now let's see if I just put it to be one instead of zero point one right so this
27:53
increases the distance between this alright so now let's see if I also want to separate this over here which basically represents mango so I will put in zero point one over here and I can also separate that right so I've also separated mango from this original bike right now similar plot which is you know a plot with similar pie chart is known as a donut plot so everything is seen between a donut plot and a pie chart it says that the donut plot looks like
28:27
and the pie chart looks like a pipe right so what I'll do is I'll copy all of this and I'll pass it over here now let me remove all of this over here I'll remove the shadow right so what your world was I'll create do plots so this is my first plot and I will store this in PI 1 now I will go ahead and create my second plot I'll name this second pie chart to be equal to PI 2 and over here I'll just give in quantity so let's say the
29:06
quantity is equal to Phi over here and I will give in the color over here right so let me also give in the color now the color has to be equal to white all right so now let me just click on run and let's see what do we get over here right so we have this let me remove this over you we've got PI one they've got PI 2 now what we have to do was we just have a white circle and we've got this over here now we'd have to given the value
29:45
for the radius so I'll set the radius for the original pie chart to be equal to 2 and I'll set in the radius further second pie chart to be equal to 1 right so now we've got a donut plot and it looks like this right so if you have a glance at this and this it's pretty much the same the only difference is this looks like a pie and this looks like a doughnut now all we did is we created two pie charts over here the first pie chart is the original one
30:13
the second pie chart it's just a white circle over here right so this is a white circle with a sign the color to be equal to W and the radius of this inner pie chart should be lesser than the radius of the outer pie chart so for the outer pie chart I've assigned the radius to be equal to 2 and for the inner pie chart I've assigned the radius to be equal to 1 all right now yep so this is how we can create a donut plot and then finally we have
30:44
something known as an area plot so let's go ahead and also create an area plot over here so um let me create some values let me just type an area plot and create a bunch of values over here so let's say x-axis it goes from 10 to 90 so I'll type in 10 20 30 40 50 60 70 80 and 90 after that I'll give in values for the by axis so this would be let's say 1 comma 1 comma 2 comma 5 comma 6 comma 4 comma 7 let's see how many values again
31:29
1 2 3 4 5 6 7 and then I'll I can give it a 4 and I'll give it a 6 or a 3 4 5 6 7 8 9 alright now let me go ahead then create this area plot so I'll just type in PL d dot stack plot so to create an area plot we've got this method known as stag plot and I'll given the values for x and y after that I'll just type in PLT dot show alright so we have successfully created this area plot over here and this looks something like this so this area plotters are very similar to
32:05
histogram right so the area plot and the histogram both of them show the distribution of your numerical data so if we look at this we basically understand that you know there is a creator distribution or there is a greater frequency of the higher order numbers right if we look at this as well so we can get to know that right there are two sixes there are there is 1/7 and there are two fours over here right so this is what this tells us right there
32:34
is a greater distribution of the numbers after 5 right so this is basically how we can create an area plot right so yes guys so this brings us to the end of this session and when this will comprehensively understable a lot of geometries so we started off with the line plot and then we learned how to customize the line plot after that we work with the bar plot now you guys have to understand the difference between a bar plot in a histogram so a bar plot is
33:09
used for categorical values and a histogram is used for numerical values so this is the basic difference between a bar plot and a scatter plot so after that we also learned how to create a horizontal bar plot so the only difference between a vertical bar plot and the horizontal bar plot the same things would be so over here you will type in PLD dot bar and over here you will type in PLD dot bar edge and then you will create a scatter plot so we can
33:36
clear the scatter plot by using this command PL d dot scatter and then B so how can we change the size and the you know markers style for these gala plots of that we created a histogram and then we also created a histogram on top of a dataset and then we went ahead and created some box plots and while in plots and then we finally understood about pie charts and area plots right so guys were attending the webinar if you have any questions you know you can ask
34:08
me right now right so people who have questions so let me actually unmute you guys oh hi can you listen to me yes it's just I'm sorry I'll be back in one second
34:38
yeah hey um so I believe this is Shubham bra No uh yeah may I know your name yeah um so I'm hanging over here - so this was a very nice session so it was quite informative so now I wanted to know something that whatever the donut plot that you were creating over there right you correct correct what if I want to add another circle in that one up inside the donut plot how would I do it okay um so as you see over here to create a donut plot I've just created two pie charts so to add another
35:15
circle inside this I'd have to add another pie chart so what I'll do is I'll add another pie chart I'll name this to be pi/3 and I'd have to do the same thing so I'll type in PLT dot pie over here I'll given the size of this which will be five again and then I'll give it a different color so I'll use the colors argument and let me give this a blue color over here now the important thing to note over here is the radius of the inner circle needs to be lesser than
35:43
this radius over here so this time I would set the radius to be equal to 0.5 all right so this is our outer circle whose radius is 2 and then we have this inner circle whose radius is 1 of that we have we are creating this new circle inside this whose radius is 0.5 now let me click on run right so we have another circle inside this donut plot seems correct okay and one more if you don't mind so yeah today I have the line plot on top of the area plot um yes you can
36:18
do that and it's a very simple step over here so all you have to do is below this you'd have to type in PLT dot plot because this is how you create a line plot and then you give them the same values over here so X comma Y now I click on run now you can also change the color to this line so let's say I'll type in color over here and I will give you no green color to this right so this is how you can add a line plot on top of this area blood so does
36:50
that help you yeah sounds convenient correct and about the pie chart how do I change the colors in it all right so you're talking about this pie chart over here right okay so for this what you'd have to do is you'd have to use the colors parameter as we've been using for you know other geometry as well and since we've got all four slices over here what I'll do is I will go for four different colors so let's say the first color which I given as black the second
37:24
color which I given us gray and then I give in jello and then let me just give in green over here yep yep all right so this has changed all right so all you have to do is you'd have to check the number of slices you have so if you have ten slices you have to create a list which comprised of ten elements if you got five slash you'd have to create a list which comprised of five elements all right so yeah that's right guys then so if no one else has any mood outs what
38:08
I'll do was um yeah so this brings us to the end of the session now you know just for an info over here so in telepath actually has this Python for data science training course you know where you can learn all the major concepts of Python and data science thoroughly so in deliberate has done a lot of research so in telepods has consulted of industry experts who've you know worked as data scientist in top companies and in consultation with them they've come for
38:41
this Python for data science course which will you know given 360-degree proficiency in data science all right so let me actually go through this course content over here so you'll start off by understanding the basic concepts of data science you'll understand what exactly is the need of the assigned so why did data science come and then you look at various applications of data science you'll understand how its data science is used in different sectors so let's say you're
39:05
working in a telecom sector or you're working in healthcare sector you'll understand how is data science used in all of these different sectors after that you'll understand the basics of Python so you'll understand about the different data types how to install Python and then you will work with looping and control statements and then we've just worked with the numpy package over here right so you will comprehensively learn about the number
39:29
package and how to do mathematical computing with numpy and then there is something else I buy which is built on top of numpy so over here you'll see how to do scientific calculations with Syfy and then you've got the machine learning concepts over here right so this is where you learn how to do data wrangling and data visualization so you're you know or you'll see how to manipulate the data with the help of the pandas library you'll learn how to extract the data you
39:57
will learn how to cleanse the data you'll learn how to find the outliers and all of that stuff right and then
40:08
alright so and then we've got the soap there are signs with Matloff lip so over here you know you just what we've done over here you'll comprehensively learn how to create different plots right so this was just a demo here but you know you saw a simple example for each of these different plots so in this course you will comprehensively learn about different plots right you'll learn about different aspects of box plot different aspects of the own applauded and
40:35
different aspects of area plot and once you could with this stuff you will competence we learn about machine learning so we'll start off with supervised learning you'll understand about classification and regression and different classification algorithms so you've got algorithm such as decision tree random forest naive Bayes and SVM shall comprehensively learn about this right so these are all the things which you can learn with this course right so
41:00
if you are interested in learning about data signs and how to implement all of these data science concepts with Python then you and Shore check out the description which would be posting the link water right so also you can check this over here now the intel pad also provides CTL assigns architect course so let me just open that up and let me show you what is so what is so amazing about this course over here alright so the best feature
41:33
about this data science architect goes by in telepath is that this is you know of this course has been created in consultation with IBM in association with IBM so you would actually be getting a certificate from IBM when you complete this course now that is very good isn't it right so this course basically comprised of 12 modules in total where there are six instructor-led modules and six self-paced modules so along with this you will also have
42:04
multiple assignments you will have multiple projects so that you know you have more hands-on expertise so in this course you will basically start up by understanding the top three analytical tools use in the industry so you'll start up by Souder physically resides with our course we will learn how to do our programming and how to do how to implement your science concepts with our and then you will start with the Python for a science course but you will
42:29
comprehensively learn about Python programming and also how to do statistical analysis with Python and then you'll learn data science with SAS where you learn SAS programming and you know how to do regression analysis and classification analysis of its ass now once you're good with these analytical tools you will get on with big data so you will see how to process big data in real time with Apache spark and Scala and to be your complete data scientist
42:58
you would also need to have good grasp on the deep learning concepts so this entire science architect goes also provides the ein deep learning module where you will comprehensively learn about deep learning and how to implement different neural networks such as convolutional neural network recurrent neural network and so on and you'll be implementing all of these different neural networks with Karass tensorflow and also dia flown right and
43:25
now once you're done with processing the data and analyzing the data you as a data scientist should also be able to represent this data in the form of you know beautiful visualizations that is why we also have this tableau desktop 10 right so with the you know when you learn tableau desktop then you'll learn how to create stunning dashboards and you provide these insights to the decision-makers you know and with the help of those insights they can come up
43:51
with valuable business ideas and what is this you also have this self-paced courses self-paced modules where you learn about statistics and probability advanced Excel MongoDB MS equal machine learning and Hadoop developer right now one more thing about this data science architect courses you will have an N to n capstone project so the specialty of this n to n capstone project does well you know you would need all of the skills which you would have learnt from
44:22
these different 12 modules so using the skills which you've learned from these 12 modules you would have to solve this capstone project now you will get the certificate by IBM once you complete this capstone project so that is truly amazing isn't it alright so guys if you are interested to enroll in the zero science architect course and if you want this certificate by IBM you know so you can check out the description and you can also check out this link over here
44:51
right so do feel free to reach us out where you know we're always there to help you out right so yes guys so if there are any more doubts with respect to what we've covered today or with respect to the courses which are provided by Intel apart I'll just go ahead and end this session right so right guys I'm Ann in session for today thank you and happy learning
Here to help you learn
Sign in to keep a private conversation with your course tutor.
Ask me anything about the material…
Sign in to chat