Welcome back to my second class for Microsoft Azure Machine Learning Studio. So, in this in the previous class, we know we talked about this administration's this was the administration, we will go through this one of this, you know, one by one and each each topics actually. So project here, you can project importable. If you do some experiments, you can put it into project, let's create one project. You know, I'm not user one, but we'll just normally this term. They use this when I'm not using this actually to be honest.

But you can create this project and you can add assets on this like data sets you want to add no experience experiments. There is no experiment, we need to add an experiment Oh, this is good thing actually. So once you perform experiments, we'll go with this project back again later. Because once you add this experiment, this will be there in the experiment and you can add to your project. So that shows that we have access to, to your colleagues, our you know, users who have this access. Okay, modules, if you have any modules, notebooks and train models, transforms.

Oh, yeah, I had district motto, my transformation. So, at this point of time, we have nothing so I'll just close this one. And this this was about project Okay, so we we just named this project a Udemy. And the content is empty. Okay, that's fine. You can create probably one more project and things you can create.

From here, you can create one more and go here and you can see this option here new and you can create another project. So, Brandon, why this useful, right of the reason of having this prior to good in one place, right? Since we did create experiments, and we'll go through it, actually, we'll go to it and actually go on. I wanted to give you also a little bit information since ETL. So I'm not even To be honest, I'm a media tester. But But I know the workflows in Informatica.

So it's, it's similar to that. If you know that one day, this will be Bs, okay. But you don't have to know it. I'll explain you. So we know so so that's the, this is the similar view, similar vision that you can perform a lot of transformations, not of atomic math, arithmetic calculations, like subsection multiplication, wrong, email flow and all those things. We can do a lot of things Using code we don't realize any code.

But using a flowchart we'll be using flowcharts and we'll run that flowchart and see how they perform. So we'll go to that action. So let's go to next experiments here you can create an experiment to go ahead and you know you can create only go to this experiment tutorial actually, for your understand for you to understand. And with select few of these and see this two of them we'll see here. There's a lot of examples actually, noodle networks you can do this for the neural networks, but for us you know, we can open the studio and see that how this thing works. But for now, we'll just stick to tutorial we will have this tutorial in the next class probably, because in this class, I will be explaining you so various models, you won't Understand this model various models, right?

So the static jumping into experience experiments and just creating it. Cool. I mean, for some people, it's okay for some people, they knew me and they do remark. So I don't want remarks I want to be as detailed as possible. So that you know, understanding what you have some samples This is let's see this. This is similar sample not similar, I don't think so, this is different from this this sample actually, right.

Get this, this is a data set to be honest, to be honest, the seniors some Blitz anomaly detection, we have a sample and you can add it you can add it to your experiments if you want to see and manipulate it and you get have to for your own reason. You can manipulate this but we were before going to this sample to the hoping that we'll first we need to try to understand what we're trying to do right here, right? First trying to difficulty the sample, we have to create our own thing, right? Then you what you can do is based on that sample, you can create your own method, our own algorithm. How do you do that you can annotate and make sure how you want the data to be shown how the graph should look like all those things. You can see that okay.

I'll be looking at looking into documentation. We are going to the documentation domain because not that I know, but I might make some mistakes. So probably I'll be looking into this documentation a little bit. But thing is the claim is the second predictive model actually, it's working but probably because of the internet internet is low or probably extinct too much. So we are not going to that the second tutorial actually, we'll be using some sample and we work. So any experiments are what you have done will show up here.

So we'll go to this right now it's empty. So don't worry about it, we'll fill it up with probably 123 or we can go to four we have more time, but you know, we'll just keep it short and sweet. So, um, so let's go to the web services. So here's the thing. Once you are created your experiment you can deploy to Azure web services. So we will also go through this right now it is empty because we have not done it.

You actually can go here and click on the zoom goddess experiment tutorial actually, to make your lesson. Not that you cannot do it, but we will see step by step procedure so that we can create our own in the next process. Right, so, and the notebooks that go to the notebook section, you can create your own notebook. So this notebooks is actually for coding normally at this time, like I'm not really into we are going to schooling at this point of time. So this notebook is for you know, if you have this Python if you're working on Python, use this notebook to code it and run the code. Okay.

Our codebook Fremont notebook for that so that you have is our code, use it our code and run it properly. And then you have to do is want to not use this property you can use this how do we get to this one so, but we go through this No, probably the I think we have more bang We will do this But I guess they need this cooling. We know unfortunately, we don't have the same query. So, you know, this is this is what the log book is all about. So this you can use for Python, Python three, Python two, this is query, if you know the scoring, you can use this right? See this logo?

Yes, that means it uses that language to implement the code. But right now, we are not working on this one. So ignite 2030. All right, that let's go to the data sets, data sets. Here. Okay, good.

Here, you can create your own data set. Right. So let's say when data set will be probably most probably will be in CSV file, data. CSV file Let's find out. I have this one data set Actually, let me show you which I will not be using that data in the homework try to do better in the homework. Go ahead and here it says healthcare dot data.

This you can use it and upload it. Okay? And once you see here, you know, sets this option is it dot CSV or you know dot php dot php the objects are protected scry dot zip file, don't use zip. That will be more complex. No zip file contain it should at least contain dot CSV file. So our object or workspace dot our data.

So this is basically data. So if you have data you can use it or use it from sample. Oh, you have this amount of samples here. Should we try this? Well, I think we will, we'll be using this and not this. But will we be actually using this data set?

From the from the sample, but not from here, not from here, but we'll be using the different user. Okay, so that's about the data set. And this so everything's empty right now at this point of time, everything is empty. Right. So, you know, here train module, you can have the string Mario, once you have trained a model. We'll see how we train it.

Okay. And based on that, you save it. So once you save it, this will get added here and you can add to that project. So this is a disabled because there's nothing here. So this is pretty much about description about these modules. In this so that's pretty much about this one, we will go in the next class we have this in an auction that probably might not take too much time, but when we create the first our first AR not algorithm actually will create an experiment tutorial.

And then the next class will be creating in our own algorithm for predicting data. A tree will train using linear regression method. There is lot of methods actually not showing up here. Either explain that in detail, but we would probably I show up in the next but this is pretty much this is all empty at this point of time, because we have not done yet anything at this point of time. We have just created a project that saw but all We will be moving on with this, click on this. And we will create a sub project that we create from we start an experiment from the next class.

So that's pretty much about this modules. This is just a Mario 60 animation. What are the various modules? What's the use of this? I wanted to explain actually the functions and mathematical operations what you can use, but we will, you know, we don't just let you jump be great. So should be shot.

For now. It's I think the finance should be good. And, you know, we'll start right here. And we will go into one sample tutorial. It is an automated tutorial to show you how to move in date and how to do that. Okay, so that's pretty much you know, as soon the next class I hope you like this video and thanks for watching.