Home
Contribute Contact Us Browse all meetings
Home Contribute Contact Us Browse all meetings
.Net Foundation / ML.NET / 23 Sep 2019
.Net Foundation / ML.NET / 23 Sep 2019
Previous Meeting Next Meeting
⏯
Add meeting Rate page Subscribe
youtube image
►
From YouTube: ML.NET Introduction | ML.NET [2 of 8]

Description

Learn all about what ML.NET is and what you can do with the Framework. You will also see how customers using it, the open source momentum, and a short demo of the experience.

Follow Pranav Rastogi: https://twitter.com/rustd

Watch the entire series here: https://aka.ms/dotnet3-mlnet
Download Visual Studio 2019 here: https://aka.ms/VisualStudio-dotnetconf19
Download .NET Core 3.0 here: https://aka.ms/Dotnet3

Learn more about ML .NET:
What is Machine Learning with .NET? https://dotnet.microsoft.com/apps/machinelearning-ai/ml-dotnet?&WT.mc_id=Educationalmlnet-c9-niner
Get started with ML.NET: https://dotnet.microsoft.com/learn/ml-dotnet/get-started-tutorial/intro?&WT.mc_id=Educationalmlnet-c9-niner
ML.NET Model Builder: https://dotnet.microsoft.com/apps/machinelearning-ai/ml-dotnet/model-builder?&WT.mc_id=Educationalmlnet-c9-niner
GitHub Repo ML .NET: https://github.com/dotnet/machinelearning
GitHub Repo ML.NET Samples: https://github.com/dotnet/machinelearning-samples/blob/master/README.md

Follow us:
 Twitter: https://twitter.com/dotnet
Facebook: https://www.facebook.com/Dotnet/
Blogs: https://devblogs.microsoft.com/dotnet/?WT.mc_id=Educationalmlnet-c9-niner
Shows and Podcasts: https://channel9.msdn.com/Shows/On-NET/?&WT.mc_id=Educationalmlnet-c9-niner

Useful Links:
Learn .NET: https://dotnet.microsoft.com/learn?&WT.mc_id=Educationalmlnet-c9-niner
.NET Community: https://dotnet.microsoft.com/platform/community?&WT.mc_id=Educationalmlnet-c9-niner
.NET Documentation: https://docs.microsoft.com/en-us/dotnet/?&WT.mc_id=Educationalmlnet-c9-niner

A

In this video, we will take a quick look at ml.net.

A

Ml.Net is an open source and.

A

Cross-Platform machine learning framework.

A

it has the following key highlights..

A

It is built for dr. developers.

A

So, as a dr. developer,, you can use your existing c-sharp and f-sharp skills.

A

And use ml.net in any.net application.

A

It allows custom machine learning models.

A

To be made easily with tools such as modelbuilder,.

A

Cli, and it uses automated machine learning as.

A

A way to increase the performance of the models that users get.

A

The framework and the ecosystem is very extensible.

A

So you can bring in other popular libraries such as.

A

Tensorflow and other popular model formats, such as onnx.

A

So you can build machine learning models for the variety of different scenarios.

A

Lastly, the framework is trusted,.

A

Privacy, and proven at scale.

A

that means that the framework runs locally within your app..

A

So all the trading happens within your app., then the framework has been used heavily for the last 10 plus years,, both internally at microsoft and now externally, by customers.

A

So it's hard-earned quite a lot..

A

Let's take a quick look at the ml.net.

A

Website and helloworld tutorial for ml.net.

A

This is how you can learn more about ml.net.

A

It's custom machine learning, framework, for.net, developers.

A

Here,, this piece of code is showing you how you can use your c-sharp libraries to build custom machine learning, model.

A

You can do the following scenarios with ml.net.

A

So you can build models for sentiment, analysis, product recommendation, price, prediction,, image, classification, sales, forecasting, and a lot more..

A

You can check out these samples that we have on github to.

A

Learn more about this other scenarios possible with ml.net.

A

Ml.Net also uses automated machine learning under.

A

The covers with tools like the modelbuilder and the cli,.

A

Which allows you to build custom machine learning models without any configuration required..

A

So as a developer,, you don't have to know the intrinsics of all machine learning models and settings,.

A

And you can quickly build custom models using these tools.

A

You can easily bring in the ecosystem for.

A

More other scenarios, such as image, classification, object, detection,, natural language, processing, or building models on sound and audio-based data,.

A

By using tensorflow and other popular libraries from the ecosystem., ml.net performs really well.

A

It has got high performance and accuracy..

A

This was a result of performance paper which.

A

Shows how ml.net pipelines compared to scikit-learn and h2o.

A

You can read more using this link about the performance characteristics..

A

So here are some of the customers using ml.net today.

A

So, let's take a quick overview of.

A

Getting started with the machine learning.net in your.net application., so what I have over here is a blazer application,.

A

And you can think about this application as an e-commerce site where.

A

Customers can go and leave you reviews.

A

In this case, I can come over here as a customer, and I can say,.

A

Ml is hard, but as an e-commerce site, owner,.

A

It's very hard for me to understand what was the sentiment of this customer.?

A

Was this customer happy or was this customer sad?

A

now, as a web developer,? I would like to use machine learning to build.

A

A custom model for doing sentiment analysis, so I can better understand this customer behavior..

A

So let's go back to visual studio and build this custom machine learning model..

A

I can right-click on my project and I have a new options. Saying, right add machine-learning.

A

This option is available if you download the model builder tool for visual studio.

A

If I launch this extension,, I'm presented with an option of choosing a scenario.

A

now, as a developer,, I'm more likely to understand what scenarios are.

A

Possible with machine learning, rather than the actual machine learning tasks..

A

So in this case,, since I want to build a model for sentiment, analysis,, I'm going to choose that template..

A

The next step in the machine learning journey.

A

Is around connecting to your data.

A

since most of the developers have the data in sql,.

A

I can choose to either upload a flat file, which is a csp or tsp,.

A

Or I can directly connect to sql server where my application specific data is.

A

Let's go ahead and quickly connect to sql server.

A

in this case,, I'm going to connect to a sql server instance, which is locally running on my box.

A

I'm going to use windows authentication, and I'm going to load up my table of customer reviews, which has all the reviews of the customer comments.

A

I'm going to select the table. Column, table review,.

A

And I can get a quick overview of what my data looks. Like.

A

So I have three columns and the appropriate sentiment and.

A

The actual sentiment text, which was the common text that the user entered.

A

in this case,, I want to predict the sentiment of the particular text.

A

So I would choose sentiment from this drop-down,, which is the output of the machine learning model,, which is what column are you predicting.?

A

The next step in this process is around training. The machine learning model.

A

in this case, modelbuilder uses.

A

Automated machine learning, which explores different models with various settings, and it's going to come back with the best model it found so far.

A

The longer I train for,, the better model I'll get. in this case, modelbuilder, chooses some defaults based.

A

On how large my dataset was.

A

So in this case, it looks like the training completed and I can.

A

Evaluate this training process.

A

To see what was the accuracy of the models.

A

in this case,, I got sdca logistic regression with an 81 percent accuracy,.

A

And this tool is telling me that it tried two other different models in this time-frame..

A

The last step in this process is code..

A

Since I'm running my web application,, I can easily add code for how.

A

The model was trained and code to consume this model in my application..

A

So when I hit "add projects", it added these two projects to my solution..

A

One is a project for how the model was trained and it actually has the training code..

A

The other one is around how the model can be consumed in my blazer app..

A

So I'm going to right-click and add a reference through this generated class library.

A

Then I'm going to go back to my blazer app,.

A

And I'm going to consume this model in my application.

A

So here the code, I'm uncommenting is the code to consume the model,.

A

And the predict function is the function. I could call to predict the sentiment of a text.

A

I'll go back to my razor view, and I will include a view which is going to give me a happiness scale and it's going to give me emojis for a happy face or a sad face.

A

Lastly, I'm going to call into this predict function which are going to pass in the common text and it's going to give me a sentiment back..

A

So, let's start this application again and see what was the impact of building a custom machine learning, model.

A

So if I could now go to review screen,, you will see that the emoji cons that appeared because of the changes to the view, and if I say ml, is hard,.

A

Now I can see what's the sentiment of my customer is.

A

If I change it to ml is fun with ml.net,.

A

You can see it's about a 99 percent accuracy., so just to summarize very quickly,.

A

I started with an app which had no machine learning and I quickly launched modelbuilder using right-click, add machine learning,, which allowed me to build a custom model for doing sentiment. Analysis,.

A

Which I was easily able to include in my application,.

A

And then I'm better able to understand customer's sentiments on my e-commerce website.

A

So this was a quick overview of how to get started with the ml.net.

A

What ml.net also provides,?

A

It's got a very strong momentum in the open source, community.

A

This is the url for our github location.

A

We have 250k plus downloads, 1,800 commits,.

A

1,500 prs, a 100 plus people contributing on the open source, repo.

A

The framework is used both internally for the last five plus years at different products at microsoft,.

A

And it's been also been used externally, quite heavily.

A

Here are few case: studies from customers using ml.net in production.

A

brenmor uses ml.net to classify free-form comments from patient surveys.

A

So they get lot of surveys and they want to classify those surveys into different categories in their departments.

A

So they've built a custom machine learning model for it.

A

Evolution software is using ml.net to predict hazelnut moisture levels..

A

So the challenge that they have over here is hazelnut drying is a very complicated process,.

A

And it takes a lot of manual labor to figure out what's the right, humidity level for the hazelnuts to dry., so they built a custom machine model which takes different inputs and then predicts the moisture content.

A

They end up building a website and a cloud tablet app as well to figure out the hazelnut drying levels.

A

in this video,. We took a quick overview introduction to machine learning.net.

A

In the next video,, we'll be looking at how to get started with ml.net.