.Net Foundation ML.NET, 23 Sep 2019

Previous Meeting Next Meeting

⏯

youtube image

►

From YouTube: Build a ML model for Sentiment Analysis | ML.NET [4 of 8]

Description

In this video, we will cover how to build a ML model for sentiment analysis of customer reviews using a binary classification algorithm.

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:
Binary Classification in ML.NET: https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/sentiment-analysis?&WT.mc_id=Educationalmlnet-c9-niner
What is Model Builder and how does it work? https://docs.microsoft.com/en-us/dotnet/machine-learning/automate-training-with-model-builder?&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
Get started with ML.NET: https://dotnet.microsoft.com/learn/ml-dotnet/get-started-tutorial/intro?&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 look at how to build a machine learning model for doing sentiment. Analysis.

A

So what is sentiment analysis.

A

Sentiment analysis allows us to.

A

Understand the sentiment based on a text,.

A

Which is comments, a user could have added or either on an e-commerce site, or through a form submission, or through various other channels..

A

So in this case, here is a sample data-set on what is the comment and a particular sentiment.

A

So in this case,, a common, which is rude as a toxic sentiment,.

A

And toxic sentiment of zero is not toxic.

A

All the features which go into training a model,.

A

In this case, comment, is input or your features and then.

A

The output column or the column you want to predict is the sentiment column.

A

This data-set is based on the wikipedia data-set.

A

Another way to look at sentiment analysis is.

A

Around what question do you want to ask.

A

Is this a or b?

A

that means is it a positive or a negative sentiment.

A

Is it a toxic common?, yes or no.

A

So sentiment analysis is an example of a binary classification task.

A

Or type of problem that users want to solve, where they want to classify sentiments into positive or negative value.

A

A typical machine learning, workflow.

A

Has three key tenants across preparing your data,.

A

Building and training your model, and then consuming your model in your application.

A

It comprises of the following steps.

A

Now that we've understood what is sentiment, analysis,.

A

Let's see how you can build a sentiment, analysis, model.

A

This is an application that I have.

A

it's a console application., let's start by seeing how can we build our sentiment? Analysis model.

A

I've installed modelbuilder,, which is a visual tool to build custom, machine learning, models.

A

I'm going to launch it by doing add machine learning on my application.

A

In this case,, since I'm doing sentiment, analysis,.

A

I'm going to choose the sentiment, analysis, template.

A

The next step in this process is around loading.

A

My data-set and choosing the column I want to predict.

A

I can either choose from file or sql server.

A

in this case,, I'm going to choose file,, which is a csv file or a tsv file.

A

So I'm going to upload the wikipedia.csv file.

A

In this case,, I'm going to see a quick preview of the first 10 rows of my data-set.

A

So again, I can get an idea as to what.

A

Makes sentiment text positive or negative.

A

That means toxic or not toxic., I'm going to choose the column that I want to predict,.

A

Which is going to be my label output., so in this case, I'm going to choose sentiment.

A

The next step in the machine learning processes around training, the machine, learning model.

A

So I'm going to start by training it for 10 seconds.

A

Underneath the covers, modelbuilder uses automated machine learning,, which figures out or evaluates different machine learning, algorithms, with different settings.

A

So, as a developer,, I don't have to worry about the intrinsics of knowing all the machine, learning algorithms and functioning the performance.

A

once the model has been trained for 10 seconds,.

A

It's going to finalize the model and the training processes, then complete..

A

I can then go to the evaluate screen and I can evaluate the performance of this model.

A

So while the tool shows me what was the best model,.

A

It also shows me what were the other models are explored.

A

In this case,, since I only ran it for 10 seconds,, there was only one model that was explored..

A

This was the accuracy of the model, and these are some other ways. I can evaluate the model as well.

A

The last step in this processes around consuming the model,.

A

So I can hit the "add projects" button,.

A

Which is going to add two projects to my solution.

A

It's going to add a project, which is a console app,, which has good in modelbuilder.cs on how the model was trained.

A

So I can retrain the model later.

A

then,. It has a class library as well,, which has the moral, lord, zip file,, which is the actual machine learning model that was trained on my data-set..

A

So let's go ahead and quickly consume this model in my console app..

A

So I'm going to add a reference to the class library,.

A

Which is going to bring in the model inputs and the actual model, as well.

A

We'll go back to the modelbuilder screen and I'm going.

A

To use this code to consume the model in my app.

A

I'm going to paste this code,.

A

I'm going to add references to the class library that I just added a reference. To,.

A

And let's understand this code on how to consume the model.

A

As we have seen, I'll create a ml contexts,.

A

Which I'll use to load the model that I just.

A

Trained and I'm going to create a prediction: engine.

A

You can think about it as a function that you can call where you can pass in your input data, and you can get the predicted sentiment of that input. Data.

A

So in this case, I'm going to write some comment that I want to predict the sentiment for.

A

So I'm just going to say, sentiment text equals that is roots.

A

Then,, I can run this app and I.

A

Can see the output of the calling the predict function.

A

So I can say console.writeline and then result.prediction.

A

The result of true means it's toxic and zero means. It's not toxic..

A

So let's go ahead and run this application.

A

It's going to launch a console app,, which is going to load the model and it's going to try the predict function,, and so this is toxic. Comment.

A

So this was a very easy way for me to add.

A

Sentiment analysis or build a custom model for doing sentiment. Analysis in my application.

A

So, now that we saw how to build custom machine learning model for doing sentiment, analysis.

A

In the next video,, we will look at how to build a custom machine learning model for classifying issues on github.