.Net Foundation ML.NET, 23 Sep 2019

Previous Meeting Next Meeting

⏯

youtube image

►

From YouTube: Build a ML model for predicting taxi fares | ML.NET [6 of 8]

Description

There are tons of different ways to use the model builder with ML.NET. In this video, we learn how to predict taxi fares based on distance traveled, trip time etc. using a regression 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:
Predict prices with ML.NET: https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/predict-prices-with-model-builder?&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

Custom machine learning model for predicting taxi fares.

A

What is price prediction?.

A

Price prediction is about predicting of.

A

Taxi fare or a fare amount based on some input. Data.

A

For example,, how long was the taxi ride?.

A

How many customers or riders were in the taxi?.

A

So here's an example of a dataset from.

A

The new york taxi fare, which captures the historical data of all the rides that happened.

A

In this case,, let us understand how would price prediction work.

A

Price prediction is an example of a regression machine learning task which can be used to predict a number.

A

for example,, predicting taxi fare,, predicting house pprices, or anything else.

A

The prediction for taxi fare works as follows.

A

You have some features which go into the training process.

A

So for example,, these features can determine.

A

How high or low was the fair amount,.

A

And, for example, if the distance traveled was very high,, then most likely,, the fare is going to be big as well.

A

Then the fare amount is your label.

A

Or output, column or the column that you want to predict.

A

So this is the outcome of calling a machine learning model.

A

Now that we have understood the basics of predicting taxi fares,,.

A

Let's look at how can we build a custom machine learning model for this scenario.

A

This is a console app that I have.

A

And I'm going to use this to build a price prediction. Model.

A

I've already downloaded the modelbuilder visual studio, tool,.

A

So I can right-click my app and say "add machine learning".

A

This will launch modelbuilder..

A

I can choose from a variety of templates., so in this case, since I am predicting taxi fares,.

A

I'm going to choose the price prediction: template which predicts.

A

A numerical value from my historical dataset.

A

So I'm going to choose that template, and the second step in the machine learning process is around connecting to your data and loading it.

A

I can choose to load by file or sql server.

A

in this case ,, since I've downloaded the new york taxi dataset, which is a csv file,.

A

I can choose file and I can navigate to that. Dataset.

A

Once the data gets loaded,, I indicate a preview of what the data looks. Like., it's showing me the 10 rows.

A

Of all these rows and about seven columns,, and I can then choose the column that I want to predict.

A

Or the label column- and this case is the fair amount,.

A

And the fair amount becomes, my label column.

A

I can use these features and the data to.

A

Train a model by simply saying start: training.

A

The longer I train the model for,, the better model, I'll get., underneath the covers, modelbuilder uses automated machine learning,, which explores various models with different settings and gives me the best moral..

A

So I don't have to worry about finetuning the model for my specific case..

A

So in this case, once the is training completed,, I got quality or accuracy of 94 percent,.

A

And the best algorithm was lightgbm regression.

A

I can go to the evaluate screen and I can understand more in terms of what happened in the system.

A

For example,, while the best model was like lightgbm regression,,.

A

The tool also explored other models and it's showing me a summary of the top five models explored along with the accuracy and other characteristics that I can use.

A

So I can use this information to further evaluate or to gain.

A

Trust in the system that it's not a black box, where I got my result,, but there were other results as well..

A

If I'm happy with the evaluation criteria,.

A

I can then go to the code step, which is the last step of your machine learning workflow,, which is around consuming the model..

A

I can click "add projects", which is going to add two projects to my solution.

A

one project, which has the code for how the model was trained in modelbuilder.cs and a class library which has the actual model that was trained, and I can include it in my application.

A

So let's go ahead and add a reference to the class library project, so I can consume it in my app.

A

So I'm going to say "add reference" to the class library and say "okay" and I can.

A

Use this code in my program.cs to consume the model in my app.

A

I'm going to add a few using.

A

Statements for the class library I included,.

A

And then what this code does over here,, it creates an ml context, and then it loads the model,.

A

It creates the prediction engine which I can use to predict a value, and I can give some values around. What was my trip? Distance?.

A

Equals 100.: what was my trip time in seconds?.

A

Which is around 1,000, so I can play around with all these values and then call the predict function to predict the fair amount, and I can write it to the console as well.

A

So I can do result.score, which is going to be the prediction value for the fair amount.

A

So I'm going to run this application., it looks like I'm missing a semicolon here,.

A

So that's why it's getting errors., so I'm going to relaunch it, and what's happening is the machine learning model is loading the model,.

A

And it's going to give me a score which is.

A

What was the fair amount for my process?.

A

So what we saw in this video was how to.

A

Build a machine learning model for predicting taxi fares.

A

In the next video, we will look at how to build a model for recommending movies.