Car Evaluation In ASP.NET Core Using ML.NET

Habibul Rehman
5y
15.6k
0
13

300

Article

CarEvaluation.zip

Problem

This problem is centred around making the Car evaluation and predicting the Car condition.

To solve this problem, we will build an ML model that takes as inputs,

buying: vhigh, high, med, low.
maint: vhigh, high, med, low.
doors: 2, 3, 4, 5more.
persons: 2, 4, more.
lug_boot: small, med, big.
safety: low, med, high.

and predicts the evaluation of the Car.

Prerequisites

Visual Studio 2019 or 2017
ML.NET Model Builder Extension for Visual Studio

Solution

To solve this problem, first, we will build an ML model. Then we will train the model on existing data, evaluate how good it is, and lastly, we'll consume the model to predict Car evaluation.

Car Evaluation In ASP.NET Core Using ML.NET

So let's start,

Download and Install ML.NET Model Builder tool from Visual Studio Marketplace. Click Here
After ML.NET Model Builder installation open your Visual Studio (in my case I'm using VS2019)

After Project has been selected, enter your Project Name.

Select Asp.Net Core template which you want to use, I'm using Web Application MVC.

After the project has been created, we will start to build our model. Right-click on Project > Add > Machine Learning,

After the project has been created, we will start to build our model. Right-click on Project > Add > Machine Learning,

After scenario selection, we will select the data set that will be used to train our model. You may add data from the file as well as using SQL Server Database. I will use car.csv data to train my model. Originally I've downloaded this dataset from UCI Machine Learning Repo Car Evaluation Dataset. You can download it from here. Select class column for prediction label and select input columns, after that click on Train link,

After data source selection, enter the time for which you want to train the model and click on Start training button, and the model training will be started for the entered time.

After the model has been successfully trained click on the evaluation button.
In evaluating tab you can see the output details of model builder showing the best algorithm and other performance measures of the ML model.
We can also predict the Car evaluation in ML.NET Model builder. Add your data and click on the Predict button to see the predicted evaluation from the trained ML model.

You can see the new build machine learning model evaluation. Click on code button to consume the model into your project.

As you can see in solution explorer, the ML.NET Machine Learning model has been created. In code tab window you can see the code snippet that can be used to consume the ML model into ASP.NET MVC project.

Now, the machine learning model for Car evaluation has been built. Now, first, we need to add the reference Car EvaluationML.Model project into our Car Evaluation Web project. Right-click on Car Evaluation Web project and select add > reference.
Select Car EvaluationML.Model project and click ok.

Now we need to create a new controller named "CarEvaluation" and paste the below snippet code.

We will use the static Predict method of ConsumeModel class which will use the CarEvaluation machine learning model and return the predicted output.

using Microsoft.AspNetCore.Mvc;
using Microsoft.Extensions.Logging;
using Car_EvaluationML.Model;
namespace Car_Evaluation.Controllers
{
public class CarEvaluationController : Controller
{
private readonly ILogger<CarEvaluationController> _logger;
public CarEvaluationController(ILogger<CarEvaluationController> logger)
{
_logger = logger;
}
public ActionResult Index()
{
return View();
}
[HttpPost]
public ActionResult Index(ModelInput input)
{
ModelOutput prediction=ConsumeModel.Predict(input);
ViewBag.Prediction = prediction;
return View();
}
}
}

Add a new view named Index in CarEvaluation Folder and copy the snippet code.

@model Car_EvaluationML.Model.ModelInput
@{
ViewData["Title"] = "Evaluate";
}
<h4>Evaluate</h4>
<hr />
<div class="row">
<div class="col-md-4">
<form asp-action="Index">
<div asp-validation-summary="ModelOnly" class="text-danger"></div>
<div class="form-group">
<label asp-for="Buying" class="control-label"></label>
<select asp-for="Buying" class="form-control">
<option value="vhigh">VHigh</option>
<option value="high">High</option>
<option value="med">Medium</option>
<option value="low">Low</option>
</select>
<span asp-validation-for="Buying" class="text-danger"></span>
</div>
<div class="form-group">
<label asp-for="Maint" class="control-label"></label>
<select asp-for="Maint" class="form-control">
<option value="vhigh">VHigh</option>
<option value="high">High</option>
<option value="med">Medium</option>
<option value="low">Low</option>
</select>
<span asp-validation-for="Maint" class="text-danger"></span>
</div>
<div class="form-group">
<label asp-for="Doors" class="control-label"></label>
<select asp-for="Doors" class="form-control">
<option value="2">Two</option>
<option value="3">Three</option>
<option value="4">Four</option>
<option value="5more">Five or More</option>
</select>
<span asp-validation-for="Doors" class="text-danger"></span>
</div>
<div class="form-group">
<label asp-for="Persons" class="control-label"></label>
<select asp-for="Persons" class="form-control">
<option value="2">Two</option>
<option value="4">Four</option>
<option value="more">More</option>
</select>
<span asp-validation-for="Persons" class="text-danger"></span>
</div>
<div class="form-group">
<label asp-for="Bug_boot" class="control-label"></label>
<select asp-for="Bug_boot" class="form-control">
<option value="small">Small</option>
<option value="med">Medium</option>
<option value="big">Big</option>
</select>
<span asp-validation-for="Bug_boot" class="text-danger"></span>
</div>
<div class="form-group">
<label asp-for="Safety" class="control-label"></label>
<select asp-for="Safety" class="form-control">
<option value="low">Low</option>
<option value="med">Medium</option>
<option value="high">High</option>
</select>
<span asp-validation-for="Safety" class="text-danger"></span>
</div>
<div class="form-group">
<input type="submit" value="Evaluate" class="btn btn-primary" />
</div>
</form>
</div>
<div class="offset-2 col-md-4">
<div class="form-group">
@if (ViewBag.Prediction != null)
{
<label>Class:</label>
<h6>@ViewBag.Prediction.Prediction</h6>
<label>Score:</label>
<h6>
@foreach (var item in ViewBag.Prediction.Score as float[])
{
<span>@item ,</span>
}
</h6>
}
</div>
</div>
</div>
@section Scripts {
@{await Html.RenderPartialAsync("_ValidationScriptsPartial");}
}

Let's explore what's inside ConsumeModel.Predict method.
First, it's creating MLContext and then creating and loading prediction engine from MLModel.zip file.

Then using prediction engine to predict Car Evaluation on given input data.

public static ModelOutput Predict(ModelInput input)
{
// Create new MLContext
MLContext mlContext = new MLContext();
// Load model & create prediction engine
string modelPath = AppDomain.CurrentDomain.BaseDirectory + "MLModel.zip";
ITransformer mlModel = mlContext.Model.Load(modelPath, out var modelInputSchema);
var predEngine = mlContext.Model.CreatePredictionEngine<ModelInput, ModelOutput>(mlModel);
// Use model to make prediction on input data
ModelOutput result = predEngine.Predict(input);
return result;
}