ML.NET Archives - icodebroker

[C#/ML.NET] k-평균 클러스터링(k-means clustering) 사용하기

■ k-평균 클러스터링(k-means clustering)을 사용하는 방법을 보여준다. ▶ SourceModel.cs


using Microsoft.ML.Data;

namespace TestProject
{
    /// <summary>
    /// 소스 모델
    /// </summary>
    public class SourceModel
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Property
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region 알코올 - Alcohol

        /// <summary>
        /// 알코올
        /// </summary>
        [LoadColumn(0)]
        public float Alcohol { get; set; }

        #endregion
        #region 사과산 - MalicAcid

        /// <summary>
        /// 사과산
        /// </summary>
        [LoadColumn(1)]
        public float MalicAcid { get; set; }

        #endregion
        #region 애쉬 - Ash

        /// <summary>
        /// 애쉬
        /// </summary>
        [LoadColumn(2)]
        public float Ash { get; set; }

        #endregion
        #region 애쉬 알카니티 - AshAlcanity

        /// <summary>
        /// 애쉬 알카니티
        /// </summary>
        [LoadColumn(3)]
        public float AshAlcanity { get; set; }

        #endregion
        #region 마그네슘 - Magnesium

        /// <summary>
        /// 마그네슘
        /// </summary>
        [LoadColumn(4)]
        public float Magnesium { get; set; }

        #endregion
        #region 전체 페놀 - TotalPhenols

        /// <summary>
        /// 전체 페놀
        /// </summary>
        [LoadColumn(5)]
        public float TotalPhenols { get; set; }

        #endregion
        #region 플라보노이드 - Flavanoids

        /// <summary>
        /// 플라보노이드
        /// </summary>
        [LoadColumn(6)]
        public float Flavanoids { get; set; }

        #endregion
        #region 비 플라보노이드 페놀 - NonflavanoidPhenols

        /// <summary>
        /// 비 플라보노이드 페놀
        /// </summary>
        [LoadColumn(7)]
        public float NonflavanoidPhenols { get; set; }

        #endregion
        #region 프로안토시아닌 - Proanthocyanins

        /// <summary>
        /// 프로안토시아닌
        /// </summary>
        [LoadColumn(8)]
        public float Proanthocyanins { get; set; }

        #endregion
        #region 색상 강도 - ColorIntensity

        /// <summary>
        /// 색상 강도
        /// </summary>
        [LoadColumn(9)]
        public float ColorIntensity { get; set; }

        #endregion
        #region 색조 - Hue

        /// <summary>
        /// 색조
        /// </summary>
        [LoadColumn(10)]
        public float Hue { get; set; }

        #endregion
        #region OD280 - OD280

        /// <summary>
        /// OD280
        /// </summary>
        [LoadColumn(11)]
        public float OD280 { get; set; }

        #endregion
        #region 프롤린 - Proline

        /// <summary>
        /// 프롤린
        /// </summary>
        [LoadColumn(12)]
        public float Proline { get; set; }

        #endregion
    }
}

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

using Microsoft.ML.Data;

namespace TestProject

{

/// <summary>

/// 소스 모델

/// </summary>

public class SourceModel

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Property

////////////////////////////////////////////////////////////////////////////////////////// Public

#region 알코올 - Alcohol

/// <summary>

/// 알코올

/// </summary>

[LoadColumn(0)]

public float Alcohol { get; set; }

#endregion

#region 사과산 - MalicAcid

/// <summary>

/// 사과산

/// </summary>

[LoadColumn(1)]

public float MalicAcid { get; set; }

#endregion

#region 애쉬 - Ash

/// <summary>

/// 애쉬

/// </summary>

[LoadColumn(2)]

public float Ash { get; set; }

#endregion

#region 애쉬 알카니티 - AshAlcanity

/// <summary>

/// 애쉬 알카니티

/// </summary>

[LoadColumn(3)]

public float AshAlcanity { get; set; }

#endregion

#region 마그네슘 - Magnesium

/// <summary>

/// 마그네슘

/// </summary>

[LoadColumn(4)]

public float Magnesium { get; set; }

#endregion

#region 전체 페놀 - TotalPhenols

/// <summary>

/// 전체 페놀

/// </summary>

[LoadColumn(5)]

public float TotalPhenols { get; set; }

#endregion

#region 플라보노이드 - Flavanoids

/// <summary>

/// 플라보노이드

/// </summary>

[LoadColumn(6)]

public float Flavanoids { get; set; }

#endregion

#region 비 플라보노이드 페놀 - NonflavanoidPhenols

/// <summary>

/// 비 플라보노이드 페놀

/// </summary>

[LoadColumn(7)]

public float NonflavanoidPhenols { get; set; }

#endregion

#region 프로안토시아닌 - Proanthocyanins

/// <summary>

/// 프로안토시아닌

/// </summary>

[LoadColumn(8)]

public float Proanthocyanins { get; set; }

#endregion

#region 색상 강도 - ColorIntensity

/// <summary>

/// 색상 강도

/// </summary>

[LoadColumn(9)]

public float ColorIntensity { get; set; }

#endregion

#region 색조 - Hue

/// <summary>

/// 색조

/// </summary>

[LoadColumn(10)]

public float Hue { get; set; }

#endregion

#region OD280 - OD280

/// <summary>

/// OD280

/// </summary>

[LoadColumn(11)]

public float OD280 { get; set; }

#endregion

#region 프롤린 - Proline

/// <summary>

/// 프롤린

/// </summary>

[LoadColumn(12)]

public float Proline { get; set; }

#endregion

}

▶ TargetModel.cs


using Microsoft.ML.Data;

namespace TestProject
{
    /// <summary>
    /// 타겟 모델
    /// </summary>
    public class TargetModel
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Property
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region PredictedClusterID

        /// <summary>
        /// 예측 클러스터 ID
        /// </summary>
        [ColumnName("PredictedLabel")]
        public uint PredictedClusterID;

        #endregion
        #region DistanceArray

        /// <summary>
        /// 거리 배열
        /// </summary>
        [ColumnName("Score")]
        public float[] DistanceArray;

        #endregion
    }
}

using Microsoft.ML.Data;

namespace TestProject

{

/// <summary>

/// 타겟 모델

/// </summary>

public class TargetModel

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Property

////////////////////////////////////////////////////////////////////////////////////////// Public

#region PredictedClusterID

/// <summary>

/// 예측 클러스터 ID

/// </summary>

[ColumnName("PredictedLabel")]

public uint PredictedClusterID;

#endregion

#region DistanceArray

/// <summary>

/// 거리 배열

/// </summary>

[ColumnName("Score")]

public float[] DistanceArray;

#endregion

}

▶ Program.cs


using System;
using System.Linq;

using Microsoft.ML;
using Microsoft.ML.Data;

namespace TestProject
{
    /// <summary>
    /// 프로그램
    /// </summary>
    class Program
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Method
        ////////////////////////////////////////////////////////////////////////////////////////// Static
        //////////////////////////////////////////////////////////////////////////////// Private

        #region 프로그램 시작하기 - Main()

        /// <summary>
        /// 프로그램 시작하기
        /// </summary>
        private static void Main()
        {
            string dataFilePath = "wine-clustering.csv";

            MLContext mlContext = new MLContext();

            IDataView sourceDataView = mlContext.Data.LoadFromTextFile<SourceModel>(dataFilePath, hasHeader : true, separatorChar : ',');

            string[] columnNameArray = sourceDataView.Schema.Select(column => column.Name).ToArray();

            var data = mlContext.Data.TrainTestSplit(sourceDataView, testFraction : 0.2);

            var pipeline = mlContext.Transforms.Concatenate("Feature", columnNameArray).Append(mlContext.Clustering.Trainers.KMeans("Feature", numberOfClusters : 3));

            var model = pipeline.Fit(data.TrainSet);

            IDataView testDataView = model.Transform(data.TestSet);

            ClusteringMetrics metrics = mlContext.Clustering.Evaluate(testDataView, scoreColumnName : "Score", featureColumnName : "Feature");

            PredictionEngine<SourceModel, TargetModel> predictionEngine = mlContext.Model.CreatePredictionEngine<SourceModel, TargetModel>(model);

            TargetModel target = predictionEngine.Predict
            (
                new SourceModel()
                {
                    Alcohol             = 11,
                    Ash                 = 2.33f,
                    AshAlcanity         = 3.21f,
                    ColorIntensity      = 2.9f,
                    Flavanoids          = 1.54f,
                    Hue                 = 1.55f,
                    Magnesium           = 120,
                    MalicAcid           = 1.44f,
                    NonflavanoidPhenols = 0.3f,
                    OD280               = 2.93f,
                    Proanthocyanins     = 1.72f,
                    TotalPhenols        = 3.86f,
                    Proline             = 1300
                }
            );

            Console.WriteLine($"예측 클러스터 ID : {target.PredictedClusterID}");
        }

        #endregion
    }
}

using System;

using System.Linq;

using Microsoft.ML;

using Microsoft.ML.Data;

namespace TestProject

{

/// <summary>

/// 프로그램

/// </summary>

class Program

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Method

////////////////////////////////////////////////////////////////////////////////////////// Static

//////////////////////////////////////////////////////////////////////////////// Private

#region 프로그램 시작하기 - Main()

/// <summary>

/// 프로그램 시작하기

/// </summary>

private static void Main()

{

string dataFilePath = "wine-clustering.csv";

MLContext mlContext = new MLContext();

IDataView sourceDataView = mlContext.Data.LoadFromTextFile<SourceModel>(dataFilePath, hasHeader : true, separatorChar : ',');

string[] columnNameArray = sourceDataView.Schema.Select(column => column.Name).ToArray();

var data = mlContext.Data.TrainTestSplit(sourceDataView, testFraction : 0.2);

var pipeline = mlContext.Transforms.Concatenate("Feature", columnNameArray).Append(mlContext.Clustering.Trainers.KMeans("Feature", numberOfClusters : 3));

var model = pipeline.Fit(data.TrainSet);

IDataView testDataView = model.Transform(data.TestSet);

ClusteringMetrics metrics = mlContext.Clustering.Evaluate(testDataView, scoreColumnName : "Score", featureColumnName : "Feature");

PredictionEngine<SourceModel, TargetModel> predictionEngine = mlContext.Model.CreatePredictionEngine<SourceModel, TargetModel>(model);

TargetModel target = predictionEngine.Predict

(

new SourceModel()

{

Alcohol = 11,

Ash = 2.33f,

AshAlcanity = 3.21f,

ColorIntensity = 2.9f,

Flavanoids = 1.54f,

Hue = 1.55f,

Magnesium = 120,

MalicAcid = 1.44f,

NonflavanoidPhenols = 0.3f,

OD280 = 2.93f,

Proanthocyanins = 1.72f,

TotalPhenols = 3.86f,

Proline = 1300

}

);

Console.WriteLine($"예측 클러스터 ID : {target.PredictedClusterID}");

}

#endregion

}

TestProject.zip

[C#/ML.NET] Microsoft.ML.DataView 누겟 설치하기

■ Microsoft.ML.DataView 누겟을 설치하는 방법을 보여준다. 1. Visual Studio를 실행한다. 2. [도구] / [NuGet 패키지 관리자] / [패키지 관리자 콘솔] 메뉴를 실행한다.

[C#/ML.NET] Microsoft.ML.CpuMath 누겟 설치하기

■ Microsoft.ML.CpuMath 누겟을 설치하는 방법을 보여준다. 1. Visual Studio를 실행한다. 2. [도구] / [NuGet 패키지 관리자] / [패키지 관리자 콘솔] 메뉴를 실행한다.

[C#/ML.NET] Microsoft.ML 누겟 설치하기

■ Microsoft.ML 누겟을 설치하는 방법을 보여준다. 1. Visual Studio를 실행한다. 2. [도구] / [NuGet 패키지 관리자] / [패키지 관리자 콘솔] 메뉴를 실행한다.

[C#/ML.NET/.NETCORE] 모델 빌더를 사용해 택시 요금 예측하기

■ 모델 빌더를 사용해 택시 요금을 예측하는 방법을 보여준다. [TestLibrary 프로젝트] ▶ ModelInput.cs


using Microsoft.ML.Data;

namespace TestLibrary
{
    /// <summary>
    /// 모델 입력
    /// </summary>
    public class ModelInput
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Property
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region 공급자 ID - VendorID

        /// <summary>
        /// 공급자 ID
        /// </summary>
        [ColumnName("vendor_id"), LoadColumn(0)]
        public string VendorID { get; set; }

        #endregion
        #region 요금 코드 - RateCode

        /// <summary>
        /// 요금 코드
        /// </summary>
        [ColumnName("rate_code"), LoadColumn(1)]
        public float RateCode { get; set; }

        #endregion
        #region 승객 수 - PassengerCount

        /// <summary>
        /// 승객 수
        /// </summary>
        [ColumnName("passenger_count"), LoadColumn(2)]
        public float PassengerCount { get; set; }

        #endregion
        #region 이동 시간 (단위 : 초) - TripTimeInSeconds

        /// <summary>
        /// 이동 시간 (단위 : 초)
        /// </summary>
        [ColumnName("trip_time_in_secs"), LoadColumn(3)]
        public float TripTimeInSeconds { get; set; }

        #endregion
        #region 이동 거리 - TripDistance

        /// <summary>
        /// 이동 거리
        /// </summary>
        [ColumnName("trip_distance"), LoadColumn(4)]
        public float TripDistance { get; set; }

        #endregion
        #region 지불 타입 - PaymentType

        /// <summary>
        /// 지불 타입
        /// </summary>
        [ColumnName("payment_type"), LoadColumn(5)]
        public string PaymentType { get; set; }

        #endregion
        #region 요금 - FareAmount

        /// <summary>
        /// 요금
        /// </summary>
        [ColumnName("fare_amount"), LoadColumn(6)]
        public float FareAmount { get; set; }

        #endregion
    }
}

using Microsoft.ML.Data;

namespace TestLibrary

{

/// <summary>

/// 모델 입력

/// </summary>

public class ModelInput

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Property

////////////////////////////////////////////////////////////////////////////////////////// Public

#region 공급자 ID - VendorID

/// <summary>

/// 공급자 ID

/// </summary>

[ColumnName("vendor_id"), LoadColumn(0)]

public string VendorID { get; set; }

#endregion

#region 요금 코드 - RateCode

/// <summary>

/// 요금 코드

/// </summary>

[ColumnName("rate_code"), LoadColumn(1)]

public float RateCode { get; set; }

#endregion

#region 승객 수 - PassengerCount

/// <summary>

/// 승객 수

/// </summary>

[ColumnName("passenger_count"), LoadColumn(2)]

public float PassengerCount { get; set; }

#endregion

#region 이동 시간 (단위 : 초) - TripTimeInSeconds

/// <summary>

/// 이동 시간 (단위 : 초)

/// </summary>

[ColumnName("trip_time_in_secs"), LoadColumn(3)]

public float TripTimeInSeconds { get; set; }

#endregion

#region 이동 거리 - TripDistance

/// <summary>

/// 이동 거리

/// </summary>

[ColumnName("trip_distance"), LoadColumn(4)]

public float TripDistance { get; set; }

#endregion

#region 지불 타입 - PaymentType

/// <summary>

/// 지불 타입

/// </summary>

[ColumnName("payment_type"), LoadColumn(5)]

public string PaymentType { get; set; }

#endregion

#region 요금 - FareAmount

/// <summary>

/// 요금

/// </summary>

[ColumnName("fare_amount"), LoadColumn(6)]

public float FareAmount { get; set; }

#endregion

}

▶ ModelOutput.cs


namespace TestLibrary
{
    /// <summary>
    /// 모델 입력
    /// </summary>
    public class ModelOutput
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Property
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region 점수 - Score

        /// <summary>
        /// 점수
        /// </summary>
        public float Score { get; set; }

        #endregion
    }
}

namespace TestLibrary

{

/// <summary>

/// 모델 입력

/// </summary>

public class ModelOutput

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Property

////////////////////////////////////////////////////////////////////////////////////////// Public

#region 점수 - Score

/// <summary>

/// 점수

/// </summary>

public float Score { get; set; }

#endregion

}

▶ ConsumeModel.cs


using Microsoft.ML;
using System;

namespace TestLibrary
{
    /// <summary>
    /// 모델 소비
    /// </summary>
    public class ConsumeModel
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Field
        ////////////////////////////////////////////////////////////////////////////////////////// Static
        //////////////////////////////////////////////////////////////////////////////// Private

        #region Field

        /// <summary>
        /// 예측 엔진 LAZY
        /// </summary>
        private static Lazy<PredictionEngine<ModelInput, ModelOutput>> _predictionEngineLazy = new Lazy<PredictionEngine<ModelInput, ModelOutput>>(CreatePredictionEngine);

        #endregion

        //////////////////////////////////////////////////////////////////////////////////////////////////// Method
        ////////////////////////////////////////////////////////////////////////////////////////// Static
        //////////////////////////////////////////////////////////////////////////////// Public

        #region 예측 엔진 생성하기 - CreatePredictionEngine()

        /// <summary>
        /// 예측 엔진 생성하기
        /// </summary>
        /// <returns>예측 엔진</returns>
        public static PredictionEngine<ModelInput, ModelOutput> CreatePredictionEngine()
        {
            MLContext context = new MLContext();

            string filePath = @"WEIGHT\MLModel.zip";

            ITransformer mlModel = context.Model.Load(filePath, out var modelInputSchema);

            PredictionEngine<ModelInput, ModelOutput> predictionEngine = context.Model.CreatePredictionEngine<ModelInput, ModelOutput>(mlModel);

            return predictionEngine;
        }

        #endregion
        #region 예측하기 - Predict(input)

        /// <summary>
        /// 예측하기
        /// </summary>
        /// <param name="input">모델 입력</param>
        /// <returns>모델 출력</returns>
        public static ModelOutput Predict(ModelInput input)
        {
            ModelOutput result = _predictionEngineLazy.Value.Predict(input);

            return result;
        }

        #endregion
    }
}

using Microsoft.ML;

using System;

namespace TestLibrary

{

/// <summary>

/// 모델 소비

/// </summary>

public class ConsumeModel

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Field

////////////////////////////////////////////////////////////////////////////////////////// Static

//////////////////////////////////////////////////////////////////////////////// Private

#region Field

/// <summary>

/// 예측 엔진 LAZY

/// </summary>

private static Lazy<PredictionEngine<ModelInput, ModelOutput>> _predictionEngineLazy = new Lazy<PredictionEngine<ModelInput, ModelOutput>>(CreatePredictionEngine);

#endregion

//////////////////////////////////////////////////////////////////////////////////////////////////// Method

////////////////////////////////////////////////////////////////////////////////////////// Static

//////////////////////////////////////////////////////////////////////////////// Public

#region 예측 엔진 생성하기 - CreatePredictionEngine()

/// <summary>

/// 예측 엔진 생성하기

/// </summary>

/// <returns>예측 엔진</returns>

public static PredictionEngine<ModelInput, ModelOutput> CreatePredictionEngine()

{

MLContext context = new MLContext();

string filePath = @"WEIGHT\MLModel.zip";

ITransformer mlModel = context.Model.Load(filePath, out var modelInputSchema);

PredictionEngine<ModelInput, ModelOutput> predictionEngine = context.Model.CreatePredictionEngine<ModelInput, ModelOutput>(mlModel);

return predictionEngine;

}

#endregion

#region 예측하기 - Predict(input)

/// <summary>

/// 예측하기

/// </summary>

/// <param name="input">모델 입력</param>

/// <returns>모델 출력</returns>

public static ModelOutput Predict(ModelInput input)

{

ModelOutput result = _predictionEngineLazy.Value.Predict(input);

return result;

}

#endregion

}

[TestProtect 프로젝트]

[C#/ML.NET] 다중 클래스 분류 모델 사용하기

■ 다중 클래스 분류 모델을 사용하는 방법을 보여준다. ▶ IssueData.cs


using Microsoft.ML.Data;

namespace TestProject
{
    /// <summary>
    /// 이슈 데이터
    /// </summary>
    public class IssueData
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Property
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region ID - ID

        /// <summary>
        /// ID
        /// </summary>
        [LoadColumn(0)]
        public string ID { get; set; }

        #endregion
        #region 영역 - Area

        /// <summary>
        /// 영역
        /// </summary>
        [LoadColumn(1)]
        public string Area { get; set; }

        #endregion
        #region 제목 - Title

        /// <summary>
        /// 제목
        /// </summary>
        [LoadColumn(2)]
        public string Title { get; set; }

        #endregion
        #region 설명 - Description

        /// <summary>
        /// 설명
        /// </summary>
        [LoadColumn(3)]
        public string Description { get; set; }

        #endregion
    }
}

using Microsoft.ML.Data;

namespace TestProject

{

/// <summary>

/// 이슈 데이터

/// </summary>

public class IssueData

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Property

////////////////////////////////////////////////////////////////////////////////////////// Public

#region ID - ID

/// <summary>

/// ID

/// </summary>

[LoadColumn(0)]

public string ID { get; set; }

#endregion

#region 영역 - Area

/// <summary>

/// 영역

/// </summary>

[LoadColumn(1)]

public string Area { get; set; }

#endregion

#region 제목 - Title

/// <summary>

/// 제목

/// </summary>

[LoadColumn(2)]

public string Title { get; set; }

#endregion

#region 설명 - Description

/// <summary>

/// 설명

/// </summary>

[LoadColumn(3)]

public string Description { get; set; }

#endregion

}

▶ IssuePrediction.cs


using Microsoft.ML.Data;

namespace TestProject
{
    /// <summary>
    /// 이슈 예측
    /// </summary>
    public class IssuePrediction
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Property
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region 영역 - Area

        /// <summary>
        /// 영역
        /// </summary>
        [ColumnName("PredictedLabel")]
        public string Area;

        #endregion
    }
}

using Microsoft.ML.Data;

namespace TestProject

{

/// <summary>

/// 이슈 예측

/// </summary>

public class IssuePrediction

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Property

////////////////////////////////////////////////////////////////////////////////////////// Public

#region 영역 - Area

/// <summary>

/// 영역

/// </summary>

[ColumnName("PredictedLabel")]

public string Area;

#endregion

}

▶ Program.cs


using System;
using System.IO;

using Microsoft.ML;
using Microsoft.ML.Data;

namespace TestProject
{
    /// <summary>
    /// 프로그램
    /// </summary>
    class Program
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Field
        ////////////////////////////////////////////////////////////////////////////////////////// Static
        //////////////////////////////////////////////////////////////////////////////// Private

        #region Field

        /// <summary>
        /// 애플리케이션 경로
        /// </summary>
        private static string _applicationPath => Path.GetDirectoryName(Environment.GetCommandLineArgs()[0]);

        /// <summary>
        /// 훈련 데이터 파일 경로
        /// </summary>
        private static string _trainingDataFilePath => Path.Combine(_applicationPath, "Data", "issues_train.tsv");

        /// <summary>
        /// 테스트 데이터 파일 경로
        /// </summary>
        private static string _testDataFilePath => Path.Combine(_applicationPath, "Data", "issues_test.tsv");

        /// <summary>
        /// 모델 파일 경로
        /// </summary>
        private static string _modelFilePath => Path.Combine(_applicationPath, "Data", "model.zip");

        /// <summary>
        /// 모델 컨텍스트
        /// </summary>
        private static MLContext _context;

        /// <summary>
        /// 예측 엔진
        /// </summary>
        private static PredictionEngine<IssueData, IssuePrediction> _predictionEngine;

        /// <summary>
        /// 모델
        /// </summary>
        private static ITransformer _model;

        /// <summary>
        /// 훈련 데이터 뷰
        /// </summary>
        private static IDataView _trainingDataView;

        #endregion

        //////////////////////////////////////////////////////////////////////////////////////////////////// Method
        ////////////////////////////////////////////////////////////////////////////////////////// Static
        //////////////////////////////////////////////////////////////////////////////// Private

        #region 프로그램 시작하기 - Main()

        /// <summary>
        /// 프로그램 시작하기
        /// </summary>
        private static void Main()
        {
            Console.WriteLine("BEGIN MAIN FUNCTION");

            _context = new MLContext(seed: 0);

            Console.WriteLine("BEGIN SET TRAINING DATA VIEW");

            _trainingDataView = _context.Data.LoadFromTextFile<IssueData>(_trainingDataFilePath, hasHeader: true);

            Console.WriteLine("END SET TRAINING DATA VIEW");

            Console.WriteLine("BEGIN SET PIPE LINE");

            var pipeline = GetPipeLine();

            Console.WriteLine("END SET PIPE LINE");

            _model = GetModel(_trainingDataView, pipeline);

            Console.WriteLine("BEGIN PREDICT SINGLE ITEM");

            _predictionEngine = _context.Model.CreatePredictionEngine<IssueData, IssuePrediction>(_model);

            IssueData issueData = new IssueData()
            {
                Title       = "WebSockets communication is slow in my machine",
                Description = "The WebSockets communication used under the covers by SignalR looks like is going slow in my development machine.."
            };

            IssuePrediction issuePrediction = _predictionEngine.Predict(issueData);

            Console.WriteLine("--------------------------------------------------");
            Console.WriteLine($"AREA : {issuePrediction.Area}");
            Console.WriteLine("--------------------------------------------------");

            Evaluate(_trainingDataView.Schema);

            SaveModel(_context, _trainingDataView.Schema, _model);

            PredictIssue();

            Console.WriteLine("END MAIN FUNCTION");
        }

        #endregion

        #region 파이프 라인 구하기 - GetPipeLine()

        /// <summary>
        /// 파이프 라인 구하기
        /// </summary>
        /// <returns>파이프 라인</returns>
        private static IEstimator<ITransformer> GetPipeLine()
        {
            Console.WriteLine("BEGIN GET PIPE LINE FUNCTION");

            var pipeline = _context.Transforms.Conversion.MapValueToKey(inputColumnName : "Area", outputColumnName : "Label")
                .Append(_context.Transforms.Text.FeaturizeText(inputColumnName : "Title"      , outputColumnName : "TitleFeaturized"      ))
                .Append(_context.Transforms.Text.FeaturizeText(inputColumnName : "Description", outputColumnName : "DescriptionFeaturized"))
                .Append(_context.Transforms.Concatenate("Features", "TitleFeaturized", "DescriptionFeaturized"))
                .AppendCacheCheckpoint(_context)
                .Append(_context.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "Features"))
                .Append(_context.Transforms.Conversion.MapKeyToValue("PredictedLabel"));

            Console.WriteLine("END GET PIPE LINE FUNCTION");

            return pipeline;
        }

        #endregion
        #region 모델 구하기 - GetModel(trainingDataView, pipeline)

        /// <summary>
        /// 모델 구하기
        /// </summary>
        /// <param name="trainingDataView">훈련 데이터 뷰</param>
        /// <param name="pipeline">파이프 라인</param>
        /// <returns>모델</returns>
        private static ITransformer GetModel(IDataView trainingDataView, IEstimator<ITransformer> pipeline)
        {
            Console.WriteLine("BEGIN GET MODEL FUNCTION");

            var model = pipeline.Fit(trainingDataView);

            Console.WriteLine("END GET MODEL FUNCTION");

            return model;
        }

        #endregion
        #region 평가하기 - Evaluate(trainingDataViewSchema)

        /// <summary>
        /// 평가하기
        /// </summary>
        /// <param name="trainingDataViewSchema">훈련 데이터 뷰 스키마</param>
        private static void Evaluate(DataViewSchema trainingDataViewSchema)
        {
            Console.WriteLine("BEGIN EVALUATE FUNCTION");

            IDataView testDataView = _context.Data.LoadFromTextFile<IssueData>(_testDataFilePath, hasHeader : true);

            MulticlassClassificationMetrics metrics = _context.MulticlassClassification.Evaluate(_model.Transform(testDataView));

            Console.WriteLine("--------------------------------------------------"      );
            Console.WriteLine("METRICS FOR MULTI-CLASS CLASSIFICATION MODEL - TEST DATA");
            Console.WriteLine("--------------------------------------------------"      );
            Console.WriteLine($"MICRO ACCURACY     : {metrics.MicroAccuracy:0.###}"     );
            Console.WriteLine($"MACRO ACCURACY     : {metrics.MacroAccuracy:0.###}"     );
            Console.WriteLine($"LOG LOSS           : {metrics.LogLoss:#.###}"           );
            Console.WriteLine($"LOG LOSS REDUCTION : {metrics.LogLossReduction:#.###}"  );
            Console.WriteLine("--------------------------------------------------"      );

            Console.WriteLine("END EVALUATE FUNCTION");
        }

        #endregion
        #region 모델 저장하기 - SaveModel(context, trainingDataViewSchema, model)

        /// <summary>
        /// 모델 저장하기
        /// </summary>
        /// <param name="context">ML 컨텍스트</param>
        /// <param name="trainingDataViewSchema">훈련 데이터 뷰 스키마</param>
        /// <param name="model">모델</param>
        private static void SaveModel(MLContext context, DataViewSchema trainingDataViewSchema, ITransformer model)
        {
            Console.WriteLine("BEGIN SAVE MODEL FUNCTION");

            context.Model.Save(model, trainingDataViewSchema, _modelFilePath);

            Console.WriteLine("END SAVE MODEL FUNCTION");
        }

        #endregion
        #region 이슈 예측하기 - PredictIssue()

        /// <summary>
        /// 이슈 예측하기
        /// </summary>
        private static void PredictIssue()
        {
            Console.WriteLine("BEGIN PREDICT ISSUE FUNCTION");

            ITransformer model = _context.Model.Load(_modelFilePath, out var inputSchema);

            IssueData issueData = new IssueData()
            {
                Title       = "Entity Framework crashes",
                Description = "When connecting to the database, EF is crashing"
            };

            _predictionEngine = _context.Model.CreatePredictionEngine<IssueData, IssuePrediction>(model);

            IssuePrediction issuePrediction = _predictionEngine.Predict(issueData);

            Console.WriteLine("--------------------------------------------------");
            Console.WriteLine($"AREA : {issuePrediction.Area}");
            Console.WriteLine("--------------------------------------------------");

            Console.WriteLine("END PREDICT ISSUE FUNCTION");
        }

        #endregion
    }
}

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

using System;

using System.IO;

using Microsoft.ML;

using Microsoft.ML.Data;

namespace TestProject

{

/// <summary>

/// 프로그램

/// </summary>

class Program

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Field

////////////////////////////////////////////////////////////////////////////////////////// Static

//////////////////////////////////////////////////////////////////////////////// Private

#region Field

/// <summary>

/// 애플리케이션 경로

/// </summary>

private static string _applicationPath => Path.GetDirectoryName(Environment.GetCommandLineArgs()[0]);

/// <summary>

/// 훈련 데이터 파일 경로

/// </summary>

private static string _trainingDataFilePath => Path.Combine(_applicationPath, "Data", "issues_train.tsv");

/// <summary>

/// 테스트 데이터 파일 경로

/// </summary>

private static string _testDataFilePath => Path.Combine(_applicationPath, "Data", "issues_test.tsv");

/// <summary>

/// 모델 파일 경로

/// </summary>

private static string _modelFilePath => Path.Combine(_applicationPath, "Data", "model.zip");

/// <summary>

/// 모델 컨텍스트

/// </summary>

private static MLContext _context;

/// <summary>

/// 예측 엔진

/// </summary>

private static PredictionEngine<IssueData, IssuePrediction> _predictionEngine;

/// <summary>

/// 모델

/// </summary>

private static ITransformer _model;

/// <summary>

/// 훈련 데이터 뷰

/// </summary>

private static IDataView _trainingDataView;

#endregion

//////////////////////////////////////////////////////////////////////////////////////////////////// Method

////////////////////////////////////////////////////////////////////////////////////////// Static

//////////////////////////////////////////////////////////////////////////////// Private

#region 프로그램 시작하기 - Main()

/// <summary>

/// 프로그램 시작하기

/// </summary>

private static void Main()

{

Console.WriteLine("BEGIN MAIN FUNCTION");

_context = new MLContext(seed: 0);

Console.WriteLine("BEGIN SET TRAINING DATA VIEW");

_trainingDataView = _context.Data.LoadFromTextFile<IssueData>(_trainingDataFilePath, hasHeader: true);

Console.WriteLine("END SET TRAINING DATA VIEW");

Console.WriteLine("BEGIN SET PIPE LINE");

var pipeline = GetPipeLine();

Console.WriteLine("END SET PIPE LINE");

_model = GetModel(_trainingDataView, pipeline);

Console.WriteLine("BEGIN PREDICT SINGLE ITEM");

_predictionEngine = _context.Model.CreatePredictionEngine<IssueData, IssuePrediction>(_model);

IssueData issueData = new IssueData()

{

Title = "WebSockets communication is slow in my machine",

Description = "The WebSockets communication used under the covers by SignalR looks like is going slow in my development machine.."

};

IssuePrediction issuePrediction = _predictionEngine.Predict(issueData);

Console.WriteLine("--------------------------------------------------");

Console.WriteLine($"AREA : {issuePrediction.Area}");

Console.WriteLine("--------------------------------------------------");

Evaluate(_trainingDataView.Schema);

SaveModel(_context, _trainingDataView.Schema, _model);

PredictIssue();

Console.WriteLine("END MAIN FUNCTION");

}

#endregion

#region 파이프 라인 구하기 - GetPipeLine()

/// <summary>

/// 파이프 라인 구하기

/// </summary>

/// <returns>파이프 라인</returns>

private static IEstimator<ITransformer> GetPipeLine()

{

Console.WriteLine("BEGIN GET PIPE LINE FUNCTION");

var pipeline = _context.Transforms.Conversion.MapValueToKey(inputColumnName : "Area", outputColumnName : "Label")

.Append(_context.Transforms.Text.FeaturizeText(inputColumnName : "Title" , outputColumnName : "TitleFeaturized" ))

.Append(_context.Transforms.Text.FeaturizeText(inputColumnName : "Description", outputColumnName : "DescriptionFeaturized"))

.Append(_context.Transforms.Concatenate("Features", "TitleFeaturized", "DescriptionFeaturized"))

.AppendCacheCheckpoint(_context)

.Append(_context.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "Features"))

.Append(_context.Transforms.Conversion.MapKeyToValue("PredictedLabel"));

Console.WriteLine("END GET PIPE LINE FUNCTION");

return pipeline;

}

#endregion

#region 모델 구하기 - GetModel(trainingDataView, pipeline)

/// <summary>

/// 모델 구하기

/// </summary>

/// <param name="trainingDataView">훈련 데이터 뷰</param>

/// <param name="pipeline">파이프 라인</param>

/// <returns>모델</returns>

private static ITransformer GetModel(IDataView trainingDataView, IEstimator<ITransformer> pipeline)

{

Console.WriteLine("BEGIN GET MODEL FUNCTION");

var model = pipeline.Fit(trainingDataView);

Console.WriteLine("END GET MODEL FUNCTION");

return model;

}

#endregion

#region 평가하기 - Evaluate(trainingDataViewSchema)

/// <summary>

/// 평가하기

/// </summary>

/// <param name="trainingDataViewSchema">훈련 데이터 뷰 스키마</param>

private static void Evaluate(DataViewSchema trainingDataViewSchema)

{

Console.WriteLine("BEGIN EVALUATE FUNCTION");

IDataView testDataView = _context.Data.LoadFromTextFile<IssueData>(_testDataFilePath, hasHeader : true);

MulticlassClassificationMetrics metrics = _context.MulticlassClassification.Evaluate(_model.Transform(testDataView));

Console.WriteLine("--------------------------------------------------" );

Console.WriteLine("METRICS FOR MULTI-CLASS CLASSIFICATION MODEL - TEST DATA");

Console.WriteLine("--------------------------------------------------" );

Console.WriteLine($"MICRO ACCURACY : {metrics.MicroAccuracy:0.###}" );

Console.WriteLine($"MACRO ACCURACY : {metrics.MacroAccuracy:0.###}" );

Console.WriteLine($"LOG LOSS : {metrics.LogLoss:#.###}" );

Console.WriteLine($"LOG LOSS REDUCTION : {metrics.LogLossReduction:#.###}" );

Console.WriteLine("--------------------------------------------------" );

Console.WriteLine("END EVALUATE FUNCTION");

}

#endregion

#region 모델 저장하기 - SaveModel(context, trainingDataViewSchema, model)

/// <summary>

/// 모델 저장하기

/// </summary>

/// <param name="context">ML 컨텍스트</param>

/// <param name="trainingDataViewSchema">훈련 데이터 뷰 스키마</param>

/// <param name="model">모델</param>

private static void SaveModel(MLContext context, DataViewSchema trainingDataViewSchema, ITransformer model)

{

Console.WriteLine("BEGIN SAVE MODEL FUNCTION");

context.Model.Save(model, trainingDataViewSchema, _modelFilePath);

Console.WriteLine("END SAVE MODEL FUNCTION");

}

#endregion

#region 이슈 예측하기 - PredictIssue()

/// <summary>

/// 이슈 예측하기

/// </summary>

private static void PredictIssue()

{

Console.WriteLine("BEGIN PREDICT ISSUE FUNCTION");

ITransformer model = _context.Model.Load(_modelFilePath, out var inputSchema);

IssueData issueData = new IssueData()

{

Title = "Entity Framework crashes",

Description = "When connecting to the database, EF is crashing"

};

_predictionEngine = _context.Model.CreatePredictionEngine<IssueData, IssuePrediction>(model);

IssuePrediction issuePrediction = _predictionEngine.Predict(issueData);

Console.WriteLine("--------------------------------------------------");

Console.WriteLine($"AREA : {issuePrediction.Area}");

Console.WriteLine("--------------------------------------------------");

Console.WriteLine("END PREDICT ISSUE FUNCTION");

}

#endregion

}

TestProject.zip

[C#/ML.NET] 이진 클래스 분류 모델 사용하기

■ 이진 클래스 분류 모델을 사용하는 방법을 보여준다. ▶ SentimentData.cs


using Microsoft.ML.Data;

namespace TestProject
{
    /// <summary>
    /// 감정 데이터
    /// </summary>
    public class SentimentData
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Field
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region Field

        /// <summary>
        /// 감정 텍스트
        /// </summary>
        [LoadColumn(0)]
        public string SentimentText;

        /// <summary>
        /// 감정
        /// </summary>
        [LoadColumn(1)]
        [ColumnName("Label")]
        public bool Sentiment;

        #endregion
    }
}

using Microsoft.ML.Data;

namespace TestProject

{

/// <summary>

/// 감정 데이터

/// </summary>

public class SentimentData

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Field

////////////////////////////////////////////////////////////////////////////////////////// Public

#region Field

/// <summary>

/// 감정 텍스트

/// </summary>

[LoadColumn(0)]

public string SentimentText;

/// <summary>

/// 감정

/// </summary>

[LoadColumn(1)]

[ColumnName("Label")]

public bool Sentiment;

#endregion

}

▶ SentimentPrediction.cs


using Microsoft.ML.Data;

namespace TestProject
{
    /// <summary>
    /// 감정 예측
    /// </summary>
    public class SentimentPrediction : SentimentData
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Property
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region 예측 - Prediction

        /// <summary>
        /// 예측
        /// </summary>
        [ColumnName("PredictedLabel")]
        public bool Prediction { get; set; }

        #endregion
        #region 확률 - Probability

        /// <summary>
        /// 확률
        /// </summary>
        public float Probability { get; set; }

        #endregion
        #region 점수 - Score

        /// <summary>
        /// 점수
        /// </summary>
        public float Score { get; set; }

        #endregion
    }
}

using Microsoft.ML.Data;

namespace TestProject

{

/// <summary>

/// 감정 예측

/// </summary>

public class SentimentPrediction : SentimentData

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Property

////////////////////////////////////////////////////////////////////////////////////////// Public

#region 예측 - Prediction

/// <summary>

/// 예측

/// </summary>

[ColumnName("PredictedLabel")]

public bool Prediction { get; set; }

#endregion

#region 확률 - Probability

/// <summary>

/// 확률

/// </summary>

public float Probability { get; set; }

#endregion

#region 점수 - Score

/// <summary>

/// 점수

/// </summary>

public float Score { get; set; }

#endregion

}

▶ Program.cs


using System;
using System.Collections.Generic;
using System.IO;

using Microsoft.ML;
using Microsoft.ML.Data;

namespace TestProject
{
    /// <summary>
    /// 프로그램
    /// </summary>
    class Program
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Field
        ////////////////////////////////////////////////////////////////////////////////////////// Static
        //////////////////////////////////////////////////////////////////////////////// Private

        #region Field

        /// <summary>
        /// 레이블 파일 경로
        /// </summary>
        private static readonly string _labelFilePath = Path.Combine(Environment.CurrentDirectory, "Data", "label.txt");

        #endregion

        //////////////////////////////////////////////////////////////////////////////////////////////////// Method
        ////////////////////////////////////////////////////////////////////////////////////////// Static
        //////////////////////////////////////////////////////////////////////////////// Private

        #region 프로그램 시작하기 - Main()

        /// <summary>
        /// 프로그램 시작하기
        /// </summary>
        private static void Main()
        {
            Console.WriteLine("BEGIN MAIN FUNCTION");

            MLContext context = new MLContext();

            DataOperationsCatalog.TrainTestData trainTestData = GetTrainTestData(context);

            ITransformer model = GetModel(context, trainTestData.TrainSet);

            Evaluate(context, model, trainTestData.TestSet);

            PredictSingleItem(context, model);

            Predict(context, model);

            Console.WriteLine("END MAIN FUNCTION");
        }

        #endregion

        #region 훈련 테스트 데이터 구하기 - GetTrainTestData(context)

        /// <summary>
        /// 훈련 테스트 데이터 구하기
        /// </summary>
        /// <param name="context">ML 컨텍스트</param>
        /// <returns>훈련 테스트 데이터</returns>
        public static DataOperationsCatalog.TrainTestData GetTrainTestData(MLContext context)
        {
            Console.WriteLine("BEGIN GET TRAIN TEST DATA");

            IDataView dataView = context.Data.LoadFromTextFile<SentimentData>(_labelFilePath, hasHeader : false);

            DataOperationsCatalog.TrainTestData trainTestData = context.Data.TrainTestSplit(dataView, testFraction : 0.2);

            Console.WriteLine("END GET TRAIN TEST DATA");

            return trainTestData;
        }

        #endregion
        #region 모델 구하기 - GetModel(context, trainingDataView)

        /// <summary>
        /// 모델 구하기
        /// </summary>
        /// <param name="context">컨텍스트</param>
        /// <param name="trainingDataView">훈련 데이터 뷰</param>
        /// <returns>모델</returns>
        public static ITransformer GetModel(MLContext context, IDataView trainingDataView)
        {
            Console.WriteLine("BEGIN GET MODEL FUNCTION");

            var estimator = context.Transforms.Text.FeaturizeText
            (
                outputColumnName : "Features",
                inputColumnName  : nameof(SentimentData.SentimentText)
            )
            .Append
            (
                context.BinaryClassification.Trainers.SdcaLogisticRegression
                (
                    labelColumnName   : "Label",
                    featureColumnName : "Features"
                )
            );

            Console.WriteLine("BEGIN CREATE AND TRAIN THE MODEL");

            var model = estimator.Fit(trainingDataView);

            Console.WriteLine("END CREATE AND TRAIN THE MODEL");

            Console.WriteLine("END GET MODEL FUNCTION");

            return model;
        }

        #endregion
        #region 평가하기 - Evaluate(context, model, testDataView)

        /// <summary>
        /// 평가하기
        /// </summary>
        /// <param name="context">ML 컨텍스트</param>
        /// <param name="model">모델</param>
        /// <param name="testDataView">테스트 데이터 뷰</param>
        public static void Evaluate(MLContext context, ITransformer model, IDataView testDataView)
        {
            Console.WriteLine("BEGIN EVALUATE FUNCTION");

            IDataView predictions = model.Transform(testDataView);

            CalibratedBinaryClassificationMetrics metrics = context.BinaryClassification.Evaluate(predictions, "Label");

            Console.WriteLine("MODEL QUALITY METRICS EVALUATION");
            Console.WriteLine("--------------------------------------------------");
            Console.WriteLine($"ACCURACY : {metrics.Accuracy:P2}"         );
            Console.WriteLine($"AUC      : {metrics.AreaUnderRocCurve:P2}");
            Console.WriteLine($"F1SCORE  : {metrics.F1Score:P2}"          );
            Console.WriteLine("--------------------------------------------------");

            Console.WriteLine("END EVALUATE FUNCTION");
        }

        #endregion
        #region 단일 항목 예측하기 - PredictSingleItem(context, model)

        /// <summary>
        /// 단일 항목 예측하기
        /// </summary>
        /// <param name="context">컨텍스트</param>
        /// <param name="model">모델</param>
        private static void PredictSingleItem(MLContext context, ITransformer model)
        {
            Console.WriteLine("BEGIN PREDICT SINGLE ITEM FUNCTION");

            PredictionEngine<SentimentData, SentimentPrediction> predictionEngine = context.Model.CreatePredictionEngine<SentimentData, SentimentPrediction>(model);

            SentimentData sentimentData = new SentimentData { SentimentText = "This was a very bad steak" };

            SentimentPrediction sentimentPrediction = predictionEngine.Predict(sentimentData);

            Console.WriteLine("--------------------------------------------------");
            Console.WriteLine($"SENTIMENT   : {sentimentPrediction.SentimentText}"                                            );
            Console.WriteLine($"PREDICTION  : {(Convert.ToBoolean(sentimentPrediction.Prediction) ? "Positive" : "Negative")}");
            Console.WriteLine($"PROBABILITY : {sentimentPrediction.Probability}"                                              );
            Console.WriteLine("--------------------------------------------------");

            Console.WriteLine("END PREDICT SINGLE ITEM FUNCTION");
        }

        #endregion
        #region 예측하기 - Predict(context, model)

        /// <summary>
        /// 예측하기
        /// </summary>
        /// <param name="context">ML 컨텍스트</param>
        /// <param name="model">모델</param>
        public static void Predict(MLContext context, ITransformer model)
        {
            Console.WriteLine("BEGIN PREDICT FUNCTION");

            IEnumerable<SentimentData> sentimentDataEnumerable = new[]
            {
                new SentimentData { SentimentText = "This was a horrible meal" },
                new SentimentData { SentimentText = "I love this spaghetti."   }
            };

            IDataView sentimentDataView = model.Transform(context.Data.LoadFromEnumerable(sentimentDataEnumerable));

            IEnumerable<SentimentPrediction> sentimentPredictionEnumerable = context.Data.CreateEnumerable<SentimentPrediction>(sentimentDataView, reuseRowObject : false);

            Console.WriteLine("--------------------------------------------------");

            foreach(SentimentPrediction sentimentPrediction  in sentimentPredictionEnumerable)
            {
                Console.WriteLine($"SENTIMENT   : {sentimentPrediction.SentimentText}");
                Console.WriteLine($"PREDICTION  : {(Convert.ToBoolean(sentimentPrediction.Prediction) ? "Positive" : "Negative")}");
                Console.WriteLine($"PROBABILITY : {sentimentPrediction.Probability}");
                Console.WriteLine("--------------------------------------------------");
            }

            Console.WriteLine("END PREDICT FUNCTION");
        }

        #endregion
    }
}

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

using System;

using System.Collections.Generic;

using System.IO;

using Microsoft.ML;

using Microsoft.ML.Data;

namespace TestProject

{

/// <summary>

/// 프로그램

/// </summary>

class Program

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Field

////////////////////////////////////////////////////////////////////////////////////////// Static

//////////////////////////////////////////////////////////////////////////////// Private

#region Field

/// <summary>

/// 레이블 파일 경로

/// </summary>

private static readonly string _labelFilePath = Path.Combine(Environment.CurrentDirectory, "Data", "label.txt");

#endregion

//////////////////////////////////////////////////////////////////////////////////////////////////// Method

////////////////////////////////////////////////////////////////////////////////////////// Static

//////////////////////////////////////////////////////////////////////////////// Private

#region 프로그램 시작하기 - Main()

/// <summary>

/// 프로그램 시작하기

/// </summary>

private static void Main()

{

Console.WriteLine("BEGIN MAIN FUNCTION");

MLContext context = new MLContext();

DataOperationsCatalog.TrainTestData trainTestData = GetTrainTestData(context);

ITransformer model = GetModel(context, trainTestData.TrainSet);

Evaluate(context, model, trainTestData.TestSet);

PredictSingleItem(context, model);

Predict(context, model);

Console.WriteLine("END MAIN FUNCTION");

}

#endregion

#region 훈련 테스트 데이터 구하기 - GetTrainTestData(context)

/// <summary>

/// 훈련 테스트 데이터 구하기

/// </summary>

/// <param name="context">ML 컨텍스트</param>

/// <returns>훈련 테스트 데이터</returns>

public static DataOperationsCatalog.TrainTestData GetTrainTestData(MLContext context)

{

Console.WriteLine("BEGIN GET TRAIN TEST DATA");

IDataView dataView = context.Data.LoadFromTextFile<SentimentData>(_labelFilePath, hasHeader : false);

DataOperationsCatalog.TrainTestData trainTestData = context.Data.TrainTestSplit(dataView, testFraction : 0.2);

Console.WriteLine("END GET TRAIN TEST DATA");

return trainTestData;

}

#endregion

#region 모델 구하기 - GetModel(context, trainingDataView)

/// <summary>

/// 모델 구하기

/// </summary>

/// <param name="context">컨텍스트</param>

/// <param name="trainingDataView">훈련 데이터 뷰</param>

/// <returns>모델</returns>

public static ITransformer GetModel(MLContext context, IDataView trainingDataView)

{

Console.WriteLine("BEGIN GET MODEL FUNCTION");

var estimator = context.Transforms.Text.FeaturizeText

(

outputColumnName : "Features",

inputColumnName : nameof(SentimentData.SentimentText)

)

.Append

(

context.BinaryClassification.Trainers.SdcaLogisticRegression

(

labelColumnName : "Label",

featureColumnName : "Features"

)

);

Console.WriteLine("BEGIN CREATE AND TRAIN THE MODEL");

var model = estimator.Fit(trainingDataView);

Console.WriteLine("END CREATE AND TRAIN THE MODEL");

Console.WriteLine("END GET MODEL FUNCTION");

return model;

}

#endregion

#region 평가하기 - Evaluate(context, model, testDataView)

/// <summary>

/// 평가하기

/// </summary>

/// <param name="context">ML 컨텍스트</param>

/// <param name="model">모델</param>

/// <param name="testDataView">테스트 데이터 뷰</param>

public static void Evaluate(MLContext context, ITransformer model, IDataView testDataView)

{

Console.WriteLine("BEGIN EVALUATE FUNCTION");

IDataView predictions = model.Transform(testDataView);

CalibratedBinaryClassificationMetrics metrics = context.BinaryClassification.Evaluate(predictions, "Label");

Console.WriteLine("MODEL QUALITY METRICS EVALUATION");

Console.WriteLine("--------------------------------------------------");

Console.WriteLine($"ACCURACY : {metrics.Accuracy:P2}" );

Console.WriteLine($"AUC : {metrics.AreaUnderRocCurve:P2}");

Console.WriteLine($"F1SCORE : {metrics.F1Score:P2}" );

Console.WriteLine("--------------------------------------------------");

Console.WriteLine("END EVALUATE FUNCTION");

}

#endregion

#region 단일 항목 예측하기 - PredictSingleItem(context, model)

/// <summary>

/// 단일 항목 예측하기

/// </summary>

/// <param name="context">컨텍스트</param>

/// <param name="model">모델</param>

private static void PredictSingleItem(MLContext context, ITransformer model)

{

Console.WriteLine("BEGIN PREDICT SINGLE ITEM FUNCTION");

PredictionEngine<SentimentData, SentimentPrediction> predictionEngine = context.Model.CreatePredictionEngine<SentimentData, SentimentPrediction>(model);

SentimentData sentimentData = new SentimentData { SentimentText = "This was a very bad steak" };

SentimentPrediction sentimentPrediction = predictionEngine.Predict(sentimentData);

Console.WriteLine("--------------------------------------------------");

Console.WriteLine($"SENTIMENT : {sentimentPrediction.SentimentText}" );

Console.WriteLine($"PREDICTION : {(Convert.ToBoolean(sentimentPrediction.Prediction) ? "Positive" : "Negative")}");

Console.WriteLine($"PROBABILITY : {sentimentPrediction.Probability}" );

Console.WriteLine("--------------------------------------------------");

Console.WriteLine("END PREDICT SINGLE ITEM FUNCTION");

}

#endregion

#region 예측하기 - Predict(context, model)

/// <summary>

/// 예측하기

/// </summary>

/// <param name="context">ML 컨텍스트</param>

/// <param name="model">모델</param>

public static void Predict(MLContext context, ITransformer model)

{

Console.WriteLine("BEGIN PREDICT FUNCTION");

IEnumerable<SentimentData> sentimentDataEnumerable = new[]

{

new SentimentData { SentimentText = "This was a horrible meal" },

new SentimentData { SentimentText = "I love this spaghetti." }

};

IDataView sentimentDataView = model.Transform(context.Data.LoadFromEnumerable(sentimentDataEnumerable));

IEnumerable<SentimentPrediction> sentimentPredictionEnumerable = context.Data.CreateEnumerable<SentimentPrediction>(sentimentDataView, reuseRowObject : false);

Console.WriteLine("--------------------------------------------------");

foreach(SentimentPrediction sentimentPrediction in sentimentPredictionEnumerable)

{

Console.WriteLine($"SENTIMENT : {sentimentPrediction.SentimentText}");

Console.WriteLine($"PREDICTION : {(Convert.ToBoolean(sentimentPrediction.Prediction) ? "Positive" : "Negative")}");

Console.WriteLine($"PROBABILITY : {sentimentPrediction.Probability}");

Console.WriteLine("--------------------------------------------------");

}

Console.WriteLine("END PREDICT FUNCTION");

}

#endregion

}

TestProject.zip

[C#/ML.NET] 선형 회귀 모델 사용하기

■ 선형 회귀 모델을 사용하는 방법을 보여준다. ▶ HouseData.cs


namespace TestProject
{
    /// <summary>
    /// 주택 데이터
    /// </summary>
    public class HouseData
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Property
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region 크기 - Size

        /// <summary>
        /// 크기
        /// </summary>
        public float Size { get; set; }

        #endregion
        #region 가격 - Price

        /// <summary>
        /// 가격
        /// </summary>
        public float Price { get; set; }

        #endregion
    }
}

namespace TestProject

{

/// <summary>

/// 주택 데이터

/// </summary>

public class HouseData

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Property

////////////////////////////////////////////////////////////////////////////////////////// Public

#region 크기 - Size

/// <summary>

/// 크기

/// </summary>

public float Size { get; set; }

#endregion

#region 가격 - Price

/// <summary>

/// 가격

/// </summary>

public float Price { get; set; }

#endregion

}

▶ Prediction.cs


using Microsoft.ML.Data;

namespace TestProject
{
    /// <summary>
    /// 예측
    /// </summary>
    public class Prediction
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Property
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region 가격 - Price

        /// <summary>
        /// 가격
        /// </summary>
        [ColumnName("Score")]
        public float Price { get; set; }

        #endregion
    }
}

using Microsoft.ML.Data;

namespace TestProject

{

/// <summary>

/// 예측

/// </summary>

public class Prediction

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Property

////////////////////////////////////////////////////////////////////////////////////////// Public

#region 가격 - Price

/// <summary>

/// 가격

/// </summary>

[ColumnName("Score")]

public float Price { get; set; }

#endregion

}

▶ Program.cs


using System;
using System.Globalization;
using System.Threading;

using Microsoft.ML;

namespace TestProject
{
    /// <summary>
    /// 프로그램
    /// </summary>
    class Program
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Method
        ////////////////////////////////////////////////////////////////////////////////////////// Static
        //////////////////////////////////////////////////////////////////////////////// Private

        #region 프로그램 시작하기 - Main()

        /// <summary>
        /// 프로그램 시작하기
        /// </summary>
        private static void Main()
        {
            Console.WriteLine("BEGIN MAIN FUNCTION");

            CultureInfo cultureInfo = new CultureInfo("en-us");

            Thread.CurrentThread.CurrentCulture   = cultureInfo;
            Thread.CurrentThread.CurrentUICulture = cultureInfo;

            MLContext context = new MLContext();

            Console.WriteLine("BEGIN SET TRAINING DATA VIEW");

            HouseData[] trainingArray =
            {
                new HouseData() { Size = 1.1f, Price = 1.2f },
                new HouseData() { Size = 1.9f, Price = 2.3f },
                new HouseData() { Size = 2.8f, Price = 3.0f },
                new HouseData() { Size = 3.4f, Price = 3.7f }
            };

            IDataView trainingDataView = context.Data.LoadFromEnumerable(trainingArray);

            Console.WriteLine("END SET TRAINING DATA VIEW");

            Console.WriteLine("BEGIN SET PIPELINE");

            var pipeline = context.Transforms.Concatenate("Features", new[] { "Size" })
                .Append(context.Regression.Trainers.Sdca(labelColumnName : "Price", maximumNumberOfIterations : 1000));

            Console.WriteLine("END SET PIPELINE");

            Console.WriteLine("BEGIN SET MODEL");

            var model = pipeline.Fit(trainingDataView);

            Console.WriteLine("END SET MODEL");

            Console.WriteLine("BEGIN PREDICT");

            HouseData houseData = new HouseData() { Size = 2.5f };

            Prediction predition = context.Model.CreatePredictionEngine<HouseData, Prediction>(model).Predict(houseData);

            Console.WriteLine("--------------------------------------------------");
            Console.WriteLine($"SIZE  : {houseData.Size * 1000} SQ FT");
            Console.WriteLine($"PRICE : {predition.Price * 100000:C}");
            Console.WriteLine("--------------------------------------------------");

            Console.WriteLine("END PREDICT");

            Console.WriteLine("END MAIN FUNCTION");
        }

        #endregion
    }
}

using System;

using System.Globalization;

using System.Threading;

using Microsoft.ML;

namespace TestProject

{

/// <summary>

/// 프로그램

/// </summary>

class Program

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Method

////////////////////////////////////////////////////////////////////////////////////////// Static

//////////////////////////////////////////////////////////////////////////////// Private

#region 프로그램 시작하기 - Main()

/// <summary>

/// 프로그램 시작하기

/// </summary>

private static void Main()

{

Console.WriteLine("BEGIN MAIN FUNCTION");

CultureInfo cultureInfo = new CultureInfo("en-us");

Thread.CurrentThread.CurrentCulture = cultureInfo;

Thread.CurrentThread.CurrentUICulture = cultureInfo;

MLContext context = new MLContext();

Console.WriteLine("BEGIN SET TRAINING DATA VIEW");

HouseData[] trainingArray =

{

new HouseData() { Size = 1.1f, Price = 1.2f },

new HouseData() { Size = 1.9f, Price = 2.3f },

new HouseData() { Size = 2.8f, Price = 3.0f },

new HouseData() { Size = 3.4f, Price = 3.7f }

};

IDataView trainingDataView = context.Data.LoadFromEnumerable(trainingArray);

Console.WriteLine("END SET TRAINING DATA VIEW");

Console.WriteLine("BEGIN SET PIPELINE");

var pipeline = context.Transforms.Concatenate("Features", new[] { "Size" })

.Append(context.Regression.Trainers.Sdca(labelColumnName : "Price", maximumNumberOfIterations : 1000));

Console.WriteLine("END SET PIPELINE");

Console.WriteLine("BEGIN SET MODEL");

var model = pipeline.Fit(trainingDataView);

Console.WriteLine("END SET MODEL");

Console.WriteLine("BEGIN PREDICT");

HouseData houseData = new HouseData() { Size = 2.5f };

Prediction predition = context.Model.CreatePredictionEngine<HouseData, Prediction>(model).Predict(houseData);

Console.WriteLine("--------------------------------------------------");

Console.WriteLine($"SIZE : {houseData.Size * 1000} SQ FT");

Console.WriteLine($"PRICE : {predition.Price * 100000:C}");

Console.WriteLine("--------------------------------------------------");

Console.WriteLine("END PREDICT");

Console.WriteLine("END MAIN FUNCTION");

}

#endregion

}

TestProject.zip