「トルコのスルタンへの手紙」またはAccord.NETを使用してモスクワのオープンデータを分析するC＃の線形回帰

• “ 大小さまざまなデータをキャッチ！ »-（認知クラスデータサイエンスコースの概要）
• 「 今、彼もあなたを数えています 」またはData Science from Scratch
• “ オスカーの代わりに氷山！ 「または、どのようにしてkaggleでDataScienceの基本を学ぼうとしたのか
• データサイエンスの初心者から見た「できる列車」または「機械学習とデータ分析の専門化」

• 「Rise of the Machines Learning」、またはデータサイエンスの趣味と光スペクトルの分析を組み合わせたもの
• 「メモのように！」またはAccord.NET Frameworkを使用したC＃の機械学習（データサイエンス）
• 「機械学習の力を活用、ルーク！」またはKSSによる照明器具の自動分類
• 「4結婚式と1葬儀」またはモスクワ政府からのオープンデータの分析のための線形回帰

 using System; using System.Linq; using Accord.Statistics.Models.Regression.Linear; using Accord.IO; using Accord.Math; using System.Data; using System.Collections.Generic; using Accord.Controls; using Accord.Math.Optimization.Losses; namespace cs_msc_mayor { class Program { static void Main(string[] args) { //for separating the training and test samples int traintPos = 18; int testPos = 22; int allData = testPos + (testPos - traintPos); //for correct reading symbol of float point in csv System.Globalization.CultureInfo customCulture = (System.Globalization.CultureInfo)System.Threading.Thread.CurrentThread.CurrentCulture.Clone(); customCulture.NumberFormat.NumberDecimalSeparator = "."; System.Threading.Thread.CurrentThread.CurrentCulture = customCulture; //read data string CsvFilePath = @"msc_appel_data.csv"; DataTable mscTable = new CsvReader(CsvFilePath, true).ToTable(); //for encoding the string values of months into numerical values Dictionary<string, double> monthNames = new Dictionary<string, double> { ["January"] = 1, ["February"] = 2, ["March"] = 3, ["April"] = 4, ["May"] = 5, ["June"] = 6, ["July"] = 7, ["August"] = 8, ["September"] = 9, ["October"] = 10, ["November"] = 11, ["December"] = 12 }; string[] months = mscTable.Columns["month"].ToArray<String>(); double[] dMonths= new double[months.Length]; for (int i=0; i< months.Length; i++) { dMonths[i] = monthNames[months[i]]; //Console.WriteLine(dMonths[i]); } //select the target column double[] OutResPositive = mscTable.Columns["res_positive"].ToArray(); // separation of the test and train target sample double[] OutResPositiveTrain = OutResPositive.Get(0, traintPos); double[] OutResPositiveTest = OutResPositive.Get(traintPos, testPos); //deleting unneeded columns mscTable.Columns.Remove("total_appeals"); mscTable.Columns.Remove("month"); mscTable.Columns.Remove("res_positive"); mscTable.Columns.Remove("year"); //add coded in a double column month into Table //create new column DataColumn newCol = new DataColumn("dMonth", typeof(double)); newCol.AllowDBNull = true; // add new column mscTable.Columns.Add(newCol); //fill new column int counter = 0; foreach (DataRow row in mscTable.Rows) { row["dMonth"] = dMonths[counter]; counter++; } //receiving input data from a table double[][] inputs = mscTable.ToArray(); //separation of the test and train sample double[][] inputsTrain= inputs.Get(0, traintPos); double[][] inputsTest = inputs.Get(traintPos, testPos); //simple linear regression model var ols = new OrdinaryLeastSquares() { UseIntercept = true }; //linear regression model for several features MultipleLinearRegression regression = ols.Learn(inputsTrain, OutResPositiveTrain); //make a prediction double[] predicted = regression.Transform(inputsTest); //console output for (int i = 0; i < testPos - traintPos; i++) { Console.WriteLine("predicted: {0} real: {1}", predicted[i], OutResPositiveTest[i]); } // And print the squared error using the SquareLoss class: Console.WriteLine("error = {0}", new SquareLoss(OutResPositiveTest).Loss(predicted)); // print the coefficient of determination double r2 = new RSquaredLoss(numberOfInputs: 29, expected: OutResPositiveTest).Loss(predicted); Console.WriteLine("R^2 = {0}", r2); // alternative print the coefficient of determination double ur2 = regression.CoefficientOfDetermination(inputs, OutResPositiveTest, adjust: true); Console.WriteLine("alternative version of R2 = {0}", r2); Console.WriteLine("Press enter and close chart to exit"); // for chart int[] classes = new int[allData]; double[] mountX = new double[allData]; for (int i = 0; i < allData; i++) { if (i<testPos) { // for csv data mountX[i] = i+1; classes[i] = 0; //csv data is class 0 } else { //for predicted mountX[i] = i- (testPos - traintPos)+1; classes[i] = 1; //predicted is class 1 } } // make points of chart List<double> OutChart = new List<double>(); OutChart.AddRange(OutResPositive); OutChart.AddRange(predicted); // plot chart ScatterplotBox.Show("res_positive from months", mountX, OutChart.ToArray(), classes).Hold(); // for pause Console.ReadLine(); } } } 

 Imports System Imports System.Linq Imports Accord.Statistics.Models.Regression.Linear Imports Accord.IO Imports Accord.Math Imports System.Data Imports System.Collections.Generic Imports Accord.Controls Imports Accord.Math.Optimization.Losses Module Program Sub Main() 'for separating the training and test samples Dim traintPos As Integer = 18 Dim testPos As Integer = 22 Dim allData As Integer = testPos + (testPos - traintPos) 'for correct reading symbol of float point in csv Dim customCulture As System.Globalization.CultureInfo = CType(System.Threading.Thread.CurrentThread.CurrentCulture.Clone(), System.Globalization.CultureInfo) customCulture.NumberFormat.NumberDecimalSeparator = "." System.Threading.Thread.CurrentThread.CurrentCulture = customCulture 'read data Dim CsvFilePath As String = "msc_appel_data.csv" Dim mscTable As DataTable = New CsvReader(CsvFilePath, True).ToTable() 'for encoding the string values of months into numerical values Dim monthNames As Dictionary(Of String, Double) = New Dictionary(Of String, Double) From {{"January", 1}, {"February", 2}, {"March", 3}, {"April", 4}, {"May", 5}, {"June", 6}, {"July", 7}, {"August", 8}, {"September", 9}, {"October", 10}, {"November", 11}, {"December", 12}} Dim months As String() = mscTable.Columns("month").ToArray(Of String)() Dim dMonths As Double() = New Double(months.Length - 1) {} For i As Integer = 0 To months.Length - 1 dMonths(i) = monthNames(months(i)) Next 'select the target column Dim OutResPositive As Double() = mscTable.Columns("res_positive").ToArray() 'separation of the test and train target sample Dim OutResPositiveTrain As Double() = OutResPositive.[Get](0, traintPos) Dim OutResPositiveTest As Double() = OutResPositive.[Get](traintPos, testPos) 'deleting unneeded columns mscTable.Columns.Remove("total_appeals") mscTable.Columns.Remove("month") mscTable.Columns.Remove("res_positive") mscTable.Columns.Remove("year") 'add coded in a double column month into Table 'create new column Dim newCol As DataColumn = New DataColumn("dMonth", GetType(Double)) newCol.AllowDBNull = True 'add new column mscTable.Columns.Add(newCol) 'fill new column Dim counter As Integer = 0 For Each row As DataRow In mscTable.Rows row("dMonth") = dMonths(counter) counter += 1 Next 'receiving input data from a table Dim inputs As Double()() = mscTable.ToArray() 'separation of the test and train sample Dim inputsTrain As Double()() = inputs.[Get](0, traintPos) Dim inputsTest As Double()() = inputs.[Get](traintPos, testPos) 'simple linear regression model Dim ols = New OrdinaryLeastSquares() With {.UseIntercept = True} 'linear regression model for several features Dim regression As MultipleLinearRegression = ols.Learn(inputsTrain, OutResPositiveTrain) 'make a prediction Dim predicted As Double() = regression.Transform(inputsTest) 'console output For i As Integer = 0 To testPos - traintPos - 1 Console.WriteLine("predicted: {0} real: {1}", predicted(i), OutResPositiveTest(i)) Next 'And print the squared error using the SquareLoss class Console.WriteLine("error = {0}", New SquareLoss(OutResPositiveTest).Loss(predicted)) 'print the coefficient of determination Dim r2 As Double = New RSquaredLoss(numberOfInputs:=29, expected:=OutResPositiveTest).Loss(predicted) Console.WriteLine("R^2 = {0}", r2) 'alternative print the coefficient of determination Dim ur2 As Double = regression.CoefficientOfDetermination(inputs, OutResPositiveTest, adjust:=True) Console.WriteLine("alternative version of R2 = {0}", r2) Console.WriteLine("Press enter and close chart to exit") 'for chart Dim classes As Integer() = New Integer(allData - 1) {} Dim mountX As Double() = New Double(allData - 1) {} For i As Integer = 0 To allData - 1 If i < testPos Then mountX(i) = i + 1 classes(i) = 0 'csv data is class 0 Else mountX(i) = i - (testPos - traintPos) + 1 classes(i) = 1 'predicted is class 1 End If Next 'make points of chart Dim OutChart As List(Of Double) = New List(Of Double)() OutChart.AddRange(OutResPositive) OutChart.AddRange(predicted) 'plot chart ScatterplotBox.Show("res_positive from months", mountX, OutChart.ToArray(), classes).Hold() 'for pause Console.ReadLine() End Sub End Module