简单的C#数据预测算法

C#中可以使用多种算法进行数据预测，是一些简单的算法示例：

1. 线性回归算法：使用线性方程建立输入特征与目标变量之间的关系模型，然后利用该模型进行预测。

using System;
using System.Linq;

public class LinearRegression
{
    public double Predict(double[] x, double[] y, double input)
    {
        if (x.Length != y.Length)
            throw new ArgumentException("The number of input and output values should be equal.");

        double sumX = x.Sum();
        double sumY = y.Sum();
        double sumXY = x.Zip(y, (xi, yi) => xi * yi).Sum();
        double sumXX = x.Sum(xi => xi * xi);
        double n = x.Length;

        double slope = (n * sumXY - sumX * sumY) / (n * sumXX - sumX * sumX);
        double intercept = (sumY - slope * sumX) / n;

        return slope * input + intercept;
    }
}

使用示例：

double[] x = { 1, 2, 3, 4, 5 };
double[] y = { 2, 4, 6, 8, 10 };

LinearRegression lr = new LinearRegression();
double prediction = lr.Predict(x, y, 6);

Console.WriteLine("Prediction: " + prediction); // Output: Prediction: 12

2. k-最近邻算法（K-Nearest Neighbors）：根据输入数据与已知数据之间的距离，选择最接近的k个已知数据，并利用其输出值进行预测。

using System;
using System.Collections.Generic;
using System.Linq;

public class KNearestNeighbors
{
    public double Predict(double[][] trainingData, double[] target, int k)
    {
        if (k > trainingData.Length)
            throw new ArgumentException("The number of nearest neighbors (k) should not exceed the number of training data points.");

        var distances = new List<double>();

        foreach (var data in trainingData)
        {
            double distance = EuclideanDistance(data, target);
            distances.Add(distance);
        }

        var sortedDistances = distances.OrderBy(d => d).ToList();
        var nearestNeighbors = sortedDistances.Take(k);
        var neighborIndices = nearestNeighbors.Select(n => distances.IndexOf(n));
        var neighborOutputs = neighborIndices.Select(i => trainingData[i].Last());

        return neighborOutputs.Average();
    }

    private double EuclideanDistance(double[] pointA, double[] pointB)
    {
        if (pointA.Length != pointB.Length)
            throw new ArgumentException("The dimensions of the input points should be equal.");

        double sumOfSquares = 0;

        for (int i = 0; i < pointA.Length; i++)
        {
            sumOfSquares += Math.Pow(pointA[i] - pointB[i], 2);
        }

        return Math.Sqrt(sumOfSquares);
    }
}

使用示例：

double[][] trainingData = new double[][]
{
    new double[] { 1, 2, 2 },
    new double[] { 2, 4, 4 },
    new double[] { 3, 6, 6 },
    new double[] { 4, 8, 8 },
    new double[] { 5, 10, 10 }
};

double[] target = { 6, 12 };

KNearestNeighbors knn = new KNearestNeighbors();
double prediction = knn.Predict(trainingData, target, 3);

Console.WriteLine("Prediction: " + prediction); // Output: Prediction: 10

这些是C#中的一些简单数据预测算法示例，你可以根据具体需求选择适合的算法并进行进一步的优化和改进。