Example #1
0
        public void TrainAndTest(IEnumerable <ItemRating> trainSet, IEnumerable <ItemRating> testSet)
        {
            var problem = new SvmProblem()
            {
                X = trainSet.Select(ir => FeatureBuilder.GetSvmNode(ir)).ToArray(),
                Y = trainSet.Select(ir => LabelSelector(ir)).ToArray()
            };


            Parameters.Check(problem);

            Console.WriteLine("Writing training samples...");
            WriteSvmFile(problem, "train.libsvm");

            Console.WriteLine("LibSvm training...");

            LibSvm.SvmModel model = Svm.Train(problem, Parameters);

            var predictedClasses = new List <float>();

            Console.WriteLine("LibSvm testing...");
            foreach (var ir in testSet)
            {
                ir.PredictedRating = (float)model.Predict(FeatureBuilder.GetSvmNode(ir));
                predictedClasses.Add(ir.PredictedRating);
            }

            Console.WriteLine("Writing output...");
            File.WriteAllLines("output.libsvm", predictedClasses.Select(i => i.ToString()));
        }
Example #2
0
        public SvmTracker(SpellFigure figure) : base(0)
        {
            if (_svm == null)
            {
                _svm = new Svm();
            }

            _figure = figure;
        }
Example #3
0
        public static void Run()
        {
            Console.WriteLine("OneClassDemo");
            var trainData = DemoHelper.GenerateClass(0, 0.5, 0.5, 100);

            var parameters = new SvmParameter
            {
                SvmType     = SvmType.ONE_CLASS,
                KernelType  = KernelType.Rbf,
                Gamma       = 0.5,
                Nu          = 0.5,
                CacheSize   = 128,
                Eps         = 1e-3,
                Shrinking   = true,
                Probability = false
            };

            var problem = new SvmProblem
            {
                Y = trainData.Select(p => 1.0).ToArray(),
                X = trainData.Select(p => p.ToSvmNodes()).ToArray()
            };

            parameters.Check(problem);

            var model = Svm.Train(problem, parameters);

            var x    = new Point(0.9, 0.9).ToSvmNodes();
            var resx = model.Predict(x);

            Console.WriteLine(resx);

            var y    = new Point(0.5, 0.5).ToSvmNodes();
            var resy = model.Predict(y);

            Console.WriteLine(resy);

            var z    = new Point(0.45, 0.45).ToSvmNodes();
            var resz = model.Predict(z);

            Console.WriteLine(resz);
        }
Example #4
0
        public IEnumerable <Label> Label(double[] input)
        {
            var labels = Svm
                         .Classify(input)
                         .Select(c => new Label(Labels[c.Number], c.Score));

            foreach (var filter in MangledName.Filters)
            {
                if (filter.IsPercent)
                {
                    labels = labels.Where(l => l.Score >= filter.Value / 100d);
                }
                else
                {
                    labels = labels.Take(filter.Value);
                }
            }

            return(labels);
        }
Example #5
0
        public static void Run()
        {
            Console.WriteLine("EpsSVRDemo");
            var rnd = new Random();

            var trainData = DemoHelper.Range(-10.0, 10.01, 0.1).Select(val => new { X = val, Y = DemoHelper.Sinc(val) + (rnd.NextDouble() - 0.5) / 4 });

            var parameters = new SvmParameter
            {
                SvmType     = SvmType.EPSILON_SVR,
                KernelType  = KernelType.Rbf,
                Gamma       = 0.5,
                CacheSize   = 128,
                C           = 1,
                Eps         = 1e-3,
                P           = 0.1,
                Shrinking   = true,
                Probability = false
            };

            var problem = new SvmProblem
            {
                Y = trainData.Select(p => p.Y).ToArray(),
                X = trainData.Select(p => p.X.ToSvmNodes()).ToArray()
            };

            parameters.Check(problem);

            var model = Svm.Train(problem, parameters);

            foreach (var item in DemoHelper.Range(-1.0, 1.01, 0.1))
            {
                var x     = item.ToSvmNodes();
                var yPred = model.Predict(x);
                var yReal = DemoHelper.Sinc(item);
                Console.WriteLine("x: {0}", item);
                Console.WriteLine("y_real: {0}", yReal);
                Console.WriteLine("y_pred: {0}", yPred);
                Console.WriteLine();
            }
        }
Example #6
0
        public static void Run()
        {
            Console.WriteLine("CSVMDemo");
            var class1 = DemoHelper.GenerateClass(0, 0.1, 0.1, 50);
            var class2 = DemoHelper.GenerateClass(1, 0.8, 0.8, 50);

            var trainData = class1.Concat(class2);

            var parameters = new SvmParameter
            {
                SvmType     = SvmType.C_SVC,
                KernelType  = KernelType.Rbf,
                Gamma       = 0.5,
                CacheSize   = 128,
                C           = 1,
                Eps         = 1e-3,
                Shrinking   = true,
                Probability = false
            };

            var problem = new SvmProblem
            {
                Y = trainData.Select(p => (double)p.Label).ToArray(),
                X = trainData.Select(p => p.ToSvmNodes()).ToArray()
            };

            parameters.Check(problem);

            var model = Svm.Train(problem, parameters);

            var x    = new Point(0.9, 0.9).ToSvmNodes();
            var resx = model.Predict(x);

            Console.WriteLine(resx);

            var y    = new Point(0.1, 0.1).ToSvmNodes();
            var resy = model.Predict(y);

            Console.WriteLine(resy);
        }
Example #7
0
        private static void Main()
        {
            // ランダムにデータを作成
            var       r          = new Random();
            const int trainCount = 500;
            const int testCount  = 100;

            var temp       = Path.GetTempPath();
            var trainDic   = new StringBuilder();
            var testDic    = new StringBuilder();
            var testDicAns = new List <int>();

            for (var l = 0; l < 10; l++)
            {
                for (var i = 0; i < trainCount; i++)
                {
                    // 0 以上 10未満の小数を生成
                    var v = r.NextDouble() + l;
                    trainDic.AppendLine($"{l} 1:{v}");
                }
                for (var i = 0; i < testCount; i++)
                {
                    // 0 以上 10未満の小数を生成
                    var v = r.NextDouble() + l;
                    testDic.AppendLine($"{l} 1:{v}");
                    testDicAns.Add(l);
                }
            }

            var tempTrainPath = Path.Combine(temp, "train");
            var tempTestPath  = Path.Combine(temp, "test");

            using (var fs = new FileStream(tempTrainPath, FileMode.Create, FileAccess.Write, FileShare.Write))
                using (var sw = new StreamWriter(fs, Encoding.ASCII))
                    sw.Write(trainDic.ToString());

            using (var fs = new FileStream(tempTestPath, FileMode.Create, FileAccess.Write, FileShare.Write))
                using (var sw = new StreamWriter(fs, Encoding.ASCII))
                    sw.Write(testDic.ToString());

            // データセットの読み込み
            var train = Svm.ReadProblem(tempTrainPath);
            var test  = Svm.ReadProblem(tempTestPath);

            // パラメータの設定
            var param = new Parameter();

            param.SvmType     = SvmType.C_SVC;
            param.KernelType  = KernelType.RBF;
            param.Gamma       = 0.05d;
            param.C           = 5d;
            param.CacheSize   = 100;
            param.Degree      = 3;
            param.Coef0       = 0;
            param.Nu          = 0.5;
            param.Eps         = 1e-3;
            param.p           = 0.1;
            param.Shrinking   = 1;
            param.Probability = 0;
            param.WeightLabel = new int[0];
            param.Weight      = new double[0];

            var message = Svm.CheckParameter(train, param);

            if (!string.IsNullOrWhiteSpace(message))
            {
                Console.WriteLine($"Error: {message} for train problem");
                return;
            }

            message = Svm.CheckParameter(test, param);
            if (!string.IsNullOrWhiteSpace(message))
            {
                Console.WriteLine($"Error: {message} for test problem");
                return;
            }

            // 学習データとパラメータから学習
            var model = Svm.Train(train, param);

            var correct = 0;
            var total   = 0;

            for (var i = 0; i < test.Count; i++)
            {
                // 学習データのベクトル
                var x = test.x[i];

                // 分類結果 (ラベルが返ってくる)
                var ret1 = (int)Svm.Predict(model, x);
                if (ret1 == testDicAns[i])
                {
                    correct++;
                }

                total++;
            }

            Console.WriteLine($"Accuracy: {correct / (double)total * 100}%");
        }