Quick Start

$ ./smile train -h
Usage: smile train [-ehV] -d=<file> [--format=<format>] [--formula=<formula>]
                   [-k=<fold>] -m=<file> [--model-id=<id>]
                   [--model-version=<ver>] [-r=<round>] [-s=<seed>]
                   [--test=<file>] [COMMAND]
Train a supervised learning model.
  -d, --data=<file>         The training data file.
  -e, --ensemble            Create the ensemble of cross validation models.
      --format=<format>     The data file format.
      --formula=<formula>   The model formula <class ~ .>.
  -h, --help                Show this help message and exit.
  -k, --kfold=<fold>        k-fold cross validation.
  -m, --model=<file>        The model file.
      --model-id=<id>       The model id.
      --model-version=<ver> The model version.
  -r, --round=<round>       The number of rounds of repeated cross validation.
  -s, --seed=<seed>         The random number generator seed.
      --test=<file>         The test data file.
  -V, --version             Print version information and exit.
Commands:
  ada-boost         Adaptive Boosting
  cart              Classification and Regression Tree
  elastic-net       Least Absolute Shrinkage and Selection Operator
  fisher            Fisher Linear Discriminant
  gaussian-process  Gaussian Process Regression
  gradient-boost    Gradient Boosting
  lasso             Least Absolute Shrinkage and Selection Operator
  lda               Linear Discriminant Analysis
  logistic          Logistic Regression
  mlp               Multilayer Perceptron
  ols               Ordinary Least Squares
  qda               Quadratic Discriminant Analysis
  random-forest     Random Forest
  rbf               Radial Basis Function Network
  rda               Regularized Discriminant Analysis
  ridge             Ridge Regression
  svm               Support Vector Machine
                

$ ./smile train --data ../data/weka/iris.arff --formula "class ~ ." --model iris_random_forest.sml random-forest
[main] INFO smile.io.Arff - Read ARFF relation iris
[ForkJoinPool.commonPool-worker-3] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 88.89%
[ForkJoinPool.commonPool-worker-2] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 95.35%
[ForkJoinPool.commonPool-worker-1] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 96.67%
...
[main] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 92.73%
[ForkJoinPool.commonPool-worker-3] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 94.44%
[main] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 92.98%
[ForkJoinPool.commonPool-worker-3] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 92.31%
[main] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 95.00%
[ForkJoinPool.commonPool-worker-3] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 96.30%
[main] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 89.47%
[ForkJoinPool.commonPool-worker-3] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 92.98%
[main] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 92.45%
[ForkJoinPool.commonPool-worker-3] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 96.30%
[main] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 89.83%
[ForkJoinPool.commonPool-worker-3] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 90.57%
[main] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 94.64%
[main] INFO smile.classification.RandomForest - Decision tree OOB accuracy: 97.92%
Training metrics: {
  fit time: 191.678 ms,
  score time: 17.059 ms,
  validation data size: 150,
  error: 6,
  accuracy: 96.00%,
  cross entropy: 0.1316
}
  

$ ./smile predict --model iris_random_forest.sml --data ../data/weka/iris.arff --probability
0 0.9601 0.0205 0.0194
0 0.9599 0.0206 0.0195
0 0.9600 0.0206 0.0194
0 0.9600 0.0206 0.0194
0 0.9601 0.0205 0.0194
0 0.9586 0.0211 0.0203
0 0.9601 0.0205 0.0194
0 0.9601 0.0205 0.0194
0 0.9599 0.0206 0.0195
0 0.9600 0.0206 0.0194
0 0.9586 0.0211 0.0203
0 0.9601 0.0205 0.0194
0 0.9599 0.0206 0.0195
0 0.9599 0.0206 0.0195
0 0.9078 0.0668 0.0254
...
  

$ ./smile serve --model iris_random_forest.sml
INFO  [io.quarkus] (main) serve 5.1.0 on JVM (powered by Quarkus 3.30.5) started in 0.844s. Listening on: http://0.0.0.0:8080
[io.quarkus] (main) Profile prod activated.
  

$ curl -X POST http://localhost:8728/v1/infer -H "Content-Type: application/json" \
        -d '{
          "sepallength": 5.1,
          "sepalwidth": 3.5,
          "petallength": 1.4,
          "petalwidth": 0.2
        }'
{"class":0,"probability":[0.9599,0.0207,0.0194]}
  

$ curl -X POST http://localhost:8728/v1/infer -H "Content-Type: application/json" \
        -d '{"sepallength": 5.1, "sepalwidth": 3.5, "petallength": 1.4,"petalwidth": 0.2}
          {"sepallength": 6.3, "sepalwidth": 3.3, "petallength": 6.0,"petalwidth": 2.5}'
{"class":0,"probability":[0.9599,0.0207,0.0194]}
{"class":2,"probability":[0.0259,0.0517,0.9224]}
  

$ for i in {1..1000}; do tail -n 153 ../data/weka/iris.arff | head -n 150 >> iris.txt; done
$ cat iris.txt | curl -H "Content-Type: text/csv" -X POST --data-binary @- http://localhost:8728/v1/infer?format=csv
  

    import $ivy.`com.github.haifengl::smile-scala:5.1.0`

    import scala.language.postfixOps
    import org.apache.commons.csv.CSVFormat
    import smile._
    import smile.util._
    import smile.math._
    import smile.math.MathEx.{log2, logistic, factorial, lfactorial, choose, lchoose, random, randomInt, permutate, c, cbind, rbind, sum, mean, median, q1, q3, `var` => variance, sd, mad, min, max, whichMin, whichMax, unique, dot, distance, pdist, KullbackLeiblerDivergence => kld, JensenShannonDivergence => jsd, cov, cor, spearman, kendall, norm, norm1, norm2, normInf, standardize, normalize, scale, unitize, unitize1, unitize2, root}
    import smile.math.distance._
    import smile.math.kernel._
    import smile.math.matrix._
    import smile.math.matrix.Matrix._
    import smile.math.rbf._
    import smile.stat.distribution._
    import smile.data._
    import smile.data.formula._
    import smile.data.measure._
    import smile.data.`type`._
    import smile.json._
    import smile.interpolation._
    import smile.validation._
    import smile.association._
    import smile.base.cart.SplitRule
    import smile.base.mlp._
    import smile.base.rbf.RBF
    import smile.classification._
    import smile.regression.{ols, ridge, lasso, svr, gpr}
    import smile.feature._
    import smile.clustering._
    import smile.vq._
    import smile.manifold._
    import smile.mds._
    import smile.sequence._
    import smile.projection._
    import smile.nlp._
    import smile.wavelet._
    

    import smile.plot.swing._
    import smile.plot.show
    import smile.plot.Render._
    

    import smile.plot.vega._
    import smile.plot.show
    import smile.plot.Render._
    

    import smile.io.*;
    var weather = Read.arff("../data/weka/weather.nominal.arff");
          

    import org.apache.commons.csv.CSVFormat;

    var format = CSVFormat.DEFAULT.withDelimiter(' ');
    var zipTrain = Read.csv("data/usps/zip.train", format);
    var zipTest = Read.csv("data/usps/zip.test", format);
          

    import smile.classification.*;
    import smile.data.formula.Formula;

    var formula = Formula.lhs("V1");
    
    var prop = new java.util.Properties();
    prop.setProperty("smile.random.forest.trees", "200");
    var forest = RandomForest.fit(formula, zipTrain, prop);
    System.out.println(forest.metrics());
          

    var x = formula.x(zipTrain).toArray();
    var y = formula.y(zipTrain).toIntArray();
    var testx = formula.x(zipTest).toArray();
    var testy = formula.y(zipTest).toIntArray();
          

    import smile.math.kernel.GaussianKernel;
    import smile.validation.*;

    var kernel = new GaussianKernel(8.0);
    var svm = OneVersusOne.fit(x, y, (x, y) -> SVM.fit(x, y, kernel, 5, 1E-3));
    var pred = svm.predict(testx);
    System.out.format("Accuracy = %.2f%%%n", (100.0 * Accuracy.of(testy, pred)));
    System.out.format("Confusion Matrix: %s%n", ConfusionMatrix.of(testy, pred));
          

    import smile.base.mlp.Layer;
    import smile.base.mlp.OutputFunction;
    import smile.classification.MLP;
    import smile.math.MathEx;
    
    var net = new MLP(Layer.input(256),
      Layer.sigmoid(768),
      Layer.sigmoid(192),
      Layer.sigmoid(30),
      Layer.mle(10, OutputFunction.SIGMOID)
    );

    net.setLearningRate(TimeFunction.linear(0.01, 20000, 0.001));
    
    for (int epoch = 0; epoch < 10; epoch++) {
      System.out.format("----- epoch %d -----%n", epoch);
      for (int i : MathEx.permutate(x.length)) {
        net.update(x[i], y[i]);
      }
      var prediction = net.predict(testx);
      System.out.format("Accuracy = %.2f%%%n", (100.0 * Accuracy.of(testy, prediction)));
    }
          

    var posteriori = new double[10];
    forest.predict(zipTest.get(0), posteriori);
    svm.predict(testx[0]);
    net.predict(testx[0], posteriori);