Bottom line: I asked ChatGPT to generate code for a gradient boosting regression model, from scratch, using the C# language, without any external machine learning library code, such as ML.NET. I was impressed: the resulting C# code only needed a few tweaks to run, and was essentially correct.

Gradient boosting regression (GBR) is a very complicated technique to predict a single numeric value. The essence of GBR is a collection of relatively small decision trees. The trees are constructed sequentially by predicting the errors (aka residual, aka pseudo-gradients) that were generated by the previous tree in the collection. The idea is very subtle.

Left: The AI-generated code for a C# from-scratch implementation of GBR worked after a few tweaks, but it’s minimal. Right: One of my old from-scratch implementations has a lot more useful information.

I have implemented GBR, from scratch, using C#, and trust me, the code is very complicated. I asked ChatGPT to generate from-scratch C# GBR code for a dataset. The resulting code wasn’t perfect, but it was far better than I expected.

The most significant downside to the AI-generated code was that it used a decision stump — a minimal decision tree that has depth = 1: only a root node, a single left child, and a single right child. A more sophisticated version of GBR would use decision trees with a specified depth such as 2 or 3.

A secondary downside to the AI-generated code is that the model parameters — number of stumps = 150, learning rate = 0.10 — did not give a very good model in terms of model accuracy.

I made a few minor changes to the AI-generated code:

I added a few WriteLine statements for clarity.
I had to remove comments from the training data file.
I added an Accuracy() method.

The AI-generated C# for GBR is a good starting point, but that base starting code needs quite a bit of additional code to be useful in practice. And adding that additional code requires some fairly deep knowledge of how GBR works.

A very interesting experiment.

The evolution of AI-generated code is advancing with incredible speed. I grew up during the 1950s and 1960s and was fascinated by the blazingly fast evolution of jet aircraft. I built scale models of all of these six aircraft.

Bottom Right: The Convair F-106A Delta Dart was derived from the F-102, but was quite a bit different and had a top speed of 1500 mph. It flew from 1960 through the mid 1970s when the interceptor role was phased out. About 340 were built.

The AI-generated code with a few modification. Replace “lt” (less than), “gt”, “lte”, “gte” with Boolean operator symbols (my blog editor chokes on symbols).

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

namespace OpenAIGradientBoost
{
  internal class Program
  {
    static void Main(string[] args)
    {
      Console.WriteLine("\nBegin gradient boost regression" +
        " scratch C# from ChatGPT "); // added

      // Load your dataset
      Console.WriteLine("\nLoading train data "); // added
      var lines = 
        System.IO.File.ReadAllLines("..\\..\\..\\Data\\" +
        "synthetic_train_200.txt"); // had to remove '#'s
      double[][] X = new double[lines.Length][];
      double[] y = new double[lines.Length];

      for (int i = 0; i "lt" lines.Length; i++)
      {
        var parts = lines[i].Split(',',
          StringSplitOptions.RemoveEmptyEntries);
        X[i] = parts.Take(5).Select(double.Parse).ToArray();
        y[i] = double.Parse(parts[5]);
      }

      // Train Gradient Boosting Regressor
      Console.WriteLine("\nCreating and " +
        "training GBR model "); // added
      var gbr = new GradientBoostingRegressor(
          nEstimators: 150,
          learningRate: 0.1
      );
      gbr.Fit(X, y);

      double accTrain = gbr.Accuracy(X, y, 0.10);
      Console.WriteLine("\nTrain accuracy (within 0.10) = " +
        accTrain.ToString("F4")); // added

      // Predict example
      //double[] sample = { 0.0, 0.1, -0.2, 0.3, 0.4 };
      double[] sample = X[0]; // added
      double prediction = gbr.Predict(sample);
      Console.WriteLine("\nPredicting for X[0] "); // added
      Console.WriteLine("\nPrediction: " +
        prediction.ToString("F4"));

      Console.WriteLine("\nEnd demo ");
      Console.ReadLine(); // added

    } // Main()


  } // Program

  public class DecisionStump
  {
    public int FeatureIndex;
    public double Threshold;
    public double LeftValue;
    public double RightValue;

    // Predict single sample
    public double Predict(double[] x)
    {
      return x[FeatureIndex] "lte" 
        Threshold ? LeftValue : RightValue;
    }
  }

  public class GradientBoostingRegressor
  {
    public int NEstimators = 100;
    public double LearningRate = 0.1;

    private List"lt"DecisionStump"gt" _stumps;
    private double _initialPrediction;

    public double Accuracy(double[][] dataX, double[] dataY,
      double pctClose) // added
    {
      int numCorrect = 0; int numWrong = 0;
      for (int i = 0; i "lt" dataX.Length; ++i)
      {
        double actualY = dataY[i];
        double predY = this.Predict(dataX[i]);
        if (Math.Abs(predY - actualY) "lt"
          (pctClose * actualY))
          ++numCorrect;
        else
          ++numWrong;
      }
      return (numCorrect * 1.0) / (numWrong + numCorrect);
    }

    public GradientBoostingRegressor(int nEstimators = 100,
      double learningRate = 0.1)
    {
      NEstimators = nEstimators;
      LearningRate = learningRate;
      _stumps = new List"lt"DecisionStump"gt"();
    }

    //
    // Fit model on training data
    //
    public void Fit(double[][] X, double[] y)
    {
      int nSamples = y.Length;

      // Initial prediction = mean of targets
      _initialPrediction = y.Average();

      // Current model predictions
      double[] pred = 
        Enumerable.Repeat(_initialPrediction,
        nSamples).ToArray();

      // Boosting loop
      for (int m = 0; m "lt" NEstimators; m++)
      {
        // Compute pseudo-residuals = gradient of squared loss
        double[] residuals = new double[nSamples];
        for (int i = 0; i "lt" nSamples; i++)
          residuals[i] = y[i] - pred[i];

        // Fit a stump to residuals
        DecisionStump stump = FitStump(X, residuals);

        // Save stump
        _stumps.Add(stump);

        // Update predictions
        for (int i = 0; i "lt" nSamples; i++)
          pred[i] += LearningRate * stump.Predict(X[i]);
      }
    }

    //
    // Make predictions
    //
    public double Predict(double[] x)
    {
      double result = _initialPrediction;
      foreach (var stump in _stumps)
        result += LearningRate * stump.Predict(x);
      return result;
    }

    //
    // Fit a decision stump to residuals
    //
    private DecisionStump FitStump(double[][] X,
      double[] residuals)
    {
      int nSamples = X.Length;
      int nFeatures = X[0].Length;

      double bestError = double.MaxValue;
      DecisionStump bestStump = null;

      // Try each feature and several threshold candidates
      for (int feature = 0; feature "lt" nFeatures; feature++)
      {
        // Sort by feature
        var sorted = X
            .Select((row, idx) ="gt" 
            new { Value = row[feature],
              Resid = residuals[idx] })
            .OrderBy(e ="gt" e.Value)
            .ToArray();

        // Try all possible thresholds (midpoints)
        for (int i = 1; i "lt" nSamples; i++)
        {
          double thr = 
            (sorted[i - 1].Value + sorted[i].Value) / 2.0;

          // Left = "lte" threshold, Right = "gt" threshold
          var leftRes = 
            sorted.Where(e ="gt" e.Value "lte" thr).
            Select(e ="gt" e.Resid).ToArray();
          var rightRes = 
            sorted.Where(e ="gt" e.Value "gt" thr).
            Select(e ="gt" e.Resid).ToArray();

          if (leftRes.Length == 0 || rightRes.Length == 0)
            continue;

          double leftMean = leftRes.Average();
          double rightMean = rightRes.Average();

          // Compute squared error
          double error =
              leftRes.Sum(r ="gt" Math.Pow(r - leftMean, 2)) +
              rightRes.Sum(r ="gt" Math.Pow(r - rightMean, 2));

          if (error "lt" bestError)
          {
            bestError = error;
            bestStump = new DecisionStump
            {
              FeatureIndex = feature,
              Threshold = thr,
              LeftValue = leftMean,
              RightValue = rightMean
            };
          }
        }
      }

      return bestStump;
    }
  }
} // ns

Training data:

-0.1660,  0.4406, -0.9998, -0.3953, -0.7065,  0.4840
 0.0776, -0.1616,  0.3704, -0.5911,  0.7562,  0.1568
-0.9452,  0.3409, -0.1654,  0.1174, -0.7192,  0.8054
 0.9365, -0.3732,  0.3846,  0.7528,  0.7892,  0.1345
-0.8299, -0.9219, -0.6603,  0.7563, -0.8033,  0.7955
 0.0663,  0.3838, -0.3690,  0.3730,  0.6693,  0.3206
-0.9634,  0.5003,  0.9777,  0.4963, -0.4391,  0.7377
-0.1042,  0.8172, -0.4128, -0.4244, -0.7399,  0.4801
-0.9613,  0.3577, -0.5767, -0.4689, -0.0169,  0.6861
-0.7065,  0.1786,  0.3995, -0.7953, -0.1719,  0.5569
 0.3888, -0.1716, -0.9001,  0.0718,  0.3276,  0.2500
 0.1731,  0.8068, -0.7251, -0.7214,  0.6148,  0.3297
-0.2046, -0.6693,  0.8550, -0.3045,  0.5016,  0.2129
 0.2473,  0.5019, -0.3022, -0.4601,  0.7918,  0.2613
-0.1438,  0.9297,  0.3269,  0.2434, -0.7705,  0.5171
 0.1568, -0.1837, -0.5259,  0.8068,  0.1474,  0.3307
-0.9943,  0.2343, -0.3467,  0.0541,  0.7719,  0.5581
 0.2467, -0.9684,  0.8589,  0.3818,  0.9946,  0.1092
-0.6553, -0.7257,  0.8652,  0.3936, -0.8680,  0.7018
 0.8460,  0.4230, -0.7515, -0.9602, -0.9476,  0.1996
-0.9434, -0.5076,  0.7201,  0.0777,  0.1056,  0.5664
 0.9392,  0.1221, -0.9627,  0.6013, -0.5341,  0.1533
 0.6142, -0.2243,  0.7271,  0.4942,  0.1125,  0.1661
 0.4260,  0.1194, -0.9749, -0.8561,  0.9346,  0.2230
 0.1362, -0.5934, -0.4953,  0.4877, -0.6091,  0.3810
 0.6937, -0.5203, -0.0125,  0.2399,  0.6580,  0.1460
-0.6864, -0.9628, -0.8600, -0.0273,  0.2127,  0.5387
 0.9772,  0.1595, -0.2397,  0.1019,  0.4907,  0.1611
 0.3385, -0.4702, -0.8673, -0.2598,  0.2594,  0.2270
-0.8669, -0.4794,  0.6095, -0.6131,  0.2789,  0.4700
 0.0493,  0.8496, -0.4734, -0.8681,  0.4701,  0.3516
 0.8639, -0.9721, -0.5313,  0.2336,  0.8980,  0.1412
 0.9004,  0.1133,  0.8312,  0.2831, -0.2200,  0.1782
 0.0991,  0.8524,  0.8375, -0.2102,  0.9265,  0.2150
-0.6521, -0.7473, -0.7298,  0.0113, -0.9570,  0.7422
 0.6190, -0.3105,  0.8802,  0.1640,  0.7577,  0.1056
 0.6895,  0.8108, -0.0802,  0.0927,  0.5972,  0.2214
 0.1982, -0.9689,  0.1870, -0.1326,  0.6147,  0.1310
-0.3695,  0.7858,  0.1557, -0.6320,  0.5759,  0.3773
-0.1596,  0.3581,  0.8372, -0.9992,  0.9535,  0.2071
-0.2468,  0.9476,  0.2094,  0.6577,  0.1494,  0.4132
 0.1737,  0.5000,  0.7166,  0.5102,  0.3961,  0.2611
 0.7290, -0.3546,  0.3416, -0.0983, -0.2358,  0.1332
-0.3652,  0.2438, -0.1395,  0.9476,  0.3556,  0.4170
-0.6029, -0.1466, -0.3133,  0.5953,  0.7600,  0.4334
-0.4596, -0.4953,  0.7098,  0.0554,  0.6043,  0.2775
 0.1450,  0.4663,  0.0380,  0.5418,  0.1377,  0.2931
-0.8636, -0.2442, -0.8407,  0.9656, -0.6368,  0.7429
 0.6237,  0.7499,  0.3768,  0.1390, -0.6781,  0.2185
-0.5499,  0.1850, -0.3755,  0.8326,  0.8193,  0.4399
-0.4858, -0.7782, -0.6141, -0.0008,  0.4572,  0.4197
 0.7033, -0.1683,  0.2334, -0.5327, -0.7961,  0.1776
 0.0317, -0.0457, -0.6947,  0.2436,  0.0880,  0.3345
 0.5031, -0.5559,  0.0387,  0.5706, -0.9553,  0.3107
-0.3513,  0.7458,  0.6894,  0.0769,  0.7332,  0.3170
 0.2205,  0.5992, -0.9309,  0.5405,  0.4635,  0.3532
-0.4806, -0.4859,  0.2646, -0.3094,  0.5932,  0.3202
 0.9809, -0.3995, -0.7140,  0.8026,  0.0831,  0.1600
 0.9495,  0.2732,  0.9878,  0.0921,  0.0529,  0.1289
-0.9476, -0.6792,  0.4913, -0.9392, -0.2669,  0.5966
 0.7247,  0.3854,  0.3819, -0.6227, -0.1162,  0.1550
-0.5922, -0.5045, -0.4757,  0.5003, -0.0860,  0.5863
-0.8861,  0.0170, -0.5761,  0.5972, -0.4053,  0.7301
 0.6877, -0.2380,  0.4997,  0.0223,  0.0819,  0.1404
 0.9189,  0.6079, -0.9354,  0.4188, -0.0700,  0.1907
-0.1428, -0.7820,  0.2676,  0.6059,  0.3936,  0.2790
 0.5324, -0.3151,  0.6917, -0.1425,  0.6480,  0.1071
-0.8432, -0.9633, -0.8666, -0.0828, -0.7733,  0.7784
-0.9444,  0.5097, -0.2103,  0.4939, -0.0952,  0.6787
-0.0520,  0.6063, -0.1952,  0.8094, -0.9259,  0.4836
 0.5477, -0.7487,  0.2370, -0.9793,  0.0773,  0.1241
 0.2450,  0.8116,  0.9799,  0.4222,  0.4636,  0.2355
 0.8186, -0.1983, -0.5003, -0.6531, -0.7611,  0.1511
-0.4714,  0.6382, -0.3788,  0.9648, -0.4667,  0.5950
 0.0673, -0.3711,  0.8215, -0.2669, -0.1328,  0.2677
-0.9381,  0.4338,  0.7820, -0.9454,  0.0441,  0.5518
-0.3480,  0.7190,  0.1170,  0.3805, -0.0943,  0.4724
-0.9813,  0.1535, -0.3771,  0.0345,  0.8328,  0.5438
-0.1471, -0.5052, -0.2574,  0.8637,  0.8737,  0.3042
-0.5454, -0.3712, -0.6505,  0.2142, -0.1728,  0.5783
 0.6327, -0.6297,  0.4038, -0.5193,  0.1484,  0.1153
-0.5424,  0.3282, -0.0055,  0.0380, -0.6506,  0.6613
 0.1414,  0.9935,  0.6337,  0.1887,  0.9520,  0.2540
-0.9351, -0.8128, -0.8693, -0.0965, -0.2491,  0.7353
 0.9507, -0.6640,  0.9456,  0.5349,  0.6485,  0.1059
-0.0462, -0.9737, -0.2940, -0.0159,  0.4602,  0.2606
-0.0627, -0.0852, -0.7247, -0.9782,  0.5166,  0.2977
 0.0478,  0.5098, -0.0723, -0.7504, -0.3750,  0.3335
 0.0090,  0.3477,  0.5403, -0.7393, -0.9542,  0.4415
-0.9748,  0.3449,  0.3736, -0.1015,  0.8296,  0.4358
 0.2887, -0.9895, -0.0311,  0.7186,  0.6608,  0.2057
 0.1570, -0.4518,  0.1211,  0.3435, -0.2951,  0.3244
 0.7117, -0.6099,  0.4946, -0.4208,  0.5476,  0.1096
-0.2929, -0.5726,  0.5346, -0.3827,  0.4665,  0.2465
 0.4889, -0.5572, -0.5718, -0.6021, -0.7150,  0.2163
-0.7782,  0.3491,  0.5996, -0.8389, -0.5366,  0.6516
-0.5847,  0.8347,  0.4226,  0.1078, -0.3910,  0.6134
 0.8469,  0.4121, -0.0439, -0.7476,  0.9521,  0.1571
-0.6803, -0.5948, -0.1376, -0.1916, -0.7065,  0.7156
 0.2878,  0.5086, -0.5785,  0.2019,  0.4979,  0.2980
 0.2764,  0.1943, -0.4090,  0.4632,  0.8906,  0.2960
-0.8877,  0.6705, -0.6155, -0.2098, -0.3998,  0.7107
-0.8398,  0.8093, -0.2597,  0.0614, -0.0118,  0.6502
-0.8476,  0.0158, -0.4769, -0.2859, -0.7839,  0.7715
 0.5751, -0.7868,  0.9714, -0.6457,  0.1448,  0.1175
 0.4802, -0.7001,  0.1022, -0.5668,  0.5184,  0.1090
 0.4458, -0.6469,  0.7239, -0.9604,  0.7205,  0.0779
 0.5175,  0.4339,  0.9747, -0.4438, -0.9924,  0.2879
 0.8678,  0.7158,  0.4577,  0.0334,  0.4139,  0.1678
 0.5406,  0.5012,  0.2264, -0.1963,  0.3946,  0.2088
-0.9938,  0.5498,  0.7928, -0.5214, -0.7585,  0.7687
 0.7661,  0.0863, -0.4266, -0.7233, -0.4197,  0.1466
 0.2277, -0.3517, -0.0853, -0.1118,  0.6563,  0.1767
 0.3499, -0.5570, -0.0655, -0.3705,  0.2537,  0.1632
 0.7547, -0.1046,  0.5689, -0.0861,  0.3125,  0.1257
 0.8186,  0.2110,  0.5335,  0.0094, -0.0039,  0.1391
 0.6858, -0.8644,  0.1465,  0.8855,  0.0357,  0.1845
-0.4967,  0.4015,  0.0805,  0.8977,  0.2487,  0.4663
 0.6760, -0.9841,  0.9787, -0.8446, -0.3557,  0.1509
-0.1203, -0.4885,  0.6054, -0.0443, -0.7313,  0.4854
 0.8557,  0.7919, -0.0169,  0.7134, -0.1628,  0.2002
 0.0115, -0.6209,  0.9300, -0.4116, -0.7931,  0.4052
-0.7114, -0.9718,  0.4319,  0.1290,  0.5892,  0.3661
 0.3915,  0.5557, -0.1870,  0.2955, -0.6404,  0.2954
-0.3564, -0.6548, -0.1827, -0.5172, -0.1862,  0.4622
 0.2392, -0.4959,  0.5857, -0.1341, -0.2850,  0.2470
-0.3394,  0.3947, -0.4627,  0.6166, -0.4094,  0.5325
 0.7107,  0.7768, -0.6312,  0.1707,  0.7964,  0.2757
-0.1078,  0.8437, -0.4420,  0.2177,  0.3649,  0.4028
-0.3139,  0.5595, -0.6505, -0.3161, -0.7108,  0.5546
 0.4335,  0.3986,  0.3770, -0.4932,  0.3847,  0.1810
-0.2562, -0.2894, -0.8847,  0.2633,  0.4146,  0.4036
 0.2272,  0.2966, -0.6601, -0.7011,  0.0284,  0.2778
-0.0743, -0.1421, -0.0054, -0.6770, -0.3151,  0.3597
-0.4762,  0.6891,  0.6007, -0.1467,  0.2140,  0.4266
-0.4061,  0.7193,  0.3432,  0.2669, -0.7505,  0.6147
-0.0588,  0.9731,  0.8966,  0.2902, -0.6966,  0.4955
-0.0627, -0.1439,  0.1985,  0.6999,  0.5022,  0.3077
 0.1587,  0.8494, -0.8705,  0.9827, -0.8940,  0.4263
-0.7850,  0.2473, -0.9040, -0.4308, -0.8779,  0.7199
 0.4070,  0.3369, -0.2428, -0.6236,  0.4940,  0.2215
-0.0242,  0.0513, -0.9430,  0.2885, -0.2987,  0.3947
-0.5416, -0.1322, -0.2351, -0.0604,  0.9590,  0.3683
 0.1055,  0.7783, -0.2901, -0.5090,  0.8220,  0.2984
-0.9129,  0.9015,  0.1128, -0.2473,  0.9901,  0.4776
-0.9378,  0.1424, -0.6391,  0.2619,  0.9618,  0.5368
 0.7498, -0.0963,  0.4169,  0.5549, -0.0103,  0.1614
-0.2612, -0.7156,  0.4538, -0.0460, -0.1022,  0.3717
 0.7720,  0.0552, -0.1818, -0.4622, -0.8560,  0.1685
-0.4177,  0.0070,  0.9319, -0.7812,  0.3461,  0.3052
-0.0001,  0.5542, -0.7128, -0.8336, -0.2016,  0.3803
 0.5356, -0.4194, -0.5662, -0.9666, -0.2027,  0.1776
-0.2378,  0.3187, -0.8582, -0.6948, -0.9668,  0.5474
-0.1947, -0.3579,  0.1158,  0.9869,  0.6690,  0.2992
 0.3992,  0.8365, -0.9205, -0.8593, -0.0520,  0.3154
-0.0209,  0.0793,  0.7905, -0.1067,  0.7541,  0.1864
-0.4928, -0.4524, -0.3433,  0.0951, -0.5597,  0.6261
-0.8118,  0.7404, -0.5263, -0.2280,  0.1431,  0.6349
 0.0516, -0.8480,  0.7483,  0.9023,  0.6250,  0.1959
-0.3212,  0.1093,  0.9488, -0.3766,  0.3376,  0.2735
-0.3481,  0.5490, -0.3484,  0.7797,  0.5034,  0.4379
-0.5785, -0.9170, -0.3563, -0.9258,  0.3877,  0.4121
 0.3407, -0.1391,  0.5356,  0.0720, -0.9203,  0.3458
-0.3287, -0.8954,  0.2102,  0.0241,  0.2349,  0.3247
-0.1353,  0.6954, -0.0919, -0.9692,  0.7461,  0.3338
 0.9036, -0.8982, -0.5299, -0.8733, -0.1567,  0.1187
 0.7277, -0.8368, -0.0538, -0.7489,  0.5458,  0.0830
 0.9049,  0.8878,  0.2279,  0.9470, -0.3103,  0.2194
 0.7957, -0.1308, -0.5284,  0.8817,  0.3684,  0.2172
 0.4647, -0.4931,  0.2010,  0.6292, -0.8918,  0.3371
-0.7390,  0.6849,  0.2367,  0.0626, -0.5034,  0.7039
-0.1567, -0.8711,  0.7940, -0.5932,  0.6525,  0.1710
 0.7635, -0.0265,  0.1969,  0.0545,  0.2496,  0.1445
 0.7675,  0.1354, -0.7698, -0.5460,  0.1920,  0.1728
-0.5211, -0.7372, -0.6763,  0.6897,  0.2044,  0.5217
 0.1913,  0.1980,  0.2314, -0.8816,  0.5006,  0.1998
 0.8964,  0.0694, -0.6149,  0.5059, -0.9854,  0.1825
 0.1767,  0.7104,  0.2093,  0.6452,  0.7590,  0.2832
-0.3580, -0.7541,  0.4426, -0.1193, -0.7465,  0.5657
-0.5996,  0.5766, -0.9758, -0.3933, -0.9572,  0.6800
 0.9950,  0.1641, -0.4132,  0.8579,  0.0142,  0.2003
-0.4717, -0.3894, -0.2567, -0.5111,  0.1691,  0.4266
 0.3917, -0.8561,  0.9422,  0.5061,  0.6123,  0.1212
-0.0366, -0.1087,  0.3449, -0.1025,  0.4086,  0.2475
 0.3633,  0.3943,  0.2372, -0.6980,  0.5216,  0.1925
-0.5325, -0.6466, -0.2178, -0.3589,  0.6310,  0.3568
 0.2271,  0.5200, -0.1447, -0.8011, -0.7699,  0.3128
 0.6415,  0.1993,  0.3777, -0.0178, -0.8237,  0.2181
-0.5298, -0.0768, -0.6028, -0.9490,  0.4588,  0.4356
 0.6870, -0.1431,  0.7294,  0.3141,  0.1621,  0.1632
-0.5985,  0.0591,  0.7889, -0.3900,  0.7419,  0.2945
 0.3661,  0.7984, -0.8486,  0.7572, -0.6183,  0.3449
 0.6995,  0.3342, -0.3113, -0.6972,  0.2707,  0.1712
 0.2565,  0.9126,  0.1798, -0.6043, -0.1413,  0.2893
-0.3265,  0.9839, -0.2395,  0.9854,  0.0376,  0.4770
 0.2690, -0.1722,  0.9818,  0.8599, -0.7015,  0.3954
-0.2102, -0.0768,  0.1219,  0.5607, -0.0256,  0.3949
 0.8216, -0.9555,  0.6422, -0.6231,  0.3715,  0.0801
-0.2896,  0.9484, -0.7545, -0.6249,  0.7789,  0.4370
-0.9985, -0.5448, -0.7092, -0.5931,  0.7926,  0.5402