public void RunOnlineKEPSampling()
{
// Kernel EP with importance sampling.
/**
* Only one W just like in Ali's paper.
* In practice, we typically observe multiple sets of observations
* where we want to do inference on the same model with the same
* parameter.
*/
Rand.Restart(init_fixed_seed);
Vector w = Vector.Zero(d);
Rand.Normal(Vector.Zero(d), PositiveDefiniteMatrix.Identity(d), w);
List <LogisticOpRecords> allRecs = new List <LogisticOpRecords>();
// Create the Logistic operator instance only one because we want to use the same
// one after a new problem (new seed).
// stopwatch for measuring inference time for each problem
Stopwatch watch = new Stopwatch();
var logisticOpIns = new KEPOnlineISLogisticOpIns(
new LogisticOpRecords(), watch, -8.5);
logisticOpIns.SetImportanceSamplingSize(importanceSamplingSize);
logisticOpIns.IsRecordMessages = true;
logisticOpIns.IsPrintTrueWhenCertain = false;
/** Use mixture or not ...*/
logisticOpIns.isGaussianOp.useMixtureProposal = false;
logisticOpIns.SetFeatures(new int[] { 300, 500 });
OpControl.Set(typeof(KEPOnlineLogisticOp), logisticOpIns);
Type logisticOp = typeof(KEPOnlineLogisticOp);
List <long> allInferTimes = new List <long>();
var allPosteriors = new List <VectorGaussian>();
var allDotNetPosteriors = new List <VectorGaussian>();
LogisticOp2.IsCollectLogisticMessages = false;
LogisticOp2.IsCollectProjMsgs = false;
LogisticOp2.IsCollectXMessages = false;
for (int seed = seed_from; seed <= seed_to; seed++)
{
Rand.Restart(seed);
double b = 0;
// combine the bias term into W
Vector[] X;
bool[] Y;
LogisticRegression.GenData(n, w, b, out X, out Y, seed);
Console.Write("Y: ");
StringUtils.PrintArray(Y);
VectorGaussian wPost;
LogisticOpRecords recorder = new LogisticOpRecords();
// Set a new recorder for a new problem seed
logisticOpIns.SetRecorder(recorder);
// Type logisticOp = typeof(LogisticOp2);
// start the watch
watch.Restart();
LogisticRegression.InferCoefficientsNoBias(X, Y, out wPost, epIter, logisticOp);
// stop the watch
long inferenceTime = watch.ElapsedMilliseconds;
recorder.inferenceTimes = new List <long>();
recorder.inferenceTimes.Add(inferenceTime);
allInferTimes.Add(inferenceTime);
recorder.postW = MatrixUtils.ToList(wPost);
allPosteriors.Add(wPost);
allRecs.Add(recorder);
//print
Console.WriteLine("n: {0}", n);
Console.WriteLine("d: {0}", d);
int t = Y.Sum(o => o ? 1 : 0);
Console.WriteLine("number of true: {0}", t);
Console.WriteLine("True bias: {0}", b);
// Vector meanW = wPost.GetMean();
Console.WriteLine("True w: {0}", w);
Console.WriteLine("Inferred w: ");
Console.WriteLine(wPost);
// Run Infer.net's operator on the same data
VectorGaussian dotNetPostW;
LogisticRegression.InferCoefficientsNoBias(X, Y, out dotNetPostW,
epIter, typeof(LogisticOp2));
recorder.dotNetPostW = MatrixUtils.ToList <VectorGaussian>(dotNetPostW);
allDotNetPosteriors.Add(dotNetPostW);
// write the records to a file
string fname = string.Format("rec_onlinekep_is{0}_n{1}_logistic_iter{2}_s{3}.mat",
importanceSamplingSize, n, epIter, seed);
string recordPath = Config.PathToSavedFile(fname);
var extra = new Dictionary <string, object>();
// MatlabWriter cannot write int
extra.Add("d", (double)d);
extra.Add("n", (double)n);
extra.Add("epIter", (double)epIter);
extra.Add("trueW", w);
extra.Add("X", MatrixUtils.StackColumns(X));
extra.Add("Y", MatrixUtils.ToDouble(Y));
recorder.WriteRecords(recordPath, extra);
}
// merge all records and write
LogisticOpRecords merged = LogisticOpRecords.Merge(allRecs.ToArray());
merged.inferenceTimes = allInferTimes;
merged.dotNetPostW = allDotNetPosteriors;
merged.postW = allPosteriors;
string fnameM = string.Format("rec_onlinekep_is{0}_n{1}_logistic_iter{2}_sf{3}_st{4}.mat",
importanceSamplingSize, n, epIter, seed_from, seed_to);
string recordPathM = Config.PathToSavedFile(fnameM);
merged.WriteRecords(recordPathM);
}
public static void CollectMessages()
{
// collect all incoming/outgoing messages from a logistic factor
// to its argument x (as in logis = logistic(x) )
// in a binary logistic regression model.
const int seed_from = 1;
const int seed_to = 20;
const int d = 10;
const int n = 400;
const int epIter = 5;
// true => collect proj messages instead of outgoing messages
const bool collectProj = false;
const string targetAnnotate = collectProj ? "_proj" : "";
LogisticOp2.IsCollectProjMsgs = collectProj;
LogisticOp2.IsCollectLogisticMessages = true;
LogisticOp2.IsCollectXMessages = true;
var allToXMsgs = new List <Tuple <Gaussian, Gaussian, Beta> >();
var allToLogisticMsgs = new List <Tuple <Beta, Gaussian, Beta> >();
for (int seed = seed_from; seed <= seed_to; seed++)
{
Vector w;
double b;
Vector[] X;
bool[] Y;
Rand.Restart(seed);
w = Vector.Zero(d);
Rand.Normal(Vector.Zero(d), PositiveDefiniteMatrix.Identity(d), w);
// b = Rand.Normal(0, 1);
b = 0;
LogisticRegression.GenData(n, w, b, out X, out Y);
Console.Write("Y: ");
StringUtils.PrintArray(Y);
VectorGaussian wPost;
Gaussian biasPost;
LogisticOp2.ResetMessageCollection();
// LogisticRegression.InferCoefficients(X, Y, out wPost,
// out biasPost, epIter, typeof(LogisticOp2));
LogisticRegression.InferCoefficientsNoBias(X, Y, out wPost,
epIter, typeof(LogisticOp2));
//print
Console.WriteLine("n: {0}", n);
Console.WriteLine("d: {0}", d);
int t = Y.Sum(o => o ? 1 : 0);
Console.WriteLine("number of true: {0}", t);
// Console.WriteLine("True bias: {0}", b);
// Console.WriteLine("Inferred bias: {0}", biasPost);
Console.WriteLine("True w: {0}", w);
Console.WriteLine("Inferred w: ");
Console.WriteLine(wPost);
// save the collected messages
List <Tuple <Gaussian, Gaussian, Beta> > toXMsgs = LogisticOp2.GetToXMessages();
allToXMsgs.AddRange(toXMsgs);
string toXFname = string.Format("binlogis_bw{0}_n{1}_iter{2}_s{3}.mat",
targetAnnotate, n, epIter, seed);
string toXPath = Config.PathToSavedFile(toXFname);
List <Tuple <Beta, Gaussian, Beta> > toLogisticMsgs = LogisticOp2.GetToLogisticMessages();
allToLogisticMsgs.AddRange(toLogisticMsgs);
string toLogisticFname = string.Format("binlogis_fw{0}_n{1}_iter{2}_s{3}.mat",
targetAnnotate, n, epIter, seed);
string toLogisticPath = Config.PathToSavedFile(toLogisticFname);
// extra information apart from collected messages
var extra = new Dictionary <string, object>()
{
{ "regression_input_dim", (double)d },
{ "true_w", w }, { "true_bias", b }, {
"regression_training_size",
(double)n
},
{ "X", X }, { "Y", Y }
};
ToXSerializeToMat(toXPath, toXMsgs, extra);
ToLogisticSerializeToMat(toLogisticPath, toLogisticMsgs, extra);
}
// save combined messages from seed_from to seed_to
string allToXFname = string.Format("binlogis_bw{0}_n{1}_iter{2}_sf{3}_st{4}.mat",
targetAnnotate, n, epIter, seed_from, seed_to);
string allToXPath = Config.PathToSavedFile(allToXFname);
ToXSerializeToMat(allToXPath, allToXMsgs, null);
string allToLogisticFname = string.Format("binlogis_fw{0}_n{1}_iter{2}_sf{3}_st{4}.mat",
targetAnnotate, n, epIter, seed_from, seed_to);
string allToLogisticPath = Config.PathToSavedFile(allToLogisticFname);
ToLogisticSerializeToMat(allToLogisticPath, allToLogisticMsgs, null);
}
public void RecordInferNETTime()
{
/**Records time by infer.net*/
/**
* Only one W just like in Ali's paper.
* In practice, we typically observe multiple sets of observations
* where we want to do inference on the same model with the same
* parameter.
*/
Rand.Restart(init_fixed_seed);
Vector w = Vector.Zero(d);
Rand.Normal(Vector.Zero(d), PositiveDefiniteMatrix.Identity(d), w);
// Create the Logistic operator instance only one because we want to use the same
// one after a new problem (new seed).
// stopwatch for measuring inference time for each problem
Stopwatch watch = new Stopwatch();
Type logisticOp = typeof(LogisticOp2);
LogisticOp2.Watch = watch;
List <long> allInferTimes = new List <long>();
var allPosteriors = new List <VectorGaussian>();
LogisticOp2.IsCollectLogisticMessages = false;
LogisticOp2.IsCollectProjMsgs = false;
LogisticOp2.IsCollectXMessages = false;
for (int seed = seed_from; seed <= seed_to; seed++)
{
Rand.Restart(seed);
double b = 0;
// combine the bias term into W
Vector[] X;
bool[] Y;
LogisticRegression.GenData(n, w, b, out X, out Y, seed);
Console.Write("Y: ");
StringUtils.PrintArray(Y);
VectorGaussian wPost;
// start the watch
watch.Restart();
LogisticRegression.InferCoefficientsNoBias(X, Y, out wPost, epIter, logisticOp);
// stop the watch
long inferenceTime = watch.ElapsedMilliseconds;
allInferTimes.Add(inferenceTime);
allPosteriors.Add(wPost);
//print
Console.WriteLine("n: {0}", n);
Console.WriteLine("d: {0}", d);
int t = Y.Sum(o => o ? 1 : 0);
Console.WriteLine("number of true: {0}", t);
Console.WriteLine("True bias: {0}", b);
// Vector meanW = wPost.GetMean();
Console.WriteLine("True w: {0}", w);
Console.WriteLine("Inferred w: ");
Console.WriteLine(wPost);
}
string fnameM = string.Format("rec_dnet_n{0}_logistic_iter{1}_sf{2}_st{3}.mat",
n, epIter, seed_from, seed_to);
string recordPathM = Config.PathToSavedFile(fnameM);
MatlabWriter writer = new MatlabWriter(recordPathM);
writer.Write("allInferTimes", MatrixUtils.ToDouble(allInferTimes));
Vector[] postMeans = allPosteriors.Select(vg => vg.GetMean()).ToArray();
Matrix[] postCovs = allPosteriors.Select(vg => vg.GetVariance()).ToArray();
writer.Write("postMeans", postMeans);
writer.Write("postCovs", postCovs);
writer.Write("dim", d);
writer.Write("n", n);
writer.Write("epIter", epIter);
writer.Write("seed_from", seed_from);
writer.Write("seed_to", seed_to);
writer.Write("init_fixed_seed", init_fixed_seed);
writer.Dispose();
}