public override Parameters GetParameters(IGroupDataProvider data)
{
return(new Parameters(new Parameter[] { new DoubleParam("C", 100)
{
Help = SvmClassification.cHelp
} }));
}
public ClassificationModel Train(BaseVector[] x, int[][] y, int ngroups, IGroupDataProvider data, int nthreads,
Action<double> reportProgress)
{
return groupWiseSelection
? TrainGroupWise(x, y, ngroups, data, nthreads)
: TrainGlobal(x, y, ngroups, data, nthreads, reportProgress);
}
public ClassificationModel Train(BaseVector[] x, int[][] y, int ngroups, IGroupDataProvider data, int nthreads,
Action <double> reportProgress)
{
return(groupWiseSelection
? TrainGroupWise(x, y, ngroups, data, nthreads)
: TrainGlobal(x, y, ngroups, data, nthreads, reportProgress));
}
public PermissionsService(IRolesDataProvider roleDataProvider, IPermissionsDataProvider permissionsDataProvider, ILogger <PermissionsService> logger, IGroupDataProvider groupDataProvider)
{
_permissionsDataProvider = permissionsDataProvider ?? throw new ArgumentNullException(nameof(permissionsDataProvider));
_roleDataProvider = roleDataProvider ?? throw new ArgumentNullException(nameof(roleDataProvider));
_logger = logger;
_groupDataProvider = groupDataProvider ?? throw new ArgumentNullException(nameof(groupDataProvider));
}
public override Parameters GetParameters(IGroupDataProvider data)
{
return(new Parameters(new Parameter[] { new DoubleParam("s0", 0)
{
Help = s0Help
} }));
}
public static Parameters[] GetAllSubParameters(IGroupDataProvider data)
{
Parameters[] result = new Parameters[allMethods.Length];
for (int i = 0; i < result.Length; i++){
result[i] = allMethods[i].GetParameters(data);
}
return result;
}
public static Parameters[] GetAllSubParameters(IGroupDataProvider data)
{
Parameters[] result = new Parameters[allMethods.Length];
for (int i = 0; i < result.Length; i++)
{
result[i] = allMethods[i].GetParameters(data);
}
return(result);
}
public override Parameters GetParameters(IGroupDataProvider data)
{
return
new Parameters(new Parameter[]{
new DoubleParam("C", 100){Help = SvmClassification.cHelp},
new DoubleParam("Reduction factor", 1.414){
Help = "The feature set will be recursively reduced in size by this factor."
}
});
}
public ClassificationModel TrainGroupWise(int i, int[][] y, BaseVector[] x, IGroupDataProvider data)
{
int[][] yb = ToBinaryClasses(y, i);
if (ranker == null || groupWiseNfeatures[i] >= x[0].Length)
{
return(classifier.Train(x, yb, 2, classifierParam, 1));
}
int[] o = ranker.Rank(x, yb, 2, rankerParam, data, 1);
int[] inds = nfeatures < o.Length ? ArrayUtils.SubArray(o, groupWiseNfeatures[i]) : o;
return(new ClassificationOnSubFeatures(classifier.Train(ExtractFeatures(x, inds), yb, 2, classifierParam, 1), inds));
}
public RegressionModel Train(BaseVector[] x, float[] y, IGroupDataProvider data)
{
if (ranker == null || nfeatures >= x[0].Length){
return regressionMethod.Train(x, y, regressionParam, 1);
}
int[] o = ranker.Rank(x, y, rankerParam, data, 1);
int[] inds = nfeatures < o.Length ? ArrayUtils.SubArray(o, nfeatures) : o;
return
new RegressionOnSubFeatures(
regressionMethod.Train(ClassificationWithRanking.ExtractFeatures(x, inds), y, regressionParam, 1), inds);
}
public override Parameters GetParameters(IGroupDataProvider data)
{
return(new Parameters(new DoubleParam("C", 100)
{
Help = SvmClassification.cHelp
},
new DoubleParam("Reduction factor", 1.414)
{
Help = "The feature set will be recursively reduced in size by this factor."
}));
}
public RegressionModel Train(BaseVector[] x, float[] y, IGroupDataProvider data)
{
if (ranker == null || nfeatures >= x[0].Length)
{
return(regressionMethod.Train(x, y, regressionParam, 1));
}
int[] o = ranker.Rank(x, y, rankerParam, data, 1);
int[] inds = nfeatures < o.Length ? ArrayUtils.SubArray(o, nfeatures) : o;
return
(new RegressionOnSubFeatures(
regressionMethod.Train(ClassificationWithRanking.ExtractFeatures(x, inds), y, regressionParam, 1), inds));
}
public ClassificationModel TrainGlobal(BaseVector[] x, int[][] y, int ngroups, IGroupDataProvider data, int nthreads,
Action<double> reportProgress)
{
if (ranker == null || nfeatures >= x[0].Length){
return classifier.Train(x, y, ngroups, classifierParam, nthreads, reportProgress);
}
int[] o = ranker.Rank(x, y, ngroups, rankerParam, data, nthreads);
int[] inds = nfeatures < o.Length ? ArrayUtils.SubArray(o, nfeatures) : o;
return
new ClassificationOnSubFeatures(classifier.Train(ExtractFeatures(x, inds), y, ngroups, classifierParam, nthreads),
inds);
}
public int[] Rank(BaseVector[] x, float[] y, Parameters param, IGroupDataProvider data, int nthreads)
{
int nfeatures = x[0].Length;
double[] s = new double[nfeatures];
for (int i = 0; i < nfeatures; i++){
float[] xx = new float[x.Length];
for (int j = 0; j < xx.Length; j++){
xx[j] = (float)x[j][i];
}
s[i] = CalcScore(xx, y);
}
return ArrayUtils.Order(s);
}
public GroupMemberNotificationService(ILogger <GroupMemberNotificationService> logger,
IEmailService emailService,
IOptionsSnapshot <GovNotifyConfiguration> notifyConfig,
IOptionsSnapshot <ApplicationGateway> gatewayConfig,
IUserDataProvider userDataProvider,
IGroupDataProvider groupDataProvider)
{
_logger = logger;
_emailService = emailService;
_govNotifyConfiguration = notifyConfig.Value;
_userDataProvider = userDataProvider;
_groupDataProvider = groupDataProvider ?? throw new ArgumentNullException(nameof(groupDataProvider));
_fqdn = gatewayConfig.Value.FQDN ?? throw new ArgumentNullException(nameof(gatewayConfig.Value.FQDN));
}
public override int[] Rank(BaseVector[] x, double[] y, Parameters param, IGroupDataProvider data, int nthreads)
{
int nfeatures = x[0].Length;
double[] s = new double[nfeatures];
for (int i = 0; i < nfeatures; i++)
{
double[] xx = new double[x.Length];
for (int j = 0; j < xx.Length; j++)
{
xx[j] = x[j][i];
}
s[i] = CalcScore(xx, y);
}
return(ArrayUtils.Order(s));
}
public override int[] Rank(BaseVector[] x, int[][] y, int ngroups, Parameters param, IGroupDataProvider data,
int nthreads, Action<double> reportProgress)
{
SvmParameter sp = new SvmParameter{
kernelFunction = new LinearKernelFunction(),
svmType = SvmType.CSvc,
c = param.GetParam<double>("C").Value
};
bool[] invert;
SvmProblem[] problems = CreateProblems(x, y, ngroups, out invert);
int[][] rankedSets = new int[problems.Length][];
for (int i = 0; i < problems.Length; ++i){
rankedSets[i] = RankBinary(problems[i], sp);
}
return CombineRankedFeaturesLists(rankedSets);
}
public override int[] Rank(BaseVector[] x, int[][] y, int ngroups, Parameters param, IGroupDataProvider data,
int nthreads, Action<double> reportProgress)
{
double s0 = param.GetParam<double>("s0").Value;
int nfeatures = x[0].Length;
int[][] yy = RearrangeGroups(y, ngroups);
double[] s = new double[nfeatures];
for (int i = 0; i < nfeatures; i++){
double[] xx = new double[x.Length];
for (int j = 0; j < xx.Length; j++){
xx[j] = x[j][i];
}
s[i] = CalcPvalue(xx, yy, ngroups, s0);
}
return ArrayUtils.Order(s);
}
public RegressionModel[] Train(BaseVector[] x, float[] y, IGroupDataProvider data)
{
int[] o = ranker.Rank(x, y, rankerParam, data, 1);
int[] sizes = GetSizes(x[0].Length, reductionFactor, maxFeatures);
RegressionModel[] result = new RegressionModel[sizes.Length];
for (int i = 0; i < result.Length; i++){
if (i == 0 && sizes[0] == x[0].Length){
result[0] = classifier.Train(x, y, classifierParam, 1);
} else{
int[] inds = ArrayUtils.SubArray(o, sizes[i]);
result[i] =
new RegressionOnSubFeatures(
classifier.Train(ClassificationWithRanking.ExtractFeatures(x, inds), y, classifierParam, 1), inds);
}
}
return result;
}
public int[] Rank(BaseVector[] x, float[] y, Parameters param, IGroupDataProvider data, int nthreads)
{
int nfeatures = x[0].Length;
float[] yr = ArrayUtils.RankF(y);
double[] s = new double[nfeatures];
for (int i = 0; i < nfeatures; i++)
{
float[] xx = new float[x.Length];
for (int j = 0; j < xx.Length; j++)
{
xx[j] = (float)x[j][i];
}
float[] xxr = ArrayUtils.RankF(xx);
s[i] = CalcScore(xxr, yr);
}
return(ArrayUtils.Order(s));
}
public RegressionModel[] Train(BaseVector[] x, float[] y, IGroupDataProvider data)
{
int[] o = ranker.Rank(x, y, rankerParam, data, 1);
int[] sizes = GetSizes(x[0].Length, reductionFactor, maxFeatures);
RegressionModel[] result = new RegressionModel[sizes.Length];
for (int i = 0; i < result.Length; i++)
{
if (i == 0 && sizes[0] == x[0].Length)
{
result[0] = classifier.Train(x, y, classifierParam, 1);
}
else
{
int[] inds = ArrayUtils.SubArray(o, sizes[i]);
result[i] =
new RegressionOnSubFeatures(
classifier.Train(ClassificationWithRanking.ExtractFeatures(x, inds), y, classifierParam, 1), inds);
}
}
return(result);
}
private const long MaxFileSizeBytes = 5242880; // 5MB
public GroupService(ISystemClock systemClock,
ILogger <DiscussionService> logger,
IPermissionsService permissionsService,
IFileCommand fileCommand,
IImageBlobStorageProvider blobStorageProvider,
IFileTypeValidator fileTypeValidator,
IGroupImageService imageService,
IGroupCommand groupCommand,
IHtmlSanitizer htmlSanitizer,
IGroupDataProvider groupDataProvider,
IContentService contentService)
{
_systemClock = systemClock ?? throw new ArgumentNullException(nameof(systemClock));
_blobStorageProvider = blobStorageProvider ?? throw new ArgumentNullException(nameof(blobStorageProvider));
_permissionsService = permissionsService ?? throw new ArgumentNullException(nameof(permissionsService));
_fileTypeValidator = fileTypeValidator ?? throw new ArgumentNullException(nameof(fileTypeValidator));
_groupCommand = groupCommand ?? throw new ArgumentNullException(nameof(groupCommand));
_groupDataProvider = groupDataProvider ?? throw new ArgumentNullException(nameof(groupDataProvider));
_logger = logger ?? throw new ArgumentNullException(nameof(logger));
_imageService = imageService ?? throw new ArgumentNullException(nameof(imageService));
_htmlSanitizer = htmlSanitizer ?? throw new ArgumentNullException(nameof(htmlSanitizer));
_contentService = contentService ?? throw new ArgumentNullException(nameof(contentService));
}
public ClassificationModel Train(BaseVector[] x, int[][] y, int ngroups, IGroupDataProvider data, int nthreads)
{
return Train(x, y, ngroups, data, nthreads, null);
}
public override Parameters GetParameters(IGroupDataProvider data)
{
return(new Parameters());
}
public ClassificationModel TrainGroupWise(BaseVector[] x, int[][] y, int ngroups, IGroupDataProvider data,
int nthreads)
{
ClassificationModel[] c = new ClassificationModel[ngroups];
ThreadDistributor td = new ThreadDistributor(nthreads, ngroups, i => { c[i] = TrainGroupWise(i, y, x, data); });
td.Start();
return new GroupWiseClassifier(c);
}
public ClassificationModel TrainGroupWise(int i, int[][] y, BaseVector[] x, IGroupDataProvider data)
{
int[][] yb = ToBinaryClasses(y, i);
if (ranker == null || groupWiseNfeatures[i] >= x[0].Length){
return classifier.Train(x, yb, 2, classifierParam, 1);
}
int[] o = ranker.Rank(x, yb, 2, rankerParam, data, 1);
int[] inds = nfeatures < o.Length ? ArrayUtils.SubArray(o, groupWiseNfeatures[i]) : o;
return new ClassificationOnSubFeatures(classifier.Train(ExtractFeatures(x, inds), yb, 2, classifierParam, 1), inds);
}
public override Parameters GetParameters(IGroupDataProvider data)
{
return new Parameters(new Parameter[]{new DoubleParam("s0", 0){Help = s0Help}});
}
public UserService(IUserDataProvider userDataProvider, IGroupDataProvider groupDataProvider)
{
_userDataProvider = userDataProvider;
_groupDataProvider = groupDataProvider;
}
public int[] Rank(BaseVector[] x, int[][] y, int ngroups, Parameters param, IGroupDataProvider data, int nthreads)
{
return(Rank(x, y, ngroups, param, data, nthreads, null));
}
public override Parameters GetParameters(IGroupDataProvider data)
{
return new Parameters(new Parameter[]{new DoubleParam("C", 100){Help = SvmClassification.cHelp}});
}
public ClassificationModel TrainGroupWise(BaseVector[] x, int[][] y, int ngroups, IGroupDataProvider data,
int nthreads)
{
ClassificationModel[] c = new ClassificationModel[ngroups];
ThreadDistributor td = new ThreadDistributor(nthreads, ngroups, i => { c[i] = TrainGroupWise(i, y, x, data); });
td.Start();
return(new GroupWiseClassifier(c));
}
public ClassificationModel Train(BaseVector[] x, int[][] y, int ngroups, IGroupDataProvider data, int nthreads)
{
return(Train(x, y, ngroups, data, nthreads, null));
}
public void Initialize(IConfigSource config)
{
IConfig groupsConfig = config.Configs["Groups"];
if (groupsConfig == null)
{
// Do not run this module by default.
return;
}
else
{
m_groupsEnabled = groupsConfig.GetBoolean("Enabled", false);
if (!m_groupsEnabled)
{
return;
}
if (groupsConfig.GetString("Module", "Default") != "FlexiGroups")
{
m_groupsEnabled = false;
return;
}
m_log.Info("[GROUPS]: Initializing FlexiGroups");
m_groupData = ProviderFactory.GetProviderFromConfigName(m_log, groupsConfig, groupsConfig.GetString("Provider"));
m_groupNoticesEnabled = groupsConfig.GetBoolean("XmlRpcNoticesEnabled", true);
m_debugEnabled = groupsConfig.GetBoolean("XmlRpcDebugEnabled", true);
}
}
public override int[] Rank(BaseVector[] x, int[][] y, int ngroups, Parameters param, IGroupDataProvider data,
int nthreads, Action <double> reportProgress)
{
int nfeatures = x[0].Length;
int[][] yy = RearrangeGroups(y, ngroups);
double[][] score = new double[ngroups][];
for (int k = 0; k < ngroups; k++)
{
score[k] = new double[nfeatures];
}
for (int i = 0; i < nfeatures; i++)
{
double[] xx = new double[x.Length];
for (int j = 0; j < xx.Length; j++)
{
xx[j] = x[j][i];
}
double[] singleFeatureScores = CalcGolubScore(xx, yy, ngroups);
for (int c = 0; c < ngroups; ++c)
{
score[c][i] = singleFeatureScores[c];
}
}
return(CombineRankedFeaturesLists(nfeatures, score));
}
public abstract Parameters GetParameters(IGroupDataProvider data);
public abstract int[] Rank(BaseVector[] x, int[][] y, int ngroups, Parameters param, IGroupDataProvider data,
int nthreads, Action <double> reportProgress);
public ClassificationModel TrainGlobal(BaseVector[] x, int[][] y, int ngroups, IGroupDataProvider data, int nthreads,
Action <double> reportProgress)
{
if (ranker == null || nfeatures >= x[0].Length)
{
return(classifier.Train(x, y, ngroups, classifierParam, nthreads, reportProgress));
}
int[] o = ranker.Rank(x, y, ngroups, rankerParam, data, nthreads);
int[] inds = nfeatures < o.Length ? ArrayUtils.SubArray(o, nfeatures) : o;
return
(new ClassificationOnSubFeatures(classifier.Train(ExtractFeatures(x, inds), y, ngroups, classifierParam, nthreads),
inds));
}
/// <summary>
/// 构造函数
/// </summary>
public GroupFacade()
{
groupData = ClassFactory.GetIGroupDataProvider();
}
public GroupService(IGroupDataProvider groupDataProvider)
{
_groupDataProvider = groupDataProvider;
}
public Parameters GetParameters(IGroupDataProvider data)
{
return new Parameters();
}
public override int[] Rank(BaseVector[] x, int[][] y, int ngroups, Parameters param, IGroupDataProvider data,
int nthreads, Action <double> reportProgress)
{
double s0 = param.GetParam <double>("s0").Value;
int nfeatures = x[0].Length;
int[][] yy = RearrangeGroups(y, ngroups);
double[] s = new double[nfeatures];
for (int i = 0; i < nfeatures; i++)
{
double[] xx = new double[x.Length];
for (int j = 0; j < xx.Length; j++)
{
xx[j] = x[j][i];
}
s[i] = CalcPvalue(xx, yy, ngroups, s0);
}
return(ArrayUtils.Order(s));
}
public override int[] Rank(BaseVector[] x, int[][] y, int ngroups, Parameters param, IGroupDataProvider data,
int nthreads, Action <double> reportProgress)
{
SvmParameter sp = new SvmParameter {
kernelFunction = new LinearKernelFunction(),
svmType = SvmType.CSvc,
c = param.GetParam <double>("C").Value
};
bool[] invert;
SvmProblem[] problems = CreateProblems(x, y, ngroups, out invert);
int[][] rankedSets = new int[problems.Length][];
for (int i = 0; i < problems.Length; ++i)
{
rankedSets[i] = RankBinary(problems[i], sp);
}
return(CombineRankedFeaturesLists(rankedSets));
}
public abstract int[] Rank(BaseVector[] x, double[] y, Parameters param, IGroupDataProvider data, int nthreads);