From 333c541f98076d2c6ea108cb005791554f78bbf4 Mon Sep 17 00:00:00 2001
From: yashu-seth <yashuseth2503@gmail.com>
Date: Sun, 18 Dec 2016 10:47:54 -0800
Subject: [PATCH 1/3] adds GammaDistribution::Train(observations,
 probabilities)

---
 src/mlpack/core/dists/gamma_distribution.cpp | 29 ++++++++++++++++++++
 src/mlpack/core/dists/gamma_distribution.hpp |  3 +-
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/core/dists/gamma_distribution.cpp b/src/mlpack/core/dists/gamma_distribution.cpp
index 8913730459b..1a55fad0ee4 100644
--- a/src/mlpack/core/dists/gamma_distribution.cpp
+++ b/src/mlpack/core/dists/gamma_distribution.cpp
@@ -64,6 +64,35 @@ void GammaDistribution::Train(const arma::mat& rdata, const double tol)
   Train(logMeanxVec, meanLogxVec, meanxVec, tol);
 }
 
+//Fits an alpha and beta parameter according to observation probabilities.
+void GammaDistribution::Train(const arma::mat& rdata, const arma::vec& probabilities,
+                              const double tol)
+{
+  // If fittingSet is empty, nothing to do.
+  if (arma::size(rdata) == arma::size(arma::mat()))
+    return;
+
+  arma::vec meanLogxVec(rdata.n_rows, arma::fill::zeros);
+  arma::vec meanxVec(rdata.n_rows, arma::fill::zeros);
+  arma::vec logMeanxVec(rdata.n_rows, arma::fill::zeros);
+
+  for(size_t i=0; i<rdata.n_cols; i++)
+  {
+    meanLogxVec += probabilities(i) * arma::log(rdata.col(i));
+    meanxVec += probabilities(i) * rdata.col(i);
+  }
+
+  double tot_probabilty = arma::accu(probabilities);
+
+  meanLogxVec /= tot_probabilty;
+  meanxVec /= tot_probabilty;
+  logMeanxVec = arma::log(meanxVec);
+
+  // Call the statistics-only GammaDistribution::Train() function to fit the
+  // parameters. That function does all the work so we're done.
+  Train(logMeanxVec, meanLogxVec, meanxVec, tol);
+}
+
 // Fits an alpha and beta parameter to each dimension of the data.
 void GammaDistribution::Train(const arma::vec& logMeanxVec, 
                               const arma::vec& meanLogxVec,
diff --git a/src/mlpack/core/dists/gamma_distribution.hpp b/src/mlpack/core/dists/gamma_distribution.hpp
index 718cd7f2d9d..766f6664005 100644
--- a/src/mlpack/core/dists/gamma_distribution.hpp
+++ b/src/mlpack/core/dists/gamma_distribution.hpp
@@ -101,11 +101,10 @@ class GammaDistribution
      * @param tol Convergence tolerance. This is *not* an absolute measure:
      *    It will stop the approximation once the *change* in the value is 
      *    smaller than tol.
-     *
+     */
     void Train(const arma::mat& observations,
                const arma::vec& probabilities,
                const double tol = 1e-8);
-     */
 
     /**
      * This function trains (fits distribution parameters) to a dataset with

From 626d94cc565a0ba2387ff2c0ee0ca73603e1ce7c Mon Sep 17 00:00:00 2001
From: yashu-seth <yashuseth2503@gmail.com>
Date: Fri, 23 Dec 2016 13:01:20 -0800
Subject: [PATCH 2/3] adds tests for GammaDistribution::Train(observations,
 probabilities)

---
 src/mlpack/tests/distribution_test.cpp | 142 +++++++++++++++++++++++++
 1 file changed, 142 insertions(+)

diff --git a/src/mlpack/tests/distribution_test.cpp b/src/mlpack/tests/distribution_test.cpp
index 2e15786fdc9..9f01d89dd03 100644
--- a/src/mlpack/tests/distribution_test.cpp
+++ b/src/mlpack/tests/distribution_test.cpp
@@ -442,6 +442,148 @@ BOOST_AUTO_TEST_CASE(GammaDistributionTrainTest)
   BOOST_REQUIRE_EQUAL(gDist.Dimensionality(), d2);
 }
 
+/**
+ * This test verifies that the fitting procedure for GammaDistribution works
+ * properly when probabilities for each sample is given.
+ */
+BOOST_AUTO_TEST_CASE(GammaDistributionTrainWithProbabilitiesTest)
+{
+  double alphaReal = 5.4;
+  double betaReal = 6.7;
+
+  // Create a gamma distribution random generator
+  std::default_random_engine generator;
+  std::gamma_distribution<double> dist(alphaReal, betaReal);
+
+  size_t N = 50000;
+  size_t d = 2;
+  arma::mat rdata(d, N);
+
+  for(size_t j = 0; j < d; j++)
+    for(size_t i = 0; i < N; i++)
+      rdata(j, i) = dist(generator);
+
+  // create a uniform distribution random generator
+  std::uniform_real_distribution<double> prob(0, 1);
+  arma::vec probabilities(N);
+
+  for(size_t i = 0; i < N; i++)
+    probabilities(i) = prob(generator);
+
+  // fit results with probabilities and data
+  GammaDistribution gDist;
+  gDist.Train(rdata, probabilities);
+
+  // fit results with only data
+  GammaDistribution gDist2;
+  gDist2.Train(rdata);
+
+  BOOST_REQUIRE_CLOSE(gDist2.Alpha(0), gDist.Alpha(0), 1);
+  BOOST_REQUIRE_CLOSE(gDist2.Beta(0), gDist.Beta(0), 1);
+
+  BOOST_REQUIRE_CLOSE(gDist2.Alpha(1), gDist.Alpha(1), 1);
+  BOOST_REQUIRE_CLOSE(gDist2.Beta(1), gDist.Beta(1), 1);
+
+  BOOST_REQUIRE_CLOSE(alphaReal, gDist.Alpha(0), 1);
+  BOOST_REQUIRE_CLOSE(betaReal, gDist.Beta(0), 1);
+
+  BOOST_REQUIRE_CLOSE(alphaReal, gDist.Alpha(1), 1);
+  BOOST_REQUIRE_CLOSE(betaReal, gDist.Beta(1), 1);
+}
+
+
+// This test ensures that the same result is obtained when
+// trained with probabilities all set to 1 and with no probabilities at all.
+BOOST_AUTO_TEST_CASE(GammaDistributionTrainALLProbabilities1Test)
+{
+  double alphaReal = 5.4;
+  double betaReal = 6.7;
+
+  // Create a gamma distribution random generator
+  std::default_random_engine generator;
+  std::gamma_distribution<double> dist(alphaReal, betaReal);
+
+  size_t N = 1000;
+  size_t d = 2;
+  arma::mat rdata(d, N);
+
+  for(size_t j = 0; j < d; j++)
+    for(size_t i = 0; i < N; i++)
+      rdata(j, i) = dist(generator);
+
+  // fit results with only data
+  GammaDistribution gDist;
+  gDist.Train(rdata);
+
+  // fit results with data and each probability as 1
+  GammaDistribution gDist2;
+  arma::vec allProbabilities1(N, arma::fill::ones);
+  gDist2.Train(rdata, allProbabilities1);
+
+  BOOST_REQUIRE_CLOSE(gDist2.Alpha(0), gDist.Alpha(0), 1e-5);
+  BOOST_REQUIRE_CLOSE(gDist2.Beta(0), gDist.Beta(0), 1e-5);
+
+  BOOST_REQUIRE_CLOSE(gDist2.Alpha(1), gDist.Alpha(1), 1e-5);
+  BOOST_REQUIRE_CLOSE(gDist2.Beta(1), gDist.Beta(1), 1e-5);
+}
+
+ /** This test draws points from two different gamma distributions,
+  *  sets the probabilities for the points from the first distribution
+  *  to something small and the probabilities for the second to something large. 
+  *  It ensures that the gamma distribution recovered has the
+  *  same parameters as the second gamma distribution with high probabilities.
+  */
+BOOST_AUTO_TEST_CASE(GammaDistributionTrainTwoDistProbabilities1Test)
+{
+  double alphaReal = 5.4;
+  double betaReal = 6.7;
+
+  double alphaReal2 = 1.9;
+  double betaReal2 = 8.4;
+
+  // Create two gamma distribution random generators
+  std::default_random_engine generator;
+  std::gamma_distribution<double> dist(alphaReal, betaReal);
+  std::gamma_distribution<double> dist2(alphaReal2, betaReal2);
+
+  std::uniform_real_distribution<double> lowProb(0, 0.02);
+  std::uniform_real_distribution<double> highProb(0.98, 1);
+
+  size_t N = 50000;
+  size_t d = 2;
+  arma::mat rdata(d, N);
+  arma::vec probabilities(N);
+
+  // draws points alternately from the two different distributions.
+  for(size_t j = 0; j < d; j++)
+  {
+    for(size_t i = 0; i < N; i++)
+    {
+      if(i % 2 == 0)
+        rdata(j, i) = dist(generator);
+      else
+        rdata(j, i) = dist2(generator);
+    }
+  }
+
+  for(size_t i = 0; i<N; i++)
+  {
+    if(i % 2 == 0)
+      probabilities(i) = lowProb(generator);
+    else
+      probabilities(i) = highProb(generator);
+  }
+
+  GammaDistribution gDist;
+  gDist.Train(rdata, probabilities);
+
+  BOOST_REQUIRE_CLOSE(alphaReal2, gDist.Alpha(0), 5);
+  BOOST_REQUIRE_CLOSE(betaReal2, gDist.Beta(0), 5);
+
+  BOOST_REQUIRE_CLOSE(alphaReal2, gDist.Alpha(1), 5);
+  BOOST_REQUIRE_CLOSE(betaReal2, gDist.Beta(1), 5);
+}
+
 /**
  * This test verifies that the fitting procedure for GammaDistribution works
  * properly and converges near the actual gamma parameters. We do this twice

From f5dadd8278480c94979f7d8681de7b16420c88e2 Mon Sep 17 00:00:00 2001
From: yashu-seth <yashuseth2503@gmail.com>
Date: Fri, 23 Dec 2016 13:04:59 -0800
Subject: [PATCH 3/3] adds my name to core.hpp and COPYRIGHT.txt

---
 COPYRIGHT.txt       | 1 +
 src/mlpack/core.hpp | 1 +
 2 files changed, 2 insertions(+)

diff --git a/COPYRIGHT.txt b/COPYRIGHT.txt
index d02ba901219..bd9e16bd976 100644
--- a/COPYRIGHT.txt
+++ b/COPYRIGHT.txt
@@ -63,6 +63,7 @@ Copyright:
   Copyright 2016, Anuraj Kanodia <akanuraj200@gmail.com>
   Copyright 2016, Ivan Georgiev <ivan@jonan.info>
   Copyright 2016, Shikhar Bhardwaj <shikharbhardwaj68@gmail.com>
+  Copyright 2016, Yashu Seth <yashuseth2503@gmail.com>
 License: BSD-3-clause
   All rights reserved.
   .
diff --git a/src/mlpack/core.hpp b/src/mlpack/core.hpp
index aa9242d1651..1409be57dfc 100644
--- a/src/mlpack/core.hpp
+++ b/src/mlpack/core.hpp
@@ -203,6 +203,7 @@
  *   - Anuraj Kanodia <akanuraj200@gmail.com>
  *   - Ivan Georgiev <ivan@jonan.info>
  *   - Shikhar Bhardwaj <shikharbhardwaj68@gmail.com>
+ *   - Yashu Seth <yashuseth2503@gmail.com>
  */
 
 // First, include all of the prerequisites.