Merge pull request #3164 from eshaanagarwal/size-checks

Added Size checks for Matrix Completion, Kmeans and Linear Regression

src/mlpack/core/util/size_checks.hpp

@@ -26,18 +26,27 @@ namespace util {
  *     error generation.
  * @param addInfo Name to use for labels for precise error generation. Default
  *     is "labels"; for example, "weights" could also be used.
+ * @param isDataTranspose Bool parameter which can be set true to transpose data
+ *     before size-check. Default is false.
+ * @param isLabelTranspose Bool parameter which can be set true to transpose label
+ *     before size-check. Default is false.
  */
 template<typename DataType, typename LabelsType>
 inline void CheckSameSizes(const DataType& data,
                            const LabelsType& label,
                            const std::string& callerDescription,
-                           const std::string& addInfo = "labels")
-{
-  if (data.n_cols != label.n_cols)
+                           const std::string& addInfo = "labels",
+                           const bool& isDataTranspose = false,
+                           const bool& isLabelTranspose = false)
+{ 
+  const size_t dataPoints = (isDataTranspose == true) ? data.n_rows : data.n_cols;
+  const size_t labelPoints = (isLabelTranspose == true) ? label.n_rows : label.n_cols;
+  
+  if (dataPoints != labelPoints)
   {
     std::ostringstream oss;
-    oss << callerDescription << ": number of points (" << data.n_cols << ") "
-        << "does not match number of " << addInfo << " (" << label.n_cols
+    oss << callerDescription << ": number of points (" << dataPoints << ") "
+        << "does not match number of " << addInfo << " (" << labelPoints
         << ")!" << std::endl;
     throw std::invalid_argument(oss.str());
   }

src/mlpack/methods/kmeans/kmeans_impl.hpp

@@ -14,6 +14,7 @@
 
 #include <mlpack/core/metrics/lmetric.hpp>
 #include <mlpack/core/util/sfinae_utility.hpp>
+#include <mlpack/core/util/size_checks.hpp>
 
 namespace mlpack {
 namespace kmeans {
@@ -161,15 +162,8 @@ Cluster(const MatType& data,
   // Check validity of initial guess.
   if (initialGuess)
   {
-    if (centroids.n_cols != clusters)
-      Log::Fatal << "KMeans::Cluster(): wrong number of initial cluster "
-        << "centroids (" << centroids.n_cols << ", should be " << clusters
-        << ")!" << std::endl;
-
-    if (centroids.n_rows != data.n_rows)
-      Log::Fatal << "KMeans::Cluster(): initial cluster centroids have wrong "
-        << " dimensionality (" << centroids.n_rows << ", should be "
-        << data.n_rows << ")!" << std::endl;
+    util::CheckSameSizes(centroids, clusters, "KMeans::Cluster()", "clusters");
+    util::CheckSameDimensionality(data, centroids, "KMeans::Cluster()");
   }
 
   // Use the partitioner to come up with the partition assignments and calculate
@@ -288,10 +282,7 @@ Cluster(const MatType& data,
   // Now, the initial assignments.  First determine if they are necessary.
   if (initialAssignmentGuess)
   {
-    if (assignments.n_elem != data.n_cols)
-      Log::Fatal << "KMeans::Cluster(): initial cluster assignments (length "
-          << assignments.n_elem << ") not the same size as the dataset (size "
-          << data.n_cols << ")!" << std::endl;
+    util::CheckSameSizes(data, assignments, "KMeans::Cluster()", "assignments");
 
     // Calculate initial centroids.
     arma::Row<size_t> counts;

src/mlpack/methods/linear_regression/linear_regression.cpp

@@ -12,6 +12,7 @@
  */
 #include "linear_regression.hpp"
 #include <mlpack/core/util/log.hpp>
+#include <mlpack/core/util/size_checks.hpp>
 
 using namespace mlpack;
 using namespace mlpack::regression;
@@ -57,6 +58,10 @@ double LinearRegression::Train(const arma::mat& predictors,
   // We store the number of rows and columns of the predictors.
   // Reminder: Armadillo stores the data transposed from how we think of it,
   //           that is, columns are actually rows (see: column major order).
+
+  // Sanity check on data.
+  util::CheckSameSizes(predictors, responses, "LinearRegression::Train()");
+
   const size_t nCols = predictors.n_cols;
 
   arma::mat p = predictors;
@@ -95,7 +100,11 @@ void LinearRegression::Predict(const arma::mat& points,
   {
     // We want to be sure we have the correct number of dimensions in the
     // dataset.
-    Log::Assert(points.n_rows == parameters.n_rows - 1);
+    // Prevent underflow.
+    const size_t labels = (parameters.n_rows == 0) ? size_t(0) :
+        size_t(parameters.n_rows - 1);
+    util::CheckSameDimensionality(points, labels, "LinearRegression::Predict()", 
+        "points");
     // Get the predictions, but this ignores the intercept value
     // (parameters[0]).
     predictions = arma::trans(parameters.subvec(1, parameters.n_elem - 1))
@@ -107,7 +116,8 @@ void LinearRegression::Predict(const arma::mat& points,
   {
     // We want to be sure we have the correct number of dimensions in
     // the dataset.
-    Log::Assert(points.n_rows == parameters.n_rows);
+    util::CheckSameDimensionality(points, parameters, 
+        "LinearRegression::Predict()", "points");
     predictions = arma::trans(parameters) * points;
   }
 }
@@ -115,6 +125,9 @@ void LinearRegression::Predict(const arma::mat& points,
 double LinearRegression::ComputeError(const arma::mat& predictors,
                                       const arma::rowvec& responses) const
 {
+  // Sanity check on data.
+  util::CheckSameSizes(predictors, responses, "LinearRegression::Train()");
+  
   // Get the number of columns and rows of the dataset.
   const size_t nCols = predictors.n_cols;
   const size_t nRows = predictors.n_rows;

src/mlpack/methods/matrix_completion/matrix_completion.cpp

@@ -11,6 +11,7 @@
  */
 
 #include "matrix_completion.hpp"
+#include <mlpack/core/util/size_checks.hpp>
 
 namespace mlpack {
 namespace matrix_completion {
@@ -59,13 +60,8 @@ void MatrixCompletion::CheckValues()
         << "indices does not have 2 rows!" << std::endl;
   }
 
-  if (indices.n_cols != values.n_elem)
-  {
-    Log::Fatal << "MatrixCompletion::CheckValues(): the number of constraint "
-        << "indices (columns of constraint indices matrix) does not match the "
-        << "number of constraint values (length of constraint value vector)!"
-        << std::endl;
-  }
+  util::CheckSameSizes(indices, values, 
+      "MatrixCompletion::CheckValues()", "labels", false, true);
 
   for (size_t i = 0; i < values.n_elem; ++i)
   {