bug fix in kmeans sparse init

oneapi-src · May 21, 2024 · 2f52a21 · 2f52a21
1 parent 908955d
commit 2f52a21
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 2 deletions.
diff --git a/cpp/daal/src/algorithms/kmeans/kmeans_plusplus_init_impl.i b/cpp/daal/src/algorithms/kmeans/kmeans_plusplus_init_impl.i
@@ -294,13 +294,19 @@ public:
     {
         algorithmFPType sumOfDist2 = algorithmFPType(0);
         size_t csrCursor           = 0u;
+        algorithmFPType pLastAddedCenterSumSq     = algorithmFPType(0.);
+        for (size_t iCol = 0u; iCol < dim; iCol++){
+            pLastAddedCenterSumSq += pLastAddedCenter[iCol] * pLastAddedCenter[iCol];
+        }
+
         for (size_t iRow = 0u; iRow < nRowsToProcess; iRow++)
         {
-            algorithmFPType dist2 = algorithmFPType(0);
+            algorithmFPType dist2 = pLastAddedCenterSumSq;
             const size_t nValues  = rowIdx[iRow + 1] - rowIdx[iRow];
             for (size_t i = 0u; i < nValues; i++, csrCursor++)
             {
-                dist2 += (pData[csrCursor] - pLastAddedCenter[colIdx[csrCursor] - 1]) * (pData[csrCursor] - pLastAddedCenter[colIdx[csrCursor] - 1]);
+                dist2 += pData[csrCursor] * pData[csrCursor];
+                dist2 -= 2 * pData[csrCursor] * pLastAddedCenter[colIdx[csrCursor] - 1];
             }
             if (aWeights)
             {

diff --git a/cpp/oneapi/dal/algo/kmeans_init/backend/cpu/compute_kernel_dense.cpp b/cpp/oneapi/dal/algo/kmeans_init/backend/cpu/compute_kernel_dense.cpp
@@ -42,10 +42,12 @@ static compute_result<Task> call_daal_kernel(const context_cpu& ctx,
                                              const table& data) {
     const std::int64_t column_count = data.get_column_count();
     const std::int64_t cluster_count = desc.get_cluster_count();
+    const std::int64_t trial_count = desc.get_local_trials_count();
 
     daal_kmeans_init::Parameter par(dal::detail::integral_cast<std::size_t>(cluster_count),
                                     0,
                                     dal::detail::integral_cast<std::size_t>(desc.get_seed()));
+    par.nTrials = dal::detail::integral_cast<std::size_t>(trial_count);
 
     const auto daal_data = interop::convert_to_daal_table<Float>(data);
     const std::size_t len_input = 1;