Add API method LGBM_BoosterPredictForMats (#2008)

* Fix index out-of-range exception generated by BaggingHelper on small datasets.

Prior to this change, the line "score_t threshold = tmp_gradients[top_k - 1];" would generate an exception, since tmp_gradients would be empty when the cnt input value to the function is zero.

* Update goss.hpp

* Update goss.hpp

* Add API method LGBM_BoosterPredictForMats which runs prediction on a data set given as of array of pointers to rows (as opposed to existing method LGBM_BoosterPredictForMat which requires data given as contiguous array)

* Fix incorrect upstream merge

* Add link to LightGBM.NET

* Fix indenting to 2 spaces

* Dummy edit to trigger CI

* Dummy edit to trigger CI

README.md

@@ -70,6 +70,8 @@ MMLSpark (Spark-package): https://github.com/Azure/mmlspark
 
 ML.NET (.NET/C#-package): https://github.com/dotnet/machinelearning
 
+LightGBM.NET (.NET/C#-package): https://github.com/rca22/LightGBM.Net
+
 Dask-LightGBM (distributed and parallel Python-package): https://github.com/dask/dask-lightgbm
 
 Get Started and Documentation

include/LightGBM/c_api.h

@@ -822,6 +822,37 @@ LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForMat(BoosterHandle handle,
                                                 int64_t* out_len,
                                                 double* out_result);
 
+/*!
+* \brief make prediction for an new data set
+*        Note:  should pre-allocate memory for out_result,
+*               for noraml and raw score: its length is equal to num_class * num_data
+*               for leaf index, its length is equal to num_class * num_data * num_iteration
+* \param handle handle
+* \param data pointer to the data space
+* \param data_type type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64
+* \param nrow number of rows
+* \param ncol number columns
+* \param predict_type
+*          C_API_PREDICT_NORMAL: normal prediction, with transform (if needed)
+*          C_API_PREDICT_RAW_SCORE: raw score
+*          C_API_PREDICT_LEAF_INDEX: leaf index
+* \param num_iteration number of iteration for prediction, <= 0 means no limit
+* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
+* \param out_len len of output result
+* \param out_result used to set a pointer to array, should allocate memory before call this function
+* \return 0 when succeed, -1 when failure happens
+*/
+LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForMats(BoosterHandle handle,
+                                                 const void** data,
+                                                 int data_type,
+                                                 int32_t nrow,
+                                                 int32_t ncol,
+                                                 int predict_type,
+                                                 int num_iteration,
+                                                 const char* parameter,
+                                                 int64_t* out_len,
+                                                 double* out_result);
+
 /*!
 * \brief save model into file
 * \param handle handle

src/c_api.cpp

@@ -389,6 +389,9 @@ RowFunctionFromDenseMatric(const void* data, int num_row, int num_col, int data_
 std::function<std::vector<std::pair<int, double>>(int row_idx)>
 RowPairFunctionFromDenseMatric(const void* data, int num_row, int num_col, int data_type, int is_row_major);
 
+std::function<std::vector<std::pair<int, double>>(int row_idx)>
+RowPairFunctionFromDenseRows(const void** data, int num_col, int data_type);
+
 std::function<std::vector<std::pair<int, double>>(int idx)>
 RowFunctionFromCSR(const void* indptr, int indptr_type, const int32_t* indices,
                    const void* data, int data_type, int64_t nindptr, int64_t nelem);
@@ -1416,6 +1419,30 @@ int LGBM_BoosterPredictForMatSingleRow(BoosterHandle handle,
 }
 
 
+int LGBM_BoosterPredictForMats(BoosterHandle handle,
+                               const void** data,
+                               int data_type,
+                               int32_t nrow,
+                               int32_t ncol,
+                               int predict_type,
+                               int num_iteration,
+                               const char* parameter,
+                               int64_t* out_len,
+                               double* out_result) {
+  API_BEGIN();
+  auto param = Config::Str2Map(parameter);
+  Config config;
+  config.Set(param);
+  if (config.num_threads > 0) {
+    omp_set_num_threads(config.num_threads);
+  }
+  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
+  auto get_row_fun = RowPairFunctionFromDenseRows(data, ncol, data_type);
+  ref_booster->Predict(num_iteration, predict_type, nrow, get_row_fun,
+                       config, out_result, out_len);
+  API_END();
+}
+
 int LGBM_BoosterSaveModel(BoosterHandle handle,
                           int start_iteration,
                           int num_iteration,
@@ -1589,6 +1616,22 @@ RowPairFunctionFromDenseMatric(const void* data, int num_row, int num_col, int d
   return nullptr;
 }
 
+// data is array of pointers to individual rows
+std::function<std::vector<std::pair<int, double>>(int row_idx)>
+RowPairFunctionFromDenseRows(const void** data, int num_col, int data_type) {
+  return [=](int row_idx) {
+    auto inner_function = RowFunctionFromDenseMatric(data[row_idx], 1, num_col, data_type, /* is_row_major */ true);
+    auto raw_values = inner_function(0);
+    std::vector<std::pair<int, double>> ret;
+    for (int i = 0; i < static_cast<int>(raw_values.size()); ++i) {
+      if (std::fabs(raw_values[i]) > kZeroThreshold || std::isnan(raw_values[i])) {
+        ret.emplace_back(i, raw_values[i]);
+      }
+    }
+    return ret;
+  };
+}
+
 std::function<std::vector<std::pair<int, double>>(int idx)>
 RowFunctionFromCSR(const void* indptr, int indptr_type, const int32_t* indices, const void* data, int data_type, int64_t , int64_t ) {
   if (data_type == C_API_DTYPE_FLOAT32) {