Fix xgboost error in predict/predict_proba

cmake/modules/CodeCoverage.cmake

@@ -137,7 +137,7 @@
 
 include(CMakeParseArguments)
 
-option(CODE_COVERAGE_VERBOSE "Verbose information" FALSE)
+option(CODE_COVERAGE_VERBOSE "Verbose information" TRUE)
 
 # Check prereqs
 find_program( GCOV_PATH gcov )
@@ -160,8 +160,12 @@ foreach(LANG ${LANGUAGES})
     endif()
   elseif(NOT "${CMAKE_${LANG}_COMPILER_ID}" MATCHES "GNU"
          AND NOT "${CMAKE_${LANG}_COMPILER_ID}" MATCHES "(LLVM)?[Ff]lang")
+         if ("${LANG}" MATCHES "CUDA")
+             message(STATUS "Ignoring CUDA")
+        else()
             message(FATAL_ERROR "Compiler is not GNU or Flang! Aborting...")
         endif()
+  endif()
 endforeach()
 
 set(COVERAGE_COMPILER_FLAGS "-g --coverage"

pyclfs/PyClassifier.cc

@@ -93,12 +93,20 @@ namespace pywrap {
             PyErr_Print();
             throw std::runtime_error("Error creating object for predict in " + module + " and class " + className);
         }
+        if (xgboost) {
+            long* data = reinterpret_cast<long*>(prediction.get_data());
+            std::vector<int> vPrediction(data, data + prediction.shape(0));
+            auto resultTensor = torch::tensor(vPrediction, torch::kInt32);
+            Py_XDECREF(incoming);
+            return resultTensor;
+        } else {
             int* data = reinterpret_cast<int*>(prediction.get_data());
             std::vector<int> vPrediction(data, data + prediction.shape(0));
             auto resultTensor = torch::tensor(vPrediction, torch::kInt32);
             Py_XDECREF(incoming);
             return resultTensor;
         }
+    }
     torch::Tensor PyClassifier::predict_proba(torch::Tensor& X)
     {
         int dimension = X.size(1);
@@ -118,12 +126,20 @@ namespace pywrap {
             PyErr_Print();
             throw std::runtime_error("Error creating object for predict_proba in " + module + " and class " + className);
         }
+        if (xgboost) {
+            float* data = reinterpret_cast<float*>(prediction.get_data());
+            std::vector<float> vPrediction(data, data + prediction.shape(0) * prediction.shape(1));
+            auto resultTensor = torch::tensor(vPrediction, torch::kFloat64).reshape({ prediction.shape(0), prediction.shape(1) });
+            Py_XDECREF(incoming);
+            return resultTensor;
+        } else {
             double* data = reinterpret_cast<double*>(prediction.get_data());
             std::vector<double> vPrediction(data, data + prediction.shape(0) * prediction.shape(1));
             auto resultTensor = torch::tensor(vPrediction, torch::kFloat64).reshape({ prediction.shape(0), prediction.shape(1) });
             Py_XDECREF(incoming);
             return resultTensor;
         }
+    }
     float PyClassifier::score(torch::Tensor& X, torch::Tensor& y)
     {
         auto [Xn, yn] = tensors2numpy(X, y);

pyclfs/PyClassifier.h

@@ -49,6 +49,7 @@ namespace pywrap {
         nlohmann::json hyperparameters;
         void trainModel(const torch::Tensor& weights, const bayesnet::Smoothing_t smoothing = bayesnet::Smoothing_t::NONE) override {};
         std::vector<std::string> notes;
+        bool xgboost = false;
     private:
         PyWrap* pyWrap;
         std::string module;

pyclfs/XGBoost.cc

@@ -5,5 +5,6 @@ namespace pywrap {
     XGBoost::XGBoost() : PyClassifier("xgboost", "XGBClassifier", true)
     {
         validHyperparameters = { "tree_method", "early_stopping_rounds", "n_jobs" };
+        xgboost = true;
     }
 } /* namespace pywrap */

tests/CMakeLists.txt

@@ -3,14 +3,15 @@ if(ENABLE_TESTING)
     include_directories(
         ${PyClassifiers_SOURCE_DIR}
         ${PyClassifiers_SOURCE_DIR}/lib/Files
-        ${PyClassifiers_SOURCE_DIR}/lib/mdlp
+        ${PyClassifiers_SOURCE_DIR}/lib/mdlp/src
         ${PyClassifiers_SOURCE_DIR}/lib/json/include
         ${Python3_INCLUDE_DIRS}
         ${TORCH_INCLUDE_DIRS}
+        ${CMAKE_BINARY_DIR}/configured_files/include
         /usr/local/include
     )
     file(GLOB_RECURSE PyClassifiers_SOURCES "${PyClassifiers_SOURCE_DIR}/pyclfs/*.cc")
     set(TEST_SOURCES_PYCLASSIFIERS TestPythonClassifiers.cc TestUtils.cc ${PyClassifiers_SOURCES})
     add_executable(${TEST_PYCLASSIFIERS} ${TEST_SOURCES_PYCLASSIFIERS})
-    target_link_libraries(${TEST_PYCLASSIFIERS} PUBLIC "${TORCH_LIBRARIES}" ${Python3_LIBRARIES} ${LIBTORCH_PYTHON} Boost::boost Boost::python Boost::numpy ArffFiles mdlp Catch2::Catch2WithMain)
+    target_link_libraries(${TEST_PYCLASSIFIERS} PUBLIC "${TORCH_LIBRARIES}" ${Python3_LIBRARIES} ${LIBTORCH_PYTHON} Boost::boost Boost::python Boost::numpy ArffFiles fimdlp Catch2::Catch2WithMain)
 endif(ENABLE_TESTING)

tests/TestPythonClassifiers.cc

@@ -33,8 +33,8 @@ TEST_CASE("Test Python Classifiers score", "[PyClassifiers]")
         {"RandomForest", new pywrap::RandomForest()}
     };
     map<std::string, std::string> versions = {
-        {"ODTE", "1.0.0"},
-        {"STree", "1.3.2"},
+        {"ODTE", "1.0.0-1"},
+        {"STree", "1.4.0"},
         {"SVC", "1.5.1"},
         {"RandomForest", "1.5.1"}
     };
@@ -116,23 +116,30 @@ TEST_CASE("XGBoost", "[PyClassifiers]")
     clf.setHyperparameters(hyperparameters);
     auto score = clf.score(raw.Xt, raw.yt);
     REQUIRE(score == Catch::Approx(0.98).epsilon(raw.epsilon));
+    std::cout << "XGBoost score: " << score << std::endl;
+}
+TEST_CASE("XGBoost predict proba", "[PyClassifiers]")
+{
+    auto raw = RawDatasets("iris", true);
+    auto clf = pywrap::XGBoost();
+    clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
+    // nlohmann::json hyperparameters = { "n_jobs=1" };
+    // clf.setHyperparameters(hyperparameters);
+    auto predict_proba = clf.predict_proba(raw.Xt);
+    auto predict = clf.predict(raw.Xt);
+    // std::cout << "Predict proba: " << predict_proba << std::endl;
+    // std::cout << "Predict proba size: " << predict_proba.sizes() << std::endl;
+    // assert(predict.size(0) == predict_proba.size(0));
+    for (int row = 0; row < predict_proba.size(0); row++) {
+        // auto sum = 0.0;
+        // std::cout << "Row " << std::setw(3) << row << ": ";
+        // for (int col = 0; col < predict_proba.size(1); col++) {
+        //     std::cout << std::setw(9) << std::fixed << std::setprecision(7) << predict_proba[row][col].item<double>() << " ";
+        //     sum += predict_proba[row][col].item<double>();
+        // }
+        // std::cout << " -> " << std::setw(9) << std::fixed << std::setprecision(7) << sum << " -> " << torch::argmax(predict_proba[row]).item<int>() << " = " << predict[row].item<int>() << std::endl;
+        //     // REQUIRE(sum == Catch::Approx(1.0).epsilon(raw.epsilon));
+        REQUIRE(torch::argmax(predict_proba[row]).item<int>() == predict[row].item<int>());
+        REQUIRE(torch::sum(predict_proba[row]).item<double>() == Catch::Approx(1.0).epsilon(raw.epsilon));
+    }
 }
-// TEST_CASE("XGBoost predict proba", "[PyClassifiers]")
-// {
-//     auto raw = RawDatasets("iris", true);
-//     auto clf = pywrap::XGBoost();
-//     clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
-//     // nlohmann::json hyperparameters = { "n_jobs=1" };
-//     // clf.setHyperparameters(hyperparameters);
-//     auto predict = clf.predict(raw.Xt);
-//     for (int row = 0; row < predict.size(0); row++) {
-//         auto sum = 0.0;
-//         for (int col = 0; col < predict.size(1); col++) {
-//             std::cout << std::setw(12) << std::setprecision(10) << predict[row][col].item<double>() << " ";
-//             sum += predict[row][col].item<int>();
-//         }
-//         std::cout << std::endl;
-//         // REQUIRE(sum == Catch::Approx(1.0).epsilon(raw.epsilon));
-//     }
-//     std::cout << predict << std::endl;
-// }