bugfix and refactoring

Author: mathias-von-ottenbreit

aplr/__init__.py

@@ -1 +1 @@
-from .aplr import *
+from .aplr import *

aplr/aplr.py

@@ -1,7 +1,7 @@
 #pragma once
 #include <limits>
 
-const double NAN_DOUBLE{ std::numeric_limits<double>::quiet_NaN() };
+const double NAN_DOUBLE{std::numeric_limits<double>::quiet_NaN()};
 const int MAX_ABS_EXPONENT_TO_APPLY_ON_LINEAR_PREDICTOR_IN_LOGIT_MODEL{std::min(16, std::numeric_limits<double>::max_exponent10)};
 const std::string MSE_LOSS_FUNCTION{"mse"};
 const size_t MIN_CATEGORIES_IN_CLASSIFIER{2};

cpp/APLRClassifier.h

@@ -10,48 +10,48 @@ using namespace Eigen;
 
 int main()
 {
-    //Model
+    // Model
     APLRRegressor model{APLRRegressor()};
-    model.m=100;
-    model.v=0.5;
-    model.bins=300;
-    model.n_jobs=0;
-    model.loss_function="mse";
-    model.verbosity=3;
-    model.min_observations_in_split=10;
-    //model.max_interaction_level=0;
-    model.max_interaction_level=100;
-    model.max_interactions=30;
-    model.ineligible_boosting_steps_added=10;
-    model.max_eligible_terms=5;
-
-    //Data    
+    model.m = 100;
+    model.v = 0.5;
+    model.bins = 300;
+    model.n_jobs = 0;
+    model.loss_function = "mse";
+    model.verbosity = 3;
+    model.min_observations_in_split = 10;
+    // model.max_interaction_level=0;
+    model.max_interaction_level = 100;
+    model.max_interactions = 30;
+    model.ineligible_boosting_steps_added = 10;
+    model.max_eligible_terms = 5;
+
+    // Data
     MatrixXd X_train{load_csv_into_eigen_matrix<MatrixXd>("X_train.csv")};
-    MatrixXd X_test{load_csv_into_eigen_matrix<MatrixXd>("X_test.csv")}; 
-    VectorXd y_train{load_csv_into_eigen_matrix<MatrixXd>("y_train.csv")};    
-    VectorXd y_test{load_csv_into_eigen_matrix<MatrixXd>("y_test.csv")}; 
+    MatrixXd X_test{load_csv_into_eigen_matrix<MatrixXd>("X_test.csv")};
+    VectorXd y_train{load_csv_into_eigen_matrix<MatrixXd>("y_train.csv")};
+    VectorXd y_test{load_csv_into_eigen_matrix<MatrixXd>("y_test.csv")};
 
-    VectorXd sample_weight{VectorXd::Constant(y_train.size(),1.0)};
-    //VectorXd sample_weight{VectorXd::Random(y_train.size()).cwiseAbs()};
+    VectorXd sample_weight{VectorXd::Constant(y_train.size(), 1.0)};
+    // VectorXd sample_weight{VectorXd::Random(y_train.size()).cwiseAbs()};
 
-    //Fitting
+    // Fitting
     clock_t time_req{clock()};
-    //model.fit(X_train,y_train);
-    model.fit(X_train,y_train,sample_weight);
-    time_req=clock()-time_req;
-    std::cout<<"time elapsed: "<<std::to_string(time_req)<<"\n\n";
-    
+    // model.fit(X_train,y_train);
+    model.fit(X_train, y_train, sample_weight);
+    time_req = clock() - time_req;
+    std::cout << "time elapsed: " << std::to_string(time_req) << "\n\n";
+
     VectorXd predictions{model.predict(X_test)};
 
-    //Saving results
-    save_as_csv_file("output.csv",predictions);
-    std::cout<<"min validation_error "<<model.validation_error_steps.minCoeff()<<"\n\n";
-    std::cout<<is_approximately_equal(model.validation_error_steps.minCoeff(),6.32895,0.00001)<<"\n";
+    // Saving results
+    save_as_csv_file("output.csv", predictions);
+    std::cout << "min validation_error " << model.validation_error_steps.minCoeff() << "\n\n";
+    std::cout << is_approximately_equal(model.validation_error_steps.minCoeff(), 6.32895, 0.00001) << "\n";
 
-    std::cout<<"mean prediction "<<predictions.mean()<<"\n\n";
-    std::cout<<is_approximately_equal(predictions.mean(),23.587,0.0001)<<"\n";
+    std::cout << "mean prediction " << predictions.mean() << "\n\n";
+    std::cout << is_approximately_equal(predictions.mean(), 23.587, 0.0001) << "\n";
 
-    std::cout<<"best_m: "<<model.m<<"\n";
+    std::cout << "best_m: " << model.m << "\n";
 
-    std::cout<<"test";
+    std::cout << "test";
 }