From 553827ef405041f57bde8ae2c31159853dbc7a63 Mon Sep 17 00:00:00 2001
From: Thomas Purcell <purcell@fhi-berlin.mpg.de>
Date: Mon, 8 Jun 2020 14:21:22 +0200
Subject: [PATCH] Bug Fixes
typos when introducing the test set led to problems
---
src/descriptor_identifier/Model/Model.cpp | 27 ++++++++++++-------
src/descriptor_identifier/Model/Model.hpp | 6 ++---
.../negative_exponential.cpp | 6 +++--
.../allowed_operator_nodes/sin.cpp | 4 +--
.../allowed_operator_nodes/subtract.hpp | 2 +-
src/inputs/InputParser.cpp | 1 +
src/main.cpp | 9 +++++--
7 files changed, 36 insertions(+), 19 deletions(-)
diff --git a/src/descriptor_identifier/Model/Model.cpp b/src/descriptor_identifier/Model/Model.cpp
index 3a3e09ae..95cbb455 100644
--- a/src/descriptor_identifier/Model/Model.cpp
+++ b/src/descriptor_identifier/Model/Model.cpp
@@ -22,11 +22,12 @@ Model::Model(std::vector<double> prop_train, std::vector<double> prop_test, std:
for(int ff = 0; ff < feats.size(); ++ff)
{
std::copy_n(feats[ff]->value_ptr(), _n_samp_train, _D_train.data() + ff * _n_samp_train);
- std::copy_n(feats[ff]->test_value_ptr(), _n_samp_test, _D_test.data() + ff * _n_samp_test);
std::copy_n(feats[ff]->value_ptr(), _n_samp_train, a.data() + ff * _n_samp_train);
+
+ if(_n_samp_test > 0)
+ std::copy_n(feats[ff]->test_value_ptr(), _n_samp_test, _D_test.data() + ff * _n_samp_test);
}
std::copy_n(a.data() + feats.size() * _n_samp_train, _n_samp_train, _D_train.data() + feats.size() * _n_samp_train);
- std::copy_n(a.data() + feats.size() * _n_samp_train, _n_samp_test, _D_test.data() + feats.size() * _n_samp_test);
std::vector<double> s(_n_dim, 0.0);
std::vector<double> work(_n_dim * _n_samp_train, 0.0);
@@ -37,10 +38,14 @@ Model::Model(std::vector<double> prop_train, std::vector<double> prop_test, std:
std::copy_n(prop_train.begin(), _n_dim, _coefs.data());
dgemv_('N', _n_samp_train, _n_dim, 1.0, _D_train.data(), _n_samp_train, _coefs.data(), 1, 0.0, _prop_train_est.data(), 1);
- dgemv_('N', _n_samp_test, _n_dim, 1.0, _D_test.data(), _n_samp_test, _coefs.data(), 1, 0.0, _prop_test_est.data(), 1);
-
std::transform(_prop_train_est.begin(), _prop_train_est.end(), _prop_train.data(), _train_error.data(), std::minus<double>());
- std::transform(_prop_test_est.begin(), _prop_test_est.end(), _prop_test.data(), _test_error.data(), std::minus<double>());
+ if(_n_samp_test > 0)
+ {
+ std::copy_n(std::vector<double>(_n_samp_test, 1.0).data(), _n_samp_test, _D_test.data() + feats.size() * _n_samp_test);
+ dgemv_('N', _n_samp_test, _n_dim, 1.0, _D_test.data(), _n_samp_test, _coefs.data(), 1, 0.0, _prop_test_est.data(), 1);
+ std::transform(_prop_test_est.begin(), _prop_test_est.end(), _prop_test.data(), _test_error.data(), std::minus<double>());
+ }
+
}
std::string Model::toString() const
@@ -67,7 +72,7 @@ void Model::train_to_file(std::string filename)
out_file_stream.open(filename);
out_file_stream << "# " << toString() << std::endl;
- out_file_stream << "# RMSE: " << rmse() << "; Max AE( " << max_ae() << std::endl;
+ out_file_stream << "# RMSE: " << rmse() << "; Max AE: " << max_ae() << std::endl;
out_file_stream << "# coeffs:";
for(auto& coef: _coefs)
out_file_stream << " " << std::setw(24) << std::setprecision(18) << coef << ";";
@@ -86,7 +91,7 @@ void Model::train_to_file(std::string filename)
out_file_stream.close();
}
-void Model::test_to_file(std::string filename)
+void Model::test_to_file(std::string filename, std::vector<int> test_inds)
{
boost::filesystem::path p(filename.c_str());
boost::filesystem::create_directories(p.remove_filename());
@@ -95,6 +100,10 @@ void Model::test_to_file(std::string filename)
out_file_stream.open(filename);
out_file_stream << "# " << toString() << std::endl;
+ out_file_stream << "# Testing Indexes: [" << test_inds[0];
+ for(int ss = 1; ss < _n_samp_test; ++ss)
+ out_file_stream << ", " << test_inds[ss];
+ out_file_stream << "]" << std::endl;
out_file_stream << "# RMSE: " << test_rmse() << "; Max AE: " << test_max_ae() << std::endl;
out_file_stream << "# coeffs:";
for(auto& coef: _coefs)
@@ -107,8 +116,8 @@ void Model::test_to_file(std::string filename)
for(int ss = 0; ss < _n_samp_test; ++ss)
{
out_file_stream << std::setw(24) << std::setprecision(18) << _prop_test[ss] << std::setw(24) << std::setprecision(18) << _prop_test_est[ss];
- for(int ff = 0; ff < _n_dim - 1; ++ff)
- out_file_stream << std::setw(24) << std::setprecision(18) << _D_test[ss + ff * _n_samp_train];
+ for(int ff = 0; ff < _feats.size(); ++ff)
+ out_file_stream << std::setw(24) << std::setprecision(18) << _feats[ff]->test_value()[ss];
out_file_stream << std::endl;
}
out_file_stream.close();
diff --git a/src/descriptor_identifier/Model/Model.hpp b/src/descriptor_identifier/Model/Model.hpp
index 208664ad..574a8abb 100644
--- a/src/descriptor_identifier/Model/Model.hpp
+++ b/src/descriptor_identifier/Model/Model.hpp
@@ -77,19 +77,19 @@ public:
*/
inline double max_ae()
{
- return *std::max_element(_train_error.data(), _train_error.data() + _n_samp_train, [](double d1, double d2){return std::abs(d1) < std::abs(d2);});
+ return std::abs(*std::max_element(_train_error.data(), _train_error.data() + _n_samp_train, [](double d1, double d2){return std::abs(d1) < std::abs(d2);}));
}
inline double test_max_ae()
{
- return *std::max_element(_test_error.data(), _test_error.data() + _n_samp_test, [](double d1, double d2){return std::abs(d1) < std::abs(d2);});
+ return std::abs(*std::max_element(_test_error.data(), _test_error.data() + _n_samp_test, [](double d1, double d2){return std::abs(d1) < std::abs(d2);}));
}
/**
* @brief Print model to a file
*/
- void test_to_file(std::string filename);
+ void test_to_file(std::string filename, std::vector<int> test_inds);
/**
* @brief Print model to a file
diff --git a/src/feature_creation/node/operator_nodes/allowed_operator_nodes/negative_exponential.cpp b/src/feature_creation/node/operator_nodes/allowed_operator_nodes/negative_exponential.cpp
index b4761ebe..df28a9e1 100644
--- a/src/feature_creation/node/operator_nodes/allowed_operator_nodes/negative_exponential.cpp
+++ b/src/feature_creation/node/operator_nodes/allowed_operator_nodes/negative_exponential.cpp
@@ -13,9 +13,10 @@ NegExpNode::NegExpNode(std::vector<node_ptr> feats, int rung, int feat_ind):
throw InvalidFeatureException();
set_value();
-
if(is_nan() || is_const())
throw InvalidFeatureException();
+
+ set_test_value();
}
NegExpNode::NegExpNode(node_ptr feat, int rung, int feat_ind):
@@ -28,9 +29,10 @@ NegExpNode::NegExpNode(node_ptr feat, int rung, int feat_ind):
throw InvalidFeatureException();
set_value();
-
if(is_nan() || is_const())
throw InvalidFeatureException();
+
+ set_test_value();
}
void NegExpNode::update_add_sub_leaves(std::map<std::string, int>& add_sub_leaves, int pl_mn, int& expected_abs_tot)
diff --git a/src/feature_creation/node/operator_nodes/allowed_operator_nodes/sin.cpp b/src/feature_creation/node/operator_nodes/allowed_operator_nodes/sin.cpp
index 3ab1f7e5..3aedd073 100644
--- a/src/feature_creation/node/operator_nodes/allowed_operator_nodes/sin.cpp
+++ b/src/feature_creation/node/operator_nodes/allowed_operator_nodes/sin.cpp
@@ -16,7 +16,7 @@ SinNode::SinNode(std::vector<node_ptr> feats, int rung, int feat_ind):
if(is_nan() || is_const())
throw InvalidFeatureException();
- set_test_value();
+ set_test_value();
}
SinNode::SinNode(node_ptr feat, int rung, int feat_ind):
@@ -32,7 +32,7 @@ SinNode::SinNode(node_ptr feat, int rung, int feat_ind):
if(is_nan() || is_const())
throw InvalidFeatureException();
- set_test_value();
+ set_test_value();
}
void SinNode::update_add_sub_leaves(std::map<std::string, int>& add_sub_leaves, int pl_mn, int& expected_abs_tot)
diff --git a/src/feature_creation/node/operator_nodes/allowed_operator_nodes/subtract.hpp b/src/feature_creation/node/operator_nodes/allowed_operator_nodes/subtract.hpp
index 2c946896..8883fe3e 100644
--- a/src/feature_creation/node/operator_nodes/allowed_operator_nodes/subtract.hpp
+++ b/src/feature_creation/node/operator_nodes/allowed_operator_nodes/subtract.hpp
@@ -33,7 +33,7 @@ public:
inline void set_test_value(int offset = -1)
{
offset = (offset == -1) ? rung() : offset;
- allowed_op_funcs::mult(_n_test_samp, _feats[0]->test_value_ptr(offset + 2), _feats[1]->test_value_ptr(offset + 1), node_value_arrs::get_test_value_ptr(_arr_ind, offset));
+ allowed_op_funcs::sub(_n_test_samp, _feats[0]->test_value_ptr(offset + 2), _feats[1]->test_value_ptr(offset + 1), node_value_arrs::get_test_value_ptr(_arr_ind, offset));
}
/**
diff --git a/src/inputs/InputParser.cpp b/src/inputs/InputParser.cpp
index f362c51a..d2ce52ef 100644
--- a/src/inputs/InputParser.cpp
+++ b/src/inputs/InputParser.cpp
@@ -31,6 +31,7 @@ InputParser::InputParser(boost::property_tree::ptree IP, std::string fn, std::sh
std::shuffle (indexes.begin(), indexes.end(), std::default_random_engine(seed));
std::copy_n(indexes.begin(), _n_leave_out, _leave_out_inds.begin());
+ std::sort(_leave_out_inds.begin(), _leave_out_inds.end());
}
else if((_n_leave_out == 0) && (_leave_out_inds.size() > 0))
_n_leave_out = _leave_out_inds.size();
diff --git a/src/main.cpp b/src/main.cpp
index 7d51ce4f..a23cff94 100644
--- a/src/main.cpp
+++ b/src/main.cpp
@@ -44,12 +44,17 @@ int main(int argc, char const *argv[])
{
for(int ii = 0; ii < sisso.models().size(); ++ii)
{
- std::cout << sisso.models()[ii][0].rmse() << std::endl;
+ std::cout << "Train RMSE: " << sisso.models()[ii][0].rmse();
+ if(IP._prop_test.size() > 0)
+ std::cout << "; Test RMSE: " << sisso.models()[ii][0].test_rmse() << std::endl;
+ else
+ std::cout << std::endl;
std::cout << sisso.models()[ii][0] << "\n" << std::endl;
for(int jj = 0; jj < sisso.models()[ii].size(); ++jj)
{
sisso.models()[ii][jj].train_to_file("models/train_dim_" + std::to_string(ii) + "_model_" + std::to_string(jj) + ".dat");
- sisso.models()[ii][jj].test_to_file("models/test_dim_" + std::to_string(ii) + "_model_" + std::to_string(jj) + ".dat");
+ if(IP._prop_test.size() > 0)
+ sisso.models()[ii][jj].test_to_file("models/test_dim_" + std::to_string(ii) + "_model_" + std::to_string(jj) + ".dat", IP._leave_out_inds);
}
}
}
--
GitLab