Compare commits
42 Commits
reports
...
solveexcep
Author | SHA1 | Date | |
---|---|---|---|
c35030f137
|
|||
182b07ed90
|
|||
7806f961e2
|
|||
7c3e315ae7
|
|||
284ef6dfd1
|
|||
1c6af619b5
|
|||
86ffdfd6f3
|
|||
d82148079d
|
|||
067430fd1b
|
|||
f5d0d16365 | |||
97ca8ac084
|
|||
1c1385b768
|
|||
35432b6294
|
|||
c59dd30e53
|
|||
d2da0ddb88
|
|||
8066701c3c
|
|||
0f66ac73d0
|
|||
4370bf51d7
|
|||
2b7353b9e0
|
|||
b686b3c9c3
|
|||
2dd04a6c44
|
|||
1da83662d0
|
|||
3ac9593c65
|
|||
6b317accf1
|
|||
4964aab722
|
|||
7a6ec73d63 | |||
1a534888d6
|
|||
59ffd179f4
|
|||
9972738deb
|
|||
bafcb26bb6
|
|||
2d7999d5f2
|
|||
a6bb22dfb5
|
|||
704dc937be
|
|||
a3e665eed6
|
|||
918a7b4180
|
|||
80b20f35b4
|
|||
4d4780c1d5
|
|||
fa612c531e
|
|||
24b68f9ae2
|
|||
a062ebf445 | |||
f26ea1f0ac
|
|||
af0419c9da
|
31
.clang-uml
Normal file
31
.clang-uml
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
compilation_database_dir: build
|
||||||
|
output_directory: puml
|
||||||
|
diagrams:
|
||||||
|
BayesNet:
|
||||||
|
type: class
|
||||||
|
glob:
|
||||||
|
- src/BayesNet/*.cc
|
||||||
|
- src/Platform/*.cc
|
||||||
|
using_namespace: bayesnet
|
||||||
|
include:
|
||||||
|
namespaces:
|
||||||
|
- bayesnet
|
||||||
|
- platform
|
||||||
|
plantuml:
|
||||||
|
after:
|
||||||
|
- "note left of {{ alias(\"MyProjectMain\") }}: Main class of myproject library."
|
||||||
|
sequence:
|
||||||
|
type: sequence
|
||||||
|
glob:
|
||||||
|
- src/Platform/main.cc
|
||||||
|
combine_free_functions_into_file_participants: true
|
||||||
|
using_namespace:
|
||||||
|
- std
|
||||||
|
- bayesnet
|
||||||
|
- platform
|
||||||
|
include:
|
||||||
|
paths:
|
||||||
|
- src/BayesNet
|
||||||
|
- src/Platform
|
||||||
|
start_from:
|
||||||
|
- function: main(int,const char **)
|
1
.gitignore
vendored
1
.gitignore
vendored
@@ -35,3 +35,4 @@ build/
|
|||||||
*.dSYM/**
|
*.dSYM/**
|
||||||
cmake-build*/**
|
cmake-build*/**
|
||||||
.idea
|
.idea
|
||||||
|
puml/**
|
||||||
|
3
.gitmodules
vendored
3
.gitmodules
vendored
@@ -10,3 +10,6 @@
|
|||||||
[submodule "lib/json"]
|
[submodule "lib/json"]
|
||||||
path = lib/json
|
path = lib/json
|
||||||
url = https://github.com/nlohmann/json.git
|
url = https://github.com/nlohmann/json.git
|
||||||
|
[submodule "lib/openXLSX"]
|
||||||
|
path = lib/openXLSX
|
||||||
|
url = https://github.com/troldal/OpenXLSX.git
|
||||||
|
21
.vscode/launch.json
vendored
21
.vscode/launch.json
vendored
@@ -10,7 +10,7 @@
|
|||||||
"-d",
|
"-d",
|
||||||
"iris",
|
"iris",
|
||||||
"-m",
|
"-m",
|
||||||
"KDB",
|
"TANLd",
|
||||||
"-s",
|
"-s",
|
||||||
"271",
|
"271",
|
||||||
"-p",
|
"-p",
|
||||||
@@ -25,14 +25,17 @@
|
|||||||
"program": "${workspaceFolder}/build/src/Platform/main",
|
"program": "${workspaceFolder}/build/src/Platform/main",
|
||||||
"args": [
|
"args": [
|
||||||
"-m",
|
"-m",
|
||||||
"SPODELd",
|
"AODE",
|
||||||
"-p",
|
"-p",
|
||||||
"/Users/rmontanana/Code/discretizbench/datasets",
|
"/home/rmontanana/Code/discretizbench/datasets",
|
||||||
"--stratified",
|
"--stratified",
|
||||||
"-d",
|
"-d",
|
||||||
"iris"
|
"mfeat-morphological",
|
||||||
|
"--discretize"
|
||||||
|
// "--hyperparameters",
|
||||||
|
// "{\"repeatSparent\": true, \"maxModels\": 12}"
|
||||||
],
|
],
|
||||||
"cwd": "/Users/rmontanana/Code/discretizbench",
|
"cwd": "/home/rmontanana/Code/discretizbench",
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"type": "lldb",
|
"type": "lldb",
|
||||||
@@ -45,6 +48,14 @@
|
|||||||
],
|
],
|
||||||
"cwd": "/Users/rmontanana/Code/discretizbench",
|
"cwd": "/Users/rmontanana/Code/discretizbench",
|
||||||
},
|
},
|
||||||
|
{
|
||||||
|
"type": "lldb",
|
||||||
|
"request": "launch",
|
||||||
|
"name": "list",
|
||||||
|
"program": "${workspaceFolder}/build/src/Platform/list",
|
||||||
|
"args": [],
|
||||||
|
"cwd": "/Users/rmontanana/Code/discretizbench",
|
||||||
|
},
|
||||||
{
|
{
|
||||||
"name": "Build & debug active file",
|
"name": "Build & debug active file",
|
||||||
"type": "cppdbg",
|
"type": "cppdbg",
|
||||||
|
23
.vscode/tasks.json
vendored
23
.vscode/tasks.json
vendored
@@ -32,6 +32,29 @@
|
|||||||
],
|
],
|
||||||
"group": "build",
|
"group": "build",
|
||||||
"detail": "Task generated by Debugger."
|
"detail": "Task generated by Debugger."
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"type": "cppbuild",
|
||||||
|
"label": "C/C++: g++ build active file",
|
||||||
|
"command": "/usr/bin/g++",
|
||||||
|
"args": [
|
||||||
|
"-fdiagnostics-color=always",
|
||||||
|
"-g",
|
||||||
|
"${file}",
|
||||||
|
"-o",
|
||||||
|
"${fileDirname}/${fileBasenameNoExtension}"
|
||||||
|
],
|
||||||
|
"options": {
|
||||||
|
"cwd": "${fileDirname}"
|
||||||
|
},
|
||||||
|
"problemMatcher": [
|
||||||
|
"$gcc"
|
||||||
|
],
|
||||||
|
"group": {
|
||||||
|
"kind": "build",
|
||||||
|
"isDefault": true
|
||||||
|
},
|
||||||
|
"detail": "Task generated by Debugger."
|
||||||
}
|
}
|
||||||
]
|
]
|
||||||
}
|
}
|
@@ -1,7 +1,7 @@
|
|||||||
cmake_minimum_required(VERSION 3.20)
|
cmake_minimum_required(VERSION 3.20)
|
||||||
|
|
||||||
project(BayesNet
|
project(BayesNet
|
||||||
VERSION 0.1.0
|
VERSION 0.2.0
|
||||||
DESCRIPTION "Bayesian Network and basic classifiers Library."
|
DESCRIPTION "Bayesian Network and basic classifiers Library."
|
||||||
HOMEPAGE_URL "https://github.com/rmontanana/bayesnet"
|
HOMEPAGE_URL "https://github.com/rmontanana/bayesnet"
|
||||||
LANGUAGES CXX
|
LANGUAGES CXX
|
||||||
@@ -30,7 +30,7 @@ set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TORCH_CXX_FLAGS}")
|
|||||||
option(ENABLE_CLANG_TIDY "Enable to add clang tidy." OFF)
|
option(ENABLE_CLANG_TIDY "Enable to add clang tidy." OFF)
|
||||||
option(ENABLE_TESTING "Unit testing build" OFF)
|
option(ENABLE_TESTING "Unit testing build" OFF)
|
||||||
option(CODE_COVERAGE "Collect coverage from test library" OFF)
|
option(CODE_COVERAGE "Collect coverage from test library" OFF)
|
||||||
|
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
|
||||||
# CMakes modules
|
# CMakes modules
|
||||||
# --------------
|
# --------------
|
||||||
set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules ${CMAKE_MODULE_PATH})
|
set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules ${CMAKE_MODULE_PATH})
|
||||||
@@ -40,8 +40,7 @@ if (CODE_COVERAGE)
|
|||||||
enable_testing()
|
enable_testing()
|
||||||
include(CodeCoverage)
|
include(CodeCoverage)
|
||||||
MESSAGE("Code coverage enabled")
|
MESSAGE("Code coverage enabled")
|
||||||
set(CMAKE_C_FLAGS " ${CMAKE_C_FLAGS} -fprofile-arcs -ftest-coverage")
|
set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage -O0")
|
||||||
set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage")
|
|
||||||
SET(GCC_COVERAGE_LINK_FLAGS " ${GCC_COVERAGE_LINK_FLAGS} -lgcov --coverage")
|
SET(GCC_COVERAGE_LINK_FLAGS " ${GCC_COVERAGE_LINK_FLAGS} -lgcov --coverage")
|
||||||
endif (CODE_COVERAGE)
|
endif (CODE_COVERAGE)
|
||||||
|
|
||||||
@@ -55,6 +54,7 @@ endif (ENABLE_CLANG_TIDY)
|
|||||||
add_git_submodule("lib/mdlp")
|
add_git_submodule("lib/mdlp")
|
||||||
add_git_submodule("lib/argparse")
|
add_git_submodule("lib/argparse")
|
||||||
add_git_submodule("lib/json")
|
add_git_submodule("lib/json")
|
||||||
|
add_git_submodule("lib/openXLSX")
|
||||||
|
|
||||||
# Subdirectories
|
# Subdirectories
|
||||||
# --------------
|
# --------------
|
||||||
|
17
Makefile
17
Makefile
@@ -11,17 +11,30 @@ setup: ## Install dependencies for tests and coverage
|
|||||||
pip install gcovr; \
|
pip install gcovr; \
|
||||||
fi
|
fi
|
||||||
|
|
||||||
|
dest ?= ../discretizbench
|
||||||
|
copy: ## Copy binary files to selected folder
|
||||||
|
@echo "Destination folder: $(dest)"
|
||||||
|
make build
|
||||||
|
@echo ">>> Copying files to $(dest)"
|
||||||
|
@cp build/src/Platform/main $(dest)
|
||||||
|
@cp build/src/Platform/list $(dest)
|
||||||
|
@cp build/src/Platform/manage $(dest)
|
||||||
|
@echo ">>> Done"
|
||||||
|
|
||||||
dependency: ## Create a dependency graph diagram of the project (build/dependency.png)
|
dependency: ## Create a dependency graph diagram of the project (build/dependency.png)
|
||||||
cd build && cmake .. --graphviz=dependency.dot && dot -Tpng dependency.dot -o dependency.png
|
cd build && cmake .. --graphviz=dependency.dot && dot -Tpng dependency.dot -o dependency.png
|
||||||
|
|
||||||
build: ## Build the main and BayesNetSample
|
build: ## Build the main and BayesNetSample
|
||||||
cmake --build build -t main -t BayesNetSample -j 32
|
cmake --build build -t main -t BayesNetSample -t manage -t list -j 32
|
||||||
|
|
||||||
clean: ## Clean the debug info
|
clean: ## Clean the debug info
|
||||||
@echo ">>> Cleaning Debug BayesNet ...";
|
@echo ">>> Cleaning Debug BayesNet ...";
|
||||||
find . -name "*.gcda" -print0 | xargs -0 rm
|
find . -name "*.gcda" -print0 | xargs -0 rm
|
||||||
@echo ">>> Done";
|
@echo ">>> Done";
|
||||||
|
|
||||||
|
clang-uml: ## Create uml class and sequence diagrams
|
||||||
|
clang-uml -p --add-compile-flag -I /usr/lib/gcc/x86_64-redhat-linux/8/include/
|
||||||
|
|
||||||
debug: ## Build a debug version of the project
|
debug: ## Build a debug version of the project
|
||||||
@echo ">>> Building Debug BayesNet ...";
|
@echo ">>> Building Debug BayesNet ...";
|
||||||
@if [ -d ./build ]; then rm -rf ./build; fi
|
@if [ -d ./build ]; then rm -rf ./build; fi
|
||||||
@@ -35,7 +48,7 @@ release: ## Build a Release version of the project
|
|||||||
@if [ -d ./build ]; then rm -rf ./build; fi
|
@if [ -d ./build ]; then rm -rf ./build; fi
|
||||||
@mkdir build;
|
@mkdir build;
|
||||||
cmake -S . -B build -D CMAKE_BUILD_TYPE=Release; \
|
cmake -S . -B build -D CMAKE_BUILD_TYPE=Release; \
|
||||||
cmake --build build -t main -t BayesNetSample -j 32;
|
cmake --build build -t main -t BayesNetSample -t manage -t list -j 32;
|
||||||
@echo ">>> Done";
|
@echo ">>> Done";
|
||||||
|
|
||||||
test: ## Run tests
|
test: ## Run tests
|
||||||
|
12
TAN_iris.dot
12
TAN_iris.dot
@@ -1,12 +0,0 @@
|
|||||||
digraph BayesNet {
|
|
||||||
label=<BayesNet >
|
|
||||||
fontsize=30
|
|
||||||
fontcolor=blue
|
|
||||||
labelloc=t
|
|
||||||
layout=circo
|
|
||||||
class [shape=circle, fontcolor=red, fillcolor=lightblue, style=filled ]
|
|
||||||
class -> sepallength class -> sepalwidth class -> petallength class -> petalwidth petallength [shape=circle]
|
|
||||||
petallength -> sepallength petalwidth [shape=circle]
|
|
||||||
sepallength [shape=circle]
|
|
||||||
sepallength -> sepalwidth sepalwidth [shape=circle]
|
|
||||||
sepalwidth -> petalwidth }
|
|
@@ -1 +0,0 @@
|
|||||||
null
|
|
BIN
diagrams/BayesNet.pdf
Executable file
BIN
diagrams/BayesNet.pdf
Executable file
Binary file not shown.
@@ -1,2 +1 @@
|
|||||||
add_library(ArffFiles ArffFiles.cc)
|
add_library(ArffFiles ArffFiles.cc)
|
||||||
#target_link_libraries(BayesNet "${TORCH_LIBRARIES}")
|
|
1
lib/openXLSX
Submodule
1
lib/openXLSX
Submodule
Submodule lib/openXLSX added at b80da42d14
@@ -3,5 +3,6 @@ include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
|
|||||||
include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
|
include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
|
||||||
include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
|
include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
|
||||||
include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
|
include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
|
||||||
|
include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
|
||||||
add_executable(BayesNetSample sample.cc ${BayesNet_SOURCE_DIR}/src/Platform/Folding.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
|
add_executable(BayesNetSample sample.cc ${BayesNet_SOURCE_DIR}/src/Platform/Folding.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
|
||||||
target_link_libraries(BayesNetSample BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
|
target_link_libraries(BayesNetSample BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
|
113
sample/sample.cc
113
sample/sample.cc
@@ -3,13 +3,14 @@
|
|||||||
#include <string>
|
#include <string>
|
||||||
#include <map>
|
#include <map>
|
||||||
#include <argparse/argparse.hpp>
|
#include <argparse/argparse.hpp>
|
||||||
|
#include <nlohmann/json.hpp>
|
||||||
#include "ArffFiles.h"
|
#include "ArffFiles.h"
|
||||||
#include "BayesMetrics.h"
|
#include "BayesMetrics.h"
|
||||||
#include "CPPFImdlp.h"
|
#include "CPPFImdlp.h"
|
||||||
#include "Folding.h"
|
#include "Folding.h"
|
||||||
#include "Models.h"
|
#include "Models.h"
|
||||||
#include "modelRegister.h"
|
#include "modelRegister.h"
|
||||||
|
#include <fstream>
|
||||||
|
|
||||||
using namespace std;
|
using namespace std;
|
||||||
|
|
||||||
@@ -178,59 +179,59 @@ int main(int argc, char** argv)
|
|||||||
cout << "end." << endl;
|
cout << "end." << endl;
|
||||||
auto score = clf->score(Xd, y);
|
auto score = clf->score(Xd, y);
|
||||||
cout << "Score: " << score << endl;
|
cout << "Score: " << score << endl;
|
||||||
// auto graph = clf->graph();
|
auto graph = clf->graph();
|
||||||
// auto dot_file = model_name + "_" + file_name;
|
auto dot_file = model_name + "_" + file_name;
|
||||||
// ofstream file(dot_file + ".dot");
|
ofstream file(dot_file + ".dot");
|
||||||
// file << graph;
|
file << graph;
|
||||||
// file.close();
|
file.close();
|
||||||
// cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
|
cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
|
||||||
// cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
|
cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
|
||||||
// string stratified_string = stratified ? " Stratified" : "";
|
string stratified_string = stratified ? " Stratified" : "";
|
||||||
// cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
|
cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
|
||||||
// cout << "==========================================" << endl;
|
cout << "==========================================" << endl;
|
||||||
// torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
|
torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
|
||||||
// torch::Tensor yt = torch::tensor(y, torch::kInt32);
|
torch::Tensor yt = torch::tensor(y, torch::kInt32);
|
||||||
// for (int i = 0; i < features.size(); ++i) {
|
for (int i = 0; i < features.size(); ++i) {
|
||||||
// Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
|
Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
|
||||||
// }
|
}
|
||||||
// float total_score = 0, total_score_train = 0, score_train, score_test;
|
float total_score = 0, total_score_train = 0, score_train, score_test;
|
||||||
// Fold* fold;
|
platform::Fold* fold;
|
||||||
// if (stratified)
|
if (stratified)
|
||||||
// fold = new StratifiedKFold(nFolds, y, seed);
|
fold = new platform::StratifiedKFold(nFolds, y, seed);
|
||||||
// else
|
else
|
||||||
// fold = new KFold(nFolds, y.size(), seed);
|
fold = new platform::KFold(nFolds, y.size(), seed);
|
||||||
// for (auto i = 0; i < nFolds; ++i) {
|
for (auto i = 0; i < nFolds; ++i) {
|
||||||
// auto [train, test] = fold->getFold(i);
|
auto [train, test] = fold->getFold(i);
|
||||||
// cout << "Fold: " << i + 1 << endl;
|
cout << "Fold: " << i + 1 << endl;
|
||||||
// if (tensors) {
|
if (tensors) {
|
||||||
// auto ttrain = torch::tensor(train, torch::kInt64);
|
auto ttrain = torch::tensor(train, torch::kInt64);
|
||||||
// auto ttest = torch::tensor(test, torch::kInt64);
|
auto ttest = torch::tensor(test, torch::kInt64);
|
||||||
// torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
|
torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
|
||||||
// torch::Tensor ytraint = yt.index({ ttrain });
|
torch::Tensor ytraint = yt.index({ ttrain });
|
||||||
// torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
|
torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
|
||||||
// torch::Tensor ytestt = yt.index({ ttest });
|
torch::Tensor ytestt = yt.index({ ttest });
|
||||||
// clf->fit(Xtraint, ytraint, features, className, states);
|
clf->fit(Xtraint, ytraint, features, className, states);
|
||||||
// auto temp = clf->predict(Xtraint);
|
auto temp = clf->predict(Xtraint);
|
||||||
// score_train = clf->score(Xtraint, ytraint);
|
score_train = clf->score(Xtraint, ytraint);
|
||||||
// score_test = clf->score(Xtestt, ytestt);
|
score_test = clf->score(Xtestt, ytestt);
|
||||||
// } else {
|
} else {
|
||||||
// auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
|
auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
|
||||||
// auto [Xtest, ytest] = extract_indices(test, Xd, y);
|
auto [Xtest, ytest] = extract_indices(test, Xd, y);
|
||||||
// clf->fit(Xtrain, ytrain, features, className, states);
|
clf->fit(Xtrain, ytrain, features, className, states);
|
||||||
// score_train = clf->score(Xtrain, ytrain);
|
score_train = clf->score(Xtrain, ytrain);
|
||||||
// score_test = clf->score(Xtest, ytest);
|
score_test = clf->score(Xtest, ytest);
|
||||||
// }
|
}
|
||||||
// if (dump_cpt) {
|
if (dump_cpt) {
|
||||||
// cout << "--- CPT Tables ---" << endl;
|
cout << "--- CPT Tables ---" << endl;
|
||||||
// clf->dump_cpt();
|
clf->dump_cpt();
|
||||||
// }
|
}
|
||||||
// total_score_train += score_train;
|
total_score_train += score_train;
|
||||||
// total_score += score_test;
|
total_score += score_test;
|
||||||
// cout << "Score Train: " << score_train << endl;
|
cout << "Score Train: " << score_train << endl;
|
||||||
// cout << "Score Test : " << score_test << endl;
|
cout << "Score Test : " << score_test << endl;
|
||||||
// cout << "-------------------------------------------------------------------------------" << endl;
|
cout << "-------------------------------------------------------------------------------" << endl;
|
||||||
// }
|
}
|
||||||
// cout << "**********************************************************************************" << endl;
|
cout << "**********************************************************************************" << endl;
|
||||||
// cout << "Average Score Train: " << total_score_train / nFolds << endl;
|
cout << "Average Score Train: " << total_score_train / nFolds << endl;
|
||||||
// cout << "Average Score Test : " << total_score / nFolds << endl;return 0;
|
cout << "Average Score Test : " << total_score / nFolds << endl;return 0;
|
||||||
}
|
}
|
@@ -2,12 +2,14 @@
|
|||||||
|
|
||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
AODE::AODE() : Ensemble() {}
|
AODE::AODE() : Ensemble() {}
|
||||||
void AODE::buildModel()
|
void AODE::buildModel(const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
models.clear();
|
models.clear();
|
||||||
for (int i = 0; i < features.size(); ++i) {
|
for (int i = 0; i < features.size(); ++i) {
|
||||||
models.push_back(std::make_unique<SPODE>(i));
|
models.push_back(std::make_unique<SPODE>(i));
|
||||||
}
|
}
|
||||||
|
n_models = models.size();
|
||||||
|
significanceModels = vector<double>(n_models, 1.0);
|
||||||
}
|
}
|
||||||
vector<string> AODE::graph(const string& title) const
|
vector<string> AODE::graph(const string& title) const
|
||||||
{
|
{
|
||||||
|
@@ -5,7 +5,7 @@
|
|||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
class AODE : public Ensemble {
|
class AODE : public Ensemble {
|
||||||
protected:
|
protected:
|
||||||
void buildModel() override;
|
void buildModel(const torch::Tensor& weights) override;
|
||||||
public:
|
public:
|
||||||
AODE();
|
AODE();
|
||||||
virtual ~AODE() {};
|
virtual ~AODE() {};
|
||||||
|
@@ -4,9 +4,9 @@
|
|||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
|
AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
|
||||||
AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
|
AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
|
||||||
{
|
{
|
||||||
// This first part should go in a Classifier method called fit_local_discretization o fit_float...
|
checkInput(X_, y_);
|
||||||
features = features_;
|
features = features_;
|
||||||
className = className_;
|
className = className_;
|
||||||
Xf = X_;
|
Xf = X_;
|
||||||
@@ -19,15 +19,16 @@ namespace bayesnet {
|
|||||||
return *this;
|
return *this;
|
||||||
|
|
||||||
}
|
}
|
||||||
void AODELd::buildModel()
|
void AODELd::buildModel(const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
models.clear();
|
models.clear();
|
||||||
for (int i = 0; i < features.size(); ++i) {
|
for (int i = 0; i < features.size(); ++i) {
|
||||||
models.push_back(std::make_unique<SPODELd>(i));
|
models.push_back(std::make_unique<SPODELd>(i));
|
||||||
}
|
}
|
||||||
n_models = models.size();
|
n_models = models.size();
|
||||||
|
significanceModels = vector<double>(n_models, 1.0);
|
||||||
}
|
}
|
||||||
void AODELd::trainModel()
|
void AODELd::trainModel(const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
for (const auto& model : models) {
|
for (const auto& model : models) {
|
||||||
model->fit(Xf, y, features, className, states);
|
model->fit(Xf, y, features, className, states);
|
||||||
|
@@ -8,13 +8,13 @@ namespace bayesnet {
|
|||||||
using namespace std;
|
using namespace std;
|
||||||
class AODELd : public Ensemble, public Proposal {
|
class AODELd : public Ensemble, public Proposal {
|
||||||
protected:
|
protected:
|
||||||
void trainModel() override;
|
void trainModel(const torch::Tensor& weights) override;
|
||||||
void buildModel() override;
|
void buildModel(const torch::Tensor& weights) override;
|
||||||
public:
|
public:
|
||||||
AODELd();
|
AODELd();
|
||||||
AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_) override;
|
AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_) override;
|
||||||
virtual ~AODELd() = default;
|
virtual ~AODELd() = default;
|
||||||
vector<string> graph(const string& name = "AODE") const override;
|
vector<string> graph(const string& name = "AODELd") const override;
|
||||||
static inline string version() { return "0.0.1"; };
|
static inline string version() { return "0.0.1"; };
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
@@ -1,18 +1,20 @@
|
|||||||
#ifndef BASE_H
|
#ifndef BASE_H
|
||||||
#define BASE_H
|
#define BASE_H
|
||||||
#include <torch/torch.h>
|
#include <torch/torch.h>
|
||||||
|
#include <nlohmann/json.hpp>
|
||||||
#include <vector>
|
#include <vector>
|
||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
class BaseClassifier {
|
class BaseClassifier {
|
||||||
protected:
|
protected:
|
||||||
virtual void trainModel() = 0;
|
virtual void trainModel(const torch::Tensor& weights) = 0;
|
||||||
public:
|
public:
|
||||||
// X is nxm vector, y is nx1 vector
|
// X is nxm vector, y is nx1 vector
|
||||||
virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
|
virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
|
||||||
// X is nxm tensor, y is nx1 tensor
|
// X is nxm tensor, y is nx1 tensor
|
||||||
virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
|
virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
|
||||||
virtual BaseClassifier& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
|
virtual BaseClassifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
|
||||||
|
virtual BaseClassifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights) = 0;
|
||||||
virtual ~BaseClassifier() = default;
|
virtual ~BaseClassifier() = default;
|
||||||
torch::Tensor virtual predict(torch::Tensor& X) = 0;
|
torch::Tensor virtual predict(torch::Tensor& X) = 0;
|
||||||
vector<int> virtual predict(vector<vector<int>>& X) = 0;
|
vector<int> virtual predict(vector<vector<int>>& X) = 0;
|
||||||
@@ -23,9 +25,10 @@ namespace bayesnet {
|
|||||||
int virtual getNumberOfStates() const = 0;
|
int virtual getNumberOfStates() const = 0;
|
||||||
vector<string> virtual show() const = 0;
|
vector<string> virtual show() const = 0;
|
||||||
vector<string> virtual graph(const string& title = "") const = 0;
|
vector<string> virtual graph(const string& title = "") const = 0;
|
||||||
const string inline getVersion() const { return "0.1.0"; };
|
const string inline getVersion() const { return "0.2.0"; };
|
||||||
vector<string> virtual topological_order() = 0;
|
vector<string> virtual topological_order() = 0;
|
||||||
void virtual dump_cpt()const = 0;
|
void virtual dump_cpt()const = 0;
|
||||||
|
virtual void setHyperparameters(nlohmann::json& hyperparameters) = 0;
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
@@ -21,6 +21,45 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
|
samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
|
||||||
}
|
}
|
||||||
|
vector<int> Metrics::SelectKBestWeighted(const torch::Tensor& weights, bool ascending, unsigned k)
|
||||||
|
{
|
||||||
|
// Return the K Best features
|
||||||
|
auto n = samples.size(0) - 1;
|
||||||
|
if (k == 0) {
|
||||||
|
k = n;
|
||||||
|
}
|
||||||
|
// compute scores
|
||||||
|
scoresKBest.clear();
|
||||||
|
featuresKBest.clear();
|
||||||
|
auto label = samples.index({ -1, "..." });
|
||||||
|
for (int i = 0; i < n; ++i) {
|
||||||
|
scoresKBest.push_back(mutualInformation(label, samples.index({ i, "..." }), weights));
|
||||||
|
featuresKBest.push_back(i);
|
||||||
|
}
|
||||||
|
// sort & reduce scores and features
|
||||||
|
if (ascending) {
|
||||||
|
sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
|
||||||
|
{ return scoresKBest[i] < scoresKBest[j]; });
|
||||||
|
sort(scoresKBest.begin(), scoresKBest.end(), std::less<double>());
|
||||||
|
if (k < n) {
|
||||||
|
for (int i = 0; i < n - k; ++i) {
|
||||||
|
featuresKBest.erase(featuresKBest.begin());
|
||||||
|
scoresKBest.erase(scoresKBest.begin());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
|
||||||
|
{ return scoresKBest[i] > scoresKBest[j]; });
|
||||||
|
sort(scoresKBest.begin(), scoresKBest.end(), std::greater<double>());
|
||||||
|
featuresKBest.resize(k);
|
||||||
|
scoresKBest.resize(k);
|
||||||
|
}
|
||||||
|
return featuresKBest;
|
||||||
|
}
|
||||||
|
vector<double> Metrics::getScoresKBest() const
|
||||||
|
{
|
||||||
|
return scoresKBest;
|
||||||
|
}
|
||||||
vector<pair<string, string>> Metrics::doCombinations(const vector<string>& source)
|
vector<pair<string, string>> Metrics::doCombinations(const vector<string>& source)
|
||||||
{
|
{
|
||||||
vector<pair<string, string>> result;
|
vector<pair<string, string>> result;
|
||||||
@@ -32,17 +71,17 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
torch::Tensor Metrics::conditionalEdge()
|
torch::Tensor Metrics::conditionalEdge(const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
auto result = vector<double>();
|
auto result = vector<double>();
|
||||||
auto source = vector<string>(features);
|
auto source = vector<string>(features);
|
||||||
source.push_back(className);
|
source.push_back(className);
|
||||||
auto combinations = doCombinations(source);
|
auto combinations = doCombinations(source);
|
||||||
// Compute class prior
|
// Compute class prior
|
||||||
auto margin = torch::zeros({ classNumStates });
|
auto margin = torch::zeros({ classNumStates }, torch::kFloat);
|
||||||
for (int value = 0; value < classNumStates; ++value) {
|
for (int value = 0; value < classNumStates; ++value) {
|
||||||
auto mask = samples.index({ -1, "..." }) == value;
|
auto mask = samples.index({ -1, "..." }) == value;
|
||||||
margin[value] = mask.sum().item<float>() / samples.size(1);
|
margin[value] = mask.sum().item<double>() / samples.size(1);
|
||||||
}
|
}
|
||||||
for (auto [first, second] : combinations) {
|
for (auto [first, second] : combinations) {
|
||||||
int index_first = find(features.begin(), features.end(), first) - features.begin();
|
int index_first = find(features.begin(), features.end(), first) - features.begin();
|
||||||
@@ -52,8 +91,9 @@ namespace bayesnet {
|
|||||||
auto mask = samples.index({ -1, "..." }) == value;
|
auto mask = samples.index({ -1, "..." }) == value;
|
||||||
auto first_dataset = samples.index({ index_first, mask });
|
auto first_dataset = samples.index({ index_first, mask });
|
||||||
auto second_dataset = samples.index({ index_second, mask });
|
auto second_dataset = samples.index({ index_second, mask });
|
||||||
auto mi = mutualInformation(first_dataset, second_dataset);
|
auto weights_dataset = weights.index({ mask });
|
||||||
auto pb = margin[value].item<float>();
|
auto mi = mutualInformation(first_dataset, second_dataset, weights_dataset);
|
||||||
|
auto pb = margin[value].item<double>();
|
||||||
accumulated += pb * mi;
|
accumulated += pb * mi;
|
||||||
}
|
}
|
||||||
result.push_back(accumulated);
|
result.push_back(accumulated);
|
||||||
@@ -70,31 +110,32 @@ namespace bayesnet {
|
|||||||
return matrix;
|
return matrix;
|
||||||
}
|
}
|
||||||
// To use in Python
|
// To use in Python
|
||||||
vector<float> Metrics::conditionalEdgeWeights()
|
vector<float> Metrics::conditionalEdgeWeights(vector<float>& weights_)
|
||||||
{
|
{
|
||||||
auto matrix = conditionalEdge();
|
const torch::Tensor weights = torch::tensor(weights_);
|
||||||
|
auto matrix = conditionalEdge(weights);
|
||||||
std::vector<float> v(matrix.data_ptr<float>(), matrix.data_ptr<float>() + matrix.numel());
|
std::vector<float> v(matrix.data_ptr<float>(), matrix.data_ptr<float>() + matrix.numel());
|
||||||
return v;
|
return v;
|
||||||
}
|
}
|
||||||
double Metrics::entropy(const torch::Tensor& feature)
|
double Metrics::entropy(const torch::Tensor& feature, const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
torch::Tensor counts = feature.bincount();
|
torch::Tensor counts = feature.bincount(weights);
|
||||||
int totalWeight = counts.sum().item<int>();
|
double totalWeight = counts.sum().item<double>();
|
||||||
torch::Tensor probs = counts.to(torch::kFloat) / totalWeight;
|
torch::Tensor probs = counts.to(torch::kFloat) / totalWeight;
|
||||||
torch::Tensor logProbs = torch::log(probs);
|
torch::Tensor logProbs = torch::log(probs);
|
||||||
torch::Tensor entropy = -probs * logProbs;
|
torch::Tensor entropy = -probs * logProbs;
|
||||||
return entropy.nansum().item<double>();
|
return entropy.nansum().item<double>();
|
||||||
}
|
}
|
||||||
// H(Y|X) = sum_{x in X} p(x) H(Y|X=x)
|
// H(Y|X) = sum_{x in X} p(x) H(Y|X=x)
|
||||||
double Metrics::conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature)
|
double Metrics::conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
int numSamples = firstFeature.sizes()[0];
|
int numSamples = firstFeature.sizes()[0];
|
||||||
torch::Tensor featureCounts = secondFeature.bincount();
|
torch::Tensor featureCounts = secondFeature.bincount(weights);
|
||||||
unordered_map<int, unordered_map<int, double>> jointCounts;
|
unordered_map<int, unordered_map<int, double>> jointCounts;
|
||||||
double totalWeight = 0;
|
double totalWeight = 0;
|
||||||
for (auto i = 0; i < numSamples; i++) {
|
for (auto i = 0; i < numSamples; i++) {
|
||||||
jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += 1;
|
jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += weights[i].item<double>();
|
||||||
totalWeight += 1;
|
totalWeight += weights[i].item<float>();
|
||||||
}
|
}
|
||||||
if (totalWeight == 0)
|
if (totalWeight == 0)
|
||||||
return 0;
|
return 0;
|
||||||
@@ -115,9 +156,9 @@ namespace bayesnet {
|
|||||||
return entropyValue;
|
return entropyValue;
|
||||||
}
|
}
|
||||||
// I(X;Y) = H(Y) - H(Y|X)
|
// I(X;Y) = H(Y) - H(Y|X)
|
||||||
double Metrics::mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature)
|
double Metrics::mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
return entropy(firstFeature) - conditionalEntropy(firstFeature, secondFeature);
|
return entropy(firstFeature, weights) - conditionalEntropy(firstFeature, secondFeature, weights);
|
||||||
}
|
}
|
||||||
/*
|
/*
|
||||||
Compute the maximum spanning tree considering the weights as distances
|
Compute the maximum spanning tree considering the weights as distances
|
||||||
|
@@ -12,16 +12,20 @@ namespace bayesnet {
|
|||||||
vector<string> features;
|
vector<string> features;
|
||||||
string className;
|
string className;
|
||||||
int classNumStates = 0;
|
int classNumStates = 0;
|
||||||
|
vector<double> scoresKBest;
|
||||||
|
vector<int> featuresKBest; // sorted indices of the features
|
||||||
|
double entropy(const Tensor& feature, const Tensor& weights);
|
||||||
|
double conditionalEntropy(const Tensor& firstFeature, const Tensor& secondFeature, const Tensor& weights);
|
||||||
|
vector<pair<string, string>> doCombinations(const vector<string>&);
|
||||||
public:
|
public:
|
||||||
Metrics() = default;
|
Metrics() = default;
|
||||||
Metrics(const Tensor&, const vector<string>&, const string&, const int);
|
Metrics(const torch::Tensor& samples, const vector<string>& features, const string& className, const int classNumStates);
|
||||||
Metrics(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&, const int);
|
Metrics(const vector<vector<int>>& vsamples, const vector<int>& labels, const vector<string>& features, const string& className, const int classNumStates);
|
||||||
double entropy(const Tensor&);
|
vector<int> SelectKBestWeighted(const torch::Tensor& weights, bool ascending=false, unsigned k = 0);
|
||||||
double conditionalEntropy(const Tensor&, const Tensor&);
|
vector<double> getScoresKBest() const;
|
||||||
double mutualInformation(const Tensor&, const Tensor&);
|
double mutualInformation(const Tensor& firstFeature, const Tensor& secondFeature, const Tensor& weights);
|
||||||
vector<float> conditionalEdgeWeights(); // To use in Python
|
vector<float> conditionalEdgeWeights(vector<float>& weights); // To use in Python
|
||||||
Tensor conditionalEdge();
|
Tensor conditionalEdge(const torch::Tensor& weights);
|
||||||
vector<pair<string, string>> doCombinations(const vector<string>&);
|
|
||||||
vector<pair<int, int>> maximumSpanningTree(const vector<string>& features, const Tensor& weights, const int root);
|
vector<pair<int, int>> maximumSpanningTree(const vector<string>& features, const Tensor& weights, const int root);
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
90
src/BayesNet/BoostAODE.cc
Normal file
90
src/BayesNet/BoostAODE.cc
Normal file
@@ -0,0 +1,90 @@
|
|||||||
|
#include "BoostAODE.h"
|
||||||
|
#include <set>
|
||||||
|
#include "BayesMetrics.h"
|
||||||
|
|
||||||
|
namespace bayesnet {
|
||||||
|
BoostAODE::BoostAODE() : Ensemble() {}
|
||||||
|
void BoostAODE::buildModel(const torch::Tensor& weights)
|
||||||
|
{
|
||||||
|
// Models shall be built in trainModel
|
||||||
|
}
|
||||||
|
void BoostAODE::setHyperparameters(nlohmann::json& hyperparameters)
|
||||||
|
{
|
||||||
|
// Check if hyperparameters are valid
|
||||||
|
const vector<string> validKeys = { "repeatSparent", "maxModels", "ascending" };
|
||||||
|
checkHyperparameters(validKeys, hyperparameters);
|
||||||
|
if (hyperparameters.contains("repeatSparent")) {
|
||||||
|
repeatSparent = hyperparameters["repeatSparent"];
|
||||||
|
}
|
||||||
|
if (hyperparameters.contains("maxModels")) {
|
||||||
|
maxModels = hyperparameters["maxModels"];
|
||||||
|
}
|
||||||
|
if (hyperparameters.contains("ascending")) {
|
||||||
|
ascending = hyperparameters["ascending"];
|
||||||
|
}
|
||||||
|
}
|
||||||
|
void BoostAODE::trainModel(const torch::Tensor& weights)
|
||||||
|
{
|
||||||
|
models.clear();
|
||||||
|
n_models = 0;
|
||||||
|
if (maxModels == 0)
|
||||||
|
maxModels = .1 * n > 10 ? .1 * n : n;
|
||||||
|
Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
|
||||||
|
auto X_ = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." });
|
||||||
|
auto y_ = dataset.index({ -1, "..." });
|
||||||
|
bool exitCondition = false;
|
||||||
|
unordered_set<int> featuresUsed;
|
||||||
|
// Step 0: Set the finish condition
|
||||||
|
// if not repeatSparent a finish condition is run out of features
|
||||||
|
// n_models == maxModels
|
||||||
|
while (!exitCondition) {
|
||||||
|
// Step 1: Build ranking with mutual information
|
||||||
|
auto featureSelection = metrics.SelectKBestWeighted(weights_, ascending, n); // Get all the features sorted
|
||||||
|
unique_ptr<Classifier> model;
|
||||||
|
auto feature = featureSelection[0];
|
||||||
|
if (!repeatSparent || featuresUsed.size() < featureSelection.size()) {
|
||||||
|
bool found = false;
|
||||||
|
for (auto feat : featureSelection) {
|
||||||
|
if (find(featuresUsed.begin(), featuresUsed.end(), feat) != featuresUsed.end()) {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
found = true;
|
||||||
|
feature = feat;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
if (!found) {
|
||||||
|
exitCondition = true;
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
featuresUsed.insert(feature);
|
||||||
|
model = std::make_unique<SPODE>(feature);
|
||||||
|
n_models++;
|
||||||
|
model->fit(dataset, features, className, states, weights_);
|
||||||
|
auto ypred = model->predict(X_);
|
||||||
|
// Step 3.1: Compute the classifier amout of say
|
||||||
|
auto mask_wrong = ypred != y_;
|
||||||
|
auto masked_weights = weights_ * mask_wrong.to(weights_.dtype());
|
||||||
|
double wrongWeights = masked_weights.sum().item<double>();
|
||||||
|
double significance = wrongWeights == 0 ? 1 : 0.5 * log((1 - wrongWeights) / wrongWeights);
|
||||||
|
// Step 3.2: Update weights for next classifier
|
||||||
|
// Step 3.2.1: Update weights of wrong samples
|
||||||
|
weights_ += mask_wrong.to(weights_.dtype()) * exp(significance) * weights_;
|
||||||
|
// Step 3.3: Normalise the weights
|
||||||
|
double totalWeights = torch::sum(weights_).item<double>();
|
||||||
|
weights_ = weights_ / totalWeights;
|
||||||
|
// Step 3.4: Store classifier and its accuracy to weigh its future vote
|
||||||
|
models.push_back(std::move(model));
|
||||||
|
significanceModels.push_back(significance);
|
||||||
|
exitCondition = n_models == maxModels && repeatSparent;
|
||||||
|
}
|
||||||
|
if (featuresUsed.size() != features.size()) {
|
||||||
|
cout << "Warning: BoostAODE did not use all the features" << endl;
|
||||||
|
}
|
||||||
|
weights.copy_(weights_);
|
||||||
|
}
|
||||||
|
vector<string> BoostAODE::graph(const string& title) const
|
||||||
|
{
|
||||||
|
return Ensemble::graph(title);
|
||||||
|
}
|
||||||
|
}
|
21
src/BayesNet/BoostAODE.h
Normal file
21
src/BayesNet/BoostAODE.h
Normal file
@@ -0,0 +1,21 @@
|
|||||||
|
#ifndef BOOSTAODE_H
|
||||||
|
#define BOOSTAODE_H
|
||||||
|
#include "Ensemble.h"
|
||||||
|
#include "SPODE.h"
|
||||||
|
namespace bayesnet {
|
||||||
|
class BoostAODE : public Ensemble {
|
||||||
|
public:
|
||||||
|
BoostAODE();
|
||||||
|
virtual ~BoostAODE() {};
|
||||||
|
vector<string> graph(const string& title = "BoostAODE") const override;
|
||||||
|
void setHyperparameters(nlohmann::json& hyperparameters) override;
|
||||||
|
protected:
|
||||||
|
void buildModel(const torch::Tensor& weights) override;
|
||||||
|
void trainModel(const torch::Tensor& weights) override;
|
||||||
|
private:
|
||||||
|
bool repeatSparent=false;
|
||||||
|
int maxModels=0;
|
||||||
|
bool ascending=false; //Process KBest features ascending or descending order
|
||||||
|
};
|
||||||
|
}
|
||||||
|
#endif
|
@@ -1,7 +1,9 @@
|
|||||||
include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
|
include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
|
||||||
include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
|
include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
|
||||||
|
include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
|
||||||
include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
|
include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
|
||||||
include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
|
include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
|
||||||
add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc
|
add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc
|
||||||
KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc Mst.cc Proposal.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
|
KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc BoostAODE.cc
|
||||||
target_link_libraries(BayesNet mdlp ArffFiles "${TORCH_LIBRARIES}")
|
Mst.cc Proposal.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
|
||||||
|
target_link_libraries(BayesNet mdlp "${TORCH_LIBRARIES}")
|
@@ -5,7 +5,7 @@ namespace bayesnet {
|
|||||||
using namespace torch;
|
using namespace torch;
|
||||||
|
|
||||||
Classifier::Classifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
|
Classifier::Classifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
|
||||||
Classifier& Classifier::build(vector<string>& features, string className, map<string, vector<int>>& states)
|
Classifier& Classifier::build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
this->features = features;
|
this->features = features;
|
||||||
this->className = className;
|
this->className = className;
|
||||||
@@ -13,15 +13,14 @@ namespace bayesnet {
|
|||||||
m = dataset.size(1);
|
m = dataset.size(1);
|
||||||
n = dataset.size(0) - 1;
|
n = dataset.size(0) - 1;
|
||||||
checkFitParameters();
|
checkFitParameters();
|
||||||
auto n_classes = states[className].size();
|
auto n_classes = states.at(className).size();
|
||||||
metrics = Metrics(dataset, features, className, n_classes);
|
metrics = Metrics(dataset, features, className, n_classes);
|
||||||
model.initialize();
|
model.initialize();
|
||||||
buildModel();
|
buildModel(weights);
|
||||||
trainModel();
|
trainModel(weights);
|
||||||
fitted = true;
|
fitted = true;
|
||||||
return *this;
|
return *this;
|
||||||
}
|
}
|
||||||
|
|
||||||
void Classifier::buildDataset(Tensor& ytmp)
|
void Classifier::buildDataset(Tensor& ytmp)
|
||||||
{
|
{
|
||||||
try {
|
try {
|
||||||
@@ -35,19 +34,20 @@ namespace bayesnet {
|
|||||||
exit(1);
|
exit(1);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
void Classifier::trainModel()
|
void Classifier::trainModel(const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
model.fit(dataset, features, className, states);
|
model.fit(dataset, weights, features, className, states);
|
||||||
}
|
}
|
||||||
// X is nxm where n is the number of features and m the number of samples
|
// X is nxm where n is the number of features and m the number of samples
|
||||||
Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
|
Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
dataset = X;
|
dataset = X;
|
||||||
buildDataset(y);
|
buildDataset(y);
|
||||||
return build(features, className, states);
|
const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
|
||||||
|
return build(features, className, states, weights);
|
||||||
}
|
}
|
||||||
// X is nxm where n is the number of features and m the number of samples
|
// X is nxm where n is the number of features and m the number of samples
|
||||||
Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
|
Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, kInt32);
|
dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, kInt32);
|
||||||
for (int i = 0; i < X.size(); ++i) {
|
for (int i = 0; i < X.size(); ++i) {
|
||||||
@@ -55,15 +55,25 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
auto ytmp = torch::tensor(y, kInt32);
|
auto ytmp = torch::tensor(y, kInt32);
|
||||||
buildDataset(ytmp);
|
buildDataset(ytmp);
|
||||||
return build(features, className, states);
|
const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
|
||||||
|
return build(features, className, states, weights);
|
||||||
}
|
}
|
||||||
Classifier& Classifier::fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states)
|
Classifier& Classifier::fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
this->dataset = dataset;
|
this->dataset = dataset;
|
||||||
return build(features, className, states);
|
const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
|
||||||
|
return build(features, className, states, weights);
|
||||||
|
}
|
||||||
|
Classifier& Classifier::fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights)
|
||||||
|
{
|
||||||
|
this->dataset = dataset;
|
||||||
|
return build(features, className, states, weights);
|
||||||
}
|
}
|
||||||
void Classifier::checkFitParameters()
|
void Classifier::checkFitParameters()
|
||||||
{
|
{
|
||||||
|
if (torch::is_floating_point(dataset)) {
|
||||||
|
throw invalid_argument("dataset (X, y) must be of type Integer");
|
||||||
|
}
|
||||||
if (n != features.size()) {
|
if (n != features.size()) {
|
||||||
throw invalid_argument("X " + to_string(n) + " and features " + to_string(features.size()) + " must have the same number of features");
|
throw invalid_argument("X " + to_string(n) + " and features " + to_string(features.size()) + " must have the same number of features");
|
||||||
}
|
}
|
||||||
@@ -145,4 +155,18 @@ namespace bayesnet {
|
|||||||
{
|
{
|
||||||
model.dump_cpt();
|
model.dump_cpt();
|
||||||
}
|
}
|
||||||
|
void Classifier::checkHyperparameters(const vector<string>& validKeys, nlohmann::json& hyperparameters)
|
||||||
|
{
|
||||||
|
for (const auto& item : hyperparameters.items()) {
|
||||||
|
if (find(validKeys.begin(), validKeys.end(), item.key()) == validKeys.end()) {
|
||||||
|
throw invalid_argument("Hyperparameter " + item.key() + " is not valid");
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
void Classifier::setHyperparameters(nlohmann::json& hyperparameters)
|
||||||
|
{
|
||||||
|
// Check if hyperparameters are valid, default is no hyperparameters
|
||||||
|
const vector<string> validKeys = { };
|
||||||
|
checkHyperparameters(validKeys, hyperparameters);
|
||||||
|
}
|
||||||
}
|
}
|
@@ -11,25 +11,27 @@ namespace bayesnet {
|
|||||||
class Classifier : public BaseClassifier {
|
class Classifier : public BaseClassifier {
|
||||||
private:
|
private:
|
||||||
void buildDataset(torch::Tensor& y);
|
void buildDataset(torch::Tensor& y);
|
||||||
Classifier& build(vector<string>& features, string className, map<string, vector<int>>& states);
|
Classifier& build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights);
|
||||||
protected:
|
protected:
|
||||||
bool fitted;
|
bool fitted;
|
||||||
Network model;
|
|
||||||
int m, n; // m: number of samples, n: number of features
|
int m, n; // m: number of samples, n: number of features
|
||||||
Tensor dataset; // (n+1)xm tensor
|
Network model;
|
||||||
Metrics metrics;
|
Metrics metrics;
|
||||||
vector<string> features;
|
vector<string> features;
|
||||||
string className;
|
string className;
|
||||||
map<string, vector<int>> states;
|
map<string, vector<int>> states;
|
||||||
|
Tensor dataset; // (n+1)xm tensor
|
||||||
void checkFitParameters();
|
void checkFitParameters();
|
||||||
virtual void buildModel() = 0;
|
virtual void buildModel(const torch::Tensor& weights) = 0;
|
||||||
void trainModel() override;
|
void trainModel(const torch::Tensor& weights) override;
|
||||||
|
void checkHyperparameters(const vector<string>& validKeys, nlohmann::json& hyperparameters);
|
||||||
public:
|
public:
|
||||||
Classifier(Network model);
|
Classifier(Network model);
|
||||||
virtual ~Classifier() = default;
|
virtual ~Classifier() = default;
|
||||||
Classifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
Classifier& fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
|
||||||
Classifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
Classifier& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
|
||||||
Classifier& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
Classifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
|
||||||
|
Classifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights) override;
|
||||||
void addNodes();
|
void addNodes();
|
||||||
int getNumberOfNodes() const override;
|
int getNumberOfNodes() const override;
|
||||||
int getNumberOfEdges() const override;
|
int getNumberOfEdges() const override;
|
||||||
@@ -41,6 +43,7 @@ namespace bayesnet {
|
|||||||
vector<string> show() const override;
|
vector<string> show() const override;
|
||||||
vector<string> topological_order() override;
|
vector<string> topological_order() override;
|
||||||
void dump_cpt() const override;
|
void dump_cpt() const override;
|
||||||
|
void setHyperparameters(nlohmann::json& hyperparameters) override;
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
||||||
|
@@ -3,9 +3,9 @@
|
|||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace torch;
|
using namespace torch;
|
||||||
|
|
||||||
Ensemble::Ensemble() : Classifier(Network()) {}
|
Ensemble::Ensemble() : Classifier(Network()), n_models(0) {}
|
||||||
|
|
||||||
void Ensemble::trainModel()
|
void Ensemble::trainModel(const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
n_models = models.size();
|
n_models = models.size();
|
||||||
for (auto i = 0; i < n_models; ++i) {
|
for (auto i = 0; i < n_models; ++i) {
|
||||||
@@ -17,10 +17,14 @@ namespace bayesnet {
|
|||||||
{
|
{
|
||||||
auto y_pred_ = y_pred.accessor<int, 2>();
|
auto y_pred_ = y_pred.accessor<int, 2>();
|
||||||
vector<int> y_pred_final;
|
vector<int> y_pred_final;
|
||||||
|
int numClasses = states.at(className).size();
|
||||||
|
// y_pred is m x n_models with the prediction of every model for each sample
|
||||||
for (int i = 0; i < y_pred.size(0); ++i) {
|
for (int i = 0; i < y_pred.size(0); ++i) {
|
||||||
vector<float> votes(y_pred.size(1), 0);
|
// votes store in each index (value of class) the significance added by each model
|
||||||
for (int j = 0; j < y_pred.size(1); ++j) {
|
// i.e. votes[0] contains how much value has the value 0 of class. That value is generated by the models predictions
|
||||||
votes[y_pred_[i][j]] += 1;
|
vector<double> votes(numClasses, 0.0);
|
||||||
|
for (int j = 0; j < n_models; ++j) {
|
||||||
|
votes[y_pred_[i][j]] += significanceModels[j];
|
||||||
}
|
}
|
||||||
// argsort in descending order
|
// argsort in descending order
|
||||||
auto indices = argsort(votes);
|
auto indices = argsort(votes);
|
||||||
@@ -34,7 +38,6 @@ namespace bayesnet {
|
|||||||
throw logic_error("Ensemble has not been fitted");
|
throw logic_error("Ensemble has not been fitted");
|
||||||
}
|
}
|
||||||
Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
|
Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
|
||||||
//Create a threadpool
|
|
||||||
auto threads{ vector<thread>() };
|
auto threads{ vector<thread>() };
|
||||||
mutex mtx;
|
mutex mtx;
|
||||||
for (auto i = 0; i < n_models; ++i) {
|
for (auto i = 0; i < n_models; ++i) {
|
||||||
|
@@ -14,7 +14,8 @@ namespace bayesnet {
|
|||||||
protected:
|
protected:
|
||||||
unsigned n_models;
|
unsigned n_models;
|
||||||
vector<unique_ptr<Classifier>> models;
|
vector<unique_ptr<Classifier>> models;
|
||||||
void trainModel() override;
|
vector<double> significanceModels;
|
||||||
|
void trainModel(const torch::Tensor& weights) override;
|
||||||
vector<int> voting(Tensor& y_pred);
|
vector<int> voting(Tensor& y_pred);
|
||||||
public:
|
public:
|
||||||
Ensemble();
|
Ensemble();
|
||||||
|
@@ -4,7 +4,19 @@ namespace bayesnet {
|
|||||||
using namespace torch;
|
using namespace torch;
|
||||||
|
|
||||||
KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta) {}
|
KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta) {}
|
||||||
void KDB::buildModel()
|
void KDB::setHyperparameters(nlohmann::json& hyperparameters)
|
||||||
|
{
|
||||||
|
// Check if hyperparameters are valid
|
||||||
|
const vector<string> validKeys = { "k", "theta" };
|
||||||
|
checkHyperparameters(validKeys, hyperparameters);
|
||||||
|
if (hyperparameters.contains("k")) {
|
||||||
|
k = hyperparameters["k"];
|
||||||
|
}
|
||||||
|
if (hyperparameters.contains("theta")) {
|
||||||
|
theta = hyperparameters["theta"];
|
||||||
|
}
|
||||||
|
}
|
||||||
|
void KDB::buildModel(const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
/*
|
/*
|
||||||
1. For each feature Xi, compute mutual information, I(X;C),
|
1. For each feature Xi, compute mutual information, I(X;C),
|
||||||
@@ -29,13 +41,13 @@ namespace bayesnet {
|
|||||||
// where C is the class.
|
// where C is the class.
|
||||||
addNodes();
|
addNodes();
|
||||||
const Tensor& y = dataset.index({ -1, "..." });
|
const Tensor& y = dataset.index({ -1, "..." });
|
||||||
vector <float> mi;
|
vector<double> mi;
|
||||||
for (auto i = 0; i < features.size(); i++) {
|
for (auto i = 0; i < features.size(); i++) {
|
||||||
Tensor firstFeature = dataset.index({ i, "..." });
|
Tensor firstFeature = dataset.index({ i, "..." });
|
||||||
mi.push_back(metrics.mutualInformation(firstFeature, y));
|
mi.push_back(metrics.mutualInformation(firstFeature, y, weights));
|
||||||
}
|
}
|
||||||
// 2. Compute class conditional mutual information I(Xi;XjIC), f or each
|
// 2. Compute class conditional mutual information I(Xi;XjIC), f or each
|
||||||
auto conditionalEdgeWeights = metrics.conditionalEdge();
|
auto conditionalEdgeWeights = metrics.conditionalEdge(weights);
|
||||||
// 3. Let the used variable list, S, be empty.
|
// 3. Let the used variable list, S, be empty.
|
||||||
vector<int> S;
|
vector<int> S;
|
||||||
// 4. Let the DAG network being constructed, BN, begin with a single
|
// 4. Let the DAG network being constructed, BN, begin with a single
|
||||||
|
@@ -1,5 +1,6 @@
|
|||||||
#ifndef KDB_H
|
#ifndef KDB_H
|
||||||
#define KDB_H
|
#define KDB_H
|
||||||
|
#include <torch/torch.h>
|
||||||
#include "Classifier.h"
|
#include "Classifier.h"
|
||||||
#include "bayesnetUtils.h"
|
#include "bayesnetUtils.h"
|
||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
@@ -11,10 +12,11 @@ namespace bayesnet {
|
|||||||
float theta;
|
float theta;
|
||||||
void add_m_edges(int idx, vector<int>& S, Tensor& weights);
|
void add_m_edges(int idx, vector<int>& S, Tensor& weights);
|
||||||
protected:
|
protected:
|
||||||
void buildModel() override;
|
void buildModel(const torch::Tensor& weights) override;
|
||||||
public:
|
public:
|
||||||
explicit KDB(int k, float theta = 0.03);
|
explicit KDB(int k, float theta = 0.03);
|
||||||
virtual ~KDB() {};
|
virtual ~KDB() {};
|
||||||
|
void setHyperparameters(nlohmann::json& hyperparameters) override;
|
||||||
vector<string> graph(const string& name = "KDB") const override;
|
vector<string> graph(const string& name = "KDB") const override;
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
@@ -3,9 +3,9 @@
|
|||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
KDBLd::KDBLd(int k) : KDB(k), Proposal(dataset, features, className) {}
|
KDBLd::KDBLd(int k) : KDB(k), Proposal(dataset, features, className) {}
|
||||||
KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
|
KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
|
||||||
{
|
{
|
||||||
// This first part should go in a Classifier method called fit_local_discretization o fit_float...
|
checkInput(X_, y_);
|
||||||
features = features_;
|
features = features_;
|
||||||
className = className_;
|
className = className_;
|
||||||
Xf = X_;
|
Xf = X_;
|
||||||
|
@@ -10,7 +10,7 @@ namespace bayesnet {
|
|||||||
public:
|
public:
|
||||||
explicit KDBLd(int k);
|
explicit KDBLd(int k);
|
||||||
virtual ~KDBLd() = default;
|
virtual ~KDBLd() = default;
|
||||||
KDBLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
KDBLd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
|
||||||
vector<string> graph(const string& name = "KDB") const override;
|
vector<string> graph(const string& name = "KDB") const override;
|
||||||
Tensor predict(Tensor& X) override;
|
Tensor predict(Tensor& X) override;
|
||||||
static inline string version() { return "0.0.1"; };
|
static inline string version() { return "0.0.1"; };
|
||||||
|
@@ -3,9 +3,8 @@
|
|||||||
#include "Network.h"
|
#include "Network.h"
|
||||||
#include "bayesnetUtils.h"
|
#include "bayesnetUtils.h"
|
||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
Network::Network() : features(vector<string>()), className(""), classNumStates(0), fitted(false) {}
|
Network::Network() : features(vector<string>()), className(""), classNumStates(0), fitted(false), laplaceSmoothing(0) {}
|
||||||
Network::Network(float maxT) : features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
|
Network::Network(float maxT) : features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false), laplaceSmoothing(0) {}
|
||||||
Network::Network(float maxT, int smoothing) : laplaceSmoothing(smoothing), features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
|
|
||||||
Network::Network(Network& other) : laplaceSmoothing(other.laplaceSmoothing), features(other.features), className(other.className), classNumStates(other.getClassNumStates()), maxThreads(other.
|
Network::Network(Network& other) : laplaceSmoothing(other.laplaceSmoothing), features(other.features), className(other.className), classNumStates(other.getClassNumStates()), maxThreads(other.
|
||||||
getmaxThreads()), fitted(other.fitted)
|
getmaxThreads()), fitted(other.fitted)
|
||||||
{
|
{
|
||||||
@@ -104,8 +103,11 @@ namespace bayesnet {
|
|||||||
{
|
{
|
||||||
return nodes;
|
return nodes;
|
||||||
}
|
}
|
||||||
void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states, const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
|
if (weights.size(0) != n_samples) {
|
||||||
|
throw invalid_argument("Weights (" + to_string(weights.size(0)) + ") must have the same number of elements as samples (" + to_string(n_samples) + ") in Network::fit");
|
||||||
|
}
|
||||||
if (n_samples != n_samples_y) {
|
if (n_samples != n_samples_y) {
|
||||||
throw invalid_argument("X and y must have the same number of samples in Network::fit (" + to_string(n_samples) + " != " + to_string(n_samples_y) + ")");
|
throw invalid_argument("X and y must have the same number of samples in Network::fit (" + to_string(n_samples) + " != " + to_string(n_samples_y) + ")");
|
||||||
}
|
}
|
||||||
@@ -136,28 +138,29 @@ namespace bayesnet {
|
|||||||
classNumStates = nodes[className]->getNumStates();
|
classNumStates = nodes[className]->getNumStates();
|
||||||
}
|
}
|
||||||
// X comes in nxm, where n is the number of features and m the number of samples
|
// X comes in nxm, where n is the number of features and m the number of samples
|
||||||
void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className, states);
|
checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className, states, weights);
|
||||||
this->className = className;
|
this->className = className;
|
||||||
Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
|
Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
|
||||||
samples = torch::cat({ X , ytmp }, 0);
|
samples = torch::cat({ X , ytmp }, 0);
|
||||||
for (int i = 0; i < featureNames.size(); ++i) {
|
for (int i = 0; i < featureNames.size(); ++i) {
|
||||||
auto row_feature = X.index({ i, "..." });
|
auto row_feature = X.index({ i, "..." });
|
||||||
}
|
}
|
||||||
completeFit(states);
|
completeFit(states, weights);
|
||||||
}
|
}
|
||||||
void Network::fit(const torch::Tensor& samples, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
void Network::fit(const torch::Tensor& samples, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
checkFitData(samples.size(1), samples.size(0) - 1, samples.size(1), featureNames, className, states);
|
checkFitData(samples.size(1), samples.size(0) - 1, samples.size(1), featureNames, className, states, weights);
|
||||||
this->className = className;
|
this->className = className;
|
||||||
this->samples = samples;
|
this->samples = samples;
|
||||||
completeFit(states);
|
completeFit(states, weights);
|
||||||
}
|
}
|
||||||
// input_data comes in nxm, where n is the number of features and m the number of samples
|
// input_data comes in nxm, where n is the number of features and m the number of samples
|
||||||
void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<float>& weights_, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className, states);
|
const torch::Tensor weights = torch::tensor(weights_, torch::kFloat64);
|
||||||
|
checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className, states, weights);
|
||||||
this->className = className;
|
this->className = className;
|
||||||
// Build tensor of samples (nxm) (n+1 because of the class)
|
// Build tensor of samples (nxm) (n+1 because of the class)
|
||||||
samples = torch::zeros({ static_cast<int>(input_data.size() + 1), static_cast<int>(input_data[0].size()) }, torch::kInt32);
|
samples = torch::zeros({ static_cast<int>(input_data.size() + 1), static_cast<int>(input_data[0].size()) }, torch::kInt32);
|
||||||
@@ -165,47 +168,16 @@ namespace bayesnet {
|
|||||||
samples.index_put_({ i, "..." }, torch::tensor(input_data[i], torch::kInt32));
|
samples.index_put_({ i, "..." }, torch::tensor(input_data[i], torch::kInt32));
|
||||||
}
|
}
|
||||||
samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
|
samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
|
||||||
completeFit(states);
|
completeFit(states, weights);
|
||||||
}
|
}
|
||||||
void Network::completeFit(const map<string, vector<int>>& states)
|
void Network::completeFit(const map<string, vector<int>>& states, const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
setStates(states);
|
setStates(states);
|
||||||
int maxThreadsRunning = static_cast<int>(std::thread::hardware_concurrency() * maxThreads);
|
laplaceSmoothing = 1.0 / samples.size(1); // To use in CPT computation
|
||||||
if (maxThreadsRunning < 1) {
|
for (auto& node : nodes) {
|
||||||
maxThreadsRunning = 1;
|
node.second->computeCPT(samples, features, laplaceSmoothing, weights);
|
||||||
|
fitted = true;
|
||||||
}
|
}
|
||||||
vector<thread> threads;
|
|
||||||
mutex mtx;
|
|
||||||
condition_variable cv;
|
|
||||||
int activeThreads = 0;
|
|
||||||
int nextNodeIndex = 0;
|
|
||||||
while (nextNodeIndex < nodes.size()) {
|
|
||||||
unique_lock<mutex> lock(mtx);
|
|
||||||
cv.wait(lock, [&activeThreads, &maxThreadsRunning]() { return activeThreads < maxThreadsRunning; });
|
|
||||||
threads.emplace_back([this, &nextNodeIndex, &mtx, &cv, &activeThreads]() {
|
|
||||||
while (true) {
|
|
||||||
unique_lock<mutex> lock(mtx);
|
|
||||||
if (nextNodeIndex >= nodes.size()) {
|
|
||||||
break; // No more work remaining
|
|
||||||
}
|
|
||||||
auto& pair = *std::next(nodes.begin(), nextNodeIndex);
|
|
||||||
++nextNodeIndex;
|
|
||||||
lock.unlock();
|
|
||||||
pair.second->computeCPT(samples, features, laplaceSmoothing);
|
|
||||||
lock.lock();
|
|
||||||
nodes[pair.first] = std::move(pair.second);
|
|
||||||
lock.unlock();
|
|
||||||
}
|
|
||||||
lock_guard<mutex> lock(mtx);
|
|
||||||
--activeThreads;
|
|
||||||
cv.notify_one();
|
|
||||||
});
|
|
||||||
++activeThreads;
|
|
||||||
}
|
|
||||||
for (auto& thread : threads) {
|
|
||||||
thread.join();
|
|
||||||
}
|
|
||||||
fitted = true;
|
|
||||||
}
|
}
|
||||||
torch::Tensor Network::predict_tensor(const torch::Tensor& samples, const bool proba)
|
torch::Tensor Network::predict_tensor(const torch::Tensor& samples, const bool proba)
|
||||||
{
|
{
|
||||||
@@ -343,7 +315,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
// Normalize result
|
// Normalize result
|
||||||
double sum = accumulate(result.begin(), result.end(), 0.0);
|
double sum = accumulate(result.begin(), result.end(), 0.0);
|
||||||
transform(result.begin(), result.end(), result.begin(), [sum](double& value) { return value / sum; });
|
transform(result.begin(), result.end(), result.begin(), [sum](const double& value) { return value / sum; });
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
vector<string> Network::show() const
|
vector<string> Network::show() const
|
||||||
@@ -395,7 +367,6 @@ namespace bayesnet {
|
|||||||
auto result = features;
|
auto result = features;
|
||||||
result.erase(remove(result.begin(), result.end(), className), result.end());
|
result.erase(remove(result.begin(), result.end(), className), result.end());
|
||||||
bool ending{ false };
|
bool ending{ false };
|
||||||
int idx = 0;
|
|
||||||
while (!ending) {
|
while (!ending) {
|
||||||
ending = true;
|
ending = true;
|
||||||
for (auto feature : features) {
|
for (auto feature : features) {
|
||||||
@@ -431,6 +402,7 @@ namespace bayesnet {
|
|||||||
{
|
{
|
||||||
for (auto& node : nodes) {
|
for (auto& node : nodes) {
|
||||||
cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
|
cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
|
||||||
|
cout << node.second->getCPT() << endl;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@@ -13,21 +13,21 @@ namespace bayesnet {
|
|||||||
int classNumStates;
|
int classNumStates;
|
||||||
vector<string> features; // Including classname
|
vector<string> features; // Including classname
|
||||||
string className;
|
string className;
|
||||||
int laplaceSmoothing = 1;
|
double laplaceSmoothing;
|
||||||
torch::Tensor samples; // nxm tensor used to fit the model
|
torch::Tensor samples; // nxm tensor used to fit the model
|
||||||
bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
|
bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
|
||||||
vector<double> predict_sample(const vector<int>&);
|
vector<double> predict_sample(const vector<int>&);
|
||||||
vector<double> predict_sample(const torch::Tensor&);
|
vector<double> predict_sample(const torch::Tensor&);
|
||||||
vector<double> exactInference(map<string, int>&);
|
vector<double> exactInference(map<string, int>&);
|
||||||
double computeFactor(map<string, int>&);
|
double computeFactor(map<string, int>&);
|
||||||
void completeFit(const map<string, vector<int>>&);
|
void completeFit(const map<string, vector<int>>& states, const torch::Tensor& weights);
|
||||||
void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>&);
|
void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states, const torch::Tensor& weights);
|
||||||
void setStates(const map<string, vector<int>>&);
|
void setStates(const map<string, vector<int>>&);
|
||||||
public:
|
public:
|
||||||
Network();
|
Network();
|
||||||
explicit Network(float, int);
|
|
||||||
explicit Network(float);
|
explicit Network(float);
|
||||||
explicit Network(Network&);
|
explicit Network(Network&);
|
||||||
|
~Network() = default;
|
||||||
torch::Tensor& getSamples();
|
torch::Tensor& getSamples();
|
||||||
float getmaxThreads();
|
float getmaxThreads();
|
||||||
void addNode(const string&);
|
void addNode(const string&);
|
||||||
@@ -39,9 +39,9 @@ namespace bayesnet {
|
|||||||
int getNumEdges() const;
|
int getNumEdges() const;
|
||||||
int getClassNumStates() const;
|
int getClassNumStates() const;
|
||||||
string getClassName() const;
|
string getClassName() const;
|
||||||
void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&, const map<string, vector<int>>&);
|
void fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<float>& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
|
||||||
void fit(const torch::Tensor&, const torch::Tensor&, const vector<string>&, const string&, const map<string, vector<int>>&);
|
void fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
|
||||||
void fit(const torch::Tensor&, const vector<string>&, const string&, const map<string, vector<int>>&);
|
void fit(const torch::Tensor& samples, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
|
||||||
vector<int> predict(const vector<vector<int>>&); // Return mx1 vector of predictions
|
vector<int> predict(const vector<vector<int>>&); // Return mx1 vector of predictions
|
||||||
torch::Tensor predict(const torch::Tensor&); // Return mx1 tensor of predictions
|
torch::Tensor predict(const torch::Tensor&); // Return mx1 tensor of predictions
|
||||||
torch::Tensor predict_tensor(const torch::Tensor& samples, const bool proba);
|
torch::Tensor predict_tensor(const torch::Tensor& samples, const bool proba);
|
||||||
@@ -53,7 +53,7 @@ namespace bayesnet {
|
|||||||
vector<string> graph(const string& title) const; // Returns a vector of strings representing the graph in graphviz format
|
vector<string> graph(const string& title) const; // Returns a vector of strings representing the graph in graphviz format
|
||||||
void initialize();
|
void initialize();
|
||||||
void dump_cpt() const;
|
void dump_cpt() const;
|
||||||
inline string version() { return "0.1.0"; }
|
inline string version() { return "0.2.0"; }
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
@@ -84,7 +84,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
void Node::computeCPT(const torch::Tensor& dataset, const vector<string>& features, const int laplaceSmoothing)
|
void Node::computeCPT(const torch::Tensor& dataset, const vector<string>& features, const double laplaceSmoothing, const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
dimensions.clear();
|
dimensions.clear();
|
||||||
// Get dimensions of the CPT
|
// Get dimensions of the CPT
|
||||||
@@ -100,7 +100,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
int name_index = pos - features.begin();
|
int name_index = pos - features.begin();
|
||||||
for (int n_sample = 0; n_sample < dataset.size(1); ++n_sample) {
|
for (int n_sample = 0; n_sample < dataset.size(1); ++n_sample) {
|
||||||
torch::List<c10::optional<torch::Tensor>> coordinates;
|
c10::List<c10::optional<at::Tensor>> coordinates;
|
||||||
coordinates.push_back(dataset.index({ name_index, n_sample }));
|
coordinates.push_back(dataset.index({ name_index, n_sample }));
|
||||||
for (auto parent : parents) {
|
for (auto parent : parents) {
|
||||||
pos = find(features.begin(), features.end(), parent->getName());
|
pos = find(features.begin(), features.end(), parent->getName());
|
||||||
@@ -111,17 +111,17 @@ namespace bayesnet {
|
|||||||
coordinates.push_back(dataset.index({ parent_index, n_sample }));
|
coordinates.push_back(dataset.index({ parent_index, n_sample }));
|
||||||
}
|
}
|
||||||
// Increment the count of the corresponding coordinate
|
// Increment the count of the corresponding coordinate
|
||||||
cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + 1);
|
cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + weights.index({ n_sample }).item<double>());
|
||||||
}
|
}
|
||||||
// Normalize the counts
|
// Normalize the counts
|
||||||
cpTable = cpTable / cpTable.sum(0);
|
cpTable = cpTable / cpTable.sum(0);
|
||||||
}
|
}
|
||||||
float Node::getFactorValue(map<string, int>& evidence)
|
float Node::getFactorValue(map<string, int>& evidence)
|
||||||
{
|
{
|
||||||
torch::List<c10::optional<torch::Tensor>> coordinates;
|
c10::List<c10::optional<at::Tensor>> coordinates;
|
||||||
// following predetermined order of indices in the cpTable (see Node.h)
|
// following predetermined order of indices in the cpTable (see Node.h)
|
||||||
coordinates.push_back(torch::tensor(evidence[name]));
|
coordinates.push_back(at::tensor(evidence[name]));
|
||||||
transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return torch::tensor(evidence[parent->getName()]); });
|
transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return at::tensor(evidence[parent->getName()]); });
|
||||||
return cpTable.index({ coordinates }).item<float>();
|
return cpTable.index({ coordinates }).item<float>();
|
||||||
}
|
}
|
||||||
vector<string> Node::graph(const string& className)
|
vector<string> Node::graph(const string& className)
|
||||||
|
@@ -26,7 +26,7 @@ namespace bayesnet {
|
|||||||
vector<Node*>& getParents();
|
vector<Node*>& getParents();
|
||||||
vector<Node*>& getChildren();
|
vector<Node*>& getChildren();
|
||||||
torch::Tensor& getCPT();
|
torch::Tensor& getCPT();
|
||||||
void computeCPT(const torch::Tensor&, const vector<string>&, const int);
|
void computeCPT(const torch::Tensor& dataset, const vector<string>& features, const double laplaceSmoothing, const torch::Tensor& weights);
|
||||||
int getNumStates() const;
|
int getNumStates() const;
|
||||||
void setNumStates(int);
|
void setNumStates(int);
|
||||||
unsigned minFill();
|
unsigned minFill();
|
||||||
|
@@ -9,6 +9,15 @@ namespace bayesnet {
|
|||||||
delete value;
|
delete value;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
void Proposal::checkInput(const torch::Tensor& X, const torch::Tensor& y)
|
||||||
|
{
|
||||||
|
if (!torch::is_floating_point(X)) {
|
||||||
|
throw std::invalid_argument("X must be a floating point tensor");
|
||||||
|
}
|
||||||
|
if (torch::is_floating_point(y)) {
|
||||||
|
throw std::invalid_argument("y must be an integer tensor");
|
||||||
|
}
|
||||||
|
}
|
||||||
map<string, vector<int>> Proposal::localDiscretizationProposal(const map<string, vector<int>>& oldStates, Network& model)
|
map<string, vector<int>> Proposal::localDiscretizationProposal(const map<string, vector<int>>& oldStates, Network& model)
|
||||||
{
|
{
|
||||||
// order of local discretization is important. no good 0, 1, 2...
|
// order of local discretization is important. no good 0, 1, 2...
|
||||||
@@ -44,15 +53,6 @@ namespace bayesnet {
|
|||||||
auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
|
auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
|
||||||
auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
|
auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
|
||||||
discretizers[feature]->fit(xvf, yxv);
|
discretizers[feature]->fit(xvf, yxv);
|
||||||
//
|
|
||||||
//
|
|
||||||
//
|
|
||||||
// auto tmp = discretizers[feature]->transform(xvf);
|
|
||||||
// Xv[index] = tmp;
|
|
||||||
// auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
|
|
||||||
// iota(xStates.begin(), xStates.end(), 0);
|
|
||||||
// //Update new states of the feature/node
|
|
||||||
// states[feature] = xStates;
|
|
||||||
}
|
}
|
||||||
if (upgrade) {
|
if (upgrade) {
|
||||||
// Discretize again X (only the affected indices) with the new fitted discretizers
|
// Discretize again X (only the affected indices) with the new fitted discretizers
|
||||||
@@ -65,7 +65,8 @@ namespace bayesnet {
|
|||||||
//Update new states of the feature/node
|
//Update new states of the feature/node
|
||||||
states[pFeatures[index]] = xStates;
|
states[pFeatures[index]] = xStates;
|
||||||
}
|
}
|
||||||
model.fit(pDataset, pFeatures, pClassName, states);
|
const torch::Tensor weights = torch::full({ pDataset.size(1) }, 1.0 / pDataset.size(1), torch::kDouble);
|
||||||
|
model.fit(pDataset, weights, pFeatures, pClassName, states);
|
||||||
}
|
}
|
||||||
return states;
|
return states;
|
||||||
}
|
}
|
||||||
|
@@ -13,6 +13,7 @@ namespace bayesnet {
|
|||||||
Proposal(torch::Tensor& pDataset, vector<string>& features_, string& className_);
|
Proposal(torch::Tensor& pDataset, vector<string>& features_, string& className_);
|
||||||
virtual ~Proposal();
|
virtual ~Proposal();
|
||||||
protected:
|
protected:
|
||||||
|
void checkInput(const torch::Tensor& X, const torch::Tensor& y);
|
||||||
torch::Tensor prepareX(torch::Tensor& X);
|
torch::Tensor prepareX(torch::Tensor& X);
|
||||||
map<string, vector<int>> localDiscretizationProposal(const map<string, vector<int>>& states, Network& model);
|
map<string, vector<int>> localDiscretizationProposal(const map<string, vector<int>>& states, Network& model);
|
||||||
map<string, vector<int>> fit_local_discretization(const torch::Tensor& y);
|
map<string, vector<int>> fit_local_discretization(const torch::Tensor& y);
|
||||||
|
@@ -4,7 +4,7 @@ namespace bayesnet {
|
|||||||
|
|
||||||
SPODE::SPODE(int root) : Classifier(Network()), root(root) {}
|
SPODE::SPODE(int root) : Classifier(Network()), root(root) {}
|
||||||
|
|
||||||
void SPODE::buildModel()
|
void SPODE::buildModel(const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
// 0. Add all nodes to the model
|
// 0. Add all nodes to the model
|
||||||
addNodes();
|
addNodes();
|
||||||
|
@@ -7,7 +7,7 @@ namespace bayesnet {
|
|||||||
private:
|
private:
|
||||||
int root;
|
int root;
|
||||||
protected:
|
protected:
|
||||||
void buildModel() override;
|
void buildModel(const torch::Tensor& weights) override;
|
||||||
public:
|
public:
|
||||||
explicit SPODE(int root);
|
explicit SPODE(int root);
|
||||||
virtual ~SPODE() {};
|
virtual ~SPODE() {};
|
||||||
|
@@ -3,9 +3,9 @@
|
|||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
SPODELd::SPODELd(int root) : SPODE(root), Proposal(dataset, features, className) {}
|
SPODELd::SPODELd(int root) : SPODE(root), Proposal(dataset, features, className) {}
|
||||||
SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
|
SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
|
||||||
{
|
{
|
||||||
// This first part should go in a Classifier method called fit_local_discretization o fit_float...
|
checkInput(X_, y_);
|
||||||
features = features_;
|
features = features_;
|
||||||
className = className_;
|
className = className_;
|
||||||
Xf = X_;
|
Xf = X_;
|
||||||
@@ -18,12 +18,13 @@ namespace bayesnet {
|
|||||||
states = localDiscretizationProposal(states, model);
|
states = localDiscretizationProposal(states, model);
|
||||||
return *this;
|
return *this;
|
||||||
}
|
}
|
||||||
SPODELd& SPODELd::fit(torch::Tensor& dataset, vector<string>& features_, string className_, map<string, vector<int>>& states_)
|
SPODELd& SPODELd::fit(torch::Tensor& dataset, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
|
||||||
{
|
{
|
||||||
|
if (!torch::is_floating_point(dataset)) {
|
||||||
|
throw std::runtime_error("Dataset must be a floating point tensor");
|
||||||
|
}
|
||||||
Xf = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." }).clone();
|
Xf = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." }).clone();
|
||||||
cout << "Xf " << Xf.sizes() << " dtype: " << Xf.dtype() << endl;
|
|
||||||
y = dataset.index({ -1, "..." }).clone();
|
y = dataset.index({ -1, "..." }).clone();
|
||||||
// This first part should go in a Classifier method called fit_local_discretization o fit_float...
|
|
||||||
features = features_;
|
features = features_;
|
||||||
className = className_;
|
className = className_;
|
||||||
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
|
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
|
||||||
|
@@ -9,8 +9,8 @@ namespace bayesnet {
|
|||||||
public:
|
public:
|
||||||
explicit SPODELd(int root);
|
explicit SPODELd(int root);
|
||||||
virtual ~SPODELd() = default;
|
virtual ~SPODELd() = default;
|
||||||
SPODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
SPODELd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
|
||||||
SPODELd& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
SPODELd& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
|
||||||
vector<string> graph(const string& name = "SPODE") const override;
|
vector<string> graph(const string& name = "SPODE") const override;
|
||||||
Tensor predict(Tensor& X) override;
|
Tensor predict(Tensor& X) override;
|
||||||
static inline string version() { return "0.0.1"; };
|
static inline string version() { return "0.0.1"; };
|
||||||
|
@@ -5,7 +5,7 @@ namespace bayesnet {
|
|||||||
|
|
||||||
TAN::TAN() : Classifier(Network()) {}
|
TAN::TAN() : Classifier(Network()) {}
|
||||||
|
|
||||||
void TAN::buildModel()
|
void TAN::buildModel(const torch::Tensor& weights)
|
||||||
{
|
{
|
||||||
// 0. Add all nodes to the model
|
// 0. Add all nodes to the model
|
||||||
addNodes();
|
addNodes();
|
||||||
@@ -15,15 +15,15 @@ namespace bayesnet {
|
|||||||
Tensor class_dataset = dataset.index({ -1, "..." });
|
Tensor class_dataset = dataset.index({ -1, "..." });
|
||||||
for (int i = 0; i < static_cast<int>(features.size()); ++i) {
|
for (int i = 0; i < static_cast<int>(features.size()); ++i) {
|
||||||
Tensor feature_dataset = dataset.index({ i, "..." });
|
Tensor feature_dataset = dataset.index({ i, "..." });
|
||||||
auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset);
|
auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset, weights);
|
||||||
mi.push_back({ i, mi_value });
|
mi.push_back({ i, mi_value });
|
||||||
}
|
}
|
||||||
sort(mi.begin(), mi.end(), [](const auto& left, const auto& right) {return left.second < right.second;});
|
sort(mi.begin(), mi.end(), [](const auto& left, const auto& right) {return left.second < right.second;});
|
||||||
auto root = mi[mi.size() - 1].first;
|
auto root = mi[mi.size() - 1].first;
|
||||||
// 2. Compute mutual information between each feature and the class
|
// 2. Compute mutual information between each feature and the class
|
||||||
auto weights = metrics.conditionalEdge();
|
auto weights_matrix = metrics.conditionalEdge(weights);
|
||||||
// 3. Compute the maximum spanning tree
|
// 3. Compute the maximum spanning tree
|
||||||
auto mst = metrics.maximumSpanningTree(features, weights, root);
|
auto mst = metrics.maximumSpanningTree(features, weights_matrix, root);
|
||||||
// 4. Add edges from the maximum spanning tree to the model
|
// 4. Add edges from the maximum spanning tree to the model
|
||||||
for (auto i = 0; i < mst.size(); ++i) {
|
for (auto i = 0; i < mst.size(); ++i) {
|
||||||
auto [from, to] = mst[i];
|
auto [from, to] = mst[i];
|
||||||
|
@@ -3,11 +3,10 @@
|
|||||||
#include "Classifier.h"
|
#include "Classifier.h"
|
||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
using namespace torch;
|
|
||||||
class TAN : public Classifier {
|
class TAN : public Classifier {
|
||||||
private:
|
private:
|
||||||
protected:
|
protected:
|
||||||
void buildModel() override;
|
void buildModel(const torch::Tensor& weights) override;
|
||||||
public:
|
public:
|
||||||
TAN();
|
TAN();
|
||||||
virtual ~TAN() {};
|
virtual ~TAN() {};
|
||||||
|
@@ -3,9 +3,9 @@
|
|||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
TANLd::TANLd() : TAN(), Proposal(dataset, features, className) {}
|
TANLd::TANLd() : TAN(), Proposal(dataset, features, className) {}
|
||||||
TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
|
TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
|
||||||
{
|
{
|
||||||
// This first part should go in a Classifier method called fit_local_discretization o fit_float...
|
checkInput(X_, y_);
|
||||||
features = features_;
|
features = features_;
|
||||||
className = className_;
|
className = className_;
|
||||||
Xf = X_;
|
Xf = X_;
|
||||||
|
@@ -10,7 +10,7 @@ namespace bayesnet {
|
|||||||
public:
|
public:
|
||||||
TANLd();
|
TANLd();
|
||||||
virtual ~TANLd() = default;
|
virtual ~TANLd() = default;
|
||||||
TANLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
TANLd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
|
||||||
vector<string> graph(const string& name = "TAN") const override;
|
vector<string> graph(const string& name = "TAN") const override;
|
||||||
Tensor predict(Tensor& X) override;
|
Tensor predict(Tensor& X) override;
|
||||||
static inline string version() { return "0.0.1"; };
|
static inline string version() { return "0.0.1"; };
|
||||||
|
@@ -4,7 +4,7 @@ namespace bayesnet {
|
|||||||
using namespace std;
|
using namespace std;
|
||||||
using namespace torch;
|
using namespace torch;
|
||||||
// Return the indices in descending order
|
// Return the indices in descending order
|
||||||
vector<int> argsort(vector<float>& nums)
|
vector<int> argsort(vector<double>& nums)
|
||||||
{
|
{
|
||||||
int n = nums.size();
|
int n = nums.size();
|
||||||
vector<int> indices(n);
|
vector<int> indices(n);
|
||||||
|
@@ -5,7 +5,7 @@
|
|||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
using namespace torch;
|
using namespace torch;
|
||||||
vector<int> argsort(vector<float>& nums);
|
vector<int> argsort(vector<double>& nums);
|
||||||
vector<vector<int>> tensorToVector(Tensor& tensor);
|
vector<vector<int>> tensorToVector(Tensor& tensor);
|
||||||
}
|
}
|
||||||
#endif //BAYESNET_UTILS_H
|
#endif //BAYESNET_UTILS_H
|
@@ -4,7 +4,9 @@ include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
|
|||||||
include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
|
include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
|
||||||
include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
|
include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
|
||||||
include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
|
include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
|
||||||
add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc Report.cc)
|
add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc ReportConsole.cc ReportBase.cc)
|
||||||
add_executable(manage manage.cc Results.cc Report.cc)
|
add_executable(manage manage.cc Results.cc ReportConsole.cc ReportExcel.cc ReportBase.cc)
|
||||||
|
add_executable(list list.cc platformUtils Datasets.cc)
|
||||||
target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
|
target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
|
||||||
target_link_libraries(manage "${TORCH_LIBRARIES}")
|
target_link_libraries(manage "${TORCH_LIBRARIES}" OpenXLSX::OpenXLSX)
|
||||||
|
target_link_libraries(list ArffFiles mdlp "${TORCH_LIBRARIES}")
|
@@ -1,6 +1,7 @@
|
|||||||
#include "Datasets.h"
|
#include "Datasets.h"
|
||||||
#include "platformUtils.h"
|
#include "platformUtils.h"
|
||||||
#include "ArffFiles.h"
|
#include "ArffFiles.h"
|
||||||
|
#include <fstream>
|
||||||
namespace platform {
|
namespace platform {
|
||||||
void Datasets::load()
|
void Datasets::load()
|
||||||
{
|
{
|
||||||
@@ -24,75 +25,110 @@ namespace platform {
|
|||||||
transform(datasets.begin(), datasets.end(), back_inserter(result), [](const auto& d) { return d.first; });
|
transform(datasets.begin(), datasets.end(), back_inserter(result), [](const auto& d) { return d.first; });
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
vector<string> Datasets::getFeatures(string name)
|
vector<string> Datasets::getFeatures(const string& name) const
|
||||||
{
|
{
|
||||||
if (datasets[name]->isLoaded()) {
|
if (datasets.at(name)->isLoaded()) {
|
||||||
return datasets[name]->getFeatures();
|
return datasets.at(name)->getFeatures();
|
||||||
} else {
|
} else {
|
||||||
throw invalid_argument("Dataset not loaded.");
|
throw invalid_argument("Dataset not loaded.");
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
map<string, vector<int>> Datasets::getStates(string name)
|
map<string, vector<int>> Datasets::getStates(const string& name) const
|
||||||
{
|
{
|
||||||
if (datasets[name]->isLoaded()) {
|
if (datasets.at(name)->isLoaded()) {
|
||||||
return datasets[name]->getStates();
|
return datasets.at(name)->getStates();
|
||||||
} else {
|
} else {
|
||||||
throw invalid_argument("Dataset not loaded.");
|
throw invalid_argument("Dataset not loaded.");
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
string Datasets::getClassName(string name)
|
void Datasets::loadDataset(const string& name) const
|
||||||
{
|
{
|
||||||
if (datasets[name]->isLoaded()) {
|
if (datasets.at(name)->isLoaded()) {
|
||||||
return datasets[name]->getClassName();
|
return;
|
||||||
|
} else {
|
||||||
|
datasets.at(name)->load();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
string Datasets::getClassName(const string& name) const
|
||||||
|
{
|
||||||
|
if (datasets.at(name)->isLoaded()) {
|
||||||
|
return datasets.at(name)->getClassName();
|
||||||
} else {
|
} else {
|
||||||
throw invalid_argument("Dataset not loaded.");
|
throw invalid_argument("Dataset not loaded.");
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
int Datasets::getNSamples(string name)
|
int Datasets::getNSamples(const string& name) const
|
||||||
{
|
{
|
||||||
if (datasets[name]->isLoaded()) {
|
if (datasets.at(name)->isLoaded()) {
|
||||||
return datasets[name]->getNSamples();
|
return datasets.at(name)->getNSamples();
|
||||||
} else {
|
} else {
|
||||||
throw invalid_argument("Dataset not loaded.");
|
throw invalid_argument("Dataset not loaded.");
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(string name)
|
int Datasets::getNClasses(const string& name)
|
||||||
|
{
|
||||||
|
if (datasets.at(name)->isLoaded()) {
|
||||||
|
auto className = datasets.at(name)->getClassName();
|
||||||
|
if (discretize) {
|
||||||
|
auto states = getStates(name);
|
||||||
|
return states.at(className).size();
|
||||||
|
}
|
||||||
|
auto [Xv, yv] = getVectors(name);
|
||||||
|
return *max_element(yv.begin(), yv.end()) + 1;
|
||||||
|
} else {
|
||||||
|
throw invalid_argument("Dataset not loaded.");
|
||||||
|
}
|
||||||
|
}
|
||||||
|
vector<int> Datasets::getClassesCounts(const string& name) const
|
||||||
|
{
|
||||||
|
if (datasets.at(name)->isLoaded()) {
|
||||||
|
auto [Xv, yv] = datasets.at(name)->getVectors();
|
||||||
|
vector<int> counts(*max_element(yv.begin(), yv.end()) + 1);
|
||||||
|
for (auto y : yv) {
|
||||||
|
counts[y]++;
|
||||||
|
}
|
||||||
|
return counts;
|
||||||
|
} else {
|
||||||
|
throw invalid_argument("Dataset not loaded.");
|
||||||
|
}
|
||||||
|
}
|
||||||
|
pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(const string& name)
|
||||||
{
|
{
|
||||||
if (!datasets[name]->isLoaded()) {
|
if (!datasets[name]->isLoaded()) {
|
||||||
datasets[name]->load();
|
datasets[name]->load();
|
||||||
}
|
}
|
||||||
return datasets[name]->getVectors();
|
return datasets[name]->getVectors();
|
||||||
}
|
}
|
||||||
pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(string name)
|
pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(const string& name)
|
||||||
{
|
{
|
||||||
if (!datasets[name]->isLoaded()) {
|
if (!datasets[name]->isLoaded()) {
|
||||||
datasets[name]->load();
|
datasets[name]->load();
|
||||||
}
|
}
|
||||||
return datasets[name]->getVectorsDiscretized();
|
return datasets[name]->getVectorsDiscretized();
|
||||||
}
|
}
|
||||||
pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(string name)
|
pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(const string& name)
|
||||||
{
|
{
|
||||||
if (!datasets[name]->isLoaded()) {
|
if (!datasets[name]->isLoaded()) {
|
||||||
datasets[name]->load();
|
datasets[name]->load();
|
||||||
}
|
}
|
||||||
return datasets[name]->getTensors();
|
return datasets[name]->getTensors();
|
||||||
}
|
}
|
||||||
bool Datasets::isDataset(const string& name)
|
bool Datasets::isDataset(const string& name) const
|
||||||
{
|
{
|
||||||
return datasets.find(name) != datasets.end();
|
return datasets.find(name) != datasets.end();
|
||||||
}
|
}
|
||||||
Dataset::Dataset(const Dataset& dataset) : path(dataset.path), name(dataset.name), className(dataset.className), n_samples(dataset.n_samples), n_features(dataset.n_features), features(dataset.features), states(dataset.states), loaded(dataset.loaded), discretize(dataset.discretize), X(dataset.X), y(dataset.y), Xv(dataset.Xv), Xd(dataset.Xd), yv(dataset.yv), fileType(dataset.fileType)
|
Dataset::Dataset(const Dataset& dataset) : path(dataset.path), name(dataset.name), className(dataset.className), n_samples(dataset.n_samples), n_features(dataset.n_features), features(dataset.features), states(dataset.states), loaded(dataset.loaded), discretize(dataset.discretize), X(dataset.X), y(dataset.y), Xv(dataset.Xv), Xd(dataset.Xd), yv(dataset.yv), fileType(dataset.fileType)
|
||||||
{
|
{
|
||||||
}
|
}
|
||||||
string Dataset::getName()
|
string Dataset::getName() const
|
||||||
{
|
{
|
||||||
return name;
|
return name;
|
||||||
}
|
}
|
||||||
string Dataset::getClassName()
|
string Dataset::getClassName() const
|
||||||
{
|
{
|
||||||
return className;
|
return className;
|
||||||
}
|
}
|
||||||
vector<string> Dataset::getFeatures()
|
vector<string> Dataset::getFeatures() const
|
||||||
{
|
{
|
||||||
if (loaded) {
|
if (loaded) {
|
||||||
return features;
|
return features;
|
||||||
@@ -100,7 +136,7 @@ namespace platform {
|
|||||||
throw invalid_argument("Dataset not loaded.");
|
throw invalid_argument("Dataset not loaded.");
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
int Dataset::getNFeatures()
|
int Dataset::getNFeatures() const
|
||||||
{
|
{
|
||||||
if (loaded) {
|
if (loaded) {
|
||||||
return n_features;
|
return n_features;
|
||||||
@@ -108,7 +144,7 @@ namespace platform {
|
|||||||
throw invalid_argument("Dataset not loaded.");
|
throw invalid_argument("Dataset not loaded.");
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
int Dataset::getNSamples()
|
int Dataset::getNSamples() const
|
||||||
{
|
{
|
||||||
if (loaded) {
|
if (loaded) {
|
||||||
return n_samples;
|
return n_samples;
|
||||||
@@ -116,7 +152,7 @@ namespace platform {
|
|||||||
throw invalid_argument("Dataset not loaded.");
|
throw invalid_argument("Dataset not loaded.");
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
map<string, vector<int>> Dataset::getStates()
|
map<string, vector<int>> Dataset::getStates() const
|
||||||
{
|
{
|
||||||
if (loaded) {
|
if (loaded) {
|
||||||
return states;
|
return states;
|
||||||
@@ -177,10 +213,11 @@ namespace platform {
|
|||||||
{
|
{
|
||||||
for (int i = 0; i < features.size(); ++i) {
|
for (int i = 0; i < features.size(); ++i) {
|
||||||
states[features[i]] = vector<int>(*max_element(Xd[i].begin(), Xd[i].end()) + 1);
|
states[features[i]] = vector<int>(*max_element(Xd[i].begin(), Xd[i].end()) + 1);
|
||||||
iota(begin(states[features[i]]), end(states[features[i]]), 0);
|
auto item = states.at(features[i]);
|
||||||
|
iota(begin(item), end(item), 0);
|
||||||
}
|
}
|
||||||
states[className] = vector<int>(*max_element(yv.begin(), yv.end()) + 1);
|
states[className] = vector<int>(*max_element(yv.begin(), yv.end()) + 1);
|
||||||
iota(begin(states[className]), end(states[className]), 0);
|
iota(begin(states.at(className)), end(states.at(className)), 0);
|
||||||
}
|
}
|
||||||
void Dataset::load_arff()
|
void Dataset::load_arff()
|
||||||
{
|
{
|
||||||
|
@@ -29,15 +29,15 @@ namespace platform {
|
|||||||
public:
|
public:
|
||||||
Dataset(const string& path, const string& name, const string& className, bool discretize, fileType_t fileType) : path(path), name(name), className(className), discretize(discretize), loaded(false), fileType(fileType) {};
|
Dataset(const string& path, const string& name, const string& className, bool discretize, fileType_t fileType) : path(path), name(name), className(className), discretize(discretize), loaded(false), fileType(fileType) {};
|
||||||
explicit Dataset(const Dataset&);
|
explicit Dataset(const Dataset&);
|
||||||
string getName();
|
string getName() const;
|
||||||
string getClassName();
|
string getClassName() const;
|
||||||
vector<string> getFeatures();
|
vector<string> getFeatures() const;
|
||||||
map<string, vector<int>> getStates();
|
map<string, vector<int>> getStates() const;
|
||||||
pair<vector<vector<float>>&, vector<int>&> getVectors();
|
pair<vector<vector<float>>&, vector<int>&> getVectors();
|
||||||
pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized();
|
pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized();
|
||||||
pair<torch::Tensor&, torch::Tensor&> getTensors();
|
pair<torch::Tensor&, torch::Tensor&> getTensors();
|
||||||
int getNFeatures();
|
int getNFeatures() const;
|
||||||
int getNSamples();
|
int getNSamples() const;
|
||||||
void load();
|
void load();
|
||||||
const bool inline isLoaded() const { return loaded; };
|
const bool inline isLoaded() const { return loaded; };
|
||||||
};
|
};
|
||||||
@@ -51,14 +51,17 @@ namespace platform {
|
|||||||
public:
|
public:
|
||||||
explicit Datasets(const string& path, bool discretize = false, fileType_t fileType = ARFF) : path(path), discretize(discretize), fileType(fileType) { load(); };
|
explicit Datasets(const string& path, bool discretize = false, fileType_t fileType = ARFF) : path(path), discretize(discretize), fileType(fileType) { load(); };
|
||||||
vector<string> getNames();
|
vector<string> getNames();
|
||||||
vector<string> getFeatures(string name);
|
vector<string> getFeatures(const string& name) const;
|
||||||
int getNSamples(string name);
|
int getNSamples(const string& name) const;
|
||||||
string getClassName(string name);
|
string getClassName(const string& name) const;
|
||||||
map<string, vector<int>> getStates(string name);
|
int getNClasses(const string& name);
|
||||||
pair<vector<vector<float>>&, vector<int>&> getVectors(string name);
|
vector<int> getClassesCounts(const string& name) const;
|
||||||
pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(string name);
|
map<string, vector<int>> getStates(const string& name) const;
|
||||||
pair<torch::Tensor&, torch::Tensor&> getTensors(string name);
|
pair<vector<vector<float>>&, vector<int>&> getVectors(const string& name);
|
||||||
bool isDataset(const string& name);
|
pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(const string& name);
|
||||||
|
pair<torch::Tensor&, torch::Tensor&> getTensors(const string& name);
|
||||||
|
bool isDataset(const string& name) const;
|
||||||
|
void loadDataset(const string& name) const;
|
||||||
};
|
};
|
||||||
};
|
};
|
||||||
|
|
||||||
|
@@ -1,8 +1,8 @@
|
|||||||
#include "Experiment.h"
|
#include "Experiment.h"
|
||||||
#include "Datasets.h"
|
#include "Datasets.h"
|
||||||
#include "Models.h"
|
#include "Models.h"
|
||||||
#include "Report.h"
|
#include "ReportConsole.h"
|
||||||
|
#include <fstream>
|
||||||
namespace platform {
|
namespace platform {
|
||||||
using json = nlohmann::json;
|
using json = nlohmann::json;
|
||||||
string get_date()
|
string get_date()
|
||||||
@@ -25,6 +25,7 @@ namespace platform {
|
|||||||
oss << std::put_time(timeinfo, "%H:%M:%S");
|
oss << std::put_time(timeinfo, "%H:%M:%S");
|
||||||
return oss.str();
|
return oss.str();
|
||||||
}
|
}
|
||||||
|
Experiment::Experiment() : hyperparameters(json::parse("{}")) {}
|
||||||
string Experiment::get_file_name()
|
string Experiment::get_file_name()
|
||||||
{
|
{
|
||||||
string result = "results_" + score_name + "_" + model + "_" + platform + "_" + get_date() + "_" + get_time() + "_" + (stratified ? "1" : "0") + ".json";
|
string result = "results_" + score_name + "_" + model + "_" + platform + "_" + get_date() + "_" + get_time() + "_" + (stratified ? "1" : "0") + ".json";
|
||||||
@@ -90,7 +91,7 @@ namespace platform {
|
|||||||
void Experiment::report()
|
void Experiment::report()
|
||||||
{
|
{
|
||||||
json data = build_json();
|
json data = build_json();
|
||||||
Report report(data);
|
ReportConsole report(data);
|
||||||
report.show();
|
report.show();
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -124,6 +125,8 @@ namespace platform {
|
|||||||
auto result = Result();
|
auto result = Result();
|
||||||
auto [values, counts] = at::_unique(y);
|
auto [values, counts] = at::_unique(y);
|
||||||
result.setSamples(X.size(1)).setFeatures(X.size(0)).setClasses(values.size(0));
|
result.setSamples(X.size(1)).setFeatures(X.size(0)).setClasses(values.size(0));
|
||||||
|
result.setHyperparameters(hyperparameters);
|
||||||
|
// Initialize results vectors
|
||||||
int nResults = nfolds * static_cast<int>(randomSeeds.size());
|
int nResults = nfolds * static_cast<int>(randomSeeds.size());
|
||||||
auto accuracy_test = torch::zeros({ nResults }, torch::kFloat64);
|
auto accuracy_test = torch::zeros({ nResults }, torch::kFloat64);
|
||||||
auto accuracy_train = torch::zeros({ nResults }, torch::kFloat64);
|
auto accuracy_train = torch::zeros({ nResults }, torch::kFloat64);
|
||||||
@@ -144,6 +147,10 @@ namespace platform {
|
|||||||
for (int nfold = 0; nfold < nfolds; nfold++) {
|
for (int nfold = 0; nfold < nfolds; nfold++) {
|
||||||
auto clf = Models::instance()->create(model);
|
auto clf = Models::instance()->create(model);
|
||||||
setModelVersion(clf->getVersion());
|
setModelVersion(clf->getVersion());
|
||||||
|
if (hyperparameters.size() != 0) {
|
||||||
|
clf->setHyperparameters(hyperparameters);
|
||||||
|
}
|
||||||
|
// Split train - test dataset
|
||||||
train_timer.start();
|
train_timer.start();
|
||||||
auto [train, test] = fold->getFold(nfold);
|
auto [train, test] = fold->getFold(nfold);
|
||||||
auto train_t = torch::tensor(train);
|
auto train_t = torch::tensor(train);
|
||||||
@@ -153,12 +160,14 @@ namespace platform {
|
|||||||
auto X_test = X.index({ "...", test_t });
|
auto X_test = X.index({ "...", test_t });
|
||||||
auto y_test = y.index({ test_t });
|
auto y_test = y.index({ test_t });
|
||||||
cout << nfold + 1 << ", " << flush;
|
cout << nfold + 1 << ", " << flush;
|
||||||
|
// Train model
|
||||||
clf->fit(X_train, y_train, features, className, states);
|
clf->fit(X_train, y_train, features, className, states);
|
||||||
nodes[item] = clf->getNumberOfNodes();
|
nodes[item] = clf->getNumberOfNodes();
|
||||||
edges[item] = clf->getNumberOfEdges();
|
edges[item] = clf->getNumberOfEdges();
|
||||||
num_states[item] = clf->getNumberOfStates();
|
num_states[item] = clf->getNumberOfStates();
|
||||||
train_time[item] = train_timer.getDuration();
|
train_time[item] = train_timer.getDuration();
|
||||||
auto accuracy_train_value = clf->score(X_train, y_train);
|
auto accuracy_train_value = clf->score(X_train, y_train);
|
||||||
|
// Test model
|
||||||
test_timer.start();
|
test_timer.start();
|
||||||
auto accuracy_test_value = clf->score(X_test, y_test);
|
auto accuracy_test_value = clf->score(X_test, y_test);
|
||||||
test_time[item] = test_timer.getDuration();
|
test_time[item] = test_timer.getDuration();
|
||||||
@@ -170,6 +179,7 @@ namespace platform {
|
|||||||
result.addTimeTrain(train_time[item].item<double>());
|
result.addTimeTrain(train_time[item].item<double>());
|
||||||
result.addTimeTest(test_time[item].item<double>());
|
result.addTimeTest(test_time[item].item<double>());
|
||||||
item++;
|
item++;
|
||||||
|
clf.reset();
|
||||||
}
|
}
|
||||||
cout << "end. " << flush;
|
cout << "end. " << flush;
|
||||||
delete fold;
|
delete fold;
|
||||||
@@ -177,6 +187,7 @@ namespace platform {
|
|||||||
result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());
|
result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());
|
||||||
result.setScoreTestStd(torch::std(accuracy_test).item<double>()).setScoreTrainStd(torch::std(accuracy_train).item<double>());
|
result.setScoreTestStd(torch::std(accuracy_test).item<double>()).setScoreTrainStd(torch::std(accuracy_train).item<double>());
|
||||||
result.setTrainTime(torch::mean(train_time).item<double>()).setTestTime(torch::mean(test_time).item<double>());
|
result.setTrainTime(torch::mean(train_time).item<double>()).setTestTime(torch::mean(test_time).item<double>());
|
||||||
|
result.setTestTimeStd(torch::std(test_time).item<double>()).setTrainTimeStd(torch::std(train_time).item<double>());
|
||||||
result.setNodes(torch::mean(nodes).item<double>()).setLeaves(torch::mean(edges).item<double>()).setDepth(torch::mean(num_states).item<double>());
|
result.setNodes(torch::mean(nodes).item<double>()).setLeaves(torch::mean(edges).item<double>()).setDepth(torch::mean(num_states).item<double>());
|
||||||
result.setDataset(fileName);
|
result.setDataset(fileName);
|
||||||
addResult(result);
|
addResult(result);
|
||||||
|
@@ -29,7 +29,8 @@ namespace platform {
|
|||||||
};
|
};
|
||||||
class Result {
|
class Result {
|
||||||
private:
|
private:
|
||||||
string dataset, hyperparameters, model_version;
|
string dataset, model_version;
|
||||||
|
json hyperparameters;
|
||||||
int samples{ 0 }, features{ 0 }, classes{ 0 };
|
int samples{ 0 }, features{ 0 }, classes{ 0 };
|
||||||
double score_train{ 0 }, score_test{ 0 }, score_train_std{ 0 }, score_test_std{ 0 }, train_time{ 0 }, train_time_std{ 0 }, test_time{ 0 }, test_time_std{ 0 };
|
double score_train{ 0 }, score_test{ 0 }, score_train_std{ 0 }, score_test_std{ 0 }, train_time{ 0 }, train_time_std{ 0 }, test_time{ 0 }, test_time_std{ 0 };
|
||||||
float nodes{ 0 }, leaves{ 0 }, depth{ 0 };
|
float nodes{ 0 }, leaves{ 0 }, depth{ 0 };
|
||||||
@@ -37,7 +38,7 @@ namespace platform {
|
|||||||
public:
|
public:
|
||||||
Result() = default;
|
Result() = default;
|
||||||
Result& setDataset(const string& dataset) { this->dataset = dataset; return *this; }
|
Result& setDataset(const string& dataset) { this->dataset = dataset; return *this; }
|
||||||
Result& setHyperparameters(const string& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
|
Result& setHyperparameters(const json& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
|
||||||
Result& setSamples(int samples) { this->samples = samples; return *this; }
|
Result& setSamples(int samples) { this->samples = samples; return *this; }
|
||||||
Result& setFeatures(int features) { this->features = features; return *this; }
|
Result& setFeatures(int features) { this->features = features; return *this; }
|
||||||
Result& setClasses(int classes) { this->classes = classes; return *this; }
|
Result& setClasses(int classes) { this->classes = classes; return *this; }
|
||||||
@@ -59,7 +60,7 @@ namespace platform {
|
|||||||
const float get_score_train() const { return score_train; }
|
const float get_score_train() const { return score_train; }
|
||||||
float get_score_test() { return score_test; }
|
float get_score_test() { return score_test; }
|
||||||
const string& getDataset() const { return dataset; }
|
const string& getDataset() const { return dataset; }
|
||||||
const string& getHyperparameters() const { return hyperparameters; }
|
const json& getHyperparameters() const { return hyperparameters; }
|
||||||
const int getSamples() const { return samples; }
|
const int getSamples() const { return samples; }
|
||||||
const int getFeatures() const { return features; }
|
const int getFeatures() const { return features; }
|
||||||
const int getClasses() const { return classes; }
|
const int getClasses() const { return classes; }
|
||||||
@@ -85,11 +86,12 @@ namespace platform {
|
|||||||
bool discretized{ false }, stratified{ false };
|
bool discretized{ false }, stratified{ false };
|
||||||
vector<Result> results;
|
vector<Result> results;
|
||||||
vector<int> randomSeeds;
|
vector<int> randomSeeds;
|
||||||
|
json hyperparameters = "{}";
|
||||||
int nfolds{ 0 };
|
int nfolds{ 0 };
|
||||||
float duration{ 0 };
|
float duration{ 0 };
|
||||||
json build_json();
|
json build_json();
|
||||||
public:
|
public:
|
||||||
Experiment() = default;
|
Experiment();
|
||||||
Experiment& setTitle(const string& title) { this->title = title; return *this; }
|
Experiment& setTitle(const string& title) { this->title = title; return *this; }
|
||||||
Experiment& setModel(const string& model) { this->model = model; return *this; }
|
Experiment& setModel(const string& model) { this->model = model; return *this; }
|
||||||
Experiment& setPlatform(const string& platform) { this->platform = platform; return *this; }
|
Experiment& setPlatform(const string& platform) { this->platform = platform; return *this; }
|
||||||
@@ -103,6 +105,7 @@ namespace platform {
|
|||||||
Experiment& addResult(Result result) { results.push_back(result); return *this; }
|
Experiment& addResult(Result result) { results.push_back(result); return *this; }
|
||||||
Experiment& addRandomSeed(int randomSeed) { randomSeeds.push_back(randomSeed); return *this; }
|
Experiment& addRandomSeed(int randomSeed) { randomSeeds.push_back(randomSeed); return *this; }
|
||||||
Experiment& setDuration(float duration) { this->duration = duration; return *this; }
|
Experiment& setDuration(float duration) { this->duration = duration; return *this; }
|
||||||
|
Experiment& setHyperparameters(const json& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
|
||||||
string get_file_name();
|
string get_file_name();
|
||||||
void save(const string& path);
|
void save(const string& path);
|
||||||
void cross_validation(const string& path, const string& fileName);
|
void cross_validation(const string& path, const string& fileName);
|
||||||
|
@@ -1,95 +1,97 @@
|
|||||||
#include "Folding.h"
|
#include "Folding.h"
|
||||||
#include <algorithm>
|
#include <algorithm>
|
||||||
#include <map>
|
#include <map>
|
||||||
Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
|
namespace platform {
|
||||||
{
|
Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
|
||||||
random_device rd;
|
{
|
||||||
random_seed = default_random_engine(seed == -1 ? rd() : seed);
|
random_device rd;
|
||||||
srand(seed == -1 ? time(0) : seed);
|
random_seed = default_random_engine(seed == -1 ? rd() : seed);
|
||||||
}
|
srand(seed == -1 ? time(0) : seed);
|
||||||
KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(vector<int>(n))
|
|
||||||
{
|
|
||||||
iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
|
|
||||||
shuffle(indices.begin(), indices.end(), random_seed);
|
|
||||||
}
|
|
||||||
pair<vector<int>, vector<int>> KFold::getFold(int nFold)
|
|
||||||
{
|
|
||||||
if (nFold >= k || nFold < 0) {
|
|
||||||
throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
|
|
||||||
}
|
}
|
||||||
int nTest = n / k;
|
KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(vector<int>(n))
|
||||||
auto train = vector<int>();
|
{
|
||||||
auto test = vector<int>();
|
iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
|
||||||
for (int i = 0; i < n; i++) {
|
|
||||||
if (i >= nTest * nFold && i < nTest * (nFold + 1)) {
|
|
||||||
test.push_back(indices[i]);
|
|
||||||
} else {
|
|
||||||
train.push_back(indices[i]);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return { train, test };
|
|
||||||
}
|
|
||||||
StratifiedKFold::StratifiedKFold(int k, torch::Tensor& y, int seed) : Fold(k, y.numel(), seed)
|
|
||||||
{
|
|
||||||
n = y.numel();
|
|
||||||
this->y = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
|
|
||||||
build();
|
|
||||||
}
|
|
||||||
StratifiedKFold::StratifiedKFold(int k, const vector<int>& y, int seed)
|
|
||||||
: Fold(k, y.size(), seed)
|
|
||||||
{
|
|
||||||
this->y = y;
|
|
||||||
n = y.size();
|
|
||||||
build();
|
|
||||||
}
|
|
||||||
void StratifiedKFold::build()
|
|
||||||
{
|
|
||||||
stratified_indices = vector<vector<int>>(k);
|
|
||||||
int fold_size = n / k;
|
|
||||||
// Compute class counts and indices
|
|
||||||
auto class_indices = map<int, vector<int>>();
|
|
||||||
vector<int> class_counts(*max_element(y.begin(), y.end()) + 1, 0);
|
|
||||||
for (auto i = 0; i < n; ++i) {
|
|
||||||
class_counts[y[i]]++;
|
|
||||||
class_indices[y[i]].push_back(i);
|
|
||||||
}
|
|
||||||
// Shuffle class indices
|
|
||||||
for (auto& [cls, indices] : class_indices) {
|
|
||||||
shuffle(indices.begin(), indices.end(), random_seed);
|
shuffle(indices.begin(), indices.end(), random_seed);
|
||||||
}
|
}
|
||||||
// Assign indices to folds
|
pair<vector<int>, vector<int>> KFold::getFold(int nFold)
|
||||||
for (auto label = 0; label < class_counts.size(); ++label) {
|
{
|
||||||
auto num_samples_to_take = class_counts[label] / k;
|
if (nFold >= k || nFold < 0) {
|
||||||
if (num_samples_to_take == 0)
|
throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
|
||||||
continue;
|
|
||||||
auto remainder_samples_to_take = class_counts[label] % k;
|
|
||||||
for (auto fold = 0; fold < k; ++fold) {
|
|
||||||
auto it = next(class_indices[label].begin(), num_samples_to_take);
|
|
||||||
move(class_indices[label].begin(), it, back_inserter(stratified_indices[fold])); // ##
|
|
||||||
class_indices[label].erase(class_indices[label].begin(), it);
|
|
||||||
}
|
}
|
||||||
while (remainder_samples_to_take > 0) {
|
int nTest = n / k;
|
||||||
int fold = (rand() % static_cast<int>(k));
|
auto train = vector<int>();
|
||||||
if (stratified_indices[fold].size() == fold_size + 1) {
|
auto test = vector<int>();
|
||||||
continue;
|
for (int i = 0; i < n; i++) {
|
||||||
|
if (i >= nTest * nFold && i < nTest * (nFold + 1)) {
|
||||||
|
test.push_back(indices[i]);
|
||||||
|
} else {
|
||||||
|
train.push_back(indices[i]);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return { train, test };
|
||||||
|
}
|
||||||
|
StratifiedKFold::StratifiedKFold(int k, torch::Tensor& y, int seed) : Fold(k, y.numel(), seed)
|
||||||
|
{
|
||||||
|
n = y.numel();
|
||||||
|
this->y = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
|
||||||
|
build();
|
||||||
|
}
|
||||||
|
StratifiedKFold::StratifiedKFold(int k, const vector<int>& y, int seed)
|
||||||
|
: Fold(k, y.size(), seed)
|
||||||
|
{
|
||||||
|
this->y = y;
|
||||||
|
n = y.size();
|
||||||
|
build();
|
||||||
|
}
|
||||||
|
void StratifiedKFold::build()
|
||||||
|
{
|
||||||
|
stratified_indices = vector<vector<int>>(k);
|
||||||
|
int fold_size = n / k;
|
||||||
|
// Compute class counts and indices
|
||||||
|
auto class_indices = map<int, vector<int>>();
|
||||||
|
vector<int> class_counts(*max_element(y.begin(), y.end()) + 1, 0);
|
||||||
|
for (auto i = 0; i < n; ++i) {
|
||||||
|
class_counts[y[i]]++;
|
||||||
|
class_indices[y[i]].push_back(i);
|
||||||
|
}
|
||||||
|
// Shuffle class indices
|
||||||
|
for (auto& [cls, indices] : class_indices) {
|
||||||
|
shuffle(indices.begin(), indices.end(), random_seed);
|
||||||
|
}
|
||||||
|
// Assign indices to folds
|
||||||
|
for (auto label = 0; label < class_counts.size(); ++label) {
|
||||||
|
auto num_samples_to_take = class_counts[label] / k;
|
||||||
|
if (num_samples_to_take == 0)
|
||||||
|
continue;
|
||||||
|
auto remainder_samples_to_take = class_counts[label] % k;
|
||||||
|
for (auto fold = 0; fold < k; ++fold) {
|
||||||
|
auto it = next(class_indices[label].begin(), num_samples_to_take);
|
||||||
|
move(class_indices[label].begin(), it, back_inserter(stratified_indices[fold])); // ##
|
||||||
|
class_indices[label].erase(class_indices[label].begin(), it);
|
||||||
|
}
|
||||||
|
while (remainder_samples_to_take > 0) {
|
||||||
|
int fold = (rand() % static_cast<int>(k));
|
||||||
|
if (stratified_indices[fold].size() == fold_size + 1) {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
auto it = next(class_indices[label].begin(), 1);
|
||||||
|
stratified_indices[fold].push_back(*class_indices[label].begin());
|
||||||
|
class_indices[label].erase(class_indices[label].begin(), it);
|
||||||
|
remainder_samples_to_take--;
|
||||||
}
|
}
|
||||||
auto it = next(class_indices[label].begin(), 1);
|
|
||||||
stratified_indices[fold].push_back(*class_indices[label].begin());
|
|
||||||
class_indices[label].erase(class_indices[label].begin(), it);
|
|
||||||
remainder_samples_to_take--;
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
pair<vector<int>, vector<int>> StratifiedKFold::getFold(int nFold)
|
||||||
pair<vector<int>, vector<int>> StratifiedKFold::getFold(int nFold)
|
{
|
||||||
{
|
if (nFold >= k || nFold < 0) {
|
||||||
if (nFold >= k || nFold < 0) {
|
throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
|
||||||
throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
|
}
|
||||||
|
vector<int> test_indices = stratified_indices[nFold];
|
||||||
|
vector<int> train_indices;
|
||||||
|
for (int i = 0; i < k; ++i) {
|
||||||
|
if (i == nFold) continue;
|
||||||
|
train_indices.insert(train_indices.end(), stratified_indices[i].begin(), stratified_indices[i].end());
|
||||||
|
}
|
||||||
|
return { train_indices, test_indices };
|
||||||
}
|
}
|
||||||
vector<int> test_indices = stratified_indices[nFold];
|
|
||||||
vector<int> train_indices;
|
|
||||||
for (int i = 0; i < k; ++i) {
|
|
||||||
if (i == nFold) continue;
|
|
||||||
train_indices.insert(train_indices.end(), stratified_indices[i].begin(), stratified_indices[i].end());
|
|
||||||
}
|
|
||||||
return { train_indices, test_indices };
|
|
||||||
}
|
}
|
@@ -4,34 +4,35 @@
|
|||||||
#include <vector>
|
#include <vector>
|
||||||
#include <random>
|
#include <random>
|
||||||
using namespace std;
|
using namespace std;
|
||||||
|
namespace platform {
|
||||||
class Fold {
|
class Fold {
|
||||||
protected:
|
protected:
|
||||||
int k;
|
int k;
|
||||||
int n;
|
int n;
|
||||||
int seed;
|
int seed;
|
||||||
default_random_engine random_seed;
|
default_random_engine random_seed;
|
||||||
public:
|
public:
|
||||||
Fold(int k, int n, int seed = -1);
|
Fold(int k, int n, int seed = -1);
|
||||||
virtual pair<vector<int>, vector<int>> getFold(int nFold) = 0;
|
virtual pair<vector<int>, vector<int>> getFold(int nFold) = 0;
|
||||||
virtual ~Fold() = default;
|
virtual ~Fold() = default;
|
||||||
int getNumberOfFolds() { return k; }
|
int getNumberOfFolds() { return k; }
|
||||||
};
|
};
|
||||||
class KFold : public Fold {
|
class KFold : public Fold {
|
||||||
private:
|
private:
|
||||||
vector<int> indices;
|
vector<int> indices;
|
||||||
public:
|
public:
|
||||||
KFold(int k, int n, int seed = -1);
|
KFold(int k, int n, int seed = -1);
|
||||||
pair<vector<int>, vector<int>> getFold(int nFold) override;
|
pair<vector<int>, vector<int>> getFold(int nFold) override;
|
||||||
};
|
};
|
||||||
class StratifiedKFold : public Fold {
|
class StratifiedKFold : public Fold {
|
||||||
private:
|
private:
|
||||||
vector<int> y;
|
vector<int> y;
|
||||||
vector<vector<int>> stratified_indices;
|
vector<vector<int>> stratified_indices;
|
||||||
void build();
|
void build();
|
||||||
public:
|
public:
|
||||||
StratifiedKFold(int k, const vector<int>& y, int seed = -1);
|
StratifiedKFold(int k, const vector<int>& y, int seed = -1);
|
||||||
StratifiedKFold(int k, torch::Tensor& y, int seed = -1);
|
StratifiedKFold(int k, torch::Tensor& y, int seed = -1);
|
||||||
pair<vector<int>, vector<int>> getFold(int nFold) override;
|
pair<vector<int>, vector<int>> getFold(int nFold) override;
|
||||||
};
|
};
|
||||||
|
}
|
||||||
#endif
|
#endif
|
@@ -26,7 +26,7 @@ namespace platform {
|
|||||||
instance = it->second();
|
instance = it->second();
|
||||||
// wrap instance in a shared ptr and return
|
// wrap instance in a shared ptr and return
|
||||||
if (instance != nullptr)
|
if (instance != nullptr)
|
||||||
return shared_ptr<bayesnet::BaseClassifier>(instance);
|
return unique_ptr<bayesnet::BaseClassifier>(instance);
|
||||||
else
|
else
|
||||||
return nullptr;
|
return nullptr;
|
||||||
}
|
}
|
||||||
|
@@ -10,6 +10,7 @@
|
|||||||
#include "KDBLd.h"
|
#include "KDBLd.h"
|
||||||
#include "SPODELd.h"
|
#include "SPODELd.h"
|
||||||
#include "AODELd.h"
|
#include "AODELd.h"
|
||||||
|
#include "BoostAODE.h"
|
||||||
namespace platform {
|
namespace platform {
|
||||||
class Models {
|
class Models {
|
||||||
private:
|
private:
|
||||||
|
@@ -1,10 +1,12 @@
|
|||||||
#ifndef PATHS_H
|
#ifndef PATHS_H
|
||||||
#define PATHS_H
|
#define PATHS_H
|
||||||
|
#include <string>
|
||||||
namespace platform {
|
namespace platform {
|
||||||
class Paths {
|
class Paths {
|
||||||
public:
|
public:
|
||||||
static std::string datasets() { return "datasets/"; }
|
static std::string datasets() { return "datasets/"; }
|
||||||
static std::string results() { return "results/"; }
|
static std::string results() { return "results/"; }
|
||||||
|
static std::string excel() { return "excel/"; }
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
@@ -1,26 +0,0 @@
|
|||||||
#ifndef REPORT_H
|
|
||||||
#define REPORT_H
|
|
||||||
#include <string>
|
|
||||||
#include <iostream>
|
|
||||||
#include <nlohmann/json.hpp>
|
|
||||||
#include "Colors.h"
|
|
||||||
|
|
||||||
using json = nlohmann::json;
|
|
||||||
const int MAXL = 121;
|
|
||||||
namespace platform {
|
|
||||||
using namespace std;
|
|
||||||
class Report {
|
|
||||||
public:
|
|
||||||
explicit Report(json data_) { data = data_; };
|
|
||||||
virtual ~Report() = default;
|
|
||||||
void show();
|
|
||||||
private:
|
|
||||||
void header();
|
|
||||||
void body();
|
|
||||||
void footer();
|
|
||||||
string fromVector(const string& key);
|
|
||||||
json data;
|
|
||||||
double totalScore; // Total score of all results in a report
|
|
||||||
};
|
|
||||||
};
|
|
||||||
#endif
|
|
37
src/Platform/ReportBase.cc
Normal file
37
src/Platform/ReportBase.cc
Normal file
@@ -0,0 +1,37 @@
|
|||||||
|
#include <sstream>
|
||||||
|
#include <locale>
|
||||||
|
#include "ReportBase.h"
|
||||||
|
#include "BestResult.h"
|
||||||
|
|
||||||
|
|
||||||
|
namespace platform {
|
||||||
|
string ReportBase::fromVector(const string& key)
|
||||||
|
{
|
||||||
|
stringstream oss;
|
||||||
|
string sep = "";
|
||||||
|
oss << "[";
|
||||||
|
for (auto& item : data[key]) {
|
||||||
|
oss << sep << item.get<double>();
|
||||||
|
sep = ", ";
|
||||||
|
}
|
||||||
|
oss << "]";
|
||||||
|
return oss.str();
|
||||||
|
}
|
||||||
|
string ReportBase::fVector(const string& title, const json& data, const int width, const int precision)
|
||||||
|
{
|
||||||
|
stringstream oss;
|
||||||
|
string sep = "";
|
||||||
|
oss << title << "[";
|
||||||
|
for (const auto& item : data) {
|
||||||
|
oss << sep << fixed << setw(width) << setprecision(precision) << item.get<double>();
|
||||||
|
sep = ", ";
|
||||||
|
}
|
||||||
|
oss << "]";
|
||||||
|
return oss.str();
|
||||||
|
}
|
||||||
|
void ReportBase::show()
|
||||||
|
{
|
||||||
|
header();
|
||||||
|
body();
|
||||||
|
}
|
||||||
|
}
|
23
src/Platform/ReportBase.h
Normal file
23
src/Platform/ReportBase.h
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
#ifndef REPORTBASE_H
|
||||||
|
#define REPORTBASE_H
|
||||||
|
#include <string>
|
||||||
|
#include <iostream>
|
||||||
|
#include <nlohmann/json.hpp>
|
||||||
|
|
||||||
|
using json = nlohmann::json;
|
||||||
|
namespace platform {
|
||||||
|
using namespace std;
|
||||||
|
class ReportBase {
|
||||||
|
public:
|
||||||
|
explicit ReportBase(json data_) { data = data_; };
|
||||||
|
virtual ~ReportBase() = default;
|
||||||
|
void show();
|
||||||
|
protected:
|
||||||
|
json data;
|
||||||
|
string fromVector(const string& key);
|
||||||
|
string fVector(const string& title, const json& data, const int width, const int precision);
|
||||||
|
virtual void header() = 0;
|
||||||
|
virtual void body() = 0;
|
||||||
|
};
|
||||||
|
};
|
||||||
|
#endif
|
@@ -1,53 +1,45 @@
|
|||||||
#include "Report.h"
|
#include <sstream>
|
||||||
|
#include <locale>
|
||||||
|
#include "ReportConsole.h"
|
||||||
#include "BestResult.h"
|
#include "BestResult.h"
|
||||||
|
|
||||||
|
|
||||||
namespace platform {
|
namespace platform {
|
||||||
string headerLine(const string& text)
|
struct separated : numpunct<char> {
|
||||||
|
char do_decimal_point() const { return ','; }
|
||||||
|
char do_thousands_sep() const { return '.'; }
|
||||||
|
string do_grouping() const { return "\03"; }
|
||||||
|
};
|
||||||
|
|
||||||
|
string ReportConsole::headerLine(const string& text)
|
||||||
{
|
{
|
||||||
int n = MAXL - text.length() - 3;
|
int n = MAXL - text.length() - 3;
|
||||||
n = n < 0 ? 0 : n;
|
n = n < 0 ? 0 : n;
|
||||||
return "* " + text + string(n, ' ') + "*\n";
|
return "* " + text + string(n, ' ') + "*\n";
|
||||||
}
|
}
|
||||||
string Report::fromVector(const string& key)
|
|
||||||
{
|
|
||||||
string result = "";
|
|
||||||
|
|
||||||
for (auto& item : data[key]) {
|
void ReportConsole::header()
|
||||||
result += to_string(item) + ", ";
|
|
||||||
}
|
|
||||||
return "[" + result.substr(0, result.size() - 2) + "]";
|
|
||||||
}
|
|
||||||
string fVector(const json& data)
|
|
||||||
{
|
|
||||||
string result = "";
|
|
||||||
for (const auto& item : data) {
|
|
||||||
result += to_string(item) + ", ";
|
|
||||||
}
|
|
||||||
return "[" + result.substr(0, result.size() - 2) + "]";
|
|
||||||
}
|
|
||||||
void Report::show()
|
|
||||||
{
|
|
||||||
header();
|
|
||||||
body();
|
|
||||||
footer();
|
|
||||||
}
|
|
||||||
void Report::header()
|
|
||||||
{
|
{
|
||||||
|
locale mylocale(cout.getloc(), new separated);
|
||||||
|
locale::global(mylocale);
|
||||||
|
cout.imbue(mylocale);
|
||||||
|
stringstream oss;
|
||||||
cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
|
cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
|
||||||
cout << headerLine("Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) + " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
|
cout << headerLine("Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) + " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
|
||||||
cout << headerLine(data["title"].get<string>());
|
cout << headerLine(data["title"].get<string>());
|
||||||
cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
|
cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
|
||||||
cout << headerLine("Execution took " + to_string(data["duration"].get<float>()) + " seconds, " + to_string(data["duration"].get<float>() / 3600) + " hours, on " + data["platform"].get<string>());
|
oss << "Execution took " << setprecision(2) << fixed << data["duration"].get<float>() << " seconds, " << data["duration"].get<float>() / 3600 << " hours, on " << data["platform"].get<string>();
|
||||||
|
cout << headerLine(oss.str());
|
||||||
cout << headerLine("Score is " + data["score_name"].get<string>());
|
cout << headerLine("Score is " + data["score_name"].get<string>());
|
||||||
cout << string(MAXL, '*') << endl;
|
cout << string(MAXL, '*') << endl;
|
||||||
cout << endl;
|
cout << endl;
|
||||||
}
|
}
|
||||||
void Report::body()
|
void ReportConsole::body()
|
||||||
{
|
{
|
||||||
cout << Colors::GREEN() << "Dataset Sampl. Feat. Cls Nodes Edges States Score Time Hyperparameters" << endl;
|
cout << Colors::GREEN() << "Dataset Sampl. Feat. Cls Nodes Edges States Score Time Hyperparameters" << endl;
|
||||||
cout << "============================== ====== ===== === ======= ======= ======= =============== ================== ===============" << endl;
|
cout << "============================== ====== ===== === ========= ========= ========= =============== ================== ===============" << endl;
|
||||||
json lastResult;
|
json lastResult;
|
||||||
totalScore = 0;
|
double totalScore = 0.0;
|
||||||
bool odd = true;
|
bool odd = true;
|
||||||
for (const auto& r : data["results"]) {
|
for (const auto& r : data["results"]) {
|
||||||
auto color = odd ? Colors::CYAN() : Colors::BLUE();
|
auto color = odd ? Colors::CYAN() : Colors::BLUE();
|
||||||
@@ -55,9 +47,9 @@ namespace platform {
|
|||||||
cout << setw(6) << right << r["samples"].get<int>() << " ";
|
cout << setw(6) << right << r["samples"].get<int>() << " ";
|
||||||
cout << setw(5) << right << r["features"].get<int>() << " ";
|
cout << setw(5) << right << r["features"].get<int>() << " ";
|
||||||
cout << setw(3) << right << r["classes"].get<int>() << " ";
|
cout << setw(3) << right << r["classes"].get<int>() << " ";
|
||||||
cout << setw(7) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
|
cout << setw(9) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
|
||||||
cout << setw(7) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
|
cout << setw(9) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
|
||||||
cout << setw(7) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
|
cout << setw(9) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
|
||||||
cout << setw(8) << right << setprecision(6) << fixed << r["score"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_std"].get<double>() << " ";
|
cout << setw(8) << right << setprecision(6) << fixed << r["score"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_std"].get<double>() << " ";
|
||||||
cout << setw(11) << right << setprecision(6) << fixed << r["time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["time_std"].get<double>() << " ";
|
cout << setw(11) << right << setprecision(6) << fixed << r["time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["time_std"].get<double>() << " ";
|
||||||
try {
|
try {
|
||||||
@@ -73,21 +65,24 @@ namespace platform {
|
|||||||
}
|
}
|
||||||
if (data["results"].size() == 1) {
|
if (data["results"].size() == 1) {
|
||||||
cout << string(MAXL, '*') << endl;
|
cout << string(MAXL, '*') << endl;
|
||||||
cout << headerLine("Train scores: " + fVector(lastResult["scores_train"]));
|
cout << headerLine(fVector("Train scores: ", lastResult["scores_train"], 14, 12));
|
||||||
cout << headerLine("Test scores: " + fVector(lastResult["scores_test"]));
|
cout << headerLine(fVector("Test scores: ", lastResult["scores_test"], 14, 12));
|
||||||
cout << headerLine("Train times: " + fVector(lastResult["times_train"]));
|
cout << headerLine(fVector("Train times: ", lastResult["times_train"], 10, 3));
|
||||||
cout << headerLine("Test times: " + fVector(lastResult["times_test"]));
|
cout << headerLine(fVector("Test times: ", lastResult["times_test"], 10, 3));
|
||||||
cout << string(MAXL, '*') << endl;
|
cout << string(MAXL, '*') << endl;
|
||||||
|
} else {
|
||||||
|
footer(totalScore);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
void Report::footer()
|
void ReportConsole::footer(double totalScore)
|
||||||
{
|
{
|
||||||
cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
|
cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
|
||||||
auto score = data["score_name"].get<string>();
|
auto score = data["score_name"].get<string>();
|
||||||
if (score == BestResult::scoreName()) {
|
if (score == BestResult::scoreName()) {
|
||||||
cout << headerLine(score + " compared to " + BestResult::title() + " .: " + to_string(totalScore / BestResult::score()));
|
stringstream oss;
|
||||||
|
oss << score << " compared to " << BestResult::title() << " .: " << totalScore / BestResult::score();
|
||||||
|
cout << headerLine(oss.str());
|
||||||
}
|
}
|
||||||
cout << string(MAXL, '*') << endl << Colors::RESET();
|
cout << string(MAXL, '*') << endl << Colors::RESET();
|
||||||
|
|
||||||
}
|
}
|
||||||
}
|
}
|
22
src/Platform/ReportConsole.h
Normal file
22
src/Platform/ReportConsole.h
Normal file
@@ -0,0 +1,22 @@
|
|||||||
|
#ifndef REPORTCONSOLE_H
|
||||||
|
#define REPORTCONSOLE_H
|
||||||
|
#include <string>
|
||||||
|
#include <iostream>
|
||||||
|
#include "ReportBase.h"
|
||||||
|
#include "Colors.h"
|
||||||
|
|
||||||
|
namespace platform {
|
||||||
|
using namespace std;
|
||||||
|
const int MAXL = 128;
|
||||||
|
class ReportConsole : public ReportBase{
|
||||||
|
public:
|
||||||
|
explicit ReportConsole(json data_) : ReportBase(data_) {};
|
||||||
|
virtual ~ReportConsole() = default;
|
||||||
|
private:
|
||||||
|
string headerLine(const string& text);
|
||||||
|
void header() override;
|
||||||
|
void body() override;
|
||||||
|
void footer(double totalScore);
|
||||||
|
};
|
||||||
|
};
|
||||||
|
#endif
|
109
src/Platform/ReportExcel.cc
Normal file
109
src/Platform/ReportExcel.cc
Normal file
@@ -0,0 +1,109 @@
|
|||||||
|
#include <sstream>
|
||||||
|
#include <locale>
|
||||||
|
#include "ReportExcel.h"
|
||||||
|
#include "BestResult.h"
|
||||||
|
|
||||||
|
|
||||||
|
namespace platform {
|
||||||
|
struct separated : numpunct<char> {
|
||||||
|
char do_decimal_point() const { return ','; }
|
||||||
|
|
||||||
|
char do_thousands_sep() const { return '.'; }
|
||||||
|
|
||||||
|
string do_grouping() const { return "\03"; }
|
||||||
|
};
|
||||||
|
|
||||||
|
void ReportExcel::createFile()
|
||||||
|
{
|
||||||
|
doc.create(Paths::excel() + "some_results.xlsx");
|
||||||
|
wks = doc.workbook().worksheet("Sheet1");
|
||||||
|
wks.setName(data["model"].get<string>());
|
||||||
|
}
|
||||||
|
|
||||||
|
void ReportExcel::closeFile()
|
||||||
|
{
|
||||||
|
doc.save();
|
||||||
|
doc.close();
|
||||||
|
}
|
||||||
|
|
||||||
|
void ReportExcel::header()
|
||||||
|
{
|
||||||
|
locale mylocale(cout.getloc(), new separated);
|
||||||
|
locale::global(mylocale);
|
||||||
|
cout.imbue(mylocale);
|
||||||
|
stringstream oss;
|
||||||
|
wks.cell("A1").value().set(
|
||||||
|
"Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " +
|
||||||
|
to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) +
|
||||||
|
" random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
|
||||||
|
wks.cell("A2").value() = data["title"].get<string>();
|
||||||
|
wks.cell("A3").value() = "Random seeds: " + fromVector("seeds") + " Stratified: " +
|
||||||
|
(data["stratified"].get<bool>() ? "True" : "False");
|
||||||
|
oss << "Execution took " << setprecision(2) << fixed << data["duration"].get<float>() << " seconds, "
|
||||||
|
<< data["duration"].get<float>() / 3600 << " hours, on " << data["platform"].get<string>();
|
||||||
|
wks.cell("A4").value() = oss.str();
|
||||||
|
wks.cell("A5").value() = "Score is " + data["score_name"].get<string>();
|
||||||
|
}
|
||||||
|
|
||||||
|
void ReportExcel::body()
|
||||||
|
{
|
||||||
|
auto head = vector<string>(
|
||||||
|
{ "Dataset", "Samples", "Features", "Classes", "Nodes", "Edges", "States", "Score", "Score Std.", "Time",
|
||||||
|
"Time Std.", "Hyperparameters" });
|
||||||
|
int col = 1;
|
||||||
|
for (const auto& item : head) {
|
||||||
|
wks.cell(8, col++).value() = item;
|
||||||
|
}
|
||||||
|
int row = 9;
|
||||||
|
col = 1;
|
||||||
|
json lastResult;
|
||||||
|
double totalScore = 0.0;
|
||||||
|
string hyperparameters;
|
||||||
|
for (const auto& r : data["results"]) {
|
||||||
|
wks.cell(row, col).value() = r["dataset"].get<string>();
|
||||||
|
wks.cell(row, col + 1).value() = r["samples"].get<int>();
|
||||||
|
wks.cell(row, col + 2).value() = r["features"].get<int>();
|
||||||
|
wks.cell(row, col + 3).value() = r["classes"].get<int>();
|
||||||
|
wks.cell(row, col + 4).value() = r["nodes"].get<float>();
|
||||||
|
wks.cell(row, col + 5).value() = r["leaves"].get<float>();
|
||||||
|
wks.cell(row, col + 6).value() = r["depth"].get<float>();
|
||||||
|
wks.cell(row, col + 7).value() = r["score"].get<double>();
|
||||||
|
wks.cell(row, col + 8).value() = r["score_std"].get<double>();
|
||||||
|
wks.cell(row, col + 9).value() = r["time"].get<double>();
|
||||||
|
wks.cell(row, col + 10).value() = r["time_std"].get<double>();
|
||||||
|
try {
|
||||||
|
hyperparameters = r["hyperparameters"].get<string>();
|
||||||
|
}
|
||||||
|
catch (const exception& err) {
|
||||||
|
stringstream oss;
|
||||||
|
oss << r["hyperparameters"];
|
||||||
|
hyperparameters = oss.str();
|
||||||
|
}
|
||||||
|
wks.cell(row, col + 11).value() = hyperparameters;
|
||||||
|
lastResult = r;
|
||||||
|
totalScore += r["score"].get<double>();
|
||||||
|
row++;
|
||||||
|
}
|
||||||
|
if (data["results"].size() == 1) {
|
||||||
|
for (const string& group : { "scores_train", "scores_test", "times_train", "times_test" }) {
|
||||||
|
row++;
|
||||||
|
col = 1;
|
||||||
|
wks.cell(row, col).value() = group;
|
||||||
|
for (double item : lastResult[group]) {
|
||||||
|
wks.cell(row, ++col).value() = item;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
footer(totalScore, row);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
void ReportExcel::footer(double totalScore, int row)
|
||||||
|
{
|
||||||
|
auto score = data["score_name"].get<string>();
|
||||||
|
if (score == BestResult::scoreName()) {
|
||||||
|
wks.cell(row + 2, 1).value() = score + " compared to " + BestResult::title() + " .: ";
|
||||||
|
wks.cell(row + 2, 5).value() = totalScore / BestResult::score();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
25
src/Platform/ReportExcel.h
Normal file
25
src/Platform/ReportExcel.h
Normal file
@@ -0,0 +1,25 @@
|
|||||||
|
#ifndef REPORTEXCEL_H
|
||||||
|
#define REPORTEXCEL_H
|
||||||
|
#include <OpenXLSX.hpp>
|
||||||
|
#include "ReportBase.h"
|
||||||
|
#include "Paths.h"
|
||||||
|
#include "Colors.h"
|
||||||
|
namespace platform {
|
||||||
|
using namespace std;
|
||||||
|
using namespace OpenXLSX;
|
||||||
|
const int MAXLL = 128;
|
||||||
|
class ReportExcel : public ReportBase{
|
||||||
|
public:
|
||||||
|
explicit ReportExcel(json data_) : ReportBase(data_) {createFile();};
|
||||||
|
virtual ~ReportExcel() {closeFile();};
|
||||||
|
private:
|
||||||
|
void createFile();
|
||||||
|
void closeFile();
|
||||||
|
XLDocument doc;
|
||||||
|
XLWorksheet wks;
|
||||||
|
void header() override;
|
||||||
|
void body() override;
|
||||||
|
void footer(double totalScore, int row);
|
||||||
|
};
|
||||||
|
};
|
||||||
|
#endif // !REPORTEXCEL_H
|
@@ -1,7 +1,8 @@
|
|||||||
#include <filesystem>
|
#include <filesystem>
|
||||||
#include "platformUtils.h"
|
#include "platformUtils.h"
|
||||||
#include "Results.h"
|
#include "Results.h"
|
||||||
#include "Report.h"
|
#include "ReportConsole.h"
|
||||||
|
#include "ReportExcel.h"
|
||||||
#include "BestResult.h"
|
#include "BestResult.h"
|
||||||
#include "Colors.h"
|
#include "Colors.h"
|
||||||
namespace platform {
|
namespace platform {
|
||||||
@@ -94,21 +95,26 @@ namespace platform {
|
|||||||
cout << "Invalid index" << endl;
|
cout << "Invalid index" << endl;
|
||||||
return -1;
|
return -1;
|
||||||
}
|
}
|
||||||
void Results::report(const int index) const
|
void Results::report(const int index, const bool excelReport) const
|
||||||
{
|
{
|
||||||
cout << Colors::YELLOW() << "Reporting " << files.at(index).getFilename() << endl;
|
cout << Colors::YELLOW() << "Reporting " << files.at(index).getFilename() << endl;
|
||||||
auto data = files.at(index).load();
|
auto data = files.at(index).load();
|
||||||
Report report(data);
|
if (excelReport) {
|
||||||
report.show();
|
ReportExcel reporter(data);
|
||||||
|
reporter.show();
|
||||||
|
} else {
|
||||||
|
ReportConsole reporter(data);
|
||||||
|
reporter.show();
|
||||||
|
}
|
||||||
}
|
}
|
||||||
void Results::menu()
|
void Results::menu()
|
||||||
{
|
{
|
||||||
char option;
|
char option;
|
||||||
int index;
|
int index;
|
||||||
bool finished = false;
|
bool finished = false;
|
||||||
string filename, line, options = "qldhsr";
|
string filename, line, options = "qldhsre";
|
||||||
while (!finished) {
|
while (!finished) {
|
||||||
cout << Colors::RESET() << "Choose option (quit='q', list='l', delete='d', hide='h', sort='s', report='r'): ";
|
cout << Colors::RESET() << "Choose option (quit='q', list='l', delete='d', hide='h', sort='s', report='r', excel='e'): ";
|
||||||
getline(cin, line);
|
getline(cin, line);
|
||||||
if (line.size() == 0)
|
if (line.size() == 0)
|
||||||
continue;
|
continue;
|
||||||
@@ -119,12 +125,14 @@ namespace platform {
|
|||||||
}
|
}
|
||||||
option = line[0];
|
option = line[0];
|
||||||
} else {
|
} else {
|
||||||
index = stoi(line);
|
if (all_of(line.begin(), line.end(), ::isdigit)) {
|
||||||
if (index >= 0 && index < files.size()) {
|
index = stoi(line);
|
||||||
report(index);
|
if (index >= 0 && index < files.size()) {
|
||||||
} else {
|
report(index, false);
|
||||||
cout << "Invalid option" << endl;
|
continue;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
cout << "Invalid option" << endl;
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
switch (option) {
|
switch (option) {
|
||||||
@@ -164,7 +172,13 @@ namespace platform {
|
|||||||
index = getIndex("report");
|
index = getIndex("report");
|
||||||
if (index == -1)
|
if (index == -1)
|
||||||
break;
|
break;
|
||||||
report(index);
|
report(index, false);
|
||||||
|
break;
|
||||||
|
case 'e':
|
||||||
|
index = getIndex("excel");
|
||||||
|
if (index == -1)
|
||||||
|
break;
|
||||||
|
report(index, true);
|
||||||
break;
|
break;
|
||||||
default:
|
default:
|
||||||
cout << "Invalid option" << endl;
|
cout << "Invalid option" << endl;
|
||||||
@@ -231,6 +245,7 @@ namespace platform {
|
|||||||
cout << "No results found!" << endl;
|
cout << "No results found!" << endl;
|
||||||
exit(0);
|
exit(0);
|
||||||
}
|
}
|
||||||
|
sortDate();
|
||||||
show();
|
show();
|
||||||
menu();
|
menu();
|
||||||
cout << "Done!" << endl;
|
cout << "Done!" << endl;
|
||||||
|
@@ -42,7 +42,7 @@ namespace platform {
|
|||||||
vector<Result> files;
|
vector<Result> files;
|
||||||
void load(); // Loads the list of results
|
void load(); // Loads the list of results
|
||||||
void show() const;
|
void show() const;
|
||||||
void report(const int index) const;
|
void report(const int index, const bool excelReport) const;
|
||||||
int getIndex(const string& intent) const;
|
int getIndex(const string& intent) const;
|
||||||
void menu();
|
void menu();
|
||||||
void sortList();
|
void sortList();
|
||||||
|
57
src/Platform/list.cc
Normal file
57
src/Platform/list.cc
Normal file
@@ -0,0 +1,57 @@
|
|||||||
|
#include <iostream>
|
||||||
|
#include <locale>
|
||||||
|
#include "Paths.h"
|
||||||
|
#include "Colors.h"
|
||||||
|
#include "Datasets.h"
|
||||||
|
|
||||||
|
using namespace std;
|
||||||
|
const int BALANCE_LENGTH = 75;
|
||||||
|
|
||||||
|
struct separated : numpunct<char> {
|
||||||
|
char do_decimal_point() const { return ','; }
|
||||||
|
char do_thousands_sep() const { return '.'; }
|
||||||
|
string do_grouping() const { return "\03"; }
|
||||||
|
};
|
||||||
|
|
||||||
|
void outputBalance(const string& balance)
|
||||||
|
{
|
||||||
|
auto temp = string(balance);
|
||||||
|
while (temp.size() > BALANCE_LENGTH - 1) {
|
||||||
|
auto part = temp.substr(0, BALANCE_LENGTH);
|
||||||
|
cout << part << endl;
|
||||||
|
cout << setw(48) << " ";
|
||||||
|
temp = temp.substr(BALANCE_LENGTH);
|
||||||
|
}
|
||||||
|
cout << temp << endl;
|
||||||
|
}
|
||||||
|
|
||||||
|
int main(int argc, char** argv)
|
||||||
|
{
|
||||||
|
auto data = platform::Datasets(platform::Paths().datasets(), false);
|
||||||
|
locale mylocale(cout.getloc(), new separated);
|
||||||
|
locale::global(mylocale);
|
||||||
|
cout.imbue(mylocale);
|
||||||
|
cout << Colors::GREEN() << "Dataset Sampl. Feat. Cls. Balance" << endl;
|
||||||
|
string balanceBars = string(BALANCE_LENGTH, '=');
|
||||||
|
cout << "============================== ====== ===== === " << balanceBars << endl;
|
||||||
|
bool odd = true;
|
||||||
|
for (const auto& dataset : data.getNames()) {
|
||||||
|
auto color = odd ? Colors::CYAN() : Colors::BLUE();
|
||||||
|
cout << color << setw(30) << left << dataset << " ";
|
||||||
|
data.loadDataset(dataset);
|
||||||
|
auto nSamples = data.getNSamples(dataset);
|
||||||
|
cout << setw(6) << right << nSamples << " ";
|
||||||
|
cout << setw(5) << right << data.getFeatures(dataset).size() << " ";
|
||||||
|
cout << setw(3) << right << data.getNClasses(dataset) << " ";
|
||||||
|
stringstream oss;
|
||||||
|
string sep = "";
|
||||||
|
for (auto number : data.getClassesCounts(dataset)) {
|
||||||
|
oss << sep << setprecision(2) << fixed << (float)number / nSamples * 100.0 << "% (" << number << ")";
|
||||||
|
sep = " / ";
|
||||||
|
}
|
||||||
|
outputBalance(oss.str());
|
||||||
|
odd = !odd;
|
||||||
|
}
|
||||||
|
cout << Colors::RESET() << endl;
|
||||||
|
return 0;
|
||||||
|
}
|
@@ -1,5 +1,6 @@
|
|||||||
#include <iostream>
|
#include <iostream>
|
||||||
#include <argparse/argparse.hpp>
|
#include <argparse/argparse.hpp>
|
||||||
|
#include <nlohmann/json.hpp>
|
||||||
#include "platformUtils.h"
|
#include "platformUtils.h"
|
||||||
#include "Experiment.h"
|
#include "Experiment.h"
|
||||||
#include "Datasets.h"
|
#include "Datasets.h"
|
||||||
@@ -10,12 +11,14 @@
|
|||||||
|
|
||||||
|
|
||||||
using namespace std;
|
using namespace std;
|
||||||
|
using json = nlohmann::json;
|
||||||
|
|
||||||
argparse::ArgumentParser manageArguments(int argc, char** argv)
|
argparse::ArgumentParser manageArguments(int argc, char** argv)
|
||||||
{
|
{
|
||||||
auto env = platform::DotEnv();
|
auto env = platform::DotEnv();
|
||||||
argparse::ArgumentParser program("main");
|
argparse::ArgumentParser program("main");
|
||||||
program.add_argument("-d", "--dataset").default_value("").help("Dataset file name");
|
program.add_argument("-d", "--dataset").default_value("").help("Dataset file name");
|
||||||
|
program.add_argument("--hyperparameters").default_value("{}").help("Hyperparamters passed to the model in Experiment");
|
||||||
program.add_argument("-p", "--path")
|
program.add_argument("-p", "--path")
|
||||||
.help("folder where the data files are located, default")
|
.help("folder where the data files are located, default")
|
||||||
.default_value(string{ platform::Paths::datasets() });
|
.default_value(string{ platform::Paths::datasets() });
|
||||||
@@ -31,6 +34,7 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
|
|||||||
);
|
);
|
||||||
program.add_argument("--title").default_value("").help("Experiment title");
|
program.add_argument("--title").default_value("").help("Experiment title");
|
||||||
program.add_argument("--discretize").help("Discretize input dataset").default_value((bool)stoi(env.get("discretize"))).implicit_value(true);
|
program.add_argument("--discretize").help("Discretize input dataset").default_value((bool)stoi(env.get("discretize"))).implicit_value(true);
|
||||||
|
program.add_argument("--save").help("Save result (always save if no dataset is supplied)").default_value(false).implicit_value(true);
|
||||||
program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value((bool)stoi(env.get("stratified"))).implicit_value(true);
|
program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value((bool)stoi(env.get("stratified"))).implicit_value(true);
|
||||||
program.add_argument("-f", "--folds").help("Number of folds").default_value(stoi(env.get("n_folds"))).scan<'i', int>().action([](const string& value) {
|
program.add_argument("-f", "--folds").help("Number of folds").default_value(stoi(env.get("n_folds"))).scan<'i', int>().action([](const string& value) {
|
||||||
try {
|
try {
|
||||||
@@ -59,6 +63,8 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
|
|||||||
auto seeds = program.get<vector<int>>("seeds");
|
auto seeds = program.get<vector<int>>("seeds");
|
||||||
auto complete_file_name = path + file_name + ".arff";
|
auto complete_file_name = path + file_name + ".arff";
|
||||||
auto title = program.get<string>("title");
|
auto title = program.get<string>("title");
|
||||||
|
auto hyperparameters = program.get<string>("hyperparameters");
|
||||||
|
auto saveResults = program.get<bool>("save");
|
||||||
if (title == "" && file_name == "") {
|
if (title == "" && file_name == "") {
|
||||||
throw runtime_error("title is mandatory if dataset is not provided");
|
throw runtime_error("title is mandatory if dataset is not provided");
|
||||||
}
|
}
|
||||||
@@ -74,7 +80,6 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
|
|||||||
int main(int argc, char** argv)
|
int main(int argc, char** argv)
|
||||||
{
|
{
|
||||||
auto program = manageArguments(argc, argv);
|
auto program = manageArguments(argc, argv);
|
||||||
bool saveResults = false;
|
|
||||||
auto file_name = program.get<string>("dataset");
|
auto file_name = program.get<string>("dataset");
|
||||||
auto path = program.get<string>("path");
|
auto path = program.get<string>("path");
|
||||||
auto model_name = program.get<string>("model");
|
auto model_name = program.get<string>("model");
|
||||||
@@ -82,9 +87,11 @@ int main(int argc, char** argv)
|
|||||||
auto stratified = program.get<bool>("stratified");
|
auto stratified = program.get<bool>("stratified");
|
||||||
auto n_folds = program.get<int>("folds");
|
auto n_folds = program.get<int>("folds");
|
||||||
auto seeds = program.get<vector<int>>("seeds");
|
auto seeds = program.get<vector<int>>("seeds");
|
||||||
|
auto hyperparameters =program.get<string>("hyperparameters");
|
||||||
vector<string> filesToTest;
|
vector<string> filesToTest;
|
||||||
auto datasets = platform::Datasets(path, true, platform::ARFF);
|
auto datasets = platform::Datasets(path, true, platform::ARFF);
|
||||||
auto title = program.get<string>("title");
|
auto title = program.get<string>("title");
|
||||||
|
auto saveResults = program.get<bool>("save");
|
||||||
if (file_name != "") {
|
if (file_name != "") {
|
||||||
if (!datasets.isDataset(file_name)) {
|
if (!datasets.isDataset(file_name)) {
|
||||||
cerr << "Dataset " << file_name << " not found" << endl;
|
cerr << "Dataset " << file_name << " not found" << endl;
|
||||||
@@ -103,9 +110,10 @@ int main(int argc, char** argv)
|
|||||||
*/
|
*/
|
||||||
auto env = platform::DotEnv();
|
auto env = platform::DotEnv();
|
||||||
auto experiment = platform::Experiment();
|
auto experiment = platform::Experiment();
|
||||||
experiment.setTitle(title).setLanguage("cpp").setLanguageVersion("1.0.0");
|
experiment.setTitle(title).setLanguage("cpp").setLanguageVersion("14.0.3");
|
||||||
experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform(env.get("platform"));
|
experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform(env.get("platform"));
|
||||||
experiment.setStratified(stratified).setNFolds(n_folds).setScoreName("accuracy");
|
experiment.setStratified(stratified).setNFolds(n_folds).setScoreName("accuracy");
|
||||||
|
experiment.setHyperparameters(json::parse(hyperparameters));
|
||||||
for (auto seed : seeds) {
|
for (auto seed : seeds) {
|
||||||
experiment.addRandomSeed(seed);
|
experiment.addRandomSeed(seed);
|
||||||
}
|
}
|
||||||
@@ -113,10 +121,10 @@ int main(int argc, char** argv)
|
|||||||
timer.start();
|
timer.start();
|
||||||
experiment.go(filesToTest, path);
|
experiment.go(filesToTest, path);
|
||||||
experiment.setDuration(timer.getDuration());
|
experiment.setDuration(timer.getDuration());
|
||||||
if (saveResults)
|
if (saveResults) {
|
||||||
experiment.save(platform::Paths::results());
|
experiment.save(platform::Paths::results());
|
||||||
else
|
}
|
||||||
experiment.report();
|
experiment.report();
|
||||||
cout << "Done!" << endl;
|
cout << "Done!" << endl;
|
||||||
return 0;
|
return 0;
|
||||||
}
|
}
|
||||||
|
@@ -16,4 +16,6 @@ static platform::Registrar registrarA("AODE",
|
|||||||
[](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODE();});
|
[](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODE();});
|
||||||
static platform::Registrar registrarALD("AODELd",
|
static platform::Registrar registrarALD("AODELd",
|
||||||
[](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODELd();});
|
[](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODELd();});
|
||||||
|
static platform::Registrar registrarBA("BoostAODE",
|
||||||
|
[](void) -> bayesnet::BaseClassifier* { return new bayesnet::BoostAODE();});
|
||||||
#endif
|
#endif
|
@@ -69,11 +69,12 @@ tuple<Tensor, Tensor, vector<string>, string, map<string, vector<int>>> loadData
|
|||||||
Xd = torch::zeros({ static_cast<int>(Xr[0].size()), static_cast<int>(Xr.size()) }, torch::kInt32);
|
Xd = torch::zeros({ static_cast<int>(Xr[0].size()), static_cast<int>(Xr.size()) }, torch::kInt32);
|
||||||
for (int i = 0; i < features.size(); ++i) {
|
for (int i = 0; i < features.size(); ++i) {
|
||||||
states[features[i]] = vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
|
states[features[i]] = vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
|
||||||
iota(begin(states[features[i]]), end(states[features[i]]), 0);
|
auto item = states.at(features[i]);
|
||||||
|
iota(begin(item), end(item), 0);
|
||||||
Xd.index_put_({ "...", i }, torch::tensor(Xr[i], torch::kInt32));
|
Xd.index_put_({ "...", i }, torch::tensor(Xr[i], torch::kInt32));
|
||||||
}
|
}
|
||||||
states[className] = vector<int>(*max_element(y.begin(), y.end()) + 1);
|
states[className] = vector<int>(*max_element(y.begin(), y.end()) + 1);
|
||||||
iota(begin(states[className]), end(states[className]), 0);
|
iota(begin(states.at(className)), end(states.at(className)), 0);
|
||||||
} else {
|
} else {
|
||||||
Xd = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, torch::kFloat32);
|
Xd = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, torch::kFloat32);
|
||||||
for (int i = 0; i < features.size(); ++i) {
|
for (int i = 0; i < features.size(); ++i) {
|
||||||
|
Reference in New Issue
Block a user