rmontanana/mdlp
1
1
Fork 0
mirror of https://github.com/rmontanana/mdlp.git synced 2025-08-16 07:55:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix mistake in class type of ArffFiles

Browse Source 
Add some type casting to CPPFImdlp
Add additional path to datasets in tests
Fix some smells in sample
Join CMakeLists
This commit is contained in:
Ricardo Montañana Gómez
2023-03-18 18:40:10 +01:00
parent 1f4abade2c
commit f0845c5bd1
12 changed files with 87 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
sample/.vscode/launch.json vendored
View File

@@ -1,30 +1,21 @@
{
// Use IntelliSense to learn about possible attributes.
// Hover to view descriptions of existing attributes.
// For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
"version": "0.2.0",
"configurations": [
{
"name": "Launch sample",
"name": "lldb puro",
"type": "cppdbg",
// "targetArchitecture": "arm64",
"request": "launch",
"program": "${workspaceRoot}/build/sample",
"args": [
"-f",
"glass"
],
"setupCommands": [
{
"description": "Enable pretty-printing for gdb",
"text": "-enable-pretty-printing",
"ignoreFailures": true
}
"iris"
],
"stopAtEntry": false,
"cwd": "${workspaceRoot}/build/",
"environment": [],
"externalConsole": false,
"MIMode": "gdb",
}
"MIMode": "lldb"
},
]
}

2
sample/CMakeLists.txt
View File

@@ -1,5 +1,3 @@
cmake_minimum_required(VERSION 3.20)
project(main)
set(CMAKE_CXX_STANDARD 11)

70
sample/sample.cpp
View File

@@ -14,39 +14,41 @@ using namespace mdlp;
const string PATH = "../../tests/datasets/";
/* print a description of all supported options */
void usage(const char* path)
{
void usage(const char *path) {
/* take only the last portion of the path */
const char* basename = strrchr(path, '/');
const char *basename = strrchr(path, '/');
basename = basename ? basename + 1 : path;
cout << "usage: " << basename << "[OPTION]" << endl;
cout << " -h, --help\t\t Print this help and exit." << endl;
cout << " -f, --file[=FILENAME]\t {all, glass, iris, kdd_JapaneseVowels, letter, liver-disorders, mfeat-factors, test}." << endl;
cout
<< " -f, --file[=FILENAME]\t {all, glass, iris, kdd_JapaneseVowels, letter, liver-disorders, mfeat-factors, test}."
<< endl;
cout << " -p, --path[=FILENAME]\t folder where the arff dataset is located, default " << PATH << endl;
cout << " -m, --max_depth=INT\t max_depth pased to discretizer. Default = MAX_INT" << endl;
cout << " -c, --max_cutpoints=FLOAT\t percentage of lines expressed in decimal or integer number or cut points. Default = 0 = any" << endl;
cout
<< " -c, --max_cutpoints=FLOAT\t percentage of lines expressed in decimal or integer number or cut points. Default = 0 = any"
<< endl;
cout << " -n, --min_length=INT\t interval min_length pased to discretizer. Default = 3" << endl;
}
tuple<string, string, int, int, float> parse_arguments(int argc, char** argv)
{
tuple<string, string, int, int, float> parse_arguments(int argc, char **argv) {
string file_name;
string path = PATH;
int max_depth = numeric_limits<int>::max();
int min_length = 3;
float max_cutpoints = 0;
static struct option long_options[] = {
{ "help", no_argument, 0, 'h' },
{ "file", required_argument, 0, 'f' },
{ "path", required_argument, 0, 'p' },
{ "max_depth", required_argument, 0, 'm' },
{ "max_cutpoints", required_argument, 0, 'c' },
{ "min_length", required_argument, 0, 'n' },
{ 0, 0, 0, 0 }
{"help", no_argument, nullptr, 'h'},
{"file", required_argument, nullptr, 'f'},
{"path", required_argument, nullptr, 'p'},
{"max_depth", required_argument, nullptr, 'm'},
{"max_cutpoints", required_argument, nullptr, 'c'},
{"min_length", required_argument, nullptr, 'n'},
{nullptr, 0, nullptr, 0}
};
while (1) {
auto c = getopt_long(argc, argv, "hf:p:m:c:n:", long_options, 0);
while (true) {
auto c = getopt_long(argc, argv, "hf:p:m:c:n:", long_options, nullptr);
if (c == -1)
break;
switch (c) {
@@ -57,13 +59,13 @@ tuple<string, string, int, int, float> parse_arguments(int argc, char** argv)
file_name = optarg;
break;
case 'm':
max_depth = atoi(optarg);
max_depth = (int) strtol(optarg, nullptr, 10);
break;
case 'n':
min_length = atoi(optarg);
min_length = (int) strtol(optarg, nullptr, 10);
break;
case 'c':
max_cutpoints = atof(optarg);
max_cutpoints = strtof(optarg, nullptr);
break;
case 'p':
path = optarg;
@@ -84,8 +86,8 @@ tuple<string, string, int, int, float> parse_arguments(int argc, char** argv)
return make_tuple(file_name, path, max_depth, min_length, max_cutpoints);
}
void process_file(string path, string file_name, bool class_last, int max_depth, int min_length, float max_cutpoints)
{
void process_file(const string &path, const string &file_name, bool class_last, int max_depth, int min_length,
float max_cutpoints) {
ArffFiles file;
file.load(path + file_name + ".arff", class_last);
@@ -93,16 +95,16 @@ void process_file(string path, string file_name, bool class_last, int max_depth,
int items = file.getSize();
cout << "Number of lines: " << items << endl;
cout << "Attributes: " << endl;
for (auto attribute : attributes) {
for (auto attribute: attributes) {
cout << "Name: " << get<0>(attribute) << " Type: " << get<1>(attribute) << endl;
}
cout << "Class name: " << file.getClassName() << endl;
cout << "Class type: " << file.getClassType() << endl;
cout << "Data: " << endl;
vector<samples_t>& X = file.getX();
labels_t& y = file.getY();
vector<samples_t> &X = file.getX();
labels_t &y = file.getY();
for (int i = 0; i < 5; i++) {
for (auto feature : X) {
for (auto feature: X) {
cout << fixed << setprecision(1) << feature[i] << " ";
}
cout << y[i] << endl;
@@ -115,7 +117,7 @@ void process_file(string path, string file_name, bool class_last, int max_depth,
cout << "Min: " << *min_max.first << " Max: " << *min_max.second << endl;
cout << "--------------------------" << setprecision(3) << endl;
test.fit(X[i], y);
for (auto item : test.getCutPoints()) {
for (auto item: test.getCutPoints()) {
cout << item << endl;
}
total += test.getCutPoints().size();
@@ -124,17 +126,18 @@ void process_file(string path, string file_name, bool class_last, int max_depth,
cout << "Total feature states: " << total + attributes.size() << endl;
}
void process_all_files(map<string, bool> datasets, string path, int max_depth, int min_length, float max_cutpoints)
{
cout << "Results: " << "Max_depth: " << max_depth << " Min_length: " << min_length << endl << endl;
void process_all_files(const map<string, bool> &datasets, const string &path, int max_depth, int min_length,
float max_cutpoints) {
cout << "Results: " << "Max_depth: " << max_depth << " Min_length: " << min_length << " Max_cutpoints: "
<< max_cutpoints << endl << endl;
printf("%-20s %4s %4s\n", "Dataset", "Feat", "Cuts Time(ms)");
printf("==================== ==== ==== ========\n");
for (auto dataset : datasets) {
for (const auto &dataset: datasets) {
ArffFiles file;
file.load(path + dataset.first + ".arff", dataset.second);
auto attributes = file.getAttributes();
vector<samples_t>& X = file.getX();
labels_t& y = file.getY();
vector<samples_t> &X = file.getX();
labels_t &y = file.getY();
size_t timing = 0;
int cut_points = 0;
for (auto i = 0; i < attributes.size(); i++) {
@@ -150,8 +153,7 @@ void process_all_files(map<string, bool> datasets, string path, int max_depth, i
}
int main(int argc, char** argv)
{
int main(int argc, char **argv) {
map<string, bool> datasets = {
{"glass", true},
{"iris", true},