Fix attribute name extraction in ArffFiles

Add hyperparameters to discretized

Hyperparameters added:

- min_length: int, default=3: The minimum length of an interval to be considered to be discretized.
- max_depth: int, default=1e6: The maximum depth of the discretization process.
- max_cuts: float, default=0: The maximum number of cut points to be computed for each feature. Compute all cutpoints and select the ones that produce less entropy

.github/workflows/codeql.yml

@@ -0,0 +1,82 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: ["main"]
+  schedule:
+    - cron: "16 22 * * 0"
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: ["python"]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
+        # Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+        with:
+          submodules: recursive
+
+      # Initializes the CodeQL tools for scanning.
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v2
+        with:
+          languages: ${{ matrix.language }}
+          # If you wish to specify custom queries, you can do so here or in a config file.
+          # By default, queries listed here will override any specified in a config file.
+          # Prefix the list here with "+" to use these queries and those in the config file.
+
+          # Details on CodeQL's query packs refer to : https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+          # queries: security-extended,security-and-quality
+
+      # Autobuild attempts to build any compiled languages  (C/C++, C#, Go, or Java).
+      # If this step fails, then you should remove it and run the build manually (see below)
+      - if: matrix.language == 'python'
+        name: Autobuild
+        uses: github/codeql-action/autobuild@v2
+
+      - if: matrix.language == 'cpp'
+        name: Build CPP
+        run: |
+          pip install -q --upgrade pip
+          pip install -q scikit-learn cython
+          make install
+      # ℹ️ Command-line programs to run using the OS shell.
+      # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+
+      #   If the Autobuild fails above, remove it and uncomment the following three lines.
+      #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
+
+      # - run: |
+      #   echo "Run, Build Application using script"
+      #   ./location_of_script_within_repo/buildscript.sh
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v2
+        with:
+          category: "/language:${{matrix.language}}"

.github/workflows/main.yml

@@ -2,9 +2,9 @@ name: CI
 
 on:
   push:
-    branches: [master]
+    branches: [main]
   pull_request:
-    branches: [master]
+    branches: [main]
   workflow_dispatch:
 
 jobs:
@@ -12,22 +12,24 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [macos-latest, ubuntu-latest, windows-latest]
-        python: [3.9, "3.10"]
+        os: [ubuntu-latest]
+        python: ["3.10"]
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
+        with:
+          submodules: recursive
       - name: Set up Python ${{ matrix.python }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python }}
       - name: Install dependencies
         run: |
           pip install -q --upgrade pip
-          pip install -q --upgrade codecov coverage black flake8 codacy-coverage
+          pip install -q scikit-learn cython
+          pip install -q coverage black flake8 codacy-coverage
       - name: Build and install
         run: |
-          cd FImdlp
           make install
       - name: Lint
         run: |
@@ -35,10 +37,10 @@ jobs:
           flake8 --count --per-file-ignores="__init__.py:F401" src
       - name: Tests
         run: |
-          coverage run -m unittest discover -v - s src
+          coverage run -m unittest discover -v -s src
           coverage xml
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v1
+        uses: codecov/codecov-action@v3
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           files: ./coverage.xml

.gitignore

@@ -33,8 +33,8 @@ MANIFEST
 *.manifest
 *.spec
 
-# Installer log2s
-pip-log2.txt
+# Installer logs
+pip-log.txt
 pip-delete-this-directory.txt
 
 # Unit test / coverage reports
@@ -56,7 +56,7 @@ coverage.xml
 *.pot
 
 # Django stuff:
-*.log2
+*.log
 local_settings.py
 db.sqlite3
 db.sqlite3-journal
@@ -134,4 +134,6 @@ cmake-build-debug
 cmake-build-debug/**
 **/lcoverage/**
 **/x/*
-**/*.so
+**/*.so
+**/CMakeFiles
+wheelhouse

.gitmodules

@@ -1,3 +1,3 @@
-[submodule "fimdlp/cppmdlp"]
-	path = src/cppfimdlp
-	url = https://github.com/rmontanana/mdlp
+[submodule "src/cppmdlp"]
+	path = src/cppmdlp
+	url = https://github.com/rmontanana/mdlp.git

MANIFEST.in

@@ -0,0 +1,5 @@
+include src/cppmdlp/CPPFImdlp.h
+include src/cppmdlp/typesFImdlp.h
+include src/cppmdlp/Metrics.h
+include src/fimdlp/Factorize.h
+include src/fimdlp/ArffFiles.h

Makefile

@@ -15,6 +15,10 @@ coverage:
 	make test
 	coverage report -m
 
+submodule:
+	git submodule update --remote src/cppmdlp
+	git submodule update --merge
+
 lint:  ## Lint and static-check
 	black src
 	flake8 --per-file-ignores="__init__.py:F401" src
@@ -33,6 +37,12 @@ install:  ## Build extension
 audit: ## Audit pip
 	pip-audit
 
+version:
+	@echo "Current Python version .: $(shell python --version)"
+	@echo "Current FImdlp version .: $(shell python -c "from fimdlp import _version; print(_version.__version__)")"
+	@echo "Current mdlp version ...: $(shell python -c "from fimdlp.cppfimdlp import CFImdlp; print(CFImdlp().get_version().decode())")"
+	@echo "Installed FImdlp version: $(shell pip show fimdlp | grep Version | cut -d' ' -f2)"
+
 help: ## Show help message
 	@IFS=$$'\n' ; \
 	help_lines=(`fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/##/:/'`); \

README.md

@@ -1,11 +1,21 @@
 # FImdlp
-
+[![CI](https://github.com/Doctorado-ML/FImdlp/actions/workflows/main.yml/badge.svg)](https://github.com/Doctorado-ML/FImdlp/actions/workflows/main.yml)
+[![CodeQL](https://github.com/Doctorado-ML/FImdlp/actions/workflows/codeql.yml/badge.svg)](https://github.com/Doctorado-ML/FImdlp/actions/workflows/codeql.yml)
 [![Codacy Badge](https://app.codacy.com/project/badge/Grade/8b4d784fee13401588aa8c06532a2f6d)](https://www.codacy.com/gh/Doctorado-ML/FImdlp/dashboard?utm_source=github.com&utm_medium=referral&utm_content=Doctorado-ML/FImdlp&utm_campaign=Badge_Grade)
+[![codecov](https://codecov.io/gh/Doctorado-ML/FImdlp/branch/main/graph/badge.svg?token=W8I45B5Z3J)](https://codecov.io/gh/Doctorado-ML/FImdlp)
+[![pypy](https://img.shields.io/pypi/v/FImdlp?color=g)](https://pypi.org/project/FImdlp)
+![https://img.shields.io/badge/python-3.9%2B-blue](https://img.shields.io/badge/python-3.9%2B-brightgreen)
 
 Discretization algorithm based on the paper by Usama M. Fayyad and Keki B. Irani 
 
-```
+
 Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning. In Proceedings of the 13th International Joint Conference on Artificial Intelligence (IJCAI-95), pages 1022-1027, Montreal, Canada, August 1995.
+
+
+## Installation
+
+```bash
+git clone --recurse-submodules https://github.com/doctorado-ml/FImdlp.git
 ```
 
 ## Build and usage sample
@@ -14,8 +24,8 @@ Multi-Interval Discretization of Continuous-Valued Attributes for Classification
 
 ```bash
 pip install -e .
-python samples/sample.py iris --original 
-python samples/sample.py iris --proposal
+python samples/sample.py iris  
+python samples/sample.py iris -c 2
 python samples/sample.py -h # for more options
 ```
 
@@ -23,9 +33,12 @@ python samples/sample.py -h # for more options
 
 ```bash
 cd samples
-mkdir build
+cmake -B build
 cd build
-cmake ..
 make
-./sample iris
+./sample -f iris -c 2
+./sample -h
 ```
+
+### Based on
+[https://github.com/rmontanana/mdlp](https://github.com/rmontanana/mdlp)

feature0.txt

@@ -1,152 +0,0 @@
-+++++++++++++++++++++++
-(  0,  13) -> (4.3, 0)
-(  1,   8) -> (4.4, 0)
-(  2,  38) -> (4.4, 0)
-(  3,  42) -> (4.4, 0)
-(  4,  41) -> (4.5, 0)
-(  5,   3) -> (4.6, 0)
-(  6,   6) -> (4.6, 0)
-(  7,  22) -> (4.6, 0)
-(  8,  47) -> (4.6, 0)
-(  9,   2) -> (4.7, 0)
-( 10,  29) -> (4.7, 0)
-( 11,  11) -> (4.8, 0)
-( 12,  12) -> (4.8, 0)
-( 13,  24) -> (4.8, 0)
-( 14,  30) -> (4.8, 0)
-( 15,  45) -> (4.8, 0)
-( 16,   1) -> (4.9, 0)
-( 17,   9) -> (4.9, 0)
-( 18,  34) -> (4.9, 0)
-( 19,  37) -> (4.9, 0)
-( 20,  57) -> (4.9, 1)
-( 21, 106) -> (4.9, 2)
-( 22,   4) -> (5.0, 0)
-( 23,   7) -> (5.0, 0)
-( 24,  25) -> (5.0, 0)
-( 25,  26) -> (5.0, 0)
-( 26,  35) -> (5.0, 0)
-( 27,  40) -> (5.0, 0)
-( 28,  43) -> (5.0, 0)
-( 29,  49) -> (5.0, 0)
-( 30,  60) -> (5.0, 1)
-( 31,  93) -> (5.0, 1)
-( 32,   0) -> (5.1, 0)
-( 33,  17) -> (5.1, 0)
-( 34,  19) -> (5.1, 0)
-( 35,  21) -> (5.1, 0)
-( 36,  23) -> (5.1, 0)
-( 37,  39) -> (5.1, 0)
-( 38,  44) -> (5.1, 0)
-( 39,  46) -> (5.1, 0)
-( 40,  98) -> (5.1, 1)
-( 41,  27) -> (5.2, 0)
-( 42,  28) -> (5.2, 0)
-( 43,  32) -> (5.2, 0)
-( 44,  59) -> (5.2, 1)
-( 45,  48) -> (5.3, 0)
-( 46,   5) -> (5.4, 0)
-( 47,  10) -> (5.4, 0)
-( 48,  16) -> (5.4, 0)
-( 49,  20) -> (5.4, 0)
-( 50,  31) -> (5.4, 0)
-( 51,  84) -> (5.4, 1)
-( 52,  33) -> (5.5, 0)
-( 53,  36) -> (5.5, 0)
-( 54,  53) -> (5.5, 1)
-( 55,  80) -> (5.5, 1)
-( 56,  81) -> (5.5, 1)
-( 57,  89) -> (5.5, 1)
-( 58,  90) -> (5.5, 1)
-( 59,  64) -> (5.6, 1)
-( 60,  66) -> (5.6, 1)
-( 61,  69) -> (5.6, 1)
-( 62,  88) -> (5.6, 1)
-( 63,  94) -> (5.6, 1)
-( 64, 121) -> (5.6, 2)
-( 65,  15) -> (5.7, 0)
-( 66,  18) -> (5.7, 0)
-( 67,  55) -> (5.7, 1)
-( 68,  79) -> (5.7, 1)
-( 69,  95) -> (5.7, 1)
-( 70,  96) -> (5.7, 1)
-( 71,  99) -> (5.7, 1)
-( 72, 113) -> (5.7, 2)
-( 73,  14) -> (5.8, 0)
-( 74,  67) -> (5.8, 1)
-( 75,  82) -> (5.8, 1)
-( 76,  92) -> (5.8, 1)
-( 77, 101) -> (5.8, 2)
-( 78, 114) -> (5.8, 2)
-( 79, 142) -> (5.8, 2)
-( 80,  61) -> (5.9, 1)
-( 81,  70) -> (5.9, 1)
-( 82, 149) -> (5.9, 2)
-( 83,  62) -> (6.0, 1)
-( 84,  78) -> (6.0, 1)
-( 85,  83) -> (6.0, 1)
-( 86,  85) -> (6.0, 1)
-( 87, 119) -> (6.0, 2)
-( 88, 138) -> (6.0, 2)
-( 89,  63) -> (6.1, 1)
-( 90,  71) -> (6.1, 1)
-( 91,  73) -> (6.1, 1)
-( 92,  91) -> (6.1, 1)
-( 93, 127) -> (6.1, 2)
-( 94, 134) -> (6.1, 2)
-( 95,  68) -> (6.2, 1)
-( 96,  97) -> (6.2, 1)
-( 97, 126) -> (6.2, 2)
-( 98, 148) -> (6.2, 2)
-( 99,  56) -> (6.3, 1)
-(100,  72) -> (6.3, 1)
-(101,  87) -> (6.3, 1)
-(102, 100) -> (6.3, 2)
-(103, 103) -> (6.3, 2)
-(104, 123) -> (6.3, 2)
-(105, 133) -> (6.3, 2)
-(106, 136) -> (6.3, 2)
-(107, 146) -> (6.3, 2)
-(108,  51) -> (6.4, 1)
-(109,  74) -> (6.4, 1)
-(110, 111) -> (6.4, 2)
-(111, 115) -> (6.4, 2)
-(112, 128) -> (6.4, 2)
-(113, 132) -> (6.4, 2)
-(114, 137) -> (6.4, 2)
-(115,  54) -> (6.5, 1)
-(116, 104) -> (6.5, 2)
-(117, 110) -> (6.5, 2)
-(118, 116) -> (6.5, 2)
-(119, 147) -> (6.5, 2)
-(120,  58) -> (6.6, 1)
-(121,  75) -> (6.6, 1)
-(122,  65) -> (6.7, 1)
-(123,  77) -> (6.7, 1)
-(124,  86) -> (6.7, 1)
-(125, 108) -> (6.7, 2)
-(126, 124) -> (6.7, 2)
-(127, 140) -> (6.7, 2)
-(128, 144) -> (6.7, 2)
-(129, 145) -> (6.7, 2)
-(130,  76) -> (6.8, 1)
-(131, 112) -> (6.8, 2)
-(132, 143) -> (6.8, 2)
-(133,  52) -> (6.9, 1)
-(134, 120) -> (6.9, 2)
-(135, 139) -> (6.9, 2)
-(136, 141) -> (6.9, 2)
-(137,  50) -> (7.0, 1)
-(138, 102) -> (7.1, 2)
-(139, 109) -> (7.2, 2)
-(140, 125) -> (7.2, 2)
-(141, 129) -> (7.2, 2)
-(142, 107) -> (7.3, 2)
-(143, 130) -> (7.4, 2)
-(144, 105) -> (7.6, 2)
-(145, 117) -> (7.7, 2)
-(146, 118) -> (7.7, 2)
-(147, 122) -> (7.7, 2)
-(148, 135) -> (7.7, 2)
-(149, 131) -> (7.9, 2)
-+++++++++++++++++++++++

pyproject.toml

@@ -18,10 +18,10 @@ authors = [
     { name = "Ricardo Montañana", email = "ricardo.montanana@alu.uclm.es" },
 ]
 dynamic = ['version']
-dependencies = ["numpy", "joblib"]
+dependencies = ["numpy", "joblib", "scikit-learn"]
 requires-python = ">=3.9"
 classifiers = [
-    "Development Status :: 3 - Alpha",
+    "Development Status :: 4 - Beta",
     "Intended Audience :: Science/Research",
     "Intended Audience :: Developers",
     "Topic :: Software Development",
@@ -33,14 +33,16 @@ classifiers = [
     "Programming Language :: Python",
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
 ]
 
 [project.urls]
 Home = "https://github.com/doctorado-ml/FImdlp"
+Base = "https://github.com/rmontanana/mdlp"
 
 [tool.black]
 line-length = 79
-target_version = ['py39', 'py310']
+target_version = ['py39', 'py310', 'py311']
 include = '\.pyi?$'
 exclude = '''
 /(

samples/ArffFiles.cpp

@@ -1,117 +0,0 @@
-#include "ArffFiles.h"
-
-#include <fstream>
-#include <sstream>
-#include <map>
-#include <iostream>
-
-using namespace std;
-
-ArffFiles::ArffFiles()
-{
-}
-vector<string> ArffFiles::getLines()
-{
-    return lines;
-}
-unsigned long int ArffFiles::getSize()
-{
-    return lines.size();
-}
-vector<tuple<string, string>> ArffFiles::getAttributes()
-{
-    return attributes;
-}
-string ArffFiles::getClassName()
-{
-    return className;
-}
-string ArffFiles::getClassType()
-{
-    return classType;
-}
-vector<vector<float>>& ArffFiles::getX()
-{
-    return X;
-}
-vector<int>& ArffFiles::getY()
-{
-    return y;
-}
-void ArffFiles::load(string fileName, bool classLast)
-{
-    ifstream file(fileName);
-    string keyword, attribute, type;
-    if (file.is_open()) {
-        string line;
-        while (getline(file, line)) {
-            if (line[0] == '%' || line.empty() || line == "\r" || line == " ") {
-                continue;
-            }
-            if (line.find("@attribute") != string::npos || line.find("@ATTRIBUTE") != string::npos) {
-                stringstream ss(line);
-                ss >> keyword >> attribute >> type;
-                attributes.push_back(make_tuple(attribute, type));
-                continue;
-            }
-            if (line[0] == '@') {
-                continue;
-            }
-            lines.push_back(line);
-        }
-        file.close();
-        if (attributes.empty())
-            throw invalid_argument("No attributes found");
-        if (classLast) {
-            className = get<0>(attributes.back());
-            classType = get<1>(attributes.back());
-            attributes.pop_back();
-        } else {
-            className = get<0>(attributes.front());
-            classType = get<1>(attributes.front());
-            attributes.erase(attributes.begin());
-        }
-        generateDataset(classLast);
-    } else
-        throw invalid_argument("Unable to open file");
-}
-void ArffFiles::generateDataset(bool classLast)
-{
-    X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
-    vector<string> yy = vector<string>(lines.size(), "");
-    int labelIndex = classLast ? attributes.size() : 0;
-    for (int i = 0; i < lines.size(); i++) {
-        stringstream ss(lines[i]);
-        string value;
-        int pos = 0, xIndex = 0;
-        while (getline(ss, value, ',')) {
-            if (pos++ == labelIndex) {
-                yy[i] = value;
-            } else {
-                X[xIndex++][i] = stof(value);
-            }
-        }
-    }
-    y = factorize(yy);
-}
-string ArffFiles::trim(const string& source)
-{
-    string s(source);
-    s.erase(0, s.find_first_not_of(" \n\r\t"));
-    s.erase(s.find_last_not_of(" \n\r\t") + 1);
-    return s;
-}
-vector<int> ArffFiles::factorize(const vector<string>& labels_t)
-{
-    vector<int> yy;
-    yy.reserve(labels_t.size());
-    map<string, int> labelMap;
-    int i = 0;
-    for (string label : labels_t) {
-        if (labelMap.find(label) == labelMap.end()) {
-            labelMap[label] = i++;
-        }
-        yy.push_back(labelMap[label]);
-    }
-    return yy;
-}

samples/ArffFiles.h

@@ -1,28 +0,0 @@
-#ifndef ARFFFILES_H
-#define ARFFFILES_H
-#include <string>
-#include <vector>
-#include <tuple>
-using namespace std;
-class ArffFiles {
-private:
-    vector<string> lines;
-    vector<tuple<string, string>> attributes;
-    string className, classType;
-    vector<vector<float>> X;
-    vector<int> y;
-    void generateDataset(bool);
-public:
-    ArffFiles();
-    void load(string, bool = true);
-    vector<string> getLines();
-    unsigned long int getSize();
-    string getClassName();
-    string getClassType();
-    string trim(const string&);
-    vector<vector<float>>& getX();
-    vector<int>& getY();
-    vector<tuple<string, string>> getAttributes();
-    vector<int> factorize(const vector<string>& labels_t);
-};
-#endif

samples/CMakeLists.txt

@@ -1,6 +1,7 @@
 cmake_minimum_required(VERSION 3.20)
-project(main)
+project(sample)
 
-set(CMAKE_CXX_STANDARD 14)
+set(CMAKE_CXX_STANDARD 11)
+set(CMAKE_BUILD_TYPE Debug)
 
-add_executable(sample sample.cpp ArffFiles.cpp ../src/fimdlp/cppmdlp/Metrics.cpp ../src/fimdlp/cppmdlp/CPPFImdlp.cpp)
+add_executable(sample sample.cpp ../src/cppmdlp/tests/ArffFiles.cpp ../src/cppmdlp/Metrics.cpp ../src/cppmdlp/CPPFImdlp.cpp)

samples/sample.cpp

@@ -1,30 +1,101 @@
-#include "ArffFiles.h"
 #include <iostream>
 #include <vector>
 #include <iomanip>
+#include <chrono>
+#include <algorithm>
+#include <cstring>
+#include <getopt.h>
 #include "../src/cppmdlp/CPPFImdlp.h"
+#include "../src/cppmdlp/tests/ArffFiles.h"
 
 using namespace std;
+using namespace mdlp;
 
-int main(int argc, char** argv)
+const string PATH = "../../src/cppmdlp/tests/datasets/";
+
+/* print a description of all supported options */
+void usage(const char* path)
+{
+    /* take only the last portion of the 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 << "  -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 << "  -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)
+{
+    string file_name;
+    string path = PATH;
+    int max_depth = numeric_limits<int>::max();
+    int min_length = 3;
+    float max_cutpoints = 0;
+    const vector<struct option> long_options = {
+            {"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,         no_argument,       nullptr, 0}
+    };
+    while (true) {
+        const auto c = getopt_long(argc, argv, "hf:p:m:c:n:", long_options.data(), nullptr);
+        if (c == -1)
+            break;
+        switch (c) {
+            case 'h':
+                usage(argv[0]);
+                exit(0);
+            case 'f':
+                file_name = string(optarg);
+                break;
+            case 'm':
+                max_depth = stoi(optarg);
+                break;
+            case 'n':
+                min_length = stoi(optarg);
+                break;
+            case 'c':
+                max_cutpoints = stof(optarg);
+                break;
+            case 'p':
+                path = optarg;
+                if (path.back() != '/')
+                    path += '/';
+                break;
+            case '?':
+                usage(argv[0]);
+                exit(1);
+            default:
+                abort();
+        }
+    }
+    if (file_name.empty()) {
+        usage(argv[0]);
+        exit(1);
+    }
+    return make_tuple(file_name, path, max_depth, min_length, 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;
-    vector<string> lines;
-    string path = "../../src/cppmdlp/tests/datasets/";
-    map<string, bool > datasets = {
-        {"mfeat-factors", true},
-        {"iris", true},
-        {"letter", true},
-        {"kdd_JapaneseVowels", false}
-    };
-    if (argc != 2 || datasets.find(argv[1]) == datasets.end()) {
-        cout << "Usage: " << argv[0] << " {mfeat-factors, iris, letter, kdd_JapaneseVowels}" << endl;
-        return 1;
-    }
 
-    file.load(path + argv[1] + ".arff", datasets[argv[1]]);
-    auto attributes = file.getAttributes();
-    int items = file.getSize();
+    file.load(path + file_name + ".arff", class_last);
+    const auto attributes = file.getAttributes();
+    const auto items = file.getSize();
     cout << "Number of lines: " << items << endl;
     cout << "Attributes: " << endl;
     for (auto attribute : attributes) {
@@ -33,22 +104,93 @@ int main(int argc, char** argv)
     cout << "Class name: " << file.getClassName() << endl;
     cout << "Class type: " << file.getClassType() << endl;
     cout << "Data: " << endl;
-    vector<vector<float>>& X = file.getX();
-    vector<int>& y = file.getY();
-    for (int i = 0; i < 50; i++) {
+    vector<samples_t>& X = file.getX();
+    labels_t& y = file.getY();
+    for (int i = 0; i < 5; i++) {
         for (auto feature : X) {
             cout << fixed << setprecision(1) << feature[i] << " ";
         }
         cout << y[i] << endl;
     }
-    mdlp::CPPFImdlp test = mdlp::CPPFImdlp(false);
+    auto test = mdlp::CPPFImdlp(min_length, max_depth, max_cutpoints);
+    size_t total = 0;
     for (auto i = 0; i < attributes.size(); i++) {
-        cout << "Cut points for " << get<0>(attributes[i]) << endl;
-        cout << "--------------------------" << setprecision(3) << endl;
+        auto min_max = minmax_element(X[i].begin(), X[i].end());
+        cout << "Cut points for feature " << get<0>(attributes[i]) << ": [" << setprecision(3);
         test.fit(X[i], y);
-        for (auto item : test.getCutPoints()) {
-            cout << item << endl;
+        auto cut_points = test.getCutPoints();
+        for (auto item : cut_points) {
+            cout << item;
+            if (item != cut_points.back())
+                cout << ", ";
         }
+        total += test.getCutPoints().size();
+        cout << "]" << endl;
+        cout << "Min: " << *min_max.first << " Max: " << *min_max.second << endl;
+        cout << "--------------------------" << endl;
+    }
+    cout << "Total cut points ...: " << total << endl;
+    cout << "Total feature states: " << total + attributes.size() << 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 (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();
+        size_t timing = 0;
+        size_t cut_points = 0;
+        for (auto i = 0; i < attributes.size(); i++) {
+            auto test = mdlp::CPPFImdlp(min_length, max_depth, max_cutpoints);
+            std::chrono::steady_clock::time_point begin = std::chrono::steady_clock::now();
+            test.fit(X[i], y);
+            std::chrono::steady_clock::time_point end = std::chrono::steady_clock::now();
+            timing += std::chrono::duration_cast<std::chrono::milliseconds>(end - begin).count();
+            cut_points += test.getCutPoints().size();
+        }
+        printf("%-20s %4lu %4zu %8zu\n", dataset.first.c_str(), attributes.size(), cut_points, timing);
+    }
+}
+
+
+int main(int argc, char** argv)
+{
+    map<string, bool> datasets = {
+            {"glass",              true},
+            {"iris",               true},
+            {"kdd_JapaneseVowels", false},
+            {"letter",             true},
+            {"liver-disorders",    true},
+            {"mfeat-factors",      true},
+            {"test",               true}
+    };
+    string file_name;
+    string path;
+    int max_depth;
+    int min_length;
+    float max_cutpoints;
+    tie(file_name, path, max_depth, min_length, max_cutpoints) = parse_arguments(argc, argv);
+    if (datasets.find(file_name) == datasets.end() && file_name != "all") {
+        cout << "Invalid file name: " << file_name << endl;
+        usage(argv[0]);
+        exit(1);
+    }
+    if (file_name == "all")
+        process_all_files(datasets, path, max_depth, min_length, max_cutpoints);
+    else {
+        process_file(path, file_name, datasets[file_name], max_depth, min_length, max_cutpoints);
+        cout << "File name ....: " << file_name << endl;
+        cout << "Max depth ....: " << max_depth << endl;
+        cout << "Min length ...: " << min_length << endl;
+        cout << "Max cutpoints : " << max_cutpoints << endl;
     }
     return 0;
-}
+}

samples/sample.py

@@ -1,43 +1,72 @@
 import time
 import argparse
 import os
-from scipy.io import arff
 import pandas as pd
 from sklearn.ensemble import RandomForestClassifier
 from fimdlp.mdlp import FImdlp
+from fimdlp.cppfimdlp import CArffFiles
 
 datasets = {
     "mfeat-factors": True,
     "iris": True,
+    "glass": True,
+    "liver-disorders": True,
     "letter": True,
     "kdd_JapaneseVowels": False,
 }
 
 ap = argparse.ArgumentParser()
-ap.add_argument("--proposal", action="store_true")
-ap.add_argument("--original", dest="proposal", action="store_false")
+ap.add_argument(
+    "-n",
+    "--min_length",
+    type=int,
+    default=3,
+    help="Minimum length of interval",
+)
+ap.add_argument(
+    "-m", "--max_depth", type=int, default=9999, help="Maximum depth"
+)
+ap.add_argument(
+    "-c",
+    "--max_cuts",
+    type=float,
+    default=0,
+    help="Maximum number of cut points",
+)
 ap.add_argument("dataset", type=str, choices=datasets.keys())
 args = ap.parse_args()
 relative = "" if os.path.isdir("src") else ".."
 file_name = os.path.join(
     relative, "src", "cppmdlp", "tests", "datasets", args.dataset
 )
-data = arff.loadarff(file_name + ".arff")
-df = pd.DataFrame(data[0])
-class_column = -1 if datasets[args.dataset] else 0
-class_name = df.columns.to_list()[class_column]
-X = df.drop(class_name, axis=1)
-y, _ = pd.factorize(df[class_name])
-X = X.to_numpy()
-test = FImdlp(proposal=args.proposal)
+arff = CArffFiles()
+arff.load(bytes(f"{file_name}.arff", "utf-8"))
+X = arff.get_X()
+y = arff.get_y()
+attributes = arff.get_attributes()
+attributes = [x[0].decode() for x in attributes]
+df = pd.DataFrame(X, columns=attributes)
+class_name = arff.get_class_name().decode()
+df[class_name] = y
+test = FImdlp(
+    min_length=args.min_length,
+    max_depth=args.max_depth,
+    max_cuts=args.max_cuts,
+)
 now = time.time()
 test.fit(X, y)
 fit_time = time.time()
-print("Fitting: ", fit_time - now)
+print(f"Fitting ....: {fit_time - now:7.5f} seconds")
 now = time.time()
 Xt = test.transform(X)
-print("Transforming: ", time.time() - now)
-print(test.get_cut_points())
+print(f"Transforming: {time.time() - now:7.5f} seconds")
+cut_points = test.get_cut_points()
+for i, cuts in enumerate(cut_points):
+    print(f"Cut points for feature {attributes[i]}: {cuts}")
+    print(f"Min: {min(X[:, i]):6.4f} Max: {max(X[:, i]):6.4f}")
+num_cuts = sum([len(x) for x in cut_points])
+print(f"Total cut points ...: {num_cuts}")
+print(f"Total feature states: {num_cuts + len(attributes)}")
 clf = RandomForestClassifier(random_state=0)
 print(
     "Random Forest score with discretized data: ", clf.fit(Xt, y).score(Xt, y)

setup.py

@@ -14,10 +14,14 @@ setup(
                 "src/fimdlp/cfimdlp.pyx",
                 "src/cppmdlp/CPPFImdlp.cpp",
                 "src/cppmdlp/Metrics.cpp",
+                "src/fimdlp/Factorize.cpp",
+                "src/fimdlp/ArffFiles.cpp",
             ],
             language="c++",
             include_dirs=["fimdlp"],
-            extra_compile_args=["-std=c++2a"],
+            extra_compile_args=[
+                "-std=c++11",
+            ],
         ),
     ]
 )

src/cppmdlp/.gitignore

@@ -1,36 +0,0 @@
-# Prerequisites
-*.d
-
-# Compiled Object files
-*.slo
-*.lo
-*.o
-*.obj
-
-# Precompiled Headers
-*.gch
-*.pch
-
-# Compiled Dynamic libraries
-*.so
-*.dylib
-*.dll
-
-# Fortran module files
-*.mod
-*.smod
-
-# Compiled Static libraries
-*.lai
-*.la
-*.a
-*.lib
-
-# Executables
-*.exe
-*.out
-*.app
-**/build
-**/lcoverage
-.idea
-cmake-*

src/cppmdlp/CMakeLists.txt

@@ -1,7 +0,0 @@
-cmake_minimum_required(VERSION 3.24)
-project(mdlp)
-
-set(CMAKE_CXX_STANDARD 17)
-
-add_library(mdlp CPPFImdlp.cpp Metrics.cpp)
-

src/cppmdlp/CPPFImdlp.cpp

@@ -1,160 +0,0 @@
-#include <numeric>
-#include <algorithm>
-#include <set>
-#include <cmath>
-#include "CPPFImdlp.h"
-#include "Metrics.h"
-
-namespace mdlp {
-    CPPFImdlp::CPPFImdlp(bool proposal):proposal(proposal), indices(indices_t()), X(samples_t()), y(labels_t()), metrics(Metrics(y, indices))
-    {
-    }
-    CPPFImdlp::~CPPFImdlp()
-        = default;
-
-    CPPFImdlp& CPPFImdlp::fit(samples_t& X_, labels_t& y_)
-    {
-        X = X_;
-        y = y_;
-        cutPoints.clear();
-        if (X.size() != y.size()) {
-            throw invalid_argument("X and y must have the same size");
-        }
-        if (X.size() == 0 || y.size() == 0) {
-            throw invalid_argument("X and y must have at least one element");
-        }
-        indices = sortIndices(X_);
-        metrics.setData(y, indices);
-        if (proposal)
-            computeCutPointsProposal();
-        else
-            computeCutPoints(0, X.size());
-        return *this;
-    }
-    void CPPFImdlp::computeCutPoints(size_t start, size_t end)
-    {
-        int cut;
-        if (end - start < 2)
-            return;
-        cut = getCandidate(start, end);
-        if (cut == -1 || !mdlp(start, cut, end)) {
-            // cut.value == -1 means that there is no candidate in the interval
-            // No boundary found, so we add both ends of the interval as cutpoints
-            // because they were selected by the algorithm before
-            if (start != 0)
-                cutPoints.push_back((X[indices[start]] + X[indices[start - 1]]) / 2);
-            if (end != X.size())
-                cutPoints.push_back((X[indices[end]] + X[indices[end - 1]]) / 2);
-            return;
-        }
-        computeCutPoints(start, cut);
-        computeCutPoints(cut, end);
-    }
-    void CPPFImdlp::computeCutPointsOriginal(size_t start, size_t end)
-    {
-        precision_t cut;
-        if (end - start < 2)
-            return;
-        cut = getCandidate(start, end);
-        if (cut == -1)
-            return;
-        if (mdlp(start, cut, end)) {
-            cutPoints.push_back((X[indices[cut]] + X[indices[cut - 1]]) / 2);
-        }
-        computeCutPointsOriginal(start, cut);
-        computeCutPointsOriginal(cut, end);
-    }
-    void CPPFImdlp::computeCutPointsProposal()
-    {
-        precision_t xPrev, xCur, xPivot, cutPoint;
-        int yPrev, yCur, yPivot;
-        size_t idx, numElements, start;
-
-        xCur = xPrev = X[indices[0]];
-        yCur = yPrev = y[indices[0]];
-        numElements = indices.size() - 1;
-        idx = start = 0;
-        while (idx < numElements) {
-            xPivot = xCur;
-            yPivot = yCur;
-            // Read the same values and check class changes
-            do {
-                idx++;
-                xCur = X[indices[idx]];
-                yCur = y[indices[idx]];
-                if (yCur != yPivot && xCur == xPivot) {
-                    yPivot = -1;
-                }
-            }
-            while (idx < numElements && xCur == xPivot);
-            // Check if the class changed and there are more than 1 element
-            if ((idx - start > 1) && (yPivot == -1 || yPrev != yCur) && mdlp(start, idx, indices.size())) {
-                start = idx;
-                cutPoint = (xPrev + xCur) / 2;
-                cutPoints.push_back(cutPoint);
-            }
-            yPrev = yPivot;
-            xPrev = xPivot;
-        }
-    }
-    long int CPPFImdlp::getCandidate(size_t start, size_t end)
-    {
-        long int candidate = -1, elements = end - start;
-        precision_t entropy_left, entropy_right, minEntropy = numeric_limits<precision_t>::max();
-        for (auto idx = start + 1; idx < end; idx++) {
-            // Cutpoints are always on boudndaries
-            if (y[indices[idx]] == y[indices[idx - 1]])
-                continue;
-            entropy_left = precision_t(idx - start) / elements * metrics.entropy(start, idx);
-            entropy_right = precision_t(end - idx) / elements * metrics.entropy(idx, end);
-            if (entropy_left + entropy_right < minEntropy) {
-                minEntropy = entropy_left + entropy_right;
-                candidate = idx;
-            }
-        }
-        return candidate;
-    }
-    bool CPPFImdlp::mdlp(size_t start, size_t cut, size_t end)
-    {
-        int k, k1, k2;
-        precision_t ig, delta;
-        precision_t ent, ent1, ent2;
-        auto N = precision_t(end - start);
-        if (N < 2) {
-            return false;
-        }
-        k = metrics.computeNumClasses(start, end);
-        k1 = metrics.computeNumClasses(start, cut);
-        k2 = metrics.computeNumClasses(cut, end);
-        ent = metrics.entropy(start, end);
-        ent1 = metrics.entropy(start, cut);
-        ent2 = metrics.entropy(cut, end);
-        ig = metrics.informationGain(start, cut, end);
-        delta = log2(pow(3, precision_t(k)) - 2) -
-            (precision_t(k) * ent - precision_t(k1) * ent1 - precision_t(k2) * ent2);
-        precision_t term = 1 / N * (log2(N - 1) + delta);
-        return ig > term;
-    }
-    cutPoints_t CPPFImdlp::getCutPoints()
-    {
-        // Remove duplicates and sort
-        cutPoints_t output(cutPoints.size());
-        set<precision_t> s;
-        unsigned size = cutPoints.size();
-        for (unsigned i = 0; i < size; i++)
-            s.insert(cutPoints[i]);
-        output.assign(s.begin(), s.end());
-        sort(output.begin(), output.end());
-        return output;
-    }
-    // Argsort from https://stackoverflow.com/questions/1577475/c-sorting-and-keeping-track-of-indexes
-    indices_t CPPFImdlp::sortIndices(samples_t& X_)
-    {
-        indices_t idx(X_.size());
-        iota(idx.begin(), idx.end(), 0);
-        for (size_t i = 0; i < X_.size(); i++)
-            sort(idx.begin(), idx.end(), [&X_](size_t i1, size_t i2)
-                { return X_[i1] < X_[i2]; });
-        return idx;
-    }
-}

src/cppmdlp/CPPFImdlp.h

@@ -1,33 +0,0 @@
-#ifndef CPPFIMDLP_H
-#define CPPFIMDLP_H
-#include "typesFImdlp.h"
-#include "Metrics.h"
-#include <utility>
-namespace mdlp {
-    class CPPFImdlp {
-    protected:
-        bool proposal;
-        indices_t indices; // sorted indices to use with X and y
-        samples_t X;
-        labels_t y;
-        Metrics metrics;
-        cutPoints_t cutPoints;
-
-        static indices_t sortIndices(samples_t&);
-        void computeCutPoints(size_t, size_t);
-        long int getCandidate(size_t, size_t);
-        bool mdlp(size_t, size_t, size_t);
-
-        // Original algorithm
-        void computeCutPointsOriginal(size_t, size_t);
-        bool goodCut(size_t, size_t, size_t);
-        void computeCutPointsProposal();
-
-    public:
-        CPPFImdlp(bool);
-        ~CPPFImdlp();
-        CPPFImdlp& fit(samples_t&, labels_t&);
-        samples_t getCutPoints();
-    };
-}
-#endif

src/cppmdlp/LICENSE

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2022 Ricardo Montañana Gómez
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.

src/cppmdlp/Metrics.cpp

@@ -1,65 +0,0 @@
-#include "Metrics.h"
-#include <set>
-#include <cmath>
-using namespace std;
-namespace mdlp {
-    Metrics::Metrics(labels_t& y_, indices_t& indices_): y(y_), indices(indices_), numClasses(computeNumClasses(0, indices.size())), entropyCache(cacheEnt_t()), igCache(cacheIg_t())
-    {
-    }
-    int Metrics::computeNumClasses(size_t start, size_t end)
-    {
-        set<int> nClasses;
-        for (auto i = start; i < end; ++i) {
-            nClasses.insert(y[indices[i]]);
-        }
-        return nClasses.size();
-    }
-    void Metrics::setData(labels_t& y_, indices_t& indices_)
-    {
-        indices = indices_;
-        y = y_;
-        numClasses = computeNumClasses(0, indices.size());
-        entropyCache.clear();
-        igCache.clear();
-    }
-    precision_t Metrics::entropy(size_t start, size_t end)
-    {
-        precision_t p, ventropy = 0;
-        int nElements = 0;
-        labels_t counts(numClasses + 1, 0);
-        if (end - start < 2)
-            return 0;
-        if (entropyCache.find(make_tuple(start, end)) != entropyCache.end()) {
-            return entropyCache[make_tuple(start, end)];
-        }
-        for (auto i = &indices[start]; i != &indices[end]; ++i) {
-            counts[y[*i]]++;
-            nElements++;
-        }
-        for (auto count : counts) {
-            if (count > 0) {
-                p = (precision_t)count / nElements;
-                ventropy -= p * log2(p);
-            }
-        }
-        entropyCache[make_tuple(start, end)] = ventropy;
-        return ventropy;
-    }
-    precision_t Metrics::informationGain(size_t start, size_t cut, size_t end)
-    {
-        precision_t iGain;
-        precision_t entropyInterval, entropyLeft, entropyRight;
-        int nElementsLeft = cut - start, nElementsRight = end - cut;
-        int nElements = end - start;
-        if (igCache.find(make_tuple(start, cut, end)) != igCache.end()) {
-            return igCache[make_tuple(start, cut, end)];
-        }
-        entropyInterval = entropy(start, end);
-        entropyLeft = entropy(start, cut);
-        entropyRight = entropy(cut, end);
-        iGain = entropyInterval - ((precision_t)nElementsLeft * entropyLeft + (precision_t)nElementsRight * entropyRight) / nElements;
-        igCache[make_tuple(start, cut, end)] = iGain;
-        return iGain;
-    }
-
-}

src/cppmdlp/Metrics.h

@@ -1,20 +0,0 @@
-#ifndef CCMETRICS_H
-#define CCMETRICS_H
-#include "typesFImdlp.h"
-namespace mdlp {
-    class Metrics {
-    protected:
-        labels_t& y;
-        indices_t& indices;
-        int numClasses;
-        cacheEnt_t entropyCache;
-        cacheIg_t igCache;
-    public:
-        Metrics(labels_t&, indices_t&);
-        void setData(labels_t&, indices_t&);
-        int computeNumClasses(size_t, size_t);
-        precision_t entropy(size_t, size_t);
-        precision_t informationGain(size_t, size_t, size_t);
-    };
-}
-#endif

src/cppmdlp/README.md

@@ -1,2 +0,0 @@
-# mdlp
-Discretization algorithm based on the paper by Fayyad & Irani Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning

src/cppmdlp/sample/ArffFiles.cpp

@@ -1,117 +0,0 @@
-#include "ArffFiles.h"
-
-#include <fstream>
-#include <sstream>
-#include <map>
-#include <iostream>
-
-using namespace std;
-
-ArffFiles::ArffFiles()
-{
-}
-vector<string> ArffFiles::getLines()
-{
-    return lines;
-}
-unsigned long int ArffFiles::getSize()
-{
-    return lines.size();
-}
-vector<tuple<string, string>> ArffFiles::getAttributes()
-{
-    return attributes;
-}
-string ArffFiles::getClassName()
-{
-    return className;
-}
-string ArffFiles::getClassType()
-{
-    return classType;
-}
-vector<vector<float>>& ArffFiles::getX()
-{
-    return X;
-}
-vector<int>& ArffFiles::getY()
-{
-    return y;
-}
-void ArffFiles::load(string fileName, bool classLast)
-{
-    ifstream file(fileName);
-    string keyword, attribute, type;
-    if (file.is_open()) {
-        string line;
-        while (getline(file, line)) {
-            if (line[0] == '%' || line.empty() || line == "\r" || line == " ") {
-                continue;
-            }
-            if (line.find("@attribute") != string::npos || line.find("@ATTRIBUTE") != string::npos) {
-                stringstream ss(line);
-                ss >> keyword >> attribute >> type;
-                attributes.push_back(make_tuple(attribute, type));
-                continue;
-            }
-            if (line[0] == '@') {
-                continue;
-            }
-            lines.push_back(line);
-        }
-        file.close();
-        if (attributes.empty())
-            throw invalid_argument("No attributes found");
-        if (classLast) {
-            className = get<0>(attributes.back());
-            classType = get<1>(attributes.back());
-            attributes.pop_back();
-        } else {
-            className = get<0>(attributes.front());
-            classType = get<1>(attributes.front());
-            attributes.erase(attributes.begin());
-        }
-        generateDataset(classLast);
-    } else
-        throw invalid_argument("Unable to open file");
-}
-void ArffFiles::generateDataset(bool classLast)
-{
-    X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
-    vector<string> yy = vector<string>(lines.size(), "");
-    int labelIndex = classLast ? attributes.size() : 0;
-    for (int i = 0; i < lines.size(); i++) {
-        stringstream ss(lines[i]);
-        string value;
-        int pos = 0, xIndex = 0;
-        while (getline(ss, value, ',')) {
-            if (pos++ == labelIndex) {
-                yy[i] = value;
-            } else {
-                X[xIndex++][i] = stof(value);
-            }
-        }
-    }
-    y = factorize(yy);
-}
-string ArffFiles::trim(const string& source)
-{
-    string s(source);
-    s.erase(0, s.find_first_not_of(" \n\r\t"));
-    s.erase(s.find_last_not_of(" \n\r\t") + 1);
-    return s;
-}
-vector<int> ArffFiles::factorize(const vector<string>& labels_t)
-{
-    vector<int> yy;
-    yy.reserve(labels_t.size());
-    map<string, int> labelMap;
-    int i = 0;
-    for (string label : labels_t) {
-        if (labelMap.find(label) == labelMap.end()) {
-            labelMap[label] = i++;
-        }
-        yy.push_back(labelMap[label]);
-    }
-    return yy;
-}

src/cppmdlp/sample/ArffFiles.h

@@ -1,28 +0,0 @@
-#ifndef ARFFFILES_H
-#define ARFFFILES_H
-#include <string>
-#include <vector>
-#include <tuple>
-using namespace std;
-class ArffFiles {
-private:
-    vector<string> lines;
-    vector<tuple<string, string>> attributes;
-    string className, classType;
-    vector<vector<float>> X;
-    vector<int> y;
-    void generateDataset(bool);
-public:
-    ArffFiles();
-    void load(string, bool = true);
-    vector<string> getLines();
-    unsigned long int getSize();
-    string getClassName();
-    string getClassType();
-    string trim(const string&);
-    vector<vector<float>>& getX();
-    vector<int>& getY();
-    vector<tuple<string, string>> getAttributes();
-    vector<int> factorize(const vector<string>& labels_t);
-};
-#endif

src/cppmdlp/sample/CMakeLists.txt

@@ -1,6 +0,0 @@
-cmake_minimum_required(VERSION 3.24)
-project(main)
-
-set(CMAKE_CXX_STANDARD 17)
-
-add_executable(sample sample.cpp ArffFiles.cpp ../Metrics.cpp ../CPPFImdlp.cpp)

src/cppmdlp/sample/sample.cpp

@@ -1,54 +0,0 @@
-#include "ArffFiles.h"
-#include <iostream>
-#include <vector>
-#include <iomanip>
-#include "../CPPFImdlp.h"
-
-using namespace std;
-
-int main(int argc, char** argv)
-{
-    ArffFiles file;
-    vector<string> lines;
-    string path = "../../tests/datasets/";
-    map<string, bool > datasets = {
-        {"mfeat-factors", true},
-        {"iris", true},
-        {"letter", true},
-        {"kdd_JapaneseVowels", false}
-    };
-    if (argc != 2 || datasets.find(argv[1]) == datasets.end()) {
-        cout << "Usage: " << argv[0] << " {mfeat-factors, iris, letter, kdd_JapaneseVowels}" << endl;
-        return 1;
-    }
-
-    file.load(path + argv[1] + ".arff", datasets[argv[1]]);
-    auto attributes = file.getAttributes();
-    int items = file.getSize();
-    cout << "Number of lines: " << items << endl;
-    cout << "Attributes: " << endl;
-    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<vector<float>>& X = file.getX();
-    vector<int>& y = file.getY();
-    for (int i = 0; i < 50; i++) {
-        for (auto feature : X) {
-            cout << fixed << setprecision(1) << feature[i] << " ";
-        }
-        cout << y[i] << endl;
-    }
-    mdlp::CPPFImdlp test = mdlp::CPPFImdlp(false);
-    for (auto i = 0; i < attributes.size(); i++) {
-        cout << "Cut points for " << get<0>(attributes[i]) << endl;
-        cout << "--------------------------" << setprecision(3) << endl;
-        test.fit(X[i], y);
-        for (auto item : test.getCutPoints()) {
-            cout << item << endl;
-        }
-    }
-    return 0;
-}

src/cppmdlp/tests/.gitignore

@@ -1,2 +0,0 @@
-build
-build/*

src/cppmdlp/tests/CMakeLists.txt

@@ -1,32 +0,0 @@
-cmake_minimum_required(VERSION 3.14)
-project(FImdlp)
-
-# GoogleTest requires at least C++14
-set(CMAKE_CXX_STANDARD 14)
-include(FetchContent)
-
-include_directories(${GTEST_INCLUDE_DIRS})
-
-FetchContent_Declare(
-  googletest
-  URL https://github.com/google/googletest/archive/03597a01ee50ed33e9dfd640b249b4be3799d395.zip
-)
-# For Windows: Prevent overriding the parent project's compiler/linker settings
-set(gtest_force_shared_crt ON CACHE BOOL "" FORCE)
-FetchContent_MakeAvailable(googletest)
-
-enable_testing()
-
-add_executable(Metrics_unittest ../Metrics.cpp Metrics_unittest.cpp)
-add_executable(FImdlp_unittest ../CPPFImdlp.cpp ../Metrics.cpp FImdlp_unittest.cpp)
-target_link_libraries(Metrics_unittest GTest::gtest_main)
-target_link_libraries(FImdlp_unittest GTest::gtest_main)
-target_compile_options(Metrics_unittest PRIVATE --coverage)
-target_compile_options(FImdlp_unittest PRIVATE --coverage)
-target_link_options(Metrics_unittest PRIVATE --coverage)
-target_link_options(FImdlp_unittest PRIVATE --coverage)
-
-include(GoogleTest)
-gtest_discover_tests(Metrics_unittest)
-gtest_discover_tests(FImdlp_unittest)
-

src/cppmdlp/tests/FImdlp_unittest.cpp

@@ -1,141 +0,0 @@
-#include "gtest/gtest.h"
-#include "../Metrics.h"
-#include "../CPPFImdlp.h"
-#include <iostream>
-
-namespace mdlp {
-    class TestFImdlp : public CPPFImdlp, public testing::Test {
-    public:
-        precision_t precision = 0.000001;
-
-        TestFImdlp() : CPPFImdlp(false) {}
-
-        void SetUp() {
-            //    5.0, 5.1, 5.1, 5.1, 5.2, 5.3, 5.6, 5.7, 5.9, 6.0]
-            //(5.0, 1) (5.1, 1) (5.1, 2) (5.1, 2) (5.2, 1) (5.3, 1) (5.6, 2) (5.7, 1) (5.9, 2) (6.0, 2)
-            X = {5.7, 5.3, 5.2, 5.1, 5.0, 5.6, 5.1, 6.0, 5.1, 5.9};
-            y = {1, 1, 1, 1, 1, 2, 2, 2, 2, 2};
-            proposal = false;
-            fit(X, y);
-        }
-
-        void setProposal(bool value) {
-            proposal = value;
-        }
-
-        // void initIndices()
-        // {
-        //     indices = indices_t();
-        // }
-        void checkSortedVector() {
-            indices_t testSortedIndices = sortIndices(X);
-            precision_t prev = X[testSortedIndices[0]];
-            for (auto i = 0; i < X.size(); ++i) {
-                EXPECT_EQ(testSortedIndices[i], indices[i]);
-                EXPECT_LE(prev, X[testSortedIndices[i]]);
-                prev = X[testSortedIndices[i]];
-            }
-        }
-
-        void checkCutPoints(cutPoints_t &expected) {
-            int expectedSize = expected.size();
-            EXPECT_EQ(cutPoints.size(), expectedSize);
-            for (auto i = 0; i < cutPoints.size(); i++) {
-                EXPECT_NEAR(cutPoints[i], expected[i], precision);
-            }
-        }
-
-        template<typename T, typename A>
-        void checkVectors(std::vector<T, A> const &expected, std::vector<T, A> const &computed) {
-            EXPECT_EQ(expected.size(), computed.size());
-            ASSERT_EQ(expected.size(), computed.size());
-            for (auto i = 0; i < expected.size(); i++) {
-                EXPECT_NEAR(expected[i], computed[i],precision);
-            }
-        }
-    };
-
-    TEST_F(TestFImdlp, FitErrorEmptyDataset) {
-        X = samples_t();
-        y = labels_t();
-        EXPECT_THROW(fit(X, y), std::invalid_argument);
-    }
-
-    TEST_F(TestFImdlp, FitErrorDifferentSize) {
-        X = {1, 2, 3};
-        y = {1, 2};
-        EXPECT_THROW(fit(X, y), std::invalid_argument);
-    }
-
-    TEST_F(TestFImdlp, SortIndices) {
-        X = {5.7, 5.3, 5.2, 5.1, 5.0, 5.6, 5.1, 6.0, 5.1, 5.9};
-        indices = {4, 3, 6, 8, 2, 1, 5, 0, 9, 7};
-        checkSortedVector();
-        X = {5.77, 5.88, 5.99};
-        indices = {0, 1, 2};
-        checkSortedVector();
-        X = {5.33, 5.22, 5.11};
-        indices = {2, 1, 0};
-        checkSortedVector();
-    }
-
-    TEST_F(TestFImdlp, TestDataset) {
-        proposal = false;
-        fit(X, y);
-        computeCutPointsOriginal(0, 10);
-        cutPoints_t expected = {5.6499996185302734};
-        vector<precision_t> computed = getCutPoints();
-        computed = getCutPoints();
-        int expectedSize = expected.size();
-        EXPECT_EQ(computed.size(), expected.size());
-        for (auto i = 0; i < expectedSize; i++) {
-            EXPECT_NEAR(computed[i], expected[i], precision);
-        }
-    }
-
-    TEST_F(TestFImdlp, ComputeCutPointsOriginal) {
-        cutPoints_t expected = {5.65};
-        proposal = false;
-        computeCutPointsOriginal(0, 10);
-        checkCutPoints(expected);
-    }
-
-    TEST_F(TestFImdlp, ComputeCutPointsOriginalGCase) {
-        cutPoints_t expected;
-        proposal = false;
-        expected = {2};
-        samples_t X_ = {0, 1, 2, 2};
-        labels_t y_ = {1, 1, 1, 2};
-        fit(X_, y_);
-        checkCutPoints(expected);
-    }
-
-    TEST_F(TestFImdlp, ComputeCutPointsProposal) {
-        proposal = true;
-        cutPoints_t expected;
-        expected = {};
-        fit(X, y);
-        computeCutPointsProposal();
-        checkCutPoints(expected);
-    }
-
-    TEST_F(TestFImdlp, ComputeCutPointsProposalGCase) {
-        cutPoints_t expected;
-        expected = {1.5};
-        proposal = true;
-        samples_t X_ = {0, 1, 2, 2};
-        labels_t y_ = {1, 1, 1, 2};
-        fit(X_, y_);
-        checkCutPoints(expected);
-    }
-
-    TEST_F(TestFImdlp, GetCutPoints) {
-        samples_t computed, expected = {5.65};
-        proposal = false;
-        computeCutPointsOriginal(0, 10);
-        computed = getCutPoints();
-        for (auto item: cutPoints)
-            cout << setprecision(6) << item << endl;
-        checkVectors(expected, computed);
-    }
-}

src/cppmdlp/tests/Metrics_unittest.cpp

@@ -1,43 +0,0 @@
-#include "gtest/gtest.h"
-#include "../Metrics.h"
-
-
-namespace mdlp {
-    class TestMetrics: public Metrics, public testing::Test {
-    public:
-        labels_t y;
-        samples_t X;
-        indices_t indices;
-        precision_t precision = 0.000001;
-
-        TestMetrics(): Metrics(y, indices) {}
-        void SetUp()
-        {
-            y = { 1, 1, 1, 1, 1, 2, 2, 2, 2, 2 };
-            indices = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 };
-            setData(y, indices);
-        }
-    };
-    TEST_F(TestMetrics, NumClasses)
-    {
-        y = { 1, 1, 1, 1, 1, 1, 1, 1, 2, 1 };
-        EXPECT_EQ(1, computeNumClasses(4, 8));
-        EXPECT_EQ(2, computeNumClasses(0, 10));
-        EXPECT_EQ(2, computeNumClasses(8, 10));
-    }
-    TEST_F(TestMetrics, Entropy)
-    {
-        EXPECT_EQ(1, entropy(0, 10));
-        EXPECT_EQ(0, entropy(0, 5));
-        y = { 1, 1, 1, 1, 1, 1, 1, 1, 2, 1 };
-        setData(y, indices);
-        ASSERT_NEAR(0.468996, entropy(0, 10), precision);
-    }
-    TEST_F(TestMetrics, InformationGain)
-    {
-        ASSERT_NEAR(1, informationGain(0, 5, 10), precision);
-        y = { 1, 1, 1, 1, 1, 1, 1, 1, 2, 1 };
-        setData(y, indices);
-        ASSERT_NEAR(0.108032, informationGain(0, 5, 10), precision);
-    }
-}

src/cppmdlp/tests/cover

@@ -1,4 +0,0 @@
-rm -fr lcoverage/*
-lcov --capture --directory ./ --output-file lcoverage/main_coverage.info
-genhtml lcoverage/main_coverage.info --output-directory lcoverage
-open lcoverage/index.html

src/cppmdlp/tests/datasets/iris.arff

@@ -1,225 +0,0 @@
-% 1. Title: Iris Plants Database
-% 
-% 2. Sources:
-%      (a) Creator: R.A. Fisher
-%      (b) Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
-%      (c) Date: July, 1988
-% 
-% 3. Past Usage:
-%    - Publications: too many to mention!!!  Here are a few.
-%    1. Fisher,R.A. "The use of multiple measurements in taxonomic problems"
-%       Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions
-%       to Mathematical Statistics" (John Wiley, NY, 1950).
-%    2. Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.
-%       (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.
-%    3. Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System
-%       Structure and Classification Rule for Recognition in Partially Exposed
-%       Environments".  IEEE Transactions on Pattern Analysis and Machine
-%       Intelligence, Vol. PAMI-2, No. 1, 67-71.
-%       -- Results:
-%          -- very low misclassification rates (0% for the setosa class)
-%    4. Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule".  IEEE 
-%       Transactions on Information Theory, May 1972, 431-433.
-%       -- Results:
-%          -- very low misclassification rates again
-%    5. See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al's AUTOCLASS II
-%       conceptual clustering system finds 3 classes in the data.
-% 
-% 4. Relevant Information:
-%    --- This is perhaps the best known database to be found in the pattern
-%        recognition literature.  Fisher's paper is a classic in the field
-%        and is referenced frequently to this day.  (See Duda & Hart, for
-%        example.)  The data set contains 3 classes of 50 instances each,
-%        where each class refers to a type of iris plant.  One class is
-%        linearly separable from the other 2; the latter are NOT linearly
-%        separable from each other.
-%    --- Predicted attribute: class of iris plant.
-%    --- This is an exceedingly simple domain.
-% 
-% 5. Number of Instances: 150 (50 in each of three classes)
-% 
-% 6. Number of Attributes: 4 numeric, predictive attributes and the class
-% 
-% 7. Attribute Information:
-%    1. sepal length in cm
-%    2. sepal width in cm
-%    3. petal length in cm
-%    4. petal width in cm
-%    5. class: 
-%       -- Iris Setosa
-%       -- Iris Versicolour
-%       -- Iris Virginica
-% 
-% 8. Missing Attribute Values: None
-% 
-% Summary Statistics:
-%  	           Min  Max   Mean    SD   Class Correlation
-%    sepal length: 4.3  7.9   5.84  0.83    0.7826   
-%     sepal width: 2.0  4.4   3.05  0.43   -0.4194
-%    petal length: 1.0  6.9   3.76  1.76    0.9490  (high!)
-%     petal width: 0.1  2.5   1.20  0.76    0.9565  (high!)
-% 
-% 9. Class Distribution: 33.3% for each of 3 classes.
-
-@RELATION iris
-
-@ATTRIBUTE sepallength	REAL
-@ATTRIBUTE sepalwidth 	REAL
-@ATTRIBUTE petallength 	REAL
-@ATTRIBUTE petalwidth	REAL
-@ATTRIBUTE class 	{Iris-setosa,Iris-versicolor,Iris-virginica}
-
-@DATA
-5.1,3.5,1.4,0.2,Iris-setosa
-4.9,3.0,1.4,0.2,Iris-setosa
-4.7,3.2,1.3,0.2,Iris-setosa
-4.6,3.1,1.5,0.2,Iris-setosa
-5.0,3.6,1.4,0.2,Iris-setosa
-5.4,3.9,1.7,0.4,Iris-setosa
-4.6,3.4,1.4,0.3,Iris-setosa
-5.0,3.4,1.5,0.2,Iris-setosa
-4.4,2.9,1.4,0.2,Iris-setosa
-4.9,3.1,1.5,0.1,Iris-setosa
-5.4,3.7,1.5,0.2,Iris-setosa
-4.8,3.4,1.6,0.2,Iris-setosa
-4.8,3.0,1.4,0.1,Iris-setosa
-4.3,3.0,1.1,0.1,Iris-setosa
-5.8,4.0,1.2,0.2,Iris-setosa
-5.7,4.4,1.5,0.4,Iris-setosa
-5.4,3.9,1.3,0.4,Iris-setosa
-5.1,3.5,1.4,0.3,Iris-setosa
-5.7,3.8,1.7,0.3,Iris-setosa
-5.1,3.8,1.5,0.3,Iris-setosa
-5.4,3.4,1.7,0.2,Iris-setosa
-5.1,3.7,1.5,0.4,Iris-setosa
-4.6,3.6,1.0,0.2,Iris-setosa
-5.1,3.3,1.7,0.5,Iris-setosa
-4.8,3.4,1.9,0.2,Iris-setosa
-5.0,3.0,1.6,0.2,Iris-setosa
-5.0,3.4,1.6,0.4,Iris-setosa
-5.2,3.5,1.5,0.2,Iris-setosa
-5.2,3.4,1.4,0.2,Iris-setosa
-4.7,3.2,1.6,0.2,Iris-setosa
-4.8,3.1,1.6,0.2,Iris-setosa
-5.4,3.4,1.5,0.4,Iris-setosa
-5.2,4.1,1.5,0.1,Iris-setosa
-5.5,4.2,1.4,0.2,Iris-setosa
-4.9,3.1,1.5,0.1,Iris-setosa
-5.0,3.2,1.2,0.2,Iris-setosa
-5.5,3.5,1.3,0.2,Iris-setosa
-4.9,3.1,1.5,0.1,Iris-setosa
-4.4,3.0,1.3,0.2,Iris-setosa
-5.1,3.4,1.5,0.2,Iris-setosa
-5.0,3.5,1.3,0.3,Iris-setosa
-4.5,2.3,1.3,0.3,Iris-setosa
-4.4,3.2,1.3,0.2,Iris-setosa
-5.0,3.5,1.6,0.6,Iris-setosa
-5.1,3.8,1.9,0.4,Iris-setosa
-4.8,3.0,1.4,0.3,Iris-setosa
-5.1,3.8,1.6,0.2,Iris-setosa
-4.6,3.2,1.4,0.2,Iris-setosa
-5.3,3.7,1.5,0.2,Iris-setosa
-5.0,3.3,1.4,0.2,Iris-setosa
-7.0,3.2,4.7,1.4,Iris-versicolor
-6.4,3.2,4.5,1.5,Iris-versicolor
-6.9,3.1,4.9,1.5,Iris-versicolor
-5.5,2.3,4.0,1.3,Iris-versicolor
-6.5,2.8,4.6,1.5,Iris-versicolor
-5.7,2.8,4.5,1.3,Iris-versicolor
-6.3,3.3,4.7,1.6,Iris-versicolor
-4.9,2.4,3.3,1.0,Iris-versicolor
-6.6,2.9,4.6,1.3,Iris-versicolor
-5.2,2.7,3.9,1.4,Iris-versicolor
-5.0,2.0,3.5,1.0,Iris-versicolor
-5.9,3.0,4.2,1.5,Iris-versicolor
-6.0,2.2,4.0,1.0,Iris-versicolor
-6.1,2.9,4.7,1.4,Iris-versicolor
-5.6,2.9,3.6,1.3,Iris-versicolor
-6.7,3.1,4.4,1.4,Iris-versicolor
-5.6,3.0,4.5,1.5,Iris-versicolor
-5.8,2.7,4.1,1.0,Iris-versicolor
-6.2,2.2,4.5,1.5,Iris-versicolor
-5.6,2.5,3.9,1.1,Iris-versicolor
-5.9,3.2,4.8,1.8,Iris-versicolor
-6.1,2.8,4.0,1.3,Iris-versicolor
-6.3,2.5,4.9,1.5,Iris-versicolor
-6.1,2.8,4.7,1.2,Iris-versicolor
-6.4,2.9,4.3,1.3,Iris-versicolor
-6.6,3.0,4.4,1.4,Iris-versicolor
-6.8,2.8,4.8,1.4,Iris-versicolor
-6.7,3.0,5.0,1.7,Iris-versicolor
-6.0,2.9,4.5,1.5,Iris-versicolor
-5.7,2.6,3.5,1.0,Iris-versicolor
-5.5,2.4,3.8,1.1,Iris-versicolor
-5.5,2.4,3.7,1.0,Iris-versicolor
-5.8,2.7,3.9,1.2,Iris-versicolor
-6.0,2.7,5.1,1.6,Iris-versicolor
-5.4,3.0,4.5,1.5,Iris-versicolor
-6.0,3.4,4.5,1.6,Iris-versicolor
-6.7,3.1,4.7,1.5,Iris-versicolor
-6.3,2.3,4.4,1.3,Iris-versicolor
-5.6,3.0,4.1,1.3,Iris-versicolor
-5.5,2.5,4.0,1.3,Iris-versicolor
-5.5,2.6,4.4,1.2,Iris-versicolor
-6.1,3.0,4.6,1.4,Iris-versicolor
-5.8,2.6,4.0,1.2,Iris-versicolor
-5.0,2.3,3.3,1.0,Iris-versicolor
-5.6,2.7,4.2,1.3,Iris-versicolor
-5.7,3.0,4.2,1.2,Iris-versicolor
-5.7,2.9,4.2,1.3,Iris-versicolor
-6.2,2.9,4.3,1.3,Iris-versicolor
-5.1,2.5,3.0,1.1,Iris-versicolor
-5.7,2.8,4.1,1.3,Iris-versicolor
-6.3,3.3,6.0,2.5,Iris-virginica
-5.8,2.7,5.1,1.9,Iris-virginica
-7.1,3.0,5.9,2.1,Iris-virginica
-6.3,2.9,5.6,1.8,Iris-virginica
-6.5,3.0,5.8,2.2,Iris-virginica
-7.6,3.0,6.6,2.1,Iris-virginica
-4.9,2.5,4.5,1.7,Iris-virginica
-7.3,2.9,6.3,1.8,Iris-virginica
-6.7,2.5,5.8,1.8,Iris-virginica
-7.2,3.6,6.1,2.5,Iris-virginica
-6.5,3.2,5.1,2.0,Iris-virginica
-6.4,2.7,5.3,1.9,Iris-virginica
-6.8,3.0,5.5,2.1,Iris-virginica
-5.7,2.5,5.0,2.0,Iris-virginica
-5.8,2.8,5.1,2.4,Iris-virginica
-6.4,3.2,5.3,2.3,Iris-virginica
-6.5,3.0,5.5,1.8,Iris-virginica
-7.7,3.8,6.7,2.2,Iris-virginica
-7.7,2.6,6.9,2.3,Iris-virginica
-6.0,2.2,5.0,1.5,Iris-virginica
-6.9,3.2,5.7,2.3,Iris-virginica
-5.6,2.8,4.9,2.0,Iris-virginica
-7.7,2.8,6.7,2.0,Iris-virginica
-6.3,2.7,4.9,1.8,Iris-virginica
-6.7,3.3,5.7,2.1,Iris-virginica
-7.2,3.2,6.0,1.8,Iris-virginica
-6.2,2.8,4.8,1.8,Iris-virginica
-6.1,3.0,4.9,1.8,Iris-virginica
-6.4,2.8,5.6,2.1,Iris-virginica
-7.2,3.0,5.8,1.6,Iris-virginica
-7.4,2.8,6.1,1.9,Iris-virginica
-7.9,3.8,6.4,2.0,Iris-virginica
-6.4,2.8,5.6,2.2,Iris-virginica
-6.3,2.8,5.1,1.5,Iris-virginica
-6.1,2.6,5.6,1.4,Iris-virginica
-7.7,3.0,6.1,2.3,Iris-virginica
-6.3,3.4,5.6,2.4,Iris-virginica
-6.4,3.1,5.5,1.8,Iris-virginica
-6.0,3.0,4.8,1.8,Iris-virginica
-6.9,3.1,5.4,2.1,Iris-virginica
-6.7,3.1,5.6,2.4,Iris-virginica
-6.9,3.1,5.1,2.3,Iris-virginica
-5.8,2.7,5.1,1.9,Iris-virginica
-6.8,3.2,5.9,2.3,Iris-virginica
-6.7,3.3,5.7,2.5,Iris-virginica
-6.7,3.0,5.2,2.3,Iris-virginica
-6.3,2.5,5.0,1.9,Iris-virginica
-6.5,3.0,5.2,2.0,Iris-virginica
-6.2,3.4,5.4,2.3,Iris-virginica
-5.9,3.0,5.1,1.8,Iris-virginica
-%
-%
-%

src/cppmdlp/tests/test

@@ -1,12 +0,0 @@
-cmake -S . -B build -Wno-dev 
-if test $? -ne 0; then
-   echo "Error in creating build commands."
-   exit 1
-fi
-cmake --build build
-if test $? -ne 0; then
-   echo "Error in build command."
-   exit 1
-fi
-cd build
-ctest --output-on-failure

src/cppmdlp/typesFImdlp.h

@@ -1,16 +0,0 @@
-#ifndef TYPES_H
-#define TYPES_H
-#include <vector>
-#include <map>
-
-using namespace std;
-namespace mdlp {
-    typedef float precision_t;
-    typedef vector<precision_t> samples_t;
-    typedef vector<int> labels_t;
-    typedef vector<size_t> indices_t;
-    typedef vector<precision_t> cutPoints_t;
-    typedef map<tuple<int, int>, precision_t> cacheEnt_t;
-    typedef map<tuple<int, int, int>, precision_t> cacheIg_t;
-}
-#endif

src/fimdlp/ArffFiles.cpp

@@ -0,0 +1,132 @@
+#include "ArffFiles.h"
+#include <fstream>
+#include <sstream>
+#include <map>
+
+using namespace std;
+
+ArffFiles::ArffFiles() = default;
+
+vector<string> ArffFiles::getLines() const
+{
+    return lines;
+}
+
+unsigned long int ArffFiles::getSize() const
+{
+    return lines.size();
+}
+
+vector<pair<string, string>> ArffFiles::getAttributes() const
+{
+    return attributes;
+}
+
+string ArffFiles::getClassName() const
+{
+    return className;
+}
+
+string ArffFiles::getClassType() const
+{
+    return classType;
+}
+
+vector<vector<float>>& ArffFiles::getX()
+{
+    return X;
+}
+
+vector<int>& ArffFiles::getY()
+{
+    return y;
+}
+
+void ArffFiles::load(const string& fileName, bool classLast)
+{
+    ifstream file(fileName);
+    if (!file.is_open()) {
+        throw invalid_argument("Unable to open file");
+    }
+    string line;
+    string keyword;
+    string attribute;
+    string type;
+    string type_w;
+    while (getline(file, line)) {
+        if (line.empty() || line[0] == '%' || line == "\r" || line == " ") {
+            continue;
+        }
+        if (line.find("@attribute") != string::npos || line.find("@ATTRIBUTE") != string::npos) {
+            stringstream ss(line);
+            ss >> keyword >> attribute;
+            type = "";
+            while (ss >> type_w)
+                type += type_w + " ";
+            attributes.emplace_back(trim(attribute), trim(type));
+            continue;
+        }
+        if (line[0] == '@') {
+            continue;
+        }
+        lines.push_back(line);
+    }
+    file.close();
+    if (attributes.empty())
+        throw invalid_argument("No attributes found");
+    if (classLast) {
+        className = get<0>(attributes.back());
+        classType = get<1>(attributes.back());
+        attributes.pop_back();
+    } else {
+        className = get<0>(attributes.front());
+        classType = get<1>(attributes.front());
+        attributes.erase(attributes.begin());
+    }
+    generateDataset(classLast);
+
+}
+
+void ArffFiles::generateDataset(bool classLast)
+{
+    X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
+    auto yy = vector<string>(lines.size(), "");
+    int labelIndex = classLast ? static_cast<int>(attributes.size()) : 0;
+    for (size_t i = 0; i < lines.size(); i++) {
+        stringstream ss(lines[i]);
+        string value;
+        int pos = 0;
+        int xIndex = 0;
+        while (getline(ss, value, ',')) {
+            if (pos++ == labelIndex) {
+                yy[i] = value;
+            } else {
+                X[xIndex++][i] = stof(value);
+            }
+        }
+    }
+    y = factorize(yy);
+}
+
+string ArffFiles::trim(const string& source)
+{
+    string s(source);
+    s.erase(0, s.find_first_not_of(" '\n\r\t"));
+    s.erase(s.find_last_not_of(" '\n\r\t") + 1);
+    return s;
+}
+
+vector<int> ArffFiles::factorize(const vector<string>& labels_t)
+{
+    vector<int> yy;
+    yy.reserve(labels_t.size());
+    map<string, int> labelMap;
+    int i = 0;
+    for (const string& label : labels_t) {
+        if (labelMap.find(label) == labelMap.end()) {
+            labelMap[label] = i++;
+        }
+        yy.push_back(labelMap[label]);
+    }
+    return yy;
+}

src/fimdlp/ArffFiles.h

@@ -0,0 +1,34 @@
+#ifndef ARFFFILES_H
+#define ARFFFILES_H
+
+#include <string>
+#include <vector>
+
+using namespace std;
+
+class ArffFiles {
+private:
+    vector<string> lines;
+    vector<pair<string, string>> attributes;
+    string className;
+    string classType;
+    vector<vector<float>> X;
+    vector<int> y;
+
+    void generateDataset(bool);
+
+public:
+    ArffFiles();
+    void load(const string&, bool = true);
+    vector<string> getLines() const;
+    unsigned long int getSize() const;
+    string getClassName() const;
+    string getClassType() const;
+    static string trim(const string&);
+    vector<vector<float>>& getX();
+    vector<int>& getY();
+    vector<pair<string, string>> getAttributes() const;
+    static vector<int> factorize(const vector<string>& labels_t);
+};
+
+#endif

src/fimdlp/Factorize.cpp

@@ -0,0 +1,18 @@
+#include "Factorize.h"
+
+namespace utils {
+    vector<int> cppFactorize(const vector<string>& labels_t)
+    {
+        vector<int> yy;
+        yy.reserve(labels_t.size());
+        map<string, int> labelMap;
+        int i = 0;
+        for (const string& label : labels_t) {
+            if (labelMap.find(label) == labelMap.end()) {
+                labelMap[label] = i++;
+            }
+            yy.push_back(labelMap[label]);
+        }
+        return yy;
+    }
+}

src/fimdlp/Factorize.h

@@ -0,0 +1,10 @@
+#ifndef FACTORIZE_H
+#define FACTORIZE_H
+#include <vector>
+#include <map>
+#include <string>
+namespace utils {
+    using namespace std;
+    vector<int> cppFactorize(const vector<string>&);
+}
+#endif

src/fimdlp/__init__.py

@@ -1,8 +1,4 @@
 from ._version import __version__
 
 
-def version():
-    return __version__
-
-
 all = ["FImdlp", "__version__"]

src/fimdlp/_version.py

@@ -1 +1 @@
-__version__ = "0.9.1"
+__version__ = "0.9.4"

src/fimdlp/cfimdlp.pyx

@@ -1,20 +1,27 @@
 # distutils: language = c++
 # cython: language_level = 3
 from libcpp.vector cimport vector
+from libcpp.pair cimport pair
+from libcpp.string cimport string
 from libcpp cimport bool
+import numpy as np
 
+cdef extern from "limits.h":
+    cdef int INT_MAX
 cdef extern from "../cppmdlp/CPPFImdlp.h" namespace "mdlp":
     ctypedef float precision_t
     cdef cppclass CPPFImdlp:
-        CPPFImdlp(bool) except + 
+        CPPFImdlp() except + 
+        CPPFImdlp(size_t, int, float) except + 
         CPPFImdlp& fit(vector[precision_t]&, vector[int]&)
+        int get_depth()
         vector[precision_t] getCutPoints()
+        string version()
         
-
 cdef class CFImdlp:
     cdef CPPFImdlp *thisptr
-    def __cinit__(self, proposal):
-        self.thisptr = new CPPFImdlp(proposal)
+    def __cinit__(self, size_t min_length=3, int max_depth=INT_MAX, float max_cuts=0):
+        self.thisptr = new CPPFImdlp(min_length, max_depth, max_cuts)
     def __dealloc__(self):
         del self.thisptr
     def fit(self, X, y):
@@ -22,4 +29,53 @@ cdef class CFImdlp:
         return self
     def get_cut_points(self):
         return self.thisptr.getCutPoints()
- 
+    def get_version(self):
+        return self.thisptr.version()
+    def get_depth(self):
+        return self.thisptr.get_depth()
+    def __reduce__(self):
+        return (CFImdlp, ())
+
+cdef extern from "Factorize.h" namespace "utils":
+    vector[int] cppFactorize(vector[string] &input_vector)
+def factorize(input_vector):
+    return cppFactorize(input_vector)
+
+cdef extern from "ArffFiles.h":
+    cdef cppclass ArffFiles:
+        ArffFiles() except +
+        void load(string, bool)
+        unsigned long int getSize()
+        string getClassName()
+        string getClassType()
+        string trim(const string&)
+        vector[vector[float]]& getX()
+        vector[int]& getY()
+        vector[string] getLines()
+        vector[pair[string, string]] getAttributes()
+
+cdef class CArffFiles:
+    cdef ArffFiles *thisptr
+    def __cinit__(self):
+        self.thisptr = new ArffFiles()
+    def __dealloc__(self):
+        del self.thisptr
+    def load(self, string filename, bool verbose = True):
+        self.thisptr.load(filename, verbose)
+    def get_size(self):
+        return self.thisptr.getSize()
+    def get_class_name(self):
+        return self.thisptr.getClassName()
+    def get_class_type(self):
+        return self.thisptr.getClassType()
+    def get_X(self):
+        return np.array(self.thisptr.getX()).T
+    def get_y(self):
+        return self.thisptr.getY()
+    def get_lines(self):
+        return self.thisptr.getLines()
+    def get_attributes(self):
+        return self.thisptr.getAttributes()
+    def __reduce__(self):
+        return (CArffFiles, ())
+   

src/fimdlp/mdlp.py

@@ -1,15 +1,18 @@
 import numpy as np
-from .cppfimdlp import CFImdlp
+from .cppfimdlp import CFImdlp, factorize
 from sklearn.base import BaseEstimator, TransformerMixin
 from sklearn.utils.multiclass import unique_labels
 from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
 from joblib import Parallel, delayed
+from ._version import __version__
 
 
 class FImdlp(TransformerMixin, BaseEstimator):
-    def __init__(self, n_jobs=-1, proposal=False):
+    def __init__(self, n_jobs=-1, min_length=3, max_depth=1e6, max_cuts=0):
         self.n_jobs = n_jobs
-        self.proposal = proposal
+        self.min_length = min_length
+        self.max_depth = max_depth
+        self.max_cuts = max_cuts
 
     """Fayyad - Irani MDLP discretization algorithm based implementation.
 
@@ -19,30 +22,35 @@ class FImdlp(TransformerMixin, BaseEstimator):
         The number of jobs to run in parallel. :meth:`fit` and
         :meth:`transform`, are parallelized over the features. ``-1`` means
         using all cores available.
+    min_length: int, default=3
+        The minimum length of an interval to be considered to be discretized.
+    max_depth: int, default=1e6
+        The maximum depth of the discretization process.
+    max_cuts: float, default=0
+        The maximum number of cut points to be computed for each feature.
 
     Attributes
     ----------
-    n_features_ : int
+    n_features_in_ : int
         The number of features of the data passed to :meth:`fit`.
     discretizer_ : list
         The list of discretizers, one for each feature.
     cut_points_ : list
         The list of cut points for each feature.
-    X_ : array
-        the samples used to fit, shape (n_samples, n_features)
-    y_ : array
-        the labels used to fit, shape (n_samples,)
+    X_ : array, shape (n_samples, n_features)
+        the samples used to fit
+    y_ : array, shape(n_samples,)
+        the labels used to fit
     features_ : list
         the list of features to be discretized
     """
 
-    def _check_params_fit(self, X, y, expected_args, kwargs):
-        """Check the common parameters passed to fit"""
+    def _more_tags(self):
+        return {"preserves_dtype": [np.int32], "requires_y": True}
+
+    def _check_args(self, X, y, expected_args, kwargs):
         # Check that X and y have correct shape
         X, y = check_X_y(X, y)
-        # Store the classes seen during fit
-        self.classes_ = unique_labels(y)
-        self.n_classes_ = self.classes_.shape[0]
         # Default values
         self.features_ = [i for i in range(X.shape[1])]
         for key, value in kwargs.items():
@@ -63,15 +71,24 @@ class FImdlp(TransformerMixin, BaseEstimator):
             raise ValueError("Feature index out of range")
         return X, y
 
+    def _update_params(self, X, y):
+        # Store the classes seen during fit
+        self.classes_ = unique_labels(y)
+        self.n_classes_ = self.classes_.shape[0]
+        self.n_features_in_ = X.shape[1]
+
+    @staticmethod
+    def get_version():
+        return f"{__version__}({CFImdlp().get_version().decode()})"
+
     def fit(self, X, y, **kwargs):
         """A reference implementation of a fitting function for a transformer.
         Parameters
         ----------
-        X : {array-like, sparse matrix}, shape (n_samples, n_features)
+        X : array, shape (n_samples, n_features)
             The training input samples.
-        y : None
-            There is no need of a target in a transformer, yet the pipeline API
-            requires this parameter.
+        y : array, shape (n_samples,)
+            the labels used to fit
         features : list, default=[i for i in range(n_features)]
             The list of features to be discretized.
         Returns
@@ -79,24 +96,41 @@ class FImdlp(TransformerMixin, BaseEstimator):
         self : object
             Returns self.
         """
-        X, y = self._check_params_fit(
+        X, y = self._check_args(
             X, y, expected_args=["features"], kwargs=kwargs
         )
-        self.n_features_ = X.shape[1]
+        self._update_params(X, y)
         self.X_ = X
         self.y_ = y
-        self.discretizer_ = [None] * self.n_features_
-        self.cut_points_ = [None] * self.n_features_
+        self.efective_min_length_ = (
+            self.min_length
+            if self.min_length > 1
+            else int(self.min_length * X.shape[0])
+        )
+        self.discretizer_ = [None] * self.n_features_in_
+        self.cut_points_ = [None] * self.n_features_in_
         Parallel(n_jobs=self.n_jobs, prefer="threads")(
             delayed(self._fit_discretizer)(feature)
-            for feature in range(self.n_features_)
+            for feature in range(self.n_features_in_)
         )
+        # target of every feature. Start with -1 => y (see join_fit)
+        self.target_ = [-1] * self.n_features_in_
         return self
 
     def _fit_discretizer(self, feature):
-        self.discretizer_[feature] = CFImdlp(proposal=self.proposal)
-        self.discretizer_[feature].fit(self.X_[:, feature], self.y_)
-        self.cut_points_[feature] = self.discretizer_[feature].get_cut_points()
+        if feature in self.features_:
+            self.discretizer_[feature] = CFImdlp(
+                min_length=self.efective_min_length_,
+                max_depth=self.max_depth,
+                max_cuts=self.max_cuts,
+            )
+            self.discretizer_[feature].fit(self.X_[:, feature], self.y_)
+            self.cut_points_[feature] = self.discretizer_[
+                feature
+            ].get_cut_points()
+        else:
+            self.discretizer_[feature] = None
+            self.cut_points_[feature] = []
 
     def _discretize_feature(self, feature, X, result):
         if feature in self.features_:
@@ -108,7 +142,7 @@ class FImdlp(TransformerMixin, BaseEstimator):
         """Discretize X values.
         Parameters
         ----------
-        X : {array-like}, shape (n_samples, n_features)
+        X : array, shape (n_samples, n_features)
             The input samples.
         Returns
         -------
@@ -116,22 +150,41 @@ class FImdlp(TransformerMixin, BaseEstimator):
             The array containing the discretized values of ``X``.
         """
         # Check is fit had been called
-        check_is_fitted(self, "n_features_")
+        check_is_fitted(self, "n_features_in_")
         # Input validation
         X = check_array(X)
         # Check that the input is of the same shape as the one passed
         # during fit.
-        if X.shape[1] != self.n_features_:
+        if X.shape[1] != self.n_features_in_:
             raise ValueError(
                 "Shape of input is different from what was seen in `fit`"
             )
-        result = np.zeros_like(X, dtype=np.int32) - 1
+        if len(self.features_) == self.n_features_in_:
+            result = np.zeros_like(X, dtype=np.int32) - 1
+        else:
+            result = np.zeros_like(X) - 1
         Parallel(n_jobs=self.n_jobs, prefer="threads")(
             delayed(self._discretize_feature)(feature, X[:, feature], result)
-            for feature in range(self.n_features_)
+            for feature in range(self.n_features_in_)
         )
         return result
 
+    @staticmethod
+    def factorize(yy):
+        """Factorize the input labels
+
+        Parameters
+        ----------
+        yy : array, shape (n_samples,)
+            Labels to be factorized, MUST be bytes, i.e. b"0", b"1", ...
+
+        Returns
+        -------
+        array, shape (n_samples,)
+            Factorized labels
+        """
+        return factorize(yy)
+
     def get_cut_points(self):
         """Get the cut points for each feature.
         Returns
@@ -140,6 +193,78 @@ class FImdlp(TransformerMixin, BaseEstimator):
             The list of cut points for each feature.
         """
         result = []
-        for feature in range(self.n_features_):
+        for feature in range(self.n_features_in_):
             result.append(self.cut_points_[feature])
         return result
+
+    def get_states_feature(self, feature):
+        """Return the states a feature can take
+
+        Parameters
+        ----------
+        feature : int
+            feature to get the states
+
+        Returns
+        -------
+        list
+            states of the feature
+        """
+        if feature in self.features_:
+            return list(range(len(self.cut_points_[feature]) + 1))
+        return None
+
+    def join_fit(self, features, target, data):
+        """Join the selected features with the labels and fit the discretizer
+        of the target variable
+        join - fit - transform
+
+        Parameters
+        ----------
+        features : [list]
+            index of the features to join with the labels
+        target : [int]
+            index of the target variable to discretize
+        data: [array] shape (n_samples, n_features)
+            dataset that contains the features to join
+
+        Returns
+        -------
+        result: np.array
+            The target variable newly discretized
+        """
+        check_is_fitted(self, "n_features_in_")
+        if len(features) < 1 or len(features) > self.n_features_in_:
+            raise ValueError(
+                "Number of features must be in range [1, "
+                f"{self.n_features_in_}]"
+            )
+        for feature in features:
+            if feature < 0 or feature >= self.n_features_in_:
+                raise ValueError(
+                    f"Feature {feature} not in range [0, "
+                    f"{self.n_features_in_})"
+                )
+        if target < 0 or target >= self.n_features_in_:
+            raise ValueError(
+                f"Target {target} not in range [0, {self.n_features_in_})"
+            )
+        if target in features:
+            raise ValueError("Target cannot be in features to join")
+        y_join = [
+            f"{str(item_y)}{''.join([str(x) for x in items_x])}".encode()
+            for item_y, items_x in zip(self.y_, data[:, features])
+        ]
+        # Store in target_ the features used with class to discretize target
+        self.target_[target] = features + [-1]
+        self.y_join_ = y_join
+        self.discretizer_[target].fit(self.X_[:, target], factorize(y_join))
+        self.cut_points_[target] = self.discretizer_[target].get_cut_points()
+        # return the discretized target variable with the new cut points
+        return np.searchsorted(self.cut_points_[target], self.X_[:, target])
+
+    def get_depths(self):
+        res = [0] * self.n_features_in_
+        for feature in self.features_:
+            res[feature] = self.discretizer_[feature].get_depth()
+        return res

src/fimdlp/tests/FImdlp_test.py

@@ -1,72 +1,57 @@
 import unittest
 import sklearn
-from sklearn.datasets import load_iris
 import numpy as np
+from sklearn.datasets import load_iris
+from sklearn.utils.estimator_checks import check_estimator
+from ..cppfimdlp import CFImdlp, factorize, CArffFiles
 from ..mdlp import FImdlp
-from .. import version
-from .._version import __version__
+from .. import __version__
 
 
 class FImdlpTest(unittest.TestCase):
+    delta = 1e-6  # same tolerance as in C++ code
+
     def test_version(self):
-        self.assertEqual(version(), __version__)
+        clf = FImdlp()
+        self.assertEqual(
+            clf.get_version(),
+            f"{__version__}({CFImdlp().get_version().decode()})",
+        )
+
+    def test_minimum_mdlp_version(self):
+        mdlp_version = tuple(
+            int(c) for c in CFImdlp().get_version().decode().split(".")[0:3]
+        )
+        minimum_mdlp_version = (1, 1, 2)
+        self.assertTrue(mdlp_version >= minimum_mdlp_version)
 
     def test_init(self):
         clf = FImdlp()
         self.assertEqual(-1, clf.n_jobs)
-        self.assertFalse(clf.proposal)
-        clf = FImdlp(proposal=True, n_jobs=7)
-        self.assertTrue(clf.proposal)
+        self.assertEqual(3, clf.min_length)
+        self.assertEqual(1e6, clf.max_depth)
+        clf = FImdlp(n_jobs=7, min_length=24, max_depth=17)
         self.assertEqual(7, clf.n_jobs)
+        self.assertEqual(24, clf.min_length)
+        self.assertEqual(17, clf.max_depth)
 
-    def test_fit_proposal(self):
-        clf = FImdlp(proposal=True)
-        clf.fit([[1, 2], [3, 4]], [1, 2])
-        self.assertEqual(clf.n_features_, 2)
-        self.assertListEqual(clf.X_.tolist(), [[1, 2], [3, 4]])
-        self.assertListEqual(clf.y_.tolist(), [1, 2])
-        self.assertListEqual([[], []], clf.get_cut_points())
+    def test_fit_definitive(self):
+        clf = FImdlp()
         X, y = load_iris(return_X_y=True)
         clf.fit(X, y)
-        self.assertEqual(clf.n_features_, 4)
+        self.assertEqual(clf.n_features_in_, 4)
         self.assertTrue(np.array_equal(X, clf.X_))
         self.assertTrue(np.array_equal(y, clf.y_))
         expected = [
-            [
-                4.900000095367432,
-                5.0,
-                5.099999904632568,
-                5.400000095367432,
-                5.699999809265137,
-            ],
-            [2.6999998092651367, 2.9000000953674316, 3.1999998092651367],
-            [2.3499999046325684, 4.5, 4.800000190734863],
-            [0.75, 1.399999976158142, 1.5, 1.7000000476837158],
+            [5.45, 5.75],
+            [2.75, 2.85, 2.95, 3.05, 3.35],
+            [2.45, 4.75, 5.05],
+            [0.8, 1.75],
         ]
-        self.assertListEqual(expected, clf.get_cut_points())
-        self.assertListEqual([0, 1, 2, 3], clf.features_)
-        clf.fit(X, y, features=[0, 2, 3])
-        self.assertListEqual([0, 2, 3], clf.features_)
-
-    def test_fit_original(self):
-        clf = FImdlp(proposal=False)
-        clf.fit([[1, 2], [3, 4]], [1, 2])
-        self.assertEqual(clf.n_features_, 2)
-        self.assertListEqual(clf.X_.tolist(), [[1, 2], [3, 4]])
-        self.assertListEqual(clf.y_.tolist(), [1, 2])
-        self.assertListEqual([[], []], clf.get_cut_points())
-        X, y = load_iris(return_X_y=True)
-        clf.fit(X, y)
-        self.assertEqual(clf.n_features_, 4)
-        self.assertTrue(np.array_equal(X, clf.X_))
-        self.assertTrue(np.array_equal(y, clf.y_))
-        expected = [
-            [5.5, 5.800000190734863],
-            [3.0999999046325684],
-            [2.450000047683716, 4.800000190734863, 5.099999904632568],
-            [0.800000011920929, 1.7000000476837158],
-        ]
-        self.assertListEqual(expected, clf.get_cut_points())
+        computed = clf.get_cut_points()
+        for item_computed, item_expected in zip(computed, expected):
+            for x_, y_ in zip(item_computed, item_expected):
+                self.assertAlmostEqual(x_, y_, delta=self.delta)
         self.assertListEqual([0, 1, 2, 3], clf.features_)
         clf.fit(X, y, features=[0, 2, 3])
         self.assertListEqual([0, 2, 3], clf.features_)
@@ -87,67 +72,296 @@ class FImdlpTest(unittest.TestCase):
             clf.fit([[1, 2], [3, 4]], [1, 2], features=[0, 2])
 
     def test_fit_features(self):
+        clf = FImdlp(n_jobs=-1)
+        # Two samples doesn't have enough information to split
+        clf.fit([[1, -2], [3, 4]], [1, 2], features=[0])
+        self.assertListEqual(clf.get_cut_points(), [[], []])
+        clf.fit([[1, -2], [3, 4], [5, 6]], [1, 2, 2], features=[0])
+        self.assertListEqual(clf.get_cut_points(), [[2], []])
+        res = clf.transform([[1, -2], [3, 4]])
+        self.assertListEqual(res.tolist(), [[0, -2], [1, 4]])
+        X, y = load_iris(return_X_y=True)
+        X_expected = X[:, [0, 2]].copy()
+        clf.fit(X, y, features=[1, 3])
+        X_computed = clf.transform(X)
+        self.assertListEqual(
+            X_expected[:, 0].tolist(), X_computed[:, 0].tolist()
+        )
+        self.assertListEqual(
+            X_expected[:, 1].tolist(), X_computed[:, 2].tolist()
+        )
+        self.assertEqual(X_computed.dtype, np.float64)
+
+    def test_transform(self):
         clf = FImdlp()
-        clf.fit([[1, 2], [3, 4]], [1, 2], features=[0])
-        res = clf.transform([[1, 2], [3, 4]])
-        self.assertListEqual(res.tolist(), [[0, 2], [0, 4]])
-
-    def test_transform_original(self):
-        clf = FImdlp(proposal=False)
-        clf.fit([[1, 2], [3, 4]], [1, 2])
+        clf.fit([[1, 2], [3, 4], [5, 6]], [1, 2, 2])
         self.assertEqual(
-            clf.transform([[1, 2], [3, 4]]).tolist(), [[0, 0], [0, 0]]
+            clf.transform([[1, 2], [3, 4]]).tolist(), [[0, 0], [1, 1]]
         )
         X, y = load_iris(return_X_y=True)
         clf.fit(X, y)
-        self.assertEqual(clf.n_features_, 4)
+        self.assertEqual(clf.n_features_in_, 4)
         self.assertTrue(np.array_equal(X, clf.X_))
         self.assertTrue(np.array_equal(y, clf.y_))
+        X_transformed = clf.transform(X)
         self.assertListEqual(
-            clf.transform(X).tolist(), clf.fit(X, y).transform(X).tolist()
+            X_transformed.tolist(), clf.fit(X, y).transform(X).tolist()
         )
+        self.assertEqual(X_transformed.dtype, np.int32)
         expected = [
-            [0, 0, 1, 1],
+            [1, 0, 1, 1],
+            [2, 3, 1, 1],
             [2, 0, 1, 1],
-            [1, 0, 1, 1],
             [0, 0, 1, 1],
             [1, 0, 1, 1],
-            [1, 0, 1, 1],
-            [1, 0, 1, 1],
+            [1, 3, 1, 1],
+            [1, 2, 1, 1],
         ]
         self.assertTrue(np.array_equal(clf.transform(X[90:97]), expected))
         with self.assertRaises(ValueError):
             clf.transform([[1, 2, 3], [4, 5, 6]])
         with self.assertRaises(sklearn.exceptions.NotFittedError):
-            clf = FImdlp(proposal=False)
+            clf = FImdlp()
             clf.transform([[1, 2], [3, 4]])
 
-    def test_transform_proposal(self):
-        clf = FImdlp(proposal=True)
-        clf.fit([[1, 2], [3, 4]], [1, 2])
-        self.assertEqual(
-            clf.transform([[1, 2], [3, 4]]).tolist(), [[0, 0], [0, 0]]
+    def test_cppfactorize(self):
+        source = [
+            b"f0",
+            b"f1",
+            b"f2",
+            b"f3",
+            b"f4",
+            b"f5",
+            b"f6",
+            b"f1",
+            b"f1",
+            b"f7",
+            b"f8",
+        ]
+        expected = [0, 1, 2, 3, 4, 5, 6, 1, 1, 7, 8]
+        computed = factorize(source)
+        self.assertListEqual(expected, computed)
+
+    def test_join_fit(self):
+        y = np.array([b"f0", b"f0", b"f2", b"f3", b"f3", b"f4", b"f4"])
+        x = np.array(
+            [
+                [0, 1, 2, 3, 4, 5],
+                [0, 2, 2, 3, 4, 5],
+                [1, 2, 3, 4, 5, 5],
+                [2, 3, 4, 5, 6, 6],
+                [3, 4, 5, 6, 7, 7],
+                [1, 2, 2, 3, 5, 7],
+                [1, 3, 4, 4, 4, 7],
+            ]
         )
+        expected = [0, 1, 1, 2, 2, 1, 2]
+        clf = FImdlp()
+        clf.fit(x, factorize(y))
+        computed = clf.join_fit([0, 2, 3, 4], 1, x)
+        self.assertListEqual(computed.tolist(), expected)
+        expected_y = [
+            b"00234",
+            b"00234",
+            b"11345",
+            b"22456",
+            b"23567",
+            b"31235",
+            b"31444",
+        ]
+        self.assertListEqual(expected_y, clf.y_join_)
+
+    def test_join_fit_error(self):
+        y = np.array([b"f0", b"f0", b"f2", b"f3", b"f4"])
+        x = np.array(
+            [
+                [0, 1, 2, 3, 4],
+                [0, 1, 2, 3, 4],
+                [1, 2, 3, 4, 5],
+                [2, 3, 4, 5, 6],
+                [3, 4, 5, 6, 7],
+            ]
+        )
+        clf = FImdlp()
+        clf.fit(x, factorize(y))
+        with self.assertRaises(ValueError) as exception:
+            clf.join_fit([], 1, x)
+        self.assertEqual(
+            str(exception.exception),
+            "Number of features must be in range [1, 5]",
+        )
+        with self.assertRaises(ValueError) as exception:
+            FImdlp().join_fit([0, 4], 1, x)
+        self.assertTrue(
+            str(exception.exception).startswith(
+                "This FImdlp instance is not fitted yet."
+            )
+        )
+        with self.assertRaises(ValueError) as exception:
+            clf.join_fit([0, 5], 1, x)
+        self.assertEqual(
+            str(exception.exception),
+            "Feature 5 not in range [0, 5)",
+        )
+        with self.assertRaises(ValueError) as exception:
+            clf.join_fit([0, 2], 5, x)
+        self.assertEqual(
+            str(exception.exception),
+            "Target 5 not in range [0, 5)",
+        )
+        with self.assertRaises(ValueError) as exception:
+            clf.join_fit([0, 2], 2, x)
+        self.assertEqual(
+            str(exception.exception),
+            "Target cannot be in features to join",
+        )
+
+    def test_factorize(self):
+        y = np.array([b"f0", b"f0", b"f2", b"f3", b"f4"])
+        clf = FImdlp()
+        computed = clf.factorize(y)
+        self.assertListEqual([0, 0, 1, 2, 3], computed)
+        y = [b"f4", b"f0", b"f0", b"f2", b"f3"]
+        clf = FImdlp()
+        computed = clf.factorize(y)
+        self.assertListEqual([0, 1, 1, 2, 3], computed)
+
+    def test_join_fit_info(self):
+        clf = FImdlp()
         X, y = load_iris(return_X_y=True)
         clf.fit(X, y)
-        self.assertEqual(clf.n_features_, 4)
-        self.assertTrue(np.array_equal(X, clf.X_))
-        self.assertTrue(np.array_equal(y, clf.y_))
-        self.assertListEqual(
-            clf.transform(X).tolist(), clf.fit(X, y).transform(X).tolist()
-        )
-        expected = [
-            [4, 0, 1, 1],
-            [5, 2, 2, 2],
-            [5, 0, 1, 1],
-            [1, 0, 1, 1],
-            [4, 1, 1, 1],
-            [5, 2, 1, 1],
-            [5, 1, 1, 1],
+        clf.join_fit([0, 2], 1, X)
+        clf.join_fit([0, 3], 2, X)
+        clf.join_fit([1, 2], 3, X)
+        expected = [-1, [0, 2, -1], [0, 3, -1], [1, 2, -1]]
+        self.assertListEqual(expected, clf.target_)
+
+    @staticmethod
+    def test_sklearn_transformer():
+        for check, test in check_estimator(FImdlp(), generate_only=True):
+            test(check)
+
+    def test_states_feature(self):
+        clf = FImdlp()
+        X, y = load_iris(return_X_y=True)
+        clf.fit(X, y)
+        expected = []
+        for i in [3, 6, 4, 3]:
+            expected.append(list(range(i)))
+        for feature in range(X.shape[1]):
+            self.assertListEqual(
+                expected[feature], clf.get_states_feature(feature)
+            )
+
+    def test_states_no_feature(self):
+        clf = FImdlp()
+        X, y = load_iris(return_X_y=True)
+        clf.fit(X, y)
+        self.assertIsNone(clf.get_states_feature(4))
+
+    def test_MaxDepth(self):
+        clf = FImdlp(max_depth=1)
+        X, y = load_iris(return_X_y=True)
+        clf.fit(X, y)
+        expected_cutpoints = [
+            [5.45],
+            [3.35],
+            [2.45],
+            [0.8],
         ]
-        self.assertTrue(np.array_equal(clf.transform(X[90:97]), expected))
-        with self.assertRaises(ValueError):
-            clf.transform([[1, 2, 3], [4, 5, 6]])
-        with self.assertRaises(sklearn.exceptions.NotFittedError):
-            clf = FImdlp(proposal=True)
-            clf.transform([[1, 2], [3, 4]])
+        expected_depths = [1] * 4
+        self.assertListEqual(expected_depths, clf.get_depths())
+        for expected, computed in zip(
+            expected_cutpoints, clf.get_cut_points()
+        ):
+            for e, c in zip(expected, computed):
+                self.assertAlmostEqual(e, c, delta=self.delta)
+
+    def test_MinLength(self):
+        clf = FImdlp(min_length=75)
+        X, y = load_iris(return_X_y=True)
+        clf.fit(X, y)
+        expected_cutpoints = [
+            [5.45, 5.75],
+            [2.85, 3.35],
+            [2.45, 4.75],
+            [0.8, 1.75],
+        ]
+        expected_depths = [3, 2, 2, 2]
+        self.assertListEqual(expected_depths, clf.get_depths())
+        for expected, computed in zip(
+            expected_cutpoints, clf.get_cut_points()
+        ):
+            for e, c in zip(expected, computed):
+                self.assertAlmostEqual(e, c, delta=self.delta)
+
+    def test_MinLengthMaxDepth(self):
+        clf = FImdlp(min_length=75, max_depth=2)
+        X, y = load_iris(return_X_y=True)
+        clf.fit(X, y)
+        expected_cutpoints = [
+            [5.45, 5.75],
+            [2.85, 3.35],
+            [2.45, 4.75],
+            [0.8, 1.75],
+        ]
+        expected_depths = [2, 2, 2, 2]
+        self.assertListEqual(expected_depths, clf.get_depths())
+        for expected, computed in zip(
+            expected_cutpoints, clf.get_cut_points()
+        ):
+            for e, c in zip(expected, computed):
+                self.assertAlmostEqual(e, c, delta=self.delta)
+
+    def test_max_cuts(self):
+        clf = FImdlp(max_cuts=1)
+        X, y = load_iris(return_X_y=True)
+        clf.fit(X, y)
+        expected_cutpoints = [
+            [5.45],
+            [2.85],
+            [2.45],
+            [0.8],
+        ]
+        expected_depths = [3, 5, 4, 3]
+        self.assertListEqual(expected_depths, clf.get_depths())
+        for expected, computed in zip(
+            expected_cutpoints, clf.get_cut_points()
+        ):
+            for e, c in zip(expected, computed):
+                self.assertAlmostEqual(e, c, delta=self.delta)
+
+    def test_ArffFiles(self):
+        loader = CArffFiles()
+        loader.load(b"src/cppmdlp/tests/datasets/iris.arff")
+        X = loader.get_X()
+        y = loader.get_y()
+        expected = [
+            (b"sepallength", b"REAL"),
+            (b"sepalwidth", b"REAL"),
+            (b"petallength", b"REAL"),
+            (b"petalwidth", b"REAL"),
+        ]
+        self.assertListEqual(loader.get_attributes(), expected)
+        self.assertListEqual(y[:10], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
+        expected = [
+            b"5.1,3.5,1.4,0.2,Iris-setosa",
+            b"4.9,3.0,1.4,0.2,Iris-setosa",
+            b"4.7,3.2,1.3,0.2,Iris-setosa",
+            b"4.6,3.1,1.5,0.2,Iris-setosa",
+            b"5.0,3.6,1.4,0.2,Iris-setosa",
+            b"5.4,3.9,1.7,0.4,Iris-setosa",
+            b"4.6,3.4,1.4,0.3,Iris-setosa",
+            b"5.0,3.4,1.5,0.2,Iris-setosa",
+            b"4.4,2.9,1.4,0.2,Iris-setosa",
+            b"4.9,3.1,1.5,0.1,Iris-setosa",
+        ]
+        self.assertListEqual(loader.get_lines()[:10], expected)
+        expected_X = [
+            [5.0999999, 3.5, 1.39999998, 0.2],
+            [4.9000001, 3, 1.39999998, 0.2],
+            [4.69999981, 3.20000005, 1.29999995, 0.2],
+        ]
+        for computed, expected in zip(X[:3].tolist(), expected_X):
+            for c, e in zip(computed, expected):
+                self.assertAlmostEqual(c, e, delta=self.delta)