Read this in other languages: English, Português.
Welcome to the PatternExtractor project, organized by Professor Daniel Ferreira at IFCE.
The PatternExtractor project is a part of the Programming Lab for the second semester of 2023. The goal of this project is to develop an AI-based solution for extracting and analyzing patterns from datasets.
The primary objective of PatternExtractor is to create a tool that can automatically identify and extract meaningful patterns from medical datasets.
Note: Although great accuracy is encouraged, we won't be avaliated in the "AI part of the code". We will be using mainly C and Weka.
Weka is an open-source software suite designed for data mining and machine learning tasks developed at the University of Waikato, New Zealand.
More about it in here: WEKA
Ensure you have the following prerequisites installed on your system:
- Linux is recommended.
Follow these steps to execute the code:
-
Step 1: Clone the repository to your local machine.
git clone https://github.com/maripasa/PatternExtractor.git
-
Step 2: Navigate to the project directory.
cd PatternExtractor
-
Step 3: Run the program.
# Example command to run SCM_Extractor ./bin/SCM_Extractor.exe <CursorFilterSize> <QuantizationLevels> <InputDirectory> <OutputDirectory>
If you encounter any issues during execution, consider the following:
-
Recompile using Makefile for maximum compatibility.
For Unix:
make clean-unix make
For Windows:
make clean-windows make
-
/bin
: Source code files -
/data
: Dataset files and output files/features_output
: Features output/oncotex_pgm
: PGM images dataset
-
/demos
: Not main code related files files/snippets
: Teacher's original codes/tests
: Old small tests
-
/docs
: Test files and suitesFinalProject.pdf
: Project instructionsRelatorioFinal.docx
: Final report docxRelatorioFinal.pdf
: Final report pdf
-
/include
: Header files -
/obj
: Compiled object files -
/src
: Source code -
README.en.md
: English README -
README.md
: Portuguese README
The PatternExtractor project has as main contributors: