Retaining Wall Stability Analysis Tool

This project is a desktop application that uses various machine learning models to predict the geotechnical factor of safety for retaining walls. It allows users to input wall geometry and soil parameters and provides an instant prediction using a selected model.

✨ Features

• 15+ Machine Learning Models: A wide range of models, from OLS to XGBoost and CatBoost.
• Visual Interface: Instantly draws the wall cross-section based on the input parameters.
• Multi-Language Support: Interface available in both Turkish and English.
• Model Information: Detailed information about each model's history, equation, and parameters.
• Performance Metrics: View the training and testing metrics for the selected model.

⚙️ Installation and Usage

Requirements

• Python 3.8 or higher

• pip (Python package installer)

• The following Python libraries:

  • numpy
  • pandas
  • scikit-learn
  • customtkinter
  • joblib
  • xgboost, lightgbm, catboost (for specific models)
  • matplotlib (if used for plotting)

  Note: tkinter, warnings, json, and logging are part of the Python standard library and do not need to be installed separately.

Installation Steps

1. Clone the repository:

   git clone [https://github.com/kullaniciadi/Geo5-Fss-Predictor.git](https://github.com/kullaniciadi/Geo5-Fss-Predictor.git)
   cd Geo5-Fss-Predictor

2. Install the required packages: The best way is to use the requirements.txt file.

   pip install -r requirements.txt

   If a requirements.txt file is not available, you can install the core packages manually:

   pip install numpy pandas scikit-learn customtkinter joblib

3. Verify the project structure: Ensure that the necessary files and folders are in place:

   • The Language folder must exist and contain the .json translation files.
   • The saved_models folder must exist and contain the .pkl model files.
   • The files scaling_factors.csv, model_scaling_info.csv, and all_models_random_search_results.csv must be present in the root directory.

Running the Application

To start the program, run the following command from the project's root directory:

python multilanguage.py