IMMO-ELIZA-ML

🧐 Description

In the Immo-Eliza-ML project we will build a performant machine learning model to predict prices of real estate proporties in Belgium. This involves cleaning the dataset, preprocessing, model training, model evaluation and iteration.

📦 Repo structure

├── data\
│   ├── cleaned_properties.csv
│   └── properties.csv
│
├── drafts\
│   ├── 1. cleaning.ipynb
│   ├── 2. preprocessing.ipynb
│   ├── 3. model_training_test.ipynb
│   ├── 4. SimpleLinReg.ipynb
│   ├── 5. MultipleLinReg.ipynb
│   ├── 6. RandomForestReg.ipynb
│   ├── 7. functions.ipynb
│   └── 8. functions_cleaned.ipynb
│
├── in_progress\
│   ├── 1. train.ipynb
│   └── 2. predict.ipynb
│
├── models\
│   ├── MultipleLinReg.ipynb
│   └── RandomForestReg.ipynb
│
├── src\
│   └── .jpg
│
├── .gitignore
├── MODELSCARD.md
├── README.md
└── requirements.txt

🏁 Getting Started

📚 Prerequisities

To run the project, you need to install the required libraries.

You can click on the badge links to learn more about each library and its specific version used in this project. You can install them manually using pip install or just running pip install -r requirements.txt.

Install the required libraries:

• 
• 
• 
• 
• 
• 

⚙️ Installation

1. Clone the repository:

   git clone https://github.com/fabienne088/immo-eliza-ml.git

2. Navigate to the project directory:

   cd IMMO-ELIZA-ML

3. You're all set! You can now explore the notebooks in the drafts and models directories and work with the data in the data directory. Enjoy!

🎈 Usage

To use this repository, follow these steps:

1. Clone the Repository:

   • Clone the repository to your local machine using the following command:

   git clone https://github.com/fabienne088/immo-eliza-ml.git

2. Navigate to the Project Directory:

   • Once cloned, navigate to the project directory:

   cd IMMO-ELIZA-ML

3. Explore drafts Notebooks:

   • The drafts directory contains Jupyter notebooks (*.ipynb) where you can see step by step cleaning, splitting and preprocessing of the data. Inluding try-outs of model training and evalution. Open these notebooks in Jupyter Notebook or JupyterLab to view the regression analyses, model trainings and results.

4. Access models:

   • The models directory contains a LinearRegression and a RandomForestRegression model. Including training, prediction and evaluation.

5. Work with Data:

   • The data directory contains the dataset used for preprocessing. You can find both original and clean versions of the dataset. Explore the data files to understand their structure and contents.

⏱️ Timeline

This project took form in six days.

📌 Personal Situation

This project was made as part of the AI Bootcamp at BeCode.