DataDynamos

Analytics and Application Group Project

Welcome to the DataDynamos project! This repository contains all the code and models developed as part of our data science project, covering data preparation, analysis, and prediction.

---

Table of Contents

1. Project Overview
2. Getting Started
3. Environment Setup
4. Project Contributors

---

Project Overview

We have provided all our code and models within a single, comprehensive Jupyter Notebook file: DataScience.ipynb. This notebook is a collectionof code and showcases the entire process, including:

• Data Preparation: Loading, cleaning, and preprocessing data for analysis.
• Data Analysis: Exploratory data analysis and visualization (differentiation of sites, kpis, clustering).
• Data Prediction: Building and evaluating predictive models.

The notebook is designed for easy navigation, providing some explanations and visual outputs at each stage.

---

Getting Started

To run the notebook and replicate our results, follow these steps:

1. Clone this repository:

   git clone https://github.com/Zeyd263/DataDynamos.git
   cd DataDynamos

2. Ensure you have conda installed on your system to manage dependencies.

---

Environment Setup

We have included an environment file (environment.yml) to simplify dependency management. This file ensures that all necessary packages are correctly installed.

Steps to set up the environment:

1. Create and activate the environment:

   conda env create -f environment.yml
   conda activate Dynamos

2. Launch Jupyter Notebook:

   jupyter notebook DataScience.ipynb

This will load the environment Dynamos with all required dependencies.

---

Project Contributors

This project is part of a university group project created for the course Analytics and Applications (AA) by the following contributors:

• Abdesselam Zeyd Boutchich
• Carlotta May
• Marlon Spiess
• Steffen Niesmann
• Yakup Kula

---

Have fun exploring our project!