• 👀 I’m interested in data science and data engineering.
• I’m currently learning data engineering, focusing on:
• Programming languages: Python, SQL
• Big data technologies: Hadoop, Spark
• Data warehousing: Amazon Redshift, Google BigQuery
• Data visualization: Tableau, Power BI
• 💼 I’m passionate about turning data into actionable insights and building efficient data pipelines.
• I’m looking to collaborate on projects involving:
• Data analysis and visualization
• Building and optimizing data pipelines
• Implementing machine learning models
• 📫 How to reach me:
  • Email: [email protected]
  • LinkedIn: linkedin.com/in/abdeladime2003
• Pronouns: He/Him

• Programming Languages: Python, SQL
• Data Warehousing: Amazon Redshift, Google BigQuery
• Data Visualization: Tableau, Power BI
• Machine Learning: Scikit-learn, TensorFlow

Our project integrates key processes essential for data scientists:

1. Data Acquisition: Web scraping of Transfermarkt and FIFA Stats websites.
2. Data Manipulation and Preprocessing: Constructing a predictive model using techniques like linear regression.
3. Model Deployment: Using Streamlit to develop an application allowing interactive feature adjustments and player fee predictions.

Project Structure:

• python_project: Contains the main Python code.
  • step1: Initial steps, including data preprocessing and web scraping notebooks.
  • step2: Intermediate steps with model training.
  • step3: Final steps with data preprocessing class, video demonstration, and website interface.

Directories:

• data: Contains CSV files with datasets.
• virtuel_environement: Virtual environment setup files.

Usage:

1. Clone the repository: git clone https://github.com/votre-nom-utilisateur/projet_baina.git
2. Install virtual environment: python -m venv venv
3. Activate virtual environment: venv\Scripts\activate
4. Install dependencies: pip install -r requirements.txt
5. Navigate and execute scripts or notebooks within the python_project directory.

Dependencies: Ensure required dependencies from virtuel_environement/requirements.txt are installed.

Project Demonstration: Google Drive Link

A Java and JavaFX application to manage football-related entities such as teams, transfers, and competitions.

Main Features:

1. Team Management: Add, modify, and delete teams; view team details.
2. Transfer Management: Track player transfers, including details like amounts and dates.
3. Competition Management: Create, schedule, and manage football competitions; view match results and team statistics.
4. User-Friendly Interface: Four graphical windows (CompetitionWindow, EquipeWindow, TransfertWindow, LoginWindow) and a main coordination window.

Technologies Used:

• Programming Language: Java
• Graphical Library: JavaFX

Personal portfolio showcasing skills, projects, and contact information.

Project Structure:

• Html_file: Contains HTML files for each page (Contact-Me.html, My_profile.html, etc.).
• Css_File: Contains CSS files for styling each page (Acceuil.css, Contact-Me.css, etc.).
• Icon and images: Contains images and icons used in the pages.
• Main_File: Main HTML file to start the portfolio.
• Demo.txt: Link to video demonstration on Google Drive.

Usage: Open the main HTML file in any HTML5-compatible web browser.

Developing a robust machine learning model using LightGBM for predicting stock prices based on historical data.

Key Features:

• Utilizes LightGBM for regression tasks.
• Implements advanced data preprocessing techniques.
• Generates key indicators like spread, mid-price, and RSI for feature engineering.
• Visualizes correlations and feature importances.

Getting Started:

1. Clone the repository: git clone https://github.com/abdeladime2003/Optiver-Trading-at-the-close.git
2. Install dependencies: pip install -r requirements.txt
3. Explore the Jupyter notebooks in the Stormy directory.

Files Structure:

• data: Contains the link to download the data.
• Stormy: Includes Jupyter notebooks for data preprocessing, model training, and evaluation.

License: This project is licensed under the MIT License.

Acknowledgments: Thanks to the open-source community and the developers of LightGBM.