This repository contains a collection of machine learning and data science projects that demonstrate different techniques, workflows, and applications. Each project is built from scratch, following the full pipeline of data preprocessing, analysis, modeling, and evaluation.
- Classification : Predictive models using logistic regression, decision trees, random forests, and SVM.
- Regression : Predicting continuous values with linear regression, ridge/lasso regression, and gradient boosting.
- Clustering : Unsupervised learning with k-means, hierarchical clustering, and DBSCAN.
- Association : Rule Mining Market basket analysis using Apriori, FP-Growth, and ECLAT.
- Data Preprocessing & Feature Engineering : Handling missing values, outliers, normalization, encoding categorical variables, etc.
- Visualization & Insights : Exploratory data analysis with matplotlib, seaborn, and Plotly.
- Languages : Python
- Libraries : scikit-learn, pandas, numpy, matplotlib, seaborn, PyECLAT, mlxtend, TensorFlow/PyTorch (for DL tasks)
- Tools : Jupyter Notebook, Git, Streamlit (for interactive dashboards)
- Demonstrate understanding of ML workflows from raw data to insights.
- Apply both classical algorithms and modern techniques.
- Build reusable templates for future applied projects.
1. Clone the repository: git clone https://github.com/serghine-abdelillah/MachineLearning-Projects.git.
2. Navigate to a project folder and open the notebook: jupyter notebook.
3. Run the cells to reproduce results.