Richard-Gidi/Cannabis_Prediction

A machine learning model to predict the use of cannabis amongst university students in Ghana # Cannabis Use Prediction Project ## Overview This project aims to predict cannabis use among university students in Ghana. Using data analysis and machine learning techniques, the goal is to build a model that identifies factors influencing cannabis use and provides valuable insights for intervention and support programs. ## Dataset The dataset contains various features related to student demographics, lifestyle, and social behaviors. Data preprocessing steps included handling missing values, encoding categorical variables, and normalizing numerical features. ## Tools & Technologies - **Python** - **Pandas** for data manipulation - **NumPy** for numerical computations - **Scikit-learn** for machine learning models - **Matplotlib** and **Seaborn** for data visualization - **Jupyter Notebook** for interactive development ## Model Building The following machine learning models were explored: 1. **Logistic Regression** 2. **Random Forest** 3. **Gradient Boosting** 4. **Neural Networks** The models were evaluated using metrics like accuracy, precision, recall, and F1 score. ## Results The best-performing model was Logitic Regression achieved an accuracy of **87%** with an F1 score of **85%**. Key features influencing cannabis use included **[Friends use of cannabis]**, **[Social life effect]** etc. ## How to Run 1. **Clone the repository** ```bash git clone