Mugambi645/food-security

Analysing food security in kenya # 🏡 Food Security Analysis in Kenya This project provides a Streamlit web application for analyzing food security in Kenyan households using a provided dataset. It covers data loading, preprocessing, statistical analysis, and predictive modeling for the Household Food Insecurity Access Scale (HFIAS). ## 🚀 Features * **Data Loading:** Upload SPSS (.sav) files for analysis. * **Data Preprocessing:** * Handling of missing values using mode imputation. * Conversion of specific string codes (e.g., '888') to missing values (`NaN`). * Outlier detection (using IQR method). * One-Hot Encoding for categorical features. * **Statistical Analysis:** * Correlation analysis and visualization (heatmap). * **Predictive Modeling:** * Random Forest Regressor to predict Household Food Insecurity Access Scale (HFIAS). * Model evaluation metrics (R-squared, MAE, RMSE, MAPE, Percentage Accuracy). * Feature importance analysis. ## 📦 Installation 1. **Clone the repository (or download the `app.py` file):** ```bash git clone # Replace with your repository URL if hosted cd food-security-app # Or wherever your app.py is located ``` 2. **Create a virtual environment (recommended):** ```bash python3 -m venv venv source venv/bin/activate # On Windows: .\venv\Scripts\activate ``` 3. **Install the required packages:** ```bash pip install streamlit pandas numpy matplotlib seaborn scikit-learn pyreadstat scipy ``` *(Note: You might need to install `ipykernel` if you encounter issues related to Jupyter notebooks, though it's not strictly necessary for the Streamlit app itself.)* ## 🏃‍♀️ How to Run 1. **Navigate to the project directory** in your terminal where `app.py` is located. 2. **Ensure your virtual environment is activated** (if you created one). 3. **Run the Streamlit application:** ```bash streamlit run app.py ``` 4. Your browser will automatically open to the Streamlit app (usually at `localhost`). ## 📁 Data The application expects an SPSS (`.sav`) file as inp …