Dagmawi-Y/Food_price_analysis-Ethiopian_Story
Domain:
agricultureCreator:
Dag
Host:
A food price analysis and predictive modelling made for Ethiopia using WFP's world food price database published in 2021.
# Food Security Analysis in Ethiopia using WFP Data and Power BI
---
This project explores food security challenges in Ethiopia using data from the WFP Food Prices Database and visualizations developed in Power BI.
## Project Goals:
- Understand inflation trends in staple food prices across different regions in Ethiopia.
- Analyze regional price disparities and market integration within the Ethiopian market system.
- Develop predictive models for forecasting food prices in Ethiopia.
## Data and Tools:
- **Data:** WFP Food Prices Database ~ 1.5M Records (Ethiopian subset)
- **Database:** PostgreSQL
- **Analysis:** Python (Jupyter Notebooks)
- **Visualization:** Power BI
## Key Findings:
- Analyzed inflation trends for key commodities in different regions of Ethiopia.
- Visualized regional price disparities to identify areas with higher food insecurity risk.
- Assessed market integration between Ethiopian markets for specific commodities.
- Developed predictive models for food price forecasting in Ethiopia.
## Project Structure:
- **data source:** Raw and processed data file.
- **notebook:** Jupyter notebooks for data cleaning, analysis, and visualization preparation.
- **scripts in notebook:** Python scripts for database interaction and tasks.
- **powerbi pdf report:** Power BI report files (.pbix) with visualizations focused on Ethiopia.
- **powerbi projects:** Additional notes and documentation related to the project.
## How to Run:
1. Install required libraries in ***group_project.ipynb***.
2. Extract ***wfp_food_prices_database.rar*** and import the dataset to the notebook. (see the steps in the notebook).
3. Set up a PostgreSQL database ***wfp***, open the database server for connection.
4. Run Jupyter notebook cells for data processing and analysis.
5. Run the cell which will create the database schema in postgresql and create the pipeline with the database server.
6. Open Power BI report files and connect to the database. use ***DirectQuery*** mode f …