Logo Lanfrica

ABdohenedi19/egypt-food-prices-analysis

Domaine:

agriculturesocioeconomic

Type de record:

project
Créateur:
ABd
Hôte:
Data science project analyzing food prices in Egypt # Egypt Food Prices Analysis 🇪🇬 ## Project Goal Analyze food price trends in Egypt and build a model to predict prices. ## Dataset - Source: CAPMAS, Central Agency for Public Mobilization and Statistics, IDSC, Information Decision Support Center, Information Decision Support Center of the Cabinet, Information Decision Support Center of the Cabinet www.agriprice.idsc.net - This dataset contains Food Prices data for Egypt, sourced from the World Food Programme Price Database. The World Food Programme Price Database covers foods such as maize, rice, beans, fish, and sugar for 98 countries and some 3000 markets. It is updated weekly but contains to a large extent monthly data. The data goes back as far as 1992 for a few countries, although many countries started reporting from 2003 or thereafter - link : data.humdata.org ## Steps ### 1️⃣ Data Collection & Integration The foundation was established by merging primary data sources to create a unified geographical context. * **Data Sources:** Merged historical price records with the `Markets Lookup` table. * **Integration:** Performed a **Left Join** on `market_id` to map every price entry to its specific Governorate. * **Imputation:** Resolved "National Average" entries by assigning them to a dedicated "National" category to maintain data continuity. ### 2️⃣ Advanced Data Augmentation (Synthetic Data) To increase dataset volume and complexity for deep learning, we implemented a custom augmentation engine. * **Category-Based Behavior:** Modeled price volatility based on food types (e.g., highly volatile Meat vs. stable Cereals). * **Stochastic Dynamics:** Introduced random price fluctuations to mimic real-world supply and demand shifts. * **Outlier Injection:** Injected a 2% noise factor to simulate economic anomalies (hyperinflation/shocks), making future models more **Robust**. ### 3️⃣ Data Preprocessing (The Engine) ⚙️ We transformed raw records into a structured, model-r …