umutoninadege/Age-Standardized-Obesity-Analysis
Domain:
healthcareCreator:
umu
Host:
Obesity trend analysis worldwide (18+) with focus on Rwanda using WHO data — Python + Power BI
# 🥗 Obesity Trend Analysis (18+ Years) – WHO Global Health Observatory
This project presents a comprehensive analysis of the **age-standardized prevalence of obesity among adults (18+ years)**, using data from the **WHO Global Health Observatory**. It focuses on **Rwanda**, with optional global comparison, and combines **Python analytics** and an **interactive Power BI dashboard** to derive actionable health insights.
---
## 🏥 Sector: Health
**Focus Area**: Non-communicable diseases, adult obesity, gender-based analysis, public health forecasting
---
## 📊 Project Objectives
🎯 **Goals:**
* Track historical trends in obesity prevalence (1990–latest)
* Compare obesity levels by gender (MALE, FEMALE, TOTAL)
* Predict future obesity rates for Rwanda (2026–2031)
* Build an interactive Power BI dashboard for decision support
---
## 🌐 Dataset Information
* **Source**: WHO Global Health Observatory
* **Scope**: Global (filtered for Rwanda)
* **Age Group**: 18+ (DIM\_AGE = Y\_GE18)
* **Columns**: Year, Country, Gender, Obesity Rate, Confidence Intervals
* **Status**: Structured CSV, required preprocessing
---
## 🛠️ Tools & Technologies
| Tool | Purpose |
| ----------------------------- | ----------------------------------- |
| Python (VS Code) | Data cleaning, EDA, forecasting |
| Pandas, Seaborn, Scikit-learn | Visualization & regression modeling |
| Power BI | Dashboard & interactive reporting |
| GitHub | Version control & documentation |
---
## 🔬 Methodology
### 1. Load Dataset
Loaded the dataset using Pandas
```python
import pandas as pd
df = pd.read_csv("RELAY_WHS.csv")
# Step 3: Show Basic Info
print("\n--- Dataset Info ---")
print(df.info())
print(df.head())
```
### 2. 🧹 Data Cleaning and Rename columns
```python
import pandas as pd
df.dropna(inplace=True) # Drop missing values
# Rename columns for clarity
df.rename(columns={
" …