generate_mock_data.py

import json
import random

donors = ["United States", "Germany", "United Kingdom", "Japan", "France", "Canada", "Sweden", "Norway", "Australia", "Netherlands"]
recipients = ["India", "Afghanistan", "Ukraine", "Kenya", "Nigeria", "Ethiopia", "Bangladesh", "Vietnam", "Pakistan", "Tanzania", "DR Congo", "Syria"]
sectors = ["Health", "Education", "Infrastructure", "Humanitarian Aid", "Agriculture", "Governance"]

data = []

# Generate consistent flows
for donor in donors:
    # Each donor gives to 3-8 recipients
    my_recipients = random.sample(recipients, k=random.randint(3, 8))
    for recipient in my_recipients:
        # Generate yearly data
        for year in range(2018, 2024):
            # Base amount with some variance
            base_amount = random.randint(10, 500) * 1000000 # 10M to 500M
            
            # Split into sectors
            amount_remaining = base_amount
            for i, sector in enumerate(sectors):
                if amount_remaining <= 0: break
                
                if i == len(sectors) - 1:
                    amount = amount_remaining
                else:
                    amount = random.randint(0, amount_remaining)
                
                if amount > 0:
                    data.append({
                        "id": f"{donor}-{recipient}-{year}-{sector}",
                        "donor": donor,
                        "recipient": recipient,
                        "year": year,
                        "amount": amount,
                        "sector": sector
                    })
                amount_remaining -= amount

with open("aid_data.json", "w") as f:
    json.dump(data, f, indent=2)

print(f"Generated {len(data)} records in aid_data.json")