Add sample data generator and CSV templates for fraud detection modules

- Created create_samples.py script to generate test data
- Generated sample CSV files for all fraud detection modules:
* sample_transactions.csv - Transaction fraud data with anomalies
* sample_kyc.csv - KYC customer data with duplicate/invalid records
* sample_sanctions.csv - Sanctions watchlist for screening
* sample_customers.csv - Customer list for sanctions screening
* sample_credit.csv - Credit risk profiles with high-risk indicators
- Updated requirements.txt with necessary dependencies
- Ready for immediate testing and demonstration

create_samples.py

@@ -0,0 +1,133 @@
+# Create sample CSV files for testing the fraud detection modules
+import pandas as pd
+import numpy as np
+from datetime import datetime, timedelta
+
+# 1. Sample Transaction Data
+def create_transaction_sample():
+    np.random.seed(42)
+    data = {
+        'transaction_id': [f'TXN_{i:06d}' for i in range(1, 1001)],
+        'customer_id': [f'CUST_{i:04d}' for i in np.random.randint(1, 501, 1000)],
+        'amount': np.random.exponential(100, 1000),
+        'merchant_category': np.random.choice(['GROCERY', 'GAS', 'RESTAURANT', 'ONLINE', 'HIGH_RISK', 'ATM'], 1000),
+        'timestamp': pd.date_range(start='2024-01-01', periods=1000, freq='H'),
+        'currency': 'USD'
+    }
+    
+    # Add some fraudulent patterns
+    fraud_indices = np.random.choice(1000, 50, replace=False)
+    data['amount'][fraud_indices] = np.random.uniform(15000, 50000, 50)  # Large amounts
+    
+    # Add negative amounts (errors)
+    error_indices = np.random.choice(1000, 10, replace=False)
+    data['amount'][error_indices] = -np.random.uniform(100, 1000, 10)
+    
+    df = pd.DataFrame(data)
+    df.to_csv('sample_transactions.csv', index=False)
+    return df
+
+# 2. Sample KYC Data
+def create_kyc_sample():
+    np.random.seed(42)
+    names = ['John Smith', 'Jane Doe', 'Michael Johnson', 'Sarah Wilson', 'David Brown', 
+             'JOHN SMITH', 'Test123', 'A B', 'Maria Garcia', 'James Miller']
+    
+    data = {
+        'customer_id': [f'CUST_{i:04d}' for i in range(1, 101)],
+        'name': np.random.choice(names, 100),
+        'email': [f'user{i}@email.com' for i in range(1, 101)],
+        'phone': [f'+1555{i:07d}' for i in range(1, 101)],
+        'dob': pd.date_range(start='1950-01-01', end='2005-12-31', periods=100).strftime('%Y-%m-%d'),
+        'address': [f'{i} Main St, City, State' for i in range(1, 101)]
+    }
+    
+    # Add duplicates
+    data['email'][5:10] = 'duplicate@email.com'
+    data['phone'][15:18] = '+15551234567'
+    
+    # Add invalid DOBs
+    data['dob'][20] = '2030-01-01'  # Future date
+    data['dob'][21] = 'invalid-date'  # Invalid format
+    data['dob'][22] = '1900-01-01'  # Very old
+    
+    df = pd.DataFrame(data)
+    df.to_csv('sample_kyc.csv', index=False)
+    return df
+
+# 3. Sample Sanctions List
+def create_sanctions_sample():
+    sanctions_data = {
+        'name': [
+            'John Doe', 'Jane Smith', 'Vladimir Putin', 'Kim Jong Un',
+            'Alexander Petrov', 'Maria Gonzalez', 'Ahmed Hassan',
+            'Natasha Volkov', 'Carlos Rodriguez', 'Wei Zhang'
+        ],
+        'list_type': [
+            'OFAC', 'EU', 'UN', 'UN', 'OFAC', 'EU', 'OFAC', 'EU', 'OFAC', 'UN'
+        ],
+        'date_added': pd.date_range(start='2020-01-01', periods=10, freq='30D')
+    }
+    
+    df = pd.DataFrame(sanctions_data)
+    df.to_csv('sample_sanctions.csv', index=False)
+    return df
+
+# 4. Sample Customer List for Sanctions Screening
+def create_customer_sample():
+    np.random.seed(42)
+    customer_names = [
+        'John Doe', 'Alice Johnson', 'Bob Wilson', 'Jane Smith',
+        'Michael Brown', 'Sarah Davis', 'Vladimir Putin', 'Emily Chen',
+        'David Miller', 'Lisa Anderson', 'Ahmed Hassan', 'Maria Lopez'
+    ]
+    
+    data = {
+        'customer_id': [f'CUST_{i:04d}' for i in range(1, 101)],
+        'name': np.random.choice(customer_names, 100),
+        'dob': pd.date_range(start='1950-01-01', end='2000-12-31', periods=100).strftime('%Y-%m-%d'),
+        'country': np.random.choice(['USA', 'UK', 'Canada', 'Germany', 'France'], 100)
+    }
+    
+    df = pd.DataFrame(data)
+    df.to_csv('sample_customers.csv', index=False)
+    return df
+
+# 5. Sample Credit Risk Data
+def create_credit_sample():
+    np.random.seed(42)
+    data = {
+        'customer_id': [f'CUST_{i:04d}' for i in range(1, 201)],
+        'credit_score': np.random.normal(700, 100, 200).astype(int),
+        'utilization_rate': np.random.beta(2, 5, 200),
+        'debt_to_income': np.random.beta(2, 3, 200),
+        'income': np.random.lognormal(10.5, 0.5, 200).astype(int),
+        'recent_defaults': np.random.poisson(0.1, 200),
+        'credit_history_length': np.random.randint(1, 30, 200)
+    }
+    
+    # Create some high-risk profiles
+    high_risk_indices = np.random.choice(200, 30, replace=False)
+    data['credit_score'][high_risk_indices] = np.random.randint(300, 600, 30)
+    data['utilization_rate'][high_risk_indices] = np.random.uniform(0.8, 1.0, 30)
+    data['debt_to_income'][high_risk_indices] = np.random.uniform(0.4, 0.8, 30)
+    
+    df = pd.DataFrame(data)
+    df.to_csv('sample_credit.csv', index=False)
+    return df
+
+# Create all sample files
+if __name__ == "__main__":
+    print("Creating sample CSV files...")
+    create_transaction_sample()
+    create_kyc_sample() 
+    create_sanctions_sample()
+    create_customer_sample()
+    create_credit_sample()
+    print("Sample files created successfully!")
+    print("\nFiles created:")
+    print("- sample_transactions.csv")
+    print("- sample_kyc.csv") 
+    print("- sample_sanctions.csv")
+    print("- sample_customers.csv")
+    print("- sample_credit.csv")