Create data/synthetic_data.py

data/synthetic_data.py

@@ -0,0 +1,89 @@
+import pandas as pd
+import numpy as np
+from faker import Faker
+from datetime import datetime, timedelta
+import random
+
+fake = Faker()
+
+class SAPDataGenerator:
+    def __init__(self):
+        self.suppliers = [
+            "Acme Corp", "Global Supplies Inc", "Tech Solutions Ltd", 
+            "Industrial Partners", "Premium Materials Co", "Swift Logistics",
+            "Quality Components", "Reliable Vendors", "Innovative Systems",
+            "Professional Services"
+        ]
+        
+        self.categories = [
+            "Raw Materials", "IT Equipment", "Office Supplies", 
+            "Professional Services", "Maintenance", "Transportation",
+            "Marketing", "Facilities", "Security", "Consulting"
+        ]
+        
+        self.plant_codes = ["1000", "2000", "3000", "4000", "5000"]
+        self.company_codes = ["US01", "DE02", "IN03", "UK04", "SG05"]
+
+    def generate_purchase_orders(self, n=1000):
+        data = []
+        for i in range(n):
+            po_date = fake.date_between(start_date='-2y', end_date='today')
+            delivery_date = po_date + timedelta(days=random.randint(7, 90))
+            
+            unit_price = round(random.uniform(10, 10000), 2)
+            quantity = random.randint(1, 1000)
+            total_value = round(unit_price * quantity, 2)
+            
+            data.append({
+                'PO_Number': f"PO{str(i+1).zfill(8)}",
+                'Supplier': random.choice(self.suppliers),
+                'Category': random.choice(self.categories),
+                'Plant': random.choice(self.plant_codes),
+                'Company_Code': random.choice(self.company_codes),
+                'PO_Date': po_date,
+                'Delivery_Date': delivery_date,
+                'Material': fake.catch_phrase(),
+                'Quantity': quantity,
+                'Unit_Price': unit_price,
+                'Total_Value': total_value,
+                'Currency': 'USD',
+                'Status': random.choice(['Open', 'Delivered', 'Partially Delivered', 'Cancelled']),
+                'Buyer': fake.name(),
+                'Payment_Terms': random.choice(['Net 30', 'Net 60', '2/10 Net 30', 'Immediate']),
+                'Delivery_Performance': round(random.uniform(85, 99), 1)
+            })
+        
+        return pd.DataFrame(data)
+
+    def generate_supplier_performance(self):
+        data = []
+        for supplier in self.suppliers:
+            data.append({
+                'Supplier': supplier,
+                'On_Time_Delivery': round(random.uniform(85, 98), 1),
+                'Quality_Score': round(random.uniform(80, 99), 1),
+                'Cost_Performance': round(random.uniform(90, 99), 1),
+                'Total_Spend_YTD': round(random.uniform(100000, 5000000), 2),
+                'Active_Contracts': random.randint(5, 50),
+                'Risk_Score': random.choice(['Low', 'Medium', 'High']),
+                'Certification_Status': random.choice(['ISO 9001', 'ISO 14001', 'Multiple', 'None'])
+            })
+        
+        return pd.DataFrame(data)
+
+    def generate_spend_analysis(self):
+        months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 
+                 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
+        data = []
+        
+        for month in months:
+            for category in self.categories:
+                data.append({
+                    'Month': month,
+                    'Category': category,
+                    'Spend': round(random.uniform(50000, 500000), 2),
+                    'Budget': round(random.uniform(60000, 550000), 2),
+                    'Variance': round(random.uniform(-10, 15), 1)
+                })
+        
+        return pd.DataFrame(data)