import numpy as np
import pandas as pd

# Load customer data
customer_data = pd.read_csv('customer_data.csv')

# Analyze customer journey
customer_journey = customer_data.groupby('customer_id')['purchase_date'].agg(list)

# Calculate Lifetime Value (LTV)
customer_revenue = customer_data.groupby('customer_id')['order_value'].sum()
customer_lifespan = customer_journey.apply(lambda x: (max(x) - min(x)).days / 365)
ltv = (customer_revenue / customer_lifespan).mean()

# Enhance customer journey
customer_journey['time_between_purchases'] = customer_journey['purchase_date'].apply(lambda x: [y - x[i-1] for i, y in enumerate(x[1:], start=1)])
customer_journey['avg_time_between_purchases'] = customer_journey['time_between_purchases'].apply(lambda x: np.mean(x))

# Optimize for conversion rate
product_data = pd.read_csv('product_data.csv')
product_conversion_rate = product_data.groupby('product_id')['purchased'].mean()

# Foster repeat purchases
customer_journey['repeat_purchases'] = customer_journey['purchase_date'].apply(lambda x: len(x) - 1)
customer_journey['repeat_purchase_rate'] = customer_journey['repeat_purchases'] / customer_journey['repeat_purchases'].max()

# Combine insights
customer_insights = pd.concat([customer_revenue, customer_lifespan, customer_journey['avg_time_between_purchases'], product_conversion_rate, customer_journey['repeat_purchase_rate']], axis=1)
customer_insights.columns = ['Customer LTV', 'Customer Lifespan', 'Avg Time Between Purchases', 'Product Conversion Rate', 'Repeat Purchase Rate']

# Provide recommendations
print('Recommendations:')
print('- Focus on products with high conversion rates to improve overall conversion')
print('- Identify customers with high repeat purchase rates and target them for loyalty programs')
print('- Analyze the customer journey to identify ways to reduce the average time between purchases')