import pandas as pd
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
from scipy import sparse

# Load the purchase history data from Excel file and convert Purchase_Date to datetime
purchase_history = pd.read_excel('datasetsample.xlsx', sheet_name='Transaction History', 
                               parse_dates=['Purchase_Date'])  # Add this parameter

# Ensure Customer_Id is treated as string
purchase_history['Customer_Id'] = purchase_history['Customer_Id'].astype(str)

# Create a dictionary to store product categories
product_categories = purchase_history[['Product_Id', 'Category']].drop_duplicates().set_index('Product_Id')['Category'].to_dict()

# Count the number of purchases for each user and product combination
purchase_counts = purchase_history.groupby(['Customer_Id', 'Product_Id']).size().unstack(fill_value=0)

# Convert the purchase counts to a sparse matrix
sparse_purchase_counts = sparse.csr_matrix(purchase_counts)

# Compute the cosine similarity matrix between the products
cosine_similarities = cosine_similarity(sparse_purchase_counts.T)

def get_customer_items_and_recommendations(user_id, n=5):
    """
    Get both purchased items and recommendations for a user
    
    Parameters:
    user_id (str): The customer ID as string
    n (int): Number of recommendations to return
    
    Returns:
    tuple: (purchased_items_info, recommended_items_info)
    """
    # Convert user_id to string if it's not already
    user_id = str(user_id)
    
    # Check if user exists in the data
    if user_id not in purchase_counts.index:
        return [], []
    
    # Get purchased items
    purchased_items = list(purchase_counts.columns[purchase_counts.loc[user_id] > 0])
    
    # Get purchased items details
    purchased_items_info = []
    user_purchases = purchase_history[purchase_history['Customer_Id'] == user_id]
    for item in purchased_items:
        item_purchases = user_purchases[user_purchases['Product_Id'] == item]
        total_amount = item_purchases['Amount (In Dollars)'].sum()
        last_purchase = pd.to_datetime(item_purchases['Purchase_Date'].max())  # Ensure datetime
        category = product_categories.get(item, 'Unknown')
        purchased_items_info.append({
            'product_id': item,
            'category': category,
            'total_amount': total_amount,
            'last_purchase': last_purchase
        })
    
    # Get the user's index in the matrix
    user_idx = purchase_counts.index.get_loc(user_id)
    
    # Get the user's purchase history
    user_history = sparse_purchase_counts[user_idx].toarray().flatten()

    # Compute similarities and get recommendations
    similarities = cosine_similarities.dot(user_history)
    purchased_indices = np.where(user_history > 0)[0]
    similarities[purchased_indices] = 0
    recommended_indices = np.argsort(similarities)[::-1][:n]
    recommended_items = list(purchase_counts.columns[recommended_indices])
    
    # Remove any purchased items from recommendations
    recommended_items = [item for item in recommended_items if item not in purchased_items]
    
    # Get recommended items details
    recommended_items_info = [
        {
            'product_id': item,
            'category': product_categories.get(item, 'Unknown')
        }
        for item in recommended_items
    ]

    return purchased_items_info, recommended_items_info

def display_customer_profile(user_id, n=5):
    """
    Display customer's purchase history and recommendations with categories
    
    Parameters:
    user_id (str): The customer ID as string
    n (int): Number of recommendations to return
    """
    purchased_items_info, recommended_items_info = get_customer_items_and_recommendations(user_id, n)
    
    print(f"\nCustomer Profile for {user_id}")
    print("-" * 70)
    
    print("\nPurchase History:")
    if purchased_items_info:
        print(f"{'Product ID':<15} {'Category':<20} {'Total Amount':>12} {'Last Purchase'}")
        print("-" * 70)
        for item in purchased_items_info:
            print(f"{item['product_id']:<15} {item['category']:<20} ${item['total_amount']:>11.2f} {item['last_purchase'].strftime('%Y-%m-%d')}")
    else:
        print("No purchase history found")
    
    print("\nRecommended Items:")
    if recommended_items_info:
        print(f"{'Product ID':<15} {'Category':<20}")
        print("-" * 35)
        for item in recommended_items_info:
            print(f"{item['product_id']:<15} {item['category']:<20}")
    else:
        print("No recommendations available")
    
    print("-" * 70)

# Example usage:
customer_id = 'CUST2025A'  # Replace with your actual customer ID
display_customer_profile(customer_id)