# Suppress warning messages for a clean workspace
import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)

# Data setup (Groceries Dataset)
import pandas as pd
import kagglehub, os
path = kagglehub.dataset_download('heeraldedhia/groceries-dataset')
files = os.listdir(path)
csv_file = [f for f in files if f.endswith('.csv')][0]
df = pd.read_csv(os.path.join(path, csv_file))
print(df.shape)
print(df.head(3))

# Basic info: columns, types, and non-null values
df.info()

# Quick look at unique values for item and members
print("Unique items:", df['itemDescription'].nunique())
print("Unique customers:", df['Member_number'].nunique())

# Are there missing values?
print(df.isnull().sum())

# How many items does each customer buy per trip?
basket_sizes = df.groupby(['Member_number']).size()
print(basket_sizes.describe())

# What is the most popular item?
top_items = df['itemDescription'].value_counts().head(5)
print(top_items)

# How many total transactions (shopping trips) are there?
num_transactions = df.groupby(['Member_number', 'Date']).ngroups
print("Total shopping trips:", num_transactions)

# Summary stats for basket sizes
print("Count, Mean, Std, Min, 25%, 50%, 75%, Max:")
print(basket_sizes.describe())

# What day do people shop the most?
busy_days = df['Date'].value_counts().sort_values(ascending=False).head(3)
print(busy_days)

# Visualize basket size distribution
import matplotlib.pyplot as plt
plt.figure(figsize=(6,3))
basket_sizes.plot(kind='hist', bins=range(1,16), color='skyblue', edgecolor='black')
plt.title('Number of Items per Shopping Trip')
plt.xlabel('Number of Items')
plt.ylabel('Number of Trips')
plt.tight_layout()
plt.show()

# Find the median number of items bought per customer overall
median_basket = basket_sizes.groupby('Member_number').median()
print(median_basket.describe())

# Top 3 items for a specific customer
customer_id = int(input("Enter a customer number, e.g. 1808: "))
top_for_customer = df[df['Member_number'] == customer_id]['itemDescription'].value_counts().head(3)
print(top_for_customer)

# Build a table: each customer's average basket size
avg_basket_size = basket_sizes.groupby('Member_number').mean()
avg_basket_size = avg_basket_size.rename('Average Basket Size')
print(avg_basket_size.head())

# Box plot: variation in customer basket sizes
plt.figure(figsize=(5,3))
avg_basket_size.plot(kind='box')
plt.ylabel('Average Items per Basket')
plt.title('Basket Size Spread across Customers')
plt.tight_layout()
plt.show()

# Median, min, and max basket size by customer
basket_stats = basket_sizes.groupby('Member_number').agg(['median', 'min', 'max'])
print(basket_stats.head())

# Which customer buys the largest baskets?
largest_basket_customers = avg_basket_size.sort_values(ascending=False).head(3)
print(largest_basket_customers)