# Always suppress warnings for a cleaner notebook
import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)

# Data setup (Product Price Scraping and Analysis)
import requests
from bs4 import BeautifulSoup
headers = {'User-Agent': 'Mozilla/5.0'}
url = 'https://webscraper.io/test-sites/e-commerce/static/computers/laptops'
html = requests.get(url, headers=headers).text
soup = BeautifulSoup(html, 'html.parser')
items = [(d.select_one('.title').get_text(strip=True), d.select_one('.price').get_text(strip=True)) for d in soup.select('.thumbnail')]
print(items[:5])

# Let us organize those products into a table for analysis
import pandas as pd
df = pd.DataFrame(items, columns=["Product", "Price"])
print(df.shape)
df.head()

# Remove currency symbols from Price column
df['Price'] = df['Price'].str.replace('$', '').astype(float)
df.head()

# Check for missing data (very common in real world scraping)
print(df.isnull().sum())

# Basic descriptive stats on product prices
print('Number of items:', df.shape[0])
print('Min price:', df['Price'].min())
print('Max price:', df['Price'].max())
print('Mean price:', round(df['Price'].mean(), 2))

# Find the name of the cheapest and most expensive products
cheapest = df.loc[df['Price'].idxmin()]
expensive = df.loc[df['Price'].idxmax()]
print('Cheapest:', cheapest['Product'], cheapest['Price'])
print('Most Expensive:', expensive['Product'], expensive['Price'])

# Plot a bar chart of product prices
import matplotlib.pyplot as plt
plt.figure(figsize=(10,5))
plt.bar(df['Product'], df['Price'])
plt.xticks(rotation=45, ha='right', fontsize=8)
plt.ylabel('Price (USD)')
plt.title('Product Price Comparison')
plt.tight_layout()
plt.show()

# Sort products by price from lowest to highest
df_sorted = df.sort_values('Price')
df_sorted.reset_index(drop=True, inplace=True)
df_sorted.head()

# Filtering: Show only products above $1000
expensive_products = df[df['Price'] > 1000]
expensive_products

# Challenge: Find the product closest to the average price
avg_price = df['Price'].mean()
closest = df.iloc[(df['Price'] - avg_price).abs().idxmin()]
print('Product closest to average:', closest['Product'], closest['Price'])

# Optional: Let the user enter a price filter using input()
price_cutoff = float(input("Show products above what price? (Enter a number): "))
filtered = df[df['Price'] > price_cutoff]
print(filtered)