{}
# Online Python compiler (interpreter) to run Python online.
# Write Python 3 code in this online editor and run it.
import requests
import re
import statistics
from collections import Counter, defaultdict
from bs4 import BeautifulSoup
# -------------------------
# 1. Romeo and Juliet - Top 10 Frequent Words
# -------------------------
def romeo_and_juliet_top_words():
url = 'http://www.gutenberg.org/files/1112/1112.txt'
text = requests.get(url).text.lower()
words = re.findall(r'\b[a-z]+\b', text)
return Counter(words).most_common(10)
# -------------------------
# 2. Cats API - Weight, Lifespan, Country/Breed Table
# -------------------------
def analyze_cats_api():
url = 'https://api.thecatapi.com/v1/breeds'
cats = requests.get(url).json()
weights, lifespans = [], []
country_breeds = defaultdict(list)
for cat in cats:
# Weight (metric)
try:
w = list(map(float, cat['weight']['metric'].split(' - ')))
weights.append(sum(w) / 2)
except:
continue
# Lifespan (years)
try:
l = list(map(float, cat['life_span'].split(' - ')))
lifespans.append(sum(l) / 2)
except:
continue
# Country and breed
country = cat.get('origin', 'Unknown')
breed = cat.get('name', 'Unknown')
country_breeds[country].append(breed)
# Stats helper
def stats(arr):
return {
'min': min(arr),
'max': max(arr),
'mean': round(statistics.mean(arr), 2),
'median': statistics.median(arr),
'stdev': round(statistics.stdev(arr), 2)
}
return {
'weight_stats': stats(weights),
'lifespan_stats': stats(lifespans),
'country_breeds': {k: len(v) for k, v in country_breeds.items()}
}
# -------------------------
# 3. Countries API - Largest Countries, Spoken Languages
# -------------------------
def analyze_countries_api():
url = 'https://restcountries.com/v3.1/all'
countries = requests.get(url).json()
# Largest countries by area
largest = sorted(countries, key=lambda c: c.get('area', 0), reverse=True)[:10]
largest_countries = [(c['name']['common'], c['area']) for c in largest]
# Language stats
language_count = defaultdict(int)
all_languages = set()
for c in countries:
langs = c.get('languages', {})
for lang in langs.values():
language_count[lang] += 1
all_languages.add(lang)
top_languages = sorted(language_count.items(), key=lambda x: x[1], reverse=True)[:10]
total_languages = len(all_languages)
return {
'largest_countries': largest_countries,
'top_languages': top_languages,
'total_languages': total_languages
}
# -------------------------
# 4. UCI Machine Learning Datasets
# -------------------------
def fetch_uci_datasets():
url = 'https://archive.ics.uci.edu/ml/datasets.php'
soup = BeautifulSoup(requests.get(url).text, 'html.parser')
datasets = [a.text.strip() for a in soup.find_all('a') if a.get('href', '').startswith('datasets/')]
return datasets[:20] # return first 20 for brevity
# -------------------------
# Main Execution
# -------------------------
if __name__ == "__main__":
# 1. Romeo and Juliet
print("\n🔤 Top 10 Frequent Words in Romeo and Juliet:")
for word, count in romeo_and_juliet_top_words():
print(f"{word}: {count}")
# 2. Cats API Analysis
cat_data = analyze_cats_api()
print("\n🐱 Cat Weight Stats (kg):", cat_data['weight_stats'])
print("🐱 Cat Lifespan Stats (years):", cat_data['lifespan_stats'])
print("\n📊 Country vs Number of Cat Breeds:")
for country, count in sorted(cat_data['country_breeds'].items(), key=lambda x: -x[1]):
print(f"{country}: {count}")
# 3. Countries API
country_data = analyze_countries_api()
print("\n🌍 10 Largest Countries by Area:")
for name, area in country_data['largest_countries']:
print(f"{name}: {area} km²")
print("\n🗣️ Top 10 Most Spoken Languages:")
for lang, count in country_data['top_languages']:
print(f"{lang}: {count} countries")
print(f"\n🧮 Total Unique Languages: {country_data['total_languages']}")
# 4. UCI Datasets
print("\n📚 Sample UCI Datasets:")
for name in fetch_uci_datasets():
print("-", name)