PANDAS TUTORIALS

Answer Key

1. unclean_listings = pd.read_pickle('unclean_listings.pkl')
2. unclean_listings = unclean_listings[['header', 'price', 'mileage']]
3. unclean_listings['header'] = unclean_listings['header'].str.upper()
4. unclean_listings = unclean_listings[(unclean_listings['header'].str.startswith('201')) | (unclean_listings['header'].str.endswith('e'))]
unclean_listings.reset_index(drop=True, inplace=True)
5. unclean_listings = unclean_listings[unclean_listings['price'].str.contains('25')]
unclean_listings.reset_index(drop=True, inplace=True)
6. unclean_listings = unclean_listings[unclean_listings['header'].str.len() <= 20]
unclean_listings.reset_index(drop=True, inplace=True)
7. unclean_listings.columns = unclean_listings.columns.str.strip()
8. unclean_listings['header'] = unclean_listings['header'].str.strip()
unclean_listings['price'] = unclean_listings['price'].str.strip()
9. unclean_listings['mileage'] = unclean_listings['mileage'].str.replace(' miles', '')
unclean_listings['mileage'] = unclean_listings['mileage'].str.replace(',', '')
10. unclean_listings[['first_split', 'price']] = unclean_listings['price'].str.split('$', n=1, expand=True)
11. unclean_listings = unclean_listings[~unclean_listings['price'].str.contains('$')]
unclean_listings.drop(['first_split'], axis=1, inplace=True)
12. unclean_listings['price'] = unclean_listings['price'].str.replace(',', '')
13. unclean_listings[['model_year', 'make', 'model']] = unclean_listings['header'].str.split(' ', n=2, expand=True)
unclean_listings.drop(['header'], axis=1, inplace=True)
14. unclean_listings = unclean_listings[['price', 'model_year', 'make', 'model', 'mileage']]