robbertvdg

%%timeit
prices = listings['price'].values
nr_reviews = listings['number_of_reviews'].values
availability = listings['availability_365'].values
room_types = listings['room_type'].values
scores = np.zeros(len(listings))
for i in range(len(listings)):
    if availability[i] == 0:
        scores[i] = 0
    elif prices[i] > 100:

robbertvdg

room_type_scores = {'Entire home/apt': 1,
                   'Private room': 0.7,
                   'Shared room': 0.2}

%%timeit
scores = np.zeros(len(listings))
for i in range(len(listings)):
    row = listings.loc[i]
    if row['availability_365'] == 0:
        scores[i] = 0

robbertvdg

# .iloc[]
%%timeit
norm_prices = np.zeros(len(listings,))
for i in range(len(listings)):
    norm_prices[i] = (listings.iloc[i]['price'] - min_price) / (max_price - min_price)
listings['norm_price'] = norm_prices
# 8.91 s ± 479 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

# Iterrows()
%%timeit

robbertvdg

%%timeit
listings['norm_price'] = (listings['price'] - min_price) / (max_price - min_price)

# 1.76 ms ± 107 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

robbertvdg

%%timeit 
listings['norm_price'] = listings['price'].map(lambda x: (x - min_price) / (max_price - min_price))

# 39.8 ms ± 2.33 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)

robbertvdg

%%timeit
norm_prices = np.zeros(len(listings,))
for i in range(len(norm_prices)):
    norm_prices[i] = (listings.loc[i, 'price'] - min_price) / (max_price - min_price)
listings['norm_price'] = norm_prices

# 408 ms ± 61.2 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

robbertvdg

%%timeit
norm_prices = np.zeros(len(listings,))
for i, row in listings.iterrows():
    norm_prices[i] = (row['price'] - min_price) / (max_price - min_price)
listings['norm_price'] = norm_prices

# 3.99 s ± 346 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

robbertvdg

%%timeit
norm_prices = np.zeros(len(listings,))
for i in range(len(listings)):
    norm_prices[i] = (listings.iloc[i]['price'] - min_price) / (max_price - min_price)
listings['norm_price'] = norm_prices

# 8.91 s ± 479 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

robbertvdg

%%timeit
reviews_subset = reviews_summary[reviews_summary['listing_id'].isin(listings['listing_id'])]
listings.merge(reviews_subset, on='listing_id')

# 48.7 ms ± 618 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)