AirBnB post: Data exploration

airbnb_post_2.py

def df_stats(df):
    print('Shape: ' , df.shape);
    
    missings = df.isnull().sum() / len(df);
    missing_vals = dict(zip(df.columns[missings > 0], missings[missings > 0]));
    print('# Columns with any missing elements : ' ,   [(w, missing_vals[w]) for w in sorted(missing_vals, key=missing_vals.get, reverse=True)])
    
    print();
    
print('Listings: ');
df_stats(listings);

print('Reviews: ');
df_stats(reviews);

print('Calandar: ');
df_stats(calandar);

#Let's look at a histogram of the different values
sns.set(style='ticks')
sns.pairplot(listings)

#The price attribute looks very skewed, and is important. Let's look at in detail:
fig, ax = plt.subplots();
listings['price'].hist(ax=ax, bins=500);
ax.set_xscale('log')

#Let's look at the correlation between the attributes in Listings
plt.figure(figsize=(14,10))
corrs = listings.corr();
sns.heatmap(corrs);

listings_cats = listings[['neighbourhood_group', 'neighbourhood', 'room_type']];

plt.figure(figsize=(12,4))
plt.subplot(1,2,1);
g = sns.countplot(x='neighbourhood_group', data=listings_cats);
g.set_xticklabels(g.get_xticklabels(), rotation=90);

plt.subplot(1,2,2);
g = sns.countplot(x='room_type', data=listings_cats);
g.set_xticklabels(g.get_xticklabels(), rotation=45);