Visualizing Airbnb Listings

With so much Airbnb data available, it can be hard to get a grasp on the trends and demands in your area. Here, we'll explore ways to visualize Airbnb listings using Python and popular visualization libraries.

To start, you'll want to create worker for Airbnb listings. Run the worker a few times and you'll get results looking like this:

Next, export your results in CSV format and save them to a convenient location on your computer, like your desktop. In this example, we'll save our results to ~/Desktop/airbnb_global.csv.

Now, we'll write a little Python code to begin our visualizations.

Loading into Pandas

Let's first load our CSV into a Pandas dataframe:

import os
import pandas as pd

df = pd.read_csv(os.path.expanduser('~/Desktop/airbnb_global.csv'))

Pandas will automatically infer the column types for you. You can check out the column names with:

df.columns.values

Mapping with Cartopy

We'll use Cartopy to visualize our listings on a map. Let's start by importing the core modules we'll need

import cartopy.crs as ccrs
import cartopy.feature as cfeature
import matplotlib.pyplot as plt

ax = plt.axes([0, 0, 1, 1], projection=ccrs.PlateCarree())
ax.add_feature(cfeature.OCEAN, zorder=0)
ax.coastlines()

This will generate a blank world map as follows:

This is cool, but where's our Airbnb data? Let's now reference back to our Pandas dataframe and begin plotting our points.

Let's first get the latitude and longitutes for our Airbnb listings:

longitudes = list(df['listing.lng'])
latitudes = list(df['listing.lat'])

Next, let's make each point on the map proportional in size to the number of reviews about the listing, e.g.:

radiuses = (df['listing.reviews_count'] / 50.0) ** 2

Lastly, let's color each datapoint by price - higher priced listings will be more red and lower priced will be less intense.

import matplotlib.cm as cm
colors = [cm.hot(x) for x in list(df['pricing_quote.rate.amount'])]

We can now combine it all together and generate a world map of our Airbnbs:

ax.scatter(
    longitudes,
    latitudes,
    c=colors,
    s=radiuses,
    zorder=2,
    alpha=0.5)

Now we'll get a nice map of Airbnb listings like this: