Exploratory data analysis

Let's start reading the data. We will be using two files: one CSV with ratings and another GeoJSON file with restaurants and their locations. Let's first read the ratings of the CSV file.

Rating data

This file contains the final rating of restaurants. It has userID and placeID, which we can merge with the GeoJSON datasets of restaurants and rating columns. Let's read the data in pandas and look at the first five rows:

ratings = pd.read_csv('RCdata/rating_final.csv')
ratings.head()

The table looks like this, with a rating of each user for some restaurants:

User ratings

We have 1,161 rating rows and if we look at the first five rows of the rating column, the first three rows...