Assignment 2：Analysis of openrice

Background:
In ASSIGNMENT 2, I picked the new restaurant part of OPENRICE. Because I am a person who likes to try new things, I often go out with my friends on weekends to try new dishes and new scenes. So I am especially interested in new restaurants. You can assess my website here.

Action:
First, I used ParseHub to grab data of 3 pages new restaurants, which includes the name and address of the restaurant as the basic information. The number of reviews and likes are two important dimensions for me to judge the restaurants, so I also grabbed the total number of reviews, positive reviews, negative reviews, and likes. Want to analyze their ratio, such as the percentage of positive reviews, to help me understand more clearly which new restaurants are more well-received and worth trying. Conversely, if it is a restaurant with a high rate of bad reviews, I may not try it even if the total number of reviews is high. In addition, the number of likes is a secondary reference to help me think about whether to try the restaurant from another perspective when the dimensions of the number of reviews are less clear.
In addition, as a student, price is also a data that I pay much attention to. I grabbed the price range in order to have an idea of the approximate spending level of this restaurant. So that I don’t break the bank.

In OpenRefine, I mainly performed a few steps of data cleaning. In addition to removing duplicates and blanks, in the number of reviews section, the site used a “k” for one thousand, which I needed to convert to a number format instead of a string. In the price range data, I split the data into minimum and maximum spend and standardized the format.

Finally, I imported the data into SQLite for SQL query analysis and used Python code in combination with the SQL query to do the analysis.

Main Questions:
1. Which is the most popular restaurant?
I learned the top 10 popular new restaurants by the total number of reviews and positive reviews. And ranked them.

2.Which is the most cost-effective new restaurant?
By using the lowest price and the highest price, I got the most cost-effective restaurants, and the restaurants I am most likely to try.

3. What is the average spending of the new restaurant?
As a non-local, I am a bit curious about the spending level of restaurants in Hong Kong, so I calculated the average spending level among the new restaurants by combining the minimum spending.