CREDITS: SMART ASSET


Introduction

This project is to demonstrate the understanding of data science process and to apply it real data set.
The data set I chose is provided by AirBNB, the house sharing company for the West Coast City of Seattle.

The data is divided in three files:

* calendar.csv - containing listing prices and data about availability
* listings.csv - the main data file, which contains detailed features about each listing
* reviews.csv - records for listing reviews


I will do some data exploration and visualizations to answer the following questions:
Q1: Are Customers Happy?
Q2: Where listings are concentrated?  
Q3: How much the customer is paying to stay in Seattle with AirBNB?
Q4: What are the average prices for each neighborhood?


Q1: Are Customers Happy?

First, we want to make sure the customer is having good time while staying with AirBNB Host, to answer that question I did some data visualization of customer reviews as shown in this plot:

 As we can see from the graph above most of the reviews are excellent, which means the customers are happy.

Q2: Where listings are concentrated?

Second, we want to know what neighbourhoods are most popular, to answer that question I did some data visualization of listings data as shown in this plot:
The most popular listings neighbourhood is: Capitol Hill.
Then almost equally popular: Ballard, Minor, Belltown, Queen Anne

Here is another plot showing Seattle Map with listing locations:


Q3: How much the customer is paying to stay in Seattle with AirBNB?

Then, we will explore the price distribution for Seattle listing,
to answer that question I did some data visualization of listings data as shown in this plot:

It is clear that the average price is 137, with highest count for 150 range.



Q4: What are the average prices for each neighborhood?


Finally, we will explore the price distribution for each neighborhood.

to answer that question I did some data visualization and manipulation of listings data as shown in this plot:

The most expensive listings neighborhoods are: Portage Bay and Industrial District .
Then almost equally expensive: Alki, Westlake and Central Business District. 

 

Conclusions:

The most expensive listings neighborhoods are not the most popular listings.
Popular listings are more in the mid range prices like the most popular listing
Capitol Hill, which has mean price of 135.