Mathew K AnalyticsLesson 10 · Data Science Projects
Comprehensive Airbnb Data Analysis Using Python for Biblical Stewardship Insights
Welcome to this beginner friendly lesson on analyzing Airbnb data. We will use a real life dataset of New York City Airbnb listings. You will learn…
- CourseData Science Projects
- Lesson10 of 33
- Video21 min
- FormatJupyter notebook · 17 code cells
What you'll learn
Data
No separate download needed — the notebook creates or downloads everything it uses.
📓 Full notebook
Download .ipynbAirbnb Data Analysis: Exploring NYC Listings#
- Welcome to this beginner friendly lesson on analyzing Airbnb data.
- We will use a real life dataset of New York City Airbnb listings.
- You will learn important steps for loading, cleaning, analyzing, and visualizing data.
- By the end, you will know how to get insights from a real world dataset.
- Let us dive in!
# Always suppress warnings at the start for a cleaner experience
import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)
# This makes sure you only see output you want while learning
What is Airbnb Data and Why Analyze It?#
- Airbnb is an online marketplace for short term rentals and stays.
- The public dataset contains listings, prices, neighbourhoods, reviews, and more for New York City.
- Learning to analyze such data is a valuable job skill for both students and professionals.
- Data analysis helps answer real questions, like:
- What is the most expensive area?
- How are prices distributed?
- Which neighborhoods are most popular?
- You will learn to answer these using Python!
# Data setup: Load the Airbnb NYC Listings dataset using pandas
import kagglehub, os, pandas as pd
path = kagglehub.dataset_download('dgomonov/new-york-city-airbnb-open-data')
files = os.listdir(path)
df = pd.read_csv(os.path.join(path, 'AB_NYC_2019.csv'))
print(df.shape)
print(df.head(3))
# Take a closer look at column names and basic info
print(df.columns)
print(df.info())
Understanding the Data Columns#
- Here is what some important columns represent:
- id: listing unique identifier
- name: title of the listing
- host_name: name of the seller
- neighbourhood_group: major NYC area like Manhattan or Brooklyn
- neighbourhood: more detailed local name
- latitude and longitude: location coordinates
- room_type: type such as entire home/apartment or private room
- price: price per night in dollars
- minimum_nights: minimum nights required to book
- number_of_reviews: how many times reviewed
- availability_365: how many days per year available
- Knowing what each column represents helps make analysis more meaningful!
# Check if there are missing values in any column
print(df.isnull().sum())
# Basic data cleaning: fill missing host_name with 'Unknown', drop rows missing price
df['host_name'].fillna('Unknown', inplace=True)
df.dropna(subset=['price'], inplace=True)
# Now let us check again for missing values
print(df.isnull().sum())
Your First Insights: Listings Count#
- Let us answer some simple questions:
- How many listings are there in total?
- How many hosts are offering places?
- How many unique neighborhoods are listed?
# Count number of listings, unique hosts, and neighborhoods
print("Total listings:", len(df))
print("Unique hosts:", df['host_name'].nunique())
print("Neighborhoods:", df['neighbourhood'].nunique())
# Explore price statistics: average, min, max, median
print("Average price:", df['price'].mean())
print("Minimum price:", df['price'].min())
print("Maximum price:", df['price'].max())
print("Median price:", df['price'].median())
Visualizing Data: Price Distribution#
- A visualization can quickly show how prices are distributed.
- You will draw a histogram, which is a bar chart showing how many listings fall into each price range.
- This helps you see if most prices are low, high, or somewhere in the middle.
# Draw a histogram of price: focus on listings under $500 for visibility
import matplotlib.pyplot as plt
plt.figure(figsize=(8,4))
df[df['price'] < 500]['price'].hist(bins=50, color='skyblue')
plt.title('NYC Airbnb Price Distribution (Below $500)')
plt.xlabel('Price ($ per night)')
plt.ylabel('Number of Listings')
plt.show()
# Let us see which neighbourhood group has the most listings
counts = df['neighbourhood_group'].value_counts()
print(counts)
Plotting Listings by Area#
- It is much easier to compare popularity visually.
- Let us make a bar chart showing the count per neighbourhood group.
# Horizontal bar chart for listings count per neighbourhood group
import seaborn as sns
plt.figure(figsize=(7,4))
sns.barplot(x=counts.values, y=counts.index, palette='pastel')
plt.title('Listings by Neighbourhood Group')
plt.xlabel('Number of Listings')
plt.ylabel('Neighbourhood Group')
plt.show()
# Find the average price for each neighbourhood group
group_avg = df.groupby('neighbourhood_group')['price'].mean().sort_values(ascending=False)
print(group_avg)
# Bar chart: average price per neighbourhood group
plt.figure(figsize=(7,4))
sns.barplot(x=group_avg.values, y=group_avg.index, palette='summer')
plt.title('Average Airbnb Price by Neighbourhood Group')
plt.xlabel('Average Price')
plt.ylabel('Neighbourhood Group')
plt.show()
Mapping Listings: Price and Location#
- Visualizing listings on a map can be powerful.
- We can use latitude and longitude to see where expensive and cheap listings are.
- Scatter plots can reveal clusters and price hot spots.
# Scatter plot: listings by location, colored by price (under $500 for clarity)
plt.figure(figsize=(8,6))
sample = df[df['price'] < 500].sample(2000, random_state=42)
plt.scatter(sample['longitude'], sample['latitude'], c=sample['price'], cmap='cool', alpha=0.7)
plt.colorbar(label='Price ($)')
plt.xlabel('Longitude')
plt.ylabel('Latitude')
plt.title('NYC Airbnb Listings: Location and Price (Sample under $500)')
plt.show()
# What are the most common room types?
print(df['room_type'].value_counts())
# Bar plot: room type counts
plt.figure(figsize=(6,3))
sns.countplot(y='room_type', data=df, palette='Set2', order=df['room_type'].value_counts().index)
plt.title('Airbnb Room Types in NYC')
plt.xlabel('Number of Listings')
plt.ylabel('Room Type')
plt.show()
Time for a Mini Project!#
- Try these questions on your own code:
- Who are the top 5 hosts by number of listings?
- What is the median price for each room type?
- How does minimum night requirement differ across neighbourhoods?
- Pause the video and give these a try.
- When you are ready, continue for more visual fun and insights.
# Correlation: Which features go together?
corr = df[['price', 'minimum_nights', 'number_of_reviews', 'availability_365']].corr()
print(corr)
# Visual heatmap of correlations
plt.figure(figsize=(5,4))
sns.heatmap(corr, annot=True, cmap='YlGnBu')
plt.title('Feature Correlations')
plt.show()
Share Your Results and Keep Exploring!#
- You just analyzed real world data, made visualizations, and discovered trends.
- Try changing filters or columns to answer your own questions.
- If you enjoyed this lesson, subscribe to the channel and leave a comment with your favorite insight.
- There is much more to learn in data science. Imagine what you will create next!
Found this useful?
All lessons, notebooks and datasets here are free. If they helped you, a coffee keeps new lessons coming.
Related lessons
36 minLesson 69
Comprehensive Pandas Tutorial in Python: Data Analysis from Beginner to Advanced
13 minLesson 5
Fundamentals of Exploratory Data Analysis and Visualization for Biblical Data Insights
24 minLesson 5
Comprehensive Guide to Pandas Series and DataFrames for Data Analysis in Python
27 minLesson 51