Sign inGet started
← Back to all guides

Introduction to Python for real estate investment analysis in Deepnote

By Filip Žitný

Updated on March 6, 2024

Importing necessary libraries install and import libraries

First, you need to install and import the libraries

!pip install pandas numpy matplotlib seaborn

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

Loading your real estate data

Upload Your Data

Drag and drop your real estate data CSV file into the file explorer on the left side of the Deepnote interface.

Load data into the data frame

Load the data by adding the following code

# Load the dataset
df = pd.read_csv('your_real_estate_data.csv')
df

Data cleaning and preparation

Check for missing values

Run the following to see if there are any missing values in your data

df.isnull().sum()

Handle missing values

Fill or drop missing values based on your needs:

df = df.fillna(method='ffill')

Convert data types

Ensure that your data types are correct, especially for dates:

df['date'] = pd.to_datetime(df['date'])
df.dtypes

Exploratory data analysis (EDA)

Summary statistics:

Generate summary statistics to understand your data:

df.describe()

Visualize data distributions:

Create a histogram of property prices:

plt.figure(figsize=(10, 6))
sns.histplot(df['price'], kde=True)
plt.title('Distribution of property prices')
plt.show()

Compare prices by location

Use a boxplot to visualize property prices by location

plt.figure(figsize=(14, 8))
sns.boxplot(x='location', y='price', data=df)
plt.title('Property prices by location')
plt.xticks(rotation=45)
plt.show()

Calculating key metrics

Gross rental yield

Calculate the gross rental yield for each property

df['gross_rental_yield'] = (df['annual_rent'] / df['price']) * 100
df[['price', 'annual_rent', 'gross_rental_yield']].head()

Cap rate

Calculate the cap rate for each property

df['cap_rate'] = (df['net_operating_income'] / df['price']) * 100
df[['price', 'net_operating_income', 'cap_rate']].head()

Visualizing investment opportunities

Scatter plot of price vs gross rental yield

Create a scatter plot to visualize the relationship between property price and gross rental yield

plt.figure(figsize=(10, 6))
sns.scatterplot(x='price', y='gross_rental_yield', data=df)
plt.title('Price vs gross rental yield')
plt.show()

Boxplot of cap rate by location

Visualize cap rate distributions by location

plt.figure(figsize=(14, 8))
sns.boxplot(x='location', y='cap_rate', data=df)
plt.title('Cap rate by location')
plt.xticks(rotation=45)
plt.show()

Making data-driven decisions

Identify the best Investment opportunities

Sort properties by gross rental yield to find the best opportunities:

best_yield_properties = df.sort_values(by='gross_rental_yield', ascending=False).head(10)
best_yield_properties

Filter properties based on criteria

Filter properties with a cap rate greater than a specified threshold

cap_rate_threshold = 5.0
good_investments = df[df['cap_rate'] > cap_rate_threshold]
good_investments

Saving and sharing your work

Export your results

Save your results to a new CSV file

df.to_csv('real_estate_analysis_results.csv', index=False)

Share your notebook or create a Deepnote app

  • Click the “Share” button in Deepnote to share your notebook with others. You can provide view or edit access to your collaborators.
  • Click on a create app on the right side of the notebook configure it and share it

Conclusion and next steps

Review findings

Summarize your key findings and insights from the analysis. Highlight the best investment opportunities and any significant patterns observed.

Further Analysis

Consider exploring more advanced analyses such as predictive modeling for property prices. Consider incorporating external factors like market trends or economic indicators to enhance your analysis. This walkthrough provides a solid foundation for analyzing real estate data and making informed investment decisions.

Filip Žitný

Data Scientist

Follow Filip on Twitter, LinkedIn and GitHub

That’s it, time to try Deepnote

Get started – it’s free
Book a demo

Footer

Solutions

  • Notebook
  • Data apps
  • Machine learning
  • Data teams

Product

Company

Comparisons

Resources

  • Privacy
  • Terms

© Deepnote