DEV Community

Bala Madhusoodhanan
Bala Madhusoodhanan

Posted on

LUX: Toolkit for Smart Data Exploration

Introduction:
Exploratory data analysis (EDA) often is the art of identifying industry relevant trends on the data you are exploring. This tasks requires creating data visualizations that help us understand the characteristics of the data. Introducing LUX to automate the visualization process

Setup:

!pip install lux
Enter fullscreen mode Exit fullscreen mode

As in the series I would leverage a dummy generated data set to see what LUX would help me to automate.

np.random.seed(10)
num_rows = 10000
num_columns = 5
data = {
    'Cust_ID': np.arange(1, num_rows + 1),  # Unique identifier for each customer
    'Age': np.random.randint(18, 60, num_rows),  # Customer Age
    'Gender': np.random.choice(['Male', 'Female'], num_rows),  # Gender 
    'Affluency': np.random.choice(['Cluster A', 'Cluster B', 'Cluster C'], num_rows),  # Cluster group
    'Avg Basket Value':np.random.randint(25, 60, num_rows),# Avg sale bucket
    'Market_Follow_status': np.random.choice(['Ongoing', 'Completed'], num_rows)  # Follow-up status
}
df = pd.DataFrame(data)

Enter fullscreen mode Exit fullscreen mode

Now once you the magic of LUX package all you need to do is type df and hit enter.. an interesting button appears to show (see below).

Image description

Go ahead and give it a click, you should see the start of some stunning visualizations that you can scroll through.

Demo:
demo

A lovely package in quickly perform EDA on the data.

PS - You can leverage the package in any work as long as you include the required notices. This permissive license contains a patent license from the contributors of the code.

Further Read:
LUX User-Guide

LUX Git

Top comments (0)