Aggregation-based features in Data Analysis Python

Introduction

Aggregation-based features help us summarize data by combining many values into one. This makes it easier to find patterns and understand the data.

You want to find the average sales per customer.

You need to count how many times a user visited a website.

You want to find the total amount spent by each customer.

You want to find the maximum temperature recorded each day.

You want to group data by categories and get summary statistics.

Syntax

Data Analysis Python

df.groupby('column_to_group')['column_to_aggregate'].agg('aggregation_function')

groupby splits data into groups based on a column.

agg applies a function like sum, mean, count to each group.

Examples

Sum of sales for each customer.

Data Analysis Python

df.groupby('CustomerID')['Sales'].sum()

Count of visits for each user.

Data Analysis Python

df.groupby('User')['Visits'].count()

Average temperature for each date.

Data Analysis Python

df.groupby('Date')['Temperature'].mean()

Minimum, maximum, and average price for each category.

Data Analysis Python

df.groupby('Category')['Price'].agg(['min', 'max', 'mean'])

Sample Program

This program creates a small sales dataset. Then it groups the data by customer and sums their sales. Finally, it prints the total sales for each customer.

Data Analysis Python

import pandas as pd

data = {
    'CustomerID': [1, 2, 1, 3, 2, 1],
    'Sales': [100, 200, 150, 300, 250, 50]
}
df = pd.DataFrame(data)

# Calculate total sales per customer
sales_per_customer = df.groupby('CustomerID')['Sales'].sum()
print(sales_per_customer)

Important Notes

You can use many aggregation functions like sum, mean, count, min, max.

Aggregation helps reduce data size and find useful summaries.

Make sure to choose the right aggregation for your question.

Summary

Aggregation-based features summarize data by groups.

They help find patterns like totals, averages, or counts.

Use groupby and agg in pandas to create them easily.