Skip to main content

Aggregation Functions

Absolutely! Here's a beginner-friendly article on 'Aggregation Functions' in pandas.

Pandas is a widely used Python library for data analysis and manipulation. One of the most powerful features of pandas is its ability to perform complex operations on data, including aggregation. In this article, we will explore various aggregation functions in pandas.

Understanding Aggregation​

Aggregation is the process of combining multiple values into a single, more meaningful value. For example, finding the sum, mean, or maximum of a group of values is aggregation. Pandas provide several functions to perform aggregation operations on data.

Built-in Aggregation Functions​

Pandas has several built-in aggregation functions. Some of the most commonly used are:

  • mean(): Returns the mean of the values.
  • sum(): Returns the sum of the values.
  • count(): Returns the count of non-NA cells.
  • median(): Returns the median of the values.
  • max(): Returns the maximum of the values.
  • min(): Returns the minimum of the values.

Let's see how to use these functions in practice. First, we need to import pandas:

import pandas as pd

Suppose we have the following DataFrame:

df = pd.DataFrame({
    'A': [1, 2, 3, 4, 5],
    'B': [10, 20, 30, 40, 50],
    'C': [100, 200, 300, 400, 500]
})

We can apply the aggregation functions like this:

df.mean()

This will return the mean of each column.

Group-Wise Aggregation​

Often, you will want to perform aggregation on groups of data rather than the entire dataset. For this, pandas provides the groupby() function.

Using groupby(), we can split the data into groups based on some criteria, apply a function to each group, and then combine the results. This is often referred to as the "split-apply-combine" pattern.

For example, suppose we have the following DataFrame:

df = pd.DataFrame({
    'Category': ['A', 'A', 'B', 'B', 'C', 'C'],
    'Value': [10, 20, 30, 40, 50, 60]
})

We can group the data by 'Category' and find the sum of 'Value' in each group:

df.groupby('Category').sum()

Custom Aggregation Functions​

In addition to the built-in functions, pandas allows us to define custom aggregation functions. A custom function must take a series of values and return a single value.

For example, we can define a range function that returns the range of values in a group:

def range_func(x):
    return x.max() - x.min()

We can then apply this function to a group:

df.groupby('Category').agg(range_func)

This will return the range of 'Value' in each 'Category'.

In conclusion, pandas provides a robust and flexible set of tools for performing aggregation operations on data. By understanding and utilizing these tools, you can perform complex data analysis tasks with ease. Happy coding!