Numpy Median: Handling Missing Values and Outliers


In this article, we will explore how to use NumPy median function to handle missing values and outliers effectively.

When analyzing data, it’s important to deal with missing values and outliers to ensure accurate results. Luckily, there’s a powerful tool called NumPy that can help us with this task.

NumPy is a library for scientific computing in Python. It provides handy functions to work with large arrays and matrices, including a useful function called median.

Numpy Median: Handling Missing Values

Missing values can mess up our data and give us incorrect conclusions. Thankfully, NumPy has some tricks up its sleeve to handle missing values.

Also Read: Mastering Interpolation Techniques with NumPy: Tips and Tricks

Let’s learn how to deal with missing values using NumPy’s median function.

1. Identifying Missing Values

Before we can handle missing values, we need to find them in our data. NumPy makes this easy with the np.isnan() function.

It helps us identify which elements in our array are NaN (Not a Number) or missing values.

2. Removing Rows with Missing Values

One simple way to handle missing values is to remove the entire row where the missing value is found. This approach works well when missing values are sporadic.

Also Read: Numpy hstack: How to Merge Arrays Horizontally with Examples

To remove rows with missing values, we can use the np.isnan() function along with boolean indexing.

3. Replacing Missing Values with Median

Another approach is to replace missing values with a suitable value that represents the dataset accurately. The median is a good choice because it’s not affected by extreme values like the mean.

Also Read: Mastering numpy vstack: A Powerful Tool for Array Manipulation

To replace missing values with the median, we can use the np.median() function. First, we calculate the median of the non-missing values, and then we replace the missing values with this calculated median.

4. Example: Handling Missing Values with NumPy Median

Let’s walk through an example to understand how to handle missing values using NumPy’s median function. Imagine we have a dataset of students’ exam scores, and some scores are missing.

Also Read: NumPy Clip: How to Efficiently Constrain Data Values in Python

We want to replace the missing scores with the median score of the available scores. Here’s how we can do it using NumPy:

import numpy as np

# Assume 'scores' is our array with missing values
missing_values = np.isnan(scores)
median = np.median(scores[~missing_values])
scores[missing_values] = median

By following these steps, we can effectively handle missing values by replacing them with the calculated median.

Numpy Median: Handling Outliers

Outliers are extreme values that don’t fit well with the rest of the data. Dealing with outliers is crucial to avoid skewed results and maintain data integrity.

Also Read: NumPy Pad: Improving Array Dimensions and Boundary Handling

NumPy’s median function can also help us handle outliers effectively. Let’s explore some techniques for handling outliers using NumPy.

1. Identifying Outliers

To handle outliers, we first need to identify them. One common method is using Tukey’s fences, which define outliers as values that are more than 1.5 times the interquartile range (IQR) away from the first and third quartiles.

Also Read: Exploring NumPy Tile: Creating Repeated Patterns in Arrays

NumPy’s np.percentile() function can help us calculate quartiles and the IQR easily.

2. Handling Outliers Using Median

A reliable way to handle outliers is to replace them with the median value. Since the median is not influenced by extreme values, it gives us a better representation of the central tendency of the data.

Also Read: Understanding Numpy Ravel: A Guide to Flattening Arrays

By replacing outliers with the median, we can reduce their impact on our analysis.

3. Example: Handling Outliers with NumPy Median

Let’s consider a scenario where we have a dataset of house prices, and we want to handle outliers using NumPy’s median function.

Here’s a step-by-step example:

import numpy as np

# Assume 'prices' is our array with outliers
q1 = np.percentile(prices, 25)
q3 = np.percentile(prices, 75)
iqr = q3 - q1
fence_low = q1 - 1.5 * iqr
fence_high = q3 + 1.5 * iqr

outliers = (prices < fence_low) | (prices > fence_high)
median = np.median(prices[~outliers])
prices[outliers] = median

By following these steps, we can effectively handle outliers by replacing them with the calculated median.

Also Read: Numpy savetxt: A Comprehensive Guide to Saving Arrays

FAQs (Frequently Asked Questions)

Q: What is NumPy?

NumPy is a Python library used for scientific computing and data manipulation. It provides support for working with large arrays and matrices, along with various mathematical functions.

Q: Why is handling missing values important?

Handling missing values is crucial because they can affect the accuracy and reliability of data analysis results. Ignoring missing values or using incorrect strategies to handle them can lead to biased or incorrect conclusions.

Q: How does NumPy’s median function handle missing values?

NumPy’s median function handles missing values by first identifying them using the np.isnan() function and then replacing them with the calculated median value. This approach allows us to preserve the statistical properties of the dataset while addressing the missing values.

Q: What are outliers?

Outliers are extreme values that deviate significantly from the majority of the data points. They can occur due to measurement errors, data entry mistakes, or genuinely unusual observations.

Q: How can outliers impact data analysis?

Outliers can significantly impact data analysis by skewing statistical measures such as the mean and standard deviation. They can distort the interpretation of results and lead to incorrect conclusions. Handling outliers is essential to ensure the integrity and reliability of data analysis.

Q: Why is the median a good choice for handling outliers?

The median is a good choice for handling outliers because it’s less sensitive to extreme values compared to the mean. By replacing outliers with the median, we can reduce the influence of extreme values on the analysis and obtain more robust results.


Handling missing values and outliers is crucial in data analysis to ensure accurate and reliable results. NumPy’s median function provides powerful capabilities to address these challenges.

By identifying missing values, replacing them with the median, identifying outliers, and replacing them with the median, we can mitigate the impact of missing values and outliers on our analysis.

Understanding and effectively utilizing these techniques empower data analysts to derive valuable insights from their datasets.