# A Complete Guide to K-Nearest Neighbors (Updated 2023)

## Introduction

In the four years of my data science career, I have built more than 80% of classification models and just 15-20% of regression models. These ratios can be more or less generalized throughout the industry. The reason behind this bias towards classification models is that most analytical problems involve making decisions. In this article, we will talk about one such widely used machine learning **classification technique** called k nearest neighbor (KNN) algorithm. Our focus will primarily be on how the algorithm works on new data and how the input parameter affects the output/prediction.

**Note**: People who prefer to learn through videos can learn the same through our free course – K-Nearest Neighbors (KNN) Algorithm in Python and R. And if you are a complete beginner to Data Science and Machine Learning, check out our Certified BlackBelt program –

**Learning Objectives**

- Understand the working of KNN and how it operates in python and R.
- Get to know how to choose the right value of k for KNN
- Understand the difference between training error rate and validation error rate

## Table of Contents

## When Do We Use the KNN Algorithm?

KNN can be used for both classification and regression predictive problems. However, it is more widely used in classification problems in the industry. To evaluate any technique, we generally look at 3 important aspects:

1. Ease of interpreting output

2. Calculation time

3. Predictive Power

Let us take a few examples to place KNN in the scale :

KNN classifier fairs across all parameters of consideration. It is commonly used for its ease of interpretation and low calculation time.

## How Does the KNN Algorithm Work?

Let’s take a simple case to understand this algorithm. Following is a spread of red circles (RC) and green squares (GS):

You intend to find out the class of the blue star (BS). BS can either be RC or GS and nothing else. The “K” in KNN algorithm is the nearest neighbor we wish to take the vote from. Let’s say K = 3. Hence, we will now make a circle with BS as the center just as big as to enclose only three data points on the plane. Refer to the following diagram for more details:

The three closest points to BS are all RC. Hence, with a good confidence level, we can say that the BS should belong to the class RC. Here, the choice became obvious as all three votes from the closest neighbor went to RC. The choice of the parameter K is very crucial in this algorithm. Next, we will understand the factors to be considered to conclude the best K.

## How Do We Choose the Factor K?

First, let us try to understand exactly the K influence in the algorithm. If we see the last example, given that all the 6 training observation remain constant, with a given K value we can make boundaries of each class. These decision boundaries will segregate RC from GS. In the same way, let’s try to see the effect of value “K” on the class boundaries. The following are the different boundaries separating the two classes with different values of K.

If you watch carefully, you can see that the boundary becomes smoother with increasing value of K. With K increasing to infinity it finally becomes all blue or all red depending on the total majority. The training error rate and the validation error rate are two parameters we need to access different K-value. Following is the curve for the training error rate with a varying value of K :

As you can see, the error rate at K=1 is always zero for the training sample. This is because the closest point to any training data point is itself.Hence the prediction is always accurate with K=1. If validation error curve would have been similar, our choice of K would have been 1. Following is the validation error curve with varying value of K:

This makes the story more clear. At K=1, we were overfitting the boundaries. Hence, error rate initially decreases and reaches a minima. After the minima point, it then increase with increasing K. To get the optimal value of K, you can segregate the training and validation from the initial dataset. Now plot the validation error curve to get the optimal value of K. This value of K should be used for all predictions.

The above content can be understood more intuitively using our free course – K-Nearest Neighbors (KNN) Algorithm in Python and R

## Breaking It Down – Pseudo Code of KNN

We can implement a KNN model by following the below steps:

- Load the data
- Initialise the value of k
- For getting the predicted class, iterate from 1 to total number of training data points
- Calculate the distance between test data and each row of training dataset. Here we will use Euclidean distance as our distance metric since it’s the most popular method. The other distance function or metrics that can be used are manhattan distance, Minkowski distance, Chebyshev, cosine, etc. If there are categorical variables, hamming distance can be used.
- Sort the calculated distances in ascending order based on distance values
- Get top k rows from the sorted array
- Get the most frequent class of these rows
- Return the predicted class

## Implementation in Python From Scratch

We will be using the popular Iris dataset for building our KNN model. You can download it from here.

## Comparing Our Model With Scikit-learn

from sklearn.neighbors import KNeighborsClassifier neigh = KNeighborsClassifier(n_neighbors=3) neigh.fit(data.iloc[:,0:4], data['Name']) # Predicted class print(neigh.predict(test)) -> ['Iris-virginica'] # 3 nearest neighbors print(neigh.kneighbors(test)[1]) -> [[141 139 120]]

We can see that both the models predicted the same class (‘Iris-virginica’) and the same nearest neighbors ( [141 139 120] ). Hence we can conclude that our model runs as expected.

## Implementation of KNN in R

**Step 1: Importing the data**

**Step 2: Checking the data and calculating the data summary**

**Output**

#Top observations present in the data SepalLength SepalWidth PetalLength PetalWidth Name 1 5.1 3.5 1.4 0.2 Iris-setosa 2 4.9 3.0 1.4 0.2 Iris-setosa 3 4.7 3.2 1.3 0.2 Iris-setosa 4 4.6 3.1 1.5 0.2 Iris-setosa 5 5.0 3.6 1.4 0.2 Iris-setosa 6 5.4 3.9 1.7 0.4 Iris-setosa #Check the dimensions of the data [1] 150 5 #Summarise the data SepalLength SepalWidth PetalLength PetalWidth Name Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100 Iris-setosa :50 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300 Iris-versicolor:50 Median :5.800 Median :3.000 Median :4.350 Median :1.300 Iris-virginica :50 Mean :5.843 Mean :3.054 Mean :3.759 Mean :1.199 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800 Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500

**Step 3: Splitting the Data**

**Step 4: Calculating the Euclidean Distance**

**Step 5: Writing the function to predict kNN**

**Step 6: Calculating the label(Name) for K=1**

**Output**

For K=1 [1] "Iris-virginica"

**In the same way, you can compute for other values of K.**

## Comparing Our KNN Predictor Function With “Class” Library

**Output**

For K=1 [1] "Iris-virginica"

We can see that both models predicted the same class (‘Iris-virginica’).

## Conclusion

The KNN algorithm is one of the simplest classification algorithms. Even with such simplicity, it can give highly competitive results. KNN algorithm can also be used for regression problems. The only difference from the discussed methodology will be using averages of nearest neighbors rather than voting from nearest neighbors. KNN can be coded in a single line on R. I am yet to explore how we can use the KNN algorithm on SAS.

**Key Takeaways**

- KNN classifier operates by finding the k nearest neighbors to a given data point, and it takes the majority vote to classify the data point.
- The value of k is crucial, and one needs to choose it wisely to prevent overfitting or underfitting the model.
- One can use cross-validation to select the optimal value of k for the k-NN algorithm, which helps improve its performance and prevent overfitting or underfitting. Cross-validation is also used to identify the outliers before applying the KNN algorithm.
- The above article provides implementations of KNN in Python and R, and it compares the result with scikit-learn and the “Class” library in R.

## Frequently Asked Questions

#### Q1. What is K nearest neighbors algorithm?

A. KNN classifier is a machine learning algorithm used for classification and regression problems. It works by finding the K nearest points in the training dataset and uses their class to predict the class or value of a new data point. It can handle complex data and is also easy to implement, which is why KNN has become a popular tool in the field of artificial intelligence.

#### Q2. What is KNN algorithm used for?

A. KNN algorithm is most commonly used for:

- Disease prediction – predicts the likelihood of a disease based on symptoms and the data available.
- Handwriting recognition – recognizes the handwritten characters.
- Image classification – recognizes images in computer vision.

#### Q3. What is the difference between KNN and Artificial Neural Networks?

A. K-nearest neighbors (KNN) are mainly used for classification and regression problems, while Artificial Neural Networks (ANN) are used for complex function approximation and pattern recognition problems. Moreover, ANN has a higher computational cost than KNN.

## 36 thoughts on "A Complete Guide to K-Nearest Neighbors (Updated 2023)"

## Harshal says: October 10, 2014 at 3:29 am

Useful article. Can you share similar article for randomforest ? What are limitations with data size for accuracy?## Tavish Srivastava says: October 10, 2014 at 4:49 am

Harshal, We have already published many articles on random forest. Here is the link of the article on random forest on similar lines http://www.analyticsvidhya.com/blog/2014/06/introduction-random-forest-simplified/. You can also subscribe to analyticsvidhya to get access to weekly updates on such articles.## saurabh says: October 10, 2014 at 5:00 am

Good one please share the value of Red circle and green square## DEBASHIS ROUT says: October 10, 2014 at 7:02 am

I am currently doing part time MS in BI & Data Mining. I found this article is really helpful to understand in more detail and expecting to utilize in my upcoming project work. I need to know do you have any article on importance of Data quality in BI , Classification & Decision Tree.## Tavish says: October 10, 2014 at 9:48 am

Debashish, We have published many articles on CART models before. Here is a link which will give you a kick start http://www.analyticsvidhya.com/blog/2014/06/comparing-random-forest-simple-cart-model/.## Tavish Srivastava says: October 10, 2014 at 9:51 am

Saurabh, The first graph is for illustrating purposes. You can create a random dataset to check the algorithm.## saraswathi says: October 10, 2014 at 1:44 pm

Hello the article is very clear and precise. I would like some clarification on the single line "To get the optimal value of K, you can segregate the training and validation from the initial dataset.". Do you mean that we segregate those points on the border of the boundaries for validation and keep the remaining for training. This is not very clear to me. Can you please elaborate ? Thanks.## Harvey S says: October 10, 2014 at 1:50 pm

Nice tease: "KNN can be coded in a single line on R. " Can you give an example?## Tavish Srivastava says: October 10, 2014 at 3:38 pm

Saraswathi, Here is what I meant : Take the entire population, and randomly split it into two. Now on the training sample, score each validation observation with different k-values. The error curve will give you the best value of k. Hope it becomes clear now.## Tavish Srivastava says: October 10, 2014 at 3:38 pm

We will cover this piece in our coming articles. Stay tuned.## saraswathi says: October 10, 2014 at 4:41 pm

I want to make sure I understand this correctly. Please confirm or correct. You say, take the entire population and split into two - are these two divisions, one for training and one for validation ? ( I am assuming so). So, now I use different values of K to cluster the training samples. I try to see where the validation samples fall in these clusters. I draw the error curve and choose the K with the smallest error ?## Felix says: October 13, 2014 at 9:02 am

Hi, great post, thanks. I would like to add, that "low calculation time" is not true for the prediction phase with big, high dimensional datasets. But it's still a good choice in many applications.## Tavish says: October 13, 2014 at 11:02 am

Saraswathi, Let me make it even simpler. Say, you have 100 datapoints. Split this population into two samples of 70 and 30 observations. Use these 70 observation to predict for the other 30. Once you have the prediction for a particular value of k, check the misclassification with actual value. Repeat this exercise for different value of k. Hopefully, you will get a curve similar to that shown in the article. Now choose the k for which the misclassification is least. Hope this makes it clear. Tavish## Tavish says: October 13, 2014 at 11:03 am

Felix, You are probably right for cases where the distance between observations comparable in the large dataset. But in general population have natural clusters which makes the calculation faster. Let me know in case you disagree. Tavish## kabir singh says: October 15, 2014 at 8:05 pm

I am trying to figure out churn analysis, any suggestions where I am start looking? BTW following this website for 6-8 months now, you guys are doing an amazing job## Najma Naaz says: June 10, 2015 at 5:08 pm

That was very helpful. Thank you! Can you please share a concise article on neural nets and deep learning as well?## Tiago says: June 21, 2016 at 6:32 pm

Thank you.## Charles says: February 12, 2017 at 6:45 pm

Very useful. it was very explanatory. Thanks for that. Can you please post about adabooster algorithm?## thue xe du lich gia re says: June 26, 2017 at 4:24 pm

Quality articles or reviews is the secret to invite the visitors to visit the website, that's what this web site is providing.## Emanuel Fakhar says: July 23, 2017 at 8:17 pm

The world of DS would be so boring and exaggerated without you guys. Anything I study, I get a better perspective from this site. And you are so generous and grounded compared to idiots here in UK. God bless.## Stonehead Park says: September 24, 2017 at 10:45 am

Excellent post, I appreciate your effort. :)## Just81100 says: September 28, 2017 at 12:23 am

KNN is fast to train but the prediction speed grows exponentially with the data set size and his complexity rather than Random forest...## Soumya Shreya says: March 27, 2018 at 7:00 pm

It is a really nice and well explained article, I am a beginner in the field of data science and machine learning and I find these articles really helpful to learn and understand the algorithms. Thanks for publishing them. Can you suggest me some datasets where I can experiment and apply KNN.## Krishna says: March 27, 2018 at 7:04 pm

How do we handle categorical features with kNN? Do we need to create dummies for them? Do you suggest any other distance method other than euclidean distance if we have more number of features? I feel we have to treat outliers as they may have impact on the distances, similarly missing values.. Please share your opinion.## Aishwarya Singh says: March 28, 2018 at 3:21 pm

Hi, Yes you can create dummies for categorical variables in kNN. Apart from Euclidean distance, there are other methods that can be used to find the distance such as Manhattan or Minkowski. For outliers adn missing value treatment, you can refer this article .## Aanish Singla says: March 28, 2018 at 8:01 pm

IMO limitation of KNN comes into play when dimensions increase because in higher dimensions, finding neighbors which are quite close to each other in all dimensions might be tough, hence so called neighbors might be really far apart from each other which defeats the purpose of the algorithm. Kindly share your thoughts/experiences.## Aishwarya Singh says: March 29, 2018 at 1:32 pm

Hi Soumya, You can use the Cancer dataset to practice kNN. Refer this link for the same.## Aishwarya Singh says: March 29, 2018 at 3:07 pm

Hi Aanish, Thank you for sharing your thoughts.## Amlesh Kanekar says: April 25, 2018 at 9:21 am

I found it "inspiring". Have spent last 4 months learning linear algebra, statistics, python. This learning list was culled from analyticsvidhya.com. Now just glimpsing through your article gives me the confidence to code knn from scratch. Thank you!## Aishwarya Singh says: April 25, 2018 at 4:16 pm

Hi Amlesh, Glad you found this useful!## Amlesh Kanekar says: May 02, 2018 at 6:46 pm

I created my own dataset to experiment with KNN. When I plotted my data, the three targets/labels I have are extremely randomly distributed across the 2D plane ... no clustering of the three colours is evident. The Iris dataset shows a fairly high degree of clustering. Should I continue with my dataset or there is the concept of "so-and-so distribution does not qualify for KNN"? I can email a picture of my data plot if needed.## Amlesh Kanekar says: May 08, 2018 at 12:53 pm

I figured this out. So it is fine if you do not respond.## Max says: October 06, 2018 at 12:21 pm

That was very helpful. Thank you! How to make the same visualization as in the pictures in section "How do we choose the factor K" ?## Aishwarya Singh says: October 08, 2018 at 7:40 pm

You'll find it here : https://www.analyticsvidhya.com/blog/2015/11/quick-introduction-boosting-algorithms-machine-learning/## Aishwarya Singh says: October 08, 2018 at 7:46 pm

Hi Max, For this, you will have to use a for loop. For each value of k, calculate the validation error and store in a separate list. Then plot these validation error values against k values.## What is a KNN (K-Nearest Neighbors)? | Unite.AI says: August 24, 2020 at 3:09 am

[…] learning technique and algorithm that can be used for both regression and classification tasks. K-Nearest Neighbors examines the labels of a chosen number of data points surrounding a target data point, in order to […]