simple-kNN

This repository is for Continuous Integration of my simple k-Nearest Neighbors (kNN) algorithm to pypi package.

For notebook version, please visit this repository

k-Nearest Neighbors

k-Nearest Neighbors, kNN for short, is a very simple but powerful technique used for making predictions. The principle behind kNN is to use “most similar historical examples to the new data.”

k-Nearest Neighbors in 4 easy steps

• Choose a value for k
• Find the distance of the new point to each record of training data
• Get the k-Nearest Neighbors
• Making Predictions
  • For a classification problem, the new data point belongs to the class that most of the neighbors belong to.
  • For a regression problem, the prediction can be an average or weighted average of the labels of k-Nearest Neighbors

Finally, we evaluate the model using the k-Fold Cross Validation technique

k-Fold Cross Validation

This technique involves randomly dividing the dataset into k approximately equal-sized groups, or folds. The first fold is kept for testing, and the model is trained on the remaining k-1 folds.

Installation

pip install simple-kNN

Usage

from simple_kNN.distanceMetrics import distanceMetrics
from simple_kNN.kFoldCV import kFoldCV
from simple_kNN.kNNClassifier import kNNClassifier

References

• My medium article on building kNN from scratch
• More info on Cross Validation can be seen here
• kNN
• kFold Cross Validation

Coming soon

• Other variants of the kNN algorithm
• Recommendations using the kNN algorithm