What is K-Nearest Neighbors in C++?

Can you explain what the K-Nearest Neighbors algorithm is?

Sure! K-Nearest Neighbors (KNN) is a simple, supervised machine learning algorithm used for classification and regression.

How does KNN work in practice?

KNN works by finding the 'k' closest data points to a given input and making predictions based on the majority class or average of those neighbors.

What are the advantages of using KNN?

Some advantages include its simplicity, effectiveness for small datasets, and the fact that it requires no training phase.

Can you show me a basic implementation of KNN in C++?

Absolutely! Here's a simple implementation:

#include <iostream>
#include <vector>
#include <algorithm>

// Define a structure for a data point
struct DataPoint {
    std::vector<double> features;
    int label;
};

// Function to calculate Euclidean distance
double euclideanDistance(const DataPoint& a, const DataPoint& b) {
    double sum = 0.0;
    for (size_t i = 0; i < a.features.size(); ++i) {
        sum += (a.features[i] - b.features[i]) * (a.features[i] - b.features[i]);
    }
    return sqrt(sum);
}

// KNN function
int knn(const std::vector<DataPoint>& dataset, const DataPoint& query, int k) {
    std::vector<std::pair<double, int>> distances;
    for (const auto& point : dataset) {
        double distance = euclideanDistance(point, query);
        distances.push_back({distance, point.label});
    }
    std::sort(distances.begin(), distances.end());
    // Count the labels of the k nearest neighbors
    std::map<int, int> labelCount;
    for (int i = 0; i < k; ++i) {
        labelCount[distances[i].second]++;
    }
    // Return the most common label
    return std::max_element(labelCount.begin(), labelCount.end(), 
        [](const auto& a, const auto& b) { return a.second < b.second; })->first;
}