knn.py

import numpy as np
from collections import Counter

# Function to calculate the Euclidean distance between two points
def euclidean_distance(x1, x2):
    return np.sqrt(np.sum((x1 - x2) ** 2))

class KNN:
    def __init__(self, k=3):
        self.k = k

    # Fit the model with the training data
    def fit(self, X, y):
        self.X_train = X
        self.y_train = y

    # Predict the class labels for the provided data
    def predict(self, X):
        predicted_labels = [self._predict(x) for x in X]
        return np.array(predicted_labels)

    # Helper function to predict the class label for a single data point
    def _predict(self, x):
        # Compute distances between x and all examples in the training set
        distances = [euclidean_distance(x, x_train) for x_train in self.X_train]
        # Sort by distance and return indices of the first k neighbors
        #find the indices of the smallest values in an array of distances.
        k_indices = np.argsort(distances)[:self.k]
        # Extract the labels of the k nearest neighbor training samples
        k_nearest_labels = [self.y_train[i] for i in k_indices]
        # Return the most common class label
        most_common = Counter(k_nearest_labels).most_common(1)
        return most_common[0][0]

# Example usage
if __name__ == "__main__":
    # Sample data
    X_train = np.array([[1, 2], [2, 3], [3, 4], [6, 7], [7, 8], [8, 9]])
    y_train = np.array([0, 0, 0, 1, 1, 1])
    X_test = np.array([[2, 3], [6, 6]])

    # Create KNN classifier
    knn = KNN(k=3)
    knn.fit(X_train, y_train)
    predictions = knn.predict(X_test)

    print("Predictions:", predictions)