K-nearest_neighbors.py

import numpy as np

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

    def fit(self, X, y):
        self.X_train = X
        self.y_train = y

    def euclidean_distance(self, x1, x2):
        return np.sqrt(np.sum((x1 - x2) ** 2))

    def predict(self, X):
        y_pred = [self._predict(x) for x in X]
        return np.array(y_pred)

    def _predict(self, x):
        # Compute distances between x and all examples in the training set
        distances = [self.euclidean_distance(x, x_train) for x_train in self.X_train]
        # Sort by distance and return indices of the first k neighbors
        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 = np.argmax(np.bincount(k_nearest_labels))
        return most_common


# Create a simple dataset
X = np.array([[1, 2], [1.5, 1.8], [5, 8], [8, 8], [1, 0.6], [9, 11]])
y = np.array([0, 0, 1, 1, 0, 1])

# Instantiate the KNN classifier
knn = KNN(k=3)

# Train the classifier
knn.fit(X, y)

# Test data
X_test = np.array([[3, 4], [5, 6], [2, 2], [4, 4]])

# Predict the labels for the test data
predictions = knn.predict(X_test)

# Print the predicted labels
print(predictions)