knn scratch

knn.py

import numpy as np
from collections import Counter

class Knn:
    
    def __init__(self, k=5):
        self.k = k
    
    def fit(self,X,y):
        self.X_train = X
        self.y_train = y
        
    def predict(self, X):
        y_pred = [self.__repredict(x) for x in X]
        return np.array(y_pred)
    
    def __repredict(self,x):
        #distances
        distances = [self.calculate_euclidean_distance(x, x_train) for x_train in self.X_train]
        #sort
        k_idx = np.argsort(distances)[: self.k]
        #extract labels
        labels = [self.y_train[i] for i in k_idx]
        #vote
        common = Counter(labels).most_common(1)
        return common[0][0]
    
    def calculate_euclidean_distance(self,x1,x2):
        return np.sqrt(np.sum(x1-x2)**2)