KNN_5.py

## K Nearest Neighbors 

y_pred_knn = []
## Iterate through each value in test data 
for val in x_test:
    euc_dis = []
    ## Finding eucledian distance for all points in training data 
    for point in x_train:
        euc_dis.append(((val[0]-point[0])**2+(val[1]-point[1])**2)**0.5)
    temp_target = y_train.tolist()
    ## Use bubble sort to sort the euclidean distances 
    for i in range(len(euc_dis)):
        for j in range(0,len(euc_dis)-i-1):
            if(euc_dis[j+1] < euc_dis[j]):
                euc_dis[j], euc_dis[j+1] = euc_dis[j+1], euc_dis[j]
                ## Sort the classes along with the eucledian distances 
                ## to maintain relevancy 
                temp_target[j], temp_target[j+1] = temp_target[j+1], temp_target[j] 
    ## Finding majority among the neighbours 
    vote = [0,0,0]
    ## We are using only the first three entries (K = 3)
    for i in range(3):
        vote[temp_target[i]] += 1
    y_pred_knn.append(vote.index(max(vote)))
## Print the accuracy score     
print('Accuracy:',accuracy_score(y_test,y_pred_knn))