Get multiple predictions from a knn model

Question

I want to my code to return multiple(5) predictions from my trained knn model. I've tried using predict_proba() but it just returns the probabilities and not the names Here is my code:

import cv2
import numpy as np
import pickle
import npwriter
m=open('finalmodel.train','rb')
model = pickle.load(m)
cap = cv2.VideoCapture(0)
classifier = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
X_test = []
while True:
        ret, frame = cap.read()
        cv2.imshow('Press c to capture your face', frame)
        if cv2.waitKey(1) & 0xFF == ord('c'):
            cv2.destroyAllWindows()
            cap.release()
            gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
            faces = classifier.detectMultiScale(gray, 1.5, 5)
            for face in faces:
                x, y, w, h = face
                im_face = gray[y:y + h, x:x + w]
                im_face = cv2.resize(im_face, (100, 100))
                X_test.append(im_face.reshape(-1))
            if len(faces) > 0:
                response = model.predict(np.array(X_test))
                print(response)
                break

Answer 1

Instead of using the classifier you might need to use a nearest neighbor instance: https://scikit-learn.org/stable/modules/neighbors.html This will allow you to get indices of nearest neighbors. An alternative might be to look at the argmax of the output to get the "most probable" neighbors.